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

Abstract

To provide an information processing device capable of reducing bias in the distribution of respondent attributes, an information processing method, and an information processing program.SOLUTION: An information processing device comprises an acceptance unit, a generation unit, and an output unit. The acceptance unit accepts a specification of statistical distribution of user attributes. The generation unit generates a prompt causing a generative AI to pseudo-generate a user response to a question such that the user attributes of a respondent become the statistical distribution whose specification has been accepted. The output unit outputs a response of the statistical distribution generated by the generative AI according to the generated prompt.SELECTED DRAWING: Figure 3

Description

Technical Field

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

Background Art

[0002] Conventionally, a technique of distributing a questionnaire to users via the Internet and obtaining users' answers to the questionnaire is known. Also, in this type of technique, there is a technique of setting pseudo-users in generative AI and causing the generative AI to pseudo-generate answers.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, when answers are aggregated, the distribution of the attributes of pseudo-users may be biased. In this case, the aggregated result may not be appropriate.

[0005] In view of the above, the present application is made, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of reducing the bias in the distribution of the attributes of respondents.

Means for Solving the Problems

[0006] The information processing apparatus according to the present application includes a reception unit, a generation unit, and an output unit. The reception unit receives a specification of a statistical distribution of user attributes. The generation unit generates a prompt for causing an AI for generating a user's response to a question to pseudo-generate a response such that the user attribute of the responder becomes the statistical distribution received. The output unit outputs the response of the statistical distribution generated by the generation AI according to the generated prompt.

Effect of the Invention

[0007] According to one aspect of the embodiment, there is an effect that the bias in the distribution of the attributes of the responder can be reduced.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Mode for Carrying Out the Invention

[0009] Hereinafter, a mode for implementing the information processing apparatus, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiment") will be described in detail with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present application are not limited by this embodiment. Also, in the following embodiments, the same parts are denoted by the same reference numerals, and duplicate explanations are omitted.

[0010] (Embodiment) First, with reference to FIG. 1, the processing executed by the information processing apparatus according to the embodiment will be described. FIG. 1 is a diagram showing the processing executed by the information processing apparatus according to the embodiment.

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

[0012] The information processing system S shown in FIG. 1 receives a specification of the statistical distribution of user attributes, generates a prompt for causing the generation AI to pseudo-generate a user's answer to a question so that the user attributes of the respondent become the statistical distribution for which the specification has been received, and outputs an answer of the statistical distribution generated by the generation AI according to the generated prompt.

[0013] Specifically, first, the information processing apparatus 1 receives a questionnaire answer request for requesting generation of questionnaire answers from the requester terminal 50 (step S1). Specifically, the information processing apparatus 1 receives a questionnaire answer request including the questionnaire question content. Further, the information processing apparatus 1 may receive a specification of the statistical distribution of user attributes, which will be described later. Further, the information processing apparatus 1 may receive, as the questionnaire answer request, an outline of the questionnaire such as "Questionnaire regarding XX". In this case, the information processing apparatus 1 automatically generates questions that match the outline of the questionnaire.

[0014] Next, the information processing apparatus 1 sets the user attributes of the respondent (step S2). The user attributes are, for example, demographic attributes such as gender, age, occupation, etc., and geographic attributes such as place of residence, characteristics of the place of residence (climate, culture, economy, etc.). The information processing apparatus 1 may set a plurality of user attributes such as, for example, gender and age. For example, the information processing apparatus 1 sets the user attributes received in the questionnaire response request. Also, the information processing apparatus sets the user attributes based on the users who are using a predetermined service. For example, the information processing apparatus 1 may set the user attributes based on the service in which the user posts questions and answers. Specifically, the information processing apparatus 1 identifies questions similar to the question content received in the questionnaire response request from among the services, and identifies and sets the user attributes of the respondents to the identified questions. Also, the information processing apparatus 1 may set the user attributes of the users who are performing search actions related to the questionnaire question content in the search service. Specifically, the information processing apparatus 1 sets the user attributes of the users whose search queries used in the search action and the content selected from the search results are similar to the question content.

