Information processing device, information processing method, and program

Abstract

To provide an information processing device capable of providing information suitable for a user on the basis of the user's behavior, an information processing method, and a program.SOLUTION: In an information processing system, an information processing device 1 comprises: a storage unit 12 which stores a behavior learning model trained to receive, as input, behavior information indicative of user behavior, and output degree information indicative of the degree to which the user behavior indicated by the input behavior information is estimated to be the behavior of a user belonging to a given community; an acquisition unit 131 which acquires behavior information indicative of the behavior of a user who is not participating in the community; an evaluation unit 132 which inputs the behavior information acquired by the acquisition unit into the behavior learning model and causes the degree information to be output; a determination unit 133 which determines whether to notify the user of community information on the basis of the degree information output by the evaluation unit; and a display control unit 134 which controls the display so that information related to the community is displayed on an information terminal of the user when the determination unit determines to notify the user of the community information.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] BACKGROUND ART In SNS (Social Networking Service), a group recommendation device is known that recommends information about a group different from the group that a user is browsing (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Re-tabled publication No. 2018 / 220734 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in conventional technology, the information recommended to a user is determined based on the groups to which other users who belong to the group the user is viewing belong, which can result in the problem of the user being provided with information about groups that are not suitable for the user.

[0005] The present invention has been made in consideration of these points, and has as its object to provide information suited to a user based on the user's behavior. [Means for solving the problem]

[0006] An information processing device of a first aspect of the present invention includes a memory unit that stores behavioral information indicating user behavior, which is a behavioral learning model that has learned the behavioral information of each of a plurality of users participating in a specified community, and which has been trained to take behavioral information as input and output degree information indicating the degree to which the user behavior indicated by the input behavioral information is estimated to be the behavior of a user belonging to the community; an acquisition unit that acquires behavioral information indicating the behavior of users who are not participating in the community; an evaluation unit that inputs the behavioral information acquired by the acquisition unit into the behavioral learning model and outputs degree information; an identification unit that identifies behavioral information to be learned by the behavioral learning model from the behavioral information acquired by the acquisition unit based on the degree information output by the evaluation unit; and a learning unit that further learns the behavioral information identified by the identification unit in the behavioral learning model.

[0007] The memory unit may further store a general-purpose learning model, which is a pre-trained general-purpose language model, configured to input behavioral information and output degree information, and the behavioral learning model is a trained model that has been fine-tuned based on behavioral information of multiple users participating in the specified community, and the evaluation unit may input the behavioral information into the general-purpose learning model and further output degree information.

[0008] The memory unit may store, for each of a plurality of different communities, a plurality of behavioral learning models that have learned behavioral information indicating the behavior of a plurality of users participating in each community, and the evaluation unit may input the behavioral information acquired by the acquisition unit into each of the plurality of behavioral learning models and output degree information for the community that each behavioral learning model targets.

[0009] The acquisition unit acquires behavioral information for each of a plurality of users who are not participating in the community, the evaluation unit inputs the behavioral information for each of the plurality of users acquired by the acquisition unit into the behavioral learning model and outputs degree information for each of the plurality of users targeted by the behavioral information, the identification unit identifies behavioral information from the behavioral information acquired by the acquisition unit to be learned by the behavioral learning model based on the degree information for each of the plurality of users output by the evaluation unit, and the learning unit may further learn the behavioral information identified by the identification unit into the behavioral learning model.

[0010] The acquisition unit acquires multiple pieces of behavioral information of users who are not participating in the community, the evaluation unit inputs the multiple pieces of behavioral information into the behavioral learning model and outputs degree information for each piece of behavioral information, the identification unit identifies behavioral information from the multiple pieces of behavioral information to be learned by the behavioral learning model based on the degree information corresponding to each piece of behavioral information output by the evaluation unit, and the learning unit may further learn the behavioral information identified by the identification unit into the behavioral learning model.

[0011] The acquisition unit may acquire multiple pieces of behavioral information of users who are not participating in the community, and the evaluation unit may input the multiple pieces of behavioral information acquired by the acquisition unit into the behavioral learning model and output degree information.

