JP2018136887A - Generation device, generation method, and generation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To generate a flexible model according to information.SOLUTION: A generation device includes an acquisition unit, a classification unit, and a generation unit. The acquisition unit obtains information on second targets associated with first targets. The classification unit classifies information pieces on the second targets associated with the first targets, into clusters; and associates the clusters corresponding to the first targets on the basis of a predetermined reference. The generation unit generates a predetermined model on the basis of the association of the clusters between the first targets.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a generation device, a generation method, and a generation program.

  Conventionally, techniques for generating (learning) models based on various information have been provided. For example, there is provided a technique for generating a predetermined model using learning data (information) obtained by correcting an erroneous action label based on a characteristic action for each stay place attribute.

JP 2006-157196 A

  However, in the above-described conventional technology, it may be difficult to enable generation of a flexible model according to information. For example, if a model is generated by uniformly classifying (clustering) information about a target such as a user, and the information acquired according to each target fluctuates, a flexible model can be generated according to the information. It is difficult to make it possible.

  The present application has been made in view of the above, and an object thereof is to provide a generation device, a generation method, and a generation program that enable generation of a flexible model according to information.

  The generation apparatus according to the present application includes an acquisition unit that acquires information about a second target associated with each first target, and each of information regarding a second target associated with each first target. A classifying unit that classifies the data into a predetermined number of clusters, and associates the clusters corresponding to the first objects based on a predetermined criterion between the first objects; And a generation unit that generates a predetermined model based on the association.

  According to one aspect of the embodiment, there is an effect that a flexible model can be generated according to information.

FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the generation system according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the generation apparatus according to the embodiment. FIG. 4 is a diagram illustrating an example of a user information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of the behavior information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the cluster information storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of a model information storage unit according to the embodiment. FIG. 8 is a flowchart illustrating an example of the generation process according to the embodiment. FIG. 9 is a diagram illustrating an example of a model generation process according to the embodiment. FIG. 10 is a diagram illustrating an example of a model generation process according to the embodiment. FIG. 11 is a diagram illustrating an example of a model generation process according to the embodiment. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the generation apparatus.

  Hereinafter, a generation apparatus, a generation method, and a mode for executing a generation program (hereinafter referred to as “embodiment”) according to the present application will be described in detail with reference to the drawings. Note that the generation device, the generation method, and the generation program according to the present application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

(Embodiment)
[1. Generation process)
First, an example of the generation process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. Specifically, FIG. 1 illustrates a case where the generation apparatus 100 generates a predetermined model using information (data) regarding each user. In the example of FIG. 1, a model used for determining content to be distributed to the user is generated as the predetermined model.

  In the example of FIG. 1, a case where each user is a first target is shown. Specifically, in FIG. 1, the user identified by the user ID “U1” (hereinafter also referred to as “user U1”), the user identified by the user ID “U2” (user U2), and the user ID “U3”. The case where the user (user U3) etc. identified by (1) is targeted is shown.

  Moreover, in the example of FIG. 1, the case where time is made into the 2nd object is shown. In the example of FIG. 1, the generation apparatus 100 clusters the behavior information associated with the date and time (time), which is the behavior information of each user, as illustrated in the behavior information storage unit 122 in FIG. 5. The case of generating is described. Note that the first object and the second object are not limited to the above, and may be various objects.

  First, the graphs GR1 to GR3 corresponding to the users U1 to U3 shown in FIG. 1 will be described. For example, the graphs GR <b> 1 to GR <b> 3 illustrated in FIG. 1 indicate the data amount (information amount) corresponding to each time for the behavior information corresponding to the time that is the second target of the users U <b> 1 to U <b> 3 that are the first targets. It is a graph. For example, the “data amount” indicated by the vertical axis (hereinafter also referred to as “Y-axis”) of the graphs GR1 to GR3 indicates the data amount of the behavior information regarding each time. For example, the Y-axis “data amount” of the graphs GR1 to GR3 indicates the data amount of the behavior information acquired at each time. Note that the Y-axis of the graphs GR1 to GR3 is not limited to the data amount of the behavior information, and may be any information as long as it is information that can grasp the correlation of information regarding each time, for example. For example, the Y axis of the graphs GR1 to GR3 may be the number of behavior information, the variance, and various other statistics.

  Further, for example, “time t” indicated by the horizontal axis (hereinafter, also referred to as “X axis”) of the graphs GR1 to GR3 indicates a time axis. In the example of FIG. 1, the X axis “time t” of the graphs GR1 to GR3 corresponds to one day (24 hours). For example, the X axis “time t” of the graphs GR1 to GR3 may have the intersection with the Y axis as “0 o'clock” and the tip of the axis as “24 o'clock”. Note that the X-axis may be any information as long as it is information related to the second target time.

  In the example of FIG. 1, the graphs GR1 to GR3 have intersections with the Y axis at “0 o'clock”, and the times on the X axis “time t” of the graphs GR1 to GR3 correspond to each other. For example, in the graphs GR2 and GR3, the position corresponding to the time t11 shown in the graph GR1 is the same time as the time t11. For example, when the time t11 is “1: 1: 1”, the time at the position corresponding to the time t11 shown in the graph GR1 in the graphs GR2 and GR3 is also “1: 1: 1”. . For example, in the example of FIG. 1, it is assumed that the time t11 is before the time t31, and the time t31 is before the time t21. In the example of FIG. 1, time t31 is assumed to be a time between time t31 and time t21.

  For example, the graph GR1 illustrated in FIG. 1 is a graph illustrating a data amount (information amount) corresponding to each time for the behavior information corresponding to the time of the user U1. For example, the graph GR1 indicates that there is little action information of the user U1 acquired at time t11. Further, for example, the graph GR1 indicates that the action information of the user U1 that is gradually acquired after time t11 is increasing. For example, the generating apparatus 100 acquires the data amount of the behavior information of the user U1 at each time based on the date information shown in the behavior information storage unit 122 in FIG. 5, and generates the graph GR1. For example, in the case where the time of the date “TM11” indicated in the behavior information storage unit 122 corresponds to the time t12, the generation apparatus 100 assumes that the behavior information identified by the behavior ID “AT11” is the behavior information regarding the time t12. A graph GR1 is generated.

  As described above, the generation device 100 generates the graph GR1 based on the behavior information of the user U1 stored in the behavior information storage unit 122, for example. Moreover, the production | generation apparatus 100 produces | generates graph GR2 based on the user U2 action information memorize | stored in the action information storage part 122, for example. Moreover, the production | generation apparatus 100 produces | generates graph GR3 based on the user's U3 action information memorize | stored in the action information storage part 122, for example.

  Hereinafter, a case where the generation apparatus 100 generates a model based on information as illustrated in the above-described graphs GR1 to GR3 will be described. First, the generation device 100 clusters the behavior information of each user based on time. In the example illustrated in FIG. 1, the generation device 100 classifies (clusters) the behavior information of each user into three clusters based on time. Note that the number of clusters may be determined based on various information such as the purpose and conditions of the model to be generated. For example, the generation apparatus 100 may classify (cluster) the behavior information of each user into any number of clusters as long as the number of clusters for each user is the same. For example, the generation apparatus 100 may classify (cluster) the behavior information of each user into N clusters (N is a natural number of 2 or more). For example, the generation apparatus 100 may classify (cluster) the behavior information of each user into five clusters. For example, the generating apparatus 100 may classify (cluster) the behavior information of each user into 10 clusters. Further, the generation apparatus 100 may determine how many clusters the behavior information of each user is classified by cross-validation (cross-validation). This point will be described later.

  First, in the example illustrated in FIG. 1, the generation device 100 clusters the graph GR1 of the user U1 into three clusters (step S11-1). For example, the generation device 100 clusters the graph GR1 of the user U1 into three clusters along the time axis (X axis). The graph GR1 shown in FIG. 1 has a periodicity that the data amount of the behavior information settles (decreases) at three time points t11, t12, and t13. Therefore, the generation device 100 clusters the graph GR1 of the user U1 into three clusters of time t11-t12, time t12-t13, and time t13-t11. In other words, the generation device 100 corresponds to the behavior information of the user U1 between the behavior information corresponding to the time t11 to the time t12, the behavior information corresponding to the time t12 to the time t13, and the time t13 to the time t11. Cluster into three clusters with behavior information.

  Note that the generation apparatus 100 may perform clustering as described above using various clustering methods as appropriate. The generation device 100 may use various clustering methods such as logistic regression using a k-means method or a Dirichlet process. Further, for example, the generation apparatus 100 may perform clustering into three clusters after approximation with a predetermined function so that three waves can be generated in the graph GR1.

  Further, in the example illustrated in FIG. 1, the generation device 100 clusters the graph GR2 of the user U2 into three clusters (Step S11-2). For example, the generating apparatus 100 clusters the graph GR2 of the user U2 into three clusters along the time axis (X axis). The graph GR2 shown in FIG. 1 has a periodicity that the data amount of the behavior information settles (decreases) at three time points of times t21, t22, and t23. Therefore, the generation device 100 clusters the graph GR2 of the user U2 into three clusters of time t21-t22, time t22-t23, and time t23-t21. In other words, the generation device 100 corresponds to the behavior information of the user U2 between the time t21 and the time t22, the behavior information corresponding to the time t22 to the time t23, and the time t23 to the time t21. Cluster into three clusters with behavior information.

