Dialogue support system, dialogue support method, and program

Abstract

To easily increase variations of attributes of a dialogue partner and to support dialogue in accordance with the attributes of the dialogue partner.SOLUTION: A dialogue support system of one aspect of the present disclosure includes: a receiving unit for receiving persona information indicating a persona that characterizes a dialogue partner of a user; a persona generation unit for generating a persona generation prompt indicating features of the persona by using a large-scale language model on the basis of the persona information received by the receiving unit; and a dialogue control unit for controlling an avatar corresponding to the persona on the basis of the persona generation prompt generated by the persona generation unit and controlling dialogue between the avatar and the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a dialogue support system, a dialogue support method, and a program. [Background technology]

[0002] Conventionally, a technology for supporting dialogue with a user is known, for example, as described in Patent Document 1. Patent Document 1 describes a training system that implements a communication AI and supports the education of professionals who require conversation skills. The training system includes a processor configured to acquire utterances from students, analyze the content of the acquired utterances from the students, create the next utterance content for the students based on the analyzed utterance content, and synthesize a voice representing the utterance content. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-014188 Summary of the Invention [Problem to be solved by the invention]

[0004] The dialogue partners, scenes, and situations desired by users are expected to vary depending on the user's purpose, but the training system described in Patent Document 1 has the problem that it is difficult to change the dialogue content according to the attributes of the dialogue partner, scene, and situation. In particular, because it is an existing role-playing system, it is difficult to increase the variety or to make the role-playing realistic.

[0005] The present disclosure has been made in consideration of the above circumstances, and aims to provide a dialogue support system, a dialogue support method, and a program that can easily increase the variety of attributes of dialogue partners and support dialogue according to the attributes of the dialogue partners. [Means for solving the problem]

[0006] The present disclosure has been made to solve the above-mentioned problems, and one aspect of the present disclosure is a dialogue support system comprising: a reception unit that receives persona information indicating a persona that characterizes a user's dialogue partner; a persona generation unit that generates a persona generation prompt that indicates the characteristics of the persona using a large-scale language model based on the persona information received by the reception unit; and a dialogue control unit that controls an avatar corresponding to the persona based on the persona generation prompt generated by the persona generation unit, and controls a dialogue between the avatar and the user.

[0007] Another aspect of the present disclosure is a dialogue support method including the steps of: a server device receiving persona information indicating a persona that characterizes a user's dialogue partner; the server device generating a persona generation prompt indicating characteristics of the persona based on the persona information using a large-scale language model; and the server device controlling an avatar corresponding to the persona based on the persona generation prompt, and controlling a dialogue between the avatar and the user.

[0008] Another aspect of the present disclosure is a program that causes a computer of a server device to perform the following steps: receiving persona information indicating a persona that characterizes a user's interaction partner; generating a persona generation prompt that indicates characteristics of the persona based on the persona information using a large-scale language model; and controlling an avatar corresponding to the persona based on the persona generation prompt, and controlling an interaction between the avatar and the user. [Effects of the Invention]

[0009] According to one aspect of the present invention, it is possible to easily increase the variety of attributes of conversation partners for role-playing, and to realize role-playing according to the attributes of the conversation partners. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing an example of the configuration of a dialogue support system 1 according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an outline of processing performed by the dialogue support system 1 according to the embodiment. [Figure 3] 4 is a flowchart showing an example of a processing procedure of the dialogue support system 1 according to the embodiment. [Figure 4] 10 is a diagram illustrating an example of customer-defined information including a variable name and a character string according to an embodiment. FIG. [Figure 5] FIG. 10 is a diagram illustrating an example of a persona generation prompt according to an embodiment. [Figure 6] FIG. 10 is a diagram illustrating an example of variables created from a persona generation prompt in the embodiment. [Figure 7] FIG. 10 is a diagram illustrating an example of a persona designation prompt according to an embodiment. [Figure 8] FIG. 10 is a diagram showing an example of persona designation information in the embodiment. [Figure 9] FIG. 10 is a diagram illustrating an example of an evaluation prompt according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] A dialogue support system, a dialogue support method, and a program to which the present invention is applied will be described below with reference to the drawings.