[0012] An information processing method of a second aspect of the present invention includes an acquisition step executed by a computer to acquire behavioral information indicating user behavior, the behavioral information indicating the behavior of a user who is not participating in a specified community; an evaluation step to input the behavioral information acquired in the acquisition step into a behavioral learning model that has learned the behavioral information of each of a plurality of users participating in the specified community and that is stored in a memory unit, the behavioral information being input and trained to output degree information indicating the degree to which the user behavior indicated by the input behavioral information is estimated to be the behavior of a user belonging to the community, and output the degree information; an identification step to identify behavioral information from the behavioral information acquired in the acquisition step to be learned by the behavioral learning model based on the degree information output in the evaluation step; and a learning step to further train the behavioral information identified in the identification step in the behavioral learning model.

[0013] In a third aspect of the program of the present invention, a computer is caused to execute an acquisition step of acquiring behavioral information indicating user behavior, the behavioral information indicating the behavior of users who are not participating in a specified community; an evaluation step of inputting the behavioral information acquired in the acquisition step into a behavioral learning model that has learned the behavioral information of each of a plurality of users participating in the specified community and that is stored in a memory unit, and that has been trained to use the behavioral information as input and output degree information indicating the degree to which the user behavior indicated by the input behavioral information is estimated to be the behavior of a user belonging to the community, and outputting the degree information; an identification step of identifying behavioral information from the behavioral information acquired in the acquisition step to be learned by the behavioral learning model based on the degree information output in the evaluation step; and a learning step of further learning the behavioral information identified in the identification step into the behavioral learning model.

[0014]

[0015] [Effects of the Invention]

[0016] According to the present invention, it is possible to provide information suited to a user based on the user's behavior. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a diagram for explaining an overview of an information processing system S according to an embodiment. [Figure 2] 1 is a block diagram showing a configuration of an information processing device 1. FIG. [Figure 3] 10 is a diagram for explaining an example of processing by an evaluation unit 132. FIG. [Figure 4] 10 is a diagram for explaining an example of processing by an evaluation unit 132. FIG. [Figure 5] 10 is a diagram for explaining an example of processing by an evaluation unit 132. FIG. [Figure 6] 3 is a flowchart showing the flow of processing in the information processing device 1. DETAILED DESCRIPTION OF THE INVENTION

[0018] [Outline of Information Processing System S] FIG. 1 is a diagram illustrating an overview of an information processing system S according to an embodiment. The information processing system S is a system for managing a fan community (hereinafter, sometimes referred to as a "predetermined community"). A fan community is a community for users who are fans of a particular product, service, brand, hobby, person, group, etc. to interact with each other. More specifically, a fan community is a social networking service (SNS) in which participating users post images, text, etc., and view, rate, and comment on other users' posts, thereby interacting with each other. As an example, the information processing system S includes an information processing device 1 and an information terminal 2.

[0019] The information processing device 1 is a device that manages fan communities. The information processing device 1 may manage each of multiple communities set up for each theme. The information processing device 1 accepts posts from users' information terminals 2 and displays information posted to the communities on the information terminals 2. The information processing device 1 evaluates the affinity between the user's behavior and the community, and sends a message encouraging users with a high affinity with the community to join.

[0020] The information terminal 2 is a terminal used by a user. The information terminal 2 is a smartphone, a tablet, or a personal computer. The information terminal 2 transmits, for example, posts made by the user to a community to the information processing device 1, and displays information obtained from the information processing device 1.

[0021] The processing in the information processing system S will be described. The information processing device 1 acquires behavioral information of a user (hereinafter referred to as a "target user") who is not a member of a predetermined community. The behavioral information is information that indicates the behavior of the user. Examples of the behavioral information include text posted by the user on an SNS, a product purchase history, or a log of a device used by the user.

[0022] The information processing device 1 stores a behavioral learning model. The behavioral learning model is a trained model for evaluating the affinity between a user's behavior and a community. The behavioral learning model is trained to receive behavioral information as input and output degree information about the user's behavior indicated by the input behavioral information. The behavioral learning model learns the behavioral information of each of multiple users participating in a specific community as training data. The degree information indicates the degree to which the user's behavior indicated by the behavioral information is estimated to be the behavior of a user belonging to the community. The behavioral learning model is generated by having a general-purpose learning model, which is a general-purpose natural language processing model, learn in advance the behavioral information of users participating in the community.

[0023] The information processing device 1 inputs the acquired behavioral information into a behavioral learning model and outputs degree information. Based on the degree information output by the behavioral learning model, the information processing device 1 determines whether to notify the target user of the community information. When determining to notify the target user of the community information, the information processing device 1 causes the information terminal 2 to display information about the community. The information about the community is, for example, a message encouraging the user to join the community.

