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

Abstract

We provide technology that generates personas that mimic the actual consumption behavior of consumers. [Solution] The information processing device (10) comprises a classification unit (11) that classifies consumer behavior data indicating a consumer's consumption behavior history and the attributes of the consumer into multiple segments, a prompt generation unit (12) that generates a prompt for generating a persona symbolizing the segment for at least a portion of the multiple segments based on the consumption behavior data belonging to the segment and the characteristics of the consumer identified from the consumption behavior data, and a content generation unit (13) that generates a persona corresponding to the segment by inputting the prompt into a generation model.

Description

[Technical field]

[0001] The present invention relates to techniques for generating personas. [Background technology]

[0002] A technique for generating a persona is known. The persona is utilized, for example, in marketing. An example of a technique for generating a persona is described in Patent Document 1. Patent Document 1 describes a persona chatbot control method including a step of receiving a user utterance, a step of adding the user utterance to a prompt including an instruction sentence related to a description of a chatbot character, a step of encoding the prompt, and a step of inputting the encoded prompt into a language model to generate a chatbot utterance responding to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2021-210522 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, although the technology described in Patent Document 1 can generate chatbot utterances that respond to user utterances, it has the problem that it cannot generate personas that mimic the actual consumption behavior of consumers.

[0005] One aspect of the present invention aims to realize a technology for generating a persona that mimics a consumer's actual consumption behavior. [Means for solving the problem]

[0006] In order to solve the above problems, an information processing device according to one embodiment of the present invention includes a classification unit that classifies consumer behavior data indicating a consumer's consumption behavior history and attributes of the consumer into a plurality of segments, a prompt generation unit that generates a prompt for generating a persona symbolizing at least a portion of the plurality of segments based on the consumption behavior data belonging to the segment and consumer characteristics identified from the consumption behavior data, and a persona generation unit that generates a persona corresponding to the segment by inputting the prompt into a generation model.

[0007] Furthermore, an information processing method according to one embodiment of the present invention includes a classification process in which at least one processor classifies consumption behavior data indicating a consumer's consumption behavior history and attributes of the consumer into a plurality of segments; a prompt generation process in which the at least one processor generates a prompt for generating a persona symbolizing at least a portion of the plurality of segments based on the consumption behavior data belonging to the segment and consumer characteristics identified from the consumption behavior data; and a persona generation process in which the at least one processor generates a persona corresponding to the segment by inputting the prompt into a generative model.

[0008] The information processing device according to each aspect of the present invention may be realized by a computer. In this case, the control program of the information processing device that realizes the information processing device on a computer by causing the computer to operate as each part (software element) of the information processing device, and the computer-readable recording medium on which the control program is recorded, also fall within the scope of the present invention. Effect of the Invention

[0009] According to one aspect of the present invention, a persona can be generated that mimics a consumer's actual consumption behavior. [Brief description of the drawings]

[0010] [Figure 1] 1 is a block diagram showing an example of a configuration of a system according to an embodiment. [Diagram 2] 1 is a block diagram showing an example of a configuration of an information processing device according to an embodiment. [Diagram 3] FIG. 4 is a diagram showing a specific example of consumption behavior data according to the embodiment. [Figure 4] FIG. 2 is a block diagram showing an example of a configuration of a user terminal according to the embodiment. [Diagram 5] FIG. 2 is a sequence diagram showing an example of a flow of an information processing method according to the embodiment. [Figure 6] FIG. 13 is a diagram illustrating an example of a prompt according to an embodiment. [Figure 7] FIG. 13 is a diagram illustrating an example of a prompt according to an embodiment. [Figure 8] FIG. 4 is a diagram illustrating an example of an input screen according to the embodiment. [Figure 9] FIG. 13 is a diagram illustrating an example of a prompt according to an embodiment. [Figure 10] FIG. 13 is a diagram illustrating an example of a prompt according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] [Embodiment] [System Configuration] An embodiment of the present invention will be described in detail below. FIG. 1 is a block diagram showing an example of the configuration of a system 1 according to this embodiment. The system 1 is a system for supporting marketing and the like. The system 1 includes an information processing device 10 and a user terminal 20. The information processing device 10 and the user terminal 20 are communicatively connected via a communication line N. Although the specific configuration of the communication line N does not limit this embodiment, examples of the communication line N include a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public line network, a mobile data communication network, or a combination of these.

[0012] The information processing device 10 is a device having a function for supporting marketing and the like, and is, for example, a general-purpose computer. The user terminal 20 is a terminal used by a user of the system 1, and is, for example, a personal computer such as a laptop computer, a tablet terminal, or a smartphone. Examples of users of the system 1 include, but are not limited to, those who plan and develop products or services, those who do branding or marketing, and those who handle customers (for example, contact center staff).