  In the example illustrated in FIG. 1, the generation device 100 clusters the graph GR3 of the user U3 into three clusters (Step S11-3). For example, the generation device 100 clusters the graph GR3 of the user U3 into three clusters along the time axis (X axis). The graph GR3 illustrated in FIG. 1 has a periodicity that the data amount of the behavior information is settled (decreased) at three time points of time t31, t32, and t33. Therefore, the generation device 100 clusters the graph GR3 of the user U3 into three clusters of time t31-t32, time t32-t33, and time t33-t31. In other words, the generation device 100 corresponds to the behavior information of the user U3, the behavior information corresponding to the time t31 to the time t32, the behavior information corresponding to the time t32 to the time t33, and the time t33 to the time t31. Cluster into three clusters with behavior information.

  Note that steps S11-1 to S11-3 are for explaining the processing, and any of steps S11-1 to S11-3 may be performed first, and each of steps S11-1 to S11-3 may be performed. May be performed multiple times. Hereinafter, when the steps S11-1 to S11-3 are described without distinction, they are collectively referred to as step S11. Thus, in step S11, the generation device 100 can appropriately cluster the behavior information of each user U1 to U3 according to the acquisition situation for each user in time.

  Then, the generation apparatus 100 associates each cluster corresponding to each user with each other based on a predetermined criterion. For example, the generating apparatus 100 associates each user with each cluster corresponding to each user based on a predetermined reference point. In the example of FIG. 1, the generation device 100 associates each cluster corresponding to each user between the users based on the reference point PV11. In the example of FIG. 1, the reference point PV11 is a predetermined time, and is a time between time t22 and time t12. The predetermined reference is not limited to the predetermined reference point, and may be various standards. For example, the predetermined criterion may be a criterion related to a cluster. Further, for example, the predetermined criterion may be a criterion different from the criterion for performing clustering. Details of this point will be described later.

  For example, the generation apparatus 100 associates each cluster corresponding to each user among the users by numbering the clusters corresponding to each user sequentially from the cluster corresponding to the reference point PV11.

  In the example of FIG. 1, since the reference point PV11 is between the time t11 and the time t12, the generation apparatus 100 numbers the time t11-t12 as the first for the user U1 (step S12-1). For example, for the user U1, the generation apparatus 100 numbers time t11-t12 as “No. T1” and sets it as a sub-cluster CL1-1 corresponding to the cluster CL1.

  In the example of FIG. 1, the generation apparatus 100 numbers the time t12-t13 next to the time t11-t12 for the user U1 as the second number (step S12-2). For example, for the user U1, the generation apparatus 100 numbers time t12-t13 as “T2” and sets it as a sub-cluster CL2-1 corresponding to the cluster CL2.

  Further, in the example of FIG. 1, the generation apparatus 100 numbers the time t13-t11 next to the time t12-t13 for the user U1 as the third number (step S12-3). For example, for the user U1, the generation apparatus 100 numbers time t13-t11 as “T3” and sets it as a sub-cluster CL3-1 corresponding to the cluster CL3.

  In the example of FIG. 1, since the reference point PV11 is between the time t22 and the time t23, the generation apparatus 100 numbers the time t22-t23 as the first for the user U2 (step S13-1). For example, for the user U2, the generation apparatus 100 numbers time t22-t23 as “No. T1” and sets the sub-cluster CL1-2 corresponding to the cluster CL1.

  Further, in the example of FIG. 1, the generation device 100 numbers the time t23-t21 next to the time t22-t23 for the user U2 as the second number (step S13-2). For example, for the user U2, the generation apparatus 100 numbers time t23-t21 as “T2” and sets it as a sub-cluster CL2-2 corresponding to the cluster CL2.

  Further, in the example of FIG. 1, the generation device 100 numbers the time t21-t22 next to the time t23-t21 for the user U2 as the third number (step S13-3). For example, for the user U2, the generation apparatus 100 numbers time t21-t22 as “T3” and sets it as a sub-cluster CL3-2 corresponding to the cluster CL3.

  In the example of FIG. 1, since the reference point PV11 is between the time t31 and the time t32, the generation apparatus 100 numbers the time t31-t32 as the first for the user U3 (step S14-1). For example, for the user U3, the generation apparatus 100 numbers time t31-t32 as “T1” and sets it as a sub-cluster CL1-3 corresponding to the cluster CL1.

  Further, in the example of FIG. 1, the generation device 100 numbers the time t32-t33 next to the time t31-t32 for the user U3 as the second number (step S14-2). For example, for the user U3, the generation apparatus 100 numbers times t32 to t33 as “T2” and sets the subcluster CL2-3 corresponding to the cluster CL2.

  Further, in the example of FIG. 1, the generation apparatus 100 numbers the time t33-t31 next to the time t32-t33 for the user U3 as the third number (step S14-3). For example, for the user U3, the generation apparatus 100 numbers time t33-t31 as “T3” and sets it as a sub-cluster CL3-3 corresponding to the cluster CL3.

  Thereby, the production | generation apparatus 100 can match each user's information appropriately. In the example of FIG. 1, the generation device 100 includes a subcluster CL1-1 including behavior information corresponding to the time t11-t12 for the user U1, and a subcluster CL1- including behavior information corresponding to the time t22-t23 for the user U2. 2 and sub-cluster CL1-3 including action information corresponding to time t31-t32 for user U3 are associated as cluster CL1. In the example of FIG. 1, the generation device 100 includes a subcluster CL2-1 including behavior information corresponding to the time t12-t13 for the user U1 and a subcluster including behavior information corresponding to the time t23-t21 for the user U2. CL2-2 and sub-cluster CL2-3 including action information corresponding to time t32-t33 for user U3 are associated as cluster CL2. Further, in the example of FIG. 1, the generation device 100 includes a subcluster CL3-1 including behavior information corresponding to the time t13-t11 for the user U1 and a subcluster including behavior information corresponding to the time t21-t22 for the user U2. CL3-2 and the sub-cluster CL3-3 including action information corresponding to the time t33-t31 for the user U3 are associated with each other as the cluster CL3.

  Thus, the production | generation apparatus 100 can produce | generate suitable data (information) used for learning (generation of a model) by matching each cluster of each user U1-U3 based on the reference point PV11.

  And the production | generation apparatus 100 produces | generates a model based on the clustered information (step S15). In the example of FIG. 1, the generation device 100 uses information corresponding to the cluster CL1, information corresponding to the cluster CL2, information corresponding to the cluster CL3, and the like to determine content to be distributed to the user as a predetermined model. Generate a model.

  As described above, the generation device 100 clusters the behavior information of each user according to the acquisition status of the behavior information of each user in time, and associates each user's cluster based on a predetermined reference point. It is possible to generate a flexible model according to information.

  For example, in the example of FIG. 1, the user U1 has a periodicity that the data amount of the behavior information settles (decreases) at three points in time t11, t12, and t13, as shown in the graph GR1. Further, for example, in the example of FIG. 1, the user U2 has a periodicity that the data amount of the behavior information settles (decreases) at three points in time t21, t22, and t23, as shown in the graph GR2. Further, for example, in the example of FIG. 1, the user U3 has a periodicity that the data amount of the behavior information settles (decreases) at three time points t31, t32, and t33, as shown in the graph GR3.

  In such a case, for example, when time is clustered based on the periodicity of the user U1 based on the times t11, t12, and t13, the user U2 and the user U3 are not clustered at an appropriate time. It will be. For example, for user U3, the amount of action information acquired at times t11, t12, and t13 is large, and therefore clustering is not performed at an appropriate time. In addition, for example, when time is clustered based on the behavior information of all users, clustering is not performed for each user, because clustering is not optimized for each user. For example, if time is clustered based on the average of the behavior information of all users, the clustering may be suitable to some extent for the average user, but it may not be appropriate for other users. Many. Therefore, when a model is generated based on the result of such clustering, it is difficult to generate an accurate model. Therefore, in such a case, it is not possible to generate a flexible model according to information.

  On the other hand, the generation apparatus 100 can perform appropriate clustering according to each user by clustering time for each user. Therefore, the generation apparatus 100 can perform appropriate clustering according to each first target by clustering the second target for each first target. And the production | generation apparatus 100 can produce | generate suitable data (information) used for learning (generation of a model) by matching each user's cluster between users based on predetermined references | standards, such as a reference point. Thereby, since the production | generation apparatus 100 can perform learning (model production | generation) based on appropriate information, it can produce | generate an accurate model. Therefore, the generation device 100 can enable generation of a flexible model according to information. Moreover, the model which the production | generation apparatus 100 produces | generates is not restricted above, A model for various uses may be sufficient. For example, the model generated by the generation device 100 may be a model for various uses such as advertisement click rate prediction, recommendation accuracy prediction, and context prediction.

(1-1. First object, second object)
In the above-described example, the case where the first target is a user and the second target is time has been described. However, the first target and the second target are not limited to the above, and may be various targets. May be.

  For example, the first target is not limited to the user, and may be a target related to time, position, and the like. For example, when the first target is a position, a model may be generated using information corresponding to each position (for example, latitude / longitude and area). For example, when the first target is time, a model may be generated using information corresponding to each time (for example, 1 o'clock or 2 o'clock). Further, for example, the first target may be a manufacturer (manufacturer) that manufactures a predetermined device or a predetermined device such as a predetermined service or the terminal device 10. Further, for example, the second target may be a predetermined service, device, or manufacturer (manufacturer). For example, the generation apparatus 100 may use the first target as a user and the second target as a service. For example, the generation apparatus 100 may use the first target as a user and the second target as a device. For example, the generation apparatus 100 may use the first target as a device and the second target as a manufacturer (manufacturer). As described above, the generation device 100 may use any target as the first target and the second target as long as the generation process is applicable.

