JP6882116B2 - Generator, generation method, generation program, training data, and model - Google Patents

Description

The present invention relates to a generator, a generator, a generator, training data, and a model.

Conventionally, a service using various information about a user such as a user's behavior history on the Web has been provided. For example, a technique for associating a predetermined category based on an action history with a questionnaire attribute is provided.

Japanese Unexamined Patent Publication No. 2013-196037

However, it is not always possible to appropriately estimate the user's emotions with the above-mentioned prior art. For example, it is difficult to appropriately estimate the user's emotion only by associating a predetermined category based on the behavior history with the questionnaire attribute.

The present application has been made in view of the above, and an object of the present application is to provide a generation device, a generation method, a generation program, learning data, and a model that can appropriately estimate a user's emotion.

The generation device according to the present application is based on an acquisition unit that acquires user behavior information and emotion information related to the user's emotion, the user's behavior information acquired by the acquisition unit, and the user's emotion information. It is characterized by including a generation unit that generates a model for estimating the emotion of the input user to which the behavior information is input.

According to one aspect of the embodiment, there is an effect that the user's emotion can be appropriately estimated.

FIG. 1 is a diagram showing an example of a generation process according to an embodiment. FIG. 2 is a diagram showing an example of associating information according to the embodiment. FIG. 3 is a diagram showing a configuration example of the generation system according to the embodiment. FIG. 4 is a diagram showing a configuration example of the generator according to the embodiment. FIG. 5 is a diagram showing an example of the behavior information storage unit according to the embodiment. FIG. 6 is a diagram showing an example of the emotion information storage unit according to the embodiment. FIG. 7 is a diagram showing an example of the linked information storage unit according to the embodiment. FIG. 8 is a diagram showing an example of a model information storage unit according to the embodiment. FIG. 9 is a flowchart showing an example of the determination process according to the embodiment. FIG. 10 is a flowchart showing an example of the generation process according to the embodiment. FIG. 11 is a diagram showing an example of the estimation process according to the embodiment. FIG. 12 is a diagram showing an example of a generation process using user operation information. FIG. 13 is a hardware configuration diagram showing an example of a computer that realizes the function of the generator.

Hereinafter, the generator, the generation method, the generation program, the learning data, and the embodiment for carrying out the model (hereinafter referred to as “the embodiment”) according to the present application will be described in detail with reference to the drawings. It should be noted that this embodiment does not limit the generator, the generation method, the generation program, the learning data, and the model according to the present application. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

(Embodiment)
[1. Generation process]
First, an example of the generation process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of a generation process according to an embodiment. FIG. 1 shows an example in which the generation device 100 associates (associates) user information. Further, FIG. 1 shows an example of generating a model using the information associated with the generation device 100. In the following, information (data) in which the user's behavior information and the correct answer information, which is the user's emotional information, are associated with each other is also referred to as "learning data".

[Configuration of generation system]
First, prior to the description of FIG. 1, the generation system 1 shown in FIG. 3 will be described. As shown in FIG. 3, the generation system 1 includes a terminal device 10, a service providing device 50, and a generation device 100. The terminal device 10, the service providing device 50, and the generating device 100 are connected to each other via a predetermined network N so as to be communicable by wire or wirelessly. FIG. 3 is a diagram showing a configuration example of the generation system according to the embodiment. The generation system 1 shown in FIG. 3 may include a plurality of terminal devices 10, a plurality of service providing devices 50, and a plurality of generation 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. In the example shown in FIG. 1, a case where the terminal device 10 is a smartphone used by a user is shown. 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. Specifically, FIG. 1 shows a case where the terminal device 10 is a smartphone used by a user identified by the user ID “U1” (hereinafter, may be referred to as “user U1”).

Further, the terminal device 10 has a function such as a GPS (Global Positioning System) sensor, and detects and acquires the user's position information (sensor information). Further, the terminal device 10 may estimate and acquire the user's position information by using the position information of the base station communicating with the user or the radio wave of WiFi (registered trademark) (Wireless Fidelity). In the following, the position information may be simply described as "position". Further, the terminal device 10 may detect various sensor information not only by a GPS sensor or the like but also by various sensors. Further, the terminal device 10 has a function of an acceleration sensor, and detects and acquires acceleration information (sensor information) in the movement of the user. Further, the terminal device 10 may have various functions such as a temperature sensor and a barometric pressure sensor, and may be able to detect and acquire environmental information such as temperature and barometric pressure in which the user is placed. Further, the terminal device 10 may have various functions such as a heart rate sensor and may be able to detect and acquire the biometric information of the user. For example, a user who uses the terminal device 10 may be able to acquire the user's own context information by the terminal device 10 by wearing a wearable device capable of communicating with the terminal device 10. For example, a user who uses the terminal device 10 wears a wristband-type wearable device capable of communicating with the terminal device 10, and the terminal device 10 acquires information on the user's own heartbeat (pulse) by the terminal device 10. It may be possible. For example, the terminal device 10 accepts a user's operation on a touch panel display.

Further, in the example shown in FIG. 1, the terminal device 10 will be described as the terminal device 10-1 to 10-5 according to the user who uses the terminal device 10. For example, the terminal device 10-1 is a terminal device 10 used by the user U1. Further, for example, the terminal device 10-2 is a terminal device 10 used by the user U2. Further, in the following, when the terminal devices 10-1 to 10-5 will be described without particular distinction, they will be referred to as the terminal device 10. As described above, when "user U * (* is an arbitrary numerical value)" is described, it means that the user is a user identified by the user ID "U *". For example, when described as "user U1", that user is a user identified by the user ID "U1".

The service providing device 50 is an information processing device that provides a user with service A, which is a video distribution service (also simply referred to as “video service”). For example, the service providing device 50 provides a moving image service to a user who uses the terminal device 10. For example, the service providing device 50 provides the terminal device 10 with various information regarding the A service.

The generation device 100 is an information processing device that determines that the questionnaire information about the questionnaire answered by the user is associated with the behavior information of the user when the information about the user satisfies a predetermined condition. Further, the generation device 100 is an information processing device that generates a model for estimating the emotion of the input user to which the behavior information is input based on the behavior information of the user and the emotion information regarding the emotion of the user. In addition, the generation device 100 provides various services based on the estimated information about the user's emotions. For example, the generation device 100 provides the service providing device 50 with information on the estimated user's emotions, and the service providing device 50 provides various services to the user using the provided information. 11 will be described.

First, an example of the generation process according to the embodiment will be described with reference to FIG. FIG. 1 shows a case where the generation device 100 associates (associates) the behavior information collected from each user with the questionnaire response based on a predetermined condition. Further, FIG. 1 shows a case where a model for estimating a user's emotion is generated by using a combination (learning data) of the behavior information (associated) associated (associated) with the questionnaire response by the generation device 100. Further, in the following, the example of FIG. 1 will be described with reference to FIG. FIG. 2 is a diagram showing an example of associating information according to the embodiment.

The generation device 100 acquires the action information of the user U1 from the terminal device 10-1 used by the user U1 (step S11-1). For example, the generation device 100 acquires the action information of the user U1 in the A service from the terminal device 10-1. As shown in FIG. 2, the generation device 100 may acquire user behavior information in a service other than the A service, such as the B service, which is an electronic commerce service. For example, the generation device 100 may acquire the action information of the user U1 in the B service from the terminal device 10-1.

Further, the generation device 100 is not limited to the above, and may acquire various behavior information of the user. For example, the generation device 100 acquires the behavior information of the user U1 on the Internet (web) from the terminal device 10-1. For example, the generation device 100 acquires various behavioral information on the web, such as information indicating that the user U1 has browsed the web content and information indicating that the user U1 has performed a search using a query. For example, the generation device 100 may acquire behavior information of the user U1 in the real world (hereinafter referred to as “real space”). Further, for example, the generation device 100 may acquire various behavioral information such as information indicating that the user U1 has purchased the B product at the A convenience store and information indicating that the user U1 has eaten or eaten at the B restaurant. Good.

Further, the generation device 100 acquires action information from the terminal device 10-2 used by the user U2 (step S11-2). For example, the generation device 100 acquires the action information of the user U2 in the A service from the terminal device 10-2. Further, as shown in FIG. 2, the generation device 100 acquires the action information of the user U2 in the A service and the B service. Further, for example, the generation device 100 acquires the behavior information of the user U2 on the web or in the real space from the terminal device 10-2.

Further, the generation device 100 acquires the action information from the terminal device 10-3 used by the user U3 (step S11-3). For example, the generation device 100 acquires the action information of the user U3 in the A service from the terminal device 10-3. For example, the generation device 100 acquires behavioral information indicating that the A service of the user U3 has been used within a predetermined period (for example, the latest one month or two weeks) before step S11-3. For example, the generation device 100 acquires the action information of the user U3 on the Web or in the real space, such as the action information of the user U3 in the A service, from the terminal device 10-3.

Further, the generation device 100 acquires the action information from the terminal device 10-4 used by the user U4 (step S11-4). For example, the generation device 100 acquires the action information of the user U4 in the A service from the terminal device 10-4. For example, the generation device 100 acquires behavioral information indicating that the A service of the user U4 has been used within a predetermined period (for example, the latest one month or two weeks) before step S11-4. For example, the generation device 100 acquires the action information of the user U4 on the Web or in the real space, such as the action information of the user U4 in the A service, from the terminal device 10-4.

