JP7760418B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

This application relates to an information processing device, an information processing method, and an information processing program.

Technology for providing information such as advertisements based on user attributes has been known in the past. For example, Patent Document 1 discloses technology for extracting advertisements based on user attributes and delivering the extracted advertisements to users.

Japanese Patent Application Publication No. 11-024603

However, existing technologies have room for improvement in terms of providing appropriate information to users.

This application has been made in light of the above, and aims to provide an information processing device, information processing method, and information processing program that can provide appropriate information to users.

The information processing device according to the present application includes a determination unit and an exclusion unit. The determination unit determines whether the user context of a destination user to whom information to be distributed is to be distributed is similar to the user context when the destination user selected to opt out of the distribution target. If the determination unit determines that the user context of the destination user is similar to the user context when the destination user selected to opt out of the distribution target, the exclusion unit excludes, for a limited period of time, from among the multiple models determining the distribution destination, the model corresponding to the distribution target for which opt-out was selected.

According to one aspect of the embodiment, appropriate information can be provided to the user.

FIG. 1 is a diagram for explaining a process that is a prerequisite for information processing according to the embodiment. FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. FIG. 3 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. FIG. 4 is a diagram illustrating an example of the configuration of a terminal device according to the embodiment. FIG. 5 is a diagram illustrating an example of the configuration of an information processing apparatus according to the embodiment. FIG. 6 is a diagram illustrating an example of attribute information according to the embodiment. FIG. 7 is a diagram illustrating an example of model information according to the embodiment. FIG. 8 is a diagram illustrating an example of opt-out user information according to the embodiment. FIG. 9 is a diagram illustrating an example of history information according to the embodiment. FIG. 10 is a diagram illustrating an example of user context information according to the embodiment. FIG. 11 is a flowchart illustrating an example of a processing procedure executed by the information processing apparatus according to the embodiment. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing apparatus according to the embodiment.

Below, detailed explanations are given of modes for implementing the information processing device, information processing method, and information processing program (hereinafter referred to as "embodiments") according to the present application, with reference to the drawings. Note that the information processing device, information processing method, and information processing program according to the present application are not limited to the multiple embodiments described below. Furthermore, the multiple embodiments described below can be combined as appropriate to the extent that the processing content is not contradictory. Furthermore, the same components in the multiple embodiments described below will be assigned the same reference numerals, and redundant explanations will be omitted.

[1. Overview of information processing]
(1-1. Prerequisite processing)
An outline of the process that is a prerequisite for the information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram for explaining the process that is a prerequisite for the information processing according to the embodiment.

As shown in Fig. 1, an information processing apparatus 100 according to an embodiment transmits and receives information to and from terminal devices ₂₁ , ₂₂ , ..., _2m used by users _U1 , _U2 , ..., _Um . In the case shown in Fig. 1, m is, for example, an integer equal to or greater than 3. Hereinafter, when referring to each of users _U1 , _U2 , ..., _Um without distinguishing them individually, they may be collectively referred to as user U. Furthermore, below, when referring to each of terminal devices ₂₁ , ₂₂ , ..., _2m without distinguishing them individually, they may be collectively referred to as terminal devices 2.

The information processing device 100 distributes distribution information _D1 , _D2 , _D3 , _D4 , _D5 , ..., _Dk, which is information to be distributed, to a user U. In the case shown in FIG. 1 , k is, for example, an integer equal to or greater than 6. The distribution information _D1 , _D2 , _D3 , _D4 , _D5 , ..., _Dk is distributed to the user U, for example, by distributing the distribution information _D1 , _D2 , _D3 , D4, _D5 , ..., _Dk to the terminal device 2 of the user U. Hereinafter, when the distribution information _D1 , _D2 , _D3 , _D4 , _D5 , ..., _Dk is referred to individually without distinction, _they may be collectively referred to as distribution information D.

Distribution information D is information displayed on the terminal device 2. For example, distribution information D includes at least one of text information and image information. Image information corresponds to still image information, animation information, video information, etc.

The information processing device 100 distributes distribution information D using a plurality of models _M1 , _M2 , _M3 , _M4 , ..., _Mn that determine the distribution destinations of distribution information D, which is information to be distributed. In the case shown in Fig. 1, n is, for example, an integer equal to or greater than 5. The plurality of models _M1 , _M2 , _M3 , _M4 , ..., _Mn are models that each determine whether or not a user U is interested in information of targets _T1 , _T2 , _T3 , _T4 , ..., _Tn .

Model _M1 is a model corresponding to target _T1 . Model _M1 determines whether a user U who is interested in the information of target _T1 is also interested in distribution information D. Model _M2 is a model corresponding to target T2. Model _M2 determines whether a user U who is interested in the information of target _T2 is also interested in distribution information D. Model M3 is a model corresponding to target _T3 . Model _M3 determines whether a user U who is interested in the information of target _T3 is also interested in distribution information D. Model _M4 is a model corresponding to target _T4 . Model _M4 determines whether a user U who is interested in the information of _{target T4 is also interested in distribution information D. Model Mn is a model corresponding to target Tn. Model Mn determines whether a user U} who is interested in the information of target _Tn is also interested in distribution information D. In the following, when objects _T1 , _T2 , _T3 , _T4 , ..., _Tn are referred to without being individually distinguished, they may be collectively referred to as object T. Furthermore, in the following, when models _M1 , _M2 , _M3 , _M4 , ..., _Mn are referred to without being individually distinguished, they may be collectively referred to as model M.

When the information provided by the information processing device 100 is news content, the target T may be, for example, politics, economics, international affairs, business, entertainment, sports, hobbies, or society. The target T may also be a more specific subset of these. For example, the target T may be a more specific subset of hobbies, such as cars, bicycles, motorbikes, movies, music, camping, or travel. The information provided by the information processing device 100 may also be advertising content instead of or in addition to news content, or may be content other than news content and advertising content.