[0013] [Configuration of information processing device] 2 is a block diagram showing an example of a configuration of the information processing device 10. The information processing device 10 includes a control unit 110, a storage unit 120, a communication unit 130, an input unit 140, and an output unit 150. The control unit 110 executes instructions of a computer program stored in the storage unit 120. The communication unit 130 communicates with devices external to the information processing device 10 via a communication line N. The communication unit 130 transmits data provided from the control unit 110 to other devices, and provides data received from other devices to the control unit 110.

[0014] <Input section / output section> The input unit 140 is configured to receive input to the information processing device 10, and includes, as an example, input devices such as a keyboard, a mouse, a touch panel, a camera, and a microphone. The input unit 140 may also be configured to receive data from the input devices via an interface such as a Universal Serial Bus (USB). The output unit 150 is configured to perform output from the information processing device 10, and includes, as an example, output devices such as a display, a printer, a touch panel, and a speaker. The output unit 150 may also be configured to include, for example, an interface such as a USB, and to output data to the output device via the interface.

[0015] <Storage section> The storage unit 120 stores instructions of a computer program executed by the control unit 110. The storage unit 120 also stores various types of information referenced by the control unit 110. Examples of such information include consumption behavior data 121, collected data 122, prompts 123, and the generative model M1. Note that storing the generative model M1 in the storage unit 120 means that parameters defining the generative model M1 are stored in the storage unit 120.

[0016] (Consumption behavior data) The consumption behavior data 121 is data indicating the history of a consumer's consumption behavior and the attributes of the consumer. An example of the consumption behavior data is so-called ID-POS data. Examples of the consumption behavior include the purchase of a product and the provision of a service. Examples of the attributes of the consumer include the gender, age, residential area, family structure, occupation, and annual income of the consumer. An example of the consumption behavior data 121 is data in which data indicating the content of the consumption behavior is linked to data indicating the attributes of the consumer who performed the consumption behavior. More specifically, an example of the consumption behavior data 121 is collected by reading user identification information (such as a two-dimensional barcode) included in a membership card of a consumer who has registered as a member in advance with a POS (Point of Sales) register, and linking the attribute data of the consumer corresponding to the read user identification information with data related to the purchased product. The consumer's membership card may be, for example, a paper medium, or may be a display screen displayed by a dedicated application on a user terminal such as a smartphone.

[0017] FIG. 3 is a diagram showing a specific example of the consumption behavior data 121. In the example of FIG. 3, the consumption behavior data 121 includes data such as "purchase date and time", "product", "purchase store", "purchase amount", "gender", "generation", "app usage log", "customer preference score", and "deposit balance". "Purchase date and time" is data indicating the date and time when the consumption behavior was performed. "Product" is data indicating the purchased product. "Purchase store" is data indicating the store where the product was purchased. "Purchase amount" is data indicating the amount of the purchased product. "Gender" is data indicating the gender of the consumer who purchased the product. "Generation" is information indicating the generation of the consumer who purchased the product. "App usage log" is data indicating the usage history of a dedicated application. "Customer preference score" is data indicating the degree of preference for each product category. "Deposit balance" is data indicating the deposit balance of the consumer who purchased the product. In addition, the data included in the consumption behavior data 121 is not limited to the above-mentioned example, and the consumption behavior data 121 may include, for example, data indicating the address of the consumer who performed the consumption behavior.

[0018] Data indicating consumer attributes (gender, age, etc.) included in the consumption behavior data 121 is read out, for example, from a consumer database (not shown) in which consumer data indicating consumer attributes, etc. is stored. The consumer data includes, for example, data such as the consumer's name, address, age, and gender. The consumer data is, for example, data input by the consumer to a user terminal to register as a member using a dedicated application.

[0019] (Data collected) The collected data 122 is data collected on consumers or services provided to consumers. Examples of the collected data include data showing the contents of interviews with consumers and data showing survey results on services. Examples of the contents of interviews with consumers include answers to interviews such as the reason why consumers choose a store to perform consumption behavior, what they feel when performing consumption behavior, and problems they have when performing consumption behavior. Examples of the answers to the interviews include opinions such as "I want to do all my shopping at a nearby convenience store as much as possible," "I don't want to spend time shopping," "I often have trouble deciding what to buy," "I want to eat as healthy food as possible," and "I want to eat low-calorie food." Examples of survey results on services include survey results such as the appeal of each company's service and the degree of recognition of each company's service. The collected data may also include NPS (Net Promoter Score). NPS is an index that quantifies the degree of attachment to a company, product, or service and measures customer loyalty. The collected data 122 may also include data showing information on the area in which the store providing the product or service is located.

