JP6963053B2 - Judgment device, judgment method, and judgment program - Google Patents

Description

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

Conventionally, a technique for providing information to a user based on a so-called context such as a user's state or situation has been provided. For example, a technique for grasping a user's state and distributing information by using a combination of an area type and a time type related to a position is provided. Further, a technique for providing information to a user is provided by using a prediction model based on the context of the user (hereinafter, simply referred to as a "model").

International Publication No. 2013/164911

However, with the above-mentioned prior art, it may be difficult to provide appropriate information to the user. For example, if the model generated based on the user's context is not appropriate, it is difficult to provide the user with appropriate information. In addition, the location of the user's home, office, etc. may change over time. In such cases, it may be necessary to change information about the user's context and information about the user's user attributes.

The present application has been made in view of the above, and an object of the present application is to provide a determination device, a determination method, and a determination program that can appropriately change information about a user by predicting accuracy of a model based on a context.

Determining apparatus according to the present application, it is generated based on the action history and user attributes of the user, an acquisition unit for acquiring a model to predict the predetermined target, the acquisition model by the acquisition unit, the predetermined for the user depending on the target of prediction accuracy, and further comprising a, a determination unit for determining whether to change the information on the user attribute information about the context of the user or the user.

According to one aspect of the embodiment, there is an effect that the information about the user can be appropriately changed by the prediction accuracy of the model based on the context.

FIG. 1 is a diagram showing an example of a determination process according to an embodiment. FIG. 2 is a diagram showing an example of the generation process according to the embodiment. FIG. 3 is a diagram showing an example of the distribution process before the context change according to the embodiment. FIG. 4 is a diagram showing an example of the distribution process after the context is changed according to the embodiment. FIG. 5 is a diagram showing a configuration example of the distribution device according to the embodiment. FIG. 6 is a diagram showing an example of a user information storage unit according to the embodiment. FIG. 7 is a diagram showing an example of the behavior information storage unit according to the embodiment. FIG. 8 is a diagram showing an example of the divided information storage unit according to the embodiment. FIG. 9 is a diagram showing an example of the cluster information storage unit according to the embodiment. FIG. 10 is a diagram showing an example of the learning information storage unit according to the embodiment. FIG. 11 is a diagram showing an example of the content information storage unit according to the embodiment. FIG. 12 is a flowchart showing an example of the generation process according to the embodiment. FIG. 13 is a flowchart showing an example of the generation process according to the embodiment. FIG. 14 is a flowchart showing an example of the distribution process according to the embodiment. FIG. 15 is a flowchart showing an example of the determination process according to the embodiment. FIG. 16 is a diagram showing an example of determination of a plurality of candidates according to an embodiment. FIG. 17 is a hardware configuration diagram showing an example of a computer that realizes the function of the distribution device.

Hereinafter, a determination device according to the present application, a determination method, and a mode for carrying out the determination program (hereinafter, referred to as “embodiment”) will be described in detail with reference to the drawings. The determination device, determination method, and determination program according to the present application are not limited by this embodiment. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

(Embodiment)
[1. Determination process〕
First, an example of the determination process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of a determination process according to an embodiment. FIG. 1A shows a determination process for an existing user, and FIG. 1B shows a change process for a new user. In the example shown in FIG. 1, the cluster information list ML11 shows information on clustering when a model for predicting interest in content in the context of each user is generated by the generation process in the distribution system 1 shown in FIG. Specifically, the cluster information list ML11-1 in FIG. 1A is a mass (hereinafter, may be referred to as “mass MS”) which is an area where one user and one context intersect. Indicates which model is assigned among the models M1 to M6 and the like. The context referred to here corresponds to the state and situation of the user including the environment in which the user is placed, and the details will be described later.

The cluster information list ML11-1 in (A) of FIG. 1 corresponds to the cluster information storage unit 124 (see FIG. 9), and includes six clusters indicated by M1 to M6 shown in each mass MS. show. For example, each model M1 to M6 is generated based on the division information corresponding to M1 to M6 shown in each mass MS stored in the division information storage unit 123 (see FIG. 8). Although the details will be described later, the divided information here means information in which the user's behavior information is divided for each context. For example, the behavior information is information that distributes content to each user and indicates whether or not each user has an action with respect to the distributed content. Further, in the mass MS in the cluster information list ML11-1, a model generated by a predetermined method is assigned to the mass MS whose symbols M1 to M6 are not shown, but the details will be described later.

For example, in FIG. 1A, the mass MS corresponding to the context CT11 of the user U1, the mass MS corresponding to the context CT15 of the user U2, the mass MS corresponding to the context CT17 of the user U2, and the context CT13 of the user U4. It is shown that the same model M1 is assigned to the corresponding mass MS. That is, it is shown that the model M1 is generated by using the union information that combines the division information included in the above four mass MSs. Further, as shown in the learning information storage unit 125 (see FIG. 10), the model information regarding the model M1 is that the weight of the feature 1 is "0.5", the weight of the feature 2 is "-0.4", and the weight of the feature 3 is "-0.4". Indicates that the weight is "0.2" or the like. For example, when the distribution system 1 requests the distribution of the content in the context CT11 corresponding to the case where the user U1 is at home (home) in the morning, the distribution system 1 determines the content to be distributed to the user U1 using the model M1.

For example, the distribution device 100 (see FIG. 5) determines whether to change the information regarding the context of the user or the information regarding the user attributes of the user according to the prediction accuracy of the model assigned to the user. The prediction accuracy here means the probability that the presence or absence of user behavior can be predicted. The example of FIG. 1 shows a case where the prediction accuracy is the probability that the user selects (clicks) the delivered content when the content is delivered using the model corresponding to the user's contest. Further, the information regarding the context referred to here includes, for example, the division information assigned to each mass MS in the division information storage unit 123 and the information regarding the model assigned to each mass MS in the cluster information storage unit 124. You may. Further, the information regarding the user attributes referred to here may include, for example, information regarding each user in the user information storage unit 121. In the following, it is a predetermined condition regarding the prediction accuracy that the number of pieces having a low prediction accuracy is 0.

As shown in FIG. 1A, in the cluster information list ML11-1, it is assumed that the prediction accuracy of the user U1 in the context CT11 and the prediction accuracy of the user U1 in the context CT12 are low. The term "low prediction accuracy" as used herein means that the prediction accuracy of the model in the corresponding combination of users and contexts is less than a predetermined threshold value (for example, 75%). That is, in FIG. 1A, it is shown that the prediction accuracy is low when the content is delivered to the user U1 by using the model M1 in the context CT11 of the user U1. Further, FIG. 1A shows that the prediction accuracy is low when the content is delivered to the user U1 by using the model M2 in the context CT12 corresponding to the case where the user U1 is in the office in the morning.

As described above, since the prediction accuracy of the two models, the model M1 assigned to the context CT11 of the user U1 and the model M2 assigned to the contest cost CT12, is low, the distribution device 100 (see FIG. 5) is used by the user. It is determined that the information regarding the context of U1 or the information regarding the user attribute of user U1 is changed. Note that FIG. 1A shows a case where the distribution device 100 determines that the information regarding the context of the user U1 is changed. Here, since the context CT11 corresponds to the morning house and the Conte cost CT12 corresponds to the morning office, the context CT11 and the context CT12 have a common time zone in the morning. Therefore, the distribution device 100 determines that the information regarding the context of the user U1 can be replaced, and determines that the information regarding the context of the user U1 is replaced.

In FIG. 1A, the distribution device 100 changes the context by exchanging the home and office of the user U1 in the cluster information list ML11-1 based on the above-mentioned determination (step S1). Specifically, the distribution device 100 replaces the model M1 assigned to the context CT11 of the user U1 with the model M2 assigned to the context CT12 (step S1-1). In this case, the distribution device 100 may replace the models assigned to the other contexts CT13 to CT18 of the user U1. For example, the distribution device 100 may replace the model M3 assigned to the context CT13 of the user U1 with the model assigned to the context CT14 (step S1-2). Further, for example, the distribution device 100 may replace the model M5 assigned to the context CT15 of the user U1 with the model M4 assigned to the context CT16 (step S1-3). Further, for example, the distribution device 100 may replace the model assigned to the context CT17 of the user U1 with the model M2 assigned to the context CT18 (step S1-4).

Due to the context change in step S1, as shown in the cluster information list ML11-2 in FIG. 1A, the model assigned to each mass MS corresponding to the user U1 is changed as the information regarding the context of the user U1. NS. Then, in FIG. 1A, it is shown that the prediction accuracy is high when the content is delivered to the user U1 by using the model M2 in the context CT11 of the user U1. Further, FIG. 1A shows that the prediction accuracy is high when the content is delivered to the user U1 by using the model M1 in the context CT12 of the user U1. The term "high prediction accuracy" as used herein means that the prediction accuracy of the model in the combination of the corresponding user and context is equal to or higher than a predetermined threshold value (for example, 75%). In addition, in FIG. 1A, it is assumed that the prediction accuracy is also improved for the models replaced in steps S1-2 to S1-4.

As described above, the distribution device 100 is changed because the model assigned to each mass MS corresponding to the user U1 is changed as the information regarding the context of the user U1 and the prediction accuracy in each context of the user U1 is improved. To maintain. When the prediction accuracy is lowered due to the change, the distribution device 100 may cancel the change and return to the original state. In the above example, the case where the prediction accuracy of the model does not satisfy the predetermined condition is described as the case where the prediction accuracy of the model in the combination of the user and the context is not equal to or higher than the predetermined threshold value. It may be set as appropriate according to the above. For example, the distribution device 100 may make a determination based on the overall tendency of the prediction accuracy of the model, or may make a determination based on the history of the prediction accuracy for each user. For example, the predetermined condition may be a case where the model assigned to a user for each context is within a predetermined range from the average of the prediction accuracy of all the contexts. For example, when the prediction accuracy of one context deviates from the average of the prediction accuracy of all contexts by a predetermined value or more in a certain user, the distribution device 100 changes the information about the user's context or the information about the user's user attribute. Then, it may be determined. For example, if the distribution device 100 has a high prediction accuracy of the context regarding the frequently visited place and home (for example, 80% or more) and a low prediction accuracy of the context regarding the office (for example, less than 60%), the user's office (work location). ) May be determined to be changed. Further, the predetermined condition may be a case where the fluctuation of the prediction accuracy with the passage of time in a certain user is within a predetermined range. For example, the distribution device 100 provides information about a user's context when the prediction accuracy of one context is high at a certain point in time (for example, 90% or more) and low at a subsequent time point (for example, less than 80%). , Or it may be determined to change the information about the user attributes of the user. For example, the distribution device 100 has a prediction accuracy (for example, 10% or more) in which the prediction accuracy of the context regarding the house is lowered from the prediction accuracy at a certain time point (for example, 90%) by a predetermined threshold value or more (for example, 10% or more) for a certain user. When it reaches 75%), it may be estimated that the user has moved and it may be determined that the information about the user's home (home) is changed. For example, the distribution device 100 may re-divide the action information in another context and determine the difference from the prediction accuracy in that case. For example, the distribution device 100 compares the prediction accuracy based on the cluster information list ML11-1 and the like with the prediction accuracy when the behavior information is divided according to the context based on the movement state and the like to generate a model, and the movement state is compared. If the prediction accuracy based on the cluster information list ML11-1 or the like is lower than the prediction accuracy of the model based on the above, it may be determined that the information on the user's context or the information on the user's user attribute is changed. The above is an example, and the distribution device 100 may determine that the information regarding the context of the user or the information regarding the user attribute of the user is changed based on any condition.

