System

Abstract

An object of a system according to an embodiment is to smoothly progress a conversation during a business visit and evaluate the atmosphere of a place.SOLUTION: A system according to an embodiment includes an acquisition unit, a topic providing unit, a conversation development unit, and an atmosphere evaluation unit. The acquisition unit acquires profile data of the other party. The topic providing unit provides a topic of the idling talk based on the data acquired by the acquisition unit. The conversation development unit develops a conversation on the basis of a specific question input in advance and content to be conveyed. The atmosphere evaluation unit evaluates the atmosphere of the place by analyzing voice and video data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques do not adequately evaluate the smooth progress of conversations or the atmosphere of the situation during sales calls, and there is room for improvement.

[0005] The system according to the embodiment aims to smoothly advance conversations during sales calls and evaluate the atmosphere of the situation. [Means for solving the problem]

[0006] The system according to the embodiment includes an acquisition unit, a topic provision unit, a conversation development unit, and an atmosphere evaluation unit. The acquisition unit acquires the profile data of the other party. The topic provision unit provides topics for idle talk based on the data acquired by the acquisition unit. The conversation development unit develops the conversation based on specific questions and content to be conveyed that are input in advance. The atmosphere evaluation unit analyzes audio and video data to evaluate the atmosphere of the situation. [Effects of the Invention]

[0007] The system according to the embodiment can smoothly advance conversations during sales calls and evaluate the atmosphere of the situation. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A conversation support system according to an embodiment of the present invention utilizes the voice, video recognition, and conversation generation capabilities of a generation AI to assist conversations between both parties making and receiving sales calls. The conversation support system acquires the other party's profile data, and the generation AI provides idle conversation topics, develops the conversation based on pre-entered questions and desired content, and analyzes the voice and video data to evaluate the atmosphere of the conversation. For example, the conversation support system selects and provides appropriate topics based on the other party's profile data, past conversation history, and current situation (e.g., weather or news). Next, the conversation support system predicts the flow of the conversation based on the pre-entered questions and desired content, and develops the topic at an appropriate time. Furthermore, the conversation support system analyzes voice and video in real time, evaluates the conversation atmosphere and the other party's reactions, and provides feedback on the results to the sales representative. This allows the conversation support system to improve the effectiveness of sales calls and facilitate smooth communication between both parties. This allows the conversation support system to assist conversations between both parties making and receiving sales calls and facilitate smooth communication. For example, this is expected to improve the effectiveness of sales calls and facilitate smooth communication between both parties.

[0029] A conversation support system according to an embodiment includes an acquisition unit, a topic provision unit, a conversation development unit, and an atmosphere evaluation unit. The acquisition unit acquires profile data of the other party. The profile data includes, but is not limited to, for example, name, age, occupation, and hobbies. The acquisition unit, for example, collects the profile data from the other party's social media account. The acquisition unit can also analyze the other party's past conversation history to supplement the profile data. For example, the acquisition unit analyzes the other party's past conversation history to understand the other party's interests and concerns. The topic provision unit provides topics for idle conversation based on the data acquired by the acquisition unit. The topic provision unit selects topics based on, for example, the other party's profile data, past conversation history, and current situation. For example, the topic provision unit provides topics related to the other party's hobbies. The topic provision unit can also provide topics based on the current weather or news. For example, the topic provision unit provides topics related to the current weather to start a conversation. The conversation development unit develops a conversation based on specific questions and desired content entered in advance. In the conversation development unit, for example, the generation AI predicts the flow of the conversation and develops the topic at the appropriate time. For example, in the conversation development unit, the generation AI predicts the flow of the conversation based on questions input in advance and asks questions at the appropriate time. In addition, the conversation development unit can predict the flow of the conversation based on the content to be communicated input in advance and convey the content at the appropriate time. For example, the conversation development unit provides an explanation of a product input in advance at the appropriate time. The atmosphere evaluation unit analyzes audio and video data to evaluate the atmosphere of a situation. The atmosphere evaluation unit performs evaluation by analyzing, for example, changes in voice tone and facial expressions. For example, the atmosphere evaluation unit analyzes voice tone to estimate the other party's emotions. In addition, the atmosphere evaluation unit can analyze changes in facial expressions to estimate the other party's emotions. For example, the atmosphere evaluation unit analyzes the frequency of the other party's smiles to evaluate the atmosphere of a situation. As a result, the conversation support system according to the embodiment can facilitate conversation between both the sales caller and the sales recipient and facilitate smooth communication. For example, it is expected that the effectiveness of sales visits will improve and communication between both parties will proceed smoothly.

[0030] The topic providing unit can select a topic based on the other party's profile data, past conversation history, and the current specific situation. The topic providing unit selects a topic based on the other party's profile data, for example. For example, the topic providing unit provides a topic related to the other party's hobbies. The topic providing unit can also select a topic based on past conversation history. For example, the topic providing unit can again provide a topic in which the other party showed interest in a past conversation. The topic providing unit can also select a topic based on the current specific situation. For example, the topic providing unit provides a topic based on the current weather or news. This makes it possible to provide a topic that is appropriate for the other party, thereby facilitating a smooth conversation.

[0031] In the conversation development unit, the generation AI predicts the flow of the conversation based on questions input in advance and the content to be communicated, and can develop the topic at specific timing. In the conversation development unit, for example, the generation AI predicts the flow of the conversation based on questions input in advance and asks questions at appropriate timing. For example, in the conversation development unit, the generation AI predicts the flow of the conversation based on questions input in advance and asks questions at a timing when it is easy for the other person to answer the questions. In addition, the conversation development unit can predict the flow of the conversation based on the content to be communicated input in advance and convey the content at an appropriate timing. For example, in the conversation development unit, the generation AI predicts the flow of the conversation based on a product description input in advance and provides the explanation at a timing when it is likely to interest the other person. In this way, smooth conversation can be achieved by predicting the flow of the conversation and developing the topic at the appropriate timing.

[0032] The atmosphere evaluation unit can analyze changes in voice tone and facial expressions to make a specific evaluation. The atmosphere evaluation unit, for example, analyzes voice tone to make an evaluation. For example, the atmosphere evaluation unit analyzes the pitch and strength of the voice to estimate the emotions of the other person. The atmosphere evaluation unit can also analyze changes in facial expressions to make an evaluation. For example, the atmosphere evaluation unit analyzes the frequency of the other person's smile and eyebrow movements to estimate the emotions of the other person. In this way, by analyzing changes in voice tone and facial expressions, the atmosphere of a situation can be accurately evaluated.

[0033] The atmosphere evaluation unit can specifically feed back the evaluation result to the sales representative. For example, the atmosphere evaluation unit feeds back the evaluation result to the sales representative. For example, the atmosphere evaluation unit calculates the evaluation result based on changes in voice tone and facial expressions and notifies the sales representative of the result. The atmosphere evaluation unit can also feed back the evaluation result in real time. For example, the atmosphere evaluation unit displays the evaluation result to the sales representative in real time during a conversation, allowing the sales representative to adjust their response on the spot. In this way, by feeding back the evaluation result to the sales representative, the effectiveness of sales visits can be improved.

