Information processing device, information processing method, and information processing program

Abstract

To provide an information processing device capable of accurately predicting user reactions to a content, an information processing method, and an information processing program.SOLUTION: An information processing device comprises: an acquisition unit which acquires an utterance content from a target user to a dialogue bot; an extraction unit which identifies extraction conditions of a user group from the acquired utterance content and extracts a user group having user attributes satisfying the identified extraction conditions; and a generation unit which generates a model trained using reactions to a past content of the extracted user group as training data and predicting reactions to a content of the user attributes corresponding to the user group.SELECTED DRAWING: Figure 3

Description

[Technical field]

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

[0002] Conventionally, there are known techniques for placing advertisements on the Internet. Among these techniques, there is a technique for proposing improvement plans for advertisements based on the operating status of the advertisements (conversion rate and fluctuations in the advertisement budget). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-42597 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, it is difficult to predict the operating status of advertisements for users with various attributes, that is, to predict how users will respond to advertisements. This problem is not limited to advertisements, but is also true when predicting whether or not a user will watch video content.

[0005] The present application has been made in consideration of the above, and has an object to provide an information processing device, an information processing method, and an information processing program that are capable of predicting a user's reaction to content with high accuracy. [Means for solving the problem]

[0006] The information processing device of the present application includes an acquisition unit that acquires the speech content of a target user to a conversational bot, an extraction unit that identifies extraction conditions for a user group from the acquired speech content and extracts a user group with user attributes that satisfy the identified extraction conditions, and a generation unit that generates a model that learns the reactions of the extracted user group to past content as learning data and predicts the reaction of the user attributes corresponding to the user group to content. Effect of the Invention

[0007] According to one aspect of the embodiment, it is possible to provide an effect that a user's reaction to content can be predicted with high accuracy. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing a process executed by an information processing device according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of user information. [Diagram 5] FIG. 5 is a diagram illustrating an example of advertiser information. [Figure 6] FIG. 6 is a diagram illustrating an example of model information. [Figure 7] FIG. 7 is a flowchart showing the processing procedure executed by the information processing device according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a hardware configuration. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments. In addition, the same parts in the following embodiments are given the same reference numerals, and duplicated descriptions are omitted.

[0010] (Embodiment) First, a process executed by an information processing device according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing a process executed by an information processing device according to an embodiment. Fig. 1 shows an operation example of an information processing system S including an information processing device 1 according to an embodiment.

[0011] As shown in FIG. 1, an information processing system S according to the embodiment includes an information processing device 1 and an advertiser terminal 50.

[0012] As shown in Figure 1, the information processing system S of the embodiment acquires the speech content of a target user in response to a dialogue bot, identifies extraction conditions for a user group from the acquired speech content, extracts a user group with user attributes that satisfy the identified extraction conditions, and generates a model that learns the reactions of the extracted user group to past content as learning data and predicts the reaction of the user attributes corresponding to the user group to content.

[0013] Specifically, first, the information processing device 1 has a conversation with a target user, who is an advertiser, via a conversation bot, and acquires the contents of the target user's speech at that time (step S1). The conversation here is not just a daily conversation, but a conversation for identifying the user attributes of a user who is a target of an advertisement delivered by an advertiser. In other words, the conversation bot is a conversational AI that extracts and provides a user group that satisfies a condition specified by a speech from the target user. For this reason, the contents of the speech of the target user are contents related to user attributes and information about the user group to be targeted. For example, the contents of the speech related to the content related to the user attributes are questions that specify the user attributes and ask about a user group that satisfies the user attributes, such as "Can you tell me a user group that is men in their 30s living in Tokyo and has golf as a hobby?". Also, the contents of the speech related to the information about the user group to be targeted are questions that specify the number of user groups to be targeted (information about the user group), such as "Can you tell me a user group with a user attribute with a user number of about 1,000 people, based on men in their 30s living in Tokyo?"

