JP6018014B2 - Information processing apparatus, feature amount conversion system, display control method, and display control program - Google Patents

Description

  The present invention relates to an information processing apparatus, a feature amount conversion system, a display control method, and a display control program.

  In recent years, machine learning technology has attracted attention as a technology that enables regularity and patterns to be extracted from a certain amount or more of data and enables data recognition, analysis, determination, and the like. Such a machine learning technique is expected to be applied to processing on large-capacity data such as BigData.

  In such machine learning, vector-format data is generally input because the machine learning algorithm performs processing such as pattern extraction, analysis, and determination. Here, in order to perform data processing by machine learning, converting various features of original data into vector format data is called feature amount conversion. The accuracy and properties of machine learning are greatly affected by what kind of vector data is generated in this feature amount conversion.

Toby Segaran, Collective Intelligence Programming, P.53-P.56, O'Reilly Japan, 2008

  However, with the conventional technology, it is difficult to understand which machine learning result changes the parameter setting change in the feature amount conversion have when changing the parameter setting in the feature amount conversion process. In the amount conversion, the user is required to have a high level of expertise, and it has been difficult to easily and efficiently realize appropriate feature amount conversion.

  SUMMARY OF THE INVENTION Accordingly, an object of the present invention is to easily and efficiently realize appropriate feature amount conversion without requiring a user to have a high degree of expertise.

  In order to solve the above-described problem and achieve the object, the information processing apparatus receives a first parameter designation and a second parameter designation, and a first parameter received by the reception unit Between the nodes using the conversion unit that performs the feature amount conversion processing for converting the feature amount of each node in the graph structure data into data of a predetermined format, and the second parameter received by the reception unit A calculation unit that calculates the distance of the node, a position determination unit that determines the position of each node on the image using the distance between the nodes calculated by the calculation unit, and the position determination unit in the image And a display unit that displays the image in which each node is drawn by arranging and drawing each node at the position of each node.

  In addition, the feature amount conversion system includes a reception unit that receives designation of the first parameter and designation of the second parameter, and each node in the graph structure data using the first parameter received by the reception unit. A conversion unit that performs a feature amount conversion process for converting a feature amount included in the data into a predetermined format, a calculation unit that calculates a distance between nodes using the second parameter received by the reception unit, A position determination unit that determines the position of each node on the image using the distance between the nodes calculated by the calculation unit, and each node is arranged at the position of each node determined by the position determination unit in the image And a display unit for displaying the image in which each of the nodes is drawn.

  The display control method is a display control method executed by the information processing apparatus, and includes a reception process that receives the designation of the first parameter and the designation of the second parameter, and the first process that is accepted by the reception process. A conversion step for performing a feature amount conversion process for converting a feature amount of each node in the graph structure data into data of a predetermined format using one parameter, and a second parameter received by the reception step A calculation step for calculating a distance between nodes, a position determination step for determining the position of each node on the image using the distance between the nodes calculated by the calculation step, and the position determination step in the image. A display step of displaying the image in which each node is drawn by arranging and drawing each node at the position of each node determined by Characterized in that it contains.

  In addition, the display control program uses the reception step for receiving the first parameter specification and the second parameter specification, and the first parameter received by the reception step is used to set each node in the graph structure data. A conversion step for performing a feature amount conversion process for converting the feature amount having data into data of a predetermined format, a calculation step for calculating a distance between nodes using the second parameter received by the reception step, and the calculation A position determining step for determining the position of each node on the image using the distance between the nodes calculated by the step, and arranging each node at the position of each node determined by the position determining step in the image A display step for displaying the image on which each of the nodes is drawn. To be executed by the over data.

  The information processing apparatus, feature amount conversion system, display control method, and display control program disclosed in the present application can easily and efficiently realize appropriate feature amount conversion without requiring a high degree of expertise from the user. It is.

FIG. 1 is a diagram illustrating an example of a configuration of a feature amount conversion system according to the first embodiment. FIG. 2 is a diagram for explaining the configuration of the server device according to the first embodiment. FIG. 3 is a diagram illustrating an example of information stored by the node data storage unit according to the first embodiment. FIG. 4 is a diagram illustrating an example of information stored by the designated data storage unit according to the first embodiment. FIG. 5 is a diagram for explaining distance calculation processing for each node. FIG. 6 is a diagram for explaining the configuration of the client device according to the first embodiment. FIG. 7 is a diagram illustrating a display example displayed by the display unit. FIG. 8 is a diagram showing an image when each node is connected by a spring having a strength inversely proportional to the distance. FIG. 9 is a diagram illustrating that the node displayed by the display unit moves by animation. FIG. 10 is a sequence diagram for explaining the flow of processing in the feature quantity conversion system according to the first embodiment. FIG. 11 is a diagram illustrating the first dimension reduction process in the client device according to the first embodiment. FIG. 12 is a diagram for explaining the second and subsequent dimension reduction processing in the client device according to the first embodiment. FIG. 13 is a diagram illustrating a computer that executes a display control program.