Hereinafter, when steps S11-1 to S11-4 will be described without distinction, they are collectively referred to as step S11. Further, the acquisition of the behavior information of each user is not limited to steps S11-1 to S11-4, and may be performed a plurality of times. In FIG. 1, five users U1 to U5 are illustrated, but the generation device 100 is not limited to the users U1 to U5, and the behavior information of a large number of users (for example, 1 million users, 10 million users, etc.) is obtained. get. Further, the generation device 100 may acquire the action information of each user from an external device other than the terminal device 10 used by each user. For example, the generation device 100 may acquire behavior information of each user from an external device that provides a service used by each user.

Here, in the examples of FIGS. 1 and 2, it is assumed that the generation device 100 has not acquired the action information in the A service from the terminal device 10-5 used by the user U5. That is, in the examples of FIGS. 1 and 2, it is assumed that the user U5 is a user who has not used the A service within a predetermined period from the time of step S11 (hereinafter, referred to as “nonconforming user”). For example, in the examples of FIGS. 1 and 2, it is assumed that the user U5 is a nonconforming user who has not used the A service for one month or more. It is assumed that the generation device 100 has acquired the behavior information ADT5 of the user U5 that does not include the behavior information regarding the use of the A service within a predetermined period. As described above, in the example of FIG. 1, the generation device 100 generates behavior information of the user group UG1 including the users U1 to U4 and the like who are using the A service within a predetermined period, and the other users U5 and the like. get.

Then, in the example shown in FIG. 1, the generation device 100 acquires the questionnaire information regarding the questionnaire answered by the user. For example, the generation device 100 acquires questionnaire information from a plurality of workers who perform tasks such as so-called crowdsourcing. Specifically, the generation device 100 causes the user (worker) to answer the questionnaire regarding the A service by crowdsourcing, and obtains the answer.

For example, as shown in FIG. 2, the generator 100 crowdsources a user (worker) to questionnaire AN11 having various contents such as "Do you recommend service A to friends and colleagues? (Answer from 0 to 10)". ) To answer and get the answer. For the questionnaire, various conventional methods such as Net Promoter Score may be used.

For example, in the example of FIG. 1, the generator 100 posts the work (task) of the answer to the questionnaire AN11 on a predetermined site or the like, and requests the work (task) from an unspecified number of people (users). , Recruit users (workers) to answer the questionnaire AN11. It should be noted that the processing related to crowdsourcing as described above may be performed by another external device, and the generation device 100 may acquire the response to the user's questionnaire from the other external device. In the examples of FIGS. 1 and 2, in order to simplify the explanation, the questionnaire AN11 shows "Do you recommend the A service to your friends and colleagues? (Answer from 0 to 10)". Explain as if only.

For example, the generation device 100 acquires the answer of the user U3 from the terminal device 10-3 used by the user U3 who is a worker (step S12-1). For example, the user U3 responds to the questionnaire AN11 by accepting the task of answering the questionnaire AN11 on a crowdsourcing site or the like using the terminal device 10-3. In the example of FIG. 1, the generation device 100 obtains an answer from the user U3 that the answer to the questionnaire AN11 is a score of “3”.

Further, for example, the generation device 100 acquires the answer of the user U4 from the terminal device 10-4 used by the user U4 who is a worker (step S12-2). For example, the user U4 responds to the questionnaire AN11 by accepting the task of answering the questionnaire AN11 on a crowdsourcing site or the like using the terminal device 10-4. In the example of FIG. 1, the generation device 100 obtains an answer from the user U4 that the answer to the questionnaire AN11 is a score of “9”.

Further, for example, the generation device 100 acquires the answer of the user U5 from the terminal device 10-5 used by the user U5 who is a worker (step S12-3). For example, the user U5 responds to the questionnaire AN11 by accepting the task of answering the questionnaire AN11 on a crowdsourcing site or the like using the terminal device 10-5. In the example of FIG. 1, the generation device 100 obtains an answer from the user U5 that the answer to the questionnaire AN11 is a score of “1”.

Hereinafter, when steps S12-1 to S12-3 are described without distinction, they are collectively referred to as step S12. Although five users U1 to U5 are shown in FIG. 1, the generation device 100 is not limited to the users U3 to U5, and a large number of users (for example, 10,000 users, 100,000 users, etc.) can submit to the questionnaire. Obtain questionnaire information including answers. Further, the generation device 100 may acquire the questionnaire information of each user from an external device other than the terminal device 10 used by each user. For example, the generation device 100 may acquire questionnaire information of each user from an external device that provides a service related to crowdsourcing. In this way, the generation device 100 obtains an answer from a user (worker) who has consented to perform a task in crowdsourcing. In the example of FIG. 1, the generation device 100 acquires a response from the response user group UG2 including the users U3 to U5 and the like.

Then, the generation device 100 collects the action information of each user U1 to U5 or the like (step S13). In the example of FIG. 1, the generation device 100 stores the collected action information of each user U1 to U5 or the like in the action information storage unit 121. For example, the generation device 100 associates the action information ADT1 of the user U1 with the user U1 and stores it in the action information storage unit 121. For example, the generation device 100 associates the action information ADT2 of the user U2 with the user U2 and stores it in the action information storage unit 121. For example, the generation device 100 collects the action log of the user of the user group UG1 who used the A service within a predetermined period as shown in the action log LG11 in FIG.

In addition, the generation device 100 collects questionnaire information including answers from each worker including each user U3 to U5 (step S14). For example, as shown in the questionnaire response log AL11 in FIG. 2, the generation device 100 collects questionnaire information and the like of the users of the response user group UG2 who answered the questionnaire of the A service in crowdsourcing. In the example of FIG. 1, the generation device 100 stores the collected questionnaire information of each user U3 to U5 and the like in the emotion information storage unit 122. For example, the generation device 100 stores the questionnaire response of each user and the emotion corresponding to the questionnaire response (hereinafter, also referred to as “corresponding emotion”) in the emotion information storage unit 122 in association with the user.

The “user ID” shown in the emotion information storage unit 122 in FIG. 1 indicates identification information for identifying a user. The “questionnaire response” shown in the emotion information storage unit 122 in FIG. 1 indicates the content of the response by the corresponding user. The “corresponding emotion” shown in the emotion information storage unit 122 in FIG. 1 indicates the emotion of the user. For example, "correspondence emotion" indicates an estimation of the presence or absence of user behavior based on a comparison between a predetermined threshold value and a questionnaire response. In FIG. 1, when the questionnaire response is "6" or less (that is, "0" to "6"), the "correspondence emotion" is estimated to be "disgust", and the questionnaire responses are "7" and "8". In this case, it is presumed to be "neutral", and when the questionnaire response is "9" or more (that is, "9", "10"), it is presumed to be "favorable".

In the example of FIG. 1, the generation device 100 stores the questionnaire response “3” of the user U3 and the corresponding emotion “disgust” in the emotion information storage unit 122 in association with the user U3. For example, the generation device 100 stores the questionnaire response “9” of the user U4 and the corresponding emotion “favorability” in the emotion information storage unit 122 in association with the user U4. For example, the generation device 100 stores the questionnaire response “1” of the user U5 and the corresponding emotion “disgust” in the emotion information storage unit 122 in association with the user U5.

Then, the generation device 100 determines the target to be associated with the user's behavior information and the user's questionnaire information (step S15). Here, in the example of FIG. 1, the questionnaire information stored in the emotion information storage unit 122 is a questionnaire of a user who is not suitable for answering the questionnaire of the A service such as a nonconforming user who does not use the A service very much. Contains information. Therefore, the generation device 100 determines a target to which the questionnaire information of a user who is not a non-conforming user (hereinafter referred to as "conforming user") is associated with the questionnaire information of the user. Then, the generation device 100 determines that the questionnaire information of the user whose behavior information group includes the behavior information among the conforming users is associated with the behavior information of the user.

In the example of FIG. 1, the generation device 100 determines that the user U3 who is using the A service within a predetermined period of the responding user group UG2 is set as the matching user and is to be linked. For example, the generation device 100 associates the action of the user U3 with the answer, as shown in FIG. For example, the generation device 100 associates the questionnaire information of the user U3 with the behavior information. In the example of FIG. 1, as shown in the association information storage unit 123, the generation device 100 stores the behavior information ADT3 of the user U3 in association with the score (emotion) included in the questionnaire information. Specifically, the generation device 100 associates the behavior information ADT3 of the user U3 with the score “3” and the emotion “disgust”, and stores the data (data DT1) identified by the data ID “DT1”.

Further, in the example of FIG. 1, the generation device 100 determines that the user U4 who is using the A service within a predetermined period of the response user group UG2 is set as the matching user and is to be linked. For example, the generation device 100 associates the action of the user U4 with the answer, as shown in FIG. For example, the generation device 100 associates the questionnaire information of the user U4 with the behavior information. In the example of FIG. 1, as shown in the association information storage unit 123, the generation device 100 stores the behavior information ADT4 of the user U4 in association with the score (emotion) included in the questionnaire information. Specifically, the generation device 100 associates the behavior information ADT4 of the user U4 with the score “9” and the emotion “favorability”, and stores the data (data DT2) identified by the data ID “DT2”.

Further, in the example of FIG. 1, the generation device 100 determines that the user U5, which is a nonconforming user, among the responding user group UG2, is not to be linked. For example, the generation device 100 determines that the answer of the user U5 is not associated with the action, as shown in FIG.

