JP6967462B2 - Information processing equipment, information processing methods, and information processing programs - Google Patents

Description

The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Conventionally, techniques for recommending various information to users and the like have been provided. For example, there is provided a technique for identifying a user similar to a user and outputting information on an item that the similar user has referred to in the past as information on an item recommended to the user.

Japanese Unexamined Patent Publication No. 2017-73114

Masajiro Iwasaki "Neighborhood Search by Approximate k Nearest Neighborhood Graph Using Tree Structure Index", IPSJ Journal, 2011/2, Vol. 52, No. 2. pp.817-828.

However, with the above-mentioned prior art, it may be difficult to recommend an appropriate product. For example, simply recommending information that a similar user has referred to in the past may not be appropriate information for the user, and it may be difficult to recommend an appropriate product.

The present application has been made in view of the above, and an object of the present application is to provide an information processing apparatus, an information processing method, and an information processing program that recommend appropriate products.

The information processing apparatus according to the present application acquires graph information in which a plurality of nodes corresponding to each of a plurality of products are linked according to the similarity of the plurality of products and order information requesting the purchase of one product. Of the acquisition unit and the plurality of nodes of the graph information acquired by the acquisition unit, the graph information is started from a starting node that is a starting point for searching the graph information determined based on a predetermined criterion. By searching for, an extraction unit that extracts a similar product that is a product similar to the one product among the plurality of products, and recommended information based on the similar product extracted by the extraction unit are obtained. It is characterized by being provided with a transmitter for transmitting to a requester requesting the purchase of the product.

According to one aspect of the embodiment, there is an effect that an appropriate product can be recommended.

FIG. 1 is a diagram showing an example of information processing according to an embodiment. FIG. 2 is a diagram showing a configuration example of an information processing system according to an embodiment. FIG. 3 is a diagram showing a configuration example of the information processing apparatus according to the embodiment. FIG. 4 is a diagram showing an example of a product information storage unit according to an embodiment. FIG. 5 is a diagram showing an example of an index information storage unit according to an embodiment. FIG. 6 is a diagram showing an example of a graph information storage unit according to an embodiment. FIG. 7 is a diagram showing an example of a model information storage unit according to an embodiment. FIG. 8 is a diagram showing an example of an inventory information storage unit according to an embodiment. FIG. 9 is a diagram showing an example of a user information storage unit according to an embodiment. FIG. 10 is a flowchart showing an example of information processing according to the embodiment. FIG. 11 is a flowchart showing an example of the generation process according to the embodiment. FIG. 12 is a diagram showing an example of extraction of a feature amount according to an embodiment. FIG. 13 is a flowchart showing an example of a search process using graph information. FIG. 14 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device.

Hereinafter, the information processing apparatus, the information processing method, and the embodiment for implementing the information processing program (hereinafter referred to as “the embodiment”) according to the present application will be described in detail with reference to the drawings. Note that this embodiment does not limit the information processing apparatus, information processing method, and information processing program according to the present application. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate explanations are omitted.

(Embodiment)
[1. Information processing]
An example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of information processing according to an embodiment. FIG. 1 shows a case where the information processing apparatus 100 acquires order information of a product from a refrigerator which is an IoT (Internet of Things) device 10. Further, in FIG. 1, when the information processing apparatus 100 searches for graph data (graph information) in which the product is graph-structured, the ordered product is out of stock, and the product is similar to the ordered product (hereinafter referred to as the product). , Also referred to as "similar products"). In FIG. 1, the information processing apparatus 100 uses graph information in which products are graph-structured using vector data (also referred to as “vector information” or simply “vector”) corresponding to each product. The information used by the information processing apparatus 100 is not limited to a vector, and may be any form of information as long as it can express the similarity of each product. For example, the information processing apparatus 100 may use graph information in which a product is graph-structured using predetermined data or values corresponding to each product. For example, the information processing apparatus 100 may use graph information in which a product is graph-structured using a predetermined numerical value (for example, a binary value or a hexadecimal value) generated from each product. Further, in the example of FIG. 1, the case where the ordered product is a product not included in the graph information is shown as an example, but any product such as a product included in the graph information may be used. That is, the target product (object) may be any product (information) as long as the similarity of each product can be expressed. Instead of the vector, the data may be in any form as long as the distance (similarity) between the data is defined.

[1-1. About graph information]
Further, as shown in the graph information GR11 in FIG. 1, the information processing apparatus 100 performs information processing on graph data in which each vector (node) is connected by a directed edge. The information processing apparatus 100 may generate the graph information as shown in the graph information GR 11 in FIG. 1, and the information processing apparatus 100 provides the graph information as shown in the graph information GR 11 in FIG. It may be acquired from another external device such as the providing device 50 (see FIG. 2).

Further, the directed edge here means an edge in which data can be traced in only one direction. In the following, the source traced by the edge, that is, the node that is the start point is referred to as the reference source, and the destination that is traced by the edge, that is, the node that is the end point is referred to as the reference destination. For example, the directed edge connected from the predetermined node "A" to the predetermined node "B" indicates that the reference source is the node "A" and the reference destination is the node "B". The edge connecting the nodes is not limited to the directed edge, and may be various edges. For example, the edge connecting the nodes may be an edge having no direction to connect the nodes. For example, the edge connecting the nodes may be an edge that can be referred to each other. For example, the edges connecting the nodes may all be bidirectional edges.

For example, the edge with the node "A" as the reference source is called the output edge of the node "A". Further, for example, such an edge with the node "B" as a reference destination is referred to as an input edge of the node "B". That is, the output edge and the input edge referred to here are differences in which node of the two nodes to which the directed edge is connected is regarded as the center, and the one directed edge is one directed edge. Becomes the output edge and the input edge. That is, the output edge and the input edge are relative concepts, and when one directed edge is regarded as the center of the reference node, the output edge is regarded as the center of the reference node. In some cases it becomes the input edge. In the present embodiment, since the edge is a directed edge such as an output edge or an input edge, the directed edge may be simply referred to as an "edge" in the following.

For example, the information processing apparatus 100 processes a node corresponding to a product of several million to several hundred million units, but only a part thereof is shown in the drawing. In the example of FIG. 1, in order to simplify the explanation, eight nodes are illustrated to explain the outline of the process. For example, as shown in the graph information GR11 in FIG. 1, the information processing apparatus 100 acquires graph information including a plurality of nodes (vectors) as shown in the nodes N1, N2, N3, and the like. Further, in the example of FIG. 1, each node in the graph information GR 11 is connected with edges (output edges) from the one having a short distance to the node to a predetermined number of nodes. For example, the predetermined number may be various values such as 2, 5, 10, and 100 depending on the purpose, use, and the like. For example, when the predetermined number is 2, the output edge is connected from the node N1 to the node having the closest distance from the node N1 and the two nodes having the second closest distance. The distance as an index indicating the degree of similarity may be any distance as long as it can be applied as a distance between vectors (N-dimensional vectors), for example, Euclidean distance, Mahalanobis distance, cosine distance, and the like. Various distances may be used.

Further, when described as "node N * (* is an arbitrary numerical value)" in this way, it means that the node is a node identified by the node ID "N *". For example, when described as "node N1", the node is a node identified by the node ID "N1".

Further, in the graph information GR11 in FIG. 1, the node N10 is connected to the edge E7, which is a directed edge toward the node N7. That is, the node N10 is connected to the node N7 by the edge E7. When "edge E * (* is an arbitrary numerical value)" is described in this way, it means that the edge is an edge identified by the edge ID "E *". For example, when described as "edge E11", the edge is an edge identified by the edge ID "E11". For example, the edge E7 connected with the node N10 as the reference source and the node N7 as the reference destination makes it possible to trace from the node N10 to the node N7. In this case, the edge E7, which is a directed edge, becomes an output edge when identified with the node N10 as the center, and becomes an input edge when identified with the node N7 as the center. Also, the bidirectional arrows in the graph information GR11 of FIG. 1 indicate that the directed edges from both nodes to the other node are connected. For example, a bidirectional arrow between node N2 and node N451 in the graph information GR11 connects two edges, a directed edge from node N2 to node N451 and a directed edge from node N451 to node N2. Indicates that it will be done.

Further, the graph information GR11 in FIG. 1 may be an Euclidean space. Further, the graph information GR 11 shown in FIG. 1 is a conceptual diagram for explaining the distance between each vector, and the graph information GR 11 is a multidimensional space. For example, the graph information GR11 shown in FIG. 1 is shown in a two-dimensional manner for being shown on a plane, but is assumed to be a multidimensional space such as 100 dimensions or 1000 dimensions.

Here, the distance between the vector data indicates the similarity of the products, and the closer the distance is, the more similar the products are. In the present embodiment, the distance of each node in the graph information GR11 is defined as the degree of similarity between the corresponding objects. For example, it is assumed that the similarity of the target (commodity) corresponding to each node is mapped as the distance between the nodes in the graph information GR11. For example, it is assumed that the similarity between the concepts corresponding to each node is mapped to the distance between each node. Here, in the example shown in FIG. 1, the similarity between the objects having a short distance between the nodes in the graph information GR11 is high, and the similarity between the objects having a long distance between the nodes in the graph information GR11 is low. For example, in the graph information GR11 in FIG. 1, the node identified by the node ID “N35” and the node identified by the node ID “N693” are close to each other, that is, the distance is short. Therefore, it is shown that the object corresponding to the node identified by the node ID “N35” and the object corresponding to the node identified by the node ID “N693” have a high degree of similarity.

Further, for example, in the graph information GR11 in FIG. 1, the node identified by the node ID “N7” and the node identified by the node ID “N2” are remote, that is, have a long distance. Therefore, it is shown that the object corresponding to the node identified by the node ID “N7” and the object corresponding to the node identified by the node ID “N2” have a low degree of similarity.

[1-2. Vector generation example]
Further, each node (vector) referred to here corresponds to each object (product). If the product data is numerical data indicating various products, it can be treated as it is as vector data. However, if the product data is text (character information), an image, or the like, conversion to vector data is required. Therefore, in the example of FIG. 1, a multidimensional (N-dimensional) vector generated by the feature amount extracted from the product data (product information) of each product may be an object.

For example, the information processing apparatus 100 may generate an N-dimensional vector from the product data of each product by using a model that extracts the features of the product data. In the example of FIG. 1, the information processing apparatus 100 uses the model (model M1) identified by the model ID “M1” as shown in the model information storage unit 124 (see FIG. 7), and the product data of each product is used. Generate a vector from. As described above, when "model M * (* is an arbitrary numerical value)" is described, it means that the model is a model identified by the model ID "M *". For example, when described as "model M1", the model is a model identified by the model ID "M1". Further, as shown in the model information storage unit 124, the model M1 is a model used for use "feature extraction (commodity)", that is, for feature extraction from product data, and the specific model data thereof is "model". It indicates that it is "data MDT1".

