System

Abstract

An object of a system according to an embodiment is to effectively support communication with a person in charge of a business partner.SOLUTION: A system according to an embodiment includes an information input unit, an analysis unit, an advice providing unit, a simulation unit, and a learning unit. The information input unit inputs information on a person in charge of a business partner. The analysis part analyzes the information of the person in charge of the business connection input by the information input part. The advice providing unit provides personalized advice based on the characteristics of the person in charge of the business partner analyzed by the analysis unit. The simulation unit simulates the interaction on the basis of the advice provided by the advice providing unit. The learning unit learns actual meeting data to improve the accuracy.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 technologies do not provide sufficient means to effectively support communication with business partners, and there is room for improvement.

[0005] The system according to the embodiment aims to effectively support communication with a business partner. [Means for solving the problem]

[0006] The system according to the embodiment includes an information input unit, an analysis unit, an advice providing unit, a simulation unit, and a learning unit. The information input unit inputs information about the business contact. The analysis unit analyzes the information about the business contact input by the information input unit. The advice providing unit provides personalized advice based on the characteristics of the business contact analyzed by the analysis unit. The simulation unit simulates a dialogue based on the advice provided by the advice providing unit. The learning unit learns from actual meeting data to improve accuracy. [Effects of the Invention]

[0007] The system according to the embodiment can effectively support communication with a business partner. [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 nonvolatile storage devices that store various programs, various parameters, etc. Examples of nonvolatile 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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 client simulator according to an embodiment of the present invention is a system in which client information is input, and a generation AI understands the client's characteristics, provides personalized advice and proposal methods, simulates dialogue, learns from actual meeting data, and improves accuracy. As a result, the client simulator supports effective communication with client representatives and strengthens business.

[0029] A client simulator according to an embodiment includes an information input unit, an analysis unit, an advice providing unit, a simulation unit, and a learning unit. The information input unit inputs information about the client representative. For example, information such as the client representative's personality, past reactions, and behavior is input. The analysis unit analyzes the information about the client representative input by the information input unit. For example, a generation AI analyzes data to understand the client representative's characteristics. The advice providing unit provides personalized advice based on the client representative's characteristics analyzed by the analysis unit. For example, the generation AI suggests an optimal approach for the client representative. The simulation unit simulates a dialogue based on the advice provided by the advice providing unit. For example, the generation AI imitates the client representative's characteristics and simulates a dialogue with a user. The learning unit learns from actual meeting data to improve accuracy. For example, the generation AI learns from actual meeting data and reflects the learned data in the next advice. This enables the client simulator according to an embodiment to support effective communication with client representatives and strengthen business.

[0030] The information input unit can analyze the contact person's past email and chat history to identify the contact person's communication style and preferences. For example, the information input unit can analyze the contact person's past emails to identify frequently used phrases and language. For example, the generation AI analyzes polite language and casual expressions. The information input unit can analyze the contact person's past chat history to identify the contact person's communication tone and style. For example, the generation AI analyzes whether the contact person prefers short exchanges or detailed explanations. The information input unit can identify the contact person's preferred topics and interests based on the contact person's past email and chat history. For example, the generation AI analyzes questions and comments about specific products and services. In this way, the contact person's communication style and preferences can be identified by analyzing past email and chat history.

[0031] The information input unit can analyze the social media activity of the contact person to identify the contact person's interests. For example, the information input unit can analyze the contact person's social media posts to identify frequently mentioned topics. For example, the generation AI can analyze hobbies and interests. The information input unit can analyze the contact person's likes and comments on social media to identify content of interest. For example, the generation AI can analyze reactions to specific brands and products. The information input unit can analyze the contact person's followers and following accounts to identify areas of interest. For example, the generation AI can analyze whether the contact person follows industry influencers or experts. In this way, the contact person's interests can be identified by analyzing social media activity.

[0032] The information input unit can analyze industry news and trends for the client and provide related information. For example, the information input unit automatically collects news related to the client's industry and provides the latest trends. For example, the generation AI analyzes the latest technology and market trends in the industry. The information input unit analyzes trends related to the client's industry and provides related information. For example, the generation AI analyzes growth areas and new business opportunities in the industry. The information input unit analyzes trends of competitors related to the client's industry and provides related information. For example, the generation AI analyzes new products and services from competitors. In this way, by analyzing industry news and trends, it is possible to provide information related to the client.

[0033] The advice providing unit can analyze the past purchasing history of the client and make optimal suggestions. For example, the advice providing unit analyzes the past purchasing history of the client and identifies frequently purchased products and services. For example, the generation AI analyzes interest in a specific product category. The advice providing unit optimizes the next proposal based on the client's past purchasing history. For example, it proposes new products or services related to products previously purchased. The advice providing unit makes suggestions at specific times based on the client's past purchasing history. For example, it suggests the timing of repeat purchases for products that are purchased regularly. In this way, by analyzing past purchasing history, it is possible to make optimal suggestions to the client.