Model M is a learning model that receives distribution information D as input and outputs a score indicating the degree to which user U is interested in distribution information D. For example, when information about target _T1 is input to model _M1 , the score output from model _M1 is higher than when information about target _T2 is input to model _M1 . Also, when information about target _T2 is input to model _M2 , the score output from model _M2 is higher than when information about target _T1 is input to model _M2 .

The model M is generated for each target T by machine learning using, for example, a dataset including information to be distributed and information indicating whether a user U who has an interest in the target T has an interest in the information to be distributed. For example, the model _M1 is generated by machine learning using a dataset including information to be distributed and information indicating whether a user U who has an interest in the target _T1 has an interest in the information to be distributed.

Model M can be generated by machine learning using a neural network such as a convolutional neural network or a recurrent neural network. However, without being limited to such examples, model M may also be generated using machine learning using a learning algorithm such as linear regression or logistic regression instead of a neural network.

When distributing distribution information D, the information processing device 100 inputs the distribution information D to each of the models _M1 , _M2 , _M3 , _M4 , ..., _Mn , and distributes the distribution information D to a user U associated with a model among the models _M1 , _M2 , _M3 , _M4 , ..., _Mn whose output score satisfies a preset distribution condition. The preset distribution condition may be, for example, a model among the models _M1 , _M2 , _M3 , _M4 , ..., _Mn whose output score is the highest or a model whose output score is equal to or greater than a preset threshold.

Here, assume that models _M1 , _M2 , _M3 , _M4 , and _M5 are associated with user _U1 , and that distribution information _D1 is information on target _T1 , distribution information _D2 is information on target _T2 , distribution information _D3 is information on target _T3 , and distribution information _D4 is information on target _T4 . Also, although not shown in FIG. 1, distribution information _D5 is information on target _T5 .

In this case, the information processing device 100 uses the models _M1 , _M2 , _M3 , _M4 , and _M5 to determine the user _U1 as one of the destinations of the distribution information _D1 , _D2 , _D3 , _D4 , and _D5 , and distributes the distribution information _D1 , _D2 , _D3 , _D4 , and _D5 to the user _U1 (step S1). In the example shown in Figure 1, the distribution of the distribution information _D1 , _D2 , _D3 , _D4 , and _D5 to the user _U1 is performed by distributing the distribution information _D1 , _D2 , _D3 , _D4 , and _D5 to the terminal device ₂₁ .

If user _U1 , who has received distribution information _D1 , _D2 , _D3 , _D4 , _{and D5,} determines that distribution of distribution information _D1 is undesirable among the distribution information _D1 , _D2 , _D3 , _D4 , and _D5 , he or she selects opt-out for model _M1 (step S2). User _U1 's selection of opt-out for model _M1 indicates user _U1 's intention to refuse notification of information distributed using model _M1 , and is performed, for example, by user _U1 operating an operation unit (e.g., operation unit 12) provided on terminal device _21. Opting out for model _M1 can also be said to be opt-out for target _T1 corresponding to model _M1 .

When the user _U1 selects opt-out for the model _M1 , opt-out information indicating that the user U1 has selected opt-out for the model _M1 is transmitted from the terminal device ₂₁ to the information processing device 100 (step S3).

On the other hand, when the information processing device 100 receives the opt-out information from the terminal device ₂₁ , it accepts the target _T1 corresponding to the model _M1 as an opt-out target and excludes and registers the user _U1 from the model _M1 (step S4). The information processing device 100 excludes and registers the user _U1 from the model _M1 , for example, by canceling the association of the model _M1 with the user _U1 .

Thereafter, the information processing device 100 starts distributing information of the plurality of distribution targets excluding the target _T1 who is the opt-out target to the user _U1 (step S5). In step S5, the information processing device 100 stops distributing information using the model _M1 , thereby distributing information of the plurality of distribution targets excluding the target _T1 who is the opt-out target to the user _U1 .

Furthermore, when the timing for recommending cancellation of the opt-out for the model _M1 arrives, the information processing device 100 generates recommendation information recommending cancellation of the opt-out for the opt-out target (step S6).Then, the information processing device 100 delivers the generated recommendation information to the terminal device ₂₁ , thereby distributing the recommendation information to the user _U1 (step S7).

When the terminal device _2.1 receives the recommendation information from the information processing device 100, it displays the recommendation information (step S8). The recommendation information displayed on the terminal device _2.1 includes distribution information D that would be distributed if the opt-out target does not opt out. In the example shown in FIG. 1, if the opt-out target is entertainment and the opt-out target does not opt out, the recommendation information includes information such as "Is actress A getting married?", "Is screenwriter C collapsed from overwork?", and "New drama B will start in September."

The recommendation information is information that includes information delivered from the information processing device 100 to the user _U1 before the user _U1 selects opt-out of the opt-out target, or information that would be delivered from the information processing device 100 to the user _U1 if the user _U1 has not selected opt-out of the opt-out target.

Therefore, by referring to the recommendation information, user _U1 can understand the distribution information D that would be distributed if the opt-out target does not opt out. Therefore, user _U1 can appropriately decide whether to cancel the opt-out of the opt-out target. In this way, the information processing device 100 can inform user U of the benefits of canceling the opt-out of the opt-out target, and can provide user U with appropriate information.

Note that the information to be distributed is not limited to information about target T using model M. For example, the information to be distributed may be store information, where information about each store is the information to be distributed. Even in this case, the information processing device 100 can inform user U of the benefits of canceling the opt-out of the opt-out target, and can provide appropriate information to user U.