[0012] FIG. 1 is a block diagram showing an example of the configuration of a dialogue support system 1 according to an embodiment. A dialogue support system 1 according to an embodiment supports a dialogue between a user and an avatar characterized by a specific persona. The dialogue support system 1 generates a persona based on information specified by the user, and controls an avatar corresponding to the generated persona, allowing the user and the avatar to engage in role-playing. Role-playing is, for example, training new employees, sales training, language training, communication training, etc., with the user and a pseudo-avatar as conversation partners. Role-playing according to an embodiment also includes those between people of different nationalities or places of origin.

[0013] The dialogue support system 1 includes, for example, a processing server device 100, a generation server device 200, and a user terminal device 300. The processing server device 100, the generation server device 200, and the user terminal device 300 are communicatively connected via a network NW such as the Internet. The processing server device 100, the generation server device 200, and the user terminal device 300 may be connected via either wired or wireless communication, and may include a general-purpose network such as the Internet, or a private network such as local 5G or WiFi (registered trademark). The processing server device 100, the generation server device 200, and the user terminal device 300 may have a communication interface, such as a network interface card (NIC) or a wireless communication module for connecting to a network, to exchange information with each other.

[0014] The user terminal device 300 is, for example, an information processing device operated by a user who interacts with an avatar. The user terminal device 300 includes, for example, a speaker, a microphone, a display device, an operation unit, and a processing unit such as a CPU.

[0015] The processing server device 100 is, for example, a server device that includes a processor that performs processing in response to requests received from the generation server device 200 and the user terminal device 300 and transmits processing results to the generation server device 200 and the user terminal device 300. The processing server device 100 includes, for example, a customer generation unit 110, a dialogue control unit 120, an operation control unit 130, and a storage unit 140. The customer generation unit 110, the dialogue control unit 120, and the operation control unit 130 are functional units realized by, for example, an information processing circuit that performs various processes by causing a central processing unit (CPU) to execute a program. Furthermore, some or all of these functional units may be realized by hardware such as a large-scale integration (LSI), an application-specific integrated circuit (ASIC), or a field-programmable gate array (FPGA), or may be realized by a combination of software and hardware. The storage unit 140 is realized by, for example, a hard disk drive (HDD), a solid state drive (SSD), a flash memory, an electrically erasable programmable read-only memory (EEPROM), a read-only memory (ROM), or a random access memory (RAM), or a hybrid storage device using a combination of these. Part or all of the storage unit 140 may be realized by an external storage device accessible via various networks. An example of an external storage device is a network attached storage (NAS) device.

[0016] The customer generation unit 110 generates customer information. The customer information is information indicating a customer envisioned by the user. The customer corresponds to, for example, an avatar that will be the user's conversation partner in a role-play. The customer generation unit 110 includes, for example, a reception unit 111 and a customer definition unit 112. The reception unit 111 receives persona information based on information received from the user terminal device 300. The persona information is customer definition information indicating a persona that characterizes the customer (conversation partner) for the user. The persona may be a virtual character image, or a character image based on information about a real person. Furthermore, the persona information may be information based in part on information about a real person, or information about a person who has already passed away. The customer definition unit 112 generates customer information based on the persona information received by the reception unit 111.

[0017] The dialogue control unit 120 controls an avatar corresponding to a persona based on the persona generation prompt generated by the persona generation unit 211, and performs processing to control a dialogue between the avatar and a user. The dialogue control unit 120 includes, for example, an utterance acquisition unit 121, an emotion parameter processing unit 122, a response prompt generation unit 123, a response text conversion unit 124, and a conversation history generation unit 125. The utterance acquisition unit 121 acquires utterance information indicating the user's utterance input from the user terminal device 300, and converts the acquired utterance information into text data. Emotion parameter processing unit 122 performs processing to set and update emotion parameters. Emotion parameters are numerical values ​​that indicate the emotion of an avatar (customer). Emotion parameters are information that expresses emotions such as joy, anger, sadness, enjoyment, confidence, confusion, and fear on a scale of 1 to 5. Note that, although the present embodiment describes a configuration related to the emotion of the customer, such as emotion parameter processing unit 122, the present invention is not limited to this, and the configuration related to the emotion of the customer may not be provided. The response prompt generation unit 123 generates a response prompt including text data of the user's voice and emotion parameters, and transmits the generated response prompt to the generation server device 200. The response text conversion unit 124 converts the response text acquired from the generation server device 200 into voice data. The conversation history generating unit 125 generates history information indicating the history of conversations between the user and the avatar.