  Moreover, in the example of FIG. 1, the case where the 1st object was made into each user, ie, user unit, was shown. That is, in the example of FIG. 1, the case where the model is generated for the first target for each predetermined unit related to the first target is shown. However, the generation apparatus 100 may generate a model for the first target for each group including a plurality of predetermined units related to the first target. In this case, for example, the first target may be a user group including a plurality of users. In this case, for example, the generation apparatus 100 may generate a model using behavior information corresponding to each of a plurality of user groups. For example, the generation apparatus 100 sets the users U1 to U5 as one group and the users U6 to U10 as one group, together with the action information of all users included in one user group, corresponding to one user group. A model may be generated as information. Similarly, when the first target is a position or time, the generation apparatus 100 sets a group (area, etc.) related to the position or a group related to time (time zone, morning, noon, night, etc.) as the first target. A model may be generated.

  For example, the second object may be an object related to a position, a user, or the like. For example, when the second target is a position, the model may be generated by clustering information according to the position (for example, latitude and longitude, area, etc.) and associating each cluster. For example, when the second target is a user, a model may be generated by clustering information according to the user (for example, demographic attribute, psychographic attribute, etc.) and associating each cluster. Details of these points will be described later.

  Further, for example, the first target and the second target may be content categories. For example, the second target may be various categories such as politics, sports, and entertainment. Further, to which category one content belongs may vary depending on the user. For example, one content may belong to the political category for the user U1 and to the entertainment category for the user U2. For example, the category to which one content belongs for the user may be determined based on the demographic attribute, psychographic attribute, or the like of each user. For example, one content may belong to the political category for the user U1 and to the entertainment category for the user U2. Different categories may be used for each user. For example, a plurality of different categories may be used for each user, and only the number (for example, five) may be common. For example, for user U1, a category based on the content is used, such as politics, economy, entertainment, sports, etc., and for user U2, content such as celebrity FA, celebrity FB, celebrity FC, celebrity FD is used. You may use the category based on the person relevant to. That is, the generation apparatus 100 may perform clustering using any criterion for each target as long as the number of clusters matches. In addition, the first target and the second target described above are examples, and the generation apparatus 100 can identify any target as long as the generation process described above is applicable to the first target and the second target. A model may be generated as follows.

(1-2. Association based on learning process)
In the above-described example, the process of associating each cluster corresponding to each first target with each first target based on a predetermined reference point (hereinafter also referred to as “corresponding process”) is shown. The association processing is not limited to processing using a reference point (for example, the reference point PV11 in FIG. 1), and may be various processing. For example, the generation device 100 may perform the association process based on a predetermined learning process regarding association of each cluster.

  For example, the generation apparatus 100 uses a part of data (information) in each cluster (hereinafter, also referred to as “training data”) for generating a model by cross-validation (cross-validation), and the remaining data (hereinafter, referred to as “training data”). The accuracy of the model generated using the “verification data”) may be verified. For example, the generation apparatus 100 may use 80% of the data in each cluster for model generation and the remaining 20% for verification. For example, the generating apparatus 100 may determine to use the clustering when the verified accuracy satisfies a predetermined criterion. For example, the generation apparatus 100 determines the association of each cluster or the hyper parameter by cross validation (cross validation).

  As an example, a case will be described in which a model to be generated is a model used for determining content to be distributed to a user. For example, the generation apparatus 100 sets the behavior information related to content browsing as correct information among the behavior information included in the training data in each cluster, and when the behavior information for a predetermined period before the content browsing is input. Generate a model to output a large score. In addition, when there is behavior information regarding content browsing among the behavior information included in the verification data of each cluster, the generation device 100 inputs the behavior information for a predetermined period before browsing the content, and is greater than or equal to a predetermined threshold value. It is verified whether or not the probability of outputting the score satisfies a predetermined criterion. Then, when there is action information related to content browsing as a result of the verification using the verification data, the generation device 100 receives the action information of a predetermined period before browsing the content as an input, and the model is set to a predetermined threshold (for example, 0). .7 etc.) It is verified whether the probability of outputting the above score satisfies a predetermined criterion (for example, 80% or more).

  In addition, when the verified accuracy does not satisfy the predetermined standard, the generation device 100 cancels the clustering, performs the clustering process again after the clustering, or maintains the clustering so that the accuracy satisfies the predetermined standard. A correspondence process may be performed until it is satisfied. Further, each time clustering is performed, the generation apparatus 100 performs cross-validation (cross-validation) a plurality of times by exchanging information used for model generation (verification data) and information used for verification (verification data). Whether to maintain or cancel clustering may be determined based on the average. In addition, the detail about the point of the matching process regarding cross verification (cross validation) is mentioned later.

(1-3. Association based on context)
For example, the generating apparatus 100 may associate each cluster corresponding to each first target between each first target based on information other than information related to the second target. For example, in the example of FIG. 1 described above, the generation apparatus 100 may indicate that the user is located at home or office at the time corresponding to each sub-cluster when the sub-cluster is numbered (corresponding processing) corresponding to time. Numbering may be performed in consideration of various information. For example, the growth apparatus 100 may perform the association process based on the context information regarding the user at the time corresponding to each sub-cluster.

  The context information regarding the user here (hereinafter also simply referred to as “context information”) is, for example, information indicating the context of the user. For example, the context means the situation of the user estimated based on the situation of the user or the terminal device 10 used by the user or the environment (background) of the user or the terminal apparatus. In addition, the context includes the content provided to the user, the content of the content that the user has reacted to, the user attribute, the current location of the user, the current time, the physical environment in which the user is placed, and the social environment in which the user is placed. Various information such as the user's exercise state and the estimated user's emotion are included. Further, the context may be a psychological state of the user U1 estimated based on the situation of the user or the terminal device 10 or the environment (background) of the user or the terminal device 10.

  For example, the generation apparatus 100 may use user context information estimated from user action information or the like. For example, the terminal device 10 may estimate what kind of situation the user is based on various kinds of behavior information such as user position information and content browsing. For example, the generation apparatus 100 may estimate the user's situation based on various action history information such as the user's position history information and content browsing. For example, if the user has a tendency to view content related to sports at night, and the time point of context estimation is night, the generation apparatus 100 estimates that the user is highly likely to browse content related to sports. May be. In addition, for example, when the position of the user is within a predetermined range from the position where the user has browsed the content related to the economy in the past, the generation apparatus 100 has a context in which the user is highly likely to browse the content related to the economy. It may be estimated. Note that the above is an example, and the generation apparatus 100 may estimate various contexts based on various information and the like.

  For example, the generation device 100 may cluster each sub-cluster corresponding to the time when each user is located at home as one cluster. Further, for example, the generation apparatus 100 may cluster each sub-cluster corresponding to the time when each user is located in the office as one cluster. In the example of FIG. 1, the generation apparatus 100 is configured such that the user U1 is located at home at many times between times t11 and t12, and the user U2 is located at home at many times between times t23 and t21. When U3 is located at home at many times between times t32 and t33, the subcluster corresponding to the time t11 to t12 of the user U1, the subcluster corresponding to the time t23 to t21 of the user U2, the time of the user U3 A sub-cluster corresponding to t32-t33 may be associated.

[2. Generation system)
FIG. 2 is a diagram illustrating a configuration example of the generation system 1. FIG. 2 is a diagram illustrating a configuration example of the generation system according to the embodiment. As illustrated in FIG. 2, the generation system 1 includes a terminal device 10 and a generation device 100. The terminal device 10 and the generation device 100 are connected via a predetermined network N so as to be communicable by wire or wirelessly. FIG. 2 is a diagram illustrating a configuration example of the generation system according to the embodiment. Note that the generation system 1 illustrated in FIG. 2 may include a plurality of terminal devices 10 and a plurality of generation devices 100.

  The terminal device 10 is an information processing device used by a user. The terminal device 10 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. In the example shown in FIG. 1, the case where the terminal device 10 is a smartphone used by the user is shown. Hereinafter, the terminal device 10 may be referred to as a user. That is, hereinafter, the user can be read as the terminal device 10.

  The generation apparatus 100 classifies each piece of information related to the second target associated with each first target into a predetermined number of clusters, and sets each cluster corresponding to each first target between the first targets. This is an information processing apparatus that is associated based on a predetermined standard. Further, the generation device 100 generates a predetermined model based on the association of each cluster in each first target.

[3. Configuration of the generator
Next, the configuration of the generation apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the generation apparatus according to the embodiment. As illustrated in FIG. 3, the generation device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The generation device 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator of the generation device 100 and a display unit (for example, a liquid crystal display) for displaying various types of information. May be.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network N (see FIG. 2) by wire or wireless, and transmits / receives information to / from the terminal device 10.

(Storage unit 120)
The storage unit 120 is realized by, 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. As illustrated in FIG. 3, the storage unit 120 according to the embodiment includes a user information storage unit 121, a behavior information storage unit 122, a cluster information storage unit 123, and a model information storage unit 124.

(User information storage unit 121)
The user information storage unit 121 according to the embodiment stores various types of information regarding the user. For example, the user information storage unit 121 stores user attribute information. FIG. 4 is a diagram illustrating an example of a user information storage unit according to the embodiment. The user information storage unit 121 illustrated in FIG. 4 includes items such as “user ID”, “age”, and “sex”.

  “User ID” indicates identification information for identifying a user. For example, the user identified by the user ID “U1” corresponds to the user U1 illustrated in the example of FIG. “Age” indicates the age of the user who uses the terminal device 10. The “age” may be a specific age of the user identified by the user ID, such as 35 years old. “Gender” indicates the gender of the user who uses the terminal device 10.

  For example, in the example illustrated in FIG. 4, the age of the user identified by the user ID “U1” is “20s”, and the gender of the user is “male”. Further, for example, in the example illustrated in FIG. 4, the age of the user identified by the user ID “U2” is “20s”, and the gender of the user is “female”.