[0020] (prompt) The prompt 123 is input data input to the generative model M1 by the content generation unit 13 described later. Examples of the prompt 123 include text, voice data, image data, and a combination of these. As an example, the prompt 123 is used by a user to converse with a persona using the generative model M1. In the present disclosure, a persona is a chatbot that responds to user utterances and is generated by the generative model M1. In the present disclosure, a persona is a user model in which age, sex, residential area, family structure, occupation, annual income, values, lifestyle, etc. are specifically set.

[0021] The prompt 123 input to the generation model M1 is, for example, a prompt generated by the prompt generation unit 12 described later. In this case, the prompt 123 is, for example, a prompt for generating a persona by the generation model M1. The prompt 123 may also be a prompt received from the user terminal 20. In this case, the prompt 123 may be, for example, text representing a question to the persona.

[0022] (Generative Model) The generative model M1 is a model generated by machine learning, and generates content such as text. The input of the generative model M1 is a prompt 123, and the output of the generative model M1 is content generated from the prompt 123. Examples of the content include text that is a response to the prompt 123, which is a request to generate a persona, and text that indicates an answer to the prompt 123 including a question to the persona. The content is not limited to text, and may include image data or audio data. Examples of the generative model M1 include generative AI (generative artificial intelligence) such as ChatGPT (Chat Generative Pre-trained Transformer) and GPT-4 (Generative Pre-trained Transformer 4), or the generative AI fine-tuned using the consumption behavior data 121 and the collected data 122, but are not limited to these.

[0023] <Control Unit> The control unit 110 includes a classification unit 11, a prompt generation unit 12, and a content generation unit 13. Each unit of the control unit 110 is realized by the control unit 110 reading and executing instructions of a computer program stored in the storage unit 120. The content generation unit 13 is an example of a persona generation unit according to the present disclosure.

[0024] (Classification Department) The classification unit 11 classifies the consumer behavior data 121 into a plurality of segments. In the present disclosure, a segment is a classification result determined from attributes, purchase frequency, purchase amount, purchase store, etc., in order to determine a focus group to be targeted for various measures in marketing, etc. More specifically, the plurality of segments are, for example, a case where the consumer behavior data 121 is classified into a plurality of groups such as "good customers," "first layer," and "second layer" based on the purchase frequency and purchase amount, etc., and each layer is further classified based on the attributes of consumers. Here, as an example, a "good customer" user is a user who purchases 20,000 yen or more per month and purchases 16 times or more per month. As an example, a "first layer" user is a user who purchases less than 10,000 yen per month and purchases 1 to 6 times per month. As an example, a "second layer" user is a user who purchases 10,000 yen or more but less than 20,000 yen per month and purchases 3 to 6 times per month.

[0025] (Prompt generation part) The prompt generation unit 12 generates a prompt 123 for generating a persona representing each of at least some of the segments included in the plurality of segments obtained by classification by the classification unit 11, based on the consumption behavior data 121 belonging to the segment and the characteristics of the consumer identified from the consumption behavior data 121. The characteristics of the consumer include, for example, information indicating the tendency of the consumer's consumption behavior. For example, the characteristics of the consumer include information such as "sensitive to 'bargains' and often uses coupons," "goes to work more often, and buys a convenience store cafe on the way to work," "often buys lunch at a convenience store near the workplace," "buys beer and dessert at a supermarket near the home on the way home," "uses a store near the workplace," and "uses a store near the home." For example, the prompt generation unit 12 may identify the characteristics of the consumer using the consumption behavior data belonging to the segment for each of at least some of the segments included in the plurality of segments, and generate the prompt 123 using the identified characteristics.

[0026] The prompt generation unit 12 may generate the prompt 123 for all of the multiple segments obtained by classification by the classification unit 11, or may generate the prompt 123 for some of the multiple segments. When generating the prompt 123 for some of the segments, the prompt generation unit 12 may, for example, extract segments whose degree of focus as a target specified for each of the multiple segments satisfies a predetermined condition from the multiple segments obtained by classification by the classification unit 11, and generate a prompt for each of the extracted segments. The degree of focus as a target may be information set by the user for each segment, for example, or may be information specified by the prompt generation unit 12 based on the characteristics of the consumption behavior data 121 included in each segment (such as the amount of data, the similarity between data, etc.).

[0027] Furthermore, the prompt generation unit 12 may generate a prompt using the collected data 122 in addition to the consumption behavior data 121 and the consumer characteristics. In other words, the prompt generation unit 12 generates a prompt 123 for at least a portion of the segments included in the plurality of segments, based on the consumption behavior data 121 belonging to the segment, the consumer characteristics identified from the consumption behavior data 121, and the collected data 122 corresponding to the consumption behavior data 121 belonging to the segment, which is stored in the storage unit 120.