[0034] The advice providing unit can provide advice that takes into account the position and role of the client representative within the industry. For example, the advice providing unit analyzes the client representative's position within the industry and provides advice according to that role. For example, the generation AI makes strategic proposals for management. The advice providing unit analyzes the client representative's role within the industry and provides advice according to that role. For example, the generation AI makes technical proposals for technical personnel. The advice providing unit proposes the optimal approach based on the client representative's position and role within the industry. For example, the generation AI proposes a sales strategy for sales personnel. In this way, by providing advice that takes into account the client representative's position and role within the industry, it is possible to make the optimal proposal to the client representative.

[0035] The advice providing unit can provide advice that takes into account the cultural background of the client representative. For example, the advice providing unit analyzes the client representative's cultural background and provides advice that is appropriate to that culture. For example, the generation AI suggests business etiquette in a specific culture. The advice providing unit adjusts the communication style based on the client representative's cultural background. For example, the generation AI suggests the use of honorific language and how to greet. The advice providing unit suggests an appropriate approach based on the client representative's cultural background. For example, the generation AI suggests how to proceed with business negotiations and how to negotiate in a specific culture. In this way, by providing advice that takes cultural background into account, it is possible to make optimal suggestions to the client representative.

[0036] The advice providing unit can also analyze information about the client's team members and make suggestions to the entire team. The advice providing unit, for example, analyzes information about the client's team members and makes suggestions to the entire team. For example, the generation AI analyzes the team's division of roles and communication style. The advice providing unit analyzes the skill sets of the client's team members and makes optimal suggestions. For example, it can suggest members who are suitable for a particular project. The advice providing unit analyzes the past project history of the client's team members and makes suggestions to the entire team. For example, the generation AI makes suggestions based on past success stories. In this way, by analyzing team member information, it is possible to make optimal suggestions to the entire team.

[0037] The simulation unit can perform more realistic simulations using past dialogue data of the business partner. The simulation unit, for example, analyzes the business partner's past dialogue data and performs a simulation based on that data. For example, it recreates past questions and reactions. The simulation unit creates a simulation scenario based on the business partner's past dialogue data. For example, it recreates the business partner's reaction in a specific situation. The simulation unit improves the accuracy of the simulation based on the business partner's past dialogue data. For example, it learns from the past dialogue data and generates more natural dialogue. In this way, by using past dialogue data, more realistic simulations can be performed.

[0038] The simulation unit can set different scenarios and simulate multiple dialogue patterns. For example, the simulation unit sets scenarios in which the client asks different questions, and the user practices appropriate responses. For example, it simulates price negotiations or technical questions. The simulation unit sets scenarios in which the client reacts differently, and the user practices appropriate responses. For example, it simulates positive and negative reactions. The simulation unit sets scenarios in which the client is placed in different situations, and the user practices appropriate approaches. For example, it simulates the introduction of a new product or problem solving. In this way, by setting different scenarios, multiple dialogue patterns can be simulated.

[0039] The simulation unit can save the simulation results so that they can be reviewed later. For example, the simulation unit can record the content of the dialogue during the simulation and play it back later. For example, the user can check what they have said and find areas for improvement. The simulation unit can convert the content of the dialogue during the simulation into text so that it can be referenced later. For example, the flow of the dialogue and important points can be recorded in text. The simulation unit can save the simulation results in a database so that they can be analyzed later. For example, it can evaluate performance based on past simulation results. In this way, saving the simulation results makes it possible to review them later.

[0040] The learning unit can analyze audio data during meetings and learn the tone and pace of the client representative. For example, the learning unit records audio data during meetings and analyzes the tone and pace of the client representative's voice. For example, the generation AI analyzes the speaking speed and pitch of the voice. The learning unit learns the speaking characteristics of the client representative based on the audio data during meetings. For example, the generation AI analyzes the points to emphasize and the flow of the conversation. The learning unit learns the communication style of the client representative based on the audio data during meetings. For example, the generation AI analyzes how questions are asked and how responses are made. In this way, the tone and pace of the client representative can be learned by analyzing the audio data during meetings.

[0041] The learning unit also learns non-verbal reactions during meetings and can reflect them in the next advice. For example, the learning unit records the facial expressions of the client representative during a meeting and analyzes the non-verbal reactions. For example, the generation AI analyzes facial expressions such as smiles and frowns. The learning unit records the gestures of the client representative during a meeting and analyzes the non-verbal reactions. For example, the generation AI analyzes hand movements and posture. The learning unit records the gaze of the client representative during a meeting and analyzes the non-verbal reactions. For example, the gaze movement is tracked and the generation AI analyzes that gaze. In this way, non-verbal reactions during meetings can be learned and reflected in the next advice.