Next, using the example shown in FIG. 1B, a case where the distribution device 100 determines whether to change the information regarding the context of the new user or the information regarding the user attributes of the new user will be shown. The new user referred to here means a user added after model generation or a user whose behavior information is not sufficient, and a user to which a model assigned to another user is assigned.

The cluster information list ML12-1 in FIG. 1B shows models M1 to M6 and the like in a mass (hereinafter, may be referred to as “mass MS”) which is an area where one user and one context intersect. Of these, which model was assigned is shown.

The cluster information list ML12-1 in FIG. 1B shows the cluster information in which the new user U10 is added to the cluster information list ML11-1 in FIG. 1A. Further, it is assumed that the new user U10 is a user whose behavior information is not sufficient, and the gender, which is the information related to the user attribute, is registered as "male" and the age is registered as "20's".

In FIG. 1B, the distribution device 100 assigns each context CT11 to CT18 of the new user U10 a model assigned to the user U1 and the user U4 similar to the user attribute of the new user U10. For example, the distribution device 100 assigns the context CT11 of the new user U10 to the model M1-3, which is a combination of the model M1 assigned to the context CT11 of the user U1 and the model M3 assigned to the context CT11 of the user U3. The details of model synthesis will be described later. Further, for example, the distribution device 100 assigns the model M2 assigned to the context CT12 of the user U1 to the context CT12 of the new user U10. In this way, the distribution device 100 assigns a model to each of the contexts CT11 to CT18 of the new user U10.

As shown in FIG. 1B, in the cluster information list ML12-1, it is assumed that the prediction accuracy of the user U10 in the context CT14 is low. That is, FIG. 1B shows that the prediction accuracy is low when the content is delivered to the user U10 by using the model M3-6 in the context CT14 of the user U10.

As described above, since the prediction accuracy of the model M3-6 assigned to the context CT14 of the user U10 is low, the distribution device 100 changes the information regarding the context of the user U10 or the information regarding the user attribute of the user U10. judge. Note that FIG. 1B shows a case where the distribution device 100 determines that the information regarding the user attribute of the user U10 is changed.

In FIG. 1B, according to the above-mentioned determination, the distribution device 100 changes the gender of the user attributes of the user U10 from “male” to “female” in the cluster information list ML12-1. The attribute is changed (step S2). As a result, the user similar to the new user U10 is changed from the user U1 and the user U4 to the user U2 who is a female in her twenties. Therefore, the distribution device 100 assigns each context CT11 to CT18 of the new user U10 a model assigned to the user U2 similar to the user attribute of the new user U10.

By changing the user attribute in step S2, the model assigned to each mass MS corresponding to the user U10 is changed as shown in the cluster information list ML12-2 in FIG. 1B. Specifically, the model assigned to the context CT12 of the new user U10 is changed from the model M2 to the model M6. Further, the model assigned to the context CT14 of the new user U10 is changed from the model M3-6 to the model M2.

Then, in FIG. 1B, it is shown that the prediction accuracy is high when the content is delivered to the user U10 by using the model M2 in the context CT14 of the user U10. In addition, in FIG. 1B, it is assumed that the prediction accuracy is also improved for the model assigned to another context in the new user U10.

As described above, in the distribution device 100, the model assigned to each mass MS corresponding to the user U10 is changed according to the change of the user attribute of the new user U10, so that the prediction accuracy in each context of the user U10 is improved. Keep the changes as they have improved. When the prediction accuracy is lowered due to the change, the distribution device 100 may cancel the change and return to the original state.

As described above, the distribution device 100 determines that the information regarding the context of the user or the information regarding the user attributes of the user is changed when the prediction accuracy of the model assigned to the user does not satisfy a predetermined condition. As a result, the distribution device 100 can appropriately change the information about the user by the prediction accuracy of the model based on the context. Further, the distribution device 100 may calculate a score regarding the reliability of each user's home (home) or office (work location). For example, the distribution device 100 may determine the reliability of the house (home) or office (work location) according to the score calculated based on the prediction accuracy before and after the replacement when the house and the office are replaced. .. For example, the distribution device 100 calculates the average value of the prediction accuracy of the context (for example, contexts CT11, CT13, CT15, CT17, etc.) relating to the house before the replacement of the house and the office as the pre-replacement score. Further, for example, the distribution device 100 calculates the average value of the prediction accuracy of the context regarding the house after the replacement of the house and the office as the post-replacement score. Then, the distribution device 100 may determine the reliability of the position set as the home by using the value obtained by dividing the pre-replacement score by the post-replacement score as the reliability score regarding the reliability of the house (home). In this case, the confidence score becomes larger as the pre-replacement score is larger than the post-replacement score. That is, the distribution device 100 shows that the prediction accuracy of the context regarding the house before the house and the office are exchanged is higher. Therefore, the distribution device 100 determines that the higher the reliability score, the higher the reliability of the position set as the home. Therefore, the distribution device 100 maintains the home position setting when the home trust score is equal to or higher than a predetermined threshold value, and changes the home position setting when the home trust score is less than the predetermined threshold value. You may. For example, the distribution device 100 may switch the position of the home and the position of the office, or may select the position at the home from a plurality of candidates. The details of the case of selecting from a plurality of candidates will be described later.

For example, the distribution device 100 may determine a user who changes the information about the context or the information about the user attribute based on the reliability of the information about the context of each user or the reliability of the information about the user attribute of each user. good. For example, when the user is a user who has undergone a credit card examination or the like, the distribution device 100 does not have to change the information regarding the user's age, gender, home, work location, etc., as it is highly reliable. .. Further, for example, when the user registers the user information with the information initially displayed when the user information is registered, the distribution device 100 gives priority to the information registered for the user because the reliability is low. It may be the target of changes made. For example, when a user registers the date of birth as the information initially displayed when registering the user information, the distribution device 100 gives priority to the age registered for the user as being unreliable. It may be the target of.

[2-1. Generation process]
From here, an example of the generation process according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing an example of the generation process according to the embodiment. In the example shown in FIG. 2, the distribution device 100 generates a model for predicting the user's interest in the content as a predetermined target. Further, the distribution device 100 provides a service of distributing content to the user using the generated model, and this point will be described with reference to FIG. 2 to 4 show a case where users U1 to U4 use terminal devices 10-1 to 10-4, respectively. In the case where the terminal devices 10-1 to 10-4 are described without distinction, they are collectively referred to as the terminal device 10.

As shown in FIG. 2, the distribution system 1 includes a terminal device 10 and a distribution device 100. The terminal device 10 and the distribution device 100 are communicably connected by wire or wirelessly via a predetermined communication network (not shown). The distribution system 1 shown in FIG. 2 may include a plurality of terminal devices 10 and a plurality of distribution devices 100.

The terminal device 10 is an information processing device used by the 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. FIG. 2 shows a case where the terminal device 10 is a smartphone.

In addition, the terminal device 10 accepts operations by the user. In the example shown in FIG. 2, the terminal device 10 requests the distribution device 100 for the content to be displayed on a predetermined application (for example, a browser or the like). In the following, the terminal device 10 may be referred to as a user. That is, in the following, the user can be read as the terminal device 10.

The distribution device 100 is an information processing device that generates a model for predicting a predetermined target for each union information in which the division information, which is the behavior information divided based on the context, is combined. Further, the distribution device 100 is a determination device that determines whether to change the information regarding the context of the user corresponding to the model or the information regarding the user attribute of the user according to the prediction accuracy of the model. Further, the distribution device 100 is an information processing device that provides a distribution service that distributes content in response to a content distribution request. For example, the distribution device 100 is an information processing device that distributes content to the terminal device 10 according to a user who uses the terminal device 10 that requests the distribution of the content.

In FIG. 2, the distribution device 100 distributes content to each user, and collects behavior information indicating the presence or absence of each user's behavior with respect to the distributed content. For example, the distribution device 100 distributes the content to the users U1 to U4, and collects the action information indicating the presence or absence of the action of each user with respect to the distributed content. For example, the distribution device 100 collects information indicating whether or not the user has an action (for example, a click of the content) with respect to the content (for example, the content CN11) distributed to the user as the action information.

First, the distribution device 100 distributes the content to the terminal device 10-1 used by the user U1 (step S11-1). Then, the distribution device 100 acquires the action information indicating the presence / absence of the action of the user U1 with respect to the distributed content from the terminal device 10-1 (step S12-1). Further, the distribution device 100 distributes the content to the terminal device 10-2 used by the user U2 (step S11-2). Then, the distribution device 100 acquires the action information indicating the presence / absence of the action of the user U2 with respect to the distributed content from the terminal device 10-2 (step S12-2). Further, the distribution device 100 distributes the content to the terminal device 10-3 used by the user U3 (step S11-3). Then, the distribution device 100 acquires the action information indicating the presence / absence of the action of the user U3 with respect to the distributed content from the terminal device 10-3 (step S12-3). Further, the distribution device 100 distributes the content to the terminal device 10-4 used by the user U4 (step S11-4). Then, the distribution device 100 acquires the action information indicating the presence / absence of the action of the user U4 with respect to the distributed content from the terminal device 10-4 (step S12-4).