For example, the information processing apparatus 100 calculates the value of each element (neuron) in the model M1 by inputting the product data of an arbitrary product into the model M1, and outputs the same information as the input product data. For example, the information processing apparatus 100 may extract the value of each element (neuron) in the intermediate layer as a feature amount and generate N-dimensional vector data corresponding to each product.

Here, FIG. 12 is used to show an example of generating vector data corresponding to each product. FIG. 12 is a diagram showing an example of extraction of a feature amount according to an embodiment. FIG. 12 is a conceptual diagram of the model M1. In FIG. 12, the line showing each connection relationship of each element (neuron) is omitted. As shown in FIG. 12, the model M1 includes an input layer IL, an intermediate layer CL, and an output layer OL. For example, the input layer IL of the model M1 is a layer into which product data is input. Further, the output layer OL is a layer that outputs the same information as the input product data in response to the input to the input layer IL.

Further, for example, the most compressed compression layer RP in the central portion of the intermediate layer CL is a layer expressing the characteristics of the input product data. For example, in the intermediate layer CL of the model M1, the portion from the input layer IL to the compression layer RP corresponds to the portion where the encoding process is performed. In the intermediate layer CL of the model M1, between the input layer IL and the compression layer RP corresponds to a portion that performs a process of compressing the characteristics of the input product data. For example, in the intermediate layer CL of the model M1, the portion from the compression layer RP to the output layer OL corresponds to the portion where the decoding process is performed. In the intermediate layer CL of the model M1, the portion from the compression layer RP to the output layer OL corresponds to a portion for performing a process of restoring the compressed product data.

For example, the information processing apparatus 100 may use information such as neuron NL1 and neuron NL2 included in the compression layer RP as a vector. For example, the information processing apparatus 100 uses the value VE1 corresponding to the calculated neuron NL1 and the value VE2 corresponding to the neuron NL2 as a vector element (one-dimensional value) when the product data of a certain product is input. It may be extracted. For example, the information processing apparatus 100 may extract the value VE1 corresponding to the calculated neuron NL1 as the first-dimensional element of the vector of the product when the product data of a certain product is input. Further, for example, the information processing apparatus 100 may extract the value VE2 corresponding to the calculated neuron NL2 as the second-dimensional element of the vector of the product when the product data of a certain product is input. As described above, the information processing apparatus 100 may generate a vector corresponding to each product by inputting the product data of each product into the model M1. The information processing device 100 may acquire a vector corresponding to each product from another external device such as the service providing device 50. The information processing apparatus 100 may use the value itself corresponding to each neuron as each element of the vector, or may use the value corresponding to each neuron multiplied by a predetermined coefficient. Further, in the example of FIG. 1, for the sake of simplicity, a case where each element (value) of the vector is an integer is shown, but each element (value) of the vector is a real number including a numerical value after the decimal point. May be good.

The information processing apparatus 100 is not limited to the element (neuron) of the compression layer RP, and may use the information of other elements (neurons) in the intermediate layer CL as the vector. For example, the information processing apparatus 100 may use information such as the neuron NL3 in the encoding portion and the neuron NL4 in the decoding portion as a vector. For example, the information processing apparatus 100 uses the calculated value VE3 corresponding to the neuron NL3 and the value VE4 corresponding to the neuron NL4 as a vector element (one-dimensional value) when the product data of a certain product is input. It may be extracted. The above is an example, and the information processing apparatus 100 is not limited to the autoencoder, and various models may be used to extract features from the product data. Further, the information processing apparatus 100 may perform feature extraction without using a model. For example, a model trained to identify each product may be generated, and the intermediate layer thereof may be extracted as vector data. In addition, a model may be generated by a method of learning similarity, for example, triplet loss. For example, the information processing apparatus 100 may be set by the administrator of the information processing apparatus 100 or the like to extract information corresponding to features (features) from the product data and generate a vector. For example, the information processing apparatus 100 may extract information corresponding to features (features) such as product categories, image information, manufacturers, and contents from product data, and generate a vector. Further, for example, the information processing apparatus 100 may generate a vector using information about a user attribute whose main target is the product.

Further, for example, the information processing device 100 may acquire the model M1 from another external device such as the service providing device 50. The information processing apparatus 100 may generate the model M1 by inputting the product information GIN1, GIN2, GIN451, etc. of each product stored in the product information storage unit 121 (see FIG. 4). For example, the information processing apparatus 100 may generate the model M1 by inputting the product information GIN1, GIN2, GIN451, etc. of each product. For example, the product information GIN1, GIN2, GIN451 and the like may include information regarding the product category, image information, manufacturer, size and the like. For example, the product information such as product information GIN1, GIN2, GIN451 may include information (first category information) indicating whether the product category of the corresponding product is drinking water, alcoholic beverages, seasonings, or the like. For example, the product information such as product information GIN1, GIN2, and GIN451 is information indicating a detailed product category (second category information) indicating whether the product category of the corresponding product is beer, wine, ketchup, sauce, or the like. May include. Further, for example, the product information may include image information obtained by capturing an image of the corresponding product. For example, the product information may include information indicating which manufacturer the corresponding product is manufactured by. For example, the product information may include information indicating what size the product has, such as the content of the corresponding product. For example, the product information includes information indicating the target of the product, such as information indicating that the target user of the corresponding product is in his twenties and information indicating that the target user of the corresponding product is a female. But it may be. The above is an example, and any information may be included in the product information.

The information processing apparatus 100 is a first element that is any of an input layer into which product information (product data) of a product is input, an output layer, and a layer from the input layer to the output layer, and belongs to a layer other than the output layer. And a second element whose value is calculated based on the first element and the weight of the first element, and each element belonging to each layer other than the output layer with respect to the product information input to the input layer is the first. As one element, a model M1 that outputs the same information as the information input to the input layer from the output layer may be generated by performing an operation based on the first element and the weight of the first element. The information processing device 100 may acquire a model used for vector generation from another external device such as the service providing device 50.

[1-3. Processing example]
From here, the case where the information processing device 100 acquires information (order information) indicating that one product is ordered from the IoT device 10 which is another information processing device will be described as an example. Further, in the example of FIG. 1, since the information processing apparatus 100 does not have one product in stock, a case where information recommending a product similar to one product is transmitted to the IoT device 10 will be described as an example.

In FIG. 1, the refrigerator, which is the IoT device 10 (TID11) identified by the ID “TID11”, is arranged in the residential HM. For example, the IoT device 10 (TID11) may be simply referred to as the IoT device 10. In this case, the IoT device 10 which is a refrigerator may detect consumption by each product such as food by detecting an internal change by various sensors such as an image sensor. The IoT device 10 is not limited to the image sensor, and may detect the status of each product by various sensors such as an infrared sensor and a weight sensor. In the example of FIG. 1, the IoT device 10 is used by the user U1 who resides in the residential HM.

In the example of FIG. 1, the IoT device 10 shows a case where the product X is ordered because the remaining amount of the product X stored inside is equal to or less than a predetermined threshold value (for example, 10% of the content). The IoT device 10 detects the date and time when the product X is stored inside, and even if a predetermined period (for example, 2 weeks or 1 month) elapses from the detected date and time, the product X is ordered. good. For example, the product X may be a seasoning (ketchup or the like) manufactured by a certain manufacturer X.

First, the IoT device 10 that detects that the remaining amount of the product X is equal to or less than a predetermined threshold value transmits the order information of the product X to the information processing device 100. Further, in the example of FIG. 1, the IoT device 10 transmits the product information GIN 11 of the product X to the information processing device 100. For example, the IoT device 10 may acquire the product information GIN 11 of the product X from the service providing device 50 and transmit it to the information processing device 100. For example, the IoT device 10 transmits the product information GIN 11 of the product X collected from the service providing device 50 to the information processing device 100. In the example of FIG. 1, the product information GIN11 and the like include information regarding product categories, image information, manufacturers, sizes, and the like.

When the information processing device 100 has already acquired the product information GIN 11 of the product X, the IoT device 10 does not have to transmit the product information GIN 11 of the product X to the information processing device 100. Further, when the service providing device 50 provides the electronic commerce service, the IoT device 10 may transmit the order information of the product X to the service providing device 50.

Then, the information processing apparatus 100 acquires the order information of one product and the product information (product data) related to one product (step S10). In the example of FIG. 1, the information processing apparatus 100 acquires the order information of the product X and the product information GIN 11 related to the product X from the IoT device 10. When the service providing device 50 provides the electronic commerce service, the information processing device 100 obtains the order information of the product X and the product information GIN 11 of the product X acquired from the IoT device 10 by the service providing device 50 from the service providing device 50. You may get it.

Then, the information processing apparatus 100 confirms the inventory of one product (step S11). In the example of FIG. 1, the information processing apparatus 100 confirms (determines) whether or not the product X is in stock based on the inventory information of the product X stored in the inventory information storage unit 125. In the example of FIG. 1, since the product X is out of stock as shown in the inventory information storage unit 125, the information processing apparatus 100 determines that the product X is out of stock. For example, when the service providing device 50 provides the electronic commerce service, the information processing device 100 requests the service providing device 50 for the inventory information of the product X, acquires the inventory information of the product X from the service providing device 50, and obtains the inventory information of the product X. You may confirm whether or not the product X is in stock by checking the acquired inventory information of the product X. When the product X is in stock, the information processing apparatus 100 may perform a process of making a payment for the product X or delivering the product X to the address AD1 of the user U1 (see FIG. 9).

In the example of FIG. 1, since the product X is out of stock, the information processing apparatus 100 performs a process of transmitting information recommending a similar product of the product X to the IoT device 10. First, the information processing apparatus 100 generates a vector used for searching graph information from product data corresponding to one product. In the example of FIG. 1, the information processing apparatus 100 generates a vector corresponding to the product X by the processing as shown in the processing group PS11. The information processing apparatus 100 inputs the product information GIN11 regarding the product X into the model M1 (step S12). Specifically, the information processing apparatus 100 inputs the product information GIN11 of the product X into the model M1. Then, the information processing apparatus 100 generates a vector by using the information in the model M1 after the input of the product information GIN11 (step S13). For example, the information processing apparatus 100 generates vector data using each element in the model M1 in which the product information GIN 11 is input.

In the example of FIG. 1, the information processing apparatus 100 generates vector data VD11 (also simply referred to as “vector VD11”) by using the value of each element in the model M1 in which the product information GIN11 is input. For example, the information processing apparatus 100 sets a value VE1 (see FIG. 12) corresponding to the neuron NL1 of the model M1 and a value VE2 (see FIG. 12) corresponding to the neuron NL2 when the product information GIN11 of the product X is input. To generate a vector. For example, the information processing apparatus 100 may extract the value VE1 corresponding to the calculated neuron NL1 as the first-dimensional element of the vector VD11 when the product information GIN11 of the product X is input. Further, for example, the information processing apparatus 100 generates the vector VD11 by using the value VE2 corresponding to the calculated neuron NL2 as the second-dimensional element of the vector VD11 when the product data of a certain product is input. In the example of FIG. 1, the information processing apparatus 100 generates a vector VD11 in which the element of the first dimension is "35" and the element of the second dimension is "63".