[0014] Next, the information processing device 1 specifies extraction conditions for a user group from the acquired speech content (step S2). Specifically, the information processing device 1 extracts user attributes and information on a user group to be targeted from the speech content, and specifies the contents of the extracted user attributes and the contents of the information on the user group as extraction conditions.

[0015] Next, the information processing device 1 extracts a user group having a user attribute that satisfies the specified extraction condition from the user information (step S3). For example, when the extraction condition is only a user attribute, the information processing device 1 extracts a user group that satisfies the user attribute. Also, when the extraction condition includes a user attribute and the number of users of the user group (information on the user group), the information processing device 1 extracts a user group that satisfies the user attribute and the number of users of the user group. For example, when the extraction conditions are "living in Tokyo", "in their 30s", "male", and "1000 users", the information processing device 1 identifies a user attribute that is "1000 users" among the user groups "living in Tokyo", "in their 30s", and "male". For example, when the user groups "living in Tokyo", "in their 30s", "male", and "like shogi" are 1000 people (the difference from 1000 is allowed to be less than a threshold), the information processing device 1 extracts the user groups "living in Tokyo", "in their 30s", "male", and "like shogi" as the user groups having the user attribute that satisfies the extraction condition. The information processing device 1 is not limited to extracting a user group with one user attribute of "shogi lover", but may extract a user group with multiple user attributes, such as "shogi lover" and "has traveled to Okinawa". Furthermore, when there are multiple patterns of user attributes that satisfy the user group of 1000 people, the information processing device 1 may extract the multiple patterns of user attributes as the extraction result.

[0016] Next, the information processing device 1 generates a model predicting a response to the content by using the response of each user in the extracted user group to the past content as learning data (step S4). Specifically, the information processing device 1 generates a model by learning feature information of the past content, such as the type of the past content, the content content, the characters, the advertised product, etc., as explanatory variables, and the presence or absence of a response to the past content as a target variable. The types of content are advertisements (content distributed by companies), entertainment (content distributed by individuals), email, etc. The content details are the form of advertisement (video, still image), the position of the advertisement, the distributor of the entertainment content, the video duration of the entertainment content, the composition of the entertainment content (product review video, video showing a scene of playing), the text of the email, etc. The characters are people who appear in the content, and are actual people or pseudo people generated such as anime characters. The advertised product is the name and type of the product (food, sporting goods, camping goods, etc.), the description of the product, the price of the product, etc. The reactions to the past content include viewing of advertisement content, purchasing of the advertised product, watching of entertainment content, posting of comments, subscribing to a channel, opening of an email, etc. When multiple patterns of user attributes are extracted, the information processing device 1 generates a model for each pattern.

[0017] Next, the information processing device 1 notifies the target user that the model generation of the user attribute specified by the utterance content has been completed, and accepts the content for which the user's reaction is to be predicted (step S5). When accepting the content, the information processing device 1 may further accept feature information (type of content, content details, characters, advertised product, etc.) that is to be an explanatory variable of the model.

[0018] Next, the information processing device 1 inputs the received content into a model and predicts the reaction of the user of the user attribute to the content (step S6). Specifically, the information processing device 1 extracts feature information of the content and predicts the reaction to the content by inputting the extracted feature information into the model. Note that, when the information processing device 1 generates a model for each pattern based on a plurality of patterns of user attributes, it predicts the reaction to the content for each pattern of user attributes.

[0019] Next, the information processing device 1 provides the prediction result to the advertiser, which is the target user (step S7). When the information processing device 1 predicts the response to the content for each pattern of user attributes, it provides the prediction result for each pattern to the target user. The information processing device 1 may also provide only the prediction result for the user attribute that has the best prediction result (the highest response rate or number of users).

[0020] In this way, according to the information processing device 1 of the embodiment, by extracting a group of users with user attributes that satisfy extraction conditions specified from the content of the conversation with the target user and generating a model that predicts the user's reaction to the content, it is possible to predict the user's reaction to the content with high accuracy.

[0021] When extracting a user group in step S3, the information processing device 1 may provide the number of users in the user group to the target user via the dialogue bot. In this case, if the target user utters an utterance that further specifies a user attribute in the dialogue with the dialogue bot, the information processing device 1 may add the user attribute to the extraction conditions to update them, and re-extract the user group using the updated extraction conditions.