It should be noted that steps S11-1 to S11-4 are for explaining the process, and any of steps S11-1 to S11-4 may be performed first, and each step S11-1 to S11-4 may be performed first. May be performed multiple times. Hereinafter, when steps S11-1 to S11-4 will be described without distinction, they are collectively referred to as step S11. Further, steps S12-1 to S12-4 are for explaining the processing, and if each is after the corresponding step S11, any of steps S12-1 to S12-4 is performed first. Each step S12-1 to S12-4 may be performed a plurality of times. Hereinafter, when steps S12-1 to S12-4 will be described without distinction, they are collectively referred to as step S12. For example, each time each step S11 is performed, step S12 may be performed to acquire action information. Further, for example, each step S11 may be performed a plurality of times, and step S12 may be performed at a predetermined timing to acquire action information.

Then, the distribution device 100 divides the information regarding the behavior of each user collected in steps S11 to S12 (step S13). Specifically, the distribution device 100 divides the collected behavior information of each user based on the context.

Here, the context means 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 context is information corresponding to a situation in which the terminal device 10 is used by the user or a state in which the user who owns the terminal device 10 is placed. That is, the context in FIGS. 2 to 4 corresponds to the situation of users U1 to U4, for example, the environment where the users U1 to U4 are located. Specifically, the contexts in FIGS. 2 to 4 correspond to the situations of users U1 to U4 when the content is distributed (displayed) to each user. For example, the context may be estimated based on the time when the content is delivered or the user's position information acquired from the terminal device 10. Note that each context may be exclusive or duplicated.

Further, in FIGS. 2 to 4, for the sake of simplicity, the context based on the time zone and the position is shown. Specifically, the contexts in the examples of FIGS. 2 to 4 are four: morning (4 to 10 o'clock), noon (10 to 16 o'clock), night (16 to 22 o'clock), and midnight (22 to 4 o'clock). Eight contexts CT11-CT18 are shown based on the time of day and two locations of home (home) or office (work location).

Here, the divided information storage unit 123 in FIG. 2 shows a state in which the action information of each user is divided for each context in step S13. The divided information storage unit 123 shows a case where the user is a row and the context is a column. The area where one user and one context intersect in the divided information storage unit 123 is defined as a mass. For example, in FIG. 2, the region where the user U4 and the context CT12 intersect is defined as the mass MS42. When the position of each cell is not distinguished, it may be referred to as mass MS. The information included in each mass MS shown in FIG. 2 is divided information in which the behavior information regarding the user's behavior for each division regarding the user is divided based on the context. Further, the lines in the divided information storage unit 123 may have any particle size as long as they are classified not only for users but also for users. For example, the line in the divided information storage unit 123 may be classified based on the user attribute, which is a classification related to the user. The classification based on the user attribute referred to here may be a classification based on the similarity of information on the user attribute such as age, gender, and interest.

For example, the mass MS at the position where the user U1 and the context CT11 intersect (the mass MS on the upper left) includes division information indicating the presence or absence of actions such as actions AT11, AT12, and AT13. For example, the mass MS at the position where the user U4 and the context CT18 intersect (the mass MS at the lower right) includes division information indicating the presence or absence of actions such as actions AT48 and AT11.

Further, “◯” shown on the right side of the action AT11 or the like in each mass MS in the divided information storage unit 123 indicates that the user has performed the corresponding action. Further, "x" shown on the right side of the action AT11 or the like in each mass MS in the divided information storage unit 123 indicates that the user did not perform the corresponding action. For example, in the mass MS at the position where the user U1 and the context CT11 intersect, the action AT11 is “◯”, indicating that the user U1 has performed the action AT11 at the house in the morning. Further, for example, in the mass MS at the position where the user U1 and the context CT11 intersect, the action AT12 is “x”, indicating that the user U1 did not perform the action AT12 in the morning house. Further, for example, in the mass MS at the position where the user U1 and the context CT11 intersect, the action AT13 is “◯”, indicating that the user U1 has performed the action AT13 at the house in the morning.

Then, the distribution device 100 generates a model by using the division information of each mass MS in the division information storage unit 123 (step S14). For example, the distribution device 100 clusters the division information of each mass MS in the division information storage unit 123, and generates a model for each cluster. For example, the distribution device 100 generates a model that predicts a user's interest in content.

For example, the distribution device 100 may perform clustering by a clustering method in which the number of clusters is not set. Further, for example, the distribution device 100 may perform clustering by a clustering method for setting the number of clusters. For example, the distribution device 100 clusters the division information of each mass MS by using the k-means method or the logistic regression method using the Dirichlet process, and generates a model using the division information for each cluster. In FIG. 2, the distribution device 100 will be described below assuming that the distribution device 100 clusters the division information of each mass MS by using the logistic regression method using the Dirichlet process and generates a model using the division information for each cluster. .. The details of the clustering method will be described later.

The distribution device 100 may target mass MS including a predetermined amount or more of division information as a model generation target in step S14. For example, the distribution device 100 does not target the mass MS corresponding to the context CT17 of the user U4 and the mass MS corresponding to the context CT11 of the user U2 that do not include the division information to be clustered. Further, for example, in the distribution device 100, the mass MS corresponding to the contexts CT13 and CT18 of the user U1 containing less than a predetermined amount (for example, two) of divided information may not be the target of clustering.

In step S14, the distribution device 100 generates the model information MD11. The model information MD 11 includes information related to clustering of divided information included in each mass MS as shown in the cluster information storage unit 124. Further, the model information MD 11 includes information about the models M1 to M6 generated for each cluster as shown in the learning information storage unit 125.

In FIG. 2, the distribution device 100 classifies the divided information of each mass MS in the divided information storage unit 123 into six clusters (M1 to M6 in the cluster information storage unit 124). Note that M1 to M6 in the cluster information storage unit 124 indicate the cluster to which each division information belongs and the model to be generated. Further, in the mass MS in the cluster information storage unit 124, a model generated by a predetermined method is assigned to the mass MS whose symbols M1 to M6 are not shown. For example, the distribution device 100 may assign a model to a mass MS in the cluster information storage unit 124 to which a model is not assigned, based on a model assigned to another mass MS. For example, the distribution device 100 assigns the model M4 assigned to the mass MS corresponding to the context CT15 of the user U1 of the same male in his twenties to the mass MS corresponding to the context CT15 of the user U4 to which the model is not assigned. May be good.

Further, for example, in the distribution device 100, the model assigned to the mass MS corresponding to the context CT17 of the user U4 to which the model is not assigned is assigned to the mass MS corresponding to the context CT17 of the user U1 or the user U2 in the same 20s. You may assign a model based on. In this case, the distribution device 100 may assign a model that combines the model M2 assigned to the mass MS corresponding to the context CT17 of the user U1 and the model M1 assigned to the mass MS corresponding to the context CT17 of the user U2. good. For example, the distribution device 100 has a weight of each feature of the model M2 assigned to the mass MS corresponding to the context CT17 of the user U1 and a weight of each feature of the model M1 assigned to the mass MS corresponding to the context CT17 of the user U2. A model in which and is synthesized at a predetermined ratio may be assigned. For example, the distribution device 100 assigns a model in which the ratio of the model M2 assigned to the mass MS corresponding to the context CT17 of the male user U1 in his twenties is larger to the mass MS corresponding to the context CT17 of the user U4. You may. For example, the distribution device 100 may assign the model M1-2, which is composed of the model M1 at a ratio of 0.3 and the model M2 at a ratio of 0.7, to the mass MS corresponding to the context CT17 of the user U4. That is, the distribution device 100 generated the model M1- by adding the weight obtained by multiplying the weight of each feature of the model M1 by 0.3 and the weight obtained by multiplying the weight of each feature of the model M2 by 0.7. 2 may be assigned to the mass MS corresponding to the context CT17 of the user U4.

In FIG. 2, the distribution device 100 corresponds to the mass MS corresponding to the context CT11 of the user U1, the mass MS corresponding to the context CT15 of the user U2, the mass MS corresponding to the context CT17 of the user U2, and the context CT13 of the user U4. The division information included in the mass MS is classified into the same cluster. Further, it is shown that the distribution device 100 generated the model M1 by using the union information obtained by combining the division information included in the above four mass MSs. Further, as shown in the learning information storage unit 125, in the model information regarding the model M1, the weight of the feature 1 is "0.5", the weight of the feature 2 is "-0.4", and the weight of the feature 3 is "0. 2 ”etc. The features may be set by the administrator of the distribution device 100 or the like, or may be extracted in the model generation process. For example, the feature may be a character string (keyword) such as "economy", "smartphone", or "soccer". In addition, the features of each model may be the same or different.

Further, the distribution device 100 shares the divided information included in the mass MS corresponding to the context CT12 and CT17 of the user U1, the mass MS corresponding to the context CT14 of the user U2, and the mass MS corresponding to the context CT12 of the user U3 in the same cluster. Classify into. Further, it is shown that the distribution device 100 generated the model M2 by using the union information obtained by combining the division information included in the above four mass MSs. Further, as shown in the learning information storage unit 125, in the model information regarding the model M2, the weight of the feature 1 is "-0.3", the weight of the feature 2 is "2.1", and the weight of the feature 3 is "-0". .2 ”etc.

As described above, in FIG. 2, the distribution device 100 classifies the division information of each mass MS in the division information storage unit 123 into six clusters (union information), and uses the information included in each cluster (union information). Models M1 to M6 are generated.

As described above, even if the distribution device 100 divides the behavior information of each division based on the context, it suppresses the shortage of the amount of information used for generating each model by performing clustering across the divisions. can do. Further, the distribution device 100 can generate an appropriate model according to each context of each division by clustering the information divided based on the division and the context. Therefore, the distribution device 100 can appropriately change the information about the user by the prediction accuracy of the model based on the context.

Note that FIG. 2 shows an example in which information regarding the presence or absence of the user's behavior in the distributed content is used as the behavior information, but what if the behavior information is the behavior performed by the user and can be collected? Information may be used. For example, the behavior information may be information related to the user's electronic commerce, or may be behavior related to the delivered advertisement (for example, click, conversion, etc.). In addition, the location is not limited to the home (home) or office (work location), and may be various information such as a waypoint during commuting, a frequently visited location, or moving.

[2-2-1. Delivery process (before change)]
Next, an example of the distribution process according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing an example of the distribution process before the context change according to the embodiment. FIG. 3 shows a case where the user is the user U1. In FIG. 3, the case where the distribution device 100 has already acquired the user information regarding the user attribute of the user U1 and the user information such as the action history has been acquired will be described as an example.