  Exemplary embodiments of an information processing apparatus, a feature amount conversion system, a display control method, and a display control program according to the present invention will be described below in detail with reference to the accompanying drawings. In addition, this invention is not limited by this embodiment.

[First embodiment]
In the following embodiments, the configuration of the feature amount conversion system according to the first embodiment, the configuration of the server device according to the first embodiment, the configuration of the client device according to the first embodiment, and processing by the feature amount conversion system The flow according to the first embodiment will be described last.

[Configuration of feature conversion system]
First, an example of the configuration of the feature amount conversion system according to the first embodiment will be described. FIG. 1 is a diagram illustrating an example of a configuration of a feature amount conversion system according to the first embodiment. As illustrated in FIG. 1, in the feature quantity conversion system 100 according to the first embodiment, a server device 10 and a client device 20 are connected via a network 30. In the example of FIG. 1, a case where there is one server device 10 and one client device 20 is illustrated as an example, but the present invention is not limited to this, and a plurality of server devices 10 may be provided. However, a plurality of client devices 20 may be provided.

  Upon receiving an operation start instruction, the server device 10 performs a feature amount conversion process for converting the feature amount of each node in the graph structure data into vector format data. Then, the server device 10 calculates the distance between the nodes on which the feature amount conversion processing has been performed, and transmits the calculation result to the client device 20.

  The client device 20 accepts designation of parameters that can be set in performing the feature amount conversion processing by a user operation. In addition, the client device 20 accepts designation of a calculation method used when calculating the distance between the nodes on which the feature amount conversion processing has been performed. When the client device 20 receives an operation start instruction by a user operation, the client device 20 instructs the server device 10 to start the operation, and transmits the parameters and calculation method specified by the user.

[Configuration of server device]
Next, the configuration of the server apparatus 10 shown in FIG. 1 will be described with reference to FIG. FIG. 2 is a diagram for explaining the configuration of the server device 10 according to the first embodiment. As illustrated in FIG. 2, the server device 10 includes a communication processing unit 11, a control unit 12, and a storage unit 13.

  The communication processing unit 11 controls communication related to various information exchanged with the connected client device 20. For example, the communication processing unit 11 receives an operation start instruction and various parameters from the client device 20. In addition, the communication processing unit 11 transmits the calculation result to the client device 20.

  As shown in FIG. 2, the storage unit 13 includes a node data storage unit 13a and a designated data storage unit 13b. The storage unit 13 is, for example, a semiconductor memory device 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 node data storage unit 13a stores data to be processed in the feature amount conversion process. For example, as illustrated in FIG. 3, the node data storage unit 13 a stores a node ID, a label representing a feature, and a value corresponding to the label. Referring to the example of FIG. 3, the node data storage unit 13a stores, for example, “Yamada Taro”, “Yamada Hanako”, “Yamada Jiro” as node IDs, and “Height”, “Weight” as labels Remember. Also, for example, the node data storage unit 13a stores “180” as “height” of “Yamata Taro” and “72” as “weight” of “Yamata Taro”. It is assumed that the data stored in the node data storage unit 13a is data stored in advance from the client device 20.

  The designated data storage unit 13b stores data related to various parameters designated by the client device 20. For example, the specified data storage unit 13b includes a “conversion rule” referred to in the feature amount conversion process, a “distance calculation method” indicating the type of method for calculating the distance between the nodes, and a binding specification unit described later. The “binding node” indicating the node ID of the node specified by 22c is stored.

  For example, referring to the example of FIG. 4, the designated data storage unit 13b uses the label “height”, the distribution type “uniform distribution”, the weighting “5” as the conversion rule, and the “Euclidean distance” as the distance calculation method. , “Yamataro” is stored as a binding node. The specification of each parameter will be described in detail in the description of the configuration of the client device described later.