[0028] (Content Generation Division) The content generation unit 13 generates content corresponding to the prompt 123 by inputting the prompt 123 to the generative model M1. As an example, the content generation unit 13 generates a persona corresponding to the above-mentioned segment by inputting the prompt 123 to the generative model M1. Also, as an example, the content generation unit 13 generates content representing an answer to the question by inputting the prompt 123, which is received from the user terminal 20 and represents a question to the persona, to the generative model M1.

[0029] The content generation unit 13 outputs the generated content by transmitting the content to the user terminal 20 via the communication unit 130. In this case, the user terminal displays the received content on a display or the like. In this specification, the content generation unit 13 transmitting the content to the user terminal 20 and displaying the content on a display or the like of the user terminal 20 is also referred to as "the content generation unit 13 displays the content."

[0030] Furthermore, the content generating unit 13 may output the content to an output device such as a display via the output unit 150. Furthermore, the content generating unit 13 may output the content by writing the content to a storage destination (which may be a storage device within the information processing device 10 or a storage device outside the information processing device 10) designated by the user of the information processing device 10.

[0031] [User terminal configuration] 4 is a block diagram showing the configuration of the user terminal 20. The user terminal 20 includes a control unit 210, a storage unit 220, a communication unit 230, an input unit 240, and an output unit 250. The control unit 210 executes instructions of a computer program stored in the storage unit 220. The storage unit 220 stores instructions of a computer program executed by the control unit 210. The storage unit 220 also stores various types of information referenced by the control unit 210. The communication unit 230 communicates with devices external to the user terminal 20 via a communication line N.

[0032] <Input section / output section> The input unit 240 is configured to receive input to the user terminal 20, and includes, as an example, input devices such as a keyboard, mouse, touch panel, camera, and microphone. The input unit 240 may also be configured to receive data from the input devices via an interface such as a USB. The output unit 250 is configured to perform output from the user terminal 20, and includes, as an example, output devices such as a display, printer, touch panel, and speaker. The output unit 250 may also be configured to include, for example, an interface such as a USB, and to output data to the output device via the interface.

[0033] <Control Unit> The control unit 210 includes an application execution unit 21. The application execution unit 21 is an example of a speech data transmission unit and an output control unit according to the present disclosure. The application execution unit 21 is realized by the control unit 210 reading and executing an instruction of an application program stored in the storage unit 220. The application execution unit 21 executes a process of receiving content transmitted from the information processing device 10, a process of transmitting text input by a user as a prompt to the information processing device 10, and the like. An application implemented by the application execution unit 21 is, for example, a general-purpose web browser, but is not limited thereto. An application implemented by the application execution unit 21 may be, for example, a dedicated application for communicating with the information processing device 10 and receiving content.

[0034] As an example, the application execution unit 21 transmits speech data representing the content of a user's speech to the persona to the information processing device 10. Also, as an example, the application execution unit 21 receives a response from the information processing device and outputs the received response to an output device such as a display.

[0035] [Information processing method flow] 5 is a sequence diagram showing an example of the flow of the information processing method according to the present embodiment. In step S11, the classification unit 11 classifies the consumption behavior data 121 into a plurality of segments. More specifically, the classification unit 11 classifies the consumption behavior data 121 into a plurality of segments based on, for example, the number of purchases, the purchase amount, and the attributes of the consumer included in the consumption behavior data 121. In step S11, the classification unit 11 may classify the consumption behavior data 121 based on classification conditions set by a user, or may classify the consumption behavior data 121 based on classification conditions set based on the analysis results of the consumption behavior data 121.

[0036] In step S12, the prompt generation unit 12 identifies consumer characteristics for each of at least some of the segments included in the plurality of segments, using the consumption behavior data 121 belonging to the segment. As an example, the prompt generation unit 12 extracts a target segment from among the plurality of segments obtained by classification by the classification unit 11, and identifies the consumer's consumption behavior tendency (using a store near the workplace, using a store near the home, etc.) as the consumer's characteristics for each of the extracted segments, based on the location information of the store where the consumption behavior indicated by the consumption behavior data belonging to each segment was performed, etc. Alternatively, the user may input data indicating characteristics corresponding to each segment using the input unit 240, etc., and the prompt generation unit 12 may identify the consumer's characteristics based on the input data.

[0037] In step S13, the prompt generation unit 12 defines a target image for the target segment. More specifically, for each of at least some of the segments, the prompt generation unit 12 generates target image definition data representing a consumer image symbolizing the segment based on consumption behavior data belonging to the segment, consumer characteristics identified from the consumption behavior data, and collected data corresponding to the consumption behavior data belonging to the segment. Here, the target image definition data is data representing a consumer image of the target segment, and is text, image data, audio data, video data, or a combination of these. The target image definition data may include, for example, text describing a consumer image, such as "likes Western-style sweets."