[0034] The acquisition unit can analyze the user's past profile data acquisition history and select the optimal acquisition method. The acquisition unit, for example, analyzes the user's past profile data acquisition history and selects the optimal acquisition method. For example, if the user has preferred voice input in the past, the acquisition unit may prioritize voice input. Also, if the user has frequently used text input in the past, the acquisition unit may recommend text input. For example, if the user has provided a lot of image data in the past, the acquisition unit may prioritize image data acquisition. In this way, by analyzing the past history, profile data can be acquired in the optimal method for the user.

[0035] The acquisition unit can perform filtering based on the user's current areas of interest when acquiring the profile data. For example, when acquiring the profile data, the acquisition unit performs filtering based on the user's current areas of interest. For example, if the user is interested in recent news, the acquisition unit preferentially acquires related profile data. Furthermore, if the user is interested in a particular hobby, the acquisition unit can also acquire data related to that hobby. For example, if the user is interested in a particular industry, the acquisition unit acquires data related to that industry. In this way, by filtering data based on the user's areas of interest, highly relevant data can be acquired.

[0036] The acquisition unit can select the optimal acquisition means depending on the user's input method when acquiring profile data. For example, when acquiring profile data, the acquisition unit selects the optimal acquisition means depending on the user's input method. For example, if the user selects voice input, the acquisition unit acquires data using voice recognition technology. Also, if the user selects text input, the acquisition unit can acquire data using text analysis technology. For example, if the user selects image input, the acquisition unit acquires data using image recognition technology. This allows efficient data acquisition by selecting the optimal means depending on the user's input method.

[0037] When acquiring profile data, the acquisition unit can prioritize acquiring highly relevant data by taking into account the user's geographical location information. For example, when acquiring profile data, the acquisition unit prioritizes acquiring highly relevant data by taking into account the user's geographical location information. For example, when the user is in a specific area, the acquisition unit prioritizes acquiring data related to that area. Furthermore, when the user is traveling, the acquisition unit can also prioritize acquiring data related to the travel destination. For example, when the user is at home, the acquisition unit prioritizes acquiring data around the user's home. In this way, highly relevant data can be prioritized by taking into account the geographical location information.

[0038] The acquisition unit can analyze the user's social media activities and acquire related data when acquiring the profile data. For example, the acquisition unit analyzes the user's social media activities and acquires related data when acquiring the profile data. For example, the acquisition unit acquires data related to places where the user has checked in on social media. The acquisition unit can also analyze the content of the user's posts on social media and acquire related data. For example, the acquisition unit acquires related data by referring to the activities of the user's friends on social media. In this way, highly relevant data can be acquired by analyzing social media activities.

[0039] The acquisition unit can customize the acquisition method by reflecting the user's past feedback when acquiring profile data. For example, the acquisition unit customizes the acquisition method by reflecting the user's past feedback when acquiring profile data. For example, the acquisition unit prioritizes acquisition methods for which the user has given favorable feedback in the past. The acquisition unit can also avoid acquisition methods for which the user has given negative feedback in the past. For example, the acquisition unit optimizes the acquisition method based on the user's past feedback. In this way, data can be acquired in a method optimal for the user by reflecting the past feedback.

[0040] The topic providing unit can adjust the level of detail of the topic based on the importance of the other party when providing the topic. For example, the topic providing unit adjusts the level of detail of the topic based on the importance of the other party when providing the topic. For example, the topic providing unit provides detailed topics when the other party is an important customer. The topic providing unit can also provide basic topics when the other party is a new customer. For example, the topic providing unit provides topics based on past transactions when the other party is an existing customer. In this way, by adjusting the level of detail of the topic based on the importance of the other party, appropriate information can be provided.

[0041] The topic providing unit can apply different topic selection algorithms depending on the category of the other party when providing a topic. For example, the topic providing unit applies different topic selection algorithms depending on the category of the other party when providing a topic. For example, if the other party is an engineer, the topic providing unit may prioritize technical topics. Also, if the other party is a manager, the topic providing unit may prioritize topics related to business strategies. For example, if the other party is a marketing person, the topic providing unit may prioritize topics related to marketing strategies. In this way, by applying a topic selection algorithm depending on the category of the other party, more appropriate topics can be provided.

[0042] The topic providing unit can improve the accuracy of topics when providing topics by referring to the user's past topic provision results. For example, the topic providing unit can improve the accuracy of topics when providing topics by referring to the user's past topic provision results. For example, the topic providing unit prioritizes topics to which the user has responded favorably in the past. The topic providing unit can also avoid topics to which the user has responded negatively in the past. For example, the topic providing unit optimizes the topic selection algorithm based on the user's past responses. In this way, the accuracy of topics can be improved by referring to past results.

[0043] The topic providing unit can determine the priority of topics based on the profile data of the other party when providing topics. For example, when providing topics, the topic providing unit determines the priority of topics based on the profile data of the other party. For example, if the other party has a specific hobby, the topic providing unit prioritizes topics related to that hobby. Also, if the other party is engaged in a specific industry, the topic providing unit can prioritize topics related to that industry. For example, if the other party lives in a specific region, the topic providing unit prioritizes topics related to that region. In this way, by determining the priority of topics based on the profile data of the other party, more appropriate topics can be provided.

[0044] The topic providing unit can adjust the order of topics based on the relevance of the other party when providing topics. For example, the topic providing unit adjusts the order of topics based on the relevance of the other party when providing topics. For example, if the other party is an important customer, the topic providing unit provides an important topic first. The topic providing unit can also provide a basic topic first if the other party is a new customer. For example, if the other party is an existing customer, the topic providing unit provides a topic based on past transactions first. This makes it possible to provide more effective topics by adjusting the order of topics based on the relevance of the other party.

[0045] The topic providing unit can adjust the use of technical terms in the topic according to the expertise level of the other party when providing a topic. For example, the topic providing unit adjusts the use of technical terms in the topic according to the expertise level of the other party when providing a topic. For example, if the other party is an expert, the topic providing unit uses a lot of technical terms. The topic providing unit can also avoid technical terms if the other party is a beginner. For example, if the other party is an intermediate learner, the topic providing unit uses technical terms appropriately. In this way, by adjusting the use of technical terms according to the expertise level of the other party, it is possible to provide a topic that is easier to understand.

[0046] The conversation development unit can adjust the level of detail of the conversation based on the importance of the question input in advance and the content to be conveyed when the conversation is developed. For example, the conversation development unit adjusts the level of detail of the conversation based on the importance of the question input in advance and the content to be conveyed when the conversation is developed. For example, the conversation development unit provides detailed explanations for important questions and content. The conversation development unit can also provide concise explanations for basic questions and content. For example, the conversation development unit provides explanations with an appropriate level of detail for questions and content of medium importance. In this way, by adjusting the level of detail of the conversation based on the importance of the question and content, appropriate information can be provided.

[0047] The conversation development unit can apply different conversation development algorithms depending on the category of the other party when developing the conversation. The conversation development unit, for example, applies different conversation development algorithms depending on the category of the other party when developing the conversation. For example, if the other party is an engineer, the conversation development unit applies a technical conversation development algorithm. Furthermore, if the other party is a manager, the conversation development unit can also apply a conversation development algorithm related to business strategy. For example, if the other party is a marketing person, the conversation development unit applies a conversation development algorithm related to marketing strategy. In this way, by applying a conversation development algorithm depending on the category of the other party, more appropriate conversation development is possible.