(1-2. An example of information processing)
An overview of information processing according to an embodiment will be described below with reference to FIG. 2. FIG. 2 is a diagram for explaining an example of information processing according to an embodiment. The information processing according to the embodiment is mainly characterized in that a model corresponding to an opt-out target is automatically opted out based on a user context. Note that FIG. 2 describes an example of information processing executed by the information processing device 100 based on the user context of user _U1 .

2, the information processing device 100 has user context information J corresponding to a user U. The user context information J stores, for each target T indicating each distribution target, information indicating the user context when a distribution destination user (e.g., user U ₁ ) selected opt-out (when opt-out information was accepted), for each user U.

For example, the information processing device 100 can record user information about the destination user when the destination user selects opt-out, and use a reference vector obtained by vectorizing the recorded user information as user context information. In this case, the information processing device 100 prepares a training dataset that associates user information about the destination user when the destination user selects opt-out with label information indicating the opt-out target, for each target T (opt-out target) indicating a target of distribution corresponding to model M for which opt-out has been selected, and uses the prepared training dataset to train a vector output model that outputs vector information corresponding to the user information.

For example, when the opt-out target is the same, the information processing device 100 generates a vector output model by optimizing the parameters of the learning model so that a determination target vector obtained by vectorizing user information is similar to a reference vector corresponding to the opt-out target. As a specific example, when the opt-out target is target _T1 , the parameters of the learning model are optimized so that a determination target vector obtained by vectorizing user information and a reference vector corresponding to target _T1 are similar to each other.

When the information processing device 100 uses an arbitrary network such as a neural network as a training model, it performs a training process to adjust the values of parameters (connection coefficients), which are weights taken into account when propagating scores (values) between nodes in each layer of the neural network. For example, the information processing device 100 uses an arbitrary method such as backpropagation to optimize (correct) the parameters (connection coefficients) to reduce the error between the output from the training model and the correct answer (correct data) corresponding to the input. In other words, the information processing device 100 optimizes the parameters (connection coefficients) so that the cosine similarity between the target vector and the reference vector increases when the target T is the same, and decreases when the target T is different. When the information processing device 100 uses the backpropagation method, it performs a training process to minimize a predetermined loss function, thereby correcting the parameters (connection coefficients) to reduce the error between the output from the training model and the correct answer (correct data) corresponding to the input.

In addition, the information processing device 100 may create a group consisting of multiple users with attributes similar to those of the target user, prepare a training dataset using information about each user included in the created group, and train the above-mentioned vector output model. This makes it possible to train the vector output model even if the amount of information recorded about the target user is insufficient to serve as training data.

The information processing device 100, which has the user context information J described above, determines, for example, at a predetermined timing when determining the destination of the distribution information D, whether the user context of the destination user to whom the information to be distributed is to be distributed is similar to the user context when the destination user selected to opt out of the distribution target (step S21).

For example, the information processing device 100 generates a determination target vector by vectorizing the user information of the destination user determined as the destination by the model M. The information processing device 100 also determines whether the determination target vector obtained by vectorizing the user information is similar to the reference vector corresponding to each target T.

Next, when the information processing device 100 determines that the user context of the distribution destination user is similar to the user context when opting out of the distribution target is selected, it excludes, from among the multiple models M that determine the distribution destination of the information to be distributed, the model M corresponding to the distribution target for which opt-out was selected from the targets for use for a limited period of time (step S22). For example, the information processing device 100 sets the target T corresponding to the reference vector determined to be similar to the target vector as the opt-out target, and performs exclusion registration of the model M corresponding to the target T. Then, when model _M1 is the target for exclusion, the information processing device 100 cancels the association of the excluded model _M1 with user _U1 .

Then, the information processing device 100 starts distributing information of the plurality of distribution targets that reflects the exclusion in step S22 to the distribution destination user (e.g., user _U1 ) determined as the distribution destination by model M (step _{S23). For example, the information processing device 100 cancels the association of model M1, which is the excluded target, with user U1, thereby stopping the distribution of distribution information using model M1 to user U1} . In this way, the information processing device 100 can automatically stop the distribution of information of distribution targets that are likely not desired by the distribution destination user, and can provide appropriate information to user _U1 .

In addition, the information processing device 100 may exclude the model M from being available for a period specified by the user U. For example, the information processing device 100 may accept a specification of an exclusion period from the user U in advance for each target T indicating a distribution target, and manage the exclusion period in association with the model M corresponding to the target T. In addition, the information processing device 100 may exclude the model M from being available for a predetermined period of time determined in advance for each target T.

In addition, the information processing device 100 may notify the user U at a predetermined timing to inquire whether or not to cancel the exclusion of model M, and may cancel the exclusion of model M in response to a request from the user U. For example, the predetermined timing may be when the exclusion period for model M has expired.

Furthermore, after model M is excluded, the information processing device 100 may determine, at a predetermined timing, whether the user context (e.g., the determination target vector) of the destination user (e.g., user U) is similar to the user context (e.g., the reference vector) when the destination user selected to opt out of the distribution target. If the information processing device 100 determines that the destination user's user context is not similar to the user context when the destination user selected to opt out of the distribution target, it may notify the destination user of an inquiry about whether to cancel the exclusion of model M, and may cancel the exclusion of the model in response to a request from the destination user. This makes it possible to, for example, control the device so that cancellation of the opt-out is postponed depending on the user's status even if the exclusion period for model M has expired.

2. Configuration of Information Processing System 1
The configuration of the information processing system according to the embodiment will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the information processing system according to the embodiment. As shown in Fig. 3, the information processing system 1 according to the embodiment includes terminal devices 2 ₁ , 2 ₂ , ..., 2 _m , and an information processing device 100.

The terminal device 2 and the information processing device 100 are each connected to a network N. The terminal device 2 can send and receive information to and from the information processing device 100 via the network N. The information processing device 100 can send and receive information to and from the terminal device 2 via the network N.