[0018] The movement control unit 130 performs processing to control the movement of the avatar. The movement control unit 130 includes, for example, an avatar generation unit 131, a voice generation unit 132, a voice information processing unit 133, a motion processing unit 134, an emote processing unit 135, and a lip sync processing unit 136. The avatar generation unit 131 generates an avatar. The avatar generation unit 131 creates component information representing content for displaying an avatar based on, for example, an image showing the appearance of a customer.

[0019] The voice generation unit 132 generates voice data to be output to the user. For example, the voice generation unit 132 generates voice data that reproduces the customer's actual voice reading. When the persona information includes nationality, place of origin, or region, the voice generation unit 132 may generate voice data in a language corresponding to the nationality or place of origin based on the persona generation prompt generated by the persona generation unit 211.

[0020] The voice timbre information processing unit 133 processes the voice data based on voice timbre information corresponding to the emotion parameters. When nationality, birthplace, or region is included as persona information, the voice timbre information processing unit 133 may process the voice data generated by the voice generation unit 132 based on the nationality or birthplace included in the persona information. The voice timbre information processing unit 133 may process the voice data to reflect, for example, the tone of voice (e.g., speaking speed), the pitch of the voice, or the tone of the voice. The voice timbre information processing unit 133 may also process the voice data to reflect dialects and intonations according to differences in nationality or birthplace.

[0021] The element data for generating the voice may include a plurality of element data corresponding to each of a plurality of languages. The voice generation unit 132 selects one of the plurality of languages ​​based on the nationality or place of origin included in the persona information and generates voice data in the selected language. As a result, the voice generation unit 132 generates voice data using synthesized voice data corresponding to each of the multiple languages.

[0022] The motion processing unit 134 controls the motion of the avatar based on the emotion parameters and the content of the response text. The motion of the avatar represents, for example, the movement of the entire avatar or the movement of the avatar's hands. The emotion processor 135 controls the facial expression of the avatar based on the emotion parameters and the content of the response text, for example, by controlling the movements of the avatar's eyes, eyebrows, mouth, and the like. Lip sync processor 136 controls the movement of the avatar's lips based on the emotion parameters and the content of the response text.

[0023] The storage unit 140 stores, for example, customer information 141, response information 142, voice information 143, and action information 144. The customer information 141 includes, for example, persona information, utterance information, a persona generation prompt, and a persona designation prompt. The persona generation prompt is detailed information for generating a persona. The persona designation prompt is information indicating a persona that is designated when a user and an avatar actually have a dialogue, such as a role-play. The response information 142 includes, for example, user voice text and response text, but may also include initial emotional parameter values ​​and current emotional parameter values. The voice information 143 includes, for example, voice data such as user voice and response voice, and tone of voice information, but may also include emotional parameters. The action information 144 includes, for example, emotional parameters, component information, motion information, emote information, and lip-sync information. The motion information is a default value representing the avatar's motion, the emote information is a default value representing the avatar's emote, and the lip-sync information is a default value representing the avatar's lip-sync.

[0024] The generation server device 200 is, for example, a server device that performs processing in response to a request received from the processing server device 100 and transmits the processing results. The generation server device 200 includes, for example, a generation unit 210, a storage unit 220, an evaluation unit 230, and an LLM learning unit 240. The generation unit 210, the evaluation unit 230, and the LLM learning unit 240 are functional units realized by, for example, an information processing circuit that performs various processes by causing a CPU to execute a program. The storage unit 220 is realized, for example, by a recording device such as an HDD or SSD, or a hybrid storage device using a plurality of these, and may also be realized by an external storage device accessible via various networks, such as a NAS device.

[0025] The generation unit 210 includes, for example, a persona generation unit 211, a response text generation unit 212, an emotion parameter generation unit 213, and a unique information acquisition unit 214. The persona generation unit 211 inputs persona information acquired from the processing server device 100 into a first large-scale language model and generates a persona generation prompt based on the output of the first large-scale language model. The persona information may be existing items including the persona's gender, age, personality, place of origin (including within the country), speaking style, tone, or dialect. The first large-scale language model may also include at least one of items specified based on user operation, items related to customer characteristics in a specific industry, and items related to customer characteristics in a specific generation. The first large-scale language model learns persona information including existing items such as the persona's gender, age, personality, place of origin (including domestic), speaking style, tone of voice, or dialect, items specified based on user operation, items related to the characteristics of customers in a specific industry, and items related to the characteristics of customers in a specific generation, as well as a persona generation prompt as learning data, and is configured to output a persona generation prompt when at least one of persona information including existing items such as the persona's gender, age, personality, place of origin (including domestic), speaking style, tone of voice, or dialect, items specified based on user operation, items related to the characteristics of customers in a specific industry, and items related to the characteristics of customers in a specific generation is input.