First, the distribution device 100 acquires a content distribution request from the terminal device 10-1 used by the user U1 (step S15). In FIG. 3, in step S15, the terminal device 10-1 transmits information for identifying the user U1 (for example, a login ID or the like), position information indicating the location of the terminal device 10-1, or the like to the distribution device 100. The terminal device 10 acquires position information by a GPS (Global Positioning System) sensor or the like. In FIG. 3, it is assumed that the step S15 is performed in a situation where the time is 9:00 am and the location (position) of the terminal device 10-1 is the position LC12-1. The position LC12-1 or the like, which is information indicating the position and has a hyphen (“−”), means the position information within a predetermined range from the position LC12. Further, the positions LC11-1, LC11-2, etc. (see FIG. 7) mean position information within a predetermined range from the position LC11. That is, when the position LC12-1 indicates the position information of the user U1, it is estimated that the user U1 is at the work location at the position LC12.

The distribution device 100 that has acquired the content distribution request from the terminal device 10-1 determines a model for determining the content to be distributed to the terminal device 10-1 (step S16). The distribution device 100 estimates that the distribution request source is the user U1 based on the information for identifying the user U1 acquired from the terminal device 10-1. Then, the distribution device 100 estimates the location of the user U1 based on the user information of the user U1 stored in the user information storage unit 121 and the position LC12-1 of the terminal device 10-1. In FIG. 3, as shown in the user information storage unit 121, the work location of the user U1 is the position LC12, and the position of the terminal device 10-1 is the position LC12-1. Therefore, in the distribution device 100, the user U1 is in the office ( Estimated to be at work location).

Then, since the time when the distribution request is made in step S15 is 9:00 am, the distribution device 100 estimates that the context is the context CT12 corresponding to the office in the morning. After that, the distribution device 100 determines the model M2 to be used for determining the content to be distributed based on the information indicating the model M2 stored in the mass MS corresponding to the user U1 and the context CT12 in the learning information storage unit 125. do.

For example, the distribution device 100 calculates the score of each content stored in the content information storage unit 126 (see FIG. 11) using the determined model M2. Specifically, the distribution device 100 includes character information and image information such as titles and article texts of each content CN11 (article A) to content CN18 (article H) stored in the content information storage unit 126, and model M2. Is used to calculate the scores of each content CN11 to CN18 and the like. In FIG. 3, the distribution device 100 calculates the scores of the contents CN11 to CN18 and the like as shown in the contents list CL11. For example, the distribution device 100 calculates the score of the content CN11 which is the article A as "3.6". Further, for example, the distribution device 100 calculates the score of the content CN12, which is the article B, as “2.5”.

Then, the distribution device 100 determines the ranking of each content CN11 to CN18 or the like based on the score shown in the content list CL11 (step S17). In FIG. 3, the distribution device 100 determines the order of the contents CN11 to CN18 and the like in order from the one with the highest score shown in the contents list CL11. Specifically, the distribution device 100 determines the ranking of the article E, which is the content CN15 having the highest score, to be the first. Further, the distribution device 100 determines the ranking of the article G, which is the content CN17 having the highest score next to the article E, to be second. As a result, as shown in the ranking list LL11, the distribution device 100 has the ranking 1st place is the article E, the ranking 2nd place is the article G, the ranking 3rd place is the article A, and the ranking 4th place is the article F. Decide that there is.

After that, the distribution device 100 distributes the content shown in the ranking list LL11 to the terminal device 10-1 (step S18). Specifically, the contents displayed in the order of article E, article G, article A, article F, and the like are distributed to the terminal device 10-1. Then, the terminal device 10-1 that has received the content shown in the ranking list LL11 displays the content (step S19). In FIG. 3, the terminal device 10-1 displays the article E, the article G, the article A, and the article F, which are the contents having the higher rank among the contents shown in the rank list LL11. The user U1 who uses the terminal device 10-1 touches the screen of the terminal device 10-1 and performs a scroll operation or the like to sequentially display the articles B, the articles H, and the like from the article F to the bottom. The user U1 did not select (click) the article E, the article G, the article A, and the article F displayed on the terminal device 10-1, that is, the prediction accuracy using the model M2 in the context CT12 of the user U1. Will be described below assuming that the value is low.

[2-2-2. Delivery process (after change)]
Next, an example of the distribution process according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram showing an example of the distribution process after the context is changed according to the embodiment. Specifically, FIG. 4 shows a case where the context is changed by exchanging the house and office of the user U1 from the cluster information storage unit 124 shown in FIG. 3, and the cluster information storage unit 124-2 is changed. show. FIG. 4 shows a state in which the cluster information storage unit 124-2 corresponds to the cluster information list ML11-2 in FIG. 1 and the model assignment of the user U1 to each of the contexts CT11 to CT18 has been changed.

The model information MD12 shown in FIG. 4 includes information related to clustering of divided information included in each mass MS as shown in the cluster information storage unit 124-2. Further, the model information MD12 includes information about the models M1 to M6 generated for each cluster as shown in the learning information storage unit 125. For example, the cluster information storage unit 124-2 replaces the model M1 assigned to the context CT11 of the user U1 with the model M2 assigned to the context CT12, assigns the model M2 to the context CT11 of the user U1, and assigns the model M2 to the context CT12. Model M1 is assigned to.

First, the distribution device 100 acquires a content distribution request from the terminal device 10-1 used by the user U1 (step S21). In FIG. 4, it is assumed that the step S21 is performed in a situation where the time is 9:00 am and the location (position) of the terminal device 10-1 is the position LC12-2.

The distribution device 100 that has acquired the content distribution request from the terminal device 10-1 determines a model for determining the content to be distributed to the terminal device 10-1 (step S22). The distribution device 100 estimates that the distribution request source is the user U1 based on the information for identifying the user U1 acquired from the terminal device 10-1. Then, the distribution device 100 estimates the location of the user U1 based on the user information of the user U1 stored in the user information storage unit 121 and the position LC12-2 of the terminal device 10-1. In FIG. 4, as shown in the user information storage unit 121, the work location of the user U1 is the position LC12, and the position of the terminal device 10-1 is the position LC12-2. Estimated to be at work location).

Then, since the time when the distribution request is made in step S21 is 9:00 am, the distribution device 100 estimates that the context is the context CT12 corresponding to the office in the morning. After that, the distribution device 100 determines the model to be used for determining the content to be distributed in the model M1 based on the information indicating the model M1 stored in the mass MS corresponding to the user U1 and the context CT12 in the learning information storage unit 125. do.

For example, the distribution device 100 calculates the score of each content stored in the content information storage unit 126 (see FIG. 11) using the determined model M1. Specifically, the distribution device 100 includes character information and image information such as titles and article texts of each content CN11 (article A) to content CN18 (article H) stored in the content information storage unit 126, and model M1. Is used to calculate the scores of each content CN11 to CN18 and the like. In FIG. 4, the distribution device 100 calculates the scores of the contents CN11 to CN18 and the like as shown in the contents list CL12. For example, the distribution device 100 calculates the score of the content CN11 which is the article A as “1.2”. Further, for example, the distribution device 100 calculates the score of the content CN12, which is the article B, as "3.2".

Then, the distribution device 100 determines the ranking of each content CN11 to CN18 or the like based on the score shown in the content list CL12 (step S23). In FIG. 4, the distribution device 100 determines the order of the contents CN11 to CN18 and the like in order from the one with the highest score shown in the contents list CL12. Specifically, the distribution device 100 determines the ranking of the article C, which is the content CN13 having the highest score, to be the first place. Further, the distribution device 100 determines the ranking of the article H, which is the content CN18 having the highest score next to the article C, to the second place. As a result, as shown in the ranking list LL12, the distribution device 100 has the ranking 1st place is the article C, the ranking 2nd place is the article H, the ranking 3rd place is the article F, and the ranking 4th place is the article B. Decide that there is.

After that, the distribution device 100 distributes the content shown in the ranking list LL12 to the terminal device 10-1 (step S24). Specifically, the contents displayed in the order of article C, article H, article F, article B, etc. are distributed to the terminal device 10-1. Then, the terminal device 10-1 that has received the content shown in the ranking list LL12 displays the content (step S25). In FIG. 4, the terminal device 10-1 displays the article C, the article H, the article F, and the article B, which are the contents having the higher rank among the contents shown in the rank list LL12. Then, the user U1 selects (clicks) the article C delivered based on the model M1 having high prediction accuracy (step S26).

As described above, the distribution device 100 determines the model according to the context when the distribution request is acquired. Then, the distribution device 100 determines the ranking of the contents based on the score of the contents calculated using the determined model. As a result, the distribution device 100 can distribute appropriate content according to the user and the context at the time of the distribution request. Therefore, the distribution device 100 can extract appropriate contents. In the above example, the distribution device 100 calculates the score of each content using the model selected based on the context of the user, and ranks the calculated contents in order from the highest score. .. As described above, in the above-described example, the distribution device 100 shows a case where the distribution device 100 uses a model that calculates the possibility of viewing each content as a continuous numerical value (score) in the corresponding context. That is, in the above example, the higher the score of each content calculated by the distribution device 100 using the model selected based on the user's context, the higher the possibility that the content will be viewed. , The distribution device 100 may make any prediction using the selected model.

For example, the distribution device 100 may predict that the user will browse the content having a score equal to or higher than a predetermined threshold value, and predict that the user will not browse the content having a score lower than the predetermined threshold value. In this way, the distribution device 100 may or may not allow the user to browse the content (for example, the value "1") based on the score of each content calculated using the model selected based on the context (for example, the value "0"). ”) The binary prediction may be performed. The distribution device 100 is not limited to binary prediction, but may generate a model for predicting continuous value or discrete value, and predict continuous value or discrete value based on the generated model. For example, the distribution device 100 may make a prediction corresponding to a so-called multi-label problem in which not only two values of "0" and "1" but also three or more values are handled. For example, the distribution device 100 may predict at which stage of three or more stages the user is present, instead of the two stages of whether or not the user browses the content. For example, the distribution device 100 may use a plurality of threshold values to predict at which stage the user is likely to browse the content. Specifically, the prediction device 100 uses a first threshold value and a second threshold value smaller than the first threshold value, and when the score is equal to or higher than the first threshold value, the user may browse the content. If it is judged to be high and the score is less than the first threshold value and is equal to or higher than the second threshold value, it is judged that the user has a medium possibility of viewing the content, and if the score is less than the second threshold value, the content is judged to be high. May be predicted to be unlikely to be viewed by the user. Further, for example, the distribution device 100 may generate a model for predicting the number of reactions or predicting the score of a predetermined target, and make a prediction based on the generated model. That is, any prediction may be made using the model selected by the distribution device 100 based on the user's context. Further, the distribution device 100 may generate a model according to the target to be predicted as described above. In the present embodiment, the case where the distribution device 100 generates or modifies the model is shown as an example, but the distribution device 100 provides information about the user's context based on the distribution result of the content using the model. Alternatively, it may be determined whether or not to change the information regarding the user attributes of the user. In this case, for example, an external device other than the distribution device 100 may generate or change the model. For example, the distribution device 100 transmits the determination result to another external device, and the other external device that has acquired the determination result from the distribution device 100 changes the information regarding the context of the user or the information regarding the user attribute of the user. You may generate a model. Further, the distribution device 100 may be a determination device that only determines whether to change the information regarding the context of the user or the information regarding the user attribute of the user. In this case, the distribution device 100 may be another external device that distributes the content using a model generated based on the information regarding the context of the changed user and the information regarding the user attributes of the changed user. .. That is, the distribution system 1 may have any device configuration.