[0048] The conversation development unit can improve the accuracy of the conversation when developing the conversation by referring to the user's past conversation development results. For example, the conversation development unit can improve the accuracy of the conversation when developing the conversation by referring to the user's past conversation development results. For example, the conversation development unit prioritizes a conversation development method to which the user has responded favorably in the past. The conversation development unit can also avoid a conversation development method to which the user has responded negatively in the past. For example, the conversation development unit optimizes the conversation development algorithm based on the user's past responses. In this way, the accuracy of the conversation can be improved by referring to past results.

[0049] The conversation development unit can determine the priority of a conversation based on the profile data of the other party when developing the conversation. For example, when developing the conversation, the conversation development unit determines the priority of a conversation based on the profile data of the other party. For example, if the other party has a particular hobby, the conversation development unit may prioritize a conversation related to that hobby. Also, if the other party is engaged in a particular industry, the conversation development unit may prioritize a conversation related to that industry. For example, if the other party lives in a particular region, the conversation development unit may prioritize a conversation related to that region. In this way, by determining the priority of a conversation based on the profile data of the other party, a more appropriate conversation can be developed.

[0050] The conversation development unit can adjust the order of conversations based on the relevance of the other party when developing the conversation. For example, the conversation development unit adjusts the order of conversations based on the relevance of the other party when developing the conversation. For example, if the other party is an important customer, the conversation development unit develops an important conversation first. Also, the conversation development unit can develop a basic conversation first if the other party is a new customer. For example, if the other party is an existing customer, the conversation development unit develops a conversation based on past transactions first. In this way, by adjusting the order of conversations based on the relevance of the other party, more effective conversation development is possible.

[0051] The conversation development unit can adjust the use of technical terms in the conversation depending on the expertise level of the other party when developing the conversation. For example, the conversation development unit adjusts the use of technical terms in the conversation depending on the expertise level of the other party when developing the conversation. For example, if the other party is an expert, the conversation development unit uses a lot of technical terms. The conversation development unit can also avoid technical terms if the other party is a beginner. For example, if the other party is an intermediate learner, the conversation development unit uses technical terms appropriately. In this way, by adjusting the use of technical terms depending on the expertise level of the other party, it is possible to develop a conversation that is easier to understand.

[0052] The atmosphere evaluation unit can adjust the level of detail of the evaluation based on the importance of voice tone and facial expression changes during atmosphere evaluation. The atmosphere evaluation unit adjusts the level of detail of the evaluation based on the importance of voice tone and facial expression changes during atmosphere evaluation, for example. For example, the atmosphere evaluation unit performs a detailed evaluation when the voice tone is gentle. The atmosphere evaluation unit can also perform a concise evaluation when facial expression changes are minimal. For example, the atmosphere evaluation unit performs a dynamic evaluation when the voice tone is intense. This allows for a more accurate evaluation by adjusting the level of detail of the evaluation based on the importance of voice tone and facial expression changes.

[0053] The atmosphere evaluation unit can apply different evaluation algorithms depending on the category of the other party when evaluating the atmosphere. For example, the atmosphere evaluation unit applies different evaluation algorithms depending on the category of the other party when evaluating the atmosphere. For example, if the other party is an engineer, the atmosphere evaluation unit applies a technical evaluation algorithm. Furthermore, if the other party is a manager, the atmosphere evaluation unit can also apply an evaluation algorithm related to business strategy. For example, if the other party is a marketing person, the atmosphere evaluation unit applies an evaluation algorithm related to marketing strategy. In this way, applying an evaluation algorithm depending on the category of the other party enables a more appropriate evaluation.

[0054] The atmosphere evaluation unit can improve the accuracy of the evaluation by referring to the user's past atmosphere evaluation results when evaluating the atmosphere. For example, the atmosphere evaluation unit can improve the accuracy of the evaluation by referring to the user's past atmosphere evaluation results when evaluating the atmosphere. For example, the atmosphere evaluation unit prioritizes evaluation methods to which the user has previously shown a favorable response. The atmosphere evaluation unit can also avoid evaluation methods to which the user has previously shown a negative response. For example, the atmosphere evaluation unit optimizes the evaluation algorithm based on the user's past responses. In this way, the accuracy of the evaluation can be improved by referring to past results.

[0055] The atmosphere evaluation unit can determine the priority of evaluations based on the profile data of the other party when evaluating the atmosphere. For example, the atmosphere evaluation unit determines the priority of evaluations based on the profile data of the other party when evaluating the atmosphere. For example, if the other party is an important customer, the atmosphere evaluation unit prioritizes important evaluations. Furthermore, the atmosphere evaluation unit can also prioritize basic evaluations if the other party is a new customer. For example, if the other party is an existing customer, the atmosphere evaluation unit prioritizes evaluations based on past transactions. This allows for more appropriate evaluations by determining the priority of evaluations based on the profile data of the other party.

[0056] The atmosphere evaluation unit can adjust the order of evaluations based on the relevance of the other party when evaluating the atmosphere. For example, the atmosphere evaluation unit adjusts the order of evaluations based on the relevance of the other party when evaluating the atmosphere. For example, if the other party is an important customer, the atmosphere evaluation unit performs an important evaluation first. Also, if the other party is a new customer, the atmosphere evaluation unit can perform a basic evaluation first. For example, if the other party is an existing customer, the atmosphere evaluation unit performs an evaluation based on past transactions first. This allows for more effective evaluation by adjusting the order of evaluations based on the relevance of the other party.

[0057] The atmosphere evaluation unit can adjust the use of technical terms in the evaluation depending on the expertise level of the other party during the atmosphere evaluation. For example, the atmosphere evaluation unit adjusts the use of technical terms in the evaluation depending on the expertise level of the other party during the atmosphere evaluation. For example, if the other party is an expert, the atmosphere evaluation unit uses a lot of technical terms. Also, the atmosphere evaluation unit can avoid technical terms if the other party is a beginner. For example, if the other party is an intermediate user, the atmosphere evaluation unit uses technical terms appropriately. In this way, by adjusting the use of technical terms depending on the expertise level of the other party, an evaluation that is easier to understand can be made.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The conversation support system may further include a timing determination unit that analyzes the user's past conversation history and determines the optimal conversation start timing. For example, if the user has previously preferred conversations during a specific time period, the conversation can be started during that time period. Also, if the user has previously preferred conversations under specific circumstances, the conversation can be started according to those circumstances. Furthermore, if the user has previously preferred conversations on a specific topic, the conversation can be started at a timing related to that topic. This allows for more effective conversations to be achieved by determining the optimal conversation start timing based on the user's past conversation history.

[0060] The conversation support system can further include a geographic information customization unit that customizes the content of the conversation taking into account the user's geographic location information. For example, if the user is in a specific area, topics related to that area can be provided. If the user is traveling, topics related to the travel destination can be provided. If the user is at home, topics related to the area around the user's home can be provided. In this way, by customizing the content of the conversation based on the user's geographic location information, more relevant conversations can be realized.