When the information processing apparatus 100 has already generated the vector VD11 of the product X, the information processing apparatus 100 does not have to perform the processing of the processing group PS11. For example, the information processing apparatus 100 may acquire the vector VD11 of the product X from the product information storage unit 121 when the vector of the product X is stored in the product information storage unit 121 (see FIG. 4).

Then, the information processing apparatus 100 searches for a product (similar product) similar to the product X (step S14). For example, the information processing apparatus 100 may search for a similar product of the product X by appropriately using various conventional techniques such as a neighborhood search technique disclosed in Non-Patent Document 1.

In the example of FIG. 1, the information processing apparatus 100 searches for similar products of the product X by using the graph information GR 11 and the index information IND 11 as shown in the information group INF 11. For example, the information processing apparatus 100 acquires graph information GR11 related to a product from the graph information storage unit 123 (see FIG. 6). Further, for example, the information processing apparatus 100 uses the index information storage unit 122 (see FIG. 5) to obtain the index information IND11 used for determining the node (hereinafter, also referred to as “starting point vector”) that is the starting point of the search in the graph information GR 11. get. The index information IND 11 may be generated by the information processing device 100, or the information processing device 100 may acquire the index information IND 11 from another external device such as the service providing device 50.

Then, the information processing apparatus 100 uses the index information IND11 to determine (specify) the starting point vector corresponding to one product (query). In the example of FIG. 1, the information processing apparatus 100 uses the index information IND11 to determine (specify) the starting point vector corresponding to the vector VD11 of the product X. That is, the information processing apparatus 100 uses the vector VD11 and the index information IND11 to determine the starting point vector in the graph information GR11.

The index information IND11 in FIG. 1 has a hierarchical structure shown in the index information storage unit 122 in FIG. For example, the index information IND11 indicates that the node (vector) of the first layer located immediately below the root RT is a node VT1, VT2, or the like. Further, for example, the index information IND11 indicates that the node of the second layer immediately below the node VT2 is the node VT2-1 to VT2-4 (not shown). Further, for example, the index information IND11 indicates that the node in the third layer immediately below the node VT2-2 is a node N35, a node N451, a node N693, that is, a node (vector) in the graph information GR11.

For example, the information processing apparatus 100 determines the starting point vector in the graph information GR 11 by using the tree-structured index information as shown in the index information IND11 in FIG. 1 (step S15). In the example of FIG. 1, the information processing apparatus 100 efficiently generates the vector VD11 and then traces the index information IND11 from top to bottom to identify a starting point vector that is a candidate near the index information IND11. The starting point vector corresponding to the search query (one product) can be determined.

For example, the information processing apparatus 100 may determine the starting point vector corresponding to the vector VD11 by tracing the index information IND11 from the root RT to the leaf node (node (vector) in the graph information GR11). In the example of FIG. 1, for example, the information processing apparatus 100 determines the node N451 as a starting point vector by tracing the index information IND11 from the root RT to the node N451. Although the example of FIG. 1 shows a case where one starting point vector is determined for the sake of simplicity, the information processing apparatus 100 may determine a plurality of starting point vectors. For example, the information processing apparatus 100 may determine a plurality of vectors (nodes) such as nodes N451, N35, N693, and N2 as starting point vectors. For example, the information processing apparatus 100 may determine the leaf node reached as a starting point vector by tracing the index information IND11 from the root RT to the leaf node by appropriately using various conventional techniques related to the tree structure. For example, the information processing apparatus 100 may determine the starting point vector by tracing the index information IND11 downward based on the degree of similarity with the vector VD11. For example, the information processing apparatus 100 may determine which node, such as node VT1 or VT2, is to be traced from the root RT based on the degree of similarity between the vector VD11 and the nodes VT1 and VT2. For example, the information processing apparatus 100 may determine to trace from the root RT to the node VT2 having the highest degree of similarity to the vector VD11 among the nodes VT1, VT2, and the like. Further, for example, the information processing apparatus 100 may determine from the node VT2 to the node VT2-2 having the highest degree of similarity to the vector VD11 among the nodes VT2-1 to VT2-4 and the like. Further, for example, the information processing apparatus 100 may determine to trace from the node VT2-2 to the node node N451 having the highest degree of similarity to the vector VD11 among the nodes N35, N451, N693 and the like. It should be noted that one or more nodes may be randomly selected from the graph information GR11 at the start of the search without using the index information IND11 and used as a starting point vector, or one or more nodes specified in advance may be used as the starting point. It may be a vector.

Then, the information processing apparatus 100 extracts a similar product of the product X by searching the graph information GR 11 (step S16). For example, the information processing apparatus 100 extracts a node located in the vicinity of the node N451 as a similar product. For example, the information processing apparatus 100 extracts a node having a short distance from the node N451 as a similar product. For example, the information processing apparatus 100 extracts a node reachable from the node N451 as a similar product by tracing the edge starting from the node N451. For example, the information processing apparatus 100 extracts a predetermined number (for example, two, ten, etc.) of nodes as similar products. For example, the information processing apparatus 100 may extract similar products of product X by a search process as shown in FIG. 13, but the details will be described later. In the example of FIG. 1, the information processing apparatus 100 extracts the node N451 and the node N35 as similar products by searching the graph information GR11 starting from the node N451.

Then, the information processing apparatus 100 determines a recommended product based on the extracted similar products (step S17). In the example of FIG. 1, the information processing apparatus 100 determines the product # 451 corresponding to the node N451 most similar to the vector VD11 of the product X as the recommended product. For example, the information processing apparatus 100 may determine (specify) the product most similar to the product X by comparing the vector VD11 of the product X with the vector of each similar product. The information processing device 100 is not limited to one product, and a plurality of products may be determined as recommended products.

Then, the information processing apparatus 100 transmits information (recommended information) regarding the recommended product to the IoT device 10 (step S18). In the example of FIG. 1, the information processing apparatus 100 transmits information indicating the product # 451 corresponding to the node N451 to the IoT device 10. For example, the product X may be a seasoning other than the product X manufactured by a certain manufacturer X or a ketchup manufactured by another manufacturer Y.

Then, the IoT device 10 that has received the recommended information indicating the product # 451 from the information processing device 100 determines whether to purchase (order) the product # 451 (step S19). For example, the IoT device 10 may notify the user U1 by a predetermined output means and determine whether to purchase (order) the product # 451 based on the operation by the user U1. For example, the IoT device 10 purchases the product # 451 (ordering) by displaying that the product # 451 is a recommended product on a predetermined display means and accepting an operation indicating whether or not the product # 451 can be ordered by the user U1. ) May be determined. For example, the IoT device 10 notifies the user U1 by voice output that it is a recommended product indicating the product # 451 and determines whether to purchase (order) the product # 451 based on the operation by the user U1. May be good.

The IoT device 10 may determine whether to purchase (order) the product # 451 without the operation by the user U1. For example, the IoT device 10 may determine that the product # 451 will be purchased if the user U1 has a history of purchasing (ordering) the product # 451 in the past. For example, the IoT device 10 may determine that the product # 451 will not be purchased if the user U1 has no history of purchasing (ordering) the product # 451 in the past.

In the example of FIG. 1, the IoT device 10 has a means for accepting a user's operation such as a touch panel (screen), and displays on the touch panel that it is a recommended product indicating product # 451. Then, the IoT device 10 receives the operation of the user U1 by the touch panel, and acquires the information indicating that the user U1 orders the product # 451. Then, the IoT device 10 transmits information (answer information) indicating that the product # 451 is ordered to the information processing device 100.

Then, the information processing apparatus 100 acquires the answer information indicating that the user U1 orders the product # 451 (step S20). In the example of FIG. 1, the information processing apparatus 100 acquires the answer information indicating that the product # 451 is ordered from the IoT device 10. Then, the information processing apparatus 100 processes the order for the product # 451. For example, the information processing apparatus 100 performs a payment process for the product # 451 using the account information of the user U1 or a procedure for delivering the product # 451 to the address AD1 of the user U1.

In the example of FIG. 1, the information processing apparatus 100 instructs the distribution center DB1 which is the distribution base A to deliver (step S21). For example, the information processing apparatus 100 instructs the distribution center DB1 to deliver the product # 451 to the address AD1 of the user U1. For example, the information processing apparatus 100 transmits information instructing the information processing apparatus (not shown) of the distribution center DB1 to deliver the product # 451 to the address AD1 of the user U1. For example, the distribution center DB1 may be a distribution base close to the address AD1 of the user U1.

Then, the distribution center DB1 that receives the delivery instruction from the information processing apparatus 100 delivers the product # 451 to the address AD1 of the user U1 (step S22). As a result, the user U1 can receive the product # 451 which is a similar product of the product X that was out of stock at the home HM.

As described above, the information processing apparatus 100 uses the graph information GR11 and the index information IND11 to extract similar products of the product X acquired from the user U1. For example, the information processing apparatus 100 uses the index information IND11 to determine the starting point vector in the graph information GR11 when extracting a similar product of the product X. Then, the information processing apparatus 100 extracts a similar product of the product X by searching the graph information GR 11 with the determined starting point vector as the starting point. Then, the information processing apparatus 100 determines a recommended product based on the extracted similar products, and transmits information (recommended information) about the recommended product to the IoT device 10. Thereby, the information processing apparatus 100 can recommend an appropriate product. For example, there is a method of identifying products by a method such as deep learning, but when there are a wide variety of products, there are few cases of each product, so it is difficult to improve the identification accuracy without learning. There is a problem. For example, there is a method of using a model generated by a learning method such as deep learning, inputting product information into the model, and identifying the product from the output score, but when there are a wide variety of products, Since there are few cases of each product, it is difficult to improve the accuracy of the model, and it is difficult to improve the identification accuracy of the product. On the other hand, the information processing apparatus 100 appropriately extracts similar products similar to the products by performing a search using graph-structured graph information of a plurality of vectors generated based on the features extracted from each product. be able to. Therefore, the information processing apparatus 100 can accurately identify what kind of product the product corresponds to.

[1-4. Recommended according to the situation]
In the example of FIG. 1, the information processing apparatus 100 may determine a recommended product based on the similarity of the products and taking into consideration the situation of the IoT device 10 and the user. For example, the information processing apparatus 100 may decide not to transmit information on recommended products when the storage space of the refrigerator, which is the IoT device 10, is insufficient. For example, the information processing apparatus 100 may decide not to transmit information about recommended products when the capacity of the refrigerator, which is the IoT device 10, is used by a predetermined threshold value or more. Further, for example, when 90% or more of the capacity of the refrigerator, which is the IoT device 10, is used in the information processing apparatus 100, a product having a smaller capacity may be determined as a recommended product among similar products. For example, when 90% or more of the capacity of the refrigerator, which is the IoT device 10, is used in the information processing apparatus 100, the product having the smallest capacity among similar products may be determined as the recommended product.

