JP2019159553A - Information processing apparatus, information processing method, and program - Google Patents

Abstract

To provide an information processing apparatus, an information processing method, and a program capable of appropriately classifying a group according to a purpose while reflecting a category definition requested by a user.SOLUTION: The information processing apparatus according to an embodiment includes an acquisition unit, a determination unit, a presentation unit, and an update unit. The acquisition unit acquires group information including the number of members constituting the group and attributes of each member. The determination unit compares a group feature represented by using the group information with a determination rule that defines a matching condition for each of a plurality of categories, and determines which of the plurality of categories the group belongs to. The presentation unit presents the determination result of the determination unit. The update unit updates the determination rule according to a correction operation for the presented determination result.SELECTED DRAWING: Figure 1

Description

  Embodiments described herein relate generally to an information processing apparatus, an information processing method, and a program.

  For example, in applications such as customer analysis, a group that is a group of people who act together is classified into categories such as “parent and child”, “family”, and “friends”, and a request is made to aggregate the number of groups for each category. There is. In general, group classification is performed by determining the definition (conformance condition) of each category in advance and determining which category the group to be classified belongs to.

  However, the definition of the group category is not necessarily uniquely determined, and may differ depending on the user's perception and the purpose of analysis. For example, even if it is “parent and child”, whether or not an infant and its parent group and an adult child and its parent group are included in the same “parent and child” category depends on the user and the purpose of analysis. Conventionally, it is impossible to classify a group reflecting the (especially implicit) definition of a category desired by such a user, and improvement is required.

JP 2004-227158 A

  The problem to be solved by the present invention is to provide an information processing apparatus, an information processing method, and a program capable of appropriately classifying a group according to a purpose by reflecting the definition of a category requested by a user. .

  The information processing apparatus according to the embodiment includes an acquisition unit, a determination unit, a presentation unit, and an update unit. The acquisition unit acquires group information including the number of members constituting the group and attributes of each member. The determination unit compares the group feature represented by using the group information with a determination rule that defines a matching condition for each of a plurality of categories, and determines which of the plurality of categories the group belongs to. The presenting unit presents the determination result of the determining unit. The update unit updates the determination rule according to a correction operation for the presented determination result.

FIG. 2 is a block diagram illustrating a functional configuration example of the information processing apparatus according to the first embodiment. The figure explaining an example of the method of estimating a group. The figure which shows an example of group information. The figure explaining the proximity of groups. The figure which shows an example of the determination rule. The figure which shows an example of a display screen. The figure which shows an example of the determination rule. The figure which shows the example of arrangement | positioning of the display information of a group. The figure which shows an example of a display screen. The figure which shows an example of a display screen. The figure which shows an example of the determination rule. The figure which shows an example of a display screen. The figure which shows an example of the determination rule. The figure which shows an example of a display screen. The figure which shows an example of a display screen. The figure which shows an example of the determination rule. The figure explaining an example of the display / correction method of a determination rule. The figure which shows the other example of a display screen. 6 is a flowchart illustrating an operation example of the information processing apparatus according to the first embodiment. The block diagram which shows the functional structural example of the information processing apparatus which concerns on 2nd Embodiment. The figure which shows an example of a display screen. The figure which shows an example of a display screen. The figure which shows an example of a display screen. The figure which shows an example of a display screen. The figure which shows an example of a display screen. The figure which shows an example of a display screen. 9 is a flowchart illustrating an operation example of an information processing apparatus according to a second embodiment. The block diagram which shows the hardware structural example of information processing apparatus.

  Hereinafter, an information processing apparatus, an information processing method, and a program according to embodiments will be described in detail with reference to the accompanying drawings. In the following description, components having similar functions are denoted by the same reference numerals, and repeated description is omitted as appropriate.

<First Embodiment>
FIG. 1 is a block diagram illustrating a functional configuration example of the information processing apparatus 10 according to the first embodiment. As illustrated in FIG. 1, the information processing apparatus 10 according to the present exemplary embodiment includes an acquisition unit 11, a cluster analysis unit 12, a determination unit 13, a presentation unit 14, an operation reception unit 15, and an update unit 16. .

  The acquisition unit 11 acquires group information regarding a group to be classified. The group information includes the number of members constituting the group and the attributes of each member.

  A group is a group of people who act together, and is estimated by analyzing a video V of a security camera, for example, as shown in FIG. Specifically, the group can be estimated based on the distance between the persons shown in the video V, the traveling direction, the proximity of the traveling speed, and the like. Further, the gaze direction of a person may be detected, and the group may be estimated based on the number of intersections in the gaze direction. It is also possible to estimate a group from clothes similarity and behavior (eg, being in the same table). In the present embodiment, as shown in FIG. 2, a single person who does not belong to another group is treated as one group for convenience.

  The attribute of each member constituting the group can be calculated based on, for example, the image characteristics of a person's face (or human body) detected from the video V of the security camera. In the present embodiment, gender and age (age) are assumed as attributes of each member constituting the group, but other attributes such as clothes and facial expressions may be used.