[0026] The persona generation unit 211 may input persona information and information about a specific field into the first large-scale language model and create a persona generation prompt that indicates the characteristics of a persona corresponding to the specific field based on the output of the first large-scale language model. The information about the specific field is various information about the field that will be a topic of conversation. The information about the specific field may be, for example, customer characteristic information such as customer issues related to product purchases that are empirically assumed for a specific industry, a specific generation, a specific nationality, or a specific place of origin. The information about the specific field is acquired as specific information by the specific information acquisition unit 214. The specific field may be a field, industry, task, etc. in which the user wants to improve.

[0027] The persona information includes nationality or place of origin, and the persona generation unit 211 may input existing items including the persona's nationality or place of origin as persona information into a persona generation prompt (first large-scale language model) and create a persona generation prompt based on the output of the persona generation prompt.

[0028] The response text generation unit 212 generates a response text from the response prompt generated by the response prompt generation unit 123, the conversation history generated by the conversation history generation unit 125, and the unique information acquired by the unique information acquisition unit 214. The response text generation unit 212, for example, inputs the response prompt, the conversation history between the user and the avatar, and the unique information into a second large-scale language model, and generates a response text based on the second large-scale language model. Note that the response text generation unit 212 may extract contextual information of the conversation and generate a response text based on the contextual information in addition to the response prompt, the conversation history, and the unique information. The first large-scale language model is, for example, a large-scale language model (LLM) using a neural network. The second large-scale language model may be the same LLM as the first large-scale language model, or they may be different LLMs.

[0029] Emotion parameter generation section 213 generates or updates emotion parameters according to the content of the generated response text. The unique information acquisition unit 214 acquires unique information that is information unique to a dialogue such as a role play. The unique information is acquired from, for example, a storage device that stores customer characteristic information, specific field information, specific industry information, specific generation information, and specific region information (both domestic and international), which are not shown.

[0030] The storage unit 220 includes, for example, specific information 221 and LLM information 222. The unique information 221 includes customer characteristic information, specific field information, specific industry information, specific generational information, and information on specific countries and regions. Customer characteristic information is information that indicates the characteristics of the customer who is interacting with the user. Customer characteristic information is information such as age, gender, occupation, speaking style, tone of voice, personality, nationality, and place of origin. Specific field information is information that indicates the field of the interaction between the user and the customer. Specific industry information is information that indicates the industry of the interaction between the user and the customer. Specific generational information is information that indicates the generation of the customer. The LLM information 222 is parameter information of an LLM (first large-scale language model) for generating a persona-generating prompt. The LLM information 222 may include parameter information of an LLM that generates a persona-specifying prompt based on a persona-generating prompt. The LLM for generating a persona-generating prompt is a machine learning model trained using past data of persona-generating prompts and persona-specifying prompts as training data, and is configured to output a persona-specifying prompt when a persona-generating prompt is input. The LLM information 222 may include parameter information of an LLM (second large-scale language model) for generating a response text based on a persona-specified prompt. The LLM for generating a response text is a machine learning model trained using past data of persona-specified prompts and response texts as training data, and is configured to output a response text when a persona-specified prompt is input. The LLM information 222 may include parameter information for an LLM that generates an evaluation prompt based on a conversation history. The LLM that generates the evaluation prompt is a machine learning model trained using past data of the conversation history and evaluation prompts as training data, and is configured to output an evaluation prompt when the conversation history is input. In addition, the LLM for generating persona generation prompts, the LLM for generating persona specification prompts, the LLM for generating response text, and the LLM for generating evaluation prompts may be a single LLM or may be different LLMs.

[0031] The LLM training unit 240 performs a process of training an LLM (first large-scale language model) for generating persona-generating prompts and an LLM (second language model) for generating response texts. The LLM training unit 240 may also train an LLM for generating persona-specifying prompts and an LLM for generating evaluation prompts.

[0032] In the embodiment, as shown in Figure 1, the dialogue support system 1 distributes the functional configuration (functional units) between the processing server device 100 and the generation server device 200, but this is not limited to this and the functional units may be distributed in other configurations, the functional units of the processing server device 100 and the generation server device 200 may be consolidated into one device, multiple functional units may be combined into one functional unit, or one function may be distributed among multiple functional units.