The network N is a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), a telephone network (such as a mobile phone network or a landline network), a regional IP (Internet Protocol) network, or the Internet. The network N may include a wired network or a wireless network.

Terminal device 2 is a communication terminal used by user U. A typical example of terminal device 2 is a smartphone, but it may also be realized as a tablet terminal, notebook PC (Personal Computer), desktop PC, mobile phone, PDA (Personal Digital Assistant), etc.

In addition, the terminal device 2 can display information for using various services provided by the information processing device 100 using a web browser or application. At this time, when the terminal device 2 receives control information from the information processing device 100 for realizing information display processing using a web browser, application, or the like, it performs the display processing in accordance with the received control information.

The information processing device 100 is an information processing terminal that executes information processing according to the embodiment. A typical example of the information processing device 100 is a server device, but it may also be implemented as a mainframe, workstation, or the like. When the information processing device 100 is implemented as a server device, it may be implemented as a single server, or as a cloud system in which multiple server devices and multiple storage devices operate in cooperation with each other.

The information processing device 100 may also function as a distribution device that distributes control information to terminal devices 2 used by users of various services. Here, the control information is written in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). Note that the application itself distributed from the information processing device 100 may also be considered to be control information.

The various services provided by the information processing device 100 may also include API (Application Programming Interface) services corresponding to various applications, as well as various online services. The various online services may include Q&A services, Internet connections, search services, SNS (Social Networking Services), e-commerce services, electronic payment services, online games, online banking services, online trading services, hotel reservation services, ticket reservation services, video distribution services, music distribution services, news distribution services, map information services, route search services, route guidance services, line information services, operation information services, and weather information services.

The information processing device 100 may also function as a device that distributes advertising content. In this case, the information processing device 100 manages advertising content submitted by advertisers and also manages information related to advertising bids set by the advertisers. For example, the information processing device 100 displays advertising content submitted by advertisers in advertising spaces provided on web pages of various services provided in response to user requests.

3. Configuration of Terminal Device 2
An example of the configuration of the terminal device 2 according to the embodiment will be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the configuration of the terminal device according to the embodiment. As shown in Fig. 4, the terminal device 2 includes a communication unit 10, a display unit 11, an operation unit 12, a sensor group 13, a storage unit 14, and a processing unit 15.

(Communication unit 10)
The communication unit 10 is realized by, for example, a network interface card (NIC). The communication unit 10 is connected to a network N via a wired or wireless connection. The communication unit 10 transmits and receives information to and from the information processing device 100 via the network N.

(Display section 11)
The display unit 11 is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display.

(Operation unit 12)
The operation unit 12 includes, for example, a keyboard including keys for inputting letters, numbers, and spaces, an enter key, arrow keys, etc., a mouse, a power button, etc. When the display unit 11 is a display device with a touch panel display, the operation unit 12 may be a touch panel.

(Sensor group 13)
The sensor group 13 includes, for example, an acceleration sensor, a gyro sensor, a geomagnetic sensor, an illuminance sensor, and an image sensor. The acceleration sensor is a sensor that detects the acceleration of the terminal device 2. The gyro sensor is a sensor that detects the attitude of the terminal device 2, such as the tilt and rotation. The geomagnetic sensor is a sensor that detects geomagnetism. The illuminance sensor is a sensor that detects illuminance that indicates the brightness of the surroundings of the terminal device 2, and the image sensor is a sensor that captures images of the surroundings of the terminal device 2.

(Storage unit 14)
The storage unit 14 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk.

The memory unit 14 stores, for example, information acquired by the processing unit 15 via the network N and the communication unit 10, and detection information, which is information detected by the sensor group 13.

(Processing unit 15)
The processing unit 15 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) by executing various programs stored in a storage device inside the terminal device 2 using RAM as a working area.

(Information acquisition unit 16)
The information acquisition unit 16 acquires information transmitted from the information processing device 100 and received by the communication unit 10 via the network N. For example, the information transmitted from the information processing device 100 is distribution information D or the like.

(Display processing unit 17)
The display processing unit 17 displays the information acquired by the information acquisition unit 16 on the display unit 11. For example, the display processing unit 17 displays a screen including the distribution information D acquired by the information acquisition unit 16 on the display unit 11.

(Output unit 18)
The output unit 18 transmits, for example, operation information, which is information corresponding to an operation performed by the user U on the operation unit 12 , to the information processing device 100 via the communication unit 10 .

For example, when user U selects opt-out by operating operation unit 12, output unit 18 transmits opt-out information to information processing device 100 via communication unit 10. The opt-out information includes identification information unique to the distribution target, model M, or distribution information D for which opt-out has been selected.

In addition, the output unit 18 transmits detection information, which is information detected by the sensor group 13, to the information processing device 100 via the communication unit 10.

[4. Configuration of information processing device 100]
An example of the configuration of the information processing device 100 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of the configuration of the information processing device according to the embodiment. As shown in Fig. 5, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

(Regarding the communication unit 110)
The communication unit 110 is realized by, for example, a network interface card (NIC). The communication unit 110 is connected to a network N by wire or wirelessly. The information processing device 100 transmits and receives information to and from the terminal device 10 via the network N.

(Regarding the storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 has an attribute information storage unit 121, a model information storage unit 122, a distribution information storage unit 123, an opt-out user information storage unit 124, a history information storage unit 125, and a user context information storage unit 126.

(Attribute information storage unit 121)
The attribute information storage unit 121 stores attribute information indicating attributes of the user U. Fig. 6 is a diagram showing an example of attribute information according to the embodiment.

As shown in FIG. 6, the attribute information stored in the attribute information storage unit 121 has multiple items, such as a "user ID" item and an "attribute" item. These items in the attribute information are associated with each other.