  The user information storage unit 121 is not limited to the above, and may store various types of information according to the purpose. For example, the user information storage unit 121 may store information on demographic attributes of users and information on psychographic attributes. For example, the user information storage unit 121 may store information such as name, family structure, income, interest, and lifestyle.

(Behavior information storage unit 122)
The behavior information storage unit 122 according to the embodiment stores various types of information regarding the user's behavior. FIG. 5 is a diagram illustrating an example of the behavior information storage unit according to the embodiment. For example, the behavior information storage unit 122 stores user behavior information for content distributed to the terminal device 10 of each user. The behavior information storage unit 122 illustrated in FIG. 5 includes items such as “user ID”, “behavior”, and “situation”. Further, the “behavior” includes items such as “behavior ID” and “content”. The “situation” includes items such as “date and time” and “position”.

  “User ID” indicates identification information for identifying a user. For example, the user identified by the user ID “U1” corresponds to the user U1 illustrated in the example of FIG. “Behavior” indicates information related to the user's behavior with respect to the notification content. “Action ID” indicates identification information for identifying the action. “Content” indicates the content of the action of the corresponding user.

  The “situation” indicates information related to the situation when the corresponding user performs an action. “Date and time” indicates the date and time when the corresponding user action was performed. The “date and time” is abstractly illustrated as “TM11” or the like, but a specific date and time such as “February 2, 2017 23:12:52” may be stored. The “position” indicates a position where the corresponding user's action is performed. In the example illustrated in FIG. 5, “position” indicates an abstract code such as “LC11”, but may be information indicating latitude and longitude. Further, for example, the “position” may be an area name or an address.

  For example, in the example shown in FIG. 5, the user U1 identified by the user ID “U1” is an action identified by the ID “AT11” (action AT11) or an action identified by the action ID “AT12” (action AT12). Or the action identified by the action ID “AT13” (action AT13) or the like.

  Specifically, in the example illustrated in FIG. 5, the user U1 indicates that a search (action AT11) using “query A” is performed at the position LC11 at the date and time TM11. Further, in the example shown in FIG. 5, the user U1 indicates that the content A is browsed (action AT12) at the date LC12 at the position LC12. Further, in the example shown in FIG. 5, the user U1 indicates that the purchase of the product A (action AT13) is performed at the position LC13 on the date and time TM13. Further, in the example illustrated in FIG. 5, the user U2 indicates that the purchase of the product B (action AT21) is performed at the position LC21 at the date and time TM21.

  The behavior information storage unit 122 is not limited to the above, and may store various types of information according to the purpose. For example, the behavior information storage unit 122 may store information indicating whether the user has viewed the notified content (displayed on the screen). Moreover, although the case where action information was memorize | stored in the action information storage part 122 for every user ID was shown in FIG. 5, action information may be memorize | stored not only for every user ID but in order of date.

(Cluster information storage unit 123)
The cluster information storage unit 123 according to the embodiment stores various types of information regarding the cluster related to the content notification purpose. FIG. 6 is a diagram illustrating an example of the cluster information storage unit according to the embodiment. For example, the cluster information storage unit 123 stores combinations of options for each element constituting each cluster. The cluster information storage unit 123 illustrated in FIG. 6 includes items such as “cluster ID” and “first target”. In the example of FIG. 6, “first target” includes items corresponding to each first target such as “user U1”, “user U2”, “user U3”, and the like.

  “Cluster ID” indicates information for identifying a cluster. The column “user U1” indicates second information corresponding to the user U1 as the first target. The column “user U2” indicates second information corresponding to the user U2 that is the first target. The column “user U3” indicates second information corresponding to the user U3 that is the first target.

  For example, in the example illustrated in FIG. 6, “CL1-1” illustrated in a grid where the cluster CL1 identified by the cluster ID “CL1” and the user U1 intersect is a time that is the second target of the user U1. Of these, it indicates that the information corresponding to the sub-cluster CL1-1 is associated with the cluster CL1. In addition, “(time t11-t12)” illustrated in the grid where the cluster CL1 and the user U1 intersect is the information corresponding to the time t11-t12 in the time that is the second target of the user U1. Indicates that it is associated with. For example, the information corresponding to the sub-cluster CL1-1 indicates that it is information acquired from time t11 to time t12 in the time that is the second target of the user U1.

  For example, in the example illustrated in FIG. 6, “CL2-1” illustrated in a grid where the cluster CL2 identified by the cluster ID “CL2” and the user U1 intersect is the time that is the second target of the user U1. Of these, information corresponding to the sub-cluster CL2-1 is associated with the cluster CL2. In addition, “(time t12-t13)” illustrated in a square where the cluster CL2 and the user U1 intersect is the information corresponding to the time t12-t13 in the time that is the second target of the user U1. Indicates that it is associated with. For example, the information corresponding to the sub-cluster CL2-1 indicates that it is information acquired from the time t12 to the time t13 in the time that is the second target of the user U1.

  For example, in the example illustrated in FIG. 6, “CL3-1” illustrated in a grid where the cluster CL3 identified by the cluster ID “CL3” and the user U1 intersect is the second time of the user U1. Of these, information corresponding to the sub-cluster CL3-1 is associated with the cluster CL3. In addition, “(time t13-t11)” illustrated in the grid where the cluster CL3 and the user U1 intersect is the information corresponding to the time t13-t11 in the time that is the second target of the user U1. Indicates that it is associated with. For example, the information corresponding to the sub-cluster CL3-1 indicates that it is information acquired from time t13 to time t11 in the time that is the second target of the user U1.

  For example, in the example illustrated in FIG. 6, “CL1-2” illustrated in a grid where the cluster CL1 identified by the cluster ID “CL1” and the user U2 intersect is a time that is the second target of the user U2. Of these, information corresponding to the sub-cluster CL1-2 is associated with the cluster CL1. In addition, “(time t22-t23)” illustrated in a square where the cluster CL1 and the user U2 intersect is the information corresponding to the time t22-t23 in the time that is the second target of the user U2. Indicates that it is associated with. For example, the information corresponding to the sub-cluster CL1-2 indicates that it is information acquired from time t22 to time t23 in the time that is the second target of the user U2.

  The cluster information storage unit 123 is not limited to the above, and may store various types of information according to the purpose.

(Model information storage unit 124)
The model information storage unit 124 according to the embodiment stores information related to learning. For example, the model information storage unit 124 stores a model. For example, the model information storage unit 124 stores model information generated by the generation process. FIG. 7 is a diagram illustrating an example of a model information storage unit according to the embodiment. The model information storage unit 124 illustrated in FIG. 7 includes items such as “feature 1” to “feature 3” corresponding to the model M1 and the like as model information.

  For example, in the example illustrated in FIG. 7, the model information regarding the model M1 includes feature 1 weight “0.3”, feature 2 weight “−0.8”, feature 3 weight “0.2”, and the like. Indicates that For example, when the feature (feature value) of the model is expressed by an m-dimensional vector, the number of features is m, and the weights of the features 1 to m are stored.

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

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller and is stored in a storage device inside the generation apparatus 100 by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Various programs (corresponding to an example of a generation program) are implemented by using the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As illustrated in FIG. 3, the control unit 130 includes an acquisition unit 131, a classification unit 132, a generation unit 133, and a transmission unit 134, and realizes or executes information processing functions and operations described below. . Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 3, and may be another configuration as long as the information processing described below is performed.

(Acquisition part 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires various types of information from an external device such as the terminal device 10. For example, the acquisition unit 131 acquires various types of information from the user information storage unit 121, the behavior information storage unit 122, the cluster information storage unit 123, the model information storage unit 124, and the like.

  In the example of FIG. 1, the acquisition unit 131 acquires the behavior information of each user from the behavior information storage unit 122 (see FIG. 5). In the example of FIG. 1, the acquisition unit 131 acquires behavior information regarding time for each user from the behavior information storage unit 122 (see FIG. 5).

  For example, the acquisition unit 131 acquires information regarding the second target associated with each first target. For example, the acquisition unit 131 acquires information regarding the second target associated with each first target for each predetermined unit regarding the first target. For example, the acquisition unit 131 acquires information regarding the second target associated with each first target for each group including a plurality of predetermined units regarding the first target.

  For example, the acquisition unit 131 acquires information regarding the second target associated with each first target regarding the user. For example, the acquisition unit 131 acquires information related to the second object related to time or position. For example, the acquisition unit 131 acquires information on the second target associated with each first target related to time. For example, the acquisition unit 131 acquires information related to the second target related to the user or the position. For example, the acquisition unit 131 acquires information regarding the second target associated with each first target regarding the position. For example, the acquisition unit 131 acquires information on the second target related to the user or time.

(Classification part 132)
The classification unit 132 classifies various information. For example, the classification unit 132 classifies various types of information into clusters. For example, the classification unit 132 generates information regarding the classified clusters.

  For example, the classification unit 132 classifies each piece of information related to the second target associated with each first target into a predetermined number of clusters, and sets each cluster corresponding to each first target to each first target. Based on a predetermined standard between. For example, the classification unit 132 associates each cluster corresponding to each first target between each first target based on a predetermined reference point. For example, the classification unit 132 associates each cluster corresponding to each first target between each first target based on a predetermined learning process related to the association of each cluster. For example, the classification unit 132 associates each first object with each cluster corresponding to each first object based on information other than information about the second object.