[0033] FIG. 2 is a diagram illustrating an outline of the processing performed by the dialogue support system 1 according to the embodiment. The reception unit 111 and the customer definition unit 112 generate customer-defined information D10 and transmit it to the generation server device 200. The persona generation unit 211 inputs the customer-defined information D10 to a persona generation LLM (P10) and generates a persona generation prompt D12 based on the output of the persona generation LLM (P10). The persona generation LLM (P10) is configured to, for example, perform learning using past data of the customer-defined information and the persona generation prompt as learning data, and output the persona generation prompt D12 when the customer-defined information D10 is input. The persona generation unit 211 generates a persona-specifying prompt D14 when the user performs role-playing. The persona-specifying prompt D14 is output to the response text generation LLM.

[0034] The generation server device 200 acquires unique information D20, such as a specific field for role-playing, and processes the unique information D20 in the following order: text extraction processing P20, chunk division processing P21, and vectorization processing P22. The processing server device 100 then performs speech recognition processing P40 on the user's speech acquired from the user terminal device 300, and vectorization processing P41 on the text information processed by the speech recognition processing P40. A reference result to the vector database is extracted from the vector database using the vector corresponding to the speech as a query. The vectorized unique information D20 and the text information processed by the speech recognition processing P40 are output to the response text generation LLM (P30) along with a persona-specifying prompt D14.

[0035] The generation server device 200 inputs the persona specification prompt D14, unique information D20, and text information processed by speech recognition processing P40 into the response text generation LLM (P30), performs speech synthesis processing P31 on the response text output from the response text generation LLM (P30), and performs avatar control processing P32 based on the emotion parameters output from the response text generation LLM (P30), thereby transmitting avatar content D30 to the user terminal device 300. This allows the user terminal device 300 to display or output sound using avatar content D30.

[0036] FIG. 3 is a flowchart showing an example of a processing procedure of the dialogue support system 1 according to the embodiment. First, the processing server device 100 inputs user information about the user who will be interacting with the avatar (step S100). The user information is, for example, character string data that characterizes the user, such as a new employee, a sales manager, a specific nationality, or a place of origin. Next, the processing server device 100 defines the customer that the user is considering (step S102). At this time, the processing server device 100 receives persona information indicating a persona that characterizes the user's interaction partner from the user terminal device 300 via the reception unit 111, and stores the persona information as a variable, for example, as shown in FIG. 4. 4 is a diagram showing an example of customer-defined information including a variable name and a character string in an embodiment. The receiving unit 111 determines whether there is further input (step S104), and if there is input, repeats the processing of step S102, or if there is no input, confirms the customer-defined information. The processing server device 100 transmits the customer-defined information to the generation server device 200.

[0037] The persona generation unit 211 inputs the customer-defined information and the unique information stored in the storage unit 220 into the persona generation LLM, and generates a persona generation prompt based on the output of the persona generation LLM (step S106). FIG. 5 is a diagram illustrating an example of a persona generation prompt according to an embodiment. The persona generation prompt includes, for example, text data indicating the customer's prerequisites, the customer's speaking style, and the customer's personality traits. The customer prerequisites include, for example, items corresponding to role-playing, such as age, gender, occupation, family structure, residential area, nationality, birthplace, and insurance information. If the customer prerequisites include, for example, a birthplace of Osaka, a prompt corresponding to the Kansai dialect can be created as a persona generation prompt. It is also possible to control the tone of voice or dialect depending on the residential area. Furthermore, by setting, for example, a birthplace of California as a prerequisite for the customer, a persona generation prompt can be created that can recreate a person who is strongly influenced by California culture. The customer's speaking style may be, for example, first person, second person, catchphrases, interjections, dialect, etc. The customer's personality traits may be, for example, neuroticism, extroversion, openness, conscientiousness, cooperativeness, etc. The persona generation unit 211 determines whether or not there is input for other items from the user terminal device 300 (step S108), and if input is received, repeats the processing of step S106, or if no input is received, confirms the persona generation prompt. The persona generation unit 211 stores the created persona generation prompt in the storage unit 220 as a variable. 6 is a diagram showing an example of variables created from a persona generation prompt in an embodiment. The variables created from the persona generation prompt are information predicted based on the output of the persona generation LLM after inputting customer-defined information into the persona generation LLM.