The "User ID" field stores identification information (user ID) for identifying user U. The "Attributes" field stores information indicating the user's attributes, such as demographic attributes and psychographic attributes. Demographic attributes are demographic attributes of user U, such as gender, age, address, occupation, or annual income. Psychographic attributes are attributes that indicate user U's values, lifestyle, personality, preferences, etc.

(Model information storage unit 122)
The model information storage unit 122 stores model information including information on the model M. Fig. 7 is a diagram illustrating an example of model information according to the embodiment.

As shown in Figure 7, the model information stored in the model information storage unit 122 has multiple items, such as a "model ID" item, a "model" item, and a "user list" item. These items in the model information are associated with each other.

The "Model ID" item stores identification information (model ID) for identifying the model.

The "Model" field stores information about the model M that determines the distribution destination of the distribution information D. The model M may be an interest model that determines whether the user U is interested in the distribution information D, or a user context model that determines whether the user U's context is a context defined by the model. For example, the user context model inputs detected information sent from the terminal device 2 and determines whether the user U's context is a context defined by the model. For example, various user contexts such as "bought a PC (Personal Computer)," "visited store Z," or "cooking food" are possible contexts defined by the model. The "Model" field may also store information about a model that vectorizes the user U's user context.

The "User List" item stores a list of users U associated with model M.

(Distribution information storage unit 123)
The distribution information storage unit 123 stores distribution information D, which is information distributed to the user U. The distribution information D is web content such as news or information provided to the user U by email, and may include advertising content. When the distribution information D is web content such as news, the distribution information D is displayed on a timeline on the terminal device 2, but the distribution information D is not limited to information displayed on a timeline on the terminal device 2.

(Opt-out user information storage unit 124)
The opt-out user information storage unit 124 stores opt-out user information including the user ID of a user U who has been set to opt out for each model M. Fig. 8 is a diagram illustrating an example of opt-out user information according to the embodiment.

As shown in Figure 8, the opt-out user information stored in the opt-out user information storage unit 124 has multiple items, such as a "model ID" item and an "opt-out user list" item. These items in the opt-out user information are associated with each other.

The "Model ID" item stores identification information (model ID) for identifying the model.

The "Opt-out User List" item stores a list of users U who have selected to opt out of model M. The list of users U consists of the user IDs of each user U who has selected to opt out of model M.

The opt-out user information storage unit 124 may store information indicating the opt-out period in association with the user ID for which opt-out has been set. The opt-out period may be set by the user U, or may be arbitrarily determined by the information processing device 100 for each model M.

(History information storage unit 125)
The history information storage unit 125 stores various information related to history information (log data) indicating the behavior of the user U. Fig. 9 is a diagram showing an example of history information according to an embodiment. In the example shown in Fig. 9, the history information stored in the history information storage unit 125 has multiple items such as a "user ID" item, a "location history" item, a "search history" item, a "browsing history" item, a "purchase history" item, and a "posting history" item. These items are associated with each other.

Note that Figure 9 shows an example of history information according to an embodiment, and the history information may include various types of information other than that shown in Figure 9 depending on the purpose. For example, the history information may include user U's usage history of a specified service. The history information may also include user U's store visit history or facility visit history. The history information may also include user U's payment history (electronic payment) using the terminal device 2. Also, Figure 9 shows an example in which conceptual information is displayed for multiple items in the history information, but in reality, specific information such as numerical values or character strings corresponding to each item is stored.

The "User ID" field stores identification information for identifying user U. The "Location History" field stores information indicating the location history, which is the history of user U's locations and movements. The "Search History" field stores information indicating the search history, which is the history of search queries entered by user U. The "Browsing History" field stores information indicating the browsing history, which is the history of content viewed by user U. The "Purchase History" field stores information indicating the purchase history, which is the history of purchases made by user U. The "Posting History" field stores information indicating the posting history, which is the history of posts made by user U.

Figure 9 shows that user U, identified by user ID: "UA111," moved as shown in "Location History R1-1," searched as shown in "Search History #1," viewed content as shown in "Browse History #1," purchased specific products at specific stores as shown in "Purchase History #1," and posted as shown in "Post History."

(User context information storage unit 126)
The user context information storage unit 126 stores, for each user U, user context information indicating the user context when the user U selected opt-out for a target T indicating a delivery target. Fig. 10 is a diagram illustrating an example of user context information according to the embodiment.

As shown in FIG. 10, the user context information stored in the user context information storage unit 126 has multiple items, such as a "user ID" item and a "context information" item. These items in the user context information are associated with each other.

The "User ID" field stores identification information for identifying user U. The "Context Information" field stores, for each target T indicating a distribution target, user context information indicating the user context when user U selected opt-out. User context information corresponds, for example, to vector information obtained by vectorizing information about the user when user U selected opt-out. Information about the user corresponds, for example, to detection information and history information transmitted from terminal device 2 to information processing device 100. Information processing device 100 can generate user context information using a model that inputs detection information and history information, which are information about the user, and outputs vectors corresponding to the detection information and history information.

In addition, the user context information storage unit 126 may store information indicating the opt-out period in association with the user ID.

(Regarding the control unit 130)
The control unit 130 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like executing various programs stored in a storage device inside the information processing device 100 using RAM as a work area. The control unit 130 is also realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

For example, the control unit 130 transmits and receives information to and from the terminal device 2 based on information received by the communication unit 20 and information stored in the memory unit 21. As shown in FIG. 5, the control unit 130 has an acquisition unit 131, a distribution unit 132, a reception unit 133, a recommendation unit 134, a determination unit 135, and an exclusion unit 136, and realizes or executes the information processing functions and actions described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 5, and may be other configurations as long as they perform the information processing described below. Furthermore, the connection relationships between the processing units in the control unit 130 are not limited to the connection relationships shown in FIG. 5, and may be other connection relationships.