As described above, the generator 100 can prevent the use of useless information by determining that the information of the user (non-conforming user) who is not suitable for answering the questionnaire of the A service is not linked. .. For example, in crowdsourcing, a worker who performs a certain task may include a user (non-conforming user) who performs the task for a predetermined benefit (points, money, etc.). Such non-conforming users are often users who are not related to the task, and when the information of such a user (worker) and the information of a user suitable for performing the task are mixed, the information of the information There is a problem that the accuracy is reduced. Therefore, the generation device 100 does not associate the information of the nonconforming user, that is, determines that the information of the nonconforming user is not used, so that the information of only the conforming user can be used and the accuracy of the information is improved. Can be done. Therefore, the generation device 100 can appropriately make available the user's information.

In addition, the generation device 100 determines whether or not the other users included in the response user group UG2 are also associated in the same manner. In the example of FIG. 1, the generation device 100 determines that the user U18 is a conforming user and is to be linked. For example, the generation device 100 associates the behavior information ADT18 of the user U18 with the score “7” and the emotion “neutral”, and stores the data (data DT3) identified by the data ID “DT3”.

Then, the generation device 100 generates a model based on the training data (step S16). For example, the generation device 100 generates a model by performing learning using the data DT1 to DT3 in the associated information storage unit 123 as learning data (teacher data). For example, the generation device 100 generates a model using the feature amount related to the user's behavior information. Further, for example, the generation device 100 generates a model by using the feature amount related to the behavior information of the user on the Web. For example, the generation device 100 generates a model using features related to behavior information in the user's real space. In this way, the generation device 100 learns the features included in the user's behavior information and generates a model for estimating information about the user's emotions. The features included in the behavior information learned by the generation device 100 may be input to the generation device 100 by a person such as an administrator of the generation device 100, or may be automatically learned (extracted) by the generation device 100. May be good.

For example, the generation device 100 generates the model M1 using the data stored in the associated information storage unit 123 as learning data (teacher data). For example, as shown in the data DT1, the generation device 100 indicates that the correct answer information has a score of "3" corresponding to the user's emotion "disgust", and the behavior information included in the data DT1 is input to the model M1. , The learning process is performed so that the score output by the model M1 approaches "3". For example, the generation device 100 performs a learning process so that when the behavior information ADT3 of the data DT1 is input to the model M1, the score output by the model M1 approaches "3". In this way, the generation device 100 generates a model using the behavior information of the user whose score is less than a predetermined threshold value (for example, "7" or the like) as a negative example (bad emotion).

Further, for example, in the generation device 100, as shown in the data DT2, when the correct answer information has a score "9" corresponding to the user's emotion "favorability", the behavior information included in the data DT2 is input to the model M1. In this case, the learning process is performed so that the score output by the model M1 approaches "9". For example, the generation device 100 performs a learning process so that when the behavior information ADT4 of the data DT2 is input to the model M1, the score output by the model M1 approaches "9". In this way, the generation device 100 generates a model using the behavior information of the user whose score is equal to or higher than a predetermined threshold value (for example, "9") as a positive example (good emotion).

Further, for example, when the correct answer information has a score of "7" corresponding to the user's emotion "neutral" as shown in the data DT3, the generation device 100 has input the action information included in the data DT3 into the model M1. In this case, the learning process is performed so that the score output by the model M1 approaches "7". For example, the generation device 100 performs a learning process so that when the behavior information ADT18 of the data DT3 is input to the model M1, the score output by the model M1 approaches "7".

The model learning method is not limited to the above-mentioned method, and any known technique can be applied. It should be noted that the generation of each model may be performed by appropriately using various conventional techniques related to machine learning. For example, the model may be generated by using a technique related to machine learning of supervised learning such as SVM (Support Vector Machine). Further, for example, model generation may be performed using a technique related to machine learning of unsupervised learning. For example, model generation may be performed using a technique of deep learning. For example, the model may be generated by appropriately using various deep learning techniques such as DNN (Deep Neural Network), RNN (Recurrent Neural Network), and CNN (Convolutional Neural Network). The description regarding the generation of the model is an example, and the generation of the model may be performed by a learning method appropriately selected according to the information that can be acquired and the like. That is, if the generation device 100 can learn the model M1 so as to output the score corresponding to the correct answer information when the behavior information included in the learning data is input, any method can be used to generate the model M1. May be done.

Through the above processing, in the example of FIG. 1, the generation device 100 generates a model (model M1) identified by the model ID “M1” as shown in the model information storage unit 124. As described above, when "model M * (* is an arbitrary numerical value)" is described, it means that the model is a model identified by the model ID "M *". For example, when described as "model M1", the model is a model identified by the model ID "M1". Further, as shown in the model information storage unit 124 in FIG. 1, the model M1 is an estimation target "emotion", that is, a model used for estimating the user's emotion, and the specific model data thereof is "model data". It indicates that it is "MDT1". For example, the generation device 100 inputs the user's behavior information into the model M1 and causes the model M1 to output a score used for estimating the emotion of the user (input user) corresponding to the input behavior information to the model M1. Estimates the emotion of the input user based on the score output by.

As described above, the generation device 100 can generate a model that enables the user's emotions to be appropriately estimated by learning using the learning data in which the behavior information and the correct answer information are associated with each other. Therefore, by using the model generated as described above, the generation device 100 can accurately estimate, for example, what kind of emotion the user using the A service has. Therefore, the generation device 100 can appropriately estimate the user's emotions.

[1-1. Questionnaire information]
In the example of FIG. 1, when the user performs an action related to the target of the questionnaire within a predetermined period, the generation device 100 determines that the user's questionnaire information is associated with the user's action information. Specifically, the generation device 100 determines that when the user is performing an action in the A service that is the target of the questionnaire within a predetermined period, the user's questionnaire information is associated with the user's action information. The above is an example, and the generation device 100 may perform the determination process by appropriately using various information.

For example, the generation device 100 acquires questionnaire information regarding the questionnaire answered by the user included in the target list of the questionnaire. For example, the generation device 100 may have a user (target user) satisfying a predetermined condition answer the questionnaire. For example, the generation device 100 may request the target user included in the target list of the questionnaire to answer the questionnaire, and acquire the questionnaire information about the questionnaire answered by the target user. Then, for example, the generation device 100 may decide to associate the questionnaire information of the user whose behavior information group includes the behavior information of the user among the target users with the behavior information of the user.

Further, for example, the generation device 100 may acquire questionnaire information regarding the questionnaire answered by the user included in the target list of the questionnaire. For example, the generation device 100 may acquire questionnaire information regarding a questionnaire answered by a user who has performed an action related to the A service that is the target of the questionnaire.

For example, the generation device 100 may decide to associate the user's questionnaire information with the user's behavior information when the behavior regarding the target of the user's questionnaire satisfies a predetermined condition. For example, the generation device 100 may decide to associate the user's questionnaire information with the user's behavior information when the behavior regarding the target of the user's questionnaire is a predetermined amount or more. For example, the generation device 100 may decide to associate the user's questionnaire information with the user's behavior information when the frequency of use of the A service, which is the target of the user's questionnaire, is equal to or higher than a predetermined threshold value. For example, the generation device 100 may decide that when the user is a heavy user of the A service, the questionnaire information of the user is associated with the behavior information of the user.

[1-2. Emotional estimation]
The generation device 100 is not limited to the example of FIG. 1, and may estimate the user's emotion by appropriately using various information. This point will be described with reference to FIG. FIG. 12 is a diagram showing an example of a generation process using user operation information. In the example of FIG. 12, a case is shown in which information regarding the operation of the user U11 with respect to the terminal device 10 is collected and a model M11 for estimating the user's emotion is generated using the user's operation history (user operation log). Further, in the example of FIG. 12, a case where the user's emotion estimated by using the input information such as the character information input by the user U11 is used as the correct answer information is shown.

First, the user U11 operates the terminal device 10 (step S21). In the example of FIG. 12, the user U11 activates the application XX and performs various operations such as clicking and scrolling on the application XX by touching (touching) the screen of the terminal device 10 with the finger F1. And. For example, the user U11 is assumed to perform various operations such as clicking and scrolling with the finger F1 on the application XX displayed on the screen of the terminal device 10. For example, since the usability of the application XX is low, the user U11 is supposed to perform various operations such as strongly pressing the screen of the terminal device 10 and performing a scrolling operation at high speed.

Then, the generation device 100 (see FIG. 1) collects the user operation log of the user U11 (step S22). In the example of FIG. 12, the generation device 100 collects the user operation log of the user U11 as shown in the user operation log OP11 in FIG. For example, the generation device 100 associates the collected user operation log of the user U11 with the user U11 and stores it in the action information storage unit 121 (see FIG. 1).

Further, the generation device 100 collects input information (posted information) input (posted) by the user U11 in a predetermined SNS (Social Networking Service) (step S23). In the example of FIG. 12, the generation device 100 collects information indicating that the user U11 posted the content "App XX is difficult to use and frustrated ..." at a predetermined SNS at the date and time dt1. In the example of FIG. 12, the generation device 100 collects the posted information of the user U11 as shown in the posted information list INF11 in FIG. For example, the generation device 100 associates the collected posted information of the user U11 with the user U11 and stores it in the action information storage unit 121.