  In the example of FIG. 1, when the time of the date “TM11” shown in the behavior information storage unit 122 (see FIG. 5) corresponds to the time t12, the classification unit 132 determines that the behavior information identified by the behavior ID “AT11” is Graph GR1 is produced | generated as it is action information regarding the time t12. Example In the example of FIG. 1, the classification unit 132 generates the graph GR <b> 1 based on the behavior information of the user U <b> 1 stored in the behavior information storage unit 122. In the example of FIG. 1, the classification unit 132 generates the graph GR <b> 2 based on the behavior information of the user U <b> 2 stored in the behavior information storage unit 122. In the example of FIG. 1, the classification unit 132 generates the graph GR3 based on the behavior information of the user U3 stored in the behavior information storage unit 122.

  For example, the classification unit 132 clusters the behavior information of each user based on time. In the example illustrated in FIG. 1, the generation device 100 classifies (clusters) the behavior information of each user into three clusters based on time.

  In the example of FIG. 1, the classification unit 132 clusters the graph GR1 of the user U1 into three clusters. In the example of FIG. 1, the classification unit 132 clusters the graph GR1 of the user U1 into three clusters along the time axis (X axis). In the example of FIG. 1, the classification unit 132 clusters the graph GR1 of the user U1 into three clusters of time t11-t12, time t12-t13, and time t13-t11. In the example of FIG. 1, the classification unit 132 sets the behavior information of the user U1 between the time t11 and the time t12, the behavior information corresponding to the time t12 to the time t13, and the time t13 to the time t11. Are clustered into three clusters with action information corresponding to. For example, the classification unit 132 may perform clustering as described above using various clustering methods as appropriate. Further, for example, in the example of FIG. 1, the classification unit 132 may be approximated with a predetermined function so as to generate three waves in the graph GR1, and then clustered into three clusters.

  In the example of FIG. 1, the classification unit 132 clusters the graph GR2 of the user U2 into three clusters. In the example of FIG. 1, the classification unit 132 clusters the graph GR2 of the user U2 into three clusters along the time axis (X axis). In the example of FIG. 1, the classification unit 132 clusters the graph GR2 of the user U2 into three clusters of time t21-t22, time t22-t23, and time t23-t21. In the example of FIG. 1, the classification unit 132 sets the behavior information of the user U2 between the time t21 and the time t22, the behavior information corresponding to the time t22 to the time t23, and the time t23 to the time t21. Are clustered into three clusters with action information corresponding to.

  In the example of FIG. 1, the classification unit 132 clusters the graph GR3 of the user U3 into three clusters. In the example of FIG. 1, the classification unit 132 clusters the graph GR3 of the user U3 into three clusters along the time axis (X axis). In the example of FIG. 1, the classification unit 132 clusters the graph GR3 of the user U3 into three clusters of time t31-t32, time t32-t33, and time t33-t31. In the example of FIG. 1, the classification unit 132 sets the behavior information of the user U3 from the time t31 to the time t32, the behavior information corresponding to the time t32 to the time t33, and the time t33 to the time t31. Are clustered into three clusters with action information corresponding to.

  In the example of FIG. 1, the classification unit 132 associates each cluster corresponding to each user with each other based on a predetermined criterion. For example, the classification unit 132 associates each user with each cluster corresponding to each user based on a predetermined reference point. In the example of FIG. 1, the classification unit 132 associates each cluster corresponding to each user with each user based on the reference point PV11. In the example of FIG. 1, the reference point PV11 is a predetermined time, and is a time between time t22 and time t12.

  In the example of FIG. 1, the classification unit 132 associates each cluster corresponding to each user among the users by numbering each cluster corresponding to each user sequentially from the cluster corresponding to the reference point PV11.

  In the example of FIG. 1, since the reference point PV11 is between the time t11 and the time t12, the classification unit 132 numbers the time t11-t12 as the first for the user U1. In the example of FIG. 1, the classification unit 132 numbers the times t11 to t12 as “T1” for the user U1 and sets it as the sub-cluster CL1-1 corresponding to the cluster CL1.

  In the example of FIG. 1, the classification unit 132 numbers the time U12-t13 next to the time U11-T12 for the user U1 as the second number. In the example of FIG. 1, the classification unit 132 numbers time t12-t13 as “T2” for the user U1 and sets it as the sub-cluster CL2-1 corresponding to the cluster CL2.

  In the example of FIG. 1, the classification unit 132 numbers the time t13-t11 next to the time t12-t13 for the user U1 as the third. In the example of FIG. 1, the classification unit 132 numbers time t13-t11 as “T3” for the user U1 and sets it as a sub-cluster CL3-1 corresponding to the cluster CL3. In the example of FIG. 1, the classification unit 132 also numbers the information on the user U2 and the user U3 in the same manner.

  Further, in the example of FIG. 1, the classification unit 132 includes a subcluster CL1-1 including behavior information corresponding to time t11-t12 for the user U1 and a subcluster including behavior information corresponding to time t22-t23 for the user U2. CL1-2 and sub-cluster CL1-3 including action information corresponding to time t31-t32 for user U3 are associated as cluster CL1. In the example of FIG. 1, the classification unit 132 includes a subcluster CL2-1 including behavior information corresponding to the time t12-t13 for the user U1 and a subcluster including behavior information corresponding to the time t23-t21 for the user U2. CL2-2 and sub-cluster CL2-3 including action information corresponding to time t32-t33 for user U3 are associated as cluster CL2. In the example of FIG. 1, the classification unit 132 includes a subcluster CL3-1 including behavior information corresponding to the time t13-t11 for the user U1 and a subcluster including behavior information corresponding to the time t21-t22 for the user U2. CL3-2 and the sub-cluster CL3-3 including action information corresponding to the time t33-t31 for the user U3 are associated with each other as the cluster CL3.

(Generator 133)
The generation unit 133 generates various information. The generation unit 133 performs learning using various types of information. For example, the generation unit 133 generates a model using various information. For example, the generation unit 133 performs learning based on information collected by the acquisition unit 131. For example, the generation unit 133 generates a predetermined model based on the association of each cluster in each first target.

  In the example of FIG. 1, the generation unit 133 generates a model based on the information clustered by the classification unit 132. In the example of FIG. 1, the generation unit 133 uses the information corresponding to the cluster CL1, the information corresponding to the cluster CL2, the information corresponding to the cluster CL3, and the like to determine content to be distributed to the user as a predetermined model. Generate a model.

(Transmitter 134)
The transmission unit 134 transmits various types of information to the terminal device 10. For example, the transmission unit 134 transmits an information acquisition request to the terminal device 10. The transmission unit 134 transmits the model generated by the generation unit 133. The transmission unit 134 also transmits the model to an external device that provides a service using the model.

[4. Generation process flow)
Next, a generation process procedure performed by the generation system 1 according to the embodiment will be described with reference to FIG. FIG. 8 is a flowchart illustrating an example of the generation process according to the embodiment.

  As illustrated in FIG. 8, the generation apparatus 100 acquires information on the second target associated with each first target (Step S101). For example, the generation apparatus 100 acquires information (behavior information) related to the second target (time) associated with each first target (user) stored in the behavior information storage unit 122.

  Thereafter, the generation apparatus 100 classifies each piece of information related to the second target of each first target into a predetermined number of clusters (step S102). For example, the generating apparatus 100 classifies information (behavior information) related to the second target (time) associated with each first target (user) into three clusters.

  Further, the generation apparatus 100 associates the clusters corresponding to the first objects based on a predetermined criterion (Step S103). For example, the generation device 100 associates the behavior information between the times t11 and t12 of the user U1, the behavior information between the times t22 and t23 of the user U2, and the behavior information between the times t31 and t32 of the user U3.

  Thereafter, the generation device 100 generates a predetermined model based on the association of each cluster in each first target (step S104). For example, the generation device 100 generates a model based on information on the clusters CL1 to CL3 and the like corresponding to the action information on the users U1 to U3 and the like.

[5. Other examples of generation processing]
The generation apparatus 100 is not limited to the example described above, and may perform processing for various first targets. This point will be described with reference to FIGS. 9 to 11 are diagrams illustrating an example of model generation processing according to the embodiment. The description of the same points as the generation process in FIG. 1 will be omitted as appropriate.

(5-1. Second object = position)
First, the example of FIG. 9 will be described. FIG. 9 illustrates a case where the generation apparatus 100 generates a predetermined model using information (data) regarding each user. In the example of FIG. 9, a model used for determining content to be distributed to the user is generated as the predetermined model.

  The example of FIG. 9 shows a case where each user is the first target. Specifically, in FIG. 1, a user identified by a user ID “U1” (hereinafter also referred to as “user U1”), a user identified by a user ID “U2” (user U2), or the like is targeted. Indicates. For example, the user U1 and the user U2 are users who use the terminal device 10, and the generation device 100 acquires the position of the terminal device 10 by using a function such as a GPS (Global Positioning System) sensor that the terminal device 10 has.

  Moreover, in the example of FIG. 9, the case where a position is made into the 2nd object is shown. In the example of FIG. 1, the generation apparatus 100 generates a model by clustering the behavior information of each user and the behavior information associated with the position as illustrated in the behavior information storage unit 122 in FIG. 5. Explain the case.

  The map information MP1 shown in FIG. 9 is a diagram schematically showing information regarding the position of the user U1. For example, the area AR11, the area AR12, and the area AR13 shown in the map information MP1 indicate an area (position) where a lot of behavior information is acquired for the user U1.

  Further, the map information MP2 shown in FIG. 9 is a diagram schematically showing information regarding the position of the user U2. For example, the area AR21, the area AR22, and the area AR23 shown in the map information MP2 indicate an area (position) where a lot of behavior information is acquired for the user U2. The map information MP1 and the map information MP2 may be map information indicating a common area or map information indicating different areas. For example, each position in the map information MP1 may match each position in the map information MP2. For example, the map information MP1 and the map information MP2 may indicate the same area (for example, a predetermined area of A prefecture or B city party).