[3. Distribution device configuration]
Next, the configuration of the distribution device 100 according to the embodiment will be described with reference to FIG. FIG. 5 is a diagram showing a configuration example of the distribution device according to the embodiment. As shown in FIG. 5, the distribution device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The distribution device 100 has an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from the administrator of the distribution device 100, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. You may.

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

(Memory unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. As shown in FIG. 5, the storage unit 120 according to the embodiment includes a user information storage unit 121, an action information storage unit 122, a division information storage unit 123, a cluster information storage unit 124, and a learning information storage unit 125. , Content information storage unit 126.

(User information storage unit 121)
The user information storage unit 121 according to the embodiment stores various information about the user. For example, the user information storage unit 121 stores various information related to user attributes. FIG. 6 is a diagram showing an example of a user information storage unit according to the embodiment. The user information storage unit 121 shown in FIG. 6 includes items such as "user ID", "age", "gender", "home", "work location", and "interest".

The "user ID" indicates identification information for identifying a user. For example, the user identified by the user ID "U1" corresponds to the user U1 shown in the example of FIG. Further, "age" indicates the age of the user identified by the user ID. The "age" may be the specific age of the user identified by the user ID, such as 35 years old. Further, "gender" indicates the gender of the user identified by the user ID.

Further, "home" indicates the location information of the user's home identified by the user ID. In the example shown in FIG. 6, “home” is illustrated with an abstract code such as “LC11”, but may be information indicating latitude or longitude. Further, for example, "home" may be an area name or an address.

Further, the "work location" indicates the location information of the user's work location identified by the user ID. In the example shown in FIG. 6, the "work location" is shown by an abstract code such as "LC12", but may be information indicating latitude or longitude. Further, for example, the "work location" may be a region name or an address.

Further, "interest" indicates the interest of the user identified by the user ID. That is, "interest" indicates an object that the user identified by the user ID is highly interested in. In the example shown in FIG. 6, one "interest" is shown for each user, but there may be a plurality of "interests".

For example, in the example shown in FIG. 6, the age of the user identified by the user ID "U1" is "20's", and the gender is "male". Further, for example, the user identified by the user ID "U1" indicates that his / her home is "LC11". Further, for example, the user identified by the user ID "U1" indicates that the work location is "LC12". Further, for example, the user identified by the user ID "U1" indicates that he / she is interested in "sports".

The user information storage unit 121 is not limited to the above, and may store various information depending on the purpose. For example, the user information storage unit 121 may store information such as a name, family structure, and income.

(Behavior information storage unit 122)
The behavior information storage unit 122 according to the embodiment stores various information related to the user's behavior. FIG. 7 is a diagram showing an example of the behavior information storage unit according to the embodiment. For example, the behavior information storage unit 122 stores the user's behavior information for the content delivered to the terminal device 10 of each user. The action information storage unit 122 shown in FIG. 7 includes items such as "user ID", "behavior", and "situation". In addition, the "action" includes items such as "action content" and "presence / absence". In addition, the "situation" includes items such as "time" and "position".

The "user ID" indicates identification information for identifying a user. For example, the user identified by the user ID "U1" corresponds to the user U1 shown in the example of FIG. Further, "behavior" indicates information about the behavior of the corresponding user. Further, "status" indicates information regarding the status of the corresponding user.

"Behavior content" indicates identification information for identifying each action. For example, the action identified by the action content "AT11" (action AT11) corresponds to the user's action (for example, clicking the content) with respect to the content (for example, content CN11) delivered to the user. The "action content" is not limited to the identification information, and a specific action content may be stored. In addition, "presence / absence" indicates the presence / absence of the corresponding action content. When "presence / absence" is "1", it indicates that the user has performed the corresponding action. Further, when "presence / absence" is "0", it indicates that the user has not performed the corresponding action.

"Time" indicates the time for each action. The time "TM11" indicates the time related to the action AT11. For example, the time "TM11" may be the time when the content (for example, the content CN11) is delivered to the user. Further, for example, the time "TM11" may be the time when the user clicks the content (for example, the content CN11) delivered to the user. The time “TM12” related to the action (action AT12) identified by the action content “AT12” which is “0” may be, for example, the time when the content is delivered to the user. Further, for example, the time "TM12" may be a time after a predetermined time has elapsed without being clicked after the content is delivered to the user.

In addition, "position" indicates a position related to each action. The position "LC11-1" indicates the position regarding the action AT11. For example, the position "LC11-1" may be the position information when the user requests the distribution of the content. Further, for example, the position "LC11-1" may be the position information when the user clicks the distributed content.

For example, in the example shown in FIG. 7, the user identified by the user ID “U1” has an action (action AT13) identified by the action content “AT13” with or without “1”, and has performed the action AT13. show. Further, the user identified by the user ID "U1" indicates that the time related to the action AT13 is the time "TM13" and the position is the position "LC11-3".

The behavior information storage unit 122 is not limited to the above, and may store various information depending on the purpose. For example, the behavior information storage unit 122 may store information regarding the time from when the content is delivered until the user acts. Further, although FIG. 7 shows a case where the action information is stored in the action information storage unit 122 for each user ID, the action information is not limited to each user ID and may be stored, for example, in chronological order.

(Divided information storage unit 123)
The divided information storage unit 123 according to the embodiment stores various information related to the divided information. FIG. 8 is a diagram showing an example of the divided information storage unit according to the embodiment. The divided information storage unit 123 shown in FIG. 8 stores the action information divided based on the “division” and the “context”. Specifically, the action information corresponding to each "context" is stored for each "classification" of the user. For example, the information stored in the divided information storage unit 123 is generated from the behavior information stored in the behavior information storage unit 122.

"Category" indicates a classification related to a user. FIG. 8 shows users U1 to U4, that is, a case where each user is a division. The "classification" is not limited to each user and may be an abstracted user classification or the like, but this point will be described later. Further, "context" indicates a context. FIG. 8 shows a context based on time zone and position for simplicity. Specifically, the "context" consists of four time zones: morning (4 to 10 o'clock), noon (10 to 16 o'clock), night (16 to 22 o'clock), midnight (22 to 4 o'clock), and home (22:00 to 4 o'clock). Eight contexts CT11-CT18 are shown based on two locations, home) or office (work location). The "○" shown on the right side of the action content such as "AT11" in each square shown in FIG. 8 corresponds to the presence / absence of "1", and the "x" corresponds to the presence / absence of "0". That is, in the case of "○", it indicates that the user has performed the corresponding action. In addition, in the case of "x", it indicates that the user did not perform the corresponding action.

For example, in the example shown in FIG. 8, the user U1 indicates that the action AT11 is “◯” in the context CT11 and the action AT11 is performed at home (home) in the time zone “morning”. Further, the user U1 indicates that the action AT11 is “x” in the context CT12 and the action AT11 is not performed in the office (work location) in the time zone “morning”.

The divided information storage unit 123 is not limited to the above, and various information may be stored depending on the purpose. Further, in FIG. 8, for the sake of explanation, a case where information regarding the action content and presence / absence of each action information is stored in the divided information storage unit 123 is illustrated, but the divided information storage unit 123 stores the information in the action information storage unit 122. Information on which cell the action information given corresponds to may be stored.

(Cluster Information Storage Unit 124)
The cluster information storage unit 124 according to the embodiment stores various information regarding the combination of the divided information. FIG. 9 is a diagram showing an example of the cluster information storage unit according to the embodiment. The cluster information storage unit 124 shown in FIG. 9 stores information indicating how the division information of each cell shown in the division information storage unit 123 in FIG. 8 is combined and information identifying a model corresponding to each combination. Will be done. Specifically, information for identifying the model corresponding to each cell according to the user's "classification" and "context" is stored. For example, the information stored in the cluster information storage unit 124 is generated by a process of generating a model.

"Category" indicates a classification related to a user. FIG. 9 shows a case where users U1 to U4, that is, each user is a division, as in FIG. Further, "context" indicates a context. FIG. 9 shows a context based on time zone and position, as in FIG. Specifically, the "context" consists of four time zones: morning (4 to 10 o'clock), noon (10 to 16 o'clock), night (16 to 22 o'clock), midnight (22 to 4 o'clock), and home (22:00 to 4 o'clock). Eight contexts CT11-CT18 are shown based on two locations, home) or office (work location). In addition, "M1", "M2", etc. in each cell shown in FIG. 9 indicate information for identifying a model generated by union information combining division information of cells in which the same code is stored.

For example, in the example shown in FIG. 9, the model identified by "M1" (hereinafter, may be referred to as "model M1"; the same applies to the other "M2" to "M6") is the context CT11 of the user U1. From the union information that combines the mass MS corresponding to the mass MS corresponding to the user U2, the mass MS corresponding to the context CT15 of the user U2, the mass MS corresponding to the context CT17 of the user U2, and the mass MS corresponding to the context CT13 of the user U4. Indicates that it was generated. Further, for example, the model M2 combines the division information included in the mass MS corresponding to the context CT12 and CT17 of the user U1, the mass MS corresponding to the context CT14 of the user U2, and the mass MS corresponding to the context CT12 of the user U3. Indicates that it was generated from the union information.

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

(Learning information storage unit 125)
The learning information storage unit 125 according to the embodiment stores information related to learning. For example, the learning information storage unit 125 stores the model information generated by the generation process. FIG. 10 is a diagram showing an example of the learning information storage unit according to the embodiment. The learning information storage unit 125 shown in FIG. 10 has items such as "feature 1" to "feature 3" corresponding to each model M1 to M6 as model information.