[0061] The conversation support system may further include a social media analysis unit that analyzes the user's social media activity and personalizes the content of the conversation. For example, the system may provide topics related to places where the user has checked in on social media. The system may also analyze the content of the user's social media posts and provide related topics. Furthermore, the system may provide related topics based on the activities of the user's friends on social media. This allows for more relevant conversations by personalizing the content of the conversation based on social media activity.

[0062] The conversation support system can further include a feedback reflection unit that reflects the user's past feedback and customizes the conversation progression method. For example, a progression method for which the user has given favorable feedback in the past can be prioritized. It can also avoid a progression method for which the user has given negative feedback in the past. Furthermore, the progression method can be optimized based on the user's past feedback. In this way, by reflecting past feedback, the conversation can be progressed in a way that is optimal for the user.

[0063] The conversation support system can further include an expertise adjustment unit that adjusts the content of the conversation according to the user's level of expertise. For example, if the user is an expert, the conversation can be conducted with specialized content. If the user is a beginner, the conversation can be conducted with basic content. Furthermore, if the user is an intermediate user, the conversation can be conducted with moderately specialized content. In this way, by adjusting the content of the conversation according to the user's level of expertise, it is possible to realize a conversation that is easier to understand.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The acquisition unit acquires the other party's profile data. The profile data includes the other party's name, age, occupation, hobbies, etc. The acquisition unit collects the profile data from the other party's social media account. The acquisition unit can also analyze the other party's past conversation history to supplement the profile data. For example, the acquisition unit analyzes the other party's past conversation history to understand the other party's interests and concerns. Step 2: The topic provider provides topics for idle conversation based on the data acquired by the acquirer. The topic provider selects topics based on the other person's profile data, past conversation history, and current situation. For example, topics related to the other person's hobbies, or current weather and news are provided. Step 3: The conversation development section develops the conversation based on specific questions and the content that the user wants to convey, which are entered in advance. In this section, the generation AI predicts the flow of the conversation and asks questions or conveys content at the appropriate time. For example, it provides a pre-entered product explanation at the appropriate time. Step 4: The atmosphere evaluation unit analyzes the audio and video data to evaluate the atmosphere of the situation. The atmosphere evaluation unit analyzes changes in the tone of the voice and facial expressions to estimate the other person's emotions. For example, it analyzes the frequency of the other person's smiles to evaluate the atmosphere of the situation.

[0066] (Example 2) A conversation support system according to an embodiment of the present invention utilizes the voice, video recognition, and conversation generation capabilities of a generation AI to assist conversations between both parties making and receiving sales calls. The conversation support system acquires the other party's profile data, and the generation AI provides idle conversation topics, develops the conversation based on pre-entered questions and desired content, and analyzes the voice and video data to evaluate the atmosphere of the conversation. For example, the conversation support system selects and provides appropriate topics based on the other party's profile data, past conversation history, and current situation (e.g., weather or news). Next, the conversation support system predicts the flow of the conversation based on the pre-entered questions and desired content, and develops the topic at an appropriate time. Furthermore, the conversation support system analyzes voice and video in real time, evaluates the conversation atmosphere and the other party's reactions, and provides feedback on the results to the sales representative. This allows the conversation support system to improve the effectiveness of sales calls and facilitate smooth communication between both parties. This allows the conversation support system to assist conversations between both parties making and receiving sales calls and facilitate smooth communication. For example, this is expected to improve the effectiveness of sales calls and facilitate smooth communication between both parties.

[0067] A conversation support system according to an embodiment includes an acquisition unit, a topic provision unit, a conversation development unit, and an atmosphere evaluation unit. The acquisition unit acquires profile data of the other party. The profile data includes, but is not limited to, for example, name, age, occupation, and hobbies. The acquisition unit, for example, collects the profile data from the other party's social media account. The acquisition unit can also analyze the other party's past conversation history to supplement the profile data. For example, the acquisition unit analyzes the other party's past conversation history to understand the other party's interests and concerns. The topic provision unit provides topics for idle conversation based on the data acquired by the acquisition unit. The topic provision unit selects topics based on, for example, the other party's profile data, past conversation history, and current situation. For example, the topic provision unit provides topics related to the other party's hobbies. The topic provision unit can also provide topics based on the current weather or news. For example, the topic provision unit provides topics related to the current weather to start a conversation. The conversation development unit develops a conversation based on specific questions and desired content entered in advance. In the conversation development unit, for example, the generation AI predicts the flow of the conversation and develops the topic at the appropriate time. For example, in the conversation development unit, the generation AI predicts the flow of the conversation based on questions input in advance and asks questions at the appropriate time. In addition, the conversation development unit can predict the flow of the conversation based on the content to be communicated input in advance and convey the content at the appropriate time. For example, the conversation development unit provides an explanation of a product input in advance at the appropriate time. The atmosphere evaluation unit analyzes audio and video data to evaluate the atmosphere of a situation. The atmosphere evaluation unit performs evaluation by analyzing, for example, changes in voice tone and facial expressions. For example, the atmosphere evaluation unit analyzes voice tone to estimate the other party's emotions. In addition, the atmosphere evaluation unit can analyze changes in facial expressions to estimate the other party's emotions. For example, the atmosphere evaluation unit analyzes the frequency of the other party's smiles to evaluate the atmosphere of a situation. As a result, the conversation support system according to the embodiment can facilitate conversation between both the sales caller and the sales recipient and facilitate smooth communication. For example, it is expected that the effectiveness of sales visits will improve and communication between both parties will proceed smoothly.

[0068] The topic providing unit can select a topic based on the other party's profile data, past conversation history, and the current specific situation. The topic providing unit selects a topic based on the other party's profile data, for example. For example, the topic providing unit provides a topic related to the other party's hobbies. The topic providing unit can also select a topic based on past conversation history. For example, the topic providing unit can again provide a topic in which the other party showed interest in a past conversation. The topic providing unit can also select a topic based on the current specific situation. For example, the topic providing unit provides a topic based on the current weather or news. This makes it possible to provide a topic that is appropriate for the other party, thereby facilitating a smooth conversation.

[0069] In the conversation development unit, the generation AI predicts the flow of the conversation based on questions input in advance and the content to be communicated, and can develop the topic at specific timing. In the conversation development unit, for example, the generation AI predicts the flow of the conversation based on questions input in advance and asks questions at appropriate timing. For example, in the conversation development unit, the generation AI predicts the flow of the conversation based on questions input in advance and asks questions at a timing when it is easy for the other person to answer the questions. In addition, the conversation development unit can predict the flow of the conversation based on the content to be communicated input in advance and convey the content at an appropriate timing. For example, in the conversation development unit, the generation AI predicts the flow of the conversation based on a product description input in advance and provides the explanation at a timing when it is likely to interest the other person. In this way, smooth conversation can be achieved by predicting the flow of the conversation and developing the topic at the appropriate timing.

[0070] The atmosphere evaluation unit can analyze changes in voice tone and facial expressions to make a specific evaluation. The atmosphere evaluation unit, for example, analyzes voice tone to make an evaluation. For example, the atmosphere evaluation unit analyzes the pitch and strength of the voice to estimate the emotions of the other person. The atmosphere evaluation unit can also analyze changes in facial expressions to make an evaluation. For example, the atmosphere evaluation unit analyzes the frequency of the other person's smile and eyebrow movements to estimate the emotions of the other person. In this way, by analyzing changes in voice tone and facial expressions, the atmosphere of a situation can be accurately evaluated.