  The estimation of the group and the calculation of the attribute of each member may be performed inside the information processing apparatus 10 of the present embodiment or may be performed outside the information processing apparatus 10. When estimating the group and calculating the attribute of each member inside the information processing apparatus 10, for example, a video V of a security camera as shown in FIG. 2 is input to the information processing apparatus 10. And the acquisition part 11 acquires the group information containing the number of members which comprise a group, and the attribute of each member by analyzing this image | video V. FIG. On the other hand, when group estimation and member attribute calculation are performed outside the information processing apparatus 10, for example, group information as illustrated in FIG. 3 is input to the information processing apparatus 10 and acquired by the acquisition unit 11.

  In this embodiment, an example in which a group is estimated or an attribute of each member is calculated by analyzing a video V of a security camera is shown. However, any method can be used as long as the above-described group information can be acquired. Well, it is not limited to this example. For example, group information can be obtained based on the entrance time to the facility and the type of admission ticket (adult / children, etc.), or group information can be obtained based on member information registered in association with the admission ticket. Or you may get it.

  The cluster analysis unit 12 performs clustering of groups to be classified based on the group feature represented using the group information acquired by the acquisition unit 11.

  The group features are, for example, two groups consisting of one woman in their twenties and one man in their thirties, one woman in their thirties, one man in their forties, and one man under the age of 10 It is expressed using information included in the group information such as a group of three people, that is, the number of members constituting the group and the attributes of each member. The cluster analysis unit 12 clusters the groups to be classified so that groups having the same group characteristics are combined into one cluster.

  It is also possible to determine the relationship between the groups to be classified from the proximity of the group feature that is a clustering reference. In the example shown in FIG. 4, among the four groups A to D, the groups A to C have the same number of people (2 people), the groups A, B, and D have the same sex (female), and the groups B to D has the same minor sex (female). Accordingly, for example, the relationship between the groups can be understood such that the group D has many common points with the group B and the common points with the group A is small.

  The determination unit 13 collates the group characteristics of each group to be classified with the determination rule DR, and determines which of the plurality of registered categories each group belongs to. The registered category is registered as a category to which the group is classified.

  An example of the determination rule DR is shown in FIG. As shown in FIG. 5, the determination rule DR defines a matching condition for each registered category, and is stored in a predetermined storage area inside the information processing apparatus 10. In the example of FIG. 5, “parent and child”, “family”, “friend”, and “couple” are registered as registration categories, and the matching condition of “parent and child” is that the ratio between adults and minors is 1: 1. “Family” conforms to the condition that one adult male and one adult female and a minor (no matter how many), and “friends” conform to the same-sex, same-generation group The condition of “unquestioned” and the matching condition of “couple” indicate that the condition consists of two men and women of the same generation. Note that the determination rule DR may be any as long as it defines the conforming conditions for each registered category, and the type of the registered category and the conforming condition format are not limited to the example of FIG.

  The determination unit 13 confirms, for each group to be classified, which registration category the group belongs to, by confirming which registration category of the plurality of registration categories meets the matching condition, that is, A registration category as a classification destination of the group is determined. Then, the determination unit 13 gives a label representing the registered category to the group whose registered category is the classification destination. At this time, a label such as “others” indicating that the group feature does not meet the matching condition of any registered category is a group other than the registered category. In addition, when there are a plurality of groups having common group characteristics, that is, a plurality of groups clustered into the same cluster by the cluster analysis unit 12 do not need to be determined for each group. Good.

  The presentation unit 14 presents the determination result of the determination unit 13. For example, the presentation unit 14 displays a display screen indicating the determination result of the determination unit 13 on a display device used by the user. An example of a display screen displayed on the display device by the presentation unit 14 is shown in FIG. The display screen 20 shown in FIG. 6 is associated with each label 21 of a plurality of registered categories, and is determined to belong to each registered category by the determination unit 13 (a group to which the label of the registered group is assigned). Is displayed on the screen. In the example shown in FIG. 6, the four groups A to D are applicable to the “parent-child” matching condition that the ratio of adults and minors is 1: 1. It is placed in the “parent-child” display area. In addition, since the group E and F meet the matching condition of being composed of two men and women of the same generation, the display information 22 of the groups E and F is arranged in the “couple” display area.

  Here, if there is a group that is determined not to belong to any of the plurality of registered categories by the determination unit 13, the group is associated with an “other” label 21 that indicates a group other than the registered category. Display information 22 is arranged. In the example illustrated in FIG. 6, the group G does not meet any of the registration conditions of the plurality of registered categories, and is determined not to belong to any registered category. Therefore, the display information 22 of the group G displays “others”. Arranged in the area. At this time, for example, as illustrated in FIG. 7, “other” may be set as a temporary registration category, and a condition that the group feature of the group G is applied may be added to the determination rule DR as a matching condition of the “other” category. .