  Hereinafter, a case where the generation apparatus 100 generates a model based on the map information MP1 and MP2 described above will be described. First, the generation device 100 clusters the behavior information of each user based on the position. In the example illustrated in FIG. 9, the generation device 100 classifies (clusters) the behavior information of each user into three clusters based on the position. Note that the number of clusters may be determined based on various information such as the purpose and conditions of the model to be generated.

  First, in the example illustrated in FIG. 9, the generation device 100 clusters the behavior information associated with the position of the user U1 into three clusters based on the position (Step S21-1). For example, the generation device 100 performs clustering into three clusters based on an area from which much position information in the map information MP1 of the user U1 is acquired. In the example of FIG. 9, the generation device 100 performs clustering into three clusters of an area AR11, an area AR12, and an area AR13 shown in the map information MP1. In other words, the generation device 100 clusters the behavior information of the user U1 into three clusters of behavior information corresponding to the area AR11, behavior information corresponding to the area AR12, and behavior information corresponding to the area AR13.

  For example, the generation apparatus 100 may perform clustering as described above using various clustering methods as appropriate. The generation device 100 may use various clustering methods such as logistic regression using a k-means method or a Dirichlet process. Further, for example, the generating apparatus 100 may perform clustering into three clusters after approximating with a predetermined function so that three sets can be formed in the map information MP1.

  Although the above shows a case where the three areas AR11 to AR13 are targeted for the sake of simplicity, the generation apparatus 100 may divide the entire map information MP1 into three areas, for example. For example, the generating apparatus 100 may specify, for example, three central points related to a range where a lot of behavior information is acquired for the user U1, and divide the entire map information MP1 into three Voronoi regions.

  In the example illustrated in FIG. 9, the generation device 100 clusters the behavior information associated with the position of the user U2 into three clusters based on the position (Step S21-2). For example, the generation device 100 performs clustering into three clusters based on an area from which much position information is acquired in the map information MP2 of the user U2. In the example of FIG. 9, the generation device 100 performs clustering into three clusters of an area AR21, an area AR22, and an area AR23 shown in the map information MP2. In other words, the generation device 100 clusters the behavior information of the user U2 into three clusters of behavior information corresponding to the area AR21, behavior information corresponding to the area AR22, and behavior information corresponding to the area AR23.

  Note that steps S21-1 and S21-2 are for explaining the processing, and either step S21-1 or S21-2 may be performed first, and each step S21-1 or S21-2 is performed. May be performed multiple times. Hereinafter, when it demonstrates without distinguishing step S21-1 and S21-2, it will be named step S21 generically. Thus, in step S21, the generation device 100 can appropriately cluster the behavior information of each user U1 to U3 according to the acquisition situation for each user at the position.

  Then, the generation apparatus 100 associates each cluster corresponding to each user with each other based on a predetermined criterion. For example, the generating apparatus 100 associates each user with each cluster corresponding to each user based on a predetermined reference point. In the example of FIG. 9, the generation apparatus 100 associates each cluster corresponding to each user between the users based on the reference point PV21. In the example of FIG. 9, the reference point PV21 is assumed to be a reference position corresponding to the home of each user. In the example of FIG. 9, the reference point PV21 corresponding to the home of the user U1 is referred to as a reference point PV21-1, and the reference point PV21 corresponding to the home of the user U2 is referred to as a reference point PV21-2. The reference point PV21 may not be a reference point that varies depending on the user, but may be a reference point common to all users.

  For example, the generation apparatus 100 associates each cluster corresponding to each user among the users by numbering the clusters corresponding to each user in order from the cluster corresponding to the reference point PV21.

  In the example of FIG. 9, since the reference point PV21-1 is closest to the area AR12 as shown in the map information MP1, the generation apparatus 100 numbers the area AR12 as the first for the user U1 (step S22-1). . For example, for the user U1, the generation apparatus 100 numbers the area AR12 as “P1” and sets it as the sub-cluster CL11-1 corresponding to the cluster CL11.

  In the example of FIG. 9, the generation device 100 numbers the area AR13 second for the user U1 because the area AR13 is next to the reference point PV21-1 next to the area AR12 (step S22-2). For example, for the user U1, the generation apparatus 100 numbers the area AR13 as “No. P2” and sets it as the sub-cluster CL12-1 corresponding to the cluster CL12.

  In the example of FIG. 9, the generation device 100 numbers the area AR11 third for the user U1 because the area AR11 is next to the reference point PV21-1 next to the area AR13 (step S22-3). For example, for the user U1, the generation apparatus 100 numbers the area AR11 as “P3” and sets it as a sub-cluster CL13-1 corresponding to the cluster CL13.

  In the example of FIG. 9, the generation apparatus 100 numbers the area AR21 to the first place for the user U2 because the reference point PV21-2 is closest to the area AR21 as shown in the map information MP2 (step S23- 1). For example, for the user U2, the generation apparatus 100 numbers the area AR21 as “P1” and sets it as a sub-cluster CL11-2 corresponding to the cluster CL11.

  In the example of FIG. 9, the generation device 100 numbers the area AR22 second for the user U2 because the area AR22 is next to the reference point PV21-1 next to the area AR21 (step S23-2). For example, for the user U2, the generation apparatus 100 numbers the area AR22 as “P2” and sets it as a sub-cluster CL12-2 corresponding to the cluster CL12.

  In the example of FIG. 9, the generation device 100 numbers the area AR23 third for the user U2 because the area AR23 is next to the reference point PV21-1 next to the area AR22 (step S23-3). For example, for the user U2, the generation apparatus 100 numbers the area AR23 as “P2” and sets it as the sub-cluster CL13-2 corresponding to the cluster CL13.

  Thereby, the production | generation apparatus 100 can match each user's information appropriately. In the example of FIG. 9, the generation device 100 clusters the subcluster CL11-1 including behavior information corresponding to the area AR12 for the user U1 and the subcluster CL11-2 including behavior information corresponding to the area AR21 for the user U2. Correspond as CL11. In the example of FIG. 9, the generation device 100 clusters a subcluster CL12-1 including behavior information corresponding to the area AR13 for the user U1 and a subcluster CL12-2 including behavior information corresponding to the area AR22 for the user U2. Correspond as CL12. In the example of FIG. 9, the generation apparatus 100 clusters a subcluster CL13-1 including behavior information corresponding to the area AR11 for the user U1 and a subcluster CL13-2 including behavior information corresponding to the area AR23 for the user U2. Correspond as CL13.

  Thus, the production | generation apparatus 100 can produce | generate suitable data (information) used for learning (generation of a model) by matching each cluster of each user U1-U3 based on the reference point PV21.

  And the production | generation apparatus 100 produces | generates a model based on the clustered information (step S24). In the example of FIG. 1, the generation device 100 uses information corresponding to the cluster CL11, information corresponding to the cluster CL12, information corresponding to the cluster CL13, and the like to determine content to be distributed to the user as a predetermined model. Generate a model.

  As described above, the generation device 100 clusters the behavior information of each user according to the acquisition status of the behavior information of each user when the second target is a position, and based on a predetermined reference point, Each user's cluster can be associated. Thereby, the production | generation apparatus 100 can enable the production | generation of a flexible model according to information.

(5-2. First object = time, second object = position)
Next, examples of FIGS. 10 and 11 will be described. 10 and 11 show a case where the generation apparatus 100 generates a predetermined model using information (data) relating to each time zone. In the example of FIGS. 10 and 11, a model used for determining content to be distributed to the user is generated as the predetermined model. Note that description of similar points in the example of FIG. 9 is omitted as appropriate.

  The example of FIG. 10 shows a case where each time zone is the first target. Specifically, FIG. 1 shows a case where a time zone A from 6 to 12:00, a time zone B from 18:00 to 24:00, and the like are targeted. For example, the user U 1, the user U 2, and the like are users who use the terminal device 10, and the generation device 100 acquires the position of the terminal device 10 by a function such as a GPS sensor that the terminal device 10 has.

  10 and 11 show a case where the position is set as the second target. In the example of FIG. 1, the generation apparatus 100 groups one piece of behavior information corresponding to each time slot among the behavior information of each user as shown in the behavior information storage unit 122 in FIG. 5. A case will be described in which the behavior information associated with the position is clustered to generate a model.

  The map information MP31-1 shown in FIG. 10 is a diagram schematically showing information related to the position for the time zone A. For example, the area AR31, the area AR32, and the area AR33 shown in the map information MP31-1 indicate that an area (position) in which a lot of user behavior information is acquired for the time zone A.

  Further, the map information MP31-2 shown in FIG. 10 is a diagram schematically showing information on the position for the time zone B. For example, the area AR34, the area AR35, and the area AR36 shown in the map information MP31-2 indicate an area (position) where a lot of user action information is acquired for the time zone B. The map information MP31-1 and the map information MP31-2 are map information indicating a common area, and map information indicating that the areas AR31 to AR36 from which a lot of user action information is acquired are different. For example, the map information MP31-1 and the map information MP31-2 are assumed to indicate the same area (for example, a predetermined area of A prefecture or B city party). Hereinafter, the map information MP31-1 and the map information MP31-2 will be referred to as map information MP31 when described in a distinction theory.

  Hereinafter, a case where the generation apparatus 100 generates a model based on the map information MP31-1 and MP31-2 described above will be described. As described above, by making each of the different time zones with respect to the same area as the first object, like the map information MP31-1 and MP31-2 shown in FIG. It is possible to generate a model that can be applied to any time zone in areas such as office districts and entertainment districts at night. In addition, like the map information MP31-1 and MP31-2 shown in FIG. 10, by setting each of the different time zones for the same area as the first target, the restaurant in the day time zone and the night time zone. Even in areas where different popular stores differ, clustering can be performed for different time zones in the daytime and nighttime periods, thereby generating a model applicable to any time zone.