  Returning to the description of FIG. 2, the control unit 12 includes a conversion unit 12 a and a calculation unit 12 b. Here, the control unit 12 is an electronic circuit such as a CPU (Central Processing Unit) or MPU (Micro Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

  The conversion unit 12a performs a feature value conversion process for converting the feature value of each node in the graph structure data into data of a predetermined format using the conversion rule received by the conversion rule setting unit 22a of the client device 20. In addition, the conversion unit 12a performs a feature amount conversion process on each node using the conversion rule specified when the update instruction is received by the calculation start specifying unit 22d.

  For example, when the conversion unit 12a receives each parameter together with the calculation start instruction of the client device 20, the conversion unit 12a stores the received parameter in the designated data storage unit 13b. And the conversion part 12a weights data based on the conversion rule designated by the conversion rule setting part 22a mentioned later among the received parameters.

  For example, when the distribution of “height”, which is a label representing a feature, is designated as “uniform distribution” and the subsequent weighting is designated as “5”, the conversion unit 12a Is linearly converted so that the minimum value is “−5” and the maximum value is “5”. Further, for example, when the distribution of the “weight” that is a label representing the feature is designated as a normal distribution and the subsequent weighting is designated as “3”, the conversion unit 12 a The value corresponding to the weight is normalized so that the average is 0 and the variance is 3.

  The calculation unit 12b calculates the distance between the nodes using the distance calculation method received by the distance calculation method designating unit 22b of the client device 20. The distance here may be anything as long as it satisfies the definition of metric space. The calculation unit 12b calculates N × (N−1) / 2 distances where N is the number of nodes. For example, as illustrated in FIG. 5, when there are three nodes, 3 × 2/2 = 3, and three distances are calculated. In the example of FIG. 5, the distance between “Yamada Taro” and “Yamada Hanako” is “1”, the distance between “Yamada Taro” and “Yamada Taro” is “2”, and “Yamada Hanako” It is assumed that the distance from “Yamadajiro” is “2”.

  For example, when the Euclidean distance, one of the n-dimensional vector distances, is designated as the distance calculation method, the calculation unit 12b represents each vector as X and Y, and T is a transpose, “sqrt The Euclidean distance is calculated by ((X−Y) × T (XY)) ”.

[Configuration of client device]
Next, the configuration of the client device 10 shown in FIG. 1 will be described with reference to FIG. FIG. 6 is a diagram for explaining the configuration of the client device 20 according to the first embodiment. As illustrated in FIG. 6, the client device 20 includes a communication processing unit 21, a control unit 22, and a storage unit 23.

  The communication processing unit 21 controls communication related to various types of information exchanged with the connected server device 10. For example, the communication processing unit 21 receives a calculation result from the server device 10. In addition, the communication processing unit 21 transmits an operation start instruction and various parameters to the server device 10.

  As shown in FIG. 6, the storage unit 23 includes a data storage unit 23a. The storage unit 23 is, for example, a semiconductor memory device 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 data storage unit 23a is data to be processed by the feature amount conversion process, and is the same data as the data stored in the node data storage unit 13a of the server device 10 described above.

  The control unit 22 includes a conversion rule setting unit 22a, a distance calculation method designating unit 22b, a binding designating unit 22c, an operation start designating unit 22d, a position determining unit 22e, and a display unit 22f. Here, the control unit 22 is an electronic circuit such as a CPU (Central Processing Unit) or MPU (Micro Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

The conversion rule setting unit 22a accepts the setting of conversion rules used in the feature amount conversion process executed by the conversion unit 12a described above. For example, the conversion rule setting unit 22a
As a conversion rule, at least a feature type, a distribution type, and a weighting factor specification are accepted.

  For example, the conversion rule setting unit 22a receives a label representing a feature included in data, a distribution assumed by the data, and a weighting setting for the label representing the feature. As the assumed distribution, for example, “uniform distribution” or “normal distribution” exists, but any other distribution can be designated.

  Here, the conversion rule setting method by the user will be described using the display example of FIG. In the example of FIG. 7, “height”, “weight”, and “age” are displayed as labels on the right side of the screen. For each label, a pull-down menu from which a distribution type can be selected and a slide in which weights can be set Bars are displayed, and you can freely set the corresponding features to be strong or weak. Each label also has a check box indicating whether or not to use the feature. In the example of FIG. 7, all are checked.

  The distance calculation method designation unit 22b accepts designation of a calculation method in the distance calculation processing between nodes executed by the calculation unit 12b described above. For example, the distance calculation method designating unit 22b can designate “Euclidean distance”, “cosine distance”, “Hamming distance”, “Jaccard coefficient”, and the like as the distance calculation method. For example, in the example of FIG. 7, a pull-down menu from which a calculation method can be selected is displayed at the upper right portion of the screen. In the example of FIG. 7, “cosine distance” is selected.