[0038] The target image definition data may include data indicating the characteristics of a consumer identified from the consumption behavior data belonging to a segment. In other words, the prompt generation unit 12 generates target image definition data for at least a portion of the segments, the target image definition data including data indicating the characteristics of a consumer identified from the consumption behavior data belonging to the segment. The target image definition data may include the consumption behavior data of the segment, and may also include data indicating the characteristics of a consumer identified from the consumption behavior data. The target image definition data may also include collected data corresponding to the segment. The target image data may also include data obtained by statistically computing the consumption behavior data or the collected data. The target image definition data may also include data input by a user using the input unit 240 or the like.

[0039] In step S14, the prompt generation unit 12 generates persona definition data that defines a persona, using the target image definition data generated in step S13. The persona definition data is, for example, text, image data, audio data, video data, or a combination of these. The persona definition data includes, for example, information such as "what kind of coupon do you want" in addition to the contents of the definition of the target image. The persona definition data includes, for example, data input by the user using the input unit 240, etc., in addition to the data included in the target image definition data.

[0040] In step S15, the prompt generation unit 12 generates a prompt 123 for generating a persona symbolizing a segment, using the persona definition data generated in step S14. The persona definition data is data generated using the target image definition data, and the target image definition data is data generated based on the consumption behavior data 121 belonging to each segment and the characteristics of consumers identified from the consumption behavior data 121. Therefore, in other words, the prompt generation unit 12 can be said to generate a prompt 123 for generating a persona symbolizing a segment, for at least a portion of the segments included in the multiple segments obtained by classification by the classification unit 11, based on the consumption behavior data 121 belonging to the segment and the characteristics of consumers identified from the consumption behavior data 121. As an example, the prompt generation unit 12 may generate the prompt 123 by converting the generated target image definition data into the prompt 123 in text format.

[0041] In step S16, the content generation unit 13 generates a persona corresponding to the segment by inputting the prompt 123 into the generation model M1. The content generation unit 13 transmits the content output from the generation model M1, which is obtained by inputting the prompt 123 into the generation model M1, to the user terminal 20. As an example, the content is content indicating that a persona has been generated, and more specifically, includes text to the effect that, for example, "I understand the target image." In addition to the content output from the generation model M1, the content generation unit 13 may transmit the prompt 123 input into the generation model M1 and data representing the characteristics of the segment corresponding to the prompt 123 to the user terminal 20. The user terminal 20 receives the content, etc. from the information processing device 10 and displays the received content, etc. on a display, etc.

[0042] As an example, the personas for each segment generated by the content generation unit 13 have characteristics such as "a man in his 40s or 50s with a child in elementary school" and "a woman in her 40s or 50s who works full-time and has a child in college."

[0043] In step S17, the application execution unit 21 displays an input screen for inputting speech data representing the content of a question to the persona on the display. The input screen is, for example, a screen illustrated in Fig. 8 described later. The user inputs text representing a question to the persona on the input screen.

[0044] In step S18, the application execution unit 21 transmits the speech data, which is the text input by the user, to the information processing device 10. The content generation unit 13 receives, from the user terminal 20, the speech data representing the content of the user's utterance to the persona.

[0045] In step S19, the content generation unit 13 generates content that is a response to the user's utterance by inputting the received utterance data into the generation model M1. When the content generation unit 13 inputs the utterance data into the generation model M1, content corresponding to the input text is output from the generation model M1. The content generation unit 13 transmits the generated response content to the user terminal 20. The user terminal 20 receives the content from the information processing device 10. In step S20, the application execution unit 21 outputs the received content, which is the response. As an example, the application execution unit 21 displays the received response on a display.

[0046] [Example of prompt] 6 and 7 are diagrams showing an example of the prompt 123. In the examples of FIG. 6 and FIG. 7, the prompt 123 includes text 123-1 and text 123-2. Text 123-1 includes text such as "You are {#role}. Please carry out {#request}. However, please refer to the contents of {#reference} and be sure to follow {#rule} when answering." Furthermore, text 123-1 includes text referenced in each of {#role}, {#request}, and {#rule}. Text referenced as {#role} includes the text "person specified in {#reference}."

[0047] 7, text 123-2 includes text referenced as {#reference}. More specifically, text 123-2 includes text T11, T12, T21, T22, T31, and T32. However, the text included in prompt 123 is not limited to the text exemplified in Fig. 6 and Fig. 7, and prompt 123 may include other text, and may also include data in other data formats, such as image data, audio data, and video data.