[0024] By configuring the information processing system S in this way, it is expected that information suitable for the user can be provided based on the user's behavior.

[0025] [Configuration of information processing device 1] 2 is a block diagram showing the configuration of the information processing device 1. The information processing device 1 has a communication unit 11, a storage unit 12, and a control unit 13. The control unit 13 has an acquisition unit 131, an evaluation unit 132, a determination unit 133, a display control unit 134, an identification unit 135, and a learning unit 136.

[0026] The communication unit 11 is a communication interface for transmitting and receiving data to and from other devices via a network. The storage unit 12 is a storage medium including a ROM (Read Only Memory), a RAM (Random Access Memory), an SSD (Solid State Drive), a hard disk drive, etc. The storage unit 12 stores in advance a program to be executed by the control unit 13.

[0027] The storage unit 12 stores the behavioral learning model. The storage unit 12 may store user information in which a user ID (Identification) for identifying a user is associated with information indicating a community to which the user belongs.

[0028] The control unit 13 is a processor such as a CPU (Central Processing Unit), etc. The control unit 13 executes a program stored in the storage unit 12, thereby functioning as an acquisition unit 131, an evaluation unit 132, a determination unit 133, a display control unit 134, an identification unit 135, and a learning unit 136.

[0029] The acquisition unit 131 acquires behavioral information indicating the behavior of a user who is not participating in a community. As an example, the acquisition unit 131 acquires behavioral information of a user who is participating in another community. As an example, the behavioral information includes the user ID of the user who posts, a community ID indicating the community to which the post is to be made, and the content of the post. The acquisition unit 131 acquires behavioral information of the user to be evaluated from the information terminal 2. The evaluation unit 132 inputs the behavioral information acquired by the acquisition unit 131 into a behavioral learning model and causes it to output degree information.

[0030] An example of the processing of the evaluation unit 132 will be described with reference to FIG. 3. As an example, the evaluation unit 132 decomposes the behavioral information A1 acquired by the acquisition unit 131 into tokens (T1 to T6). A token is the smallest unit processed as natural language, and is a character, word, or vector corresponding to the content indicated by the purchase history of a specific product or a device log. The evaluation unit 132 inputs the tokens generated by decomposition from the behavioral information into a behavioral learning model in an autoregressive manner, and outputs degree information. In this case, the degree information is a conditional probability that an input token will be consecutive given a previously input token. As an example, the evaluation unit 132 inputs the sum of the conditional probabilities output by the behavioral learning model for each token as degree information to the determination unit 133.

[0031] 2, the determination unit 133 determines whether or not to notify the user of the community information based on the degree information output by the evaluation unit 132. As an example, the determination unit 133 may determine to notify the target user of the community information when the degree information output by the evaluation unit 132 is equal to or greater than a predetermined threshold.

[0032] When the determination unit 133 determines that the user should be notified, the display control unit 134 controls the information terminal 2 of the user to display information about the community. When the determination unit 133 determines that the target user should be notified of information about the community, the display control unit 134 controls the information terminal 2 to display, as an example, a message encouraging the user to join the community.

[0033] By configuring the information processing device 1 in this way, it is possible to provide information suited to the user based on the user's behavior.

[0034] The information processing device 1 may be configured to output degree information based on multiple pieces of behavioral information of the same user. An example of the processing of the evaluation unit 132 in this case will be described with reference to FIG. 4. The acquisition unit 131 acquires multiple pieces of behavioral information (A11 and A12) of users who are not participating in the community. The evaluation unit 132 inputs the multiple pieces of behavioral information acquired by the acquisition unit 131 into a behavior learning model and outputs degree information. As an example, the evaluation unit 132 targets behavioral information acquired within a predetermined period from the information terminal 2 of a user who is not participating in the community to be simultaneously input into the behavior learning model. The predetermined period is a period set in advance to associate behavioral information, such as several hours or one day.

[0035] The evaluation unit 132 generates tokens (T11 to T17) by decomposing each piece of behavioral information acquired by the acquisition unit 131. In the example shown in Fig. 4, the evaluation unit 132 generates tokens T11 to T16 based on behavioral information A11, and generates token T17 based on behavioral information A12. The evaluation unit 132 inputs the generated tokens T11 to T17 into a behavior learning model and causes it to output degree information.