  The binding designation unit 22c accepts designation of a predetermined node from among the nodes on the image displayed by the display unit 22f described later. For example, the binding specification unit 22c can specify the previous drawn node in conjunction with the display unit 22f, and fixes the position of the specified node in the processing of the position determination unit 22e.

  For example, in the example of FIG. 7, among the displayed nodes, the node indicated as “Binding designation” at the top is designated. Note that the nodes designated to be bound may be displayed in a different color from other nodes.

  The calculation start designating unit 22d receives a calculation start instruction by a user operation, and transmits a calculation start instruction to the server device 10 when the calculation start instruction is received. The calculation start instruction unit 22d receives an instruction to update the image after the image is displayed. For example, in the example of FIG. 7, a button “update display” is displayed in the upper right part of the screen. By clicking this button, the feature amount conversion process and the distance using the currently specified parameters are displayed. A calculation process is performed and the image is updated.

  The position determination unit 22e determines the position of each node on the image using the distance between the nodes calculated by the calculation unit 12b of the server device 10 described above. In addition, the position determination unit 22e does not change the position of the binding specification node specified by the binding specification unit 22c, and between the nodes calculated using the distance calculation method specified when the update instruction is received. Based on the distance, the positions of nodes other than the binding designation node are determined.

  Here, specific processing by the position determination unit 22e will be described. The position determination unit 22e receives a list of N × (N−1) / 2 distances as the distance between the N nodes from the calculation unit 12b of the server device 10 described above. Then, the position determination unit 22e determines the position of each node by using an algorithm obtained by improving an existing multidimensional scaling method as a dimension deletion process for mapping in two dimensions or three dimensions.

  First, a description will be given of the first dimension deletion process, that is, a process when an image is first displayed on the display unit 22f described later. First, the position determination unit 22e randomly arranges N nodes. The position determining unit 22e connects the N nodes with a spring having a strength inversely proportional to the distance. For example, as illustrated in FIG. 8, when the distance between “Yamada Taro” and “Yamada Hanako” is “1” and the distance between “Yamada Taro” and “Yamada Taro” is “2”, The spring connecting “Yamada Taro” and “Yamada Hanako” is twice as strong as the spring connecting “Yamada Taro” and “Yamada Taro”.

  Subsequently, the position determination unit 22e obtains the position between the nodes at the next moment, and notifies the display unit 22f of the coordinate position of each node. Then, the position determination unit 22e repeatedly performs a process of obtaining the position between the nodes for a specified number of times (for example, 10,000 times) and notifying the display unit 22f of the coordinate position of each node. That is, the position determination unit 22e obtains the position (stable state) of the node so that the spring force applied to the node is minimized. For this reason, the process of starting from the initial arrangement of random nodes, calculating the resultant force acting on the node at each time point, and moving the node a little in the direction of the force is repeated. When the position determination unit 22e repeatedly performs the designated number of times processing, the position determination unit 22e notifies the display unit 22f of the final N node positions.

  Next, the second and subsequent dimension deletion processing, that is, processing when an image has already been displayed on the display unit 22f described later will be described. The position determination unit 22e arranges N nodes at the previous position. That is, the initial arrangement of the nodes is not random, but the last node position of the previous time.

  Subsequently, the position determination unit 22e connects N nodes with a spring, but the position of the node specified by the binding specification unit 22c is fixed. Then, the position determination unit 22e obtains the position between the nodes at the next moment, and notifies the display unit 22f of the coordinate position of each node. Then, the position determination unit 22e repeatedly performs a process of obtaining the position between the nodes for a specified number of times (for example, 10,000 times) and notifying the display unit 22f of the coordinate position of each node. When the position determination unit 22e repeatedly performs the designated number of times processing, the position determination unit 22e notifies the display unit 22f of the final N node positions.

  The display unit 22f arranges and draws each node at the position of each node determined by the position determination unit 22e in the image, and displays an image in which each node is drawn. The display unit 22f draws the points of each node converted to two-dimensional or three-dimensional as coordinates, and displays an image in which each node is drawn.