Further, for example, the information processing apparatus 100 may determine whether or not to transmit information on recommended products based on schedule information such as a schedule of a user who uses the IoT device 10. For example, the information processing apparatus 100 determines not to transmit information on recommended products to the IoT device 10 when the user who uses the IoT device 10 is absent for a predetermined period (for example, one month or the like). You may. For example, in the information processing apparatus 100, when the scheduled information that the user who uses the IoT device 10 will be absent after a predetermined period (for example, two weeks or the like) is acquired, among similar products, before the user is absent. A product having a capacity that can be consumed in a predetermined period may be determined as a recommended product.

[1-5. Model and graph information for each category]
In the example of FIG. 1, the case where the model M1 is used is shown, but for example, the information processing apparatus 100 may use a different model for each product category.

For example, the information processing apparatus 100 corresponds to each category by using a model generated for each of various product categories such as alcoholic beverages, seasonings, vegetables, meats, frozen foods, etc. (hereinafter, also referred to as “category-specific model”). You may extract similar products of the products to be processed. For example, the information processing apparatus 100 may generate a model for each category. The information processing apparatus 100 may generate a category-specific model (autoencoder) that inputs product information of a category corresponding to each category-specific model and outputs the same information as the product information. For example, the information processing apparatus 100 uses the input product information itself as correct answer information, and generates a category-specific model (auto encoder) that outputs the same information as the input product information. For example, the product information input to the categorical model includes image information, manufacturer, size, and the like. In this case, the information processing apparatus 100 may generate graph information for each product group corresponding to each category. Further, the information processing apparatus 100 may acquire graph information generated for each product group corresponding to each category from an external information processing apparatus such as the service providing apparatus 50.

Then, when the information processing apparatus 100 extracts similar products of products belonging to the liquor category, the information processing apparatus 100 extracts similar products of the products belonging to the liquor category by searching using the graph information corresponding to the liquor category. You may. Further, when the information processing apparatus 100 extracts similar products of products belonging to the frozen food category, the information processing apparatus 100 searches for similar products of the products belonging to the liquor category by using the graph information corresponding to the frozen food category. May be extracted.

[1-6. Index information]
The index information (index data) shown in the example of FIG. 1 is an example, and the information processing apparatus 100 may search for graph information using various index information. Further, for example, the information processing apparatus 100 may generate index data to be used at the time of search. For example, the information processing apparatus 100 generates a search index for searching a high-dimensional vector as index data. The high-dimensional vector referred to here may be, for example, a vector having several hundred dimensions to several thousand dimensions, or a vector having more dimensions.

For example, the information processing apparatus 100 may generate a search index related to a tree structure (tree structure) as shown in FIG. 1 as index data. For example, the information processing apparatus 100 may generate a search index for a kd tree (k-dimensional tree) as index data. For example, the information processing apparatus 100 may generate a search index for a VP tree (Vantage-Point tree) as index data.

Further, for example, the information processing apparatus 100 may generate index data having another tree structure. For example, the information processing apparatus 100 may generate various index data in which leafs of index data having a tree structure are connected to graph data. For example, the information processing apparatus 100 may generate various index data in which the leaf of the index data of the tree structure corresponds to the node in the graph data. Further, when the information processing apparatus 100 searches using such index data, the information processing apparatus 100 may search the graph data from the leaf (node) reached by tracing the index data.

The index data as described above is an example, and the information processing apparatus 100 may generate index data having any data structure as long as the query in the graph data can be specified at high speed. .. For example, the information processing apparatus 100 generates index data by appropriately using various conventional techniques such as a technique related to binary space partitioning if it is possible to identify a node in the graph information corresponding to the query at high speed. You may. For example, the information processing apparatus 100 may generate index data having any data structure as long as it is an index capable of searching for a high-dimensional vector. For example, the information processing apparatus 100 may use information about a graph-type search index as described in Non-Patent Document 1 as index information. The information processing apparatus 100 can enable a more efficient search for a predetermined target by using the index data and the graph data as described above.

[2. Information processing system configuration]
As shown in FIG. 2, the information processing system 1 includes an IoT device 10, a service providing device 50, and an information processing device 100. The IoT device 10, the service providing device 50, and the information processing device 100 are connected to each other via a predetermined network N so as to be communicable by wire or wirelessly. FIG. 2 is a diagram showing a configuration example of an information processing system according to an embodiment. The information processing system 1 shown in FIG. 2 may include a plurality of IoT devices 10, a plurality of service providing devices 50, and a plurality of information processing devices 100.

The IoT device 10 is an information processing device used by a user. The IoT device 10 accepts various operations by the user. In the following, the IoT device 10 may be referred to as a user. That is, in the following, the user can be read as the IoT device 10.

The IoT device 10 is various devices having an information processing function used by the user. For example, the IoT device 10 may be any device as long as it has a communication function and can use the services provided by the service providing device 50, the information processing device 100, and the like. For example, the IoT device 10 may be a so-called home electric appliance such as a washing machine or a refrigerator, or may be a vehicle such as an automobile. For example, the IoT device 10 may be a device that detects voice or the like of a smart speaker, a robot, or the like. For example, the IoT device 10 may be a product package itself for detecting the capacity of the contents or the like, or may be a device such as a button for purchasing a predetermined product. Further, the IoT device 10 may be, for example, an information processing device such as a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, or a PDA (Personal Digital Assistant). .. Further, for example, the IoT device 10 may be a wearable device (Wearable Device) or the like that the user can wear. For example, the IoT device 10 may be a wristwatch-type terminal, a glasses-type terminal, or the like. In the following, the IoT device 10 may be referred to as a user. That is, in the following, the user can be read as the IoT device 10. For example, the IoT device 10 collects product data (product information) and transmits the product data to the information processing device 100.

The information processing device 100 is an information processing device that extracts similar products that are similar to one product among a plurality of products by searching graph information with the starting point vector as the starting point. For example, the information processing apparatus 100 acquires product information about one product, and determines the starting point vector based on the product information and the information about the starting point vector that is the starting point for searching the graph information.

The information processing device 100 is an information processing device in which information for providing various information to the IoT device 10 (user) or the like is stored. For example, when the information processing apparatus 100 acquires the order information of one product from the IoT device 10, the information processing apparatus 100 obtains a product (vector information or the like) similar to the one product information (hereinafter, also referred to as "query information" or "query"). The search is performed, and information indicating similar products based on the search results is transmitted to the IoT device 10. For example, when the information processing apparatus 100 acquires the product data of one product from the IoT device 10, it searches for a product similar to the query and provides the IoT device 10 with recommended information indicating the similar product based on the search result. In the example of FIG. 1, when the information processing apparatus 100 acquires the product data of one product from the IoT device 10, it searches for a product similar to the one product and provides the search result to the IoT device 10 as a similar product. .. Further, for example, the data provided by the information processing apparatus 100 to the IoT device 10 may be the product name or the product data itself of the product, or for referring to the corresponding data such as a URL (Uniform Resource Locator). It may be information.

The information processing apparatus 100 may also provide, for example, an electronic commerce service. Further, the information processing apparatus 100 may perform order processing such as settlement of goods sold in the electronic commerce service and delivery instructions.

The service providing device 50 is an information processing device in which information for providing various information to the information processing device 100 is stored. For example, the service providing device 50 may store product information or the like collected from various external devices such as a web server that provides an electronic commerce service. For example, the service providing device 50 is an information processing device that provides various information such as graph information, index information, and a model to the information processing device 100.

Further, for example, the service providing device 50 may provide an electronic commerce service. Further, the service providing device 50 may provide the information processing device 100 with the product information of the products sold in the electronic commerce service.

[3. Information processing device configuration]
Next, the configuration of the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing a configuration example of the information processing apparatus according to the embodiment. As shown in FIG. 3, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The information processing device 100 includes an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from the administrator of the information processing device 100, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. You may have.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 110 is connected to the network (for example, the network N in FIG. 2) by wire or wirelessly, and transmits / receives information to / from the IoT device 10 and the service providing device 50.

(Memory unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. As shown in FIG. 3, the storage unit 120 according to the embodiment includes a product information storage unit 121, an index information storage unit 122, a graph information storage unit 123, a model information storage unit 124, and an inventory information storage unit 125. , And a user information storage unit 126.

(Product information storage unit 121)
The product information storage unit 121 according to the embodiment stores various information about the product (object). For example, the product information storage unit 121 stores the product ID and vector data. FIG. 4 is a diagram showing an example of a product information storage unit according to an embodiment. The product information storage unit 121 shown in FIG. 4 includes items such as "product ID", "product", "product information", and "vector information".

The "product ID" indicates identification information for identifying a product (object). Further, the "product" indicates a specific name, content, or the like of the product identified by the product ID. In the example of FIG. 4, the product is indicated by an abstract code such as "product # 1", but each product includes information indicating what kind of product it is and position information such as an address and latitude / longitude. It may be.

"Product information" indicates information about a product identified by a product ID. In the example of FIG. 4, the product information is indicated by an abstract code such as "GIN1", but each product information relates to various products such as a product category, image information, manufacturer, and size identified by the product ID. Contains information. The "vector information" indicates the vector information corresponding to the product (object) identified by the product ID. That is, in the example of FIG. 4, the vector data (vector information) corresponding to the object is associated and registered with the product ID that identifies the product (object).

For example, in the example of FIG. 4, the product (object) identified by the product ID “GD1” is associated with multidimensional (N-dimensional) vector information of “10, 24, 54, 2 ...”. Is shown. For example, for the product # 1, the multidimensional (N-dimensional) vector information of "10, 24, 54, 2 ..." indicating the characteristics of the product # 1 is extracted from the product information GIN1 by the model M1 or the like. Show that.

The product information storage unit 121 is not limited to the above, and may store various information depending on the purpose.

(Index information storage unit 122)
The index information storage unit 122 according to the embodiment stores various information related to the index. FIG. 5 is a diagram showing an example of an index information storage unit according to an embodiment. Specifically, in the example of FIG. 5, the index information storage unit 122 shows index information having a tree structure. In the example of FIG. 5, the index information storage unit 122 includes items such as "root hierarchy", "first hierarchy", "second hierarchy", and "third hierarchy". It should be noted that the present invention is not limited to the "first layer" to the "third layer", and may include "fourth layer", "fifth layer", "sixth layer" and the like depending on the number of layers of the index.

The "root hierarchy" indicates a hierarchy of routes (top level) that is a starting point for determining a starting node using an index. The "first layer" stores information for identifying (identifying) a node (node or vector in graph information) belonging to the first layer of the index. The node stored in the "first layer" is a node corresponding to the layer directly connected to the root of the index.