[0038] The persona generation unit 211 may input existing items including at least one of the persona's gender, age, personality, place of origin (including within the country), speaking style, tone, and dialect as persona information (customer-defined information) into a persona generation LLM (first large-scale language model), and may further input at least one of items specified based on user operation, items related to customer characteristics in a specific industry, and items related to customer characteristics in a specific generation into the persona generation LLM, and create a persona generation prompt based on the output of the persona generation LLM. Note that the persona generation unit 211 may input existing items including the persona's speaking style in addition to the persona's gender, age, and personality into the persona generation LLM. In this way, the persona generation unit 211 realizes Retrieval-Augmented Generation (RAG) by inputting various information into the persona generation LLM, and can create highly accurate persona generation prompts that meet the user's requirements.

[0039] The persona generation unit 211 may input items related to issues customers have with respect to a specific product into a persona generation LLM (first large-scale language model) and create persona generation prompts based on the output of the persona generation LLM. This persona generation LLM is a machine learning model that is trained, for example, using information related to issues customers have with respect to a specific product and past data of persona generation prompts as learning data, and is configured to output a persona generation prompt when an item related to issues customers have with respect to a specific product is input. The item related to issues customers have with respect to a specific product is information empirically assumed in a specific field or industry, or information such as customer issues related to product purchases assumed based on market analysis and survey results. The item related to issues customers have with respect to a specific product may be added or modified as a variable by the user. Furthermore, the persona generation unit 211 may input existing items including the persona's nationality or birthplace as persona information into a persona generation LLM (first large-scale language model), and create a persona generation prompt based on the output of the persona generation LLM. This persona generation LLM is configured to learn past data of existing items including the persona's nationality or birthplace and persona generation prompts as learning data, and to output a persona generation prompt when an existing item including the persona's nationality or birthplace is input.

[0040] Next, the persona generation unit 211 creates a persona specification prompt (step S110). FIG. 7 is a diagram showing an example of a persona specification prompt in an embodiment. The persona generation unit 211 may input a variable corresponding to the persona generation prompt into the LLM and create the persona specification prompt based on the output of the LLM. The variable corresponding to the persona generation prompt may be a variable selected based on a user operation, or may be a variable extracted from the persona generation prompt randomly or according to a predetermined rule. The persona generation unit 211 transmits persona specification information such as that shown in FIG. 8 to the processing server device 100 based on the persona specification prompt. FIG. 8 is a diagram showing an example of persona specification information in an embodiment.

[0041] Next, the dialogue control unit 120 controls an avatar corresponding to the persona based on the persona designation information, and controls the dialogue between the avatar and the user (step S112). As a result, the dialogue control unit 120 performs role-playing through dialogue between the user and the avatar. The utterance acquisition unit 121 acquires utterance information indicating the user's utterances, and the conversation history generation unit 125 stores the conversation history (step S114).

[0042] Next, the processing server device 100 determines whether or not to evaluate the user (step S116). If the processing server device 100 does not evaluate the user, it repeats the processes of steps S112 and S114. If the processing server device 100 detects, for example, a user utterance such as "evaluate the role-play," it determines to evaluate the user and transmits the conversation history to the generation server device 200.

[0043] The timing for evaluating the user (role play) may be at the end of the role play (such as a business negotiation) to evaluate the entire role play, but is not limited to this and may be for each rally (each round of conversation) during the role play. The processing server device 100 allows the user to select either a comprehensive evaluation (end evaluation) or an evaluation on an individual basis, for example, at the start of the role play. The comprehensive evaluation is a process of evaluating the entire conversation history, while the evaluation on an individual basis is a process of evaluating each rally during the conversation (including a pair of a take and a reply). When the comprehensive evaluation is selected, the processing server device 100 transmits the conversation history to the generation server device 200 when it detects a user utterance such as "evaluate the role play." When the evaluation on an individual basis is selected, the processing server device 100 transmits the conversation history for one rally to the generation server device 200 when it detects a break in the rally during the conversation. The generation server device 200 stores the results of the on-the-fly evaluation based on the conversation history for one rally in the storage unit 220, and transmits one or more on-the-fly evaluation results to the processing server device 100 when the role-play ends. This allows the on-the-fly evaluation results to be presented to the user.