[0048] Text 123-2 includes items such as "(1) Target Profile Overview," "(2) Target Information," "(3) Channel Usage and Values," and "(4) Shopping Needs, Insights, and Problems." The "(1) Target Profile Overview" item includes characteristics common to the consumer behavior data belonging to that segment. The characteristics, for example, represent the classification conditions of the segment. The "(2) Target Information" item includes information that represents the specific characteristics of the target. For example, the information represents family structure, consumer behavior trends, etc. The "(3) Channel Usage and Values" item includes information that represents the channel usage and values ​​of consumers belonging to that segment. The "(4) Shopping Needs, Insights, and Problems" item includes information that represents consumers' thoughts on consumer behavior.

[0049] Of the texts included in text 123-2, texts T11 and T12 are data included in the consumer behavior data 121 of the segment, and in particular are data used to classify the consumer behavior data 121. Texts T21 and T22 are data representing the characteristics of consumers identified from the consumer behavior data 121 of the segment. Texts T31 and T32 are collected data corresponding to consumers belonging to the segment. In this way, text 123-2 shown in Figure 7, which is a prompt, is generated based on the consumer behavior data 121 belonging to the segment, the characteristics of consumers identified from the consumer behavior data, and collected data corresponding to consumers belonging to the segment.

[0050] [Example of input screen] FIG. 8 is a diagram showing a specific example of an input screen for interviewing a persona. The application execution unit 21 of the user terminal 20 displays the screen shown in FIG. 8 on the display based on the content received from the information processing device 10. In the example of FIG. 8, the screen SC1 includes text T41, T42, and a text box B43. The text T41 is text explaining the persona to be interviewed, specifically, the text "We can interview a male in his 40s or 50s who is an office worker who frequently uses XX both at work and near his home." The text T42 is text representing the prompt 123 used to generate the persona. The text box B43 is a component for the user to input text.

[0051] When the user inputs a question for the persona as text in the text box B43, the user terminal 20 transmits the input text to the information processing device 10. The information processing device 10 transmits an answer to the question obtained by inputting the received text into the generative model M1 to the user terminal 20. The user terminal 20 displays the received response on a display or the like. By checking the displayed response, the user can check the results of the interview with the persona that mimics the actual consumption behavior of a consumer, without actually interviewing a real consumer.

[0052] The personas generated by this embodiment can be used in various operations such as product and service planning and development, branding and marketing, customer service training (including contact centers), etc. In addition, the generated personas can also be used, for example, to participate in a simulated conference.

[0053] [Other examples of prompts] 9 and 10 are diagrams showing other examples of the prompt 123. In FIG. 9 and FIG. 10, an example of the prompt 123 in the case where a plurality of personas are generated and the personas are allowed to converse with each other is shown. In the example of FIG. 9 and FIG. 10, the prompt 123 includes text 123-3 and text 123-4. The text 123-3 includes text such as "You are {#role}. Please carry out {#request}. However, please refer to the contents of {#reference} and be sure to follow {#rule} and {#notes} and answer according to {#format}". The text 123-3 also includes texts referenced in each of {#role}, {#request}, and {#rule}. The texts referenced as {#role} include texts such as "a group of three people appropriated in {#reference}". The texts referenced as {#reference} include, for example, the text 123-2 exemplified in FIG. 7, but are not limited thereto. Also, in the example of FIG. 10, text 123-4 includes text referenced as {#Notes}.

[0054] <Effects> As described above, according to this embodiment, the information processing device 10 classifies the consumption behavior history of a consumer and consumption behavior data indicating the attributes of the consumer into a plurality of segments, and for each of at least some of the plurality of segments, generates a prompt 123 for generating a persona symbolizing the segment, based on the consumption behavior data 121 belonging to the segment and the characteristics of the consumer identified from the consumption behavior data 121. The information processing device 10 inputs the generated prompt 123 into the generation model M1, thereby making it possible to generate a persona for each segment obtained by classifying the consumption behavior data.

[0055] [Variations] The functions of the information processing device 10 described above may be shared and implemented by a plurality of devices. For example, the information processing device 10 described above may be realized as a system in which two or more devices are connected via a communication network. In this case, the system may be, for example, a system having a first device including a classification unit 11 and a prompt generation unit 12, and a second device including a content generation unit 13. In this case, the functions of the information processing device 10 are realized by the cooperation of the first device and the second device.

[0056] In the above embodiment, the case where the generation model M1 is stored in the storage unit 120 of the information processing device 10 has been described, but the generation model M1 may be stored in a device other than the information processing device 10. In this case, the information processing device 10 transmits a prompt to the device in which the generation model M1 is stored, and receives inference result data transmitted from the device as a response to the transmitted prompt. In addition, at least a part of the functions of the information processing device 10 described above may be implemented in the user terminal 20.

[0057] [Software implementation example] The functions of the information processing device 10 and the user terminal 20 (hereinafter referred to as the "device") can be realized by a program for causing a computer to function as the device, and a program for causing a computer to function as each control block of the device (particularly each part included in the control units 110, 210).