The "second layer" stores information for identifying (identifying) a node (node or vector in graph information) belonging to the second layer of the index. The node stored in the "second layer" is a node corresponding to the immediately lower layer connected to the node of the first layer. The "third layer" stores information for identifying (identifying) a node (node or vector in graph information) belonging to the third layer of the index. The node stored in the "third layer" is a node corresponding to the immediately lower layer connected to the node of the second layer.

For example, in the example shown in FIG. 5, the index information storage unit 122 stores information corresponding to the index information IND11 in FIG. For example, the index information storage unit 122 indicates that the node of the first layer is the node VT1 to VT3 or the like. The numerical values in parentheses below each node indicate the value of the vector corresponding to each node.

Further, for example, the index information storage unit 122 indicates that the node of the second layer immediately below the node VT2 is the node VT2-1 to VT2-4. Further, for example, the index information storage unit 122 indicates that the node in the third layer immediately below the node VT2-2 is a node (vector) in the graph information GR11 of the node N35, the node N451, and the node N693.

The index information storage unit 122 is not limited to the above, and may store various information depending on the purpose.

(Graph information storage unit 123)
The graph information storage unit 123 according to the embodiment stores various information related to the graph information. FIG. 6 is a diagram showing an example of a graph information storage unit according to an embodiment. In the example of FIG. 6, the graph information storage unit 123 has items such as “node ID”, “product ID”, and “edge information”. Further, the "edge information" includes information such as "edge ID" and "reference destination".

The "node ID" indicates identification information for identifying each node (target) in the graph data. Further, the "product ID" indicates identification information for identifying a product (object).

Further, "edge information" indicates information about the edge connected to the corresponding node. In the example of FIG. 6, “edge information” indicates a case where the edge is a directed edge, and indicates information about an output edge output from the corresponding node. Further, the "edge ID" indicates identification information for identifying an edge connecting the nodes. Further, "reference destination" indicates information indicating a reference destination (node) connected by an edge. That is, in the example of FIG. 6, the reference destination (output edge) to which the information for identifying the object (target) corresponding to the node and the directed edge (output edge) from the node are concatenated with respect to the node ID for identifying the node. Node) is associated and registered.

For example, in the example of FIG. 6, it is shown that the node (vector) identified by the node ID “N1” corresponds to the product (object) identified by the product ID “GD1”. Further, from the node identified by the node ID "N1", it is shown that the edge identified by the edge ID "E11" is connected to the node (vector) identified by the node ID "N25". That is, in the example of FIG. 6, it is shown that the node (vector) identified by the node ID “N1” can be traced to the node (vector) identified by the node ID “N25”.

The graph information storage unit 123 is not limited to the above, and may store various information depending on the purpose. For example, the graph information storage unit 123 may store the length of the edge connecting each node (vector). That is, the graph information storage unit 123 may store information indicating the distance between each node (vector).

(Model information storage unit 124)
The model information storage unit 124 according to the embodiment stores information about the model. For example, the model information storage unit 124 stores model information (model data) generated by the generation process. FIG. 7 is a diagram showing an example of a model information storage unit according to an embodiment. The model information storage unit 124 shown in FIG. 7 includes items such as "model ID", "use", and "model data". Although only the models M1 and M2 are shown in FIG. 7, a large number of model information such as M21 and M22 may be stored according to each application (prediction target).

The "model ID" indicates identification information for identifying the model. For example, the model identified by the model ID "M1" corresponds to the model M1 shown in the example of FIG. "Use" indicates the use of the corresponding model. Further, the "model data" indicates the data of the corresponding corresponding model associated with the model data. For example, "model data" includes information including nodes in each layer, functions adopted by each node, connection relationships of the nodes, and connection coefficients set for connections between the nodes.

For example, in the example shown in FIG. 7, the model (model M1) identified by the model ID "M1" has a purpose of "feature extraction (product)" and is used for extracting features from the input product information. Show that. Further, it is shown that the model data of the model M1 is the model data MDT1.

The model M1 (model data MDT1) is an input layer into which product information (product data) of a predetermined product is input, an output layer, and any layer from the input layer to the output layer, which is a layer other than the output layer. Including the first element belonging to the above and the second element whose value is calculated based on the weights of the first element and the first element, and for the product information input to the input layer, to each layer other than the output layer. By performing an operation based on the first element and the weight of the first element with each element to which it belongs as the first element, the computer functions to output the same information as the information input to the input layer from the output layer. Is a model for.

Further, it is assumed that the models M1, M2 and the like are realized by a neural network having one or a plurality of intermediate layers such as a DNN (Deep Neural Network). In this case, for example, the first element included in the models M1 and M2 corresponds to any node of the input layer or the intermediate layer. Further, the second element corresponds to the node of the next stage, which is the node to which the value is transmitted from the node corresponding to the first element. Further, the weight of the first element corresponds to a connection coefficient which is a weight considered for the value transmitted from the node corresponding to the first element to the node corresponding to the second element.

Here, it is assumed that the models M21, M22 and the like are realized by the regression model represented by "y = a1 * x1 + a2 * x2 + ... + ai * xi". In this case, for example, the first element included in the models M21 and M22 corresponds to input data (xi) such as x1 and x2. Further, the weight of the first element corresponds to the coefficient ai corresponding to xi. Here, the regression model can be regarded as a simple perceptron having an input layer and an output layer. When each model is regarded as a simple perceptron, the first element corresponds to any node of the input layer, and the second element can be regarded as the node of the output layer.

The model information storage unit 124 is not limited to the above, and may store various model information depending on the purpose.

(Inventory information storage unit 125)
The inventory information storage unit 125 according to the embodiment stores various information regarding the inventory of products. FIG. 8 is a diagram showing an example of an inventory information storage unit according to an embodiment. For example, the inventory information storage unit 125 stores information about products sold in electronic commerce services such as online shopping. The inventory information storage unit 125 shown in FIG. 8 includes items such as “commodity” and “inventory information”.

The "product" indicates a specific name, content, or the like of the product identified by the product ID. In addition, identification information for identifying a product such as a product ID may be stored in the "product". For example, "inventory information" indicates the inventory status of the corresponding product. In the example of FIG. 8, the "inventory information" illustrates the case where only the presence or absence of inventory of the corresponding product is stored, but the "inventory information" stores information related to the number of products such as the number of stocks. May be good.

In the example shown in FIG. 8, the product X is shown to be out of stock. For example, the product X indicates that it is out of stock in the electronic commerce service. Further, in the example shown in FIG. 8, the product # 500 indicates that the product is in stock. For example, commodities # 500 indicate that they are in stock in an e-commerce service.

The inventory information storage unit 125 is not limited to the above, and may store various information depending on the purpose.

(User information storage unit 126)
The user information storage unit 126 according to the embodiment stores information about the user. FIG. 9 is a diagram showing an example of a user information storage unit according to an embodiment. FIG. 9 shows an example of information about a user stored in the user information storage unit 126. For example, the user information storage unit 126 stores information about the IoT device used by the user. As shown in FIG. 9, the user information storage unit 126 includes items such as "user ID", "address", and "IoT device 1" as information about the IoT device used by the user. In the example of FIG. 9, only "IoT device 1" is shown for the sake of simplicity, but the user information storage unit 126 is used by users such as "IoT device 2" and "IoT device 3". Information on each IoT device may be stored according to the number of IoT devices to be used.

The "user ID" indicates identification information for identifying a user. For example, the user identified by the user ID "U1" corresponds to the user U1 shown in the example of FIG. Further, the "address" indicates information regarding the address (residential place) of the user's home or the like. In the example of FIG. 9, the information stored in the "address" is illustrated by a code such as "AD1", but the "address" is specifically such as "Apartment A201, XX-ku, Tokyo". Date and time shall be memorized.

Further, the "IoT device 1" includes items such as "type" and "ID". Although only "IoT device 1" is shown, for example, when the corresponding user uses eight IoT devices, information about the IoT devices used from "IoT device 1" to "IoT device 8" is stored. Will be done. That is, when the corresponding user has eight IoT devices, information about the eight IoT devices used by the user is stored. The "type" of the "IoT device 1" indicates the type of the IoT device used by the user. Further, the "ID" of the "IoT device 1" indicates identification information for identifying the corresponding IoT device. For example, the "ID" of the "IoT device 1" indicates identification information for identifying the IoT device used by the corresponding user.

For example, in the example shown in FIG. 9, the user (user U1) identified by the user ID "U1" has an address of "AD1" and a gender of "female". Further, in the example shown in FIG. 9, the user U1 uses the IoT device of the type "refrigerator", and the ID of the IoT device (refrigerator) used by the user U1 is "TID11". Further, for example, in the example shown in FIG. 8, the user (user U2) identified by the user ID "U2" indicates that the address is "AD2". For example, the user U2 uses an IoT device of the type "smartphone", and the ID of the IoT device (smartphone) used by the user U2 is "TID21".

The user information storage unit 126 is not limited to the above, and may store various information depending on the purpose. For example, the user information storage unit 126 may store information such as gender, age, place of work, interest / interest, name, family structure, and income. For example, when the services that can be used by each IoT device are different, the user information storage unit 126 may store information about the service to be used for each IoT device in association with each other.

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller, and is stored in a storage device inside the information processing device 100 by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). Various programs (corresponding to an example of an information processing program) are realized by executing the RAM as a work area. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 130 is from an input layer, an output layer, and an input layer into which product information (product data) of a product is input by information processing according to models M1, M2, etc. stored in the model information storage unit 124. An input including a first element which is any layer up to the output layer and belongs to a layer other than the output layer, and a second element whose value is calculated based on the weights of the first element and the first element. Information input to the input layer by performing an operation based on the first element and the weight of the first element, with each element belonging to each layer other than the output layer as the first element for the product information input to the layer. The same information as is output from the output layer.

As shown in FIG. 3, the control unit 130 includes an acquisition unit 131, a generation unit 132, a determination unit 133, an extraction unit 134, and a transmission unit 135, and has functions and operations of information processing described below. Realize or execute. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3, and may be any other configuration as long as it is configured to perform information processing described later.

(Acquisition unit 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires various information from the storage unit 120. For example, the acquisition unit 131 is various from the product information storage unit 121, the index information storage unit 122, the graph information storage unit 123, the model information storage unit 124, the inventory information storage unit 125, the user information storage unit 126, and the like. Get information. Further, the acquisition unit 131 acquires various information from an external information processing device. The acquisition unit 131 acquires various information from the IoT device 10 and the service providing device 50.

The acquisition unit 131 acquires graph information in which a plurality of nodes corresponding to each of the plurality of products are linked according to the similarity of the plurality of products, and order information requesting the purchase of one product. The acquisition unit 131 acquires graph information in which a plurality of vectors showing the characteristics of each of the plurality of products are concatenated according to the similarity. The acquisition unit 131 acquires graph information in which a plurality of vectors corresponding to each of the plurality of products are concatenated according to the similarity, and product information related to one product. Further, the acquisition unit 131 acquires graph information in which a plurality of vectors showing the characteristics of each of the plurality of products are concatenated according to the similarity. In addition, the acquisition unit 131 acquires graph information in which a plurality of vectors whose elements are feature quantities extracted from each of a plurality of products using a predetermined model are concatenated according to the similarity.