  The display information 22 indicating each group on the display screen 20 includes, for example, an image showing each member constituting the group or an icon representing each member. The display screen 20 shown in FIG. 6 shows an example in which an icon that can estimate the attributes of the constituent members of the group is used as the display information 22 of each group. Further, text information describing the group characteristics of each group may be used as the display information 22 together with the image or icon of the group member or instead of the image or icon of the member.

  In addition, for a plurality of groups grouped into one cluster by clustering by the cluster analysis unit 12, the plurality of groups may be aggregated with a single display information 22. Since a plurality of groups belonging to one cluster have a common group feature, display information 22 indicating any one of the plurality of groups may be arranged on the display screen 20. Further, when a plurality of groups belonging to one cluster are aggregated with one display information 22, for example, if the number of groups belonging to the cluster is 2, “× 2”, and if the number of groups is 3, “× 3”. Thus, it is desirable to include information indicating the number of groups belonging to the cluster in the display information 22. In addition, when the user performs an operation of selecting display information 22 in which a plurality of groups are aggregated, the individual display information 22 of the plurality of groups may be expanded.

  Further, when the display information 22 of a plurality of groups determined to belong to the same registered category is arranged in association with the label 21 of the registered category, the display information 22 of the plurality of groups depends on the proximity of the group feature. It is desirable to be arranged. That is, for example, as shown in FIG. 8, it is desirable that the display information 22 is arranged close to the groups having many common points, and the display information 22 is arranged apart from the groups having few common points. FIG. 8 shows an example in which the display information 22 of the four groups A to D shown in FIG. 4 is arranged in the “parent-child” display area according to the proximity of the group characteristics. Further, when it is determined that groups having many common points belong to different registration categories, the arrangement for each registration category may be determined so that the display information 22 of these groups is arranged nearby.

  The display screen 20 displayed on the display device by the presentation unit 14 is used not only to present the determination result of the determination unit 13 to the user but also for the user to perform a correction operation on the determination result of the determination unit 13. For example, as shown in FIG. 6, a check box 23 is arranged near the display information 22 of each group on the display screen 20, and when the user checks the check box 23 corresponding to the group whose determination result is to be corrected, A correction operation can be performed on the determination result of the group. The user can also perform a correction operation on the determination result by changing the description of the label 21 on the display screen 20. A specific example of the correction operation by the user using the display screen 20 will be described later in detail.

  The operation reception unit 15 receives a user operation using the display screen 20 described above. In the present embodiment, the user operation received by the operation receiving unit 15 is a correction operation for the determination result of the determination unit 13 presented to the user by the display on the display screen 20. The operation content received by the operation receiving unit 15 is transmitted to the updating unit 16.

  The updating unit 16 updates the determination rule DR stored in a predetermined storage area inside the information processing apparatus 10 according to the correction operation received by the operation receiving unit 15.

  For example, it is assumed that the user performs an operation (first correction operation) for excluding a group (first group) determined to belong to one of a plurality of registered categories (first category) from the first category. In this case, the update unit 16 updates the determination rule DR according to the first correction operation so that the conformity condition of the first category is a condition that the group feature of the first group does not apply.

  Further, it is assumed that the user performs an operation (second correction operation) for adding the first group excluded from the first category to another category (second category). In this case, the update unit 16 updates the determination rule DR according to the second correction operation so that the conformity condition of the second category is a condition that the group feature of the first group is applicable.

  Further, it is assumed that the user performs an operation (third correction operation) for designating a new category other than a plurality of registered categories as a category to which the first group excluded from the first category belongs. In this case, the update unit 16 updates the determination rule DR so as to newly add a condition that the group feature of the first group is applied as the matching condition of the third category in accordance with the third correction operation.

  In addition, an operation (fourth correction operation) in which the user adds a group (second group) determined not to belong to any of the plurality of registered categories to any one of the plurality of registered categories (first category). Suppose you went. In this case, the update unit 16 updates the determination rule DR according to the fourth correction operation so that the conformity condition of the first category is a condition that the group feature of the second group is applicable.

  When the determination rule DR is updated by the update unit 16, the determination by the determination unit 13 is performed based on the updated new determination rule DR. In addition, the determination result of the determination unit 13 based on the updated new determination rule DR is reflected on the display screen 20.

  Hereinafter, assuming that the display screen 20 having the configuration illustrated in FIG. 6 is displayed on the display device, a specific example of the correction operation by the user using the display screen 20 and the update of the determination rule DR according to the correction operation Will be described. The example described below is merely an example, and the method of correcting the determination result of the determination unit 13 and updating the determination rule DR is not limited to this example.

  First, as shown in FIG. 9, it is assumed that the user checks a check box 23 corresponding to the display information 22 of the group D arranged in the “parent-child” display area on the display screen 20. In this case, as shown in FIG. 10, the display information 22 of the group D is excluded from the “parent / child” display area, and is arranged in the “new category” display area in association with the label 21 such as “new category”. Is done.

  In this case, the update unit 16 determines that the matching condition of “parent and child” included in the determination rule DR does not apply to the group D group characteristics (a group of four people including two adult women and two minor women). The determination rule DR is updated so that For example, as shown in FIG. 11, the matching condition of “parent and child” included in the determination rule DR is changed to a condition that includes one adult and one minor. At this time, as shown in FIG. 11, “new category” may be set as a temporary registration category, and a condition that the group feature of group D is applied may be added to the determination rule DR as the “new category” matching condition. .