[0071] The atmosphere evaluation unit can specifically feed back the evaluation result to the sales representative. For example, the atmosphere evaluation unit feeds back the evaluation result to the sales representative. For example, the atmosphere evaluation unit calculates the evaluation result based on changes in voice tone and facial expressions and notifies the sales representative of the result. The atmosphere evaluation unit can also feed back the evaluation result in real time. For example, the atmosphere evaluation unit displays the evaluation result to the sales representative in real time during a conversation, allowing the sales representative to adjust their response on the spot. In this way, by feeding back the evaluation result to the sales representative, the effectiveness of sales visits can be improved.

[0072] The acquisition unit can estimate the user's emotions and adjust the timing of acquiring the profile data based on the estimated user emotions. The acquisition unit, for example, estimates the user's emotions and adjusts the timing of acquiring the profile data based on the estimated emotions. For example, if the user is relaxed, the acquisition unit acquires the profile data immediately after the start of a conversation. Alternatively, if the user is nervous, the acquisition unit can acquire the profile data after the conversation has progressed. For example, if the user is in a hurry, the acquisition unit quickly acquires the profile data in the middle of a conversation. This allows the profile data acquisition timing to be adjusted according to the user's emotions, thereby acquiring data at a more appropriate time. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0073] The acquisition unit can analyze the user's past profile data acquisition history and select the optimal acquisition method. The acquisition unit, for example, analyzes the user's past profile data acquisition history and selects the optimal acquisition method. For example, if the user has preferred voice input in the past, the acquisition unit may prioritize voice input. Also, if the user has frequently used text input in the past, the acquisition unit may recommend text input. For example, if the user has provided a lot of image data in the past, the acquisition unit may prioritize image data acquisition. In this way, by analyzing the past history, profile data can be acquired in the optimal method for the user.

[0074] The acquisition unit can perform filtering based on the user's current areas of interest when acquiring the profile data. For example, when acquiring the profile data, the acquisition unit performs filtering based on the user's current areas of interest. For example, if the user is interested in recent news, the acquisition unit preferentially acquires related profile data. Furthermore, if the user is interested in a particular hobby, the acquisition unit can also acquire data related to that hobby. For example, if the user is interested in a particular industry, the acquisition unit acquires data related to that industry. In this way, by filtering data based on the user's areas of interest, highly relevant data can be acquired.

[0075] The acquisition unit can select the optimal acquisition means depending on the user's input method when acquiring profile data. For example, when acquiring profile data, the acquisition unit selects the optimal acquisition means depending on the user's input method. For example, if the user selects voice input, the acquisition unit acquires data using voice recognition technology. Also, if the user selects text input, the acquisition unit can acquire data using text analysis technology. For example, if the user selects image input, the acquisition unit acquires data using image recognition technology. This allows efficient data acquisition by selecting the optimal means depending on the user's input method.

[0076] The acquisition unit can estimate the user's emotions and determine the priority of profile data to be acquired based on the estimated user emotions. The acquisition unit, for example, estimates the user's emotions and determines the priority of profile data based on the estimated emotions. For example, if the user is excited, the acquisition unit prioritizes acquiring interesting data. The acquisition unit can also prioritize acquiring detailed data if the user is calm. For example, if the user is tired, the acquisition unit prioritizes acquiring concise data. In this way, by determining the priority of data based on the user's emotions, important data can be prioritized. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0077] When acquiring profile data, the acquisition unit can prioritize acquiring highly relevant data by taking into account the user's geographical location information. For example, when acquiring profile data, the acquisition unit prioritizes acquiring highly relevant data by taking into account the user's geographical location information. For example, when the user is in a specific area, the acquisition unit prioritizes acquiring data related to that area. Furthermore, when the user is traveling, the acquisition unit can also prioritize acquiring data related to the travel destination. For example, when the user is at home, the acquisition unit prioritizes acquiring data around the user's home. In this way, highly relevant data can be prioritized by taking into account the geographical location information.

[0078] The acquisition unit can analyze the user's social media activities and acquire related data when acquiring the profile data. For example, the acquisition unit analyzes the user's social media activities and acquires related data when acquiring the profile data. For example, the acquisition unit acquires data related to places where the user has checked in on social media. The acquisition unit can also analyze the content of the user's posts on social media and acquire related data. For example, the acquisition unit acquires related data by referring to the activities of the user's friends on social media. In this way, highly relevant data can be acquired by analyzing social media activities.

[0079] The acquisition unit can customize the acquisition method by reflecting the user's past feedback when acquiring profile data. For example, the acquisition unit customizes the acquisition method by reflecting the user's past feedback when acquiring profile data. For example, the acquisition unit prioritizes acquisition methods for which the user has given favorable feedback in the past. The acquisition unit can also avoid acquisition methods for which the user has given negative feedback in the past. For example, the acquisition unit optimizes the acquisition method based on the user's past feedback. In this way, data can be acquired in a method optimal for the user by reflecting the past feedback.

[0080] The topic providing unit can estimate the user's emotions and adjust the way the topic is expressed based on the estimated user emotions. The topic providing unit, for example, estimates the user's emotions and adjusts the way the topic is expressed based on the estimated emotions. For example, if the user is relaxed, the topic providing unit can provide the topic using casual expressions. Also, if the user is nervous, the topic providing unit can provide the topic using formal expressions. For example, if the user is excited, the topic providing unit can provide the topic using energetic expressions. In this way, by adjusting the way the topic is expressed based on the user's emotions, more appropriate topics can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0081] The topic providing unit can adjust the level of detail of the topic based on the importance of the other party when providing the topic. For example, the topic providing unit adjusts the level of detail of the topic based on the importance of the other party when providing the topic. For example, the topic providing unit provides detailed topics when the other party is an important customer. The topic providing unit can also provide basic topics when the other party is a new customer. For example, the topic providing unit provides topics based on past transactions when the other party is an existing customer. In this way, by adjusting the level of detail of the topic based on the importance of the other party, appropriate information can be provided.

[0082] The topic providing unit can apply different topic selection algorithms depending on the category of the other party when providing a topic. For example, the topic providing unit applies different topic selection algorithms depending on the category of the other party when providing a topic. For example, if the other party is an engineer, the topic providing unit may prioritize technical topics. Also, if the other party is a manager, the topic providing unit may prioritize topics related to business strategies. For example, if the other party is a marketing person, the topic providing unit may prioritize topics related to marketing strategies. In this way, by applying a topic selection algorithm depending on the category of the other party, more appropriate topics can be provided.

[0083] The topic providing unit can improve the accuracy of topics when providing topics by referring to the user's past topic provision results. For example, the topic providing unit can improve the accuracy of topics when providing topics by referring to the user's past topic provision results. For example, the topic providing unit prioritizes topics to which the user has responded favorably in the past. The topic providing unit can also avoid topics to which the user has responded negatively in the past. For example, the topic providing unit optimizes the topic selection algorithm based on the user's past responses. In this way, the accuracy of topics can be improved by referring to past results.