[0036] By combining the behavioral information and evaluating the behavior of the user, the information processing device 1 is expected to be able to determine with higher accuracy whether or not the user should be notified of the community information.

[0037] The information processing device 1 may be configured to determine whether to notify the user of information based on the degree information output by the general-purpose learning model and the degree information output by the behavioral learning model.

[0038] The information processing device 1 may be configured to determine whether to notify the user of information about the community based on the difference with the degree information output by the general-purpose learning model. In this case, the behavioral learning model is a trained model obtained by fine-tuning the general-purpose learning model based on behavioral information of multiple users participating in a specific community. The general-purpose learning model is a pre-trained general-purpose language model. The general-purpose learning model is trained to be able to perform natural language processing based on a large amount of data set. The general-purpose learning model is configured to input behavioral information and output degree information. The memory unit 12 stores the general-purpose learning model.

[0039] Compared to a general-purpose learning model, a behavioral learning model is learned using behavioral information of users belonging to a specific community as training data, and therefore differs from a general-purpose learning model in that when behavioral information of a user belonging to a specific community is input, it is expected to output degree information indicating a higher likelihood that the user belongs to the specific community.

[0040] The evaluation unit 132 inputs the behavioral information acquired by the acquisition unit 131 into the general-purpose learning model and causes it to output degree information. The determination unit 133 determines whether or not to notify the user targeted by the behavioral information acquired by the acquisition unit 131 of community information, based on the degree information that the evaluation unit 132 has caused the behavioral learning model to output and the degree information that the evaluation unit 132 has caused the general-purpose learning model to output. As an example, the evaluation unit 132 may calculate the difference between the degree information output by the behavioral learning model and the degree information output by the general-purpose learning model, and determine to notify the user of the community information if the calculated difference is equal to or greater than a predetermined threshold.

[0041] In addition, when the magnitude relationship between the degree information that the evaluation unit 132 has output to the behavioral learning model and the degree information that the evaluation unit 132 has output to the general-purpose learning model satisfies a predetermined condition, the judgment unit 133 determines whether or not to notify the user targeted by the behavioral information acquired by the acquisition unit 131 of community information.

[0042] As an example, the determination unit 133 may determine whether to notify the user of the community information based on the ratio of the degree information output by the general-purpose learning model to the degree information output by the behavioral learning model. For example, if the degree information output by the general-purpose learning model is P0 and the degree information output by the behavioral learning model is P L In this case, the determination unit 133 determines that P L If / P0 is equal to or greater than a predetermined threshold, it is determined that the target user should be notified of the community information.

[0043] By configuring the information processing device 1 in this way, if the user's behavior has a high affinity with the behavior of a user who belongs to the community, the user can be notified of information about the community.

[0044] The information processing device 1 may manage a plurality of different communities. The processing in the information processing device 1 in this case will be described with reference to FIG. 5. The storage unit 12 stores, for each of the plurality of different communities, a plurality of behavior learning models (M i (i=1...n)

[0045] The evaluation unit 132 evaluates the behavior information acquired by the acquisition unit 131 based on a plurality of behavior learning models (M i ) and provide degree information (P Li (i=1...n)) is output for each of the communities. This configuration makes it possible to evaluate affinity with each of multiple different communities.

[0046] Furthermore, the information processing device 1 may be configured to determine which community's information to notify the user of, based on the degree information for each of a plurality of different communities. The determination unit 133 determines whether or not to notify the user, whose behavior information is acquired by the acquisition unit 131, of information about any of the communities based on the degree information about each community that the evaluation unit 132 has output. As an example, the determination unit 133 determines whether or not to notify the user, whose behavior information is acquired by the acquisition unit 131, of information about the communities based on the degree information (P Li ) is judged whether it exceeds the threshold, and the degree information (P Li ) exceeds a threshold value, the determination unit 133 may determine to notify the user of the community information. Li ) and the degree information output by the general-purpose learning model (P Li / P0), and whether or not any of the ratios exceeds a threshold may be used to determine whether to notify the user of the community information.