  For example, as illustrated in FIG. 12, it is assumed that the user changes the label 21 of “Others” to the label 21 of “Family” that is one of the registered categories. This operation can be realized, for example, by selecting a label 21 to be changed on the display screen 20 and directly inputting characters. In this case, the updating unit 16 sets the group characteristics of the group G (one adult woman and two underage women) that are included in the display area of “others” as the matching condition of “family” included in the determination rule DR. The determination rule DR is updated so that the condition of 3 groups of For example, as shown in FIG. 13, the matching condition of “family” included in the determination rule DR is changed to a condition that consists of one adult woman and zero or one adult man and a minor (the number of people does not matter). .

  Further, for example, as illustrated in FIG. 14, it is assumed that the user changes the label 21 of “new category” to the label 21 of “family” that is one of registered categories. In this case, as shown in FIG. 15, the display area of “family” on the display screen 20 is expanded, and the display information 22 of the group D arranged in the display area of “new category” is displayed as “family”. Move to the area. Then, the updating unit 16 sets the group family characteristics (two adult women and two underage women) in the “new group” display area where the “family” matching condition included in the determination rule DR is The determination rule DR is updated so that the condition of 4 groups of For example, as shown in FIG. 16, the matching condition of “family” included in the determination rule DR is changed to a condition that includes one or more adult women and zero or one adult man and a minor (the number of people is not required). The

  Although not shown, the user may be able to register a new category indicated by the category name by changing the label 21 of “new category” to a desired category name on the display screen 20. For example, it is assumed that the user changes the label 21 of “New Category” to the label 21 of “Mama Friends” on the display screen 20 shown in FIG. In this case, the update unit 16 sets “mama friend” as a new registration category, and the group feature of group D (4 adult women and 2 minor women 4 as the matching condition of “mama friend”). A condition for which (name group) applies is added to the determination rule DR. Thereby, the category of the group which a user can image intuitively can be registered by simple operation.

  Although the example in which the determination rule DR is updated according to the operation on the display screen 20 has been described above, the determination rule DR stored in the storage area is read according to a predetermined operation and displayed on the display device. The registration category name and the matching conditions may be directly modified by the user. For example, when the matching condition for “parent and child” included in the determination rule DR is a condition that the ratio of adults to minors is 1: 1, the user directly sets the matching condition for “parent and child” to adult 1 You may make it change into the conditions which consist of a name and one minor. Further, the display of the determination rule DR and the user's correction operation are not limited to text display / correction. For example, as shown in FIG. 17, display / correction may be performed using an attribute icon.

  Further, the user may be able to change the definition and granularity of attributes used for the matching condition for each registration category of the determination rule DR. For example, the classification criteria of “adult” and “underage” may be changed by the user to “20 years or older” and “under 20 years”, or may be changed to the classification criteria in increments of 10 years.

  In addition, in the display screen 20 illustrated in FIG. 6 and the like, the display information 22 of each group is arranged according to the proximity of the group feature. However, the display screen showing the determination result of the determination unit 13 includes each group. Any configuration can be used as long as it can be displayed in an easy-to-understand manner which registration category is classified and what common groups are classified into the same registration category. The display screen 20 illustrated in FIG. The configuration is not limited. For example, as shown in FIG. 18, display information 22 of a plurality of groups determined to belong to the same registration category may be displayed on a display screen 20 having a configuration in which the display information 22 is arranged in a list format in the arrangement order corresponding to the group characteristics.

  In this case, as shown in FIG. 18, a category list 25 displaying the number of groups determined to belong to the registered category is displayed in association with the label 21 of each registered category. For the registration category selected by the user, the display information 22 of each group determined to belong to the registration category may be displayed in a list format. Thereby, even when the number of groups to be classified is large, the determination result by the determination unit 13 can be presented so that the user can easily confirm.

  In the display screen 20 shown in FIG. 18, display information 22 of each group that is determined to belong to the registered category by selecting the registered category by designating the desired registered category in the category list 25 by clicking or the like. Be expanded. In addition, by designating any one of the display information 22 by a click operation or the like, a group corresponding to the display information 22 is selected. For example, the same correction operation as in the case of using the display screen 20 illustrated in FIG. It can be performed.

  FIG. 19 is a flowchart illustrating an operation example of the information processing apparatus 10 according to the present embodiment described above. In addition, since the specific content of each step of FIG. 19 is as above-mentioned, detailed description is abbreviate | omitted suitably.

  When the process shown in the flowchart of FIG. 19 is started, the acquisition unit 11 first acquires group information of a group to be classified (step S101). The group information acquired by the acquisition unit 11 is sent to the cluster analysis unit 12.

  Next, the cluster analysis unit 12 determines the classification target based on the group characteristics of each group represented by using the group information acquired by the acquisition unit 11 (the number of members constituting the group and the attribute of each member). Clustering is performed (step S102). By this clustering, groups having common group characteristics are combined into one.