[0022] Next, a configuration example of an information processing system S according to an embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing a configuration example of an information processing system S according to an embodiment. As shown in Fig. 2, in the information processing system S according to the embodiment, an information processing device 1, a plurality of advertiser terminals 50, and a plurality of user terminals 100 are connected to a network N by wire or wirelessly. The network N is, for example, a network such as the Internet, a Wide Area Network (WAN), or a Local Area Network (LAN).

[0023] The information processing device 1 is a server device that executes an information processing method according to an embodiment. The information processing device 1 acquires the contents of utterances of a target user to a conversation bot, identifies extraction conditions for a user group from the acquired contents of utterances, extracts a user group having user attributes that satisfy the identified extraction conditions, and generates a model that learns responses of the extracted user group to past content as learning data and predicts responses of the user attributes corresponding to the user group to content.

[0024] In addition, the information processing device 1 is an information processing device that cooperates with multiple advertiser terminals 50 and multiple user terminals 100 and provides API (Application Programming Interface) services for various applications (hereinafter, apps) and the like, as well as various data, to the multiple advertiser terminals 50 and the multiple user terminals 100, and is realized by a server device, a cloud system, etc.

[0025] The information processing device 1 may also be an information processing device that provides some kind of Web service online to a plurality of advertiser terminals 50 and a plurality of user terminals 100. For example, the information processing device 1 may provide services such as Internet connection, search service, SNS (Social Networking Service), electronic commerce (EC), electronic payment, online games, online banking, online trading, hotel and ticket reservations, video and music distribution, news, maps, route search, route guidance, line information, operation information, and weather forecasts as Web services. In practice, the information processing device 1 may cooperate with various servers that provide the above-mentioned Web services, and may mediate the Web services or be responsible for processing the Web services.

[0026] The advertiser terminal 50 is a terminal device owned by an advertiser (= target user) who requests advertisement distribution. The advertiser terminal 50 can be any type of terminal device such as a smartphone, a desktop PC, a notebook PC, or a tablet PC. The advertiser terminal 50 transmits various information to the information processing device 1, etc., and receives information provided by the information processing device 1, etc.

[0027] The user terminal 100 is a terminal device owned by a user (≠ target user) to whom an advertisement is to be distributed. The user terminal 100 may be any type of terminal device, such as a smartphone, a desktop PC, a notebook PC, or a tablet PC. The user terminal 100 transmits various types of information to the information processing device 1 or the like, and receives information provided by the information processing device 1 or the like.

[0028] Next, a configuration example of the information processing device 1 will be described with reference to FIG.

[0029] Fig. 3 is a diagram showing a configuration example of an information processing device 1 according to an embodiment. As shown in Fig. 3, the information processing device 1 has a communication unit 2, a control unit 3, and a storage unit 4. The control unit 3 includes an acquisition unit 31, an identification unit 32, an extraction unit 33, a generation unit 34, a reception unit 35, a prediction unit 36, and a provision unit 37. The storage unit 4 stores user information 41, advertiser information 42, and model information 43.

[0030] The communication unit 2 is realized by, for example, a network interface card (NIC) etc. The communication unit 2 is connected to a network by wire or wirelessly.

[0031] The control unit 3 is a controller, and is realized by, for example, a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM or the like as a working area. The control unit 3 is also a controller, and may be realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPGPU (General Purpose Graphic Processing Unit).

[0032] The storage unit 4 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0033] The user information 41 is information relating to a user.

[0034] Fig. 4 is a diagram showing an example of the user information 41. As shown in Fig. 4, the user information 41 includes items such as "user ID", "attribute information", and "behavior information".

[0035] "User ID" is identification information that identifies a user. "Attribute information" is information about the attributes of a user. Attribute information includes, for example, psychographic attributes and demographic attributes. "Behavioral information" is information about the user's behavior history, and includes behavior related to reactions to content (past content).