Then, the generation device 100 estimates the user's emotion using the collected posted information (step S24). Here, in the example of FIG. 12, at the date and time dt1 after the user operates the application XX, the user U11 makes a post presumed to have become angry, saying "The application XX is difficult to use and frustrated ...". Therefore, the generation device 100 estimates the emotion of the user U11 at the date and time dt1 as “anger”. For example, the generation device 100 may estimate whether the user's emotions are of various types such as "joy", "anger", "sadness", "enjoyment", and "emotionlessness". The generation device 100 is not limited to the above, and may estimate various types of emotions depending on the purpose and the like. For example, the generation device 100 may estimate anger, sadness, or the like as negative emotions. Further, for example, the generation device 100 may estimate joy, enjoyment, or the like as positive emotions. Further, for example, the generation device 100 may estimate the state in which the user's mind does not move as emotionless.

As described above, in the example of FIG. 12, the generation device 100 estimates the user's emotion based on the information (posted information) posted by the user. The user's emotions may be estimated by appropriately using various conventional techniques. For example, the generation device 100 may estimate the user's emotion by appropriately analyzing the character information posted by the user by using various conventional techniques such as syntactic analysis. For example, a list of keywords for each of various emotions may be stored in the storage unit 120 (see FIG. 3), and the emotions in the list to which the keywords included in the character information posted by the user most correspond may be estimated as the emotions of the user. .. Further, for example, the generation device 100 may estimate the user's emotion by using various input information input by the user such as a query used by the user for the search. The above is an example, and the generation device 100 may estimate the user's emotions by any method as long as it can be estimated.

Then, the generation device 100 generates a model based on the collected information (step S25). In the example of FIG. 12, the generation device 100 uses the user operation log as an input to generate the model M11 for estimating the user's emotions. For example, the generation device 100 generates a model M11 that estimates that the user's emotion is "anger" when the operation information of the user U11 as shown in the user operation log OP11 is input. For example, the generation device 100 generates a model M11 that outputs a score equal to or higher than a predetermined threshold value corresponding to the user's emotion "anger" when the operation information of the user U11 as shown in the user operation log OP11 is input. ..

The generation device 100 generates the model M11 by the same processing as in FIG. 1, as shown in the model list ML11. For example, the generation device 100 stores the generated model M11 in the model information storage unit 124 (see FIG. 1). In this way, the generation device 100 uses the user's operation log as input data and generates the model M11 which is the estimation target “emotion (anger)”. For example, the generation device 100 inputs the user's operation log to the model M11, and causes the model M11 to output a score used for estimating the anger emotion of the user (input user) corresponding to the input operation log. Based on the score output by the model M11, it is estimated whether the input user is feeling angry.

In the example of FIG. 12, only the user U11 is shown, but the generation device 100 collects operation logs, posting information, and the like of a large number of users to generate a model. That is, the generation device 100 generates a model using operation logs, posting information, and the like of a large number of users.

Further, for example, the generation device 100 may generate a model using behavior information including input information input by the user in a service via a network. In this case, the generation device 100 may estimate the user's emotions based on the behavioral information including the input information input by the user in the service via the network. For example, the generation device 100 may generate a model using the posting information posted by the user in the social networking service (SNS) and the location information of the user at the time of posting. For example, the generation device 100 may generate a model using the posted information posted by the user on Twitter (registered trademark), Facebook (registered trademark), or the like. For example, the generation device 100 may generate a model using sentences (character information) posted by the user on Twitter.

For example, the prediction device 100 may generate a model using the input information input by the user in the message service. For example, the prediction device 100 may generate a model using the input information input by the user in a message service such as LINE (registered trademark). For example, the prediction device 100 may generate a model using the input information input in the e-mail.

For example, the generation device 100 may generate a model using behavior information including a user's operation history. In this case, the generation device 100 may estimate the user's emotions based on the behavior information including the user's operation history. For example, the generation device 100 may generate a model using behavior information including an operation history of the user for the terminal device 10. For example, the generation device 100 may generate a model using an operation history including information such as the strength and speed of a tap operation or a swipe operation on the terminal device 10 of the user. For example, the generation device 100 generates a model that estimates that the user has an angry feeling when the strength or speed of the tap operation or swipe operation on the terminal device 10 of the user is equal to or higher than a predetermined threshold value. May be good.

Further, for example, the generation device 100 may generate a model using information about a UI (user interface). In this case, the generation device 100 may estimate the user's emotions based on the information about the UI (behavior information such as the user's operation history). For example, the generator 100 may estimate the user's emotions based on behavioral information including information about the UI (user interface). In this case, for example, the generator 100 provides the user with a plurality of UI screens and the like as in the so-called AB test, and is based on the output of the model when information (user behavior information) related to each UI is input. You may evaluate each UI. For example, in the generation device 100, the output of the model when the information about the first UI (user's behavior information) is input is the model when the information about the second UI (user's behavior information) is input. If the feeling is better than the output (eg, higher score), it may be determined that the first UI has a better rating than the second UI.

Further, for example, the generation device 100 may estimate the user's emotions using various information (features) such as the communication speed (communication environment) in the terminal device 10 used by the user and the area where the user is located. .. Further, for example, the generation device 100 may estimate the user's emotions by using environmental information such as temperature and atmospheric pressure in which the user is placed. Further, for example, the generation device 100 may estimate the emotion of the user by using the image information obtained by capturing the image of the user. Further, for example, the generation device 100 may estimate the user's emotion using the user's biological information. For example, the generation device 100 may estimate the user's emotion using biological information such as the user's heartbeat and blood pressure.

The above is an example, and the generation device 100 may estimate the user's emotions by appropriately using various information.

[2. Generator configuration]
Next, the configuration of the generation device 100 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram showing a configuration example of the generator according to the embodiment. As shown in FIG. 4, the generation device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The generation device 100 has an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from the administrator of the generation 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 N 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. 4, the storage unit 120 according to the embodiment includes an action information storage unit 121, an emotion information storage unit 122, an associative information storage unit 123, and a model information storage unit 124.

(Behavior information storage unit 121)
The behavior information storage unit 121 according to the embodiment stores various information related to the user's behavior. FIG. 5 is a diagram showing an example of the behavior information storage unit according to the embodiment. For example, the behavior information storage unit 121 stores various behavior information such as the behavior of each user. The action information storage unit 121 shown in FIG. 5 includes items such as "user ID" and "behavior information".

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. The "behavior information" indicates the user's behavior information corresponding to the data identified by the data ID. In FIG. 5, an example in which conceptual information such as "ADT1" is stored in "behavior information" is shown, but in reality, various information about the action performed by the user or a file path name indicating the storage location thereof. Etc. are stored.

For example, in the example shown in FIG. 5, it is shown that the action information ADT1 has been collected for the user (user U1) identified by the user ID "U1". For example, the behavior information ADT1 may include the behavior information of the user U1 on the Internet (web). For example, the behavior information ADT1 includes various behaviors of information indicating the behavior (page transition, etc.) of the user U1 in the site of the A service and information indicating that the video content was viewed using the A service at a certain date and time. Information may be included. For example, the behavior information ADT1 includes information indicating that the user U1 has browsed the contents of the C site at a certain date and time, and information indicating that the user U1 has posted predetermined input information such as "A service is convenient" at a certain date and time. Behavioral information on various web sites may be included. Further, for example, the behavior information ADT1 includes various information such as information indicating that the user U1 purchased the B product at the A convenience store on a certain date and time, and information indicating that the user U1 ate and drank at the B restaurant on a certain date and time. Information may be included.

The behavior information storage unit 121 is not limited to the above, and may store various information depending on the purpose. Further, although FIG. 5 shows a case where the action information is stored in the action information storage unit 121 for each user ID, the action information is not limited to each user ID and may be stored, for example, in chronological order.

For example, the action information may include information on items such as "action ID", "date and time", "type", and "content". In this case, for example, the "behavior ID" indicates information that identifies the user's behavior. For example, "date and time" indicates the date and time when the corresponding user's action was performed. For example, a specific date and time such as "August 1, 2017 22:58:42" may be stored in the "date and time". Further, "type" indicates information regarding the type of action of the corresponding user. In addition, "content" indicates the content targeted in the corresponding user's behavior. For example, for user U1, "date and time X" is stored in the date and time in the action log identified by the action ID "AC11", "viewing" is stored in the type, and "video content of service A" is stored in the content. It may be stored.

(Emotion information storage unit 122)
The emotion information storage unit 122 according to the embodiment stores various information related to the user's emotions. FIG. 6 is a diagram showing an example of the emotion information storage unit according to the embodiment. The emotion information storage unit 122 shown in FIG. 6 has items such as "user ID", "questionnaire response", and "corresponding emotion".

The "user ID" indicates identification information for identifying a user. For example, the user identified by the user ID "U3" corresponds to the user U3 shown in the example of FIG. "Questionnaire response" indicates the content answered by the corresponding user. "Corresponding emotion" indicates the emotion of the user. For example, "correspondence emotion" indicates an estimation of the presence or absence of user behavior based on a comparison between a predetermined threshold value and a questionnaire response. In FIG. 6, when the questionnaire response is "6" or less (that is, "0" to "6"), "disgust" is stored in the "correspondence emotion", and the questionnaire responses are "7" and "8". In this case, "neutral" is stored, and when the questionnaire response is "9" or more (that is, "9", "10"), "favorable feeling" is stored.