[0044] Furthermore, both evaluation of the entire role-play (such as a business negotiation) and evaluation of each conversation rally (each round of conversation) during the role-play may be performed simultaneously. For example, at the start of a role-play, the processing server device 100 allows the user to select whether to perform both an overall evaluation and an individual evaluation. The processing server device 100 transmits a conversation history for one rally to the generation server device 200 upon detecting a break in a conversation, and further transmits the conversation history to the generation server device 200 upon detecting a user utterance of "evaluate the role-play." The generation server device 200 stores the results of the individual evaluation based on the conversation history for one rally in the storage unit 220. When the role-play ends, the generation server device 200 transmits the results of the overall evaluation and one or more individual evaluations to the processing server device 100. This allows the overall evaluation result and the individual evaluation results to be presented to the user on the same screen.

[0045] The evaluation unit 230 evaluates the user based on the utterance information acquired by the utterance acquisition unit 121 (step S118). At this time, the evaluation unit 230 generates an evaluation prompt based on the conversation history acquired from the processing server device 100. The evaluation unit 230 may input the conversation history to an LLM that generates an evaluation prompt, and generate the evaluation prompt based on the output of the LLM. For example, when a user explains a product in a role-play, the evaluation unit 230 may input the conversation history and information stored in a product information database to an LLM that generates an evaluation prompt, and generate the evaluation prompt based on the output of the LLM that generates the evaluation prompt. Figure 9 is a diagram showing an example of an evaluation prompt in an embodiment. The evaluation prompt includes, for example, evaluation items, evaluation criteria, evaluation points, customer understanding evaluation, product knowledge evaluation, and communication evaluation for conversations for sales activities.

[0046] The receiving unit 111 may receive purpose of use information indicating the purpose of use for the user to interact with the avatar, and the evaluation unit 230 may evaluate the user based on evaluation items set according to the purpose of use. The evaluation unit 230 may, for example, input the purpose of use information to an LLM that generates an evaluation prompt, and generate an evaluation prompt including an evaluation for the purpose of use.

[0047] The evaluation unit 230 may acquire user speech information and avatar speech information using the speech acquisition unit 121. The evaluation items may include at least one of the customer's level of understanding based on the user's speech information and the avatar's speech information, the accuracy of product knowledge, the accuracy of specialized knowledge, and communication ability. The evaluation items may be, for example, evaluations based on evaluation criteria for each individual company (individual company evaluations). Examples of individual company evaluations include whether a mobile phone dealer is able to suggest switching to a more advantageous plan (such as a family plan) based on customer information, whether a car dealer is able to suggest three or more types of estimates, and whether an insurance dealer is able to make a next appointment and close the deal.

[0048] The evaluation unit 230 outputs evaluation information to the processing server device 100 as a result of evaluating the user's conversation based on the evaluation prompt (step S120). As a result, the processing server device 100 transmits the evaluation information to the user terminal device 300, and the user terminal device 300 can present the evaluation to the user.

[0049] As described above, the dialogue support system 1 of the embodiment accepts persona information indicating a persona that characterizes a dialogue partner of a user, generates a persona generation prompt indicating the characteristics of the persona using a first large-scale language model based on the persona information, controls an avatar corresponding to the persona based on the persona generation prompt generated by the persona generation unit, and controls a dialogue between the avatar and the user. With this dialogue support system 1, if persona information is input based on, for example, a user's operation, the persona generation prompt can be generated using the first large-scale language model, making it possible to easily increase the variety of attributes of dialogue partners for role-playing and realize role-playing that matches the attributes of the dialogue partner.

[0050] The functions of the processing server device 100, the generation server device 200, and the user terminal device 300 in the above-described embodiments may be implemented by a computer. In this case, a program for implementing the functions may be recorded on a computer-readable recording medium, and the program may be loaded into a computer system and executed. Note that the term "computer system" as used herein includes hardware such as an operating system and peripheral devices. Furthermore, the term "computer-readable recording medium" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, as well as storage devices such as hard disks built into a computer system. Furthermore, the term "computer-readable recording medium" may also include devices that dynamically store programs for a short period of time, such as communication lines used when transmitting programs via networks such as the Internet or telephone lines, or devices that store programs for a fixed period of time, such as volatile memory within the computer system serving as the server or client. The program may be designed to implement only a portion of the above-described functions, or may be capable of implementing the above-described functions in combination with a program already stored in the computer system, or may be implemented using a programmable logic device such as an FPGA (Field Programmable Gate Array).