[0015] Next, the information processing apparatus 1 calculates the statistical distribution of the users corresponding to the set user attributes based on the user statistical information (step S3). The user statistical information is statistical information indicating the distribution of user attributes in a predetermined segment. The segment is a region (country, prefecture, etc.) or a service. When the segment is a service, the information processing apparatus 1 calculates the distribution of the user attributes of the users using the service as the statistical distribution. Specifically, the information processing apparatus 1 calculates the distribution of the user attributes of the respondents to the questions similar to the question content received in the questionnaire response request as the statistical distribution in the service of posting the above-described questions and answers. Note that when calculating the statistical distribution, the information processing apparatus 1 may delete the user attributes whose user ratio is less than a predetermined value from the statistical distribution. Also, the information processing apparatus 1 may calculate the distribution of the user attributes of a plurality of users who are performing search actions related to the questionnaire question content in the search service as the statistical distribution.

[0016] Subsequently, the information processing apparatus 1 accepts the calculated statistical distribution as the specification of the statistical distribution of the user attributes of the respondents (step S4). Further, the information processing apparatus 1 may accept the specification of the statistical distribution together with the questionnaire response request.

[0017] Subsequently, the information processing apparatus 1 generates a prompt for causing the generation AI to pseudo-generate the user's response to the question (questionnaire) so as to be the specified statistical distribution (step S5). Specifically, the information processing apparatus 1 generates a prompt including the information of the statistical distribution such as "generate a response to the question of XX so that the male-female ratio of the respondents is 1:1" and the content of the question. Note that the information processing apparatus 1 may include the specification of the number of respondents in the prompt.

[0018] Subsequently, the information processing apparatus 1 generates a response by the generation AI according to the generated prompt (step S6). This generation AI is a model trained to output a response from the perspective of a pseudo-user having specific user attributes for the question input as a prompt. Specifically, the generation AI is a language model that performs natural language processing such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers). And the generation AI is within the information processing apparatus 1 and is independently created by the operator who manages the information processing apparatus 1. Note that it is desirable that the input information be learned so as not to be used as a new response, thereby concealing information such as the input personal information.

[0019] The generative AI prepares a predetermined number of pseudo-users such that the user attributes follow a specified statistical distribution, and generates answers to questions from the perspective of the predetermined number of pseudo-users. Note that for attributes other than the user attributes with the specified statistical distribution, any statistical distribution may be used, or they may be made somewhat uniform. That is, in the case of the above prompt, while the male-female ratio is 1:1, the ages may be made somewhat uniform across each age group.

[0020] In addition, the generative AI is not limited to setting pseudo-users with the set user attributes. It may also select users from among the actual users registered in a predetermined service so that they follow the specified statistical distribution, and set pseudo-users having the user attributes of the selected users (including attributes other than the set user attributes).

[0021] Subsequently, the information processing apparatus 1 outputs the generated answers to the requesting terminal 50 (step S7). Specifically, the information processing apparatus 1 outputs to the requesting terminal 50 the aggregation result of the answers generated by the generative AI and the information on the statistical distribution of the answerers.

[0022] Thus, according to the information processing apparatus 1 according to the embodiment, by generating a prompt that specifies the statistical distribution of the user attributes of the answerers, it is possible to reduce the bias in the user attributes of the questionnaire answerers.

[0023] Next, with reference to FIG. 2, a configuration example of the information processing system S according to the embodiment will be described. FIG. 2 is a block diagram showing a configuration example of the information processing system S according to the embodiment. As shown in FIG. 2, in the information processing system S according to the embodiment, the information processing apparatus 1 and a plurality of requesting terminals 50 are connected to the network N by wire or wirelessly. The network N is, for example, a network such as the Internet, a WAN (Wide Area Network), or a LAN (Local Area Network).

[0024] The information processing apparatus 1 is a server apparatus that executes the information processing method according to the embodiment. The information processing apparatus 1 cooperates with a plurality of requesting terminal devices 50 and provides API (Application Programming Interface) services and various data for the plurality of requesting terminal devices 50 with respect to various applications (hereinafter referred to as applications), etc. The information processing apparatus 1 is realized by a server apparatus, a cloud system, or the like.

[0025] Further, the information processing apparatus 1 may be an information processing apparatus that provides some kind of web service online to a plurality of requesting terminal devices 50. For example, as a web service, the information processing apparatus 1 may provide services such as Internet connection, search service, SNS (Social Networking Service), electronic commerce (EC: Electronic Commerce), electronic payment, online game, online banking, online trading, accommodation / ticket reservation, video / music distribution, news, map, route search, route guidance, route information, operation information, weather forecast, etc. Actually, the information processing apparatus 1 may cooperate with various servers that provide the above web services and mediate the web services, or may be in charge of the processing of the web services.