[0047] When the determination unit 133 determines that the community information should be notified, the display control unit 134 controls the display on the user's information terminal 2 of information related to a community that, among the plurality of different communities, is the target of degree information output by the evaluation unit 132 and that indicates the highest degree to which the user belongs. Note that the display control unit 134 may also control the display on the user's information terminal 2 of information related to a predetermined number of communities (for example, 3, 5, or 10) in descending order of the degree information output by the evaluation unit 132. Furthermore, the display control unit 134 may also control the display on the user's information terminal 2 of information related to each community whose degree information exceeds a threshold.

[0048] The accuracy of the behavioral learning model's judgment can be improved by having the behavioral learning model further learn behavioral information of users who are not members of the community but who have a high affinity with the behavior of users who belong to the community.

[0049] The acquisition unit 131 acquires behavioral information of each of a plurality of users who are not participating in the community. The evaluation unit 132 inputs the behavioral information of each of the plurality of users acquired by the acquisition unit 131 into a behavior learning model, and outputs degree information for each of the plurality of users targeted by the behavioral information.

[0050] The identification unit 135 identifies behavioral information to be learned by the behavioral learning model from the behavioral information acquired by the acquisition unit 131, based on the degree information for each of the multiple users output by the evaluation unit 132. As an example, the identification unit 135 may identify behavioral information input to output degree information indicating that the degree information is equal to or greater than a predetermined threshold as behavioral information to be learned by the behavioral learning model. Furthermore, the identification unit 135 may identify behavioral information in which the ratio between the degree information output by the behavioral learning model and the degree information output by the general-purpose learning model based on the same behavioral information is equal to or greater than a predetermined threshold as behavioral information to be learned by the behavioral learning model. The learning unit 136 further learns the behavioral information identified by the identification unit 135 in the behavioral learning model.

[0051] Furthermore, the information processing device 1 may be configured to have the behavior learning model learn multiple pieces of behavioral information about a single user.

[0052] The acquisition unit 131 acquires a plurality of pieces of behavioral information of users who are not participating in a community. The evaluation unit 132 inputs the plurality of pieces of behavioral information acquired by the acquisition unit 131 into the behavior learning model, and causes it to output degree information for each piece of behavioral information.

[0053] The identification unit 135 identifies behavioral information to be learned by the behavioral learning model from the plurality of behavioral information based on the degree information corresponding to each of the plurality of behavioral information output by the evaluation unit 132. The method by which the identification unit 135 identifies behavioral information to be learned by the behavioral learning model is as described above. Then, the learning unit 136 causes the behavioral learning model to further learn the behavioral information identified by the identification unit 135.

[0054] [Processing flow in information processing device 1] Fig. 6 is a flowchart showing the flow of processing in the information processing device 1. The flowchart shown in Fig. 6 starts from the point when it becomes possible to send a message encouraging participation in a community.

[0055] The acquisition unit 131 acquires behavioral information (S01). The evaluation unit 132 inputs the acquired behavioral information into a behavioral learning model and causes it to output degree information (S02). The evaluation unit 132 inputs the acquired behavioral information into a general-purpose learning model and causes it to output degree information (S03).

[0056] The determination unit 133 determines whether or not to notify the user of the community information based on the degree information output by the behavioral learning model and the degree information output by the general-purpose learning model (S04).

[0057] If the determination unit 133 determines that the user should be notified of the community information (YES in S04), the information processing device 1 causes the information terminal 2 of the user whose behavior information is the target to display the community information (S05), and ends the processing.

[0058] If the determination unit 133 does not determine that the user should be notified of the community information (NO in S04), the information processing device 1 ends the process.

[0059] [Effects of information processing device 1] By configuring the information processing device 1 in this way, it is expected that information suitable for the user can be provided based on the user's behavior.

[0060] Furthermore, this invention will make it possible to contribute to Goal 9 of the United Nations' Sustainable Development Goals (SDGs), which is "Build resilient infrastructure, promote inclusive and sustainable industrialization, and promote innovation and resilience."