[0084] The topic providing unit can estimate the user's emotions and adjust the length of the topic based on the estimated user's emotions. The topic providing unit, for example, estimates the user's emotions and adjusts the length of the topic based on the estimated emotions. For example, the topic providing unit provides a longer topic when the user is relaxed. The topic providing unit can also provide a shorter topic when the user is in a hurry. For example, the topic providing unit provides a topic of appropriate length when the user is excited. In this way, by adjusting the length of the topic based on the user's emotions, it is possible to provide a topic of appropriate length. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0085] The topic providing unit can determine the priority of topics based on the profile data of the other party when providing topics. For example, when providing topics, the topic providing unit determines the priority of topics based on the profile data of the other party. For example, if the other party has a specific hobby, the topic providing unit prioritizes topics related to that hobby. Also, if the other party is engaged in a specific industry, the topic providing unit can prioritize topics related to that industry. For example, if the other party lives in a specific region, the topic providing unit prioritizes topics related to that region. In this way, by determining the priority of topics based on the profile data of the other party, more appropriate topics can be provided.

[0086] The topic providing unit can adjust the order of topics based on the relevance of the other party when providing topics. For example, the topic providing unit adjusts the order of topics based on the relevance of the other party when providing topics. For example, if the other party is an important customer, the topic providing unit provides an important topic first. The topic providing unit can also provide a basic topic first if the other party is a new customer. For example, if the other party is an existing customer, the topic providing unit provides a topic based on past transactions first. This makes it possible to provide more effective topics by adjusting the order of topics based on the relevance of the other party.

[0087] The topic providing unit can adjust the use of technical terms in the topic according to the expertise level of the other party when providing a topic. For example, the topic providing unit adjusts the use of technical terms in the topic according to the expertise level of the other party when providing a topic. For example, if the other party is an expert, the topic providing unit uses a lot of technical terms. The topic providing unit can also avoid technical terms if the other party is a beginner. For example, if the other party is an intermediate learner, the topic providing unit uses technical terms appropriately. In this way, by adjusting the use of technical terms according to the expertise level of the other party, it is possible to provide a topic that is easier to understand.

[0088] The conversation development unit can estimate the user's emotions and adjust the way the conversation develops based on the estimated user emotions. The conversation development unit, for example, estimates the user's emotions and adjusts the way the conversation develops based on the estimated emotions. For example, if the user is relaxed, the conversation development unit develops the conversation at a leisurely pace. Also, if the user is nervous, the conversation development unit can develop the conversation at a formal pace. For example, if the user is excited, the conversation development unit develops the conversation at an energetic pace. This allows for more appropriate conversation development by adjusting the way the conversation develops based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0089] The conversation development unit can adjust the level of detail of the conversation based on the importance of the question input in advance and the content to be conveyed when the conversation is developed. For example, the conversation development unit adjusts the level of detail of the conversation based on the importance of the question input in advance and the content to be conveyed when the conversation is developed. For example, the conversation development unit provides detailed explanations for important questions and content. The conversation development unit can also provide concise explanations for basic questions and content. For example, the conversation development unit provides explanations with an appropriate level of detail for questions and content of medium importance. In this way, by adjusting the level of detail of the conversation based on the importance of the question and content, appropriate information can be provided.

[0090] The conversation development unit can apply different conversation development algorithms depending on the category of the other party when developing the conversation. The conversation development unit, for example, applies different conversation development algorithms depending on the category of the other party when developing the conversation. For example, if the other party is an engineer, the conversation development unit applies a technical conversation development algorithm. Furthermore, if the other party is a manager, the conversation development unit can also apply a conversation development algorithm related to business strategy. For example, if the other party is a marketing person, the conversation development unit applies a conversation development algorithm related to marketing strategy. In this way, by applying a conversation development algorithm depending on the category of the other party, more appropriate conversation development is possible.

[0091] The conversation development unit can improve the accuracy of the conversation when developing the conversation by referring to the user's past conversation development results. For example, the conversation development unit can improve the accuracy of the conversation when developing the conversation by referring to the user's past conversation development results. For example, the conversation development unit prioritizes a conversation development method to which the user has responded favorably in the past. The conversation development unit can also avoid a conversation development method to which the user has responded negatively in the past. For example, the conversation development unit optimizes the conversation development algorithm based on the user's past responses. In this way, the accuracy of the conversation can be improved by referring to past results.

[0092] The conversation development unit can estimate the user's emotions and adjust the length of the conversation based on the estimated user emotions. The conversation development unit, for example, estimates the user's emotions and adjusts the length of the conversation based on the estimated emotions. For example, the conversation development unit develops a longer conversation when the user is relaxed. The conversation development unit can also develop a shorter conversation when the user is in a hurry. For example, the conversation development unit develops a conversation of an appropriate length when the user is excited. In this way, by adjusting the length of the conversation based on the user's emotions, it is possible to develop a conversation of an appropriate length. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0093] The conversation development unit can determine the priority of a conversation based on the profile data of the other party when developing the conversation. For example, when developing the conversation, the conversation development unit determines the priority of a conversation based on the profile data of the other party. For example, if the other party has a particular hobby, the conversation development unit may prioritize a conversation related to that hobby. Also, if the other party is engaged in a particular industry, the conversation development unit may prioritize a conversation related to that industry. For example, if the other party lives in a particular region, the conversation development unit may prioritize a conversation related to that region. In this way, by determining the priority of a conversation based on the profile data of the other party, a more appropriate conversation can be developed.

[0094] The conversation development unit can adjust the order of conversations based on the relevance of the other party when developing the conversation. For example, the conversation development unit adjusts the order of conversations based on the relevance of the other party when developing the conversation. For example, if the other party is an important customer, the conversation development unit develops an important conversation first. Also, the conversation development unit can develop a basic conversation first if the other party is a new customer. For example, if the other party is an existing customer, the conversation development unit develops a conversation based on past transactions first. In this way, by adjusting the order of conversations based on the relevance of the other party, more effective conversation development is possible.

[0095] The conversation development unit can adjust the use of technical terms in the conversation depending on the expertise level of the other party when developing the conversation. For example, the conversation development unit adjusts the use of technical terms in the conversation depending on the expertise level of the other party when developing the conversation. For example, if the other party is an expert, the conversation development unit uses a lot of technical terms. The conversation development unit can also avoid technical terms if the other party is a beginner. For example, if the other party is an intermediate learner, the conversation development unit uses technical terms appropriately. In this way, by adjusting the use of technical terms depending on the expertise level of the other party, it is possible to develop a conversation that is easier to understand.

[0096] The atmosphere evaluation unit can estimate the user's emotions and adjust the atmosphere evaluation method based on the estimated user emotions. The atmosphere evaluation unit, for example, estimates the user's emotions and adjusts the atmosphere evaluation method based on the estimated emotions. For example, the atmosphere evaluation unit applies gentle evaluation criteria when the user is relaxed. The atmosphere evaluation unit can also apply strict evaluation criteria when the user is tense. For example, the atmosphere evaluation unit applies dynamic evaluation criteria when the user is excited. This allows for more appropriate evaluation by adjusting the atmosphere evaluation method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0097] The atmosphere evaluation unit can adjust the level of detail of the evaluation based on the importance of voice tone and facial expression changes during atmosphere evaluation. The atmosphere evaluation unit adjusts the level of detail of the evaluation based on the importance of voice tone and facial expression changes during atmosphere evaluation, for example. For example, the atmosphere evaluation unit performs a detailed evaluation when the voice tone is gentle. The atmosphere evaluation unit can also perform a concise evaluation when facial expression changes are minimal. For example, the atmosphere evaluation unit performs a dynamic evaluation when the voice tone is intense. This allows for a more accurate evaluation by adjusting the level of detail of the evaluation based on the importance of voice tone and facial expression changes.