  Next, the determination unit 13 takes out one group (cluster) to be classified (step S103), and collates the group feature of this group (cluster) with the determination rule DR, whereby a plurality of groups (clusters) are obtained. Which registration category belongs, that is, the registration category that is the classification destination of this group (cluster) is determined (step S104). Thereafter, the determination unit 13 confirms whether there is an undetermined group among the groups to be classified (step S105). If there is an undetermined group (step S105: Yes), the process returns to step S103. The subsequent processing is repeated.

  On the other hand, when the determination by the determination unit 13 is completed for all the groups to be classified (step S105: No), the presentation unit 14 displays the above-described display screen 20 on the display device, for example, whereby the determination by the determination unit 13 is performed. The result is presented to the user (step S106). Then, the operation receiving unit 15 confirms whether or not there is a correcting operation for the determination result (step S107). If there is a correcting operation (step S107: Yes), the updating unit 16 receives the operation receiving unit 15. The determination rule DR is updated according to the corrected operation (step S108).

  Thereafter, the processing from step S106 to step S108 is repeated until the determination result of the determination unit 13 is corrected to the shape desired by the user. Then, when the correction operation for the determination result is not performed (step S107: No), the group classification is determined and the series of processes is ended.

  The information processing apparatus 10 according to the present embodiment is useful in applications such as customer analysis, for example. That is, by classifying customer groups into registered categories and counting the number of groups for each registered category, it is possible to analyze in what group the customer is acting. Moreover, if the acquisition part 11 is set as the structure which further acquires the information showing a condition or action, such as a customer's position, time information, conducting wire information, purchase information, in addition to the above-mentioned group information, according to these information, a registration category You can also count the number of groups for each.

  As described above in detail with reference to specific examples, in the information processing apparatus 10 according to the present embodiment, the determination unit 13 checks the group characteristics of the group to be classified with the determination rule DR, and this group. Is included in a plurality of registered categories, and the presentation unit 14 presents the determination result of the determination unit 13 to the user. Then, the update unit 16 updates the determination rule DR in accordance with the user's correction operation for the determination result. Therefore, according to the information processing apparatus 10 of this embodiment, it is possible to appropriately classify groups according to purposes by reflecting the definition of the category required by the user.

  In the above description, it is assumed that the information processing apparatus 10 stores a single determination rule DR. However, the information processing apparatus 10 according to the present embodiment may be, for example, a season, time, weather, or event. A plurality of determination rules DR for each situation or each user are stored, and used by the determination unit 13 based on input information (information specifying a situation, a user ID specifying a user, etc.) input from the outside. The determination rule DR may be switched.

  For example, the determination rule DR used by the determination unit 13 may be switched in accordance with a specified specific event. On Mother's Day, not only is a group of older and older people grouping a group of women (mother and child) into one category, but also by age group of the younger (whether the child is an adult or a minor) For example) is used. This makes it possible to perform customer analysis that is useful in developing a marketing strategy for Mother's Day. In addition, on Father's Day, the group of older people and older people not only classifies the number of male groups (fathers and children) into one category, but also classifies them into younger age groups. The determination rule DR is used. This makes it possible to conduct customer analysis that is useful in developing a marketing strategy for Father's Day. Note that father and child on Mother's Day and mother and child on Father's Day do not need to be analyzed in detail by child age (low priority), so it is better not to classify them into age-specific categories Easy to grasp trends. In addition, other than Mother's Day and Father's Day, classification by parental gender may not be necessary.

  Also, in marketing according to events such as Mother's Day and Father's Day, it may be effective to classify children as parents with children even if the child is an adult. There are many cases where the definition of a category to which a group is classified is different depending on the user's charge, such as it is not necessary to classify a child and a parent as a parent and child (there is no need to distinguish it from a friend who is an adult or more). For this reason, it is also effective to switch the determination rule DR used by the determination unit 13 for each user.

Second Embodiment
Next, a second embodiment will be described. The present embodiment is an example in which the arrangement of the group display information 22 on the display screen 20 can be changed in accordance with a user operation. That is, in the present embodiment, for example, the presentation unit 14 displays on the display device a display screen 20 (see FIG. 18) having a configuration in which display information 22 of a plurality of groups determined to belong to the same category is arranged in a list format. At this time, the arrangement order of the display information 22 is determined with priority given to the items designated among the items (for example, sex, number of people, age, etc.) constituting the group feature. Further, in the present embodiment, the cluster analysis unit 12 performs the clustering of the group again in accordance with an operation for changing the granularity of the items constituting the group feature, and the result is reflected on the display screen 20.

  FIG. 20 is a block diagram illustrating a functional configuration example of the information processing apparatus 10 according to the second embodiment. In the present embodiment, the operation receiving unit 15 performs not only a correction operation for the determination result of the determination unit 13 but also an operation for specifying an item to be prioritized among items constituting the group feature, and the granularity of the item constituting the group feature. Accept the operation to change. When the operation receiving unit 15 receives an operation for designating a priority item among the items constituting the group feature, the operation content is transmitted to the presentation unit 14. When the operation accepting unit 15 accepts an operation for changing the granularity of items constituting the group feature, the operation content is transmitted to the cluster analyzing unit 12.