Further, by inputting information about a plurality of products into a predetermined model, the acquisition unit 131 connects a plurality of vectors having the feature quantities of the plurality of products to be extracted as elements according to the similarity. Get graph information. Further, the acquisition unit 131 acquires order information from the requester, which is the predetermined IoT device 10. In addition, the acquisition unit 131 acquires response information indicating whether or not to purchase a similar product from the requester.

For example, the acquisition unit 131 acquires a plurality of nodes (vectors) to be searched for data. For example, the acquisition unit 131 acquires a plurality of nodes and a group of directed edges including a plurality of directed edges connecting each of the plurality of nodes.

For example, the acquisition unit 131 acquires graph information (graph data) from an external information processing device. For example, the acquisition unit 131 acquires graph information from the graph information storage unit 123. For example, the acquisition unit 131 acquires graph information. In the example of FIG. 1, the acquisition unit 131 acquires the graph information GR11.

For example, the acquisition unit 131 acquires index information (index data) from an external information processing device. For example, the acquisition unit 131 acquires index information from the index information storage unit 122. For example, the acquisition unit 131 acquires the index information of the tree structure type. In the example of FIG. 1, the acquisition unit 131 acquires the index information IND11.

In addition, the acquisition unit 131 acquires product information about one product from the IoT device 10 used by the user. For example, the acquisition unit 131 acquires the product data of one product as a search query. For example, the acquisition unit 131 acquires a search query related to a product. The acquisition unit 131 acquires the product information GIN 11 related to the product X from the IoT device 10 used by the user U1.

For example, the acquisition unit 131 acquires product information (product data) related to one product. For example, the acquisition unit 131 acquires the product information GIN 11 related to the product X from the IoT device 10. For example, the acquisition unit 131 acquires the graph information GR11 regarding the product from the graph information storage unit 123. Further, for example, the acquisition unit 131 acquires the index information IND11 used for determining the node (starting point vector) that is the starting point of the search in the graph information GR 11 from the index information storage unit 122 (see FIG. 5).

For example, the acquisition unit 131 acquires order information of one product and product information (product data) related to one product. For example, the acquisition unit 131 acquires the order information of the product X and the product information GIN 11 related to the product X from the IoT device 10. When the service providing device 50 provides the electronic commerce service, the acquisition unit 131 acquires the order information of the product X and the product information GIN 11 of the product X acquired from the IoT device 10 by the service providing device 50 from the service providing device 50. You may.

In the example of FIG. 1, the acquisition unit 131 acquires the response information indicating that the user U1 orders the product # 451. The acquisition unit 131 acquires the response information indicating that the product # 451 is ordered from the IoT device 10.

(Generation unit 132)
The generation unit 132 generates various information. For example, the generation unit 132 uses the learning data (product information) stored in the product information storage unit 121 to generate a model as shown in the model information storage unit 124. For example, the generation unit 132 generates a model (autoencoder) that outputs the same information as the input product information based on the learning data acquired by the acquisition unit 131. For example, the generation unit 132 generates a model (autoencoder) that outputs the same information as the input product information, using the input product information itself as correct answer information.

For example, the generation unit 132 generates the model M1 and the like, and stores the generated model M1 and the like in the model information storage unit 124. The generation unit 132 may generate the model M1 using any learning algorithm. For example, the generation unit 132 generates the model M1 by using a learning algorithm such as a neural network. As an example, when the generation unit 132 generates a model M1 or the like using a neural network, the model M1 or the like includes an input layer containing one or more neurons, an intermediate layer containing one or more neurons, and one or more neurons. It has an output layer including.

The generation unit 132 includes an input layer into which product information (product data) of a product is input, an output layer, and a first element which is any layer from the input layer to the output layer and belongs to a layer other than the output layer. , A second element whose value is calculated based on the first element and the weight of the first element, and each element belonging to each layer other than the output layer with respect to the product information input to the input layer is the first. By performing an operation based on the first element and the weight of the first element as elements, a model that outputs the same information as the information input to the input layer from the output layer is generated.

For example, the generation unit 132 generates a model based on the training data. For example, the generation unit 132 generates a model based on the training data. For example, the generation unit 132 generates a model by learning using the product information GIN1, GIN2, etc. in the product information storage unit 121 as learning data (teacher data).

For example, the generation unit 132 performs a learning process so that when the product information GIN1 is input, the model M1 outputs the same information as the product information GIN1. For example, the generation unit 132 performs a learning process so that when the product information GIN2 is input, the model M1 outputs the same information as the product information GIN2. The generation unit 132 generates a model and stores the generated model in the model information storage unit 124.

The generation unit 132 is not limited to M1 as an autoencoder, and may generate a model M21 or the like corresponding to a product by using various learning algorithms. For example, the generation unit 132 generates a model M21 or the like by using a learning algorithm such as a neural network, a support vector machine (SVM), clustering, or reinforcement learning. As an example, when the generation unit 132 generates a model M21 or the like using a neural network, the model M21 or the like includes an input layer containing one or more neurons, an intermediate layer containing one or more neurons, and one or more neurons. It has an output layer including.

In the example of FIG. 1, the generation unit 132 generates an N-dimensional vector from the product data of each product using a model that extracts the features of the product data. The generation unit 132 generates a vector from the product data of each product by using the model M1 shown in the model information storage unit 124 (FIG. 7).

Further, the generation unit 132 generates a vector used for searching graph information from the product data corresponding to one product. In the example of FIG. 1, the generation unit 132 generates the vector corresponding to the product X by the processing as shown in the processing group PS11. The generation unit 132 inputs the product information GIN11 regarding the product X into the model M1. Specifically, the generation unit 132 inputs the product information GIN 11 including information such as the ground, topography, sea area, soil, and weather of the product X into the model M1. Then, the generation unit 132 generates a vector by using the information in the model M1 after the input of the product information GIN11. For example, the generation unit 132 generates vector data using each element in the model M1 in which the product information GIN 11 is input.

In the example of FIG. 1, the generation unit 132 generates the vector VD11 by using the value of each element in the model M1 in which the product information GIN11 is input. For example, the generation unit 132 uses the value VE1 (see FIG. 12) corresponding to the neuron NL1 of the model M1 and the value VE2 (see FIG. 12) corresponding to the neuron NL2 when the product information GIN11 of the product X is input. To generate a vector. For example, the generation unit 132 may extract the value VE1 corresponding to the calculated neuron NL1 as the first-dimensional element of the vector VD11 when the product information GIN11 of the product X is input. Further, for example, the generation unit 132 generates the vector VD11 by using the value VE2 corresponding to the calculated neuron NL2 as the second-dimensional element of the vector VD11 when the product data of the product is input. In the example of FIG. 1, the generation unit 132 generates the vector VD11 such that the element of the first dimension is “35” and the element of the second dimension is “63”.

(Decision unit 133)
The determination unit 133 determines various information. The determination unit 133 determines the origin node based on the index information used for determining the origin node. The determination unit 133 determines the starting node based on the index information of the tree structure type. For example, the determination unit 133 determines the starting point vector based on the product information acquired by the acquisition unit 131 and the information regarding the starting point vector that is the starting point for searching the graph information. For example, the determination unit 133 determines the starting point vector based on the product information and the information that serves as a reference for determining the starting point vector for searching the graph information. Further, the determination unit 133 determines the origin vector based on the index information used for determining the origin vector. Further, the determination unit 133 determines the starting point vector based on the index information of the tree structure type. Further, when the product (query product) corresponding to the query exists on the graph, the determination unit 133 determines the query product as the starting node. For example, when the graph information includes a node corresponding to one product, the determination unit 133 determines the node as a starting node.

In the example of FIG. 1, the determination unit 133 uses the index information IND11 to determine (specify) the origin vector corresponding to one product (query). For example, the determination unit 133 uses the index information IND11 to determine (specify) the origin vector corresponding to the vector VD11 of the product X. The determination unit 133 determines the starting point vector in the graph information GR 11 by using the vector VD11 and the index information IND11.

For example, the determination unit 133 determines the starting point vector in the graph information GR 11 by using the tree-structured index information as shown in the index information IND11 in FIG. In the example of FIG. 1, after generating the vector VD11, the determination unit 133 efficiently searches by tracing the index information IND11 from top to bottom to specify a starting point vector that is a candidate near the index information IND11. Determine the origin vector corresponding to the query (one product).

For example, the determination unit 133 determines the starting point vector corresponding to the vector VD11 by tracing the index information IND11 from the root RT to the leaf node (node (vector) in the graph information GR11). In the example of FIG. 1, the determination unit 133 determines the node N451 as a starting point vector by tracing the index information IND11 from the root RT to the node N451.

For example, the determination unit 133 determines a recommended product based on the extracted similar products. For example, the determination unit 133 determines the product # 451 corresponding to the node N451 most similar to the vector VD11 of the product X as the recommended product. For example, the determination unit 133 may determine (specify) the product most similar to the product X by comparing the vector VD11 of the product X with the vector of each similar product. The determination unit 133 is not limited to one product, and may determine a plurality of products as recommended products.

(Extraction unit 134)
The extraction unit 134 extracts various information. The extraction unit 134 searches for graph information from a plurality of nodes of the graph information acquired by the acquisition unit 131, starting from the starting node that is the starting point for searching the graph information determined based on a predetermined criterion. Therefore, a similar product, which is a product similar to one product, is extracted from a plurality of products. The extraction unit 134 searches for graph information from a plurality of vectors of graph information acquired by the acquisition unit 131, starting from a starting point vector that is a starting point for searching graph information determined based on a predetermined criterion. , Extract similar products that are similar to one product from a plurality of products. For example, the extraction unit 134 extracts a similar product, which is a product similar to one product, from a plurality of products by searching the graph information with the starting point vector determined by the determination unit 133 as the starting point. For example, the extraction unit 134 may use information on the length (distance) of the edge connecting each node (vector) stored in the graph information storage unit 123, or each node (from the vector information of each node). Information on the length (distance) of the edges connecting the vectors) may be calculated, and the calculated length (distance) information may be used. The extraction unit 134 extracts similar products from the starting point vector determined by the determination unit 133. Further, when the one product is out of stock, the extraction unit 134 extracts a similar product of the one product. Further, when the graph information includes a node corresponding to one product, the extraction unit 134 extracts similar products from the node as a starting node. Further, when the extraction unit 134 extracts similar products with the node corresponding to one product as the starting node, the extraction unit 134 extracts the products excluding one product as similar products. For example, when extracting similar products from a node corresponding to one product as a starting node, the extraction unit 134 extracts a plurality of products and extracts products excluding one product from a plurality of products as similar products.