[0098] The atmosphere evaluation unit can apply different evaluation algorithms depending on the category of the other party when evaluating the atmosphere. For example, the atmosphere evaluation unit applies different evaluation algorithms depending on the category of the other party when evaluating the atmosphere. For example, if the other party is an engineer, the atmosphere evaluation unit applies a technical evaluation algorithm. Furthermore, if the other party is a manager, the atmosphere evaluation unit can also apply an evaluation algorithm related to business strategy. For example, if the other party is a marketing person, the atmosphere evaluation unit applies an evaluation algorithm related to marketing strategy. In this way, applying an evaluation algorithm depending on the category of the other party enables a more appropriate evaluation.

[0099] The atmosphere evaluation unit can improve the accuracy of the evaluation by referring to the user's past atmosphere evaluation results when evaluating the atmosphere. For example, the atmosphere evaluation unit can improve the accuracy of the evaluation by referring to the user's past atmosphere evaluation results when evaluating the atmosphere. For example, the atmosphere evaluation unit prioritizes evaluation methods to which the user has previously shown a favorable response. The atmosphere evaluation unit can also avoid evaluation methods to which the user has previously shown a negative response. For example, the atmosphere evaluation unit optimizes the evaluation algorithm based on the user's past responses. In this way, the accuracy of the evaluation can be improved by referring to past results.

[0100] The atmosphere evaluation unit can estimate the user's emotion and adjust the display method of the atmosphere evaluation result based on the estimated user emotion. The atmosphere evaluation unit, for example, estimates the user's emotion and adjusts the display method of the atmosphere evaluation result based on the estimated emotion. For example, the atmosphere evaluation unit provides a calm display method when the user is relaxed. The atmosphere evaluation unit can also provide a detailed display method when the user is nervous. For example, the atmosphere evaluation unit provides a dynamic display method when the user is excited. This allows for a more appropriate display by adjusting the display method of the evaluation result based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0101] The atmosphere evaluation unit can determine the priority of evaluations based on the profile data of the other party when evaluating the atmosphere. For example, the atmosphere evaluation unit determines the priority of evaluations based on the profile data of the other party when evaluating the atmosphere. For example, if the other party is an important customer, the atmosphere evaluation unit prioritizes important evaluations. Furthermore, the atmosphere evaluation unit can also prioritize basic evaluations if the other party is a new customer. For example, if the other party is an existing customer, the atmosphere evaluation unit prioritizes evaluations based on past transactions. This allows for more appropriate evaluations by determining the priority of evaluations based on the profile data of the other party.

[0102] The atmosphere evaluation unit can adjust the order of evaluations based on the relevance of the other party when evaluating the atmosphere. For example, the atmosphere evaluation unit adjusts the order of evaluations based on the relevance of the other party when evaluating the atmosphere. For example, if the other party is an important customer, the atmosphere evaluation unit performs an important evaluation first. Also, if the other party is a new customer, the atmosphere evaluation unit can perform a basic evaluation first. For example, if the other party is an existing customer, the atmosphere evaluation unit performs an evaluation based on past transactions first. This allows for more effective evaluation by adjusting the order of evaluations based on the relevance of the other party.

[0103] The atmosphere evaluation unit can adjust the use of technical terms in the evaluation depending on the expertise level of the other party during the atmosphere evaluation. For example, the atmosphere evaluation unit adjusts the use of technical terms in the evaluation depending on the expertise level of the other party during the atmosphere evaluation. For example, if the other party is an expert, the atmosphere evaluation unit uses a lot of technical terms. Also, the atmosphere evaluation unit can avoid technical terms if the other party is a beginner. For example, if the other party is an intermediate user, the atmosphere evaluation unit uses technical terms appropriately. In this way, by adjusting the use of technical terms depending on the expertise level of the other party, an evaluation that is easier to understand can be made. === Hard Collateral 1-1 === Each of the multiple elements including the acquisition unit, topic provision unit, conversation development unit, and atmosphere evaluation unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit collects profile data of the other party using the control unit 46A of the smart device 14, and analyzes past conversation history using the specific processing unit 290 of the data processing device 12. For example, the topic provision unit selects a topic based on the other party's profile data and current situation using the specific processing unit 290 of the data processing device 12, and provides the topic through the output device 40 of the smart device 14. For example, the conversation development unit predicts the flow of conversation using a generation AI using the specific processing unit 290 of the data processing device 12, and develops the topic at an appropriate time using the control unit 46A of the smart device 14. For example, the atmosphere evaluation unit collects audio and video data using the camera 42 and microphone 38B of the smart device 14, and analyzes the data using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the acquisition unit, topic provision unit, conversation development unit, and mood evaluation unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the acquisition unit collects profile data of the other party using the control unit 46A of the smart glasses 214, and analyzes past conversation history using the specific processing unit 290 of the data processing device 12. For example, the topic provision unit selects a topic based on the other party's profile data and current situation using the specific processing unit 290 of the data processing device 12, and provides the topic through the speaker 240 of the smart glasses 214. For example, the conversation development unit predicts the flow of the conversation using a generation AI using the specific processing unit 290 of the data processing device 12, and develops the topic at an appropriate time using the control unit 46A of the smart glasses 214. For example, the mood evaluation unit collects audio and video data using the camera 42 and microphone 238 of the smart glasses 214, and analyzes the data using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the acquisition unit, topic provision unit, conversation development unit, and atmosphere evaluation unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the acquisition unit collects profile data of the other party using the control unit 46A of the headset-type terminal 314, and analyzes past conversation history using the specific processing unit 290 of the data processing device 12. For example, the topic provision unit selects a topic based on the other party's profile data and current situation using the specific processing unit 290 of the data processing device 12, and provides the topic through the speaker 240 of the headset-type terminal 314. For example, the conversation development unit predicts the flow of the conversation using a generation AI using the specific processing unit 290 of the data processing device 12, and develops the topic at an appropriate time using the control unit 46A of the headset-type terminal 314. For example, the atmosphere evaluation unit collects audio and video data using the camera 42 and microphone 238 of the headset-type terminal 314, and analyzes the data using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the acquisition unit, topic provision unit, conversation development unit, and atmosphere evaluation unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the acquisition unit collects profile data of the other party using the control unit 46A of the robot 414, and analyzes past conversation history using the specific processing unit 290 of the data processing device 12. For example, the topic provision unit selects a topic based on the other party's profile data and current situation using the specific processing unit 290 of the data processing device 12, and provides the topic through the speaker 240 of the robot 414. For example, the conversation development unit predicts the flow of the conversation using a generation AI using the specific processing unit 290 of the data processing device 12, and develops the topic at an appropriate time using the control unit 46A of the robot 414. For example, the atmosphere evaluation unit collects audio and video data using the camera 42 and microphone 238 of the robot 414, and analyzes the data using the specific processing unit 290 of the data processing device 12.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] The conversation support system can further include a tempo adjustment unit that estimates the user's emotions and adjusts the tempo of the conversation based on the estimated emotions. For example, if the user is relaxed, the tempo adjustment unit can proceed with the conversation at a relaxed tempo. If the user is nervous, the tempo adjustment unit can also proceed with the conversation at a faster tempo. Furthermore, if the user is excited, the tempo adjustment unit can proceed with the conversation at an energetic tempo. In this way, by adjusting the tempo of the conversation according to the user's emotions, a more natural conversation can be achieved.