[0026] The requesting terminal device 50 is a terminal device held by a requester who requests the generation of questionnaire answers. The requesting terminal device 50 can use any type of terminal device such as a smartphone, a desktop PC, a notebook PC, or a tablet PC. The requesting terminal device 50 transmits various information to the information processing apparatus 1, etc., and receives information provided from the information processing apparatus 1, etc.

[0027] Next, with reference to FIG. 3, a configuration example of the information processing apparatus 1 will be described.

[0028] FIG. 3 is a diagram showing a configuration example of the information processing apparatus 1 according to the embodiment. As shown in FIG. 3, the information processing apparatus 1 includes a communication unit 2, a control unit 3, and a storage unit 4. The control unit 3 includes a reception unit 31, a setting unit 32, a calculation unit 33, a generation unit 34, and an output unit 35. The storage unit 4 stores model information 41.

[0029] The communication unit 2 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 2 is connected to a network via wire or wirelessly.

[0030] The control unit 3 is a controller and is realized, for example, by 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 apparatus 1 with a RAM or the like as a work area. Further, the control unit 3 may be realized by 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).

[0031] The storage unit 4 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0032] The model information 41 is information regarding a model that takes a questionnaire question as an input and outputs an answer to the question.

[0033] FIG. 4 is a diagram showing an example of the model information 41. As shown in FIG. 4, the model information 41 includes items such as "Model ID" and "Model Information".

[0034] The "model ID" is identification information for identifying a model. The "model information" is information about the model and includes, for example, input parameters of the model, coefficients, and the like. The model may be generated for each user attribute, for example.

[0035] Next, each function (reception unit 31, setting unit 32, calculation unit 33, generation unit 34, and output unit 35) of the control unit 3 of the information processing apparatus 1 will be described.

[0036] The reception unit 31 receives a questionnaire response request for requesting generation of a questionnaire response from the requester terminal 50. Specifically, the reception unit 31 receives a questionnaire response request including the content of the questionnaire questions. Further, the reception unit 31 may receive a specification of the statistical distribution of user attributes, which will be described later. Further, the reception unit 31 may receive, as a questionnaire response request, an outline of a questionnaire such as "questionnaire regarding XX". In this case, the reception unit 31 automatically generates questions that match the outline of the questionnaire.

[0037] Further, the reception unit 31 receives a specification of the statistical distribution of user attributes. For example, the reception unit 31 receives the statistical distribution calculated by the calculation unit 33 described later as the specification of the statistical distribution of the user attributes of the respondents. Further, the reception unit 31 may receive a specification of the statistical distribution in combination with the questionnaire response request.

[0038] The setting unit 32 sets the user attributes of the respondent. The user attributes are, for example, demographic attributes such as gender, age, occupation, etc., or geographic attributes such as place of residence, characteristics of the place of residence (climate, culture, economy, etc.). The setting unit 32 may set a plurality of user attributes such as, for example, gender and age. For example, the setting unit 32 sets the user attributes received in the questionnaire response request. Also, the setting unit 32 sets the user attributes based on users who are using a predetermined service. For example, the setting unit 32 may set the user attributes based on the service in which the user posts questions and answers. Specifically, the setting unit 32 identifies questions similar to the question content received in the questionnaire response request from among the services, and identifies and sets the user attributes of the respondents to the identified questions. Also, the setting unit 32 may set the user attributes of users who are performing a search action related to the question content of the questionnaire in the search service. Specifically, the setting unit 32 sets the user attributes of users whose search queries used in the search action and the content selected from the search results are similar to the question content.

[0039] The calculation unit 33 calculates the statistical distribution of users corresponding to the set user attributes based on the user statistical information. The user statistical information is statistical information indicating the distribution of user attributes in a predetermined segment. The segment is a region (country, prefecture, etc.) or a service. When the segment is a service, the calculation unit 33 calculates the distribution of the user attributes of users using the service as the statistical distribution. Specifically, the calculation unit 33 calculates, as the statistical distribution, the distribution of the user attributes of the respondents to questions similar to the question content received in the questionnaire response request in the above-described service for posting questions and answers. Note that when calculating the statistical distribution, the calculation unit 33 may delete the user attributes for which the ratio of users is less than a predetermined value from the statistical distribution. Also, the calculation unit 33 may calculate, as the statistical distribution, the distribution of the user attributes of a plurality of users who are performing a search action related to the question content of the questionnaire in the search service.