[0036] The advertiser information 42 is information relating to the advertiser.

[0037] Fig. 5 is a diagram showing an example of the advertiser information 42. As shown in Fig. 5, the advertiser information 42 includes items such as "advertiser ID", "advertiser information", and "distribution content".

[0038] "Advertiser ID" is identification information that identifies the advertiser. "Advertiser information" is information about the advertiser, such as the advertiser's business and the products they sell (the products that are the subject of advertising). "Distribution content" is information about the advertising content (the subject of input to the model) submitted by the advertiser, and includes feature information, etc.

[0039] The model information 43 is information about a model that predicts a user's reaction to content. Fig. 6 is a diagram showing an example of the model information 43. As shown in Fig. 6, the model information 43 includes items such as "model ID", "model information", and "user attributes".

[0040] "Model ID" is identification information for identifying the model. "Model information" is information about the model, such as model parameters (weighting coefficients, etc.). "User attributes" is information indicating the user attributes of a group of users whose responses are predicted by the model.

[0041] Next, each function of the control unit 3 of the information processing device 1 (the acquisition unit 31, the identification unit 32, the extraction unit 33, the generation unit 34, the reception unit 35, the prediction unit 36, and the provision unit 37) will be described.

[0042] The acquisition unit 31 has a conversation with the target user, who is the advertiser, via the conversation bot, and acquires the contents of the target user's speech at that time. The conversation here is not just a daily conversation, but a conversation for identifying the user attributes of the user who is the target of the advertisement delivered by the advertiser. In other words, the conversation bot is a conversational AI that extracts and provides a user group that satisfies a condition specified by the speech from the target user. For this reason, the contents of the speech of the target user are contents related to the user attributes and information about the user group to be targeted. For example, the contents of the speech related to the content related to the user attributes are questions that specify the user attributes and ask about the user group that satisfies the user attributes, such as "Can you tell me a user group that is men in their 30s living in Tokyo and has golf as a hobby?". In addition, the contents of the speech related to the information about the user group to be targeted are questions that specify the number of user groups to be targeted (information about the user group) and ask about the user group that satisfies the number of the user groups, such as "Can you tell me a user group with a user attribute that is based on men in their 30s living in Tokyo and has about 1,000 users?".

[0043] The identification unit 32 identifies extraction conditions for a user group from the acquired utterance content. Specifically, the identification unit 32 extracts user attributes and information on a user group to be targeted from the utterance content, and identifies the contents of the extracted user attributes and the contents of the information on the user group as extraction conditions.

[0044] The extraction unit 33 extracts a user group having a user attribute that satisfies the specified extraction condition from the user information. For example, when the extraction condition is only a user attribute, the extraction unit 33 extracts a user group that satisfies the user attribute. In addition, when the extraction condition includes a user attribute and the number of users of the user group (information on the user group), the extraction unit 33 extracts a user group that satisfies the user attribute and the number of users of the user group. For example, when the extraction conditions are "living in Tokyo", "in their 30s", "male", and "1000 users", the extraction unit 33 specifies a user attribute that has "1000 users" among the user groups "living in Tokyo", "in their 30s", and "male". For example, when the user groups "living in Tokyo", "in their 30s", "male", and "like shogi" have 1000 users (a difference from 1000 is allowed to be less than a threshold), the extraction unit 33 extracts the user groups "living in Tokyo", "in their 30s", "male", and "like shogi" as the user groups having the user attribute that satisfies the extraction condition. The extraction unit 33 is not limited to extracting a user group with one user attribute of "shogi lover", but may extract a user group with multiple user attributes, such as "shogi lover" and "experience traveling to Okinawa". In addition, when there are multiple patterns of user attributes that satisfy the user group of 1000 people, the extraction unit 33 may extract the multiple patterns of user attributes as the extraction result.