  The presenting unit 14 according to the present embodiment determines the arrangement order of the display information 22 on the display screen 20 in accordance with the operation content received from the operation receiving unit 15 in consideration of the group feature item designated by the user. To do. Further, the cluster analysis unit 12 of this embodiment performs group clustering again according to the operation content received from the operation reception unit 15. If there is a change in the clustering result, the result is reflected on the display screen 20.

  Hereinafter, a specific example of a user operation and a change in the display screen 20 according to the user operation in the present embodiment will be described. In addition, the example demonstrated below is an example to the last, and the structure of the display screen 20 and a user's operation method are not limited to this example.

  In the present embodiment, the presentation unit 14 displays a display screen 20 having a configuration illustrated in FIG. 21 on the display device, for example. The display screen 20 shown in FIG. 21 changes the granularity of the items constituting the group feature and the operation for designating the priority item among the items constituting the group feature with respect to the display screen 20 shown in FIG. There are item tabs (“gender” tab 26, “number of people” tab 27, and “age” tab 28) for performing operations, and a “+” button 29 for performing operations for setting priorities of a plurality of items. This is an added configuration. The item tab specifies a category (all / adult / minor) that refers to the value of the item to determine the order of display information 22 and the order (ascending / descending) of display information 22 based on the item. It can be configured. Note that the category referring to the value of the item may be changed according to the user's operation, as in the case of changing the granularity of the item described later.

  First, an example of determining the arrangement order of the group display information 22 on the display screen 20 will be described. For example, as shown in FIG. 21, in a state where the display information 22 of each group determined to belong to “parent and child” is expanded, the user selects “△ (ascending order)” of “adult” on the “sex” tab 26. Suppose that a click operation is performed. In this case, the arrangement order of the display information 22 of each group determined to belong to “parent and child” is determined so that the display information 22 of the group including the adult male is arranged at the top.

  Further, for example, as shown in FIG. 22, in the state where the display information 22 of each group determined to belong to “parent and child” is expanded, the user selects “adult” “▽ (descending order)” on the “sex” tab 26. ”Is clicked. In this case, the arrangement order of the display information 22 of each group determined to belong to “parent and child” is determined so that the display information 22 of the group including the adult female is arranged at the top. At this time, as shown in FIG. 22, when there are a plurality of groups including adult women, for example, priority is given to the other items specified in the previous operation according to the priority order of other items set in advance. Thus, the arrangement order of the display information 22 of a plurality of groups including adult women may be determined.

  Further, for example, as shown in FIG. 23, in a state where the display information 22 of each group determined to belong to “parent and child” is expanded, the user displays “▽ (descending order)” of “all” in the “number of people” tab 27. ”Is clicked. In this case, the arrangement order of the display information 22 of each group determined to belong to “parent and child” is determined so that the display information 22 of the group with a small total number of people is arranged at the top. At this time, as shown in FIG. 23, when there are groups having the same number of people as a whole, for example, priority is given to the other items specified in the previous operation in accordance with the priority order of other items set in advance. The arrangement order of the display information 22 of the groups having the same total number of persons may be determined.

  Also, for example, as shown in FIG. 24, it is assumed that the user performs an operation of clicking the “+” button 29 in a state where the display information 22 of each group determined to belong to “parent and child” is expanded. In this case, a dialog box 30 for setting the priority order of a plurality of items is displayed as a pop-up. When the user sets the priority order of a plurality of items using this dialog box 30, the arrangement order of the display information 22 of each group determined to belong to “parent and child” is determined according to the set priority order of each item. It is determined. The dialog box 30 for designating the priority order of a plurality of items may be displayed as a screen different from the display screen 20.

  In the above example, the arrangement order of the display information 22 is determined by an operation on the item tab or the “+” button 29 for each item constituting the group feature. For example, “order from male to female”, The user may be able to directly specify a rule for determining the arrangement order of the display information 22, such as “arrange in order of increasing number of people”.

  In the above example, the arrangement order of the group display information 22 is determined according to a user operation on the display screen 20, but the present invention is not limited to this. For example, a history of correction operations for the determination results of the past determination unit 13 is recorded as a log, and items selected based on the history of the correction operations (for example, among the conforming conditions of the determination rule DR according to the correction operation) The order in which the display information 22 is arranged may be determined by giving priority to the item frequently changed in step (b).