  Each time the display unit 22f receives the coordinate position of each node from the position determination unit 22e, the display unit 22f draws the coordinate position by arranging each node, and displays an image in which each node is drawn. For this reason, for example, as illustrated in FIG. 9, the display unit 22 f displays an animation in which a node moves little by little as an image. In the example of FIG. 9, it is assumed that the node with the node ID “Yamata Taro” is a binding designation node, and the screen is switched in the order of (1) → (2) → (3). As illustrated in FIG. 9, in the display unit 22f, the position of the node with the node ID “Yamada Taro” specified to be bound is fixed, and the node with the node ID “Yamada Taro” moves little by little to the left. An animation is displayed in which the node of ID “Yamahanako” is gradually moving up. Note that the position of the node of the previous image may be drawn transparently. This makes it easy for the user to understand how the node is moving.

  Further, as illustrated in FIG. 7, a past result may be displayed as a past history at the lower left of the screen. Thereby, the user can refer to the past two-dimensional or three-dimensional machine learning result.

  In this way, by visualizing the parameter setting and the result in conjunction with each other, for example, the user views the image displayed by the display unit 22f and determines whether or not the image is appropriate. And when a user judges that it is not appropriate, for example, the setting of the conversion rule setting part 22a is changed and the update of a display is instruct | indicated. In addition, if the user moves the node in the desired direction, it can be seen that the conversion rule has been changed to the correct direction. By repeating such an operation, a feature amount conversion rule that matches the user's sense can be configured. As a result, the feature amount conversion work can be performed efficiently.

[Processing by feature conversion system]
Next, processing of the entire feature quantity conversion system 100 according to the first embodiment will be described with reference to FIG. FIG. 10 is a sequence diagram for explaining the flow of processing in the feature quantity conversion system 100 according to the first embodiment.

  As shown in FIG. 10, the client device 20 accepts settings of various parameters used for feature conversion processing or the like (step S101). For example, the client device 20 accepts designations from the user regarding conversion rules and distance calculation methods. When the client device 20 receives a calculation start instruction from the user, the client device 20 notifies the server device 10 of various parameters together with the calculation start instruction (step S102).

  Subsequently, the server device 10 performs data weighting based on the conversion rule (step S103). And the server apparatus 10 calculates the distance for every node (step S104), and transmits a calculation result to the client apparatus 20 (step S105).

  Then, the client device 20 executes an initial dimension reduction process that will be described in detail later with reference to FIG. 11 (step S106). Subsequently, as a calculation result, the client apparatus 20 arranges and draws each node at the determined position of each node, and displays an image in which each node is drawn (step S107).

  Thereafter, the client device 20 receives a setting change of various parameters used for the feature conversion processing or the like (step S108), and then receives an image update instruction (step S109). Then, the client device 20 notifies the server device 10 of the changed parameter together with the calculation start instruction (step S110).

  Subsequently, the server device 10 performs data weighting based on the conversion rule (step S111). And the server apparatus 10 calculates the distance for every node (step S112), and transmits a calculation result to the client apparatus 20 (step S113).

  Then, the client device 20 executes the second and subsequent dimension reduction processing, which will be described in detail later with reference to FIG. 12 (step S114). Subsequently, as a calculation result, the client device 20 arranges and draws each node at the determined position of each node, and displays an image in which each node is drawn (step S115).

  Next, the dimension deletion process will be described with reference to FIGS. 11 and 12. FIG. 11 is a diagram illustrating the first dimension reduction process in the client device 20 according to the first embodiment. FIG. 12 is a diagram for explaining the second and subsequent dimension reduction processing in the client device 20 according to the first embodiment.

  As illustrated in FIG. 11, the position determination unit 22e of the client device 20 randomly arranges N nodes (step S201). Then, the position determining unit 22e connects the N nodes with a spring having a strength inversely proportional to the distance (step S202). For example, as illustrated in FIG. 8, when the distance between “Yamada Taro” and “Yamada Hanako” is “1” and the distance between “Yamada Taro” and “Yamada Taro” is “2”, The spring connecting “Yamada Taro” and “Yamada Hanako” is twice as strong as the spring connecting “Yamada Taro” and “Yamada Taro”.

  Subsequently, the position determination unit 22e obtains the position between the nodes at the next moment (step S203). The information regarding the position between the nodes obtained here is notified to the display unit 22f as the coordinate position of each node. Then, the position determination unit 22e determines whether the process for obtaining the position between the nodes has been executed a predetermined number of times (for example, 10,000 times) (step S204). As a result, if it is determined that the position determination unit 22e has not executed the predetermined number of times (No at Step S204), the process returns to Step S203 and repeats the process for obtaining the position between the nodes. If the position determination unit 22e determines that the predetermined number of times has been executed (Yes at step S204), the process ends.