[0106] The conversation support system may further include a timing determination unit that analyzes the user's past conversation history and determines the optimal conversation start timing. For example, if the user has previously preferred conversations during a specific time period, the conversation can be started during that time period. Also, if the user has previously preferred conversations under specific circumstances, the conversation can be started according to those circumstances. Furthermore, if the user has previously preferred conversations on a specific topic, the conversation can be started at a timing related to that topic. This allows for more effective conversations to be achieved by determining the optimal conversation start timing based on the user's past conversation history.

[0107] The conversation support system can further include a content adjustment unit that estimates the user's emotions and adjusts the content of the conversation based on the estimated emotions. For example, if the user is relaxed, the content adjustment unit can proceed with the conversation in a casual manner. If the user is nervous, the content adjustment unit can proceed with the conversation in a formal manner. Furthermore, if the user is excited, the content adjustment unit can proceed with the conversation in an energetic manner. In this way, by adjusting the content of the conversation according to the user's emotions, a more appropriate conversation can be achieved.

[0108] The conversation support system can further include a geographic information customization unit that customizes the content of the conversation taking into account the user's geographic location information. For example, if the user is in a specific area, topics related to that area can be provided. If the user is traveling, topics related to the travel destination can be provided. If the user is at home, topics related to the area around the user's home can be provided. In this way, by customizing the content of the conversation based on the user's geographic location information, more relevant conversations can be realized.

[0109] The conversation support system may further include a social media analysis unit that analyzes the user's social media activity and personalizes the content of the conversation. For example, the system may provide topics related to places where the user has checked in on social media. The system may also analyze the content of the user's social media posts and provide related topics. Furthermore, the system may provide related topics based on the activities of the user's friends on social media. This allows for more relevant conversations by personalizing the content of the conversation based on social media activity.

[0110] The conversation support system may further include a feedback adjustment unit that estimates the user's emotions and adjusts the conversation feedback method based on the estimated emotions. For example, if the user is relaxed, the feedback adjustment unit may provide gentle feedback. If the user is nervous, the feedback adjustment unit may provide detailed feedback. Furthermore, if the user is excited, dynamic feedback may be provided. In this way, by adjusting the feedback method according to the user's emotions, more appropriate feedback may be provided.

[0111] The conversation support system can further include a feedback reflection unit that reflects the user's past feedback and customizes the conversation progression method. For example, a progression method for which the user has given favorable feedback in the past can be prioritized. It can also avoid a progression method for which the user has given negative feedback in the past. Furthermore, the progression method can be optimized based on the user's past feedback. In this way, by reflecting past feedback, the conversation can be progressed in a way that is optimal for the user.

[0112] The conversation support system can further include an end timing adjustment unit that estimates the user's emotions and adjusts the timing to end the conversation based on the estimated emotions. For example, if the user is relaxed, the end timing adjustment unit continues the conversation for a longer period of time. Also, if the user is nervous, the end timing adjustment unit can end the conversation earlier. Furthermore, if the user is excited, the conversation can be ended at an appropriate time. In this way, by adjusting the end timing of the conversation according to the user's emotions, a more appropriate end to the conversation can be achieved.

[0113] The conversation support system can further include an expertise adjustment unit that adjusts the content of the conversation according to the user's level of expertise. For example, if the user is an expert, the conversation can be conducted with specialized content. If the user is a beginner, the conversation can be conducted with basic content. Furthermore, if the user is an intermediate user, the conversation can be conducted with moderately specialized content. In this way, by adjusting the content of the conversation according to the user's level of expertise, it is possible to realize a conversation that is easier to understand.

[0114] The conversation support system may further include a topic selection unit that estimates the user's emotions and selects a conversation topic based on the estimated emotions. For example, if the user is relaxed, the topic selection unit may select a casual topic. If the user is nervous, the topic selection unit may select a formal topic. If the user is excited, the topic selection unit may select an energetic topic. In this way, by selecting a conversation topic according to the user's emotions, more appropriate conversations can be realized.

[0115] The processing flow of the second embodiment will be briefly explained below.

[0116] Step 1: The acquisition unit acquires the other party's profile data. The profile data includes the other party's name, age, occupation, hobbies, etc. The acquisition unit collects the profile data from the other party's social media account. The acquisition unit can also analyze the other party's past conversation history to supplement the profile data. For example, the acquisition unit analyzes the other party's past conversation history to understand the other party's interests and concerns. Step 2: The topic provider provides topics for idle conversation based on the data acquired by the acquirer. The topic provider selects topics based on the other person's profile data, past conversation history, and current situation. For example, topics related to the other person's hobbies, or current weather and news are provided. Step 3: The conversation development section develops the conversation based on specific questions and the content that the user wants to convey, which are entered in advance. In this section, the generation AI predicts the flow of the conversation and asks questions or conveys content at the appropriate time. For example, it provides a pre-entered product explanation at the appropriate time. Step 4: The atmosphere evaluation unit analyzes the audio and video data to evaluate the atmosphere of the situation. The atmosphere evaluation unit analyzes changes in the tone of the voice and facial expressions to estimate the other person's emotions. For example, it analyzes the frequency of the other person's smiles to evaluate the atmosphere of the situation.

[0117] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0118] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0120] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0131] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0161] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0162] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0163] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0164] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0165] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0166] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0171] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0172] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0173] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0174] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0175] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0176] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0177] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0178] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0179] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0180] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0181] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0182] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0183] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0184] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0185] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0186] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0187] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0188] [Explanation of symbols]

[0189] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an acquisition unit for acquiring profile data of the other party; a topic providing unit that provides topics for idle talk based on the data acquired by the acquisition unit; A conversation development section develops a conversation based on specific questions and the content you want to convey in advance, and An atmosphere evaluation unit that analyzes audio and video data and evaluates the atmosphere of the place. A system characterized by:

2. The topic providing unit Select topics based on the other person's profile data, past conversation history, and the current specific situation 2. The system of claim 1.

3. The conversation development section Based on pre-entered questions and the content you want to convey, the generative AI predicts the flow of the conversation and develops the topic at specific times.

2. The system of claim 1.

4. The atmosphere evaluation unit Analyzing voice tone and facial expression changes to provide specific evaluations 2. The system of claim 1.

5. The atmosphere evaluation unit Provide specific feedback of the evaluation results to sales representatives 2. The system of claim 1.

6. The acquisition unit The system estimates the user's emotions and adjusts the timing of profile data acquisition based on the estimated user emotions.

2. The system of claim 1.

7. The acquisition unit Analyze the user's past profile data acquisition history and select the optimal acquisition method 2. The system of claim 1.

8. The acquisition unit When retrieving profile data, filter it based on the user's current interests 2. The system of claim 1.

Images