[0040] The generation unit 34 generates a prompt that causes the generation AI to pseudo-generate the user's response to the question (questionnaire) so as to be the specified statistical distribution. Specifically, the generation unit 34 generates a prompt that includes information on the statistical distribution such as "generate responses to the question of XX so that the male-female ratio of the respondents is 1:1" and the content of the question. Note that the information processing apparatus 1 may include the specification of the number of respondents in the prompt.

[0041] Subsequently, the generation unit 34 generates responses by the generation AI according to the generated prompt. This generation AI is a model trained to output responses from the perspective of a pseudo-user with specific user attributes for the question input as a prompt.

[0042] The generation AI prepares a predetermined number of pseudo-users so that the user attributes are the specified statistical distribution, and generates responses to the question from the perspective of the predetermined number of pseudo-users. Note that for attributes other than the user attributes with the specified statistical distribution, any statistical distribution may be used, or it may be made to be somewhat uniform. That is, in the case of the above prompt, while the male-female ratio is 1:1, the age may be made somewhat uniform for each age group.

[0043] Also, the generation AI is not limited to the case of setting pseudo-users with the set user attributes, but may select users from among the actual users registered in a predetermined service so as to be the specified statistical distribution, and set pseudo-users having the user attributes of the selected users (including attributes other than the set user attributes).

[0044] The output unit 35 outputs the generated responses to the requesting main terminal 50. Specifically, the output unit 35 outputs the aggregation result of the responses generated by the generation AI and the information on the statistical distribution of the respondents to the requesting main terminal 50.

[0045] Next, with reference to FIG. 5, the processing procedure of the information processing apparatus 1 according to the embodiment will be described. FIG. 5 is a flowchart showing the processing procedure of the processing executed by the information processing apparatus 1 according to the embodiment.

[0046] As shown in FIG. 5, first, the control unit 3 receives a questionnaire response request from the requester terminal 50 (step S101).

[0047] Subsequently, the control unit 3 sets user attributes (step S102).

[0048] Subsequently, the control unit 3 calculates the statistical distribution of the set user attributes (step S103).

[0049] Subsequently, the control unit 3 generates a prompt for causing the generation AI to pseudo-generate the user's answer to the question so that the user attributes of the respondent become the received statistical distribution (step S104).

[0050] Subsequently, the control unit 3 generates a questionnaire answer by the generation AI according to the generated prompt (step S105).

[0051] Subsequently, the control unit 3 outputs the generated answer to the requester terminal 50 (step S106) and ends the process.

[0052] 〔Others〕 In addition, among the processes described in the above embodiment, a part of the processes described as being automatically performed can also be manually performed. Alternatively, all or part of the processes described as being manually performed can also be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above documents 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.

[0053] Moreover, each component of each illustrated device is functionally conceptual and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of the distribution and integration of each device is not limited to that shown in the figure, and all or part of it can be functionally or physically distributed and integrated in any unit according to various loads, usage situations, etc.

[0054] For example, part or all of the storage unit 4 shown in FIG. 3 may be held not by each device but by a storage server or the like. In this case, each device acquires various information by accessing the storage server.

[0055] 〔Hardware Configuration〕 In addition, the information processing apparatus 1 according to the above-described embodiment is realized by a computer 1000 having a configuration as shown in FIG. 6, for example. FIG. 6 is a diagram showing an example of a hardware configuration. The computer 1000 has a form in which an output device 1010, an input device 1020 are connected, and an arithmetic unit 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.

[0056] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 or the secondary storage device 1050, programs read from the input device 1020, etc., 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 unit 1030 for various operations. The secondary storage device 1050 is a storage device in which data used by the arithmetic unit 1030 for various operations and various databases are registered, and is realized by a ROM (Read Only Memory), an HDD (Hard Disk Drive), a flash memory, etc.

[0057] 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 and a printer, and is realized by connectors of standards such as USB (Universal Serial Bus), DVI (Digital Visual Interface), and HDMI (registered trademark) (High Definition Multimedia Interface). Also, the input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, a keyboard, and a scanner, and is realized by, for example, USB or the like.

[0058] Note that the input device 1020 may be, for example, a device that reads information from 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. Also, the input device 1020 may be an external storage medium such as a USB memory.

[0059] The network IF 1080 receives data from other devices via the network N and sends it to the arithmetic unit 1030, and also sends data generated by the arithmetic unit 1030 via the network N to other devices.

[0060] 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.