  Next, an example of changing the granularity of items constituting the group feature will be described. For example, as shown in FIG. 25, it is assumed that the user performs an operation of double-clicking or right-clicking the “age” tab 28. In this case, a dialog box 40 for changing the granularity of the item “age” constituting the group feature is popped up. Then, if the user changes the granularity of the item “age” constituting the group feature from, for example, “10-year-old increments” to “adult / minor” using this dialog box 40, the operation content is cluster analysis. It is transmitted to part 12. In this case, the cluster analysis unit 12 performs the clustering of the groups again based on the group characteristics of each group in which the granularity of the “age” item is changed from “10-year increments” to “adult / minor”. Thus, for example, a group consisting of women in their twenties and women under the age of 10 and a group consisting of women in the thirties and women under the age of ten are grouped as a group consisting of adult women and minor women. As a result, as shown in FIG. 26, the display information 22 of these groups is integrated and displayed on the display screen 20.

  In the above example, the example of changing the granularity of “age” among the items constituting the group feature has been described. However, the items that can change the granularity are not limited thereto. For example, in the case of “number of people”, it is conceivable to distinguish from the method of counting by one person to the method of counting by 10 persons, the number of adults (for example, 10 or more) and the small number of persons (for example, less than 10). The granularity of the “number of people” can be changed.

  Further, the presentation unit 14 displays the priority items and classifications of the group features designated by the above-described user operation, the granularity of the item of the group feature to be changed, etc. on the display screen 20 or another screen and presents them to the user. You may do it. In this case, for example, a list of group feature items is displayed, and the current priority item and the granularity of each item are highlighted, and the current priority item and the granularity of each item are presented to the user. Also good. Thereby, user operability is improved.

  FIG. 27 is a flowchart illustrating an operation example of the information processing apparatus 10 according to the present embodiment described above. Note that the processing from step S201 to step S208 in FIG. 27 is the same as the processing from step S101 to step S108 in FIG. 19 (processing of the first embodiment), and thus the description thereof is omitted.

  In the present embodiment, when it is determined in step S207 that the correction operation for the determination result of the determination unit 13 has not been performed (step S207: No), the operation reception unit 15 displays the display information 22 on the display screen 20. It is confirmed whether or not there is an operation for changing the arrangement order of (step S209). And if there exists operation which changes the arrangement | sequence order of the display information 22 on the display screen 20 (step S209: Yes), the presentation part 14 will determine the arrangement | sequence order of the display information 22 according to the operation, and will step S206 Returning, the display screen 20 on which the display information 22 is arranged in the changed arrangement order is displayed on the display device, so that the determination result of the determination unit 13 is presented to the user.

  Further, when there is no operation for changing the arrangement order of the display information 22 (step S209: No), the operation receiving unit 15 checks whether there is an operation for changing the granularity of items constituting the group feature (step). S210). If there is an operation for changing the granularity of the items constituting the group feature (step S210: Yes), the process returns to step S202, and the cluster analysis unit 12 performs grouping based on the group feature whose item granularity is changed. Perform the clustering again.

  Thereafter, the processing from step S206 to step S210 is repeated until the determination result of the determination unit 13 is corrected to the shape desired by the user. Then, the correction operation for the determination result is not performed (step S207: No), and the operation for changing the arrangement order of the display information 22 and the operation for changing the granularity of items constituting the group feature are not performed (step S209: No, Step S210: No) The group classification is confirmed and the series of processing ends.

  As described above, the information processing apparatus 10 according to the present embodiment can change the arrangement of the group display information 22 on the display screen 20 and the granularity of items constituting the group feature in accordance with a user operation. Therefore, in the same manner as in the first embodiment described above, in addition to reflecting the definition of the category required by the user and appropriately classifying the group according to the purpose, the user can change the order of the group display information 22 and The determination result of the determination unit 13 can be confirmed while appropriately changing the group, and for example, a new group (cut) can be found.

<Supplementary explanation>
The information processing apparatus 10 of each embodiment described above can be realized by using, for example, a general-purpose computer as basic hardware. That is, the function of each unit of the information processing apparatus 10 described above can be realized by causing a processor mounted on a general-purpose computer to execute a program. At this time, the information processing apparatus 10 may be realized by installing the above program in a computer in advance, or storing the program in a storage medium such as a CD-ROM or distributing the program through a network. Thus, this program may be realized by appropriately installing it in a computer.

  FIG. 28 is a block diagram illustrating a hardware configuration example of the information processing apparatus 10 according to the embodiment. For example, as shown in FIG. 28, the information processing apparatus 10 includes a processor 101 such as a CPU (Central Processing Unit), a memory 102 such as a RAM (Random Access Memory) and a ROM (Read Only Memory), and an HDD (Hard Disk Drive). ) And SSD (Solid State Drive) storage device 103, a display device 106 such as a liquid crystal panel, and a device I / F 104 for connecting devices such as a keyboard, mouse, and touch panel input device 107, and communication with the outside of the device A hardware configuration as a general computer including a communication I / F 105 that performs the above and a bus 108 that connects these units.

  When the information processing apparatus 10 has a hardware configuration as shown in FIG. 28, for example, the processor 101 reads out and executes a program stored in the storage device 103 or the like using the memory 102, whereby the above-described units ( The functions of the acquisition unit 11, the cluster analysis unit 12, the determination unit 13, the presentation unit 14, the operation reception unit 15, and the update unit 16) can be realized.