In the example of FIG. 1, the extraction unit 134 searches for a product similar to the product X. For example, the extraction unit 134 extracts a similar product of the product X by searching the graph information GR11. The extraction unit 134 extracts a node located in the vicinity of the node N451 as a similar product. For example, the extraction unit 134 extracts a node having a short distance from the node N451 as a similar product. For example, the extraction unit 134 extracts a node reachable from the node N451 as a similar product by tracing the edge starting from the node N451. For example, the extraction unit 134 extracts a predetermined number of nodes (for example, 2 or 10) as similar products. For example, the extraction unit 134 extracts similar products of product X by a search process as shown in FIG. In the example of FIG. 1, the extraction unit 134 extracts the node N451 and the node N35 as similar products by searching the graph information GR11 starting from the node N451.

(Sender 135)
The transmission unit 135 transmits various information. For example, the transmission unit 135 transmits various information to the IoT device 10 and the service providing device 50. For example, the transmission unit 135 distributes various information to the IoT device 10 and the service providing device 50. For example, the transmission unit 135 transmits various information to the IoT device 10 and the service providing device 50. The transmission unit 135 provides a predetermined service based on the similar products extracted by the extraction unit 134. In addition, the transmission unit 135 provides an information providing service regarding similar products. The transmission unit 135 transmits information about similar products to the IoT device 10.

The transmission unit 135 transmits recommended information based on similar products extracted by the extraction unit 134 to a requester requesting the purchase of one product. In addition, the transmission unit 135 transmits recommended information prompting the purchase of similar products to the requester. For example, the transmission unit 135 transmits the object ID corresponding to the query as a search result. For example, the transmission unit 135 transmits the object ID selected by the extraction unit 134 to the service providing device 50. The transmission unit 135 transmits the object ID selected by the extraction unit 134 to the service providing device 50 as information indicating a vector corresponding to the query. Further, the transmission unit 135 may transmit the model generated by the generation unit 132 to an external information processing device.

In the example of FIG. 1, the transmission unit 135 transmits information (recommended information) regarding the recommended product to the IoT device 10. The transmission unit 135 transmits information indicating the product # 451 corresponding to the node N451 to the IoT device 10.

Further, in the example of FIG. 1, the transmission unit 135 instructs the distribution center DB 1, which is the distribution base A, to deliver. The transmission unit 135 instructs the distribution center DB1 to deliver the product # 451 to the address AD1 of the user U1. For example, the transmission unit 135 transmits information instructing the information processing device (not shown) of the distribution center DB1 to deliver the product # 451 to the address AD1 of the user U1.

[4. Information processing flow]
Next, the procedure of information processing by the information processing system 1 according to the embodiment will be described with reference to FIG. FIG. 10 is a flowchart showing an example of information processing according to the embodiment.

As shown in FIG. 10, the information processing apparatus 100 acquires order information of one product from the IoT device 10 (step S101). In the example of FIG. 1, the information processing apparatus 100 acquires the order information of the product X and the product information GIN 11 related to the product X from the IoT device 10 (TID 11) which is a refrigerator used by the user U1.

Then, the information processing apparatus 100 determines whether or not one product is in stock (step S102). In the example of FIG. 1, the information processing apparatus 100 determines whether or not the product X is in stock based on the inventory information stored in the inventory information storage unit 125. For example, when the information processing apparatus 100 does not have one product in stock (step S102: No), the information processing apparatus 100 performs the processes of steps S103 to S108.

The information processing apparatus 100 acquires graph information about the product (step S103). For example, the information processing apparatus 100 acquires graph information GR11 related to a product from the graph information storage unit 123.

Then, the information processing apparatus 100 generates a vector from the product data related to one product using the model (step S104). In the example of FIG. 1, the information processing apparatus 100 generates the vector VD11 from the product information GIN 11 by using the model M1 stored in the model information storage unit 124.

Then, the information processing apparatus 100 determines the starting point vector using the generated vector and the index information (step S105). In the example of FIG. 1, the information processing apparatus 100 determines the starting point vector at the node N451 by using the vector VD11 and the index information IND11 stored in the index information storage unit 122.

Then, the information processing apparatus 100 extracts a similar product of one product by searching the graph information (step S106). In the example of FIG. 1, the information processing apparatus 100 extracts the node N451 and the node N35 as similar products by searching the graph information GR11 starting from the node N451.

Then, the information processing apparatus 100 determines a recommended product based on the similar product (step S107). In the example of FIG. 1, the information processing apparatus 100 determines the product # 451 corresponding to the node N451 most similar to the vector of the product X as the recommended product.

Then, the information processing apparatus 100 transmits the recommended information indicating the recommended product to the IoT device (step S108). In the example of FIG. 1, the information processing apparatus 100 provides the information indicating the product # 451 corresponding to the node N451 as recommended information to the IoT device 10 (TID11) which is a refrigerator used by the user U1.

On the other hand, when the information processing apparatus 100 has one product in stock (step S102: Yes), the information processing apparatus 100 processes an order for one product (step S109). For example, the information processing apparatus 100 uses the user's account information or the like to perform payment processing for one product, or performs a procedure for delivering one product to an address designated by the user.

[5. Generation process flow]
Next, the procedure of the generation process by the information processing system 1 according to the embodiment will be described with reference to FIG. FIG. 11 is a flowchart showing an example of the generation process according to the embodiment.

As shown in FIG. 11, the information processing apparatus 100 acquires learning data (step S201). For example, the information processing apparatus 100 acquires learning data from the product information storage unit 121. For example, the information processing apparatus 100 acquires product information GIN1, GIN2, etc. as learning data from the product information storage unit 121.

After that, the information processing apparatus 100 generates a model based on the learning data (step S202). For example, the information processing apparatus 100 generates a model M1 from the product information storage unit 121 using the learning data. For example, the information processing apparatus 100 generates the model M1 so as to output the same information (product data) as the information (product data) input to the input layer from the output layer. For example, the information processing apparatus 100 generates a model M1 as an autoencoder that inputs product data of a product.

[6. Search example]
Here, an example of a search using the graph information described above is shown. The search using graph information (graph data) is not limited to the following, and may be performed by various procedures. This point will be described with reference to FIG. 13 as an example. FIG. 13 is a flowchart showing an example of a search process using graph information. In addition, the objects referred to below may be read as vectors and nodes. In the following description, it is assumed that the information processing apparatus 100 performs the search process, but the search process may be performed by another device. For example, the information processing apparatus 100 uses vector data generated from product data of one product as a search query. For example, the information processing apparatus 100 searches graph data starting from a starting point vector determined based on vector data generated from product data of one product and index information. In the example of FIG. 1, the information processing apparatus 100 searches for graph information GR11 starting from node N451, which is a starting point vector determined based on the vector VD11 of the product X and the index information IND11.

Here, the neighborhood object set N (G, y) is a set of neighborhood objects associated with the edge assigned to the node y. “G” may be predetermined graph data (for example, graph information GR11 or the like). For example, the information processing apparatus 100 executes the k-nearest neighbor search process.

For example, the information processing apparatus 100 sets the radius r of the hypersphere to ∞ (infinity) (step S300), and extracts the subset S from the existing object set (step S301). For example, the information processing apparatus 100 may extract an object (node) selected as a root node (starting point vector) as a subset S. In the example of FIG. 1, the information processing apparatus 100 may extract the node N451 or the like, which is a starting point vector, as a subset S. Further, for example, a hypersphere is a virtual sphere indicating a search range. The objects included in the object set S extracted in step S301 are also included in the initial set of the object set R of the search results at the same time.

Next, the information processing apparatus 100 extracts the object having the shortest distance from the object y from the objects included in the object set S, where y is the search query object, and sets it as the object s (step S302). In the example of FIG. 1, the information processing apparatus 100 extracts an object having the shortest distance from the vector VD11, which is a search query object, among the objects included in the object set S, and uses them as objects s. For example, the information processing apparatus 100 extracts the node N451 having the shortest distance from the vector VD11 among the objects included in the object set S, and uses it as the object s. For example, in the information processing apparatus 100, when only the object (node) selected as the root node (starting point vector) is an element of the object set S, the root node (starting point vector) is extracted as the object s as a result. .. Next, the information processing apparatus 100 excludes the objects s from the object set S (step S303).

Next, the information processing apparatus 100 determines whether or not the distance d (s, y) between the object s and the object y exceeds r (1 + ε) (step S304). Here, ε is an extension element, and r (1 + ε) is a value indicating the radius of the search range (searching only the nodes within this range. The accuracy can be improved by making it larger than the search range). be. When the distance d (s, y) between the object s and the object y exceeds r (1 + ε) (step S304: Yes), the information processing apparatus 100 outputs the object set R as a neighborhood object set of the object y (step). S305), the process is terminated.

When the distance d (s, y) between the object s and the search query object y does not exceed r (1 + ε) (step S304: No), the information processing apparatus 100 determines the neighborhood object set N (G, s) of the objects s. One object not included in the object set C is selected from the objects that are the elements of the above, and the selected object u is stored in the object set C (step S306). The object set C is provided for convenience in order to avoid duplicate search, and is set to an empty set at the start of processing.

Next, the information processing apparatus 100 determines whether or not the distance d (u, y) between the object u and the object y is r (1 + ε) or less (step S307). When the distance d (u, y) between the object u and the object y is r (1 + ε) or less (step S307: Yes), the information processing apparatus 100 adds the object u to the object set S (step S308).

Next, the information processing apparatus 100 determines whether or not the distance d (u, y) between the object u and the object y is r or less (step S309). When the distance d (u, y) between the object u and the object y exceeds r (step S309: No), the information processing apparatus 100 determines (processes) step S315.

When the distance d (u, y) between the object u and the object y is r or less (step S309: Yes), the information processing apparatus 100 adds the object u to the object set R (step S310). Then, the information processing apparatus 100 determines whether or not the number of objects included in the object set R exceeds ks (step S311). The predetermined number ks is an arbitrarily determined natural number. For example, various settings such as ks = 2 and ks = 10 may be used.

When the number of objects included in the object set R exceeds ks (step S311: Yes), the information processing apparatus 100 selects the object having the longest distance (far) from the object y among the objects included in the object set R. Exclude from the object set R (step S312).

Next, the information processing apparatus 100 determines whether or not the number of objects included in the object set R matches ks (step S313). When the number of objects included in the object set R matches ks (step S313: Yes), the information processing apparatus 100 determines that the object included in the object set R has the longest distance (far) from the object y. , The distance to the object y is set to a new r (step S314).

Then, the information processing apparatus 100 selects all the objects from the objects that are the elements of the object set N (G, s) in the vicinity of the objects s, and determines whether or not the objects have been stored in the object set C (step S315). .. When all the objects have been selected from the objects which are the elements of the object set N (G, s) in the vicinity of the objects and stored in the object set C (step S315: No), the information processing apparatus 100 has step S306. Return to and repeat the process.