For example, in the example shown in FIG. 10, the model information regarding the model M1 is such that the weight of the feature 1 is "0.5", the weight of the feature 2 is "-0.4", the weight of the feature 3 is "0.2", and the like. Indicates that. For example, when the features (features) of the model are represented by an m-dimensional vector, the number of features is m, and the weights of features 1 to m are stored.

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

(Content information storage unit 126)
The content information storage unit 126 according to the embodiment stores various information related to the content (article). FIG. 11 is a diagram showing an example of the content information storage unit according to the embodiment. The content information storage unit 126 shown in FIG. 11 has items such as "content ID", "content", and "category".

The "content ID" indicates identification information for identifying the content. "Content" indicates an article that is content acquired from a provider such as a so-called content provider. In FIG. 11, an example in which conceptual information such as "article A" is stored in "content" is shown, but in reality, a file showing character information, a combination of character information and an image, or a storage location thereof. The path name etc. are stored. In addition, "category" indicates classification information based on the content.

For example, in the example shown in FIG. 11, the article A (content CN11) identified by the content ID “CN11” is classified into the category “economy”. Further, in the example shown in FIG. 11, the article B (content CN12) identified by the content ID “CN12” is classified into the category “sports”.

The content information storage unit 126 is not limited to the above, and may store various information depending on the purpose. For example, the content information storage unit 126 may store information regarding the date and time when the content was acquired and the date and time when the content was created. The content information storage unit 126 may store information regarding the evaluation value of each provider. Further, the content information storage unit 126 may store identification information for identifying the content provider. Further, the content information storage unit 126 may store the score of the content calculated by each model.

(Control unit 130)
Returning to the description of FIG. 5, the control unit 130 is an example of various programs (an example of a distribution program) stored in a storage device inside the distribution device 100 by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). Is realized by executing RAM as a work area. Further, the control unit 130 is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 5, the control unit 130 includes an acquisition unit 131, an estimation unit 132, a generation unit 133, a determination unit 134, a determination unit 135, and a distribution unit 136, and the information described below. Realize or execute the function or action of processing. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 5, and may be another configuration as long as it is a configuration for performing information processing described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship shown in FIG. 5, and may be another connection relationship.

(Acquisition unit 131)
The acquisition unit 131 acquires the user's behavior information. The acquisition unit 131 acquires the user's action information from the terminal device 10 used by the user. In addition, the acquisition unit 131 acquires user information about the user. In addition, the acquisition unit 131 acquires the division information which is the behavior information regarding the user's behavior for each division regarding the user and which is the behavior information divided based on the context. For example, the acquisition unit 131 acquires the division information from the division information storage unit 123. In addition, the acquisition unit 131 acquires the division information in which the behavior information regarding the behavior of the user or the user for each classification based on the user attribute is divided based on the context as the division.

In addition, the acquisition unit 131 acquires a content distribution request from the terminal device 10. In addition, the acquisition unit 131 acquires information that identifies the user (for example, login ID, terminal identification information, etc.), location information of the terminal device 10, and the like.

Further, the acquisition unit 131 combines the behavioral information related to the behavior of each user, which is the behavioral information divided based on the context, based on the tendency of the behavioral information included in each of the divided information. Acquire a model that predicts a predetermined target, which is a model generated for each union information that is the information. For example, the acquisition unit 131 acquires information about the model from the cluster information storage unit 124 and the learning information storage unit 125. Further, when the user is a new user, the acquisition unit 131 acquires the model assigned to the new user corresponding to the allocation of the model for each context in another user similar to the user attribute of the new user.

(Estimation unit 132)
The estimation unit 132 estimates various information from the various acquired information. For example, the estimation unit 132 estimates various information based on the time when the content is delivered and the user's position information acquired from the terminal device 10. For example, the estimation unit 132 estimates the user of the distribution request source from the information for identifying the user acquired from the terminal device 10. For example, the estimation unit 132 estimates the location of the user based on the user information of the user stored in the user information storage unit 121 and the position of the terminal device 10. In FIG. 3, in the estimation unit 132, as shown in the user information storage unit 121, the work location of the user U1 is the position LC12, and the position of the terminal device 10-1 is the position LC12-1. Estimated to be at work location). Further, in FIG. 3, since the delivery request is made at 9:00 am, the estimation unit 132 estimates the context to be the context CT12 corresponding to the office in the morning.

Further, in the case where one division is a user, the estimation unit 132 uses the user based on the degree of similarity between the union information including each division information of the user and the union information including each division information of the other division. Estimate the user attributes of.

(Generator 133)
The generation unit 133 may generate the division information by dividing the collected behavior information regarding the user's behavior based on the context. Further, the generation unit 133 may store the generated division information in the division information storage unit 123. For example, the generation unit 133 may divide the collected information regarding the behavior of each user. For example, the generation unit 133 divides the collected behavior information of each user based on the context estimated by the estimation unit 132.

The generation unit 133 generates a model for predicting a predetermined target for each union information which is the division information combined based on the tendency of the behavior information included in each division information. For example, in FIG. 2, the mass MS at the position where the user U1 and the context CT11 intersect and the mass MS at the position where the user U4 and the context CT13 intersect are classified into the same cluster. The mass MS at the position where the user U1 and the context CT11 intersect and the mass MS at the position where the user U4 and the context CT13 intersect both include division information in which the action AT11 is “◯”. The mass MS at the position where the user U1 and the context CT11 intersect, and the mass MS at the position where the user U4 and the context CT13 intersect include division information showing the same tendency. Then, the generation unit 133 uses the union information including the division information of the mass MS at the position where the user U1 and the context CT11 intersect and the division information of the mass MS at the position where the user U4 and the context CT13 intersect, and the model M1 To generate.

In addition, the generation unit 133 generates a model that predicts a predetermined target regarding the user included in the division corresponding to the division information in the context corresponding to each of the division information included in the union information. The generation unit 133 generates a model for predicting a predetermined target for each union information including a combination that straddles the divisions. For example, the generation unit 133 uses the union information including the division information of the mass MS at the position where the user U2 and the context CT12 intersect and the division information of the mass MS at the position where the user U4 and the context CT14 intersect, and the model M6 To generate. That is, the generation unit 133 generates the model M6 by using the union information straddling the divisions between the user U2 and the user U4.

For example, the generation unit 133 determines for each union information in which the division information is combined so that the prediction accuracy of the predetermined target in the combination of the user classification and the context corresponding to each division information included in the union information is high. Generate a model that predicts the target. For example, the generation unit 133 generates a model for predicting a predetermined target for each union information in which the division information in which the behavior information included in each division information is similar is combined. For example, the generation unit 133 generates a model that predicts the user's interest in the content as a predetermined target.

For example, the generation unit 133 generates a model for predicting a predetermined target for each union information in which the division information is combined by a method in which the number of union information becomes a predetermined number. For example, the generation unit 133 generates a model for each union information in which the division information is combined by using the k-means method. In this case, the generation unit 133 generates the union information by combining the division information so as to be the number of clusters (the number of union information) determined (set) by the determination unit 134, and generates a model for each union information.

For example, the generation unit 133 generates a model for predicting a predetermined target for each union information in which the division information is combined by a method in which the number of union information can fluctuate. For example, the generation unit 133 generates a model for each union information in which the division information is combined by using the logistic regression method using the Dirichlet process. For example, the generation unit 133 generates union information by sequentially combining the division information, and generates a model for each union information.

For example, the generation unit 133 generates union information by combining a plurality of division information, and generates a model for the union information. For example, the generation unit 133 randomly selects a plurality of division information to generate union information, and generates a model for the union information. Then, the generation unit 133 verifies the prediction accuracy of the generated model. The prediction accuracy here means the probability that the presence or absence of user behavior can be predicted. For example, the prediction accuracy referred to here means the probability that a predetermined score or higher will be calculated for the content that is "○" in the behavior information when the model is used. Then, when the prediction accuracy of the generated model is equal to or higher than a predetermined threshold value, the generation unit 133 may perform a process of maintaining the combination and further combining the division information. Further, the generation unit 133 may use a predetermined hyperparameter such as a penalty term. For example, the generation unit 133 may use a penalty term whose value decreases as the number of clusters decreases. For example, the generation unit 133 may determine whether to maintain or cancel the combination based on a numerical value calculated by subtracting a value obtained by multiplying the number of clusters by a predetermined coefficient from the prediction accuracy of the model. In this case, the generation unit 133 generates union information and a model classified into a predetermined number of clusters based on a trade-off between the decrease in the number of clusters and the prediction accuracy of the model.

For example, the generation unit 133 may verify the prediction accuracy of the generated model by cross-validating a part of the model for generation and the rest for verification. For example, the generation unit 133 may use 80% of the union information for model generation and the remaining 20% for verification. For example, when the verified prediction accuracy satisfies a predetermined criterion, the generation unit 133 may perform a process of maintaining the combination and further combining the division information. Further, when the verified prediction accuracy does not satisfy a predetermined criterion, the generation unit 133 may release the combination and perform a process of combining another division information. Further, each time the division information is combined, the generation unit 133 maintains or cancels the combination by averaging the information used for model generation and the information used for verification and performing cross-validation a plurality of times. May be determined.

For example, when the generation unit 133 is a user and the division information of the user in one context does not satisfy a predetermined condition, the generation unit 133 divides another division similar to the user attribute of the user in one context. A model is generated by adding information to the user's split information in one context. For example, when the amount of division information of the user in one context is less than a predetermined amount, the generation unit 133 adds the division information of the other division in one context to the division information of the user in one context, thereby performing a model. To generate. The details of these points will be described later.

(Decision unit 134)
The determination unit 134 determines a model for determining the content to be distributed to the terminal device 10. In FIG. 3, the determination unit 134 uses a model M2 for determining the content to be distributed based on the information indicating the model M2 stored in the mass MS corresponding to the user U1 and the context CT12 in the cluster information storage unit 124. To decide. In FIG. 4, the determination unit 134 uses a model used to determine the content to be distributed based on the information indicating the model M1 stored in the mass MS corresponding to the user U1 and the context CT12 in the cluster information storage unit 124-2. Determined to be model M1.

For example, the determination unit 134 calculates the score of the content based on the determined model and the content. Further, for example, the determination unit 134 determines the ranking of each content based on the calculated score. In FIG. 3, the determination unit 134 determines the ranking of each content CN11 to CN18 or the like based on the score shown in the content list CL11. Further, the determination unit 134 determines the ranking of the article E, which is the content CN15 having the highest score, to be the first place. In addition, the determination unit 134 determines the ranking of the article G, which is the content CN17 having the highest score next to the article E, to be second. As a result, as shown in the ranking list LL11, the determination unit 134 has the ranking 1st place is the article E, the ranking 2nd place is the article G, the ranking 3rd place is the article A, and the ranking 4th place is the article F. Decide that there is. In FIG. 4, the determination unit 134 determines the ranking of each content CN11 to CN18 or the like based on the score shown in the content list CL12.