  Next, as illustrated in FIG. 12, the position determination unit 22e of the client device 20 arranges N nodes at the previous position (step S301). That is, the initial arrangement of the nodes is not random, but the last node position of the previous time. The position determination unit 22e connects the N nodes with springs, but fixes the position of the node specified by the binding specification unit 22c (step S302).

  Subsequently, the position determination unit 22e obtains the position between the nodes at the next moment (step S303). The information regarding the position between the nodes obtained here is notified to the display unit 22f as the coordinate position of each node. Then, the position determination unit 22e determines whether or not the process for obtaining the position between the nodes has been performed a predetermined number of times (for example, 10,000 times) (step S304). As a result, if the position determination unit 22e determines that the predetermined number of times has not been executed (No at Step S304), the process returns to Step S303 and repeats the process for obtaining the position between the nodes. In addition, when the position determination unit 22e determines that the predetermined number of times has been executed (Yes in step S304), the process ends.

[Effect of the first embodiment]
As described above, in the feature amount conversion system 100 according to the first embodiment, the client device 20 receives the specification of the conversion rule and the specification of the distance calculation method. Then, the server apparatus 10 performs a feature value conversion process for converting the feature value of each node in the graph structure data into vector format data using the received conversion rule. Subsequently, the server device 10 calculates the distance between the nodes using the accepted distance calculation method. Then, the client device 20 determines the position of each node on the image using the calculated distance between the nodes, arranges and draws each node at the determined position of each node in the image, Displays the image in which the node is drawn. For this reason, even users who do not have a high level of expertise can visually determine whether or not their own parameter change (tuning) is appropriate for feature value conversion, improving efficiency and facilitating feature value conversion work. It can be realized. As a result, it is possible to easily and efficiently implement appropriate feature amount conversion without requiring the user to have advanced expertise.

  In the feature amount conversion system 100 according to the first embodiment, the client device 20 can accept the specification of the conversion rule and the specification of the distance calculation method even after the image is displayed, and the image is displayed. Later, an instruction to update the image is received. Then, the server device 10 performs a feature amount conversion process on each node using the conversion rule specified when the update instruction is received, and the distance specified when the update instruction is received. Using a calculation method, the distance between the nodes on which the feature amount conversion processing has been performed is calculated. For this reason, since the result can be referred to while adjusting the parameter, it is possible to visually determine whether or not the parameter change (tuning) is appropriate.

  In the feature amount conversion system 100 according to the first embodiment, the client device 20 receives designation of a predetermined node from among nodes on the displayed image. Then, the client device 20 does not change the position of the received predetermined node, and based on the distance between the nodes calculated using the distance calculation method specified when the update instruction is received, The position of a node other than a predetermined node is determined. For this reason, since the position of the focused node is fixed and the positional relationship with other nodes is displayed in an easy-to-understand manner, it is possible to easily grasp the difference between the parameter setting change and the result change.

  In the feature amount conversion system 100 according to the first embodiment, at least specification of a feature amount type, a distribution type, and a weight value is accepted as a conversion rule. Then, the feature quantity belonging to the designated feature quantity type is converted based on the designated distribution type and weighting value. For this reason, it is possible to freely change the setting of the conversion rule.

  In the feature quantity conversion system 100 according to the first embodiment, designation of a distance calculation method is received, and a distance between nodes is calculated by the calculation method. For this reason, it is possible to freely change the setting of the distance calculation method.

[System configuration, etc.]
Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured. For example, the conversion rule setting unit 22a and the distance calculation method designating unit 22b may be integrated. Moreover, although the case where the client apparatus 20 has the position determination part 22e was demonstrated above, the server apparatus 10 may have. Further, by providing the client device 20 with the conversion unit 12a and the calculation unit 12b included in the server device 10, all the processing may be completed only by the client device 20.

  Further, all or any part of each processing function performed in each device may be realized by a CPU and a program analyzed and executed by the CPU, or may be realized as hardware by wired logic.

  In addition, among the processes described in the present embodiment, all or part of the processes described as being performed automatically can be performed manually, or the processes described as being performed manually can be performed. All or a part can be automatically performed by a known method. In addition, the processing procedure, control procedure, specific name, and information including various data and parameters shown in the above-described document and drawings can be arbitrarily changed unless otherwise specified.