(Acquisition unit 131)
When the communication unit 110 receives information transmitted from the terminal device 2 via the network N, the acquisition unit 131 acquires the information transmitted from the terminal device 2 from the communication unit 110. For example, the information transmitted from the terminal device 2 includes operation information, which is information corresponding to an operation performed on the operation unit 12 by the user U, and detection information, which is information detected by the sensor group 13. Furthermore, for example, the operation information includes opt-out information.

(Distribution unit 132)
The distribution unit 132 distributes the distribution information D to the user U by using multiple models M that determine the distribution destination of the information to be distributed and transmitting the distribution information D to the terminal device 2 via the communication unit 20 and the network N.

Furthermore, when model M is an interest model, the distribution unit 132 inputs distribution information D to multiple models M, determines a user U associated with a model M that satisfies preset distribution conditions among the multiple models M as a distribution destination of the distribution information D, and distributes the distribution information D to the determined destination user U. An example of a preset distribution condition is, but is not limited to, a condition in which distribution information D is input and the highest score is output, and that score is equal to or greater than a preset threshold.

Furthermore, when model M is a user context model, the distribution unit 132 inputs the detection information acquired by the acquisition unit 131 into each user context model and determines, from the scores output by each user context model, a user context model that satisfies a preset distribution condition. An example of the preset distribution condition is, but is not limited to, a condition that the score output from the user context model is equal to or greater than a preset threshold. Furthermore, distribution information D is associated with each user context model. The distribution unit 132 distributes distribution information D associated with a user context model that outputs a score equal to or greater than a preset threshold to user U, who is the sender of the detection information.

Furthermore, when the exclusion unit 136 excludes a model M, the distribution unit 132 determines the user U to whom the model M will be distributed using the model M that remains after the exclusion is reflected.

(Reception unit 133)
The reception unit 133 receives, as an opt-out target, a distribution target for which the user U has selected opt-out. The opt-out target is a target T indicating a distribution target. The reception unit 133 acquires, from the communication unit 110 via the network N, the opt-out information received by the communication unit 110 as information on the opt-out target.

In addition, the reception unit 133 updates the model information stored in the model information storage unit 122 or the opt-out user information stored in the opt-out user information storage unit 124 based on the opt-out information acquired from the communication unit 110. The opt-out information is opt-out information for model M.

For example, when the reception unit 133 receives opt-out information from the user _U1 regarding the model _M1 , it changes the state in the model information storage unit 122 in which the user ID of the user _U1 is associated with the model _M1 to a state in which it is not associated with the model M1. Furthermore, when the reception unit 133 receives opt-out information from the user _U1 regarding the model _M1 , it associates the user ID of the user _U1 with the target model for the model _M1 in the opt-out user information storage unit 124.

The reception unit 133 also acquires, via the network N, an opt-out cancellation request received by the communication unit 110 from the communication unit 110. For example, the reception unit 133 updates the model information stored in the model information storage unit 122 or the opt-out user information stored in the opt-out user information storage unit 124.

(Recommendation unit 134)
The recommendation unit 134 notifies the opt-out user of recommendation information recommending cancellation of opt-out for the opt-out target after the distribution unit 132 starts distribution of information of multiple distribution targets excluding the opt-out target to the opt-out user. The opt-out target is a distribution target for which opt-out has been selected by the opt-out user, for example, target T.

Recommendation information is, for example, information that notifies the opt-out user of the benefits of canceling the opt-out of the opt-out target. This can encourage the opt-out user to cancel the opt-out. Furthermore, recommendation information includes information that is delivered to the opt-out user from the delivery unit 132 when the opt-out user does not select opt-out of the opt-out target. This allows the opt-out user to easily understand the benefits of canceling the opt-out of the opt-out target.

(Determination unit 135)
The determination unit 135 determines whether the user context of a delivery destination user to whom information to be delivered is to be delivered is similar to the user context when the delivery destination user selected to opt out of the delivery target. For example, at a predetermined timing when determining the delivery destination of the delivery information D, the determination unit 135 determines whether the user context of the delivery destination user is similar to the user context when the delivery destination user selected to opt out of the delivery target (target T).

Specifically, the determination unit 135 acquires user context information (reference vector) for each target T corresponding to the destination user from the user context information storage unit 126. Then, the determination unit 135 determines whether or not a determination target vector, which is a vectorization of the user information of the destination user determined as the destination by the model M, is similar to the reference vector corresponding to each target T. The determination unit 135 passes the determination result to the exclusion unit 136.

(Exclusion section 136)
When the determination unit 135 determines that the user context of the distribution destination user is similar to the user context when opt-out of the distribution target is selected, the exclusion unit 136 excludes from the targets of use, among the multiple models that determine the distribution destination of the information of the distribution target, a model that corresponds to (a target T indicating) the distribution target for which opt-out was selected. For example, the exclusion unit 136 sets the target T corresponding to the reference vector determined to be similar to the determination target vector as the opt-out target, and performs exclusion registration of the model M corresponding to the target T.

Specifically, for example, when target _T1 is an opt-out target for user _U1 , the exclusion unit 136 deletes the user ID of user _U1 from the user list associated with model _M1 corresponding to target _T1 in the model information stored in the model information storage unit 122, and cancels the association between model _M1 corresponding to target _T1 and user _U1 . In addition, the exclusion unit 136 adds the user ID of user _U1 to the opt-out user list associated with model _M1 corresponding to target _T1 in the model information stored in the model information storage unit 122, and updates the opt-out user list.

The exclusion unit 136 can also exclude model M from use for a period specified by user U. For example, the exclusion unit 136 may accept a specification of an exclusion period from user U in advance for each target T indicating a distribution target, and manage the period in association with the model M corresponding to target T.