(Judgment unit 135)
The determination unit 135 uses the model acquired by the acquisition unit 131 to predict the prediction accuracy of a predetermined target for the user corresponding to the classification information in the context corresponding to each of the classification information included in the union information. Determine whether to change the information about the context or the information about the user attributes of the user. For example, the determination unit 135 determines that the information regarding the context of one user or the information regarding the user attributes of one user is changed when the prediction accuracy of the model assigned to one user does not satisfy a predetermined condition. In FIG. 1, since the determination unit 135 has low prediction accuracy of the two models, the model M1 assigned to the context CT11 of the user U1 and the model M2 assigned to the contest cost CT12, the information regarding the context of the user U1. Alternatively, it is determined that the information regarding the user attribute of the user U1 is changed. Further, the determination unit 135 changes the information regarding the context of the user or the information regarding the user attribute of the user according to the determination result.

For example, when there are a plurality of candidates for information on the user attribute of one user, the determination unit 135 changes the information on the user attribute of one user to which candidate based on the prediction accuracy to which each candidate is assigned. To judge. Details on this point will be described later. Further, for example, the determination unit 135 determines that the information regarding the context of one user is exchanged when the information regarding the context of one user can be exchanged. In FIG. 1, the determination unit 135 determines that the information regarding the context of the user U1 can be exchanged and that the information regarding the context of the user U1 is exchanged.

For example, the determination unit 135 determines a user who changes the information regarding the context or the information regarding the user attribute based on the reliability of the information regarding the context of each user or the reliability of the information regarding the user attribute of each user. For example, if the user is a user who has undergone a credit card examination, the determination unit 135 determines that the information regarding the user's age, gender, home, work location, etc. is highly reliable and is not subject to change. You may. Further, for example, when the user registers the user information with the information initially displayed when the user information is registered, the determination unit 135 gives priority to the information registered for the user as being unreliable. It may be determined that the change is the target. For example, when a user registers the date of birth with the information initially displayed when registering the user information, the determination unit 135 gives priority to the age registered for the user as being unreliable. It may be determined that it is the target of.

For example, the determination unit 135 determines that the information regarding the context of the new user or the information regarding the user attributes of the new user is changed when the prediction accuracy of the model assigned to the new user does not satisfy a predetermined condition. In FIG. 1, since the determination unit 135 has low prediction accuracy of the model M3-6 assigned to the context CT14 of the user U10, the distribution device 100 relates to the information regarding the context of the user U10 or the user attribute of the user U1. Judge that the information will be changed.

(Distribution Department 136)
The distribution unit 136 distributes various information to the terminal device 10. For example, the distribution unit 136 distributes the content to the terminal device 10. In addition, the distribution unit 136 distributes the content determined by the determination unit 134. In FIG. 3, the distribution unit 136 distributes the content shown in the ranking list LL11 to the terminal device 10-1. Further, the distribution unit 136 distributes the contents displayed in the order of article E, article G, article A, article F, and the like to the terminal device 10-1. Further, in FIG. 4, the distribution unit 136 distributes the content shown in the ranking list LL12 to the terminal device 10-1.

[4. Generation process flow]
[4-1. Method without setting the number of clusters]
Next, the procedure of the generation process by the distribution system 1 according to the embodiment will be described with reference to FIG. FIG. 12 is a flowchart showing an example of the generation process according to the embodiment. Specifically, FIG. 12 is a flowchart showing an example of generation processing by a method that does not determine the number of clusters (number of union information).

As shown in FIG. 12, the acquisition unit 131 of the distribution device 100 acquires the behavior information of each user (step S101). For example, the acquisition unit 131 acquires user behavior information from the terminal device 10 used by each user.

Further, the generation unit 133 of the distribution device 100 divides the information according to the context (step S102). For example, the generation unit 133 generates the divided information by dividing the action information according to the context when the action information is acquired. In addition, step S101 and step S102 may be performed a plurality of times.

After that, the generation unit 133 clusters the division information and generates a model by a method that does not determine the number of clusters (step S103). For example, the generation unit 133 generates a model for each union information in which the division information is combined by using the logistic regression method using the Dirichlet process.

[4-2. Method to set the number of clusters]
Next, the procedure of the generation process by the distribution system 1 according to the embodiment will be described with reference to FIG. FIG. 13 is a flowchart showing an example of the generation process according to the embodiment. Specifically, FIG. 13 is a flowchart showing an example of a generation process by a method of presetting (determining) the number of clusters (number of union information).

As shown in FIG. 13, the acquisition unit 131 of the distribution device 100 acquires the behavior information of each user (step S201). For example, the acquisition unit 131 acquires user behavior information from the terminal device 10 used by each user.

Further, the generation unit 133 of the distribution device 100 divides the information according to the context (step S202). For example, the generation unit 133 generates the divided information by dividing the action information according to the context when the action information is acquired. In addition, step S201 and step S202 may be performed a plurality of times.

Further, the determination unit 134 of the distribution device 100 sets (determines) the number of clusters (the number of union information) (step S203). For example, the determination unit 134 sets (determines) the number of clusters (the number of union information) to "6". The process of step S203 may be performed at any timing as long as it is before step S204.

After that, the generation unit 133 performs clustering of division information and generation of a model by a method of determining the number of clusters (step S204). For example, the generation unit 133 generates a model for each union information in which the division information is combined by using the k-means method.

[5. Delivery processing flow]
Next, the procedure of the distribution process by the distribution system 1 according to the embodiment will be described with reference to FIG. FIG. 14 is a flowchart showing an example of the distribution process according to the embodiment.

As shown in FIG. 14, the acquisition unit 131 of the distribution device 100 acquires the distribution request (step S301). For example, the acquisition unit 131 acquires a content distribution request from the terminal device 10 used by each user.

Then, the estimation unit 132 of the distribution device 100 estimates the user and the context (step S302). For example, the estimation unit 132 estimates the user of the distribution request source from the information for identifying the user acquired from the terminal device 10. Further, for example, the estimation unit 132 estimates the context based on the time when the distribution request is made and the position of the terminal device 10.

After that, the determination unit 134 of the distribution device 100 determines the model (step S303). For example, the determination unit 134 determines a model for determining the content to be distributed to the terminal device 10.

Then, the determination unit 134 determines the order of the contents (step S304). For example, the determination unit 134 calculates the score of the content based on the model and the content determined in step S303. Further, for example, the determination unit 134 determines the ranking of each content based on the calculated score.

After that, the distribution unit 136 of the distribution device 100 distributes the content based on the order (step S305). For example, the distribution unit 136 distributes the content based on the order determined in step S304.

[6. Judgment processing flow]
Next, the procedure of the determination process by the distribution system 1 according to the embodiment will be described with reference to FIG. FIG. 15 is a flowchart showing an example of the determination process according to the embodiment.

As shown in FIG. 15, the distribution unit 136 of the distribution device 100 distributes the content using the context-based model (step S401). For example, the distribution device 100 distributes the content by the processing of steps S301 to S305 shown in FIG.

Then, the determination unit 135 of the distribution device 100 determines whether or not the prediction accuracy of the predetermined user does not satisfy the predetermined condition (step S402). When the prediction accuracy of the predetermined user satisfies the predetermined condition (step S402: No), the distribution device 100 returns to step S401 and repeats the process.

On the other hand, when the prediction accuracy of the predetermined user does not satisfy the predetermined condition (step S402: Yes), the determination unit 135 changes the model assigned to the user attribute or context of the predetermined user to be determined (step S402: Yes). Step S403). That is, the determination unit 135 changes the information regarding the context of the predetermined user who is the determination target or the information regarding the user attribute of the user.

After that, the determination unit 135 determines whether or not the predicted accuracy after the change satisfies a predetermined condition (step S404). The predetermined conditions in steps S402 and S404 may be the same or different. When the prediction accuracy of the predetermined user does not satisfy the predetermined condition (step S402: No), the distribution device 100 returns to step S403 and repeats the process.

On the other hand, when the prediction accuracy of a predetermined user satisfies a predetermined condition (step S404: Yes), the distribution device 100 maintains the changed state in step S403, returns to step S401, and repeats the process.

[7. Judgment of multiple candidates]
In the above example, the case where the house and the office are exchanged and the context is exchanged is shown. You may decide whether to make the change. This point will be described with reference to FIG. FIG. 16 is a diagram showing an example of determination of a plurality of candidates according to an embodiment.

The division information list AL11 shown in FIG. 16 is the same as the division information storage unit 123 shown in FIG. That is, the divided information list AL11 has four time zones of morning (4 to 10 o'clock), noon (10 to 16 o'clock), night (16 to 22 o'clock), and midnight (22 to 4 o'clock), and home (home). Or, the case where it is divided into eight contexts CT11 to CT18 based on two positions of the office (work location) is shown. The divided information list AL11 includes users U1 to U4 and the like.

Here, it is assumed that the user U1 has three positions, LC111, LC112, and LC113, as candidates for a house (home). In this case, the distribution device 100 determines which of the user U1's homes will be used according to the prediction accuracy when the three positions LC111, LC112, and LC113 are assigned as the user U1's homes.

In the example shown in FIG. 16, it is assumed that the behavior information storage unit 122 stores the behavior information corresponding to each of the positions LC111, LC112, and LC113. For example, the division information AD111 indicates the behavior information (division information) of the user U1 at the morning position LC111 stored in the behavior information storage unit 122. Further, for example, the division information AD 112 indicates the behavior information (division information) of the user U1 at the morning position LC 112 stored in the behavior information storage unit 122. Further, for example, the division information AD113 indicates the behavior information (division information) of the user U1 in the morning position LC113 stored in the behavior information storage unit 122. Although not shown in FIG. 16, the action information storage unit 122 corresponds to each of the positions LC111, LC112, and LC113, and the action information corresponding to each time zone (day, night, midnight, etc.) other than the morning. Is also remembered.