When all the objects are selected from the objects that are the elements of the object set N (G, s) in the vicinity of the objects s and stored in the object set C (step S315: Yes), the information processing apparatus 100 sets the object set S. Is an empty set or not (step S316). If the object set S is not an empty set (step S316: No), the information processing apparatus 100 returns to step S302 and repeats the process. When the object set S is an empty set (step S316: Yes), the information processing apparatus 100 outputs the object set R and ends the process (step S317). For example, the information processing apparatus 100 may provide an object (node) included in the object set R to the searched IoT device 10 or the like as a search result corresponding to the search query (input object y). In the example of FIG. 1, the information processing apparatus 100 provides the node N451 and the node N35 included in the object set R to the searched IoT device 10 or the like as a search result corresponding to the search query (vector VD11 of the product X). You may. For example, the information processing apparatus 100 provides information indicating the product # 451 corresponding to the node N451 and the product # 35 corresponding to the node N35 to the IoT device 10 used by the user U1 as information on the product similar to the product X. do.

[7. effect〕
As described above, the information processing apparatus 100 according to the embodiment includes an acquisition unit 131, an extraction unit 134, and a transmission unit 135. The acquisition unit 131 acquires graph information in which a plurality of nodes corresponding to each of the plurality of products are linked according to the similarity of the plurality of products, and order information requesting the purchase of one product. The extraction unit 134 searches for graph information from a plurality of nodes of the graph information acquired by the acquisition unit 131, starting from the starting node that is the starting point for searching the graph information determined based on a predetermined criterion. Therefore, a similar product, which is a product similar to one product, is extracted from a plurality of products. The transmission unit 135 transmits recommended information based on similar products extracted by the extraction unit 134 to a requester requesting the purchase of one product.

As described above, the information processing apparatus 100 according to the embodiment searches for graph information starting from the starting node, and transmits recommended information based on the extracted similar products to the requester requesting the purchase of one product. Therefore, it is possible to recommend an appropriate product.

Further, the information processing apparatus 100 according to the embodiment has a determination unit 133. The determination unit 133 determines the origin node based on the index information used for determining the origin node. The extraction unit 134 extracts similar products from the starting point node determined by the determination unit 133.

As described above, the information processing apparatus 100 according to the embodiment can recommend an appropriate product by determining the starting node based on the index information used for determining the starting node.

Further, in the information processing apparatus 100 according to the embodiment, the determination unit 133 determines the starting node based on the index information of the tree structure type.

As described above, the information processing apparatus 100 according to the embodiment can recommend an appropriate product by determining the starting node based on the index information of the tree structure type.

Further, in the information processing apparatus 100 according to the embodiment, when the graph information includes a node corresponding to one product, the extraction unit 134 extracts similar products from the node as a starting node.

As described above, when the information processing apparatus 100 according to the embodiment includes the node corresponding to one product in the graph information, the node corresponding to the one product is set as the starting node, and the similar product of the one product is used. By extracting the above, similar products can be appropriately extracted.

Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires graph information in which a plurality of vectors indicating the characteristics of each of the plurality of products are concatenated according to the similarity.

As described above, the information processing apparatus 100 according to the embodiment appropriately extracts similar products by acquiring graph information in which a plurality of vectors indicating the characteristics of each of the plurality of products are concatenated according to the similarity. can do.

Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires graph information in which a plurality of vectors indicating the characteristics of each of the plurality of products are concatenated according to the similarity.

As described above, the information processing apparatus 100 according to the embodiment recommends an appropriate product by acquiring graph information in which a plurality of vectors indicating the characteristics of each of the plurality of products are concatenated according to the similarity. be able to.

Further, in the information processing apparatus 100 according to the embodiment, in the acquisition unit 131, a plurality of vectors whose elements are the feature quantities extracted from each of the plurality of products using a predetermined model are connected according to the similarity. Get graph information.

As described above, in the information processing apparatus 100 according to the embodiment, graph information in which a plurality of vectors whose elements are feature quantities extracted from each of a plurality of products using a predetermined model are concatenated according to the similarity. By acquiring, it is possible to make appropriate product recommendations.

Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 inputs information about a plurality of products into a predetermined model, and a plurality of vectors whose elements are the feature quantities of the plurality of products to be extracted. Gets the graph information concatenated according to the similarity.

As described above, in the information processing apparatus 100 according to the embodiment, by inputting information about a plurality of products into a predetermined model, a plurality of vectors whose elements are the feature quantities of the plurality of products to be extracted are similar. Appropriate product recommendations can be made by acquiring graph information linked according to gender.

Further, in the information processing apparatus 100 according to the embodiment, the transmission unit 135 transmits recommended information for urging the purchase of similar products to the requester.

As described above, the information processing apparatus 100 according to the embodiment can recommend an appropriate product by transmitting recommended information prompting the purchase of a similar product to the requester.

Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires order information from a requester which is a predetermined IoT device 10.

As described above, the information processing apparatus 100 according to the embodiment can recommend an appropriate product to the predetermined IoT device 10 by acquiring the order information from the requester which is the predetermined IoT device 10. ..

Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires response information indicating whether or not to purchase a similar product from the requester.

As described above, the information processing apparatus 100 according to the embodiment can acquire the answer to the recommended product from the requester by acquiring the answer information indicating whether or not to purchase the similar product from the requester.

Further, in the information processing apparatus 100 according to the embodiment, the extraction unit 134 extracts a similar product of one product when the product is out of stock.

As described above, the information processing apparatus 100 according to the embodiment extracts a similar product of one product when one product is out of stock, thereby substituting one product when there is no stock of one product. It is possible to make recommendations for appropriate products that can be used.

[8. Hardware configuration]
The information processing apparatus 100 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 14 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) Has 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via the network N and sends it to the CPU 1100, and transmits the data generated by the CPU 1100 to the other device via the network N.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 executes a program or data (for example, model M1 (model data MDT1)) loaded on the RAM 1200. The function of the control unit 130 is realized. The CPU 1100 of the computer 1000 reads and executes these programs or data (for example, model M1 (model data MDT1)) from the recording medium 1800, but as another example, these programs from other devices via the network N. May be obtained.

Although some of the embodiments of the present application have been described in detail with reference to the drawings, these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure line of the invention. It is possible to carry out the present invention in other modified forms.

[9. others〕
Further, among the processes described in the above-described embodiment, all or a part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed can be performed. All or part of it can be done automatically by a known method. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown in the figure.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

In addition, the processes described in the above-described embodiments can be appropriately combined as long as the processing contents do not contradict each other.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition means or an acquisition circuit.

1 Information processing system 100 Information processing device 121 Product information storage unit 122 Index information storage unit 123 Graph information storage unit 124 Model information storage unit 125 Inventory information storage unit 126 User information storage unit 130 Control unit 131 Acquisition unit 132 Generation unit 133 Decision unit 134 Extractor 135 Transmitter 10 IoT device 50 Service provider N Network

Claims (12)

A plurality of nodes corresponding to each of a plurality of products are stored in a refrigerator as an IoT (Internet of Things) device having a communication function and graph information connected according to the similarity of the plurality of products. Obtains order information requesting the purchase of a product that has passed a predetermined period from the date and time when it was stored or whose remaining amount is equal to or less than a predetermined threshold value from the requester of the refrigerator. Acquisition department and
When the product is out of stock , the starting point node, which is the starting point for searching the graph information determined based on a predetermined criterion, is the starting point among the plurality of nodes of the graph information acquired by the acquisition unit. As an extraction unit for extracting similar products that are similar to the one product among the plurality of products by searching the graph information.
A transmission unit that transmits recommended information based on the similar product extracted by the extraction unit to a requester requesting the purchase of the one product, and a transmission unit.
An information processing device characterized by being equipped with. A determination unit that determines the origin node based on the index information used to determine the origin node.
Further prepare
The extraction unit
The information processing apparatus according to claim 1, wherein the similar product is extracted from the starting node determined by the determination unit. The decision-making part
The information processing apparatus according to claim 2, wherein the origin node is determined based on the index information of the tree structure type. The extraction unit
The information processing apparatus according to claim 1, wherein when the graph information includes a node corresponding to the one product, the similar product is extracted with the node as the starting node. The acquisition unit
The invention according to any one of claims 1 to 4, wherein the graph information in which the plurality of nodes are concatenated is acquired according to the similarity of the plurality of vectors corresponding to each of the plurality of products. Information processing device. The acquisition unit
The information processing apparatus according to claim 5, wherein the plurality of vectors showing the characteristics of each of the plurality of products are connected according to the similarity to obtain the graph information. The acquisition unit
5. Claim 5, wherein the plurality of vectors having feature quantities extracted from each of the plurality of products using a predetermined model are concatenated according to the similarity to obtain the graph information. Or the information processing apparatus according to claim 6. The acquisition unit
By inputting information about the plurality of products into a predetermined model, the graph information in which the plurality of vectors whose elements are the feature quantities of the plurality of products to be extracted are concatenated according to the similarity is obtained. The information processing apparatus according to any one of claims 5 to 7, wherein the information processing apparatus is to be acquired. The transmitter is
The information processing apparatus according to any one of claims 1 to 8, wherein the recommended information prompting the purchase of the similar product is transmitted to the requester. The acquisition unit
The information processing apparatus according to any one of claims 1 to 9 , wherein response information indicating whether or not to purchase the similar product is acquired from the requester. It is an information processing method executed by a computer.
A plurality of nodes corresponding to each of a plurality of products are stored in a refrigerator as an IoT (Internet of Things) device having a communication function and graph information connected according to the similarity of the plurality of products. Obtains order information requesting the purchase of a product that has passed a predetermined period from the date and time when it was stored or whose remaining amount is equal to or less than a predetermined threshold from the requester of the refrigerator. Acquisition process and
When the product is out of stock , the starting point node, which is the starting point for searching the graph information determined based on a predetermined criterion, is the starting point among the plurality of nodes of the graph information acquired by the acquisition process. As an extraction step, by searching the graph information, a similar product, which is a product similar to the one product, is extracted from the plurality of products.
A transmission step of transmitting recommended information based on the similar product extracted by the extraction step to a requester requesting the purchase of the one product, and a transmission step.
An information processing method characterized by including. A plurality of nodes corresponding to each of a plurality of products are stored in a refrigerator as an IoT (Internet of Things) device having a communication function and graph information connected according to the similarity of the plurality of products. Obtains order information requesting the purchase of a product that has passed a predetermined period from the date and time when it was stored or whose remaining amount is equal to or less than a predetermined threshold value from the requester of the refrigerator. Acquisition procedure and
When the product is out of stock, the starting node that is the starting point for searching the graph information determined based on a predetermined criterion among the plurality of nodes of the graph information acquired by the acquisition procedure is the starting point. As an extraction procedure for extracting a similar product that is a product similar to the one product from the plurality of products by searching the graph information.
A transmission procedure for transmitting recommended information based on the similar product extracted by the extraction procedure to a requester requesting the purchase of the one product, and a transmission procedure.
An information processing program characterized by having a computer execute.

Images