[0045] The generation unit 34 generates a model predicting a response to the content using the response of each user in the extracted user group to the past content as learning data. Specifically, the generation unit 34 generates a model by learning feature information of the past content, such as the type of the past content, the content content, the characters, the advertised product, etc., as explanatory variables, and the presence or absence of a response to the past content as a target variable. The types of content are advertisements (content distributed by companies), entertainment (content distributed by individuals), email, etc. The content details are the form of the advertisement (video, still image), the position of the advertisement, the distributor of the entertainment content, the video time of the entertainment content, the composition of the entertainment content (product review video, video showing a playing scene), the text of the email, etc. The characters are people who appear in the content, and are actual people or pseudo people generated such as anime characters. The advertised product is the name and type of the product (food, sporting goods, camping goods, etc.), the description of the product, the price of the product, etc. The responses to the past content are viewing the advertisement content, purchasing the advertised product, watching the entertainment content, posting a comment, subscribing to a channel, opening an email, etc. When multiple patterns of user attributes are extracted, the generation unit 34 generates a model for each pattern.

[0046] The reception unit 35 notifies the target user that the model generation of the user attribute specified by the utterance content has been completed, and receives the content for which the user's reaction is to be predicted. When receiving the content, the reception unit 35 may further receive feature information (type of content, content details, characters, advertised product, etc.) that is to be an explanatory variable of the model.

[0047] The prediction unit 36 ​​inputs the received content into a model and predicts the reaction of the user of the user attribute to the content. Specifically, the prediction unit 36 ​​extracts feature information of the content and predicts the reaction to the content by inputting the extracted feature information into the model. Note that, when the prediction unit 36 ​​generates a model for each pattern based on a plurality of patterns of user attributes, it predicts the reaction to the content for each pattern of the user attributes.

[0048] The providing unit 37 provides the prediction result to the advertiser, which is the target user. When the providing unit 37 predicts the reaction to the content for each pattern of the user attributes, the providing unit 37 provides the prediction result for each pattern to the target user. The providing unit 37 may provide only the prediction result for the user attribute with the best prediction result (the highest reaction rate or the highest number of users).

[0049] When the extraction unit 33 extracts a user group, the provision unit 37 may provide the number of users in the user group to the target user via the dialogue bot. At this time, when the target user utters an utterance that further specifies a user attribute in the dialogue with the dialogue bot, the extraction unit 33 may add the user attribute to the extraction conditions to update them, and re-extract the user group using the updated extraction conditions.

[0050] Next, a processing procedure of the processing executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the processing procedure of the processing executed by the information processing device 1 according to the embodiment.

[0051] As shown in FIG. 7, the control unit 3 first acquires the contents of an utterance of an advertiser, who is a target user, in a conversation between the advertiser and a conversational bot (step S101).

[0052] Next, the control unit 3 identifies extraction conditions for a user group from the acquired speech content (step S102).

[0053] Next, the control unit 3 extracts a group of users having user attributes that satisfy the specified extraction conditions from the user information (step S103).

[0054] Next, the control unit 3 uses the responses of the extracted user group to past content as learning data to generate a model for predicting the responses of user attributes corresponding to the user group to content (step S104).

[0055] Next, the control unit 3 inputs the feature information of the advertisement content received from the advertiser into the model, and predicts the response of the user group to the advertisement content (step S105).

[0056] Next, the control unit 3 provides the prediction result to the advertiser (step S106), and ends the process.

[0057] 〔others〕 In addition, among the processes described in the above embodiments, some of the processes described as being performed automatically can be performed manually. Alternatively, all or some of the processes described as being performed manually can be performed automatically using a known method. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0058] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0059] 3 may be held in a storage server or the like instead of being held by each device. In this case, each device obtains various pieces of information by accessing the storage server.

[0060] [Hardware configuration] The information processing device 1 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 8. Fig. 8 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which a calculation device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected by a bus 1090.

[0061] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050 and programs read from the input device 1020, and executes various processes. The primary storage device 1040 is a memory device, such as a RAM, that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), a HDD (Hard Disk Drive), a flash memory, or the like.

[0062] The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a monitor or a printer, and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (registered trademark) (High Definition Multimedia Interface). The input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, and scanner, and is realized by a USB, for example.