[0058] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. The control device and storage device execute the program to realize each function described in each of the above embodiments.

[0059] The program may be non-transitory and may be recorded in one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be provided to the device via any wired or wireless transmission medium.

[0060] In addition, some or all of the functions of each of the control blocks can be realized by a logic circuit. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of each of the control blocks can be realized by, for example, a quantum computer.

[0061] Furthermore, each process described in each of the above embodiments may be executed by AI (Artificial Intelligence). In this case, the AI ​​may be executed by the control device or another device (for example, an edge computer or a cloud server).

[0062] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention.

[0063] [summary] An information processing device according to aspect 1 of the present invention includes a classification unit that classifies consumer behavior data indicating a consumer's consumption behavior history and attributes of the consumer into a plurality of segments, a prompt generation unit that generates a prompt for generating a persona symbolizing at least a portion of the plurality of segments based on the consumption behavior data belonging to the segment and consumer characteristics identified from the consumption behavior data, and a persona generation unit that generates a persona corresponding to the segment by inputting the prompt into a generation model.

[0064] According to the above aspect, a persona can be generated that mimics the actual consumption behavior of a consumer.

[0065] An information processing device according to aspect 2 of the present invention is an information processing device as described in aspect 1 above, wherein the prompt generation unit extracts from the plurality of segments those segments whose degree of focus as a target identified for each of the plurality of segments satisfies a predetermined condition, and generates the prompt for each of the extracted segments.

[0066] According to the above aspect, personas can be categorized not simply by age group or characteristics, but also by the level of focus they deserve as targets.

[0067] An information processing device according to aspect 3 of the present invention is an information processing device according to aspect 1 or 2 above, wherein the prompt generation unit identifies consumer characteristics for at least some of the segments included in the plurality of segments using consumption behavior data belonging to the segment, and generates the prompt based on the identified characteristics.

[0068] According to the above aspect, for each of a plurality of segments obtained by classifying consumption behavior data, a persona can be generated that reflects the consumption behavior data belonging to each segment and the characteristics of consumers identified from the consumption behavior data.

[0069] An information processing device according to a fourth aspect of the present invention is the information processing device according to any one of the first to third aspects, wherein the characteristics of the consumer include information indicating a tendency of the consumer's consumption behavior.

[0070] According to the above aspect, a persona that reflects the consumer consumption behavior trends identified from the consumer consumption behavior history can be generated for each of multiple segments obtained by classifying consumption behavior data.

[0071] An information processing device according to aspect 5 of the present invention is an information processing device according to any one of aspects 1 to 4 above, wherein the prompt generation unit generates, for at least a portion of the segments included in the plurality of segments, target image definition data representing a consumer image symbolizing the segment based on consumer behavior data belonging to the segment and consumer characteristics identified from the consumer behavior data, and converts the generated target image definition data into the prompt in text format.

[0072] According to the above aspect, for each of a plurality of segments obtained by classifying consumption behavior data, a persona can be generated that reflects the consumption behavior data belonging to each segment and the characteristics of consumers identified from the consumption behavior data.

[0073] An information processing device according to a sixth aspect of the present invention is an information processing device as described in the fifth aspect above, in which the prompt generation unit generates target image definition data for each of at least some of the segments included in the plurality of segments, the target image definition data including data representing characteristics of consumers identified from consumption behavior data belonging to the segment.

[0074] According to the above aspect, for each of a plurality of segments obtained by classifying consumption behavior data, a persona can be generated that reflects the consumption behavior data belonging to each segment and the characteristics of consumers identified from the consumption behavior data.

[0075] An information processing device according to a seventh aspect of the present invention is an information processing device according to any one of the first to sixth aspects above, wherein the prompt generation unit generates a prompt for at least a portion of the segments included in the plurality of segments based on consumption behavior data belonging to the segment, consumer characteristics identified from the consumption behavior data, and collected data corresponding to the consumption behavior data belonging to the segment stored in a memory unit that stores collected data related to consumers or services provided to consumers.

[0076] According to the above aspect, for each of the multiple segments obtained by classifying consumer behavior data, a persona can be generated that reflects not only the consumer behavior data but also information from collected data collected about consumers or services provided to consumers.

[0077] An information processing method according to aspect 8 of the present invention includes a classification process in which at least one processor classifies consumption behavior data indicating a consumer's consumption behavior history and attributes of the consumer into a plurality of segments; a prompt generation process in which the at least one processor generates a prompt for generating a persona symbolizing at least a portion of the plurality of segments based on the consumption behavior data belonging to the segment and consumer characteristics identified from the consumption behavior data; and a persona generation process in which the at least one processor generates a persona corresponding to the segment by inputting the prompt into a generative model.