[0061] The present invention has been described above using embodiments, but the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of the gist of the present invention. For example, all or part of the device can be configured by functionally or physically distributing or integrating any unit. Furthermore, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effects of the new embodiments resulting from the combination also have the effects of the original embodiments. [Explanation of symbols]

[0062] 1. Information processing equipment 2. Information terminal 11 Communications Department 12 Storage section 13 Control Unit 131 Acquisition Department 132 Evaluation Department 133 Judgment section 134 Display control unit 135 Specific part 136 Learning Department

Claims

1. a memory unit that stores behavioral information indicating user behavior, the behavioral learning model having learned the behavioral information of each of a plurality of users participating in a predetermined community, the behavioral learning model being trained to take the behavioral information as input and output degree information indicating the degree to which the user behavior indicated by the input behavioral information is estimated to be the behavior of a user belonging to the community; an acquisition unit that acquires behavior information indicating the behavior of users who are not participating in the community; an evaluation unit that inputs the behavioral information acquired by the acquisition unit into the behavior learning model and outputs degree information; an identification unit that identifies behavioral information to be learned by the behavior learning model from the behavioral information acquired by the acquisition unit based on the degree information output by the evaluation unit; a learning unit that further learns the behavioral information identified by the identification unit into the behavioral learning model; An information processing device having the above.

2. the storage unit further stores a general-purpose learning model that is a pre-trained general-purpose language model, the general-purpose learning model being configured to receive behavioral information as input and output degree information; the behavioral learning model is a trained model obtained by fine-tuning the general-purpose learning model based on behavioral information of a plurality of users participating in the predetermined community, The evaluation unit inputs the behavioral information into the general-purpose learning model and further outputs degree information. The information processing device according to claim 1 .

3. the storage unit stores, for each of a plurality of different communities, a plurality of behavioral learning models that have learned behavioral information indicating the behaviors of a plurality of users participating in each community; The evaluation unit inputs the behavioral information acquired by the acquisition unit into each of a plurality of behavioral learning models, and causes each behavioral learning model to output degree information about a target community. The information processing device according to claim 1 .

4. the acquisition unit acquires behavioral information of each of a plurality of users who are not participating in the community; the evaluation unit inputs the behavioral information of each of the plurality of users acquired by the acquisition unit into the behavior learning model, and outputs degree information for each of the plurality of users targeted by the behavioral information; the identifying unit identifies behavioral information to be learned by the behavior learning model from among the behavioral information acquired by the acquiring unit, based on degree information for each of the plurality of users output by the evaluating unit; the learning unit causes the behavioral learning model to further learn the behavioral information identified by the identification unit; The information processing device according to claim 1 .

5. the acquisition unit acquires a plurality of pieces of behavioral information of users who are not participating in the community; the evaluation unit inputs the plurality of pieces of behavioral information into the behavior learning model and outputs degree information for each piece of behavioral information; the identifying unit identifies behavioral information to be learned by the behavior learning model from among the plurality of behavioral information based on degree information corresponding to each of the plurality of behavioral information output by the evaluating unit; the learning unit causes the behavioral learning model to further learn the behavioral information identified by the identification unit; The information processing device according to claim 1 .

6. the acquisition unit acquires a plurality of pieces of behavioral information of users who are not participating in the community; the evaluation unit inputs the plurality of pieces of behavioral information acquired by the acquisition unit into the behavior learning model, and outputs degree information; The information processing device according to claim 1 .

7. The computer executes an acquiring step of acquiring behavioral information indicating user behavior, the behavioral information indicating the behavior of a user who is not participating in a predetermined community; an evaluation step of inputting the behavioral information acquired in the acquiring step into a behavioral learning model that has learned the behavioral information of each of a plurality of users participating in the specified community, which is stored in a memory unit, and that has been trained to take the behavioral information as input and output degree information that indicates the degree to which the user behavior indicated by the input behavioral information is estimated to be the behavior of a user belonging to the community, and outputting the degree information; a specifying step of specifying behavioral information to be learned by the behavior learning model from among the behavioral information acquired in the acquiring step, based on the degree information output in the evaluating step; a learning step of further learning the behavioral information identified in the identification step into the behavioral learning model; An information processing method comprising:

8. On the computer, an acquiring step of acquiring behavioral information indicating user behavior, the behavioral information indicating the behavior of a user who is not participating in a predetermined community; an evaluation step of inputting the behavioral information acquired in the acquiring step into a behavioral learning model that has learned the behavioral information of each of a plurality of users participating in the specified community, which is stored in a memory unit, and that has been trained to take the behavioral information as input and output degree information that indicates the degree to which the user behavior indicated by the input behavioral information is estimated to be the behavior of a user belonging to the community, and outputting the degree information; a specifying step of specifying behavioral information to be learned by the behavior learning model from among the behavioral information acquired in the acquiring step, based on the degree information output in the evaluating step; a learning step of further learning the behavioral information identified in the identification step into the behavioral learning model; A program to execute.

Images