[0063] The input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a 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. The input device 1020 may also be an external storage medium such as a USB memory.

[0064] The network IF 1080 receives data from other devices via the network N and sends it to the arithmetic device 1030, and also transmits data generated by the arithmetic device 1030 to other devices via the network N.

[0065] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0066] For example, when the computer 1000 functions as the information processing device 1, the arithmetic unit 1030 of the computer 1000 realizes the functions of the control unit 3 by executing a program loaded onto the primary storage device 1040.

[0067] 〔effect〕 As described above, the information processing device 1 according to the embodiment includes an acquisition unit 31 that acquires the speech content of the target user to the conversation bot, an extraction unit 33 that identifies an extraction condition for a user group from the acquired speech content and extracts a user group having a user attribute that satisfies the identified extraction condition, and a generation unit 34 that generates a model that learns the reactions of the extracted user group to past content as learning data and predicts the reaction of the user attribute corresponding to the user group to content. According to the information processing device 1 according to each of the above-mentioned embodiments, the user's reaction to content can be predicted with high accuracy.

[0068] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be embodied in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0069] 〔others〕 In addition, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0070] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0071] Furthermore, the processes described in the above-described embodiments can be appropriately combined as long as the process contents are not contradictory.

[0072] Moreover, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, the control unit 3 can be read as control means or a control circuit. [Explanation of symbols]

[0073] 1. Information processing device 2. Communications Department 3. Control Unit 4 Storage section 31 Acquisition Department 32 Specific part 33 Extraction part 34 Generation part 35 Reception 36 Prediction Department 37 Providing Department 41 User Information 42 Advertiser Information 43 Model Information 50 Advertiser Terminal 100 user terminals S Information Processing System

Claims

1. An acquisition unit that acquires the contents of a speech of a target user to a conversation bot; an extraction unit that specifies an extraction condition for a user group from the acquired utterance content and extracts a user group having a user attribute that satisfies the specified extraction condition; a generation unit that generates a model that is learned using the responses of the extracted user group to past content as learning data, and predicts the responses of the user attributes corresponding to the user group to content; An information processing device comprising:

2. a reception unit that receives content from the target user; a prediction unit that inputs the received content into the model and outputs a prediction result of a reaction to the content from the model; a providing unit for providing the prediction result to the target user; The information processing device according to claim 1 .

3. The providing unit is Providing information about the user group extracted by the extraction unit to the target user. The information processing device according to claim 2 .

4. The acquisition unit is After providing information about the user group to the target user by the providing unit, acquiring utterance content related to the user group from the target user; The extraction unit is The extraction condition is updated based on the acquired speech content, and the user group that satisfies the updated extraction condition is extracted. The information processing device according to claim 3 .

5. The content is advertising content, The generation unit is Generate the model to predict a response to the advertising content The information processing device according to claim 1 .

6. The utterance content includes content related to the user attributes, The extraction unit is The user attribute indicated by the content related to the user attribute included in the utterance content is specified as the extraction condition. The information processing device according to claim 1 .

7. The utterance content includes content related to the number of users in the user group, The extraction unit is The number of users indicated by the content regarding the number of users of the user group included in the utterance content is specified as the extraction condition. The information processing device according to claim 1 .

8. 1. A computer-implemented information processing method, comprising: An acquisition step of acquiring the contents of a speech of a target user to a conversation bot; an extraction step of identifying an extraction condition for a user group from the acquired speech content and extracting a user group having a user attribute that satisfies the identified extraction condition; a generation step of generating a model that is trained using the responses of the extracted user group to past content as learning data, and that predicts the responses of the user attributes corresponding to the user group to content; An information processing method comprising:

9. An acquisition procedure for acquiring the contents of a target user's utterance to a conversational bot; An extraction step of identifying an extraction condition for a user group from the acquired speech content, and extracting a user group having a user attribute that satisfies the identified extraction condition; a generation step of generating a model that is learned using the responses of the extracted user group to past content as learning data, and that predicts the responses of the user attributes corresponding to the user group to content; An information processing program that causes a computer to execute the above.

Images