Furthermore, the exclusion unit 136 may notify the user U of an inquiry as to whether or not to cancel the exclusion of the model M at a predetermined timing, and may cancel the exclusion of the model M in response to a request from the user U. For example, when the user _U1 requests to cancel the opt-out of the target _T1 , the exclusion unit 136 registers the user ID of the user _U1 in the user list associated with the model _{M1 corresponding to the target T1 in} the model information stored in the model information storage unit 122, and associates the model _M1 corresponding to the target _T1 with the user _U1 . Furthermore, the exclusion unit 136 deletes the user ID of the user _U1 from the opt-out user list associated with the model _M1 corresponding to the target _T1 in the model information stored in the model information storage unit 122, and updates the opt-out user list. Note that an example of the predetermined timing is the timing when the exclusion period for the model M has expired.

Furthermore, after model M is excluded, the exclusion unit 136 may determine at a predetermined timing whether the user context (e.g., the determination target vector) is similar to the user context (e.g., the reference vector) when user U selected opt-out. If the exclusion unit 136 determines that the user context is not similar to the user context when user U selected opt-out, it may notify user U of an inquiry about whether to cancel the exclusion of model M. This makes it possible to, for example, control the cancellation of opt-out depending on the user's state, even if the exclusion period for model M has expired.

5. Processing Procedure
An example of a processing procedure executed by the information processing device 100 according to the embodiment will be described below with reference to Fig. 11. Fig. 11 is a flowchart showing an example of a processing procedure executed by the information processing device according to the embodiment. The processing procedure shown in Fig. 11 is executed by the control unit 130 of the information processing device 100. The processing procedure shown in Fig. 11 is repeatedly executed while the information processing device 100 is operating.

As shown in FIG. 11, the determination unit 135 executes a determination process (step S101). Specifically, the determination unit 135 determines whether the user context of the destination user is similar to the user context when opt-out was selected.

The exclusion unit 136 also executes exclusion processing (step S102). Specifically, if it is determined in step S101 that the user context of the destination user is similar to the user context when the destination user selected opt-out, the exclusion unit 136 excludes, for a limited period of time, from the models that determine the destination, the model that corresponds to the destination for which opt-out was selected.

The distribution unit 132 also starts information distribution (step S103) and ends the processing procedure shown in FIG. 11. Specifically, the distribution unit 132 starts information distribution for multiple distribution targets that reflects the results of the exclusion process in step S102.

Note that if multiple recipient users are determined, the processing procedure shown in Figure 11 above will be executed for each recipient user.

6. Modifications
The information processing device 100 according to the above embodiment may be implemented in various different forms other than the above embodiment, so other embodiments of the information processing device 100 will be described below.

In the above embodiment, an example was described in which the information processing device 100 excludes models corresponding to recipients for whom opt-out has been selected from among multiple models that determine the recipients of information for which opt-out has been selected. However, information processing different from this example may be performed. For example, when performing information distribution corresponding to an opt-out target, the information processing device 100 may accept from user U a selection of a delivery method for which distribution will be stopped from multiple delivery methods such as web content, email, and push notification. Furthermore, the information processing device 100 may record information about delivery methods for which distribution has been stopped for each user U, estimate which delivery methods are likely to be selected by user U, and automatically select the delivery method for which distribution will be stopped based on the estimation result.

In the above embodiment, the administrator of the information processing device 100 may analyze the history information stored in the history information storage unit 125 to estimate the user context when the destination user selected to opt out of the delivery target. The administrator then associates the estimated user context with a model corresponding to the delivery target and manages it for each user U. When delivering information to a destination user, the information processing device 100 may determine whether to opt out of the delivery target based on whether the destination user's user context associated with the model corresponding to the delivery target is similar to the destination user's current user context. This allows the information processing device 100 to implement specific individual responses, such as estimating the destination user's interests from the destination user's search history and excluding models that determine destinations for information that the destination user is unlikely to be interested in, excluding models that determine destinations for information corresponding to a specified area when the destination user's location is within a specified area, excluding models that determine destinations for food-related information when the destination user's weight exceeds a threshold, or excluding models that deliver bargain-related information when the destination user's card usage exceeds a specified amount.

7. Hardware Configuration
The information processing device 100 according to the embodiment described above is realized, for example, by a computer 1000 having a configuration as shown in Fig. 12. Fig. 12 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment.

The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected via a bus 1090.

The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and secondary storage device 1050, and programs read from the input device 1020, and executes various processes. The primary storage device 1040 is a memory device, such as RAM, that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), HDD, flash memory, etc.

The output IF 1060 is an interface for transmitting information to be output to an output device 1010, such as a monitor or printer, which outputs various types of information. It is implemented, for example, by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface). The input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, and scanner, and is implemented, for example, by USB.

The input device 1020 may be a device that reads information from optical recording media such as a CD (Compact Disc), DVD (Digital Versatile Disc), or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. The input device 1020 may also be an external storage medium such as a USB memory.

Network IF 1080 receives data from other devices via network N and sends it to the computing device 1030, and also transmits data generated by the computing device 1030 to other devices via network N.

The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

For example, when the computer 1000 functions as the information processing device 100 according to the above embodiment, the arithmetic unit 1030 of the computer 1000 executes a program (e.g., an information processing program) loaded onto the primary storage device 1040, thereby realizing functions similar to those of the control unit 130. In other words, the arithmetic unit 1030 works in cooperation with the program (e.g., an information processing program) loaded onto the primary storage device 1040 to realize the processing performed by the information processing device 100 according to the above embodiment.

[8. Other]
Of the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method.In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified.

Furthermore, the components of each device shown in the figure are functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

Furthermore, the above-described embodiments can be combined as appropriate to the extent that the processing content is not contradictory.