For example, in the example shown in FIG. 6, the questionnaire response of the user U3 is "3", indicating that the corresponding emotion is "disgust". Further, for example, the questionnaire response of the user U4 is "9", indicating that the corresponding emotion is "favorable". Further, for example, the questionnaire response of the user U5 is "1", indicating that the corresponding emotion is "disgust".

The emotion information storage unit 122 is not limited to the above, and may store various information depending on the purpose.

(Linked information storage unit 123)
The associated information storage unit 123 according to the embodiment stores various associated information. The association information storage unit 123 stores the association information as learning data. FIG. 7 is a diagram showing an example of the linked information storage unit according to the embodiment. For example, the association information storage unit 123 stores the teacher data used for generating the model. The linked information storage unit 123 shown in FIG. 7 includes items such as "data ID", "user ID", "correct answer information (score (emotion))", and "behavior information".

The "data ID" indicates identification information for identifying the data. For example, the "data ID" indicates identification information for identifying a combination of information associated with the user's behavior information and emotion information. For example, the "data ID" indicates identification information for identifying a combination of user behavior information and correct answer information used as learning data (teacher data). The "user ID" indicates identification information for identifying a user. "Correct answer information (score (emotion))" indicates correct answer information corresponding to the data identified by the data ID. For example, "correct answer information (score (emotion))" indicates the emotion of the user corresponding to the data identified by the data ID.

The "behavior information" indicates the user's behavior information corresponding to the data identified by the data ID. In FIG. 7, an example in which conceptual information such as "ADT3" is stored in "behavior information" is shown, but in reality, various information about the behavior performed by the user or a file path name indicating the storage location thereof. Etc. are stored.

For example, in the example shown in FIG. 7, the data (learning data DT1) identified by the data ID "DT1" is information (data) corresponding to the user (user U3) identified by the user ID "U3". Is shown. Further, the learning data DT1 indicates that the correct answer information is "3 (disgust)". That is, the learning data DT1 indicates that the user U3 has an aversion to the A service. Further, it is shown that the learning data DT1 includes the behavior information ADT3.

The linked information storage unit 123 is not limited to the above, and may store various information depending on the purpose. For example, the associated information storage unit 123 may store information regarding the date and time when the learning data was added. For example, when the correct answer information is "Yes (1)", the associated information storage unit 123 may store information indicating the date and time when the user performed the action. Further, for example, the association information storage unit 123 may store information indicating by what kind of determination processing each learning data is added. For example, the associated information storage unit 123 may store information indicating whether or not each learning data is determined by the selection of the administrator.

(Model information storage unit 124)
The model information storage unit 124 according to the embodiment stores information about the model. For example, the model information storage unit 124 stores model information (model data) generated by the determination process. FIG. 8 is a diagram showing an example of a model information storage unit according to the embodiment. The model information storage unit 124 shown in FIG. 8 includes items such as “model ID”, “estimation target”, and “model data”. Although only the model M1 is shown in FIG. 8, a large amount of model information such as M2, M3, M4, M5, etc. may be stored according to each estimation target.

The "model ID" indicates identification information for identifying the model. For example, the model identified by the model ID "M1" corresponds to the model M1 shown in the example of FIG. “Estimation target” indicates the estimation target of the corresponding model. Further, the "model data" indicates the data of the corresponding corresponding model associated with the model data. For example, "model data" includes information including nodes in each layer, functions adopted by each node, connection relationships of nodes, and connection coefficients set for connections between nodes.

For example, in the example shown in FIG. 8, in the model (model M1) identified by the model ID "M1", the estimation target is the user's "emotion", and the information regarding the user's emotion corresponding to the input behavior information is used. Indicates that it is used for estimation. Further, it is shown that the model data of the model M1 is the model data MDT1.

The model M1 (model data MDT1) includes an input layer into which user action information is input, an output layer, and a first element that is any layer from the input layer to the output layer and belongs to a layer other than the output layer. , A second element whose value is calculated based on the first element and the weight of the first element, and each element belonging to each layer other than the output layer with respect to the action information input to the input layer is first. As an element, it is a model for making a computer function so as to output a score value used for estimating a user's emotion from an output layer by performing an operation based on a first element and a weight of the first element.

Here, it is assumed that the model M1 and the like are realized by the regression model represented _{by "y = a 1} * x ₁ + a ₂ * x ₂ + ... + a _i * x _i". In this case, for example, the first element included in the model M1 corresponds to input data (xi) such as x1 and x2. Further, the weight of the first element corresponds to the coefficient ai corresponding to xi. Here, the regression model can be regarded as a simple perceptron having an input layer and an output layer. When each model is regarded as a simple perceptron, the first element corresponds to any node of the input layer, and the second element can be regarded as the node of the output layer.

Further, it is assumed that the model M1 or the like is realized by a neural network or the like having one or a plurality of intermediate layers such as DNN. In this case, for example, the first element included in the model M1 corresponds to either the node of the input layer or the intermediate layer. Further, the second element corresponds to a node in the next stage, which is a node to which a value is transmitted from a node corresponding to the first element. Further, the weight of the first element corresponds to a connection coefficient which is a weight considered for the value transmitted from the node corresponding to the first element to the node corresponding to the second element.

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

(Control unit 130)
Returning to the description of FIG. 4, the control unit 130 is a controller, and is stored in a storage device inside the generation device 100 by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). It is realized by executing various programs (corresponding to an example of a determination program and a generation program) using the RAM as a work area. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 130 is any one of an input layer, an output layer, and an input layer to an output layer into which user action information is input by information processing according to a model M1 or the like stored in the model information storage unit 124. The action input to the input layer, including the first element which is a layer of the above and belongs to a layer other than the output layer, and the second element whose value is calculated based on the weights of the first element and the first element. For the information, each element belonging to each layer other than the output layer is set as the first element, and the value of the score used for estimating the user's emotion is output by performing the calculation based on the weight of the first element and the first element. Output from the layer.

As shown in FIG. 4, the control unit 130 includes an acquisition unit 131, a determination unit 132, a generation unit 133, an estimation unit 134, and a provision unit 135, and functions and operations of information processing described below. To realize or execute. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and may be another configuration as long as it is a configuration for performing information processing described later. The control unit 130 includes a second element whose value is calculated based on the first element and the weight of the first element by information processing according to the model M1 (model data MDT1) stored in the storage unit 120. The user's emotions are calculated based on the weights of the first element and the first element with each element belonging to each layer other than the output layer as the first element for the action information input to the input layer. The score value used for the estimation of is output from the output layer.

(Acquisition unit 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires various information from the behavior information storage unit 121, the emotion information storage unit 122, the associative information storage unit 123, the model information storage unit 124, and the like. Further, the acquisition unit 131 may acquire various information from an external information processing device. Further, the acquisition unit 131 may acquire various information from the terminal device 10 or the like. For example, the acquisition unit 131 acquires the user's action information from the terminal device 10.

The acquisition unit 131 acquires the questionnaire information regarding the questionnaire answered by the user. For example, the acquisition unit 131 acquires a behavior information group including behavior information of a plurality of users. For example, the acquisition unit 131 acquires questionnaire information regarding a questionnaire answered by a user in crowdsourcing.

For example, the acquisition unit 131 acquires questionnaire information regarding the questionnaire answered by the user included in the target list of the questionnaire. For example, the acquisition unit 131 acquires questionnaire information regarding a questionnaire answered by a user whose behavior regarding the subject of the questionnaire satisfies a predetermined condition. For example, the acquisition unit 131 acquires questionnaire information regarding a questionnaire answered by a user whose behavior regarding the target of the questionnaire is a predetermined amount or more.

The acquisition unit 131 acquires the user's behavior information and emotion information regarding the user's emotions. For example, the acquisition unit 131 acquires the user's emotional information based on other behavioral information other than the user's behavioral information. For example, the acquisition unit 131 acquires user behavior information including information regarding the user's operation with respect to the terminal device 10 used by the user.

For example, the acquisition unit 131 acquires the user's emotional information based on the questionnaire information regarding the questionnaire answered by the user. For example, the acquisition unit 131 acquires the user's emotional information based on the questionnaire information regarding the questionnaire answered by the user in crowdsourcing. For example, the acquisition unit 131 acquires questionnaire information regarding a questionnaire answered by a user whose behavior regarding the target of the questionnaire is a predetermined amount or more. For example, the acquisition unit 131 acquires the user's emotional information based on the input information input by the user in the service via the network. For example, the acquisition unit 131 acquires the user's behavior information and the score indicating the user's emotion.

In the example of FIG. 1, the acquisition unit 131 acquires the action information of the user U1 from the terminal device 10-1 used by the user U1. For example, the acquisition unit 131 acquires the action information of the user U1 in the A service from the terminal device 10-1. For example, as shown in FIG. 2, the acquisition unit 131 may acquire user behavior information in a service other than the A service, such as the B service, which is an electronic commerce service. For example, the acquisition unit 131 may acquire the action information of the user U1 in the B service from the terminal device 10-1.

For example, the acquisition unit 131 acquires the behavior information of the user U1 on the Internet (web) from the terminal device 10-1. For example, the acquisition unit 131 acquires various behavioral information on the web, such as information indicating that the user U1 has browsed the web content and information indicating that the user U1 has performed a search using a query. For example, the acquisition unit 131 may acquire the behavior information of the user U1 in the real world. For example, the acquisition unit 131 may acquire various behavioral information such as information indicating that the user U1 has purchased the B product at the A convenience store and information indicating that the user U1 has eaten or drink at the B restaurant.