[0061] For example, when the computer 1000 functions as the information processing device 1, the arithmetic unit 1030 of the computer 1000 realizes the function of the control unit 3 by executing the program loaded onto the primary storage device 1040.

[0062] 〔Effect〕 As described above, the information processing apparatus 1 according to the embodiment includes a reception unit 31, a generation unit 34, and an output unit 35. The reception unit 31 receives a specification of the statistical distribution of user attributes. The generation unit 34 generates a prompt for causing the generation AI to pseudo-generate a user's answer to a question so that the user attributes of the answerer become the specified statistical distribution. The output unit 35 outputs an answer of the statistical distribution generated by the generation AI according to the generated prompt. With such a configuration, it is possible to reduce the bias in the distribution of the attributes (user attributes) of the answerer.

[0063] As described above, some of the embodiments of the present application have been described in detail with reference to the drawings. However, these are examples, and the present invention can be implemented in other forms in which various modifications and improvements are made based on the knowledge of those skilled in the art, starting from the aspects described in the column of the disclosure of the invention.

[0064] 〔Others〕 In addition, among the processes described in the above embodiment, all or part of the processes described as being automatically performed can be manually performed, or all or part of the processes described as being manually performed can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above documents 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.

[0065] In addition, each component of each illustrated device is conceptually functional, and it is not necessarily physically configured as illustrated. That is, the specific form of the distribution and integration of each device is not limited to that shown in the figure, and all or part of it can be functionally or physically distributed and integrated in any unit according to various loads and usage situations.

[0066] In addition, the processes described in the above-described embodiments can be appropriately combined as long as the processing contents do not conflict with each other.

[0067] Also, the "section (section, module, unit)" described above can be read as "means", "circuit", etc. For example, the control unit 3 can be read as a control means or a control circuit.

Explanation of Signs

[0068] 1 Information processing device 2 Communication unit 3 Control unit 4 Storage unit 31 Reception unit 32 Setting unit 33 Calculation unit 34 Generation unit 35 Output unit 41 Model information 50 Client terminal S Information processing system

Claims

1. A reception unit that receives a specification of a statistical distribution of user attributes, A generation unit that generates a prompt for causing a generative AI to pseudo-generate a user's response to a question so that the user attributes of the respondent become the statistical distribution received by the specification, An output unit that outputs the response of the statistical distribution generated by the generative AI according to the generated prompt An information processing apparatus comprising.

2. Further comprising a setting unit for setting the user attributes, The reception unit, Receives a specification of the statistical distribution of the set user attributes The information processing apparatus according to claim 1.

3. The setting unit, Sets the attributes of users who use a predetermined service as the user attributes The information processing apparatus according to claim 2.

4. The setting unit, In a search service, sets the attributes of users who are performing a search action related to the content of the question as the user attributes The information processing apparatus according to claim 3.

5. The setting unit, In a service for posting questions and answers, identifies questions similar to the content of the questions for which the generative AI generates answers from among the services, and sets the attributes of the users who answer the identified questions as the user attributes The information processing apparatus according to claim 3.

6. Further comprising a calculation unit that calculates the statistical distribution of users corresponding to the user attributes set by the setting unit based on user statistical information, which is user statistical information regarding the distribution of the user attributes, The reception unit, Receives the statistical distribution calculated by the calculation unit as a specification The information processing apparatus according to claim 2.

7. The calculation unit, In a service for posting questions and answers, calculates the distribution of user attributes of respondents to questions similar to the content of the questions for which the generative AI generates answers as the statistical distribution The information processing apparatus according to claim 6.

8. The calculation unit, In a search service, calculates the distribution of user attributes of users who are performing a search action related to the content of the question as the statistical distribution The information processing apparatus according to claim 6.

9. An information processing method executed by a computer, A reception step of receiving a specification of a statistical distribution of user attributes, A generation step of generating a prompt for causing a generative AI to pseudo-generate a user's response to a question so that the user attributes of the respondent become the statistical distribution received by the specification, An output step of outputting the answer of the statistical distribution generated by the generation AI according to the generated prompt An information processing method including the above.

10. A reception procedure for receiving a designation of a statistical distribution of user attributes, A generation procedure for generating a prompt that causes the generation AI to pseudo-generate a user's answer to a question so that the user attributes of the answerer become the designated statistical distribution, An output procedure for outputting the answer of the statistical distribution generated by the generation AI according to the generated prompt An information processing program for causing a computer to execute the above.

Images