[9. Effects]
The information processing device 100 according to the embodiment includes a determination unit 135 and an exclusion unit 136. The determination unit 135 determines whether the user context of a delivery destination user to whom information to be distributed is to be distributed is similar to the user context when the delivery destination user selected to opt out of the delivery target. When the determination unit determines that the user context of the delivery destination user is similar to the user context when the delivery target user selected to opt out of the delivery target, the exclusion unit 136 excludes, from among multiple models determining the delivery destination, a model corresponding to the delivery target for which opt-out was selected, from the models to be used for a limited period of time.

For this reason, the information processing device 100 according to the embodiment can automatically stop the distribution of information that is likely to be unwanted by the recipient user, and can provide appropriate information to the user.

Furthermore, in the information processing device 100 according to the embodiment, the exclusion unit 136 excludes the model from use for a period specified by the recipient user. In this way, the information processing device 100 according to the embodiment can realize a time-limited opt-out that reflects the user's wishes, through the processes executed by the above-mentioned units or any combination of the units.

In addition, in the information processing device 100 according to the embodiment, the exclusion unit 136 notifies the destination user at a predetermined timing of an inquiry about whether or not to cancel the exclusion of the model, and cancels the exclusion of the model in response to a request from the destination user.

In this way, the information processing device 100 according to the embodiment can re-distribute information that has been opted out of distribution by using the processes executed by the above-mentioned units or any combination of the units, thereby providing appropriate information to the user.

Furthermore, in the information processing device 100 according to the embodiment, after a model is excluded, the determination unit 135 determines at a predetermined timing whether the user context of the destination user is similar to the user context when the destination user selected to opt out of the distribution target. If the determination unit 135 determines that the user context of the destination user is not similar to the user context when the destination user selected to opt out of the distribution target, the exclusion unit 136 notifies the destination user of an inquiry about whether to cancel the exclusion of the model, and cancels the exclusion of the model in response to a request from the destination user.

In this way, the information processing device 100 according to the embodiment can, through the processes executed by the above-mentioned units or any combination of the units, control the device to postpone cancellation of the opt-out depending on the user's status, even if the exclusion period for model M has expired, and can provide the user with appropriate information.

The above describes in detail the embodiments of the present application based on several drawings, but these are merely examples, and the present invention can be implemented in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the Disclosure of the Invention section.

In addition, the above-mentioned "section, module, unit" can be interpreted as "means" or "circuit." For example, a control unit can be interpreted as a control means or a control circuit.

REFERENCE SIGNS LIST 1 Information processing system 2 Terminal device 10 Communication unit 11 Display unit 12 Operation unit 13 Sensor group 14 Storage unit 15 Processing unit 16 Information acquisition unit 17 Display processing unit 18 Output unit 100 Information processing device 110 Communication unit 120 Storage unit 121 Attribute information storage unit 122 Model information storage unit 123 Distribution information storage unit 124 Opt-out user information storage unit 125 History information storage unit 126 User context information storage unit 130 Control unit 131 Acquisition unit 132 Distribution unit 133 Reception unit 134 Recommendation unit 135 Determination unit 136 Exclusion unit

Claims (5)

a storage unit that stores, for each target corresponding to each of a plurality of models that determine the destination of the distribution information, a reference vector obtained by vectorizing search information and history information that are user information of the user when opting out of the model that determines the destination of the distribution information is selected, in association with identification information for identifying users who may be destination users of distribution information that is information to be distributed;
a determination unit that acquires from the storage unit the reference vector corresponding to the user determined as the destination user, and determines whether the acquired reference vector is similar to a determination target vector obtained by vectorizing the user information of the destination user;
an exclusion unit that, when the determination unit determines that the reference vector and the target vector are similar, excludes from use the model among the plurality of models that corresponds to the target for which the reference vector and the target vector are determined to be similar , for a period specified by the user . The exclusion section is
The information processing device according to claim 1, characterized in that, when a period for excluding the model from use expires , the destination user is notified of an inquiry as to whether or not to cancel the exclusion of the model, and the exclusion of the model is canceled in response to a request from the destination user. The determination unit
After the model is excluded , it is determined whether the target vector of the destination user is similar to the reference vector ;
The exclusion section is
The information processing device according to claim 1, characterized in that, when the determination unit determines that the target vector is not similar to the reference vector , the information processing device notifies the destination user of an inquiry about whether or not to cancel the exclusion of the model, and cancels the exclusion of the model in response to a request from the destination user. 1. A computer-implemented information processing method, comprising:
a determination step of acquiring, from a storage unit that stores, for each target corresponding to each of a plurality of models that determine the destination of the distribution information, a reference vector obtained by vectorizing search information and history information that are user information of the user when opt-out for the model that determines the destination of the distribution information, the reference vector corresponding to the user determined as the destination user, in association with identification information for identifying users who can be destination users of distribution information that is information to be distributed, the reference vector, and determining whether the acquired reference vector is similar to a determination target vector obtained by vectorizing the user information of the destination user;
an exclusion step of, when the determination step determines that the reference vector and the target vector are similar, excluding from use the model among the plurality of models that corresponds to the target determined to have a similar reference vector and target vector for a period specified by the user . On the computer,
a determination step of acquiring, from a storage unit that stores, for each target corresponding to each of a plurality of models that determine the destination of the distribution information, a reference vector obtained by vectorizing search information and history information that are user information of the user when opt-out for the model that determines the destination of the distribution information, the reference vector corresponding to the user determined as the destination user, in association with identification information for identifying users who may be destination users of distribution information that is information to be distributed, the reference vector corresponding to the user determined as the destination user, and determining whether the acquired reference vector is similar to a determination target vector obtained by vectorizing the user information of the destination user;
and an exclusion procedure for excluding, from the target of use for a period of time specified by the user, the model corresponding to the target determined to have a similar reference vector and the target vector to be judged, among the plurality of models, when the judgment procedure judges that the reference vector and the target vector are similar.