[program]
In addition, it is possible to create a program in which processing executed by the server device 10 and the client device 20 described in the above embodiment is described in a language that can be executed by a computer. For example, it is possible to create a display control program in which processing executed by the server device 10 and the client device 20 according to the first embodiment is described in a language that can be executed by a computer. In this case, when the computer executes the display control program, it is possible to obtain the same effect as in the above embodiment. Further, the display control program is recorded on a computer-readable recording medium, and the processing similar to that of the first embodiment is realized by recording the display control program on the recording medium and causing the computer to read and execute the display control program. May be. Hereinafter, an example of a computer that executes a display control program that realizes the same functions as those of the server device 10 and the client device 20 illustrated in FIGS. 2 and 6 will be described.

  FIG. 13 is a diagram illustrating a computer 1000 that executes a display control program. As illustrated in FIG. 13, the computer 1000 includes, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These units are connected by a bus 1080.

  The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012 as illustrated in FIG. The ROM 1011 stores a boot program such as BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to the hard disk drive 1031 as illustrated in FIG. The disk drive interface 1040 is connected to the disk drive 1041 as illustrated in FIG. For example, a removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1041. The serial port interface 1050 is connected to a mouse 1051 and a keyboard 1052, for example, as illustrated in FIG. The video adapter 1060 is connected to a display 1061, for example, as illustrated in FIG.

  Here, as illustrated in FIG. 13, the hard disk drive 1031 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. That is, the display control program is stored in, for example, the hard disk drive 1031 as a program module in which a command executed by the computer 1000 is described.

  The various data described in the above embodiment is stored as program data, for example, in the memory 1010 or the hard disk drive 1031. Then, the CPU 1020 reads the program module 1093 and the program data 1094 stored in the memory 1010 and the hard disk drive 1031 to the RAM 1012 as necessary, and executes various processing procedures.

  Note that the program module 1093 and the program data 1094 related to the display control program are not limited to being stored in the hard disk drive 1031, but are stored in, for example, a removable storage medium and read out by the CPU 1020 via the disk drive or the like. Also good. Alternatively, the program module 1093 and the program data 1094 related to the display control program are stored in another computer connected via a network (LAN (Local Area Network), WAN (Wide Area Network), etc.), and the network interface 1070 Via the CPU 1020.

DESCRIPTION OF SYMBOLS 10 Server apparatus 11, 21 Communication processing part 12, 22 Control part 12a Conversion part 12b Calculation part 13, 23 Storage part 13a Node data storage part 13b Designated data storage part 20 Client apparatus 22a Conversion rule setting part 22b Distance calculation method designation part 22c Binding designation part 22d Operation start designation part 22e Position determination part 22f Display part 23a Data storage part 30 Network

Claims (5)