  First, the generation device 100 clusters the behavior information of each user based on the position. In the example illustrated in FIG. 10, the generation device 100 classifies (clusters) user behavior information in each time zone into three clusters based on the position. Note that the number of clusters may be determined based on various information such as the purpose and conditions of the model to be generated.

  First, in the example illustrated in FIG. 10, the generation device 100 clusters the action information associated with the position of the time zone A into three clusters based on the position (Step S <b> 31-1). For example, the generation device 100 performs clustering into three clusters based on an area from which much position information is acquired in the map information MP31-1 for the time zone A. In the example of FIG. 10, the generation device 100 performs clustering into three clusters of an area AR31, an area AR32, and an area AR33 shown in the map information MP31-1. In other words, the generation apparatus 100 clusters user behavior information in the time zone A into three clusters of behavior information corresponding to the area AR31, behavior information corresponding to the area AR32, and behavior information corresponding to the area AR33. To do.

  In the example illustrated in FIG. 10, the generation device 100 clusters the behavior information associated with the position of the time zone B into three clusters based on the position (Step S <b> 31-2). For example, the generation device 100 performs clustering into three clusters based on an area from which much position information is acquired in the map information MP31-2 for the time zone B. In the example of FIG. 10, the generation device 100 performs clustering into three clusters of an area AR34, an area AR35, and an area AR36 shown in the map information MP31-2. In other words, the generation apparatus 100 clusters user behavior information in the time zone B into three clusters of behavior information corresponding to the area AR34, behavior information corresponding to the area AR325, and behavior information corresponding to the area AR36. .

  Note that steps S31-1 and S31-2 are for explaining the processing, and either step S31-1 or S31-2 may be performed first, and each of steps S31-1 and S31-2 may be performed. May be performed multiple times. Hereinafter, when it demonstrates without distinguishing step S31-1, S31-2, it is named step S31 generically. As described above, in step S31, the generation device 100 can appropriately cluster user behavior information in each time period according to the acquisition situation for each area (position).

  Then, the generation apparatus 100 associates each cluster corresponding to each user with each other based on a predetermined criterion. For example, the generating apparatus 100 associates each cluster corresponding to each first target between each first target based on a predetermined learning process related to the association of each cluster. In the example of FIG. 10, the generation apparatus 100 associates each cluster corresponding to each time zone between each time zone by cross-validation (cross validation). This point will be described in detail with reference to FIG.

  FIG. 11 is a diagram conceptually showing the association processing by cross-validation (cross-validation). In FIG. 11, a data set corresponding to the area AR31 in the time zone A is a data set DS31, a data set corresponding to the area AR32 in the time zone A is a data set DS32, and a data set corresponding to the area AR33 in the time zone A is The data set is DS33. In FIG. 11, a data set corresponding to the area AR34 in the time zone B is a data set DS34, a data set corresponding to the area AR35 in the time zone B is a data set DS35, and data corresponding to the area AR36 in the time zone B The set is a data set DS36.

  The example of FIG. 11 illustrates data DT31-1 to DT31-3 etc. as training data and data DT31-4, DT31-5 etc. as verification data for the data set DS31. The example of FIG. 11 illustrates data DT36-1 to DT36-3 etc. as training data and data DT36-4, DT36-5 etc. as verification data for the data set DS36. The training data and the verification data are similarly determined for the other data sets DS32 to DS35. As described above, which data is used as training data or verification data may be determined as appropriate.

  Then, the generation apparatus 100 determines which association is to be made by verifying each numbering pattern. In the example of FIG. 11, the generation device 100 generates and verifies a model based on the association as indicated by the numbering pattern PT51 (numbering pattern A) (step S51). For example, the numbering pattern PT51 corresponds to a numbering pattern that associates behavior information corresponding to the area AR31 in the time zone A and behavior information corresponding to the area AR34 in the time zone B as the cluster CL31. For example, the numbering pattern PT51 corresponds to a numbering pattern that associates the behavior information corresponding to the area AR32 in the time zone A and the behavior information corresponding to the area AR35 in the time zone B as the cluster CL32. For example, the numbering pattern PT51 corresponds to a numbering pattern that associates the behavior information corresponding to the area AR33 in the time zone A and the behavior information corresponding to the area AR36 in the time zone B as the cluster CL33.

  For example, the generating apparatus 100 generates a model using training data of each of the data sets DS31 to DS36 based on the numbering pattern PT51. In the example of FIG. 11, as a result of cross-validation (cross-validation), the generation apparatus 100 has a medium accuracy (for example, 60%) based on the correspondence of the numbering pattern PT51 as shown in the result information RS51. ). And the production | generation apparatus 100 determines with the precision of the model produced | generated based on the numbering pattern PT51 not satisfy | filling a predetermined reference | standard (for example, 80% or more).

  In the example of FIG. 11, the generation device 100 generates and verifies a model based on the association as indicated by the numbering pattern PT52 (numbering pattern B) (step S52).

  For example, the generating apparatus 100 generates a model using training data of each of the data sets DS31 to DS36 based on the numbering pattern PT52. In the example of FIG. 11, as a result of cross-validation (cross-validation), the generation apparatus 100 has a low accuracy (for example, 20%) of a model generated based on the association of the numbering pattern PT52 as shown in the result information RS52. ). Then, the generation device 100 determines that the accuracy of the model generated based on the numbering pattern PT52 does not satisfy a predetermined criterion (for example, 80% or more). For example, the generating apparatus 100 repeats the same processing for each numbering pattern until a numbering pattern that satisfies a predetermined criterion is obtained.

  In the example of FIG. 11, the generation device 100 generates a model and verifies it based on the association as shown by the numbering pattern PT55 (numbering pattern N) (step S55).

  For example, the generating apparatus 100 generates a model using training data of each of the data sets DS31 to DS36 based on the numbering pattern PT55. In the example of FIG. 11, as a result of cross-validation (cross-validation), the generation apparatus 100 has high accuracy (for example, 90%) of a model generated based on the association of the numbering pattern PT55 as shown in the result information RS55. ). And the production | generation apparatus 100 determines with the precision of the model produced | generated based on the numbering pattern PT55 satisfy | filling a predetermined reference | standard (for example, 80% or more).

  Therefore, in the example of FIG. 11, the generation device 100 determines the association between the clusters as the numbering pattern PT55 (step S56).

  For example, the generation apparatus 100 associates each cluster corresponding to each user between each time zone by numbering each cluster corresponding to each time zone based on the numbering pattern PT55 as shown in FIG. .

  In the example of FIG. 10, as illustrated in the map information MP31-1, the generation apparatus 100 numbers the area AR32 for the time zone A as the first (step S32-1). For example, for the time zone A, the generation apparatus 100 numbers the area AR32 as “P1” and sets it as a sub-cluster CL31-1 corresponding to the cluster CL31.

  In the example of FIG. 10, the generation device 100 numbers the area AR33 second for the time zone A as shown in the map information MP31-1 (step S32-2). For example, for the time zone A, the generation apparatus 100 numbers the area AR33 as “P2” and sets it as a sub-cluster CL32-1 corresponding to the cluster CL32.

  In the example of FIG. 10, the generating apparatus 100 numbers the area AR31 for the time zone A as shown in the map information MP31-1 (step S32-3). For example, for the time zone A, the generation device 100 numbers the area AR31 as “P3” and sets it as a sub-cluster CL33-1 corresponding to the cluster CL33.

  In the example of FIG. 10, the generation device 100 numbers the area AR34 for the time zone B as shown in the map information MP31-2 (step S33-1). For example, for the time zone B, the generation apparatus 100 numbers the area AR34 as “P1” and sets it as a sub-cluster CL31-2 corresponding to the cluster CL31.

  In the example of FIG. 10, the generating apparatus 100 numbers the area AR35 second for the time zone B as shown in the map information MP31-2 (step S33-2). For example, for the time zone B, the generation apparatus 100 numbers the area AR35 as “P2”, and sets it as the sub-cluster CL32-2 corresponding to the cluster CL32.

  In the example of FIG. 10, the generation device 100 numbers the area AR36 for the time zone B as No. 3 as shown in the map information MP31-2 (step S33-3). For example, for the time zone B, the generation apparatus 100 numbers the area AR36 as “P3” and sets it as the sub-cluster CL33-2 corresponding to the cluster CL33.

  Thereby, the production | generation apparatus 100 can match the information of each time slot | zone appropriately. In the example of FIG. 10, the generation apparatus 100 includes a subcluster CL31-1 including behavior information corresponding to the area AR32 for the time zone A, and a subcluster CL31-2 including behavior information corresponding to the area AR34 for the time zone B. Are associated as cluster CL31. In the example of FIG. 10, the generation device 100 includes a subcluster CL32-1 including behavior information corresponding to the area AR33 for the time zone A, and a subcluster CL32-2 including behavior information corresponding to the area AR35 for the time zone B. Are associated as cluster CL32. In the example of FIG. 10, the generation device 100 includes a subcluster CL33-1 including behavior information corresponding to the area AR31 for the time zone A, and a subcluster CL33-2 including behavior information corresponding to the area AR36 for the time zone B. Are associated as cluster CL33.

  As described above, the generation apparatus 100 associates each cluster such as each time zone A and B based on the result of cross-validation (cross-validation) to thereby obtain appropriate data (information) used for learning (model generation). Can be generated.