Therefore, the distribution device 100 assigns a position with the house of the user U1 as the position LC111 (step S31). In this case, the division information AD111 is assigned to the mass MS corresponding to the context CT11 of the user U1 in the division information list AL11. Further, the corresponding divided information is also assigned to the mass MS corresponding to the contexts CT13, CT15, and CT17 related to the house of the user U1 in the discount information list AL11. Further, the distribution device 100 performs position allocation with the house of the user U1 as the position LC112 (step S32). Further, the distribution device 100 performs position allocation with the house of the user U1 as the position LC113 (step S33).

Then, the distribution device 100 performs the generation process for each allocation in steps S31 to S33 (step S34). That is, the distribution device 100 generates a model when each of the three positions LC111, LC112, and LC113 is assigned. Although described as steps S31 to S34 in FIG. 16 for the sake of simplicity, the generation process of step S34 may be performed for each of steps S31 to S33.

In FIG. 16, the distribution device 100 generates a model assigned to the mass MS corresponding to the context CT11 of the user U1 when the positions LC111, LC112, and LC113 are assigned to the home positions as shown in the model generation list RS11. .. Specifically, when the position LC111 is the position of the house of the user U1, the model M111 is assigned to the mass MS corresponding to the context CT11 of the user U1. Further, when the position LC112 is the position of the house of the user U1, the model M112 is assigned to the mass MS corresponding to the context CT11 of the user U1. Further, when the position LC113 is the position of the house of the user U1, the model M113 is assigned to the mass MS corresponding to the context CT11 of the user U1.

Here, in FIG. 16, the prediction accuracy is low when the model M111 is used in the context CT11 of the user U1 or when the model M113 is used in the context CT11 of the user U1. On the other hand, when the model M112 is used in the context CT11 of the user U1, the prediction accuracy is high. Therefore, the distribution device 100 determines the position LC112 as the position of the user U1's house (step S35). As a result, the distribution device 100 assigns the position LC112 to the position of the house of the user U1 as shown in the user attribute list UL11.

In the example of FIG. 16, in order to simplify the explanation, a case where the position of the house of the user U1 is determined according to the prediction accuracy of the model assigned to the mass MS corresponding to the context CT11 of the user U1 is shown. However, the distribution device 100 may determine the position of the user U1's house based on the prediction accuracy of the entire model corresponding to the allocation of each position. In the above example, the case where the distribution device 100 selects the candidate having the highest prediction accuracy from a plurality of candidates is shown, but the distribution device 100 uses various context estimation methods depending on the user, and the user's house ( You may estimate your home) or office (work location). For example, the distribution device 100 may perform context estimation by properly using a normal context estimation method and a highly accurate context estimation method capable of estimating a house or office more accurately than a normal context estimation method. good. For example, the normal context estimation method is inferior in estimation accuracy to the high-precision context estimation method, but the processing time is shorter. On the other hand, the highly accurate context estimation method requires a longer processing time than the normal context estimation method. For example, when the distribution device 100 estimates a user's home (home) or office (work location) using a normal context estimation method, the distribution device 100 provides a highly accurate context for a user whose estimation accuracy is difficult to improve. The estimation method may be used to estimate the user's home or office. For example, if a user's home or office is estimated using a highly accurate context estimation method for all users (for example, 1 million users), the time required for context estimation will be long, and it will be high for all. It is difficult to use an accurate context estimation method. Therefore, the distribution device 100 uses a highly accurate context estimation method for a user who has difficulty in improving the estimation accuracy when estimating a house or office when using a normal context estimation method. It is possible to improve the accuracy of context estimation while suppressing the time required for context estimation from becoming long. As a result, the distribution device 100 can improve the prediction accuracy by the model while suppressing the increase in the processing time.

[8. effect〕
As described above, the distribution device 100 according to the embodiment has an acquisition unit 131 and a determination unit 135. The acquisition unit 131 is behavior information related to the behavior of each user, and is information in which the division information, which is the behavior information divided based on the context, is combined based on the tendency of the behavior information included in each of the division information. It is a model generated for each union information, and a model for predicting a predetermined target is acquired. Further, the determination unit 135 corresponds to the prediction accuracy of a predetermined target regarding the user corresponding to the classification information in the context corresponding to each of the classification information included in the union information by the model acquired by the acquisition unit 131. Determine if you want to change information about the user's context or information about the user's user attributes.

As a result, the distribution device 100 according to the embodiment determines whether to change the information regarding the context of the user or the information regarding the user attributes of the user according to the prediction accuracy of the model in each context, thereby relating to the user. The information can be changed appropriately. Therefore, the distribution device 100 can appropriately change the information about the user by the prediction accuracy of the model based on the context.

Further, in the distribution device 100 according to the embodiment, when the prediction accuracy of the model assigned to one user does not satisfy a predetermined condition, the determination unit 135 provides information on the context of one user or the user of one user. Judge that the information about the attribute is changed.

As a result, the distribution device 100 according to the embodiment determines whether to change the information regarding the context of each user or the information regarding the user attributes of each user according to the prediction accuracy of the model assigned to each user. , Information about each user can be appropriately changed according to the prediction accuracy of the model based on the context. Therefore, the distribution device 100 can appropriately change the information about the user by the prediction accuracy of the model based on the context.

Further, in the distribution device 100 according to the embodiment, when there are a plurality of candidates for information on the user attribute of one user, the determination unit 135 relates to the user attribute of one user based on the prediction accuracy to which each candidate is assigned. Determine which candidate to change the information to.

As a result, the distribution device 100 according to the embodiment can appropriately change the information about the user according to the prediction accuracy of the model based on the context even when there are a plurality of candidates for the information about the user attribute of one user. Can be. Therefore, the distribution device 100 can appropriately change the information about the user by the prediction accuracy of the model based on the context.

Further, in the distribution device 100 according to the embodiment, the determination unit 135 determines that the information regarding the context of one user is replaced when the information regarding the context of one user can be replaced.

As a result, the distribution device 100 according to the embodiment determines that when the information regarding the context of a certain user can be replaced, the information regarding the context of the user is replaced, so that the information about the user can be predicted by the prediction accuracy of the model based on the context. Can be changed appropriately. Therefore, the distribution device 100 can appropriately change the information about the user according to the prediction accuracy of the model based on the context.

Further, in the distribution device 100 according to the embodiment, the determination unit 135 determines the information regarding the context or the information regarding the user attribute based on the reliability of the information regarding the context of each user or the reliability of the information regarding the user attribute of each user. Determine which user wants to change.

As a result, the distribution device 100 according to the embodiment has information on the context of the user or user attributes of the user, depending on the reliability of the information on the context of each user or the reliability of the information on the user attributes of each user. By determining whether to change the information about the user, the information about the user can be appropriately changed.

Further, in the distribution device 100 according to the embodiment, when the user is a new user, the determination unit 135 allocates the model to the new user corresponding to the allocation of the model for each context in another user similar to the user attribute of the new user. Get the model

As a result, the distribution device 100 according to the embodiment is set to the context even when a new user to which the model corresponding to the model allocation for each context in another user similar to the user attribute is assigned is the target of the change. The predictive accuracy of the based model allows the information about the user to be appropriately modified.

Further, in the distribution device 100 according to the embodiment, the determination unit 135 determines that the user attribute of the new user is changed when the prediction accuracy of the model assigned to the new user does not satisfy a predetermined condition.

As a result, the distribution device 100 according to the embodiment can appropriately change the user attributes of the new user according to the prediction accuracy of the model based on the context, even when the new user is the target of the change. ..

[9. Hardware configuration]
The distribution device 100 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 17 is a hardware configuration diagram showing an example of a computer that realizes the function of the distribution device. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a 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 part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program depending on the hardware of the computer 1000, and the like.

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

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

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

For example, when the computer 1000 functions as the distribution device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the network N.

Although some of the embodiments and modifications of the present application have been described in detail with reference to the drawings, these are examples and vary based on the knowledge of those skilled in the art, including the embodiments described in the disclosure line of the invention. It is possible to carry out the present invention in another form in which the above is modified or improved.

[10. others〕
Further, among the processes described in the above-described embodiments and modifications, all or part of the processes described as being automatically performed can be manually performed, or are described as being manually performed. It is also possible to automatically perform all or part of the processed processing by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

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

Further, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not contradict each other.

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

1 Distribution system 100 Distribution device (judgment device)
121 User information storage unit 122 Behavior information storage unit 123 Divided information storage unit 124 Cluster information storage unit 125 Learning information storage unit 126 Content information storage unit 130 Control unit 131 Acquisition unit 132 Estimating unit 133 Generation unit 134 Decision unit 135 Judgment unit 136 Distribution Part 10 Terminal device N network

Claims (7)

For each union information, which is behavior information related to the behavior of each user, the division information which is the behavior information divided based on the context is combined based on the tendency of the behavior information included in each of the division information. a generated model, an acquisition unit for acquiring a model to predict the predetermined target,
Wherein by model acquired by the acquiring unit, in accordance with the predetermined target prediction accuracy about the user corresponding to the classification information in the context corresponding to each of the classification information included in the union information, information related to the user Judgment unit that determines whether to change
Judgment device characterized by being equipped with. The acquisition unit
The determination device according to claim 1, wherein the model for predicting the user's interest in the content is acquired as the predetermined object. The determination unit
The determination according to claim 1 or 2, wherein when the prediction accuracy of the model does not satisfy a predetermined condition, it is determined that the information regarding the context of the user or the information regarding the user attribute of the user is changed. Device. The determination unit
The determination device according to claim 3, wherein when the prediction accuracy of the model is low, it is determined that the information regarding the context of the user is changed. The determination unit
The determination device according to claim 3 or 4, wherein when the prediction accuracy of the model is low, it is determined that the information regarding the position of the user is changed. It is a judgment method executed by a computer.
For each union information, which is behavior information related to the behavior of each user, the division information which is the behavior information divided based on the context is combined based on the tendency of the behavior information included in each of the division information. The acquisition process of acquiring a model that predicts a predetermined target , which is a model generated in
Wherein by model acquired by the acquisition step, in response to the predetermined target prediction accuracy about the user corresponding to the classification information in the context corresponding to each of the classification information included in the union information, information related to the user Judgment process to determine whether to change
A determination method characterized by including. For each union information, which is behavior information related to the behavior of each user, the division information which is the behavior information divided based on the context is combined based on the tendency of the behavior information included in each of the division information. The acquisition procedure for acquiring a model that predicts a predetermined target , which is a model generated in
Wherein by model acquired by the acquisition procedure, in accordance with the predetermined target prediction accuracy about the user corresponding to the classification information in the context corresponding to each of the classification information included in the union information, information related to the user Judgment procedure to determine whether to change
A judgment program characterized by having a computer execute the above.

Images