[0078] According to the above aspect, a persona can be generated that mimics the actual consumption behavior of a consumer.

[0079] An information processing device according to a ninth aspect of the present invention is an information processing device described in any one of the first to seventh aspects above, wherein the persona generation unit receives speech data representing the content of a user's utterance to the persona from a user terminal, generates a response to the user's utterance by inputting the utterance data into the generative model, and transmits the generated response to the user terminal.

[0080] According to the above aspect, a user can use a user terminal to have a dialogue with a persona that mimics the actual consumption behavior of a consumer.

[0081] A program relating to aspect 10 of the present invention is a program for causing a computer to function as an information processing device relating to any one of aspects 1 to 7, and 9, and causes the computer to function as the classification unit, the prompt generation unit, and the persona generation unit.

[0082] According to the above aspect, a persona can be generated that mimics the actual consumption behavior of a consumer.

[0083] An information processing system of aspect 11 of the present invention comprises an information processing device described in aspect 9 and the user terminal, wherein the user terminal comprises an utterance data transmission unit that transmits the utterance data to the information processing device, and an output control unit that receives the response from the information processing device and outputs the received response to an output device.

[0084] According to the above aspect, a persona can be generated that mimics the actual consumption behavior of a consumer. [Explanation of symbols]

[0085] 1 System 10. Information processing device 11 Classification section 12 Prompt Generation 13 Content Generation Division 20 User terminal 21 Application execution unit 110, 210 Control unit 120, 220 storage section 130, 230 Communications Department 140, 240 Input section 150, 250 Output section

Claims

1. A classification unit that classifies consumer behavior data indicating a consumer's consumption behavior history and attributes of the consumer into a plurality of segments; a prompt generation unit that generates, for each of at least some of the segments included in the plurality of segments, a prompt for generating a persona representing the segment based on consumer behavior data belonging to the segment and consumer characteristics identified from the consumer behavior data; a persona generation unit that generates a persona corresponding to the segment by inputting the prompt into a generative model; Equipped with the prompt generation unit extracts, from the plurality of segments, segments whose respective degrees of focus as targets specified for the plurality of segments satisfy a predetermined condition, and generates the prompt for each of the extracted segments. Information processing device.

2. The prompt generation unit is Identifying consumer characteristics for each of at least some of the segments included in the plurality of segments using consumer behavior data belonging to the segment; generating the prompt based on the identified characteristics; The information processing device according to claim 1 .

3. The characteristics of the consumer include information indicating the consumer's consumption behavior tendency.

3. The information processing device according to claim 1 or 2.

4. The prompt generation unit is generating target profile definition data representing a consumer profile representative of each of at least some of the segments included in the plurality of segments, based on consumer behavior data belonging to the segment and consumer characteristics identified from the consumer behavior data; converting the generated target image definition data into said prompt in text form; 3. The information processing device according to claim 1 or 2.

5. the prompt generation unit generates target profile definition data for each of at least some of the segments, the target profile definition data including data representing characteristics of consumers identified from the consumption behavior data belonging to the segment; The information processing device according to claim 4.

6. the prompt generation unit generates a prompt for each of at least some of the segments included in the plurality of segments based on consumption behavior data belonging to the segment, consumer characteristics identified from the consumption behavior data, and collected data corresponding to the consumption behavior data belonging to the segment, the collected data being stored in a storage unit that stores collected data relating to consumers or services provided to consumers; 3. The information processing device according to claim 1 or 2.

7. A classification process in which at least one processor classifies consumer behavior data indicating a consumer's consumption behavior history and attributes of the consumer into a plurality of segments; a prompt generation process in which the at least one processor generates, for each of at least some of the segments included in the plurality of segments, a prompt for generating a persona representing the segment based on consumer behavior data belonging to the segment and consumer characteristics identified from the consumer behavior data; a persona generation process in which the at least one processor generates a persona corresponding to the segment by inputting the prompt into a generative model; Including, In the prompt generation process, the at least one processor extracts, from the plurality of segments, segments whose degree of focus as a target specified for each of the plurality of segments satisfies a predetermined condition, and generates the prompt for each of the extracted segments. Information processing methods.

8. The persona generation unit includes: receiving, from a user terminal, speech data representing the content of a user's speech to the persona; generating a response to the user's utterance by inputting the utterance data into the generative model; Transmitting the generated response to the user terminal; 3. The information processing device according to claim 1 or 2.

9. 3. A program for causing a computer to function as the information processing device according to claim 1, the program causing the computer to function as the classification unit, the prompt generation unit, and the persona generation unit.

10. An information processing device according to claim 8 and the user terminal, The user terminal, a speech data transmission unit that transmits the speech data to the information processing device; an output control unit that receives the response from the information processing device and outputs the received response to an output device; Information processing system.

Images