Further, in the example of FIG. 1, the acquisition unit 131 acquires the action information from the terminal device 10-2 used by the user U2. For example, the acquisition unit 131 acquires the action information of the user U2 in the A service from the terminal device 10-2. For example, as shown in FIG. 2, the acquisition unit 131 acquires the action information of the user U2 in the A service and the B service. Further, for example, the generation device 100 acquires the behavior information of the user U2 on the web or in the real space from the terminal device 10-2.

For example, the acquisition unit 131 acquires action information from the terminal device 10-3 used by the user U3. For example, the acquisition unit 131 acquires the action information of the user U3 in the A service from the terminal device 10-3. For example, the acquisition unit 131 acquires behavioral information indicating that the user U3's A service has been used within a predetermined period (for example, the latest one week, three weeks, etc.). For example, the acquisition unit 131 acquires the behavior information of the user U3 on the Web or in the real space, such as the behavior information of the user U3 in the A service, from the terminal device 10-3.

For example, the acquisition unit 131 acquires action information from the terminal device 10-4 used by the user U4. For example, the acquisition unit 131 acquires the action information of the user U4 in the A service from the terminal device 10-4. For example, the acquisition unit 131 acquires behavioral information indicating that the user U4 has used the A service within a predetermined period (for example, the latest one month or two weeks). For example, the acquisition unit 131 acquires the behavior information of the user U4 on the Web or in the real space, such as the behavior information of the user U4 in the A service, from the terminal device 10-4.

Further, in the example of FIG. 1, the acquisition unit 131 acquires the questionnaire information regarding the questionnaire answered by the user. For example, the acquisition unit 131 acquires questionnaire information from a plurality of workers who perform tasks such as so-called crowdsourcing. For example, the acquisition unit 131 causes the user (worker) to answer the questionnaire regarding the A service by crowdsourcing, and acquires the answer.

For example, as shown in FIG. 2, the acquisition unit 131 crowdsources the user (worker) to the questionnaire AN11 with various contents such as "Do you recommend service A to friends and colleagues? (Answer from 0 to 10)". ) To answer and get the answer.

Further, in the example of FIG. 1, the acquisition unit 131 acquires the answer of the user U3 from the terminal device 10-3 used by the user U3 who is a worker. For example, the acquisition unit 131 acquires an answer from the user U3 that the answer to the questionnaire AN11 is a score of “3”. For example, the acquisition unit 131 acquires the answer of the user U4 from the terminal device 10-4 used by the user U4 who is a worker. For example, the acquisition unit 131 acquires an answer from the user U4 that the answer to the questionnaire AN11 is a score of “9”. For example, the acquisition unit 131 acquires the answer of the user U5 from the terminal device 10-5 used by the user U5 who is a worker. For example, the acquisition unit 131 acquires an answer from the user U5 that the answer to the questionnaire AN11 is a score of “1”.

(Decision unit 132)
The determination unit 132 estimates various types of information. The decision unit 132 makes various decisions based on various information such as the action information storage unit 121, the emotion information storage unit 122, the associative information storage unit 123, and the model information storage unit 124.

When the information about the user satisfies a predetermined condition, the determination unit 132 determines that the user's questionnaire information acquired by the acquisition unit 131 is associated with the user's behavior information. For example, when the behavior information group includes the behavior information of the user, the determination unit 132 determines that the questionnaire information of the user is associated with the behavior information of the user.

For example, the determination unit 132 determines that the user's questionnaire information is associated with the user's behavior information when the user's behavior information includes the behavior information regarding the target of the questionnaire. For example, the determination unit 132 determines that the user's questionnaire information is associated with the user's behavior information when the user is performing an action regarding the target of the questionnaire within a predetermined period.

For example, the determination unit 132 determines that the user's questionnaire information is associated with the user's behavior information when the behavior regarding the target of the user's questionnaire satisfies a predetermined condition. For example, the determination unit 132 determines that the user's questionnaire information is associated with the user's behavior information when the behavior regarding the target of the user's questionnaire is equal to or greater than a predetermined amount.

In the example of FIG. 1, the determination unit 132 determines the target to be associated with the user's behavior information and the user's questionnaire information. For example, the determination unit 132 determines a target to which the questionnaire information of a user who is not a nonconforming user is associated with the questionnaire information of the user. For example, the determination unit 132 determines that the questionnaire information of a user whose behavior information group includes the behavior information among the conforming users is associated with the behavior information of the user.

In the example of FIG. 1, the determination unit 132 determines that the user U3 who is using the A service within a predetermined period of the response user group UG2 is to be linked as a conforming user. For example, the determination unit 132 associates the action of the user U3 with the answer, as shown in FIG. For example, the decision unit 132 associates the questionnaire information of the user U3 with the action information. For example, the determination unit 132 associates the behavior information ADT3 of the user U3 with the score (emotion) included in the questionnaire information and stores it in the association information storage unit 123, as shown in the association information storage unit 123. For example, the determination unit 132 associates the behavior information ADT3 of the user U3 with the score “3” and the emotion “disgust”, and supplies the associated information storage unit 123 as data (data DT1) identified by the data ID “DT1”. Store.

For example, the determination unit 132 determines that the user U4 who is using the A service within a predetermined period of the response user group UG2 is set as the matching user and is to be linked. For example, the determination unit 132 associates the action of the user U4 with the answer, as shown in FIG. For example, the determination unit 132 associates the questionnaire information of the user U4 with the behavior information. For example, the determination unit 132 associates the behavior information ADT4 of the user U4 with the score (emotion) included in the questionnaire information and stores it in the association information storage unit 123, as shown in the association information storage unit 123. For example, the determination unit 132 associates the behavior information ADT4 of the user U4 with the score “9” and the emotion “favorability”, and supplies the associated information storage unit 123 as data (data DT2) identified by the data ID “DT2”. Store.

Further, in the example of FIG. 1, the determination unit 132 determines that the user U5, which is a nonconforming user, among the responding user group UG2 is not to be linked. For example, the determination unit 132 determines that the response of the user U5 is not associated with the action, as shown in FIG. For example, the determination unit 132 determines that the user U18 is a conforming user and is to be linked. For example, the determination unit 132 associates the behavior information ADT18 of the user U18 with the score “7” and the emotion “neutral”, and supplies the associated information storage unit 123 as data (data DT3) identified by the data ID “DT3”. Store.

(Generator 133)
The generation unit 133 generates various information. Further, the generation unit 133 generates various information based on various information such as the behavior information storage unit 121, the emotion information storage unit 122, the association information storage unit 123, and the model information storage unit 124.

For example, the generation unit 133 generates a model for estimating the emotion of the input user to which the behavior information is input by using the user's behavior information and the emotion information about the user's emotion based on the user's questionnaire information. For example, the generation unit 133 generates a model using the behavior information of a user whose score is equal to or higher than a predetermined threshold value as a positive example. For example, the generation unit 133 generates a model using the behavior information of a user whose score is less than a predetermined threshold as a negative example.

Further, the generation unit 133 generates a model for estimating the emotion of the input user to which the behavior information is input, based on the user's behavior information acquired from the acquisition unit 131 and the user's emotion information. In addition, the generation unit 133 generates a model that outputs a score indicating the emotion of the input user to which the behavior information is input, based on the behavior information of the user and the score.

For example, the generation unit 133 generates the model M1 and the like, and stores the generated model M1 and the like in the model information storage unit 124. The generation unit 133 may generate the model M1 or the like by using any learning algorithm. For example, the generation unit 133 generates a model M1 or the like by using a learning algorithm such as a neural network, a support vector machine (SVM), clustering, or reinforcement learning. As an example, when the generation unit 133 uses a neural network to generate a model M1 or the like, the model M1 or the like includes an input layer containing one or more neurons, an intermediate layer containing one or more neurons, and one or more neurons. It has an output layer including.

The generation unit 133 generates a model and stores the generated model in the model information storage unit 124. Specifically, the generation unit 133 is a first element that is any of an input layer into which user action information is input, an output layer, and a layer from the input layer to the output layer, and belongs to a layer other than the output layer. And the second element whose value is calculated based on the first element and the weight of the first element, and each element belonging to each layer other than the output layer with respect to the action information input to the input layer is the first. By performing an operation based on the first element and the weight of the first element as one element, a model for outputting the score value used for estimating the user's emotion from the output layer is generated.

For example, the generation unit 133 generates a model based on the training data. For example, the generation unit 133 generates a model based on the training data. For example, the generation unit 133 generates a model by performing learning using the data DT1 to DT3 in the associated information storage unit 123 as learning data (teacher data).

In the example of FIG. 1, the generation unit 133 generates the model M1 as shown in the model information storage unit 124. For example, the generation unit 133 generates a model based on the training data. For example, the generation unit 133 generates a model by performing learning using the data DT1 to DT3 in the associated information storage unit 123 as learning data (teacher data). For example, the generation unit 133 generates a model using the feature amount related to the user's behavior information. Further, for example, the generation unit 133 generates a model by using the feature amount related to the behavior information of the user on the Web. For example, the generation unit 133 generates a model using the feature amount related to the behavior information of the user in the real space. In this way, the generation unit 133 learns the features included in the user's behavior information and generates a model for estimating the information about the user's emotions. The features included in the action information learned by the generation unit 133 may be input to the generation unit 133 by a person such as an administrator of the generation unit 133, or may be automatically learned (extracted) by the generation unit 133. May be good.