As a first parameter , at least accepting specification of a feature type, distribution type, and weight value of each node in the graph structure data, and accepting a calculation method designation as a second parameter;
And using said first parameter received by the receiving unit, a conversion unit for performing feature conversion processing for converting the feature amount into a predetermined format data,
Using the second parameter received by the reception unit, a calculation unit that calculates the distance between the nodes;
A position determination unit that determines the position of each node on the image using the distance between the nodes calculated by the calculation unit;
In the image, each node is arranged and drawn at the position of each node determined by the position determination unit, the image on which each node is drawn is displayed , and the feature quantity among the types of feature quantities Displays a check box for selecting the type of feature used in the conversion process, a pull-down menu for selecting the distribution type, a slide bar for setting the weight, and a pull-down menu for selecting the calculation method. A display unit;
An update receiving unit that receives an instruction to update the image after the image is displayed by the display unit;
Equipped with a,
The conversion unit converts the feature amount belonging to the type of feature amount specified at the time when the update instruction is received by the update receiving unit based on the specified distribution type and weighting value,
The calculation unit calculates the distance between the nodes on which the feature amount conversion processing has been performed by the conversion unit, using the calculation method specified at the time of receiving the update instruction by the update reception unit,
The position determination unit determines the position of each node on the image using the distance between the nodes calculated by the calculation unit,
The display unit arranges and draws each node at the position of each node determined by the position determination unit, displays the image in which each node is drawn, and draws each node displayed in the past. An information processing apparatus for displaying the image on the same screen . A node designation receiving unit that receives designation of a predetermined node from among the nodes on the image displayed by the display unit ;
The position determination unit does not change the position of the predetermined node received by the node specification reception unit, and the node is calculated using the second parameter specified when the update instruction is received. based on the distance between information processing apparatus according to claim 1, characterized in that to determine the position of the nodes other than the given node. As a first parameter , at least accepting specification of a feature type, distribution type, and weight value of each node in the graph structure data, and accepting a calculation method designation as a second parameter;
And using said first parameter received by the receiving unit, a conversion unit for performing feature conversion processing for converting the feature amount into a predetermined format data,
Using the second parameter received by the reception unit, a calculation unit that calculates the distance between the nodes;
A position determination unit that determines the position of each node on the image using the distance between the nodes calculated by the calculation unit;
In the image, each node is arranged and drawn at the position of each node determined by the position determination unit, the image on which each node is drawn is displayed , and the feature quantity among the types of feature quantities Displays a check box for selecting the type of feature used in the conversion process, a pull-down menu for selecting the distribution type, a slide bar for setting the weight, and a pull-down menu for selecting the calculation method. A display unit;
An update receiving unit that receives an instruction to update the image after the image is displayed by the display unit;
Equipped with a,
The conversion unit converts the feature amount belonging to the type of feature amount specified at the time when the update instruction is received by the update receiving unit based on the specified distribution type and weighting value,
The calculation unit calculates the distance between the nodes on which the feature amount conversion processing has been performed by the conversion unit, using the calculation method specified at the time of receiving the update instruction by the update reception unit,
The position determination unit determines the position of each node on the image using the distance between the nodes calculated by the calculation unit,
The display unit arranges and draws each node at the position of each node determined by the position determination unit, displays the image in which each node is drawn, and draws each node displayed in the past. A feature amount conversion system , wherein the image is displayed on the same screen . A display control method executed by an information processing apparatus,
A reception step of receiving at least a specification of a feature type, distribution type, and weight value of each node in the graph structure data as a first parameter , and receiving a calculation method specification as a second parameter;
Using the first parameter received by said receiving step, a conversion step of performing feature transformation process which transforms the feature that each node in the graph structure data has a predetermined format data,
A calculation step of calculating a distance between nodes using the second parameter received by the reception step;
A position determining step of determining the position of each node on the image using the distance between the nodes calculated by the calculating step;
In the image, each node is arranged and drawn at the position of each node determined by the position determination step, the image on which each node is drawn is displayed , and the feature quantity among the types of feature quantities Displays a check box for selecting the type of feature used in the conversion process, a pull-down menu for selecting the distribution type, a slide bar for setting the weight, and a pull-down menu for selecting the calculation method. Display process;
An update receiving step for receiving an instruction to update the image after the image is displayed by the display step;
Only including,
The conversion step converts the feature amount belonging to the type of feature amount specified at the time of receiving the update instruction by the update receiving step based on the specified distribution type and weighting value,
The calculation step uses the calculation method specified at the time when an update instruction is received by the update reception step, and calculates a distance between nodes on which feature amount conversion processing has been performed by the conversion step,
The position determining step determines the position of each node on the image using the distance between the nodes calculated by the calculating step,
In the display step, each node is arranged and drawn at the position of each node determined in the position determination step, the image in which each node is drawn is displayed, and each node displayed in the past is drawn. A display control method , comprising: displaying the image on the same screen . A reception step of receiving at least a specification of a feature amount type, a distribution type, and a weight value of each node in the graph structure data as a first parameter , and receiving a calculation method specification as a second parameter;
Using the first parameter received by the receiving step, a conversion step for performing feature conversion processing for converting the feature amount each node in the graph structure data has a predetermined format data,
A calculation step of calculating a distance between nodes using the second parameter received by the reception step;
A position determining step of determining the position of each node on the image using the distance between the nodes calculated by the calculating step;
In the image, each node is arranged and drawn at the position of each node determined by the position determining step, the image on which each node is drawn is displayed , and the feature amount among the feature amount types is displayed. Displays a check box for selecting the type of feature used in the conversion process, a pull-down menu for selecting the distribution type, a slide bar for setting the weight, and a pull-down menu for selecting the calculation method. A display step;
An update receiving step for receiving an instruction to update the image after the image is displayed by the display step;
To the computer ,
The conversion step converts the feature amount belonging to the type of feature amount specified at the time when the update instruction is received by the update reception step based on the specified distribution type and weighting value,
The calculation step uses the calculation method specified at the time when an update instruction is received by the update reception step, and calculates the distance between the nodes on which the feature amount conversion processing has been performed by the conversion step,
The position determination step determines the position of each node on the image using the distance between the nodes calculated by the calculation step,
The display step arranges and draws each node at the position of each node determined by the position determination step, displays the image in which each node is drawn, and draws each node displayed in the past. A display control program for displaying the image on the same screen .

Images