  And the production | generation apparatus 100 produces | generates a model based on the clustered information (step S34). In the example of FIG. 1, the generation device 100 uses information corresponding to the cluster CL31, information corresponding to the cluster CL32, information corresponding to the cluster CL33, and the like to determine content to be distributed to the user as a predetermined model. Generate a model.

  As described above, the generation apparatus 100 obtains the behavior information of each time zone according to the acquisition status of the behavior information of each time zone when the first target is a time zone and the second target is a position. Clustering can be performed to associate clusters in each time zone based on the result of cross-validation (cross-validation). Thereby, the production | generation apparatus 100 can enable the production | generation of a flexible model according to information. In the example described above, the generation apparatus 100 has shown the case where the number of clusters of each first target data is three and the first target clusters are associated with each other based on the result of cross-validation. The number of clusters of each first target data may be determined based on the result of cross-validation. When the number of clusters of each first target data is three, the number of clusters of each first target data is four, or the number of clusters of each first target data is In the case of five, etc., cross-validation may be performed, and the clustering of data used for learning may be determined as the most accurate cluster number and cluster association. For example, the generation apparatus 100 determines the optimum association when the number of clusters is three by verifying each numbering pattern when the number of clusters of each first target data is three. Further, for example, the generation apparatus 100 determines the optimum association when the number of clusters is four by verifying each numbering pattern when the number of clusters of each first target data is four. . Further, for example, the generation apparatus 100 determines the optimum association when the number of clusters is five by verifying each numbering pattern when the number of clusters of each first target data is five. . Then, the accuracy between each optimum association when the number of clusters is 3, 4, and 5 is compared, and the most accurate cluster number (for example, “4” etc.) and the cluster association are determined. Also good. The number of clusters 3, 4, and 5 described above is an example, and the number of clusters may be any number as long as it is a predetermined number N (N is a natural number of 2 or more).

[6. effect〕
As described above, the generation device 100 according to the embodiment includes the acquisition unit 131, the classification unit 132, and the generation unit 133. The acquisition unit 131 acquires information regarding the second target associated with each first target. The classification unit 132 classifies each piece of information related to the second target associated with each first target into a predetermined number of clusters, and sets each cluster corresponding to each first target between the first targets. Corresponding based on a predetermined standard. In addition, the generation unit 133 generates a predetermined model based on the association of the clusters between the first targets.

  Thereby, the generation device 100 according to the embodiment classifies each piece of information related to the second target associated with each first target into a predetermined number of clusters, and sets each cluster corresponding to each first target. Flexible model generation according to information by creating association between each first target based on a predetermined criterion and generating a predetermined model based on association of each cluster between each first target Can be made possible.

  In the generation device 100 according to the embodiment, the acquisition unit 131 acquires information regarding the second target associated with each first target for each predetermined unit regarding the first target.

  Thereby, the generation apparatus 100 according to the embodiment obtains information about the second target associated with each first target for each predetermined unit regarding the first target, thereby responding to the information for each predetermined unit. And flexible model generation.

  In the generation device 100 according to the embodiment, the acquisition unit 131 acquires information regarding the second target associated with each first target for each group including a plurality of predetermined units regarding the first target.

  Accordingly, the generation apparatus 100 according to the embodiment acquires information on the second target associated with each first target for each group including a plurality of predetermined units regarding the first target, thereby obtaining the information for each group. It is possible to generate a flexible model according to information.

  In the generation device 100 according to the embodiment, the acquisition unit 131 acquires information on the second target associated with each first target related to the user.

  Thereby, the generation apparatus 100 according to the embodiment can generate a flexible model according to information about the user by acquiring information about the second target associated with each first target about the user. Can be.

  In the generation device 100 according to the embodiment, the acquisition unit 131 acquires information related to the second target related to time or position.

  Thereby, the generation apparatus 100 according to the embodiment can generate a flexible model according to the second object related to time or position by acquiring information related to the second object related to time or position. it can.

  In the generation device 100 according to the embodiment, the acquisition unit 131 acquires information on the second target associated with each first target related to time.

  Thereby, the generation apparatus 100 according to the embodiment can generate a flexible model according to information on time by acquiring information on the second object associated with each first object on time. Can be.

  In the generation device 100 according to the embodiment, the acquisition unit 131 acquires information related to the second target related to the user or the position.

  Thereby, the generation apparatus 100 according to the embodiment can generate a flexible model according to the second target related to the user or the position by acquiring the information related to the second target related to the user or the position. it can.

  In the generation device 100 according to the embodiment, the acquisition unit 131 acquires information on the second target associated with each first target regarding the position.

  Thereby, the generation device 100 according to the embodiment can generate a flexible model according to information about the user by acquiring information about the second target associated with each first target about the position. Can be.

  In the generation device 100 according to the embodiment, the acquisition unit 131 acquires information on the second target related to the user or time.

  Thereby, the generation device 100 according to the embodiment can generate a flexible model according to the second target related to the user or time by acquiring information about the second target related to the user or time. it can.

  Further, in the generation device 100 according to the embodiment, the classification unit 132 associates each cluster corresponding to each first target between each first target based on a predetermined reference point.

  Thereby, the generation apparatus 100 according to the embodiment associates each cluster corresponding to each first target between each first target based on a predetermined reference point, thereby generating a flexible model according to information. Can be generated.

  Further, in the generation device 100 according to the embodiment, the classification unit 132 associates each cluster corresponding to each first target between each first target based on a predetermined learning process related to the association of each cluster.

  Thereby, the generation apparatus 100 according to the embodiment associates each cluster corresponding to each first target with each first target based on a predetermined learning process related to each cluster, thereby obtaining information. Accordingly, it is possible to generate a flexible model.

  Further, in the generation device 100 according to the embodiment, the classification unit 132 associates each cluster corresponding to each first target between each first target based on information other than information related to the second target.

  Accordingly, the generation apparatus 100 according to the embodiment responds to the information by associating each cluster corresponding to each first target between each first target based on information other than information related to the second target. And flexible model generation.

[7. Hardware configuration)
The generation apparatus 100 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in FIG. 12, for example. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the generation apparatus. The computer 1000 includes a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

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

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from other devices via the network N and sends the data to the CPU 1100, and transmits data collected by the CPU 1100 to other devices via the network N.

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

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

  For example, when the computer 1000 functions as the generation apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them. However, as another example, these programs may be acquired from other devices via the network N.

  As described above, some of the embodiments and modifications of the present application have been described in detail with reference to the drawings. It is possible to carry out the present invention in other forms that have been modified and improved.

[8. Others]
In addition, among the processes described in the above-described embodiments and modifications, all or a part of the processes described as being automatically performed can be manually performed, or are described as being performed manually. All or part of the processing can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  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.

  In addition, the above-described embodiments and modifications can be combined as appropriate within a range that does not contradict processing contents.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Generation system 100 Generation apparatus 121 User information storage part 122 Behavior information storage part 123 Cluster information storage part 124 Model information storage part 130 Control part 131 Acquisition part 132 Classification part 133 Generation part 134 Transmission part 10 Terminal device N Network

Claims (14)

An acquisition unit for acquiring information on a second object associated with each first object;
Each of the information related to the second object associated with each first object is classified into a predetermined number of clusters, and each cluster corresponding to each first object is determined between the first objects by a predetermined number. A classification unit to be associated based on a criterion;
A generating unit that generates a predetermined model based on association of each cluster between the first objects;
A generating apparatus comprising: The acquisition unit
The generation apparatus according to claim 1, wherein information related to a second object associated with each first object for each predetermined unit related to the first object is acquired. The acquisition unit
The generation apparatus according to claim 1, wherein information relating to a second object associated with each first object for each group including a plurality of predetermined units relating to the first object is acquired. The acquisition unit
The information regarding the 2nd object matched for every said 1st object about a user is acquired. A generating device given in any 1 paragraph of Claims 1-3 characterized by things. The acquisition unit
The information regarding the said 2nd object regarding time or a position is acquired. The generation apparatus of Claim 4 characterized by the above-mentioned. The acquisition unit
The information regarding the 2nd object matched for every said 1st object about time is acquired. A generating device given in any 1 paragraph of Claims 1-3 characterized by things. The acquisition unit
The apparatus according to claim 6, wherein information related to the second object related to a user or a position is acquired. The acquisition unit
The information regarding the 2nd object matched for every said 1st object about a position is acquired. A generating device given in any 1 paragraph of Claims 1-3 characterized by things. The acquisition unit
The generation apparatus according to claim 8, wherein information related to the second object related to a user or time is acquired. The classification unit includes:
The generation device according to claim 1, wherein each cluster corresponding to each first target is associated between each first target based on a predetermined reference point. The classification unit includes:
The cluster corresponding to each of the first objects is associated between each of the first objects based on a predetermined learning process related to the association of each of the clusters. The generating device according to item. The classification unit includes:
The cluster corresponding to each of the first objects is associated between each of the first objects based on information other than the information on the second object. The generating device described in 1. A generation method executed by a computer,
An acquisition step of acquiring information about a second object associated with each first object;
Each of the information related to the second object associated with each first object is classified into a predetermined number of clusters, and each cluster corresponding to each first object is determined between the first objects by a predetermined number. A classification process to be matched based on a standard;
A generating step of generating a predetermined model based on the association of each cluster between the first objects;
A generation method comprising: An acquisition procedure for acquiring information about a second object associated with each first object;
Each of the information related to the second object associated with each first object is classified into a predetermined number of clusters, and each cluster corresponding to each first object is determined between the first objects by a predetermined number. A classification procedure for mapping based on criteria,
A generation procedure for generating a predetermined model based on the association of each cluster between the first objects;
A program for causing a computer to execute.

Images