For example, the generation unit 133 generates the model M1 using the data stored in the association information storage unit 123 as learning data (teacher data). For example, as shown in the data DT1, the generation unit 133 indicates that the correct answer information has a score of "3" corresponding to the user's emotion "disgust", and the behavior information included in the data DT1 is input to the model M1. , The learning process is performed so that the score output by the model M1 approaches "3". For example, the generation unit 133 performs learning processing so that when the behavior information ADT3 of the data DT1 is input to the model M1, the score output by the model M1 approaches "3".

Further, for example, when the correct answer information has a score of "9" corresponding to the user's emotion "favorability" as shown in the data DT2, the generation unit 133 has input the action information included in the data DT2 into the model M1. In this case, the learning process is performed so that the score output by the model M1 approaches "9". For example, the generation unit 133 performs learning processing so that when the behavior information ADT4 of the data DT2 is input to the model M1, the score output by the model M1 approaches "9".

Further, for example, when the correct answer information has a score of "7" corresponding to the user's emotion "neutral" as shown in the data DT3, the generation unit 133 has input the action information included in the data DT3 into the model M1. In this case, the learning process is performed so that the score output by the model M1 approaches "7". For example, the generation unit 133 performs a learning process so that when the behavior information ADT18 of the data DT3 is input to the model M1, the score output by the model M1 approaches "7".

Further, for example, the generation unit 133 uses the learning data stored in the associated information storage unit 123 to generate a model as shown in the model information storage unit 124. For example, the generation unit 133 generates a model used for estimating the emotion of each user based on the learning data acquired by the acquisition unit 131. For example, the generation unit 133 generates a model used for estimating the emotion of each user based on the learning data including the behavior information and the correct answer information indicating the emotion information regarding the emotion of each user corresponding to the behavior information.

(Estimating unit 134)
The estimation unit 134 estimates various types of information. The estimation unit 134 estimates various information using the model stored in the model information storage unit 124. For example, the estimation unit 134 estimates various information based on various information acquired by the acquisition unit 131. The estimation unit 134 estimates information about the user's emotions by inputting the user's behavior information into the model.

For example, the estimation unit 134 inputs the user's behavior information into the model M1, causes the model M1 to output a score regarding the user's emotion corresponding to the input behavior information, and based on the score output by the model M1. Estimate what the user is feeling.

For example, the estimation unit 134 calculates the score using a model having an arbitrary structure such as the regression model and the neural network described above. Specifically, the model M1 is a value that quantifies the estimation of the user's emotion (that is, how the user is) when the user's behavior information (that is, each element used for calculating the score described above) is input. The coefficient is set to output a score that suggests such feelings. The estimation unit 134 uses such a model M1 to calculate a score regarding the probability of an action by the user regarding a predetermined target.

In the above example, the model M1 is a model that outputs a quantified value of the estimation of the probability of the behavior of a predetermined target by the user when the behavior information of the user is input. However, the model (model X) according to the embodiment may be a model generated based on the result obtained by repeating the input / output of data to the model M1. For example, the model X may be a model (model Y) trained to input the user's behavior information and output the score output by the model M1. Alternatively, the model M1 may be a model trained to input the user's behavior information and output the output value of the model Y. Further, when the estimation unit 134 performs estimation processing using GAN (Generative Adversarial Networks), the model M1 may be a model forming a part of GAN.

(Providing section 135)
The providing unit 135 provides various types of information. For example, the providing unit 135 provides various information to the terminal device 10. The providing unit 135 may provide a service based on the estimation information estimated by the estimation unit 134. For example, the providing unit 135 may provide information about the model generated by the generating unit 133 to an external information processing device. Further, for example, the providing unit 135 may provide the information output by the model to an external information processing device. For example, the providing unit 135 provides the mapping information generated by the generating unit 133 to an external information processing device.

For example, the providing unit 135 provides information by using the user's behavior information and the user's emotional information based on the user's questionnaire information. For example, the providing unit 135 provides information on the emotion of the input user estimated using the model generated by the generating unit 133.

[3. Decision processing flow]
Next, the procedure of the determination process by the generation system 1 according to the embodiment will be described with reference to FIG. FIG. 9 is a flowchart showing an example of the determination process according to the embodiment.

As shown in FIG. 9, the generation device 100 acquires the action information (step S101). For example, the generation device 100 acquires the behavior information ADT1 to ADT5 of the users U1 to U5 from the behavior information storage unit 121.

Further, the generation device 100 acquires the questionnaire information (step S102). In the example of FIG. 1, the generation device 100 acquires questionnaire information and the like of users U3 to U5 from the emotion information storage unit 122.

Then, the generation device 100 determines that the behavior information of the user satisfying the predetermined condition and the questionnaire information are associated with each other (step S103). In the example of FIG. 1, the generation device 100 determines that the behavior information of the user U3, the user U4, etc. is associated with the questionnaire information.

[4. Generation process flow]
Next, the procedure of the generation process by the generation system 1 according to the embodiment will be described with reference to FIG. FIG. 10 is a flowchart showing an example of the generation process according to the embodiment.

As shown in FIG. 10, the generation device 100 acquires the user's behavior information and emotion information (step S201). For example, the generation device 100 acquires learning data in which the user's behavior information and emotion information are associated with each other from the association information storage unit 123.

After that, the generation device 100 generates a model for estimating the user's emotion based on the user's behavior information and emotion information (step S202). In the example of FIG. 1, the generation device 100 generates a model M1 for estimating the user's emotion by using the learning data in which the user's behavior information and the emotion information are associated with each other as shown in the associated information storage unit 123.

[5. Estimate processing]
An example of the estimation process according to the embodiment will be described with reference to FIG. FIG. 11 is a diagram showing an example of the estimation process according to the embodiment. FIG. 11 shows a case where the generation device 100 provides information on the user's emotions estimated based on the emotion information when the user's behavior information is acquired.

First, the generation device 100 acquires the behavior information of the user U101 who is the target user (step S21). In the example of FIG. 11, the generation device 100 acquires the action information ADT 101 of the user U 101 from the terminal device 10 used by the user U 101. The generation device 100 may acquire the action information ADT 101 of the user U101 from the service providing device 50 or another external device.

The generation device 100 that generated the action information ADT 101 inputs the action information ADT 101 into the model. For example, the generation device 100 inputs the action information ADT 101 into the model M1.

In the example of FIG. 11, the generation device 100 calculates a score indicating the emotion of the user U101 by the processing as shown in the processing group PS21. The generation device 100 inputs the action information ADT 101 into the model M1 (step S22). The model M1 to which the action information ADT101 is input outputs a score (step S23). The model M1 outputs the score corresponding to each class. In the example of FIG. 11, the model M1 to which the action information ADT101 is input outputs the score “9.5” as shown in the score SC11. As a result, the generation device 100 estimates that the emotion of the user U101 is "favorable" using the model M1.

Then, the generation device 100 generates an estimation result (step S24). In the example of FIG. 11, the generation device 100 generates the estimation result information ER21 that the emotion of the user U101, which is the target user, is “favorable”.

After that, the generation device 100 provides information based on the estimation result (step S25). In the example of FIG. 11, the generation device 100 provides the generated estimation result information ER21 to the service providing device 50.

Then, the service providing device 50 that has received the information provided from the generating device 100 provides the A service to the terminal device 10 used by the user U101 based on the information acquired from the generating device 100 (step S26).

[6. effect〕
As described above, the generation device 100 according to the embodiment has an acquisition unit 131 and a generation unit 133. The acquisition unit 131 acquires the user's behavior information and emotion information regarding the user's emotions. Further, the generation unit 133 generates a model for estimating the emotion of the input user to which the behavior information is input, based on the user's behavior information acquired from the acquisition unit 131 and the user's emotion information.

As described above, the generation device 100 according to the embodiment generates a model for estimating the emotion of the input user to which the behavior information is input based on the behavior information of the user and the emotion information of the user. Emotions can be properly estimated.

Further, in the generation device 100 according to the embodiment, the acquisition unit 131 acquires the user's emotional information based on other behavioral information other than the user's behavioral information.

As described above, the generation device 100 according to the embodiment can appropriately estimate the user's emotion by acquiring the user's emotion information based on the behavior information other than the user's behavior information.

Further, in the generation device 100 according to the embodiment, the acquisition unit 131 acquires the user's emotional information based on the questionnaire information regarding the questionnaire answered by the user.

As described above, the generation device 100 according to the embodiment can appropriately estimate the user's emotion by acquiring the user's emotion information based on the questionnaire information regarding the questionnaire answered by the user.

Further, in the generation device 100 according to the embodiment, the acquisition unit 131 acquires the user's emotional information based on the questionnaire information regarding the questionnaire answered by the user in crowdsourcing.

As described above, the generation device 100 according to the embodiment can appropriately estimate the user's emotion by acquiring the user's emotion information based on the questionnaire information regarding the questionnaire answered by the user in crowdsourcing.