[0051] Although each embodiment and variant example has been described, these are merely examples and are not intended to limit the scope of the present invention. For example, one of the embodiments or variant examples, or a part of each embodiment or a part of each variant example, may be combined with one or more other embodiments or one or more other variant examples to realize one aspect of the present invention. [Explanation of symbols]

[0052] 1...dialogue support system, 100...processing server device, 110...customer generation unit, 111...reception unit, 112...customer definition unit, 120...dialogue control unit, 121...utterance acquisition unit, 122...emotion parameter processing unit, 123...response prompt generation unit, 124...response text conversion unit, 125...conversation history generation unit, 130...motion control unit, 131...avatar generation unit, 132...voice generation unit, 133...voice tone information processing unit, 134...motion processing unit, 135 ...Emote processing unit, 136...lip sync processing unit, 140...storage unit, 141...customer information, 142...response information, 143...voice information, 144...action information, 200...generation server device, 210...generation unit, 211...persona generation unit, 212...response text generation unit, 213...emotion parameter generation unit, 214...unique information acquisition unit, 220...storage unit, 222...LLM information, 230...evaluation unit, 240...LLM learning unit, 300...user terminal device

Claims

1. a reception unit that receives persona information indicating a persona that characterizes a conversation partner of a user; a persona generation unit that generates a persona generation prompt indicating characteristics of the persona using a large-scale language model based on the persona information received by the reception unit; a dialogue control unit that controls an avatar corresponding to the persona based on the persona generation prompt generated by the persona generation unit, and controls a dialogue between the avatar and a user; A dialogue support system comprising:

2. The dialogue support system according to claim 1, wherein the persona generation unit inputs the persona information and information relating to a specific field into the large-scale language model, and creates a persona generation prompt indicating characteristics of a persona corresponding to the specific field based on an output of the large-scale language model.

3. 2. The dialogue support system of claim 1, wherein the persona generation unit inputs existing items including the persona's gender, age, personality, place of origin (including within the country), speaking style, tone, or dialect into the large-scale language model as the persona information, and further inputs at least one of an item specified based on a user's operation, an item related to the characteristics of customers in a specific industry, or an item related to the characteristics of customers in a specific generation into the large-scale language model, and creates a persona generation prompt based on the output of the large-scale language model.

4. The persona information includes nationality or place of origin, The dialogue support system according to claim 1 , wherein the persona generation unit inputs existing items including the persona's nationality or place of origin into the large-scale language model as the persona information, and creates a persona generation prompt based on an output of the large-scale language model.

5. a voice generation unit that generates voice data in a language corresponding to the nationality or place of origin based on the persona generation prompt generated by the persona generation unit; a voice information processing unit that processes the voice data generated by the voice generation unit based on the nationality or place of origin included in the persona information; The dialogue support system according to claim 4 , comprising:

6. The dialogue support system according to claim 5 , wherein the speech generation unit selects one of a plurality of languages ​​based on the nationality or place of origin included in the persona information, and generates speech data in the selected language.

7. The dialogue support system according to claim 1 , wherein the persona generation unit inputs items relating to issues that customers have with respect to a specific product into the large-scale language model, and creates a persona generation prompt based on an output of the large-scale language model.

8. an utterance acquisition unit that acquires utterance information indicating an utterance of a user; an evaluation unit that evaluates a user based on the utterance information acquired by the utterance acquisition unit; The dialogue support system according to claim 1 , comprising:

9. the receiving unit receives purpose of use information indicating a purpose of use for the user to interact with the avatar; The dialogue support system according to claim 8 , wherein the evaluation unit evaluates the user based on evaluation items set according to the purpose of use.

10. the utterance acquisition unit acquires the utterance information of the user and the utterance information of an avatar; The evaluation items include at least one of a customer's level of understanding based on the user's speech information and the avatar's speech information, accuracy of product knowledge, accuracy of specialized knowledge, and communication ability. The dialogue support system according to claim 9.

11. a step in which the server device receives persona information indicating a persona that characterizes a conversation partner of the user; generating, by the server device, a persona generation prompt that indicates characteristics of the persona using a large-scale language model based on the persona information; the server device controls an avatar corresponding to the persona based on the persona generation prompt and controls a dialogue between the avatar and a user; A dialogue support method comprising:

12. The server computer receiving persona information indicating a persona characterizing a user's interaction partner; generating persona-generating prompts based on the persona information using a large-scale language model, the prompts indicating characteristics of the persona; controlling an avatar corresponding to the persona based on the persona generation prompt and controlling an interaction between the avatar and a user; A program that executes.

Images