  Note that some or all of the functions of each unit of the information processing apparatus 10 described above are dedicated hardware (not a general-purpose processor but a general-purpose processor) such as an application specific integrated circuit (ASIC) or a field-programmable gate array (FPGA). It can also be realized by a processor). Moreover, the structure which implement | achieves the function of each part mentioned above using a some processor may be sufficient.

  Further, the information processing apparatus 10 according to the embodiment may be configured as an information processing system using a plurality of computers and realizing the functions of the above-described units distributed over the plurality of computers. Further, the information processing apparatus 10 according to the embodiment may be a virtual machine that operates on a cloud system.

  As mentioned above, although embodiment of this invention was described, embodiment described here is shown as an example and is not intending limiting the range of invention. The novel embodiments described herein can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the spirit of the invention. The embodiments and modifications described herein are included in the scope and gist of the invention, and are also included in the invention described in the claims and the equivalents thereof.

DESCRIPTION OF SYMBOLS 10 Information processing apparatus 11 Acquisition part 12 Cluster analysis part 13 Determination part 14 Presentation part 15 Operation reception part 16 Update part DR determination rule

Claims (17)

An acquisition unit for acquiring group information including the number of members constituting the group and attributes of each member;
A determination unit that matches a group feature represented using the group information with a determination rule that defines a matching condition for each of a plurality of categories, and determines which of the plurality of categories the group belongs to;
A presentation unit for presenting a determination result of the determination unit;
An update unit that updates the determination rule according to a correction operation on the presented determination result;
An information processing apparatus comprising: In accordance with a first correction operation for excluding the first group determined to belong to the first category of the plurality of categories from the first category, the update condition is that the conforming condition of the first category is The information processing apparatus according to claim 1, wherein the determination rule is updated so that the group feature of the first group becomes a condition that does not apply. The update unit may further include a matching condition of the second category according to a second correction operation for adding the first group to the second category of the plurality of categories, wherein the group feature of the first group is The information processing apparatus according to claim 2, wherein the determination rule is updated so as to satisfy a condition. The update unit further includes a group of the first group as a matching condition of the third category in response to a third correction operation that designates a third category other than the plurality of categories as a category to which the first group belongs. The information processing apparatus according to claim 2, wherein the determination rule is updated so as to newly add a condition to which the feature applies. The presenting unit presents the determination result in which a second group determined not to belong to any of the plurality of categories is associated with a label indicating that the group is a group other than the plurality of categories. Information processing apparatus as described in any one of thru | or 4. The update unit is configured such that a conformance condition of the first category is applied to a group feature of the second group according to a fourth correction operation for adding the second group to the first category of the plurality of categories. The information processing apparatus according to claim 5, wherein the determination rule is updated so that 7. The display unit displays a display screen on which display information indicating a group determined to belong to each category is arranged in association with each label of the plurality of categories on a display device. The information processing apparatus according to one item. The information processing apparatus according to claim 7, wherein the display information includes at least one of an image showing each member constituting the group or an icon representing each member and text information describing the group feature. A cluster analysis unit for clustering groups based on the group features;
The information processing apparatus according to claim 7, wherein the presentation unit causes the display device to display the display screen in which a plurality of groups belonging to one cluster are aggregated with one display information. The information processing apparatus according to claim 9, wherein the cluster analysis unit performs group clustering again according to an operation for changing a granularity of items constituting the group feature used for clustering. 11. The display unit causes the display device to display the display screen in which display information of a plurality of groups determined to belong to the same category is arranged according to the proximity of the group feature. The information processing apparatus according to one item. The display unit causes the display device to display the display screen in which display information of a plurality of groups determined to belong to the same category is arranged in a list format in an arrangement order corresponding to the group feature. The information processing apparatus according to any one of the above. The information processing apparatus according to claim 12, wherein the presenting unit determines the arrangement order by giving priority to an item designated among items constituting the group feature. The information processing apparatus according to claim 12, wherein the presenting unit preferentially determines the arrangement order among items constituting the group feature, with preference given to an item selected based on the history of the correction operation. The information processing apparatus according to any one of claims 1 to 14, wherein a plurality of the determination rules are stored and the determination rule used by the determination unit is switched based on input information input from the outside. An acquisition step of acquiring group information including the number of members constituting the group and attributes of each member;
A determination step of checking a group feature represented using the group information with a determination rule that defines a matching condition for each of a plurality of categories, and determining which of the plurality of categories the group belongs to;
A presenting step for presenting a determination result of the determination step;
An update step of updating the determination rule according to a correction operation on the presented determination result;
An information processing method including: On the computer,
A function of an acquisition unit that acquires group information including the number of members constituting the group and attributes of each member;
A function of a determination unit that matches a group feature represented using the group information with a determination rule that defines a matching condition for each of a plurality of categories, and determines which of the plurality of categories the group belongs to;
A function of a presentation unit for presenting a determination result of the determination unit;
A function of an update unit that updates the determination rule in accordance with a correction operation on the presented determination result;
A program to realize

Images