Further, in the generation device 100 according to the embodiment, the acquisition unit 131 acquires the questionnaire information regarding the questionnaire answered by the user whose behavior regarding the target of the questionnaire is a predetermined amount or more.

As described above, the generation device 100 according to the embodiment can appropriately estimate the user's emotion by acquiring the questionnaire information regarding the questionnaire answered by the user whose behavior regarding the subject of the questionnaire is a predetermined amount or more. it can.

Further, in the generation device 100 according to the embodiment, the acquisition unit 131 acquires the user's action information including the information regarding the user's operation with respect to the terminal device 10 used by the user.

As described above, the generation device 100 according to the embodiment can appropriately estimate the user's emotion by acquiring the user's behavior information including the information regarding the user's operation with respect to the terminal device 10 used by the user. it can.

Further, in the generation device 100 according to the embodiment, the acquisition unit 131 acquires the user's emotion information based on the input information input by the user in the service via the network.

As described above, the generation device 100 according to the embodiment can appropriately estimate the user's emotion by acquiring the user's emotion information based on the input information input by the user in the service via the network. ..

Further, in the generation device 100 according to the embodiment, the acquisition unit 131 acquires the user's behavior information and the score indicating the user's emotion. In addition, the generation unit 133 generates a model that outputs a score indicating the emotion of the input user to which the behavior information is input, based on the behavior information of the user and the score.

In this way, the generation device 100 according to the embodiment generates a model that outputs a score indicating the emotion of the input user to which the behavior information is input based on the behavior information of the user and the score. Emotions can be properly estimated.

Further, in the generation device 100 according to the embodiment, the generation unit 133 generates a model using the behavior information of the user whose score is equal to or higher than a predetermined threshold value as a positive example.

As described above, the generation device 100 according to the embodiment can appropriately estimate the user's emotion by generating a model using the behavior information of the user whose score is equal to or higher than a predetermined threshold value as a positive example.

Further, in the generation device 100 according to the embodiment, the generation unit 133 generates a model using the behavior information of the user whose score is less than a predetermined threshold as a negative example.

As described above, the generation device 100 according to the embodiment can appropriately estimate the user's emotion by generating a model using the behavior information of the user whose score is less than a predetermined threshold as a negative example.

Further, in the generation device 100 according to the embodiment, the providing unit 135 provides information on the emotion of the input user estimated by using the model generated by the generating unit 133.

As described above, the generation device 100 according to the embodiment can appropriately estimate the user's emotion by providing the information regarding the input user's emotion estimated by using the model.

[7. Hardware configuration]
The generation device 100 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 13 is a hardware configuration diagram showing an example of a computer that realizes the function of the generator. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) Has 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 an 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 generator 100 according to the embodiment, the CPU 1100 of the computer 1000 is controlled by executing a program or data (for example, model M1 (model data MDT1)) loaded on the RAM 1200. The function of the unit 130 is realized. The CPU 1100 of the computer 1000 reads and executes these programs or data (for example, model M1 (model data MDT1)) from the recording medium 1800, but as another example, these programs from another device via the network N. May be obtained.

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.

[8. 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 the processes 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 distributed / physically in arbitrary units 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 Generation system 100 Generation device 121 Behavior information storage unit 122 Emotion information storage unit 123 Linked information storage unit 124 Model information storage unit 130 Control unit 131 Acquisition unit 132 Decision unit 133 Generation unit 134 Estimation unit 135 Providing unit 10 Terminal device 50 Service provision Equipment N network

Claims (18)

An acquisition unit that acquires user behavior information and emotion information related to the user's emotions,
A generation unit that generates a model for estimating the emotion of the input user to which the behavior information is input based on the behavior information of the user acquired by the acquisition unit and the emotion information of the user.
Equipped with a,
The acquisition unit
Generating apparatus characterized that you get the behavior information of the user including information about the operation of the user for the terminal device the user uses. An acquisition unit that acquires user behavior information and emotion information related to the user's emotions,
A generation unit that generates a model for estimating the emotion of the input user to which the behavior information is input based on the behavior information of the user acquired by the acquisition unit and the emotion information of the user.
With
The acquisition unit
A generation device characterized by acquiring emotional information of the user based on input information input by the user in a service via a network. An acquisition unit that acquires user behavior information and emotion information related to the user's emotions,
A generation unit that generates a model for estimating the emotion of the input user to which the behavior information is input based on the behavior information of the user acquired by the acquisition unit and the emotion information of the user.
With
The acquisition unit
The behavior information of the user and the score indicating the emotion of the user are acquired, and the result is obtained.
The generator
A generation device for generating a model that outputs a score indicating the emotion of the input user to which the behavior information is input based on the behavior information of the user and the score. An acquisition unit that acquires user behavior information and emotion information related to the user's emotions,
A generation unit that generates a model for estimating the emotion of the input user to which the behavior information is input based on the behavior information of the user acquired by the acquisition unit and the emotion information of the user.
A providing unit that provides information on the emotion of the input user estimated using the model generated by the generating unit, and a providing unit.
A generator characterized by comprising. The generator
The generator according to claim 3 , wherein the model is generated using the behavior information of the user whose score is equal to or higher than a predetermined threshold value as a positive example. The generator
The generator according to claim 3 or 5 , wherein the model is generated using the behavior information of the user whose score is less than a predetermined threshold value as a negative example. The acquisition unit
Acquires the user's emotional information based on other behavioral information other than the user's behavioral information.
The generator according to any one of claims 1 to 6, wherein the generator is characterized by the above. The acquisition unit
Acquire emotional information of the user based on the questionnaire information regarding the questionnaire answered by the user.
The generator according to any one of claims 1 to 7, wherein the generator is characterized by the above. The acquisition unit
Acquire emotional information of the user based on the questionnaire information regarding the questionnaire answered by the user in crowdsourcing.
The generator according to any one of claims 1 to 8 , wherein the generator is characterized by the above. The acquisition unit
Acquire questionnaire information about the questionnaire answered by the user whose behavior regarding the subject of the questionnaire is equal to or more than a predetermined amount.
The generator according to any one of claims 1 to 9 , wherein the generator is characterized by the above. It ’s a computer-executed generation method.
An acquisition process for acquiring user behavior information and emotion information related to the user's emotions,
A generation step of generating a model for estimating the emotion of the input user to which the behavior information is input based on the behavior information of the user acquired by the acquisition step and the emotion information of the user.
Only including,
The acquisition process is
A generation method comprising acquiring behavioral information of the user including information on the operation of the user with respect to the terminal device used by the user. An acquisition procedure for acquiring user behavior information and emotion information related to the user's emotions, and
A generation procedure for generating a model for estimating the emotion of an input user to which the behavior information is input based on the behavior information of the user acquired by the acquisition procedure and the emotion information of the user.
Let the computer run
The acquisition procedure is
Generator characterized that you get the behavior information of the user including information about the operation of the user for the terminal device the user uses. It ’s a computer-run generation method.
An acquisition process for acquiring user behavior information and emotion information related to the user's emotions,
A generation step of generating a model for estimating the emotion of the input user to which the behavior information is input based on the behavior information of the user acquired by the acquisition step and the emotion information of the user.
Including
The acquisition process is
A generation method comprising acquiring emotional information of the user based on input information input by the user in a service via a network. An acquisition procedure for acquiring user behavior information and emotion information related to the user's emotions, and
A generation procedure for generating a model for estimating the emotion of an input user to which the behavior information is input based on the behavior information of the user acquired by the acquisition procedure and the emotion information of the user.
Let the computer run
The acquisition procedure is
A generation program characterized by acquiring emotional information of the user based on input information input by the user in a service via a network. It ’s a computer-run generation method.
An acquisition process for acquiring user behavior information and emotion information related to the user's emotions,
A generation step of generating a model for estimating the emotion of the input user to which the behavior information is input based on the behavior information of the user acquired by the acquisition step and the emotion information of the user.
Including
The acquisition process is
The behavior information of the user and the score indicating the emotion of the user are acquired, and the result is obtained.
The production step is
A generation method characterized by generating a model that outputs a score indicating the emotion of the input user to which the behavior information is input based on the behavior information of the user and the score. An acquisition procedure for acquiring user behavior information and emotion information related to the user's emotions, and
A generation procedure for generating a model for estimating the emotion of an input user to which the behavior information is input based on the behavior information of the user acquired by the acquisition procedure and the emotion information of the user.
Let the computer run
The acquisition procedure is
The behavior information of the user and the score indicating the emotion of the user are acquired, and the result is obtained.
The generation procedure is
A generation program characterized by generating a model that outputs a score indicating the emotion of the input user to which the behavior information is input based on the behavior information of the user and the score. It ’s a computer-run generation method.
An acquisition process for acquiring user behavior information and emotion information related to the user's emotions,
A generation step of generating a model for estimating the emotion of the input user to which the behavior information is input based on the behavior information of the user acquired by the acquisition step and the emotion information of the user.
A providing step of providing information on the emotion of the input user estimated using the model generated by the generation step, and a providing step.
A generation method characterized by including. An acquisition procedure for acquiring user behavior information and emotion information related to the user's emotions, and
A generation procedure for generating a model for estimating the emotion of an input user to which the behavior information is input based on the behavior information of the user acquired by the acquisition procedure and the emotion information of the user.
A provision procedure for providing information on the emotion of the input user estimated using the model generated by the generation procedure, and a provision procedure.
A generator characterized by having a computer execute.

Images