[0042] The learning unit can automatically generate meeting minutes so that they can be referenced later. For example, the learning unit converts audio data from a meeting into text and automatically generates minutes. For example, it records what is said and important points in text. The learning unit summarizes the content of the dialogue during the meeting and automatically generates minutes. For example, it summarizes the flow of the conversation and the conclusions. The learning unit saves meeting minutes in a database so that they can be referenced later. For example, it searches past minutes and obtains the necessary information. In this way, meeting minutes can be automatically generated so that they can be referenced later.

[0043] The learning unit can analyze the questions and interests of the contact person during a meeting and use the information to help prepare for the next meeting. For example, the learning unit can analyze the questions and interests of the contact person during a meeting and use the information to help prepare for the next meeting. For example, it can prepare materials based on the questions asked. The learning unit can analyze the interests of the contact person during a meeting and use the information to help prepare for the next meeting. For example, it can collect information on a specific topic. The learning unit can create an agenda for the next meeting based on the questions and interests of the contact person during a meeting. For example, it can prioritize important topics. In this way, analyzing the questions and interests of the contact person during a meeting can be used to help prepare for the next meeting.

[0044] The learning unit can analyze communication history with the client representative and identify successful patterns. For example, the learning unit analyzes past communication history with the client representative and identifies successful patterns. For example, the generation AI analyzes cases where a specific approach was successful. The learning unit identifies successful patterns based on past communication history with the client representative. For example, the generation AI analyzes cases where a proposal made at a specific timing was successful. The learning unit identifies the optimal approach based on past communication history with the client representative. For example, the generation AI analyzes cases where a specific topic or issue was successful. In this way, successful patterns can be identified by analyzing communication history.

[0045] The learning unit can collect feedback from contact persons and improve the accuracy of the advice provided by the generation AI. The learning unit, for example, collects feedback from contact persons and improves the accuracy of the advice provided by the generation AI. For example, the learning unit adjusts the advice based on the content of the feedback. The learning unit improves the accuracy of the advice provided by the generation AI based on feedback from contact persons. For example, the learning unit generates new advice that reflects the feedback. The learning unit continuously improves the accuracy of the advice provided by the generation AI based on feedback from contact persons. For example, the feedback is stored in a database and reflected in the next advice. In this way, the accuracy of the advice provided by the generation AI can be improved by collecting feedback from contact persons.

[0046] The learning unit can analyze the contact person's network within the industry and identify other potential business partners. For example, the learning unit analyzes the contact person's network within the industry and identifies related companies and personnel. For example, the generation AI analyzes the companies with which the contact person has relationships. The learning unit identifies other potential business partners based on the contact person's network within the industry. For example, the generation AI analyzes the companies and personnel that the contact person follows. The learning unit identifies business opportunities based on the contact person's network within the industry. For example, the generation AI analyzes the fields and markets in which the contact person is interested. In this way, other potential business partners can be identified by analyzing the network within the industry.

[0047] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0048] The Account Simulator can also analyze the contact person's health data and provide advice based on their stress level and health condition. For example, it can analyze the contact person's sleep data and suggest adjusting meeting timing if fatigue is detected. It can analyze the contact person's exercise data and suggest relaxation methods if stress levels are high. It can also analyze the contact person's dietary data and provide advice based on their health condition. This allows for more personalized advice to be provided by analyzing the contact person's health data.

[0049] The client simulator can also provide advice that takes into account the client's cultural background. For example, it can suggest appropriate business etiquette and communication styles based on the client's country or region. It can also consider the client's religious background and make suggestions that take into account specific religious ceremonies and customs. It can also suggest appropriate expressions and wording based on the client's language or dialect. By providing advice that takes cultural background into account, communication with the client can proceed smoothly.

[0050] The Account Simulator can also analyze a contact's network within the industry to identify other potential business partners. For example, it can analyze the companies and individuals with whom the contact has relationships and suggest new business opportunities. It can also analyze industry events and conferences that the contact attends to identify related companies and individuals. It can also analyze the contact's social media activity to make suggestions for expanding the contact's network within the industry. By analyzing the network within the industry, it can identify other potential business partners and expand business opportunities.

[0051] The customer simulator can also analyze the past purchasing history of the customer contact and make optimal proposals. For example, it can analyze the customer contact's past purchasing history and identify frequently purchased products and services. It can optimize the next proposal based on the customer contact's past purchasing history. It can also make proposals at specific times based on the customer contact's past purchasing history. In this way, by analyzing past purchasing history, it is possible to make optimal proposals to the customer contact.

[0052] The account simulator can also collect feedback from contact persons to improve the accuracy of the advice of the generation AI. For example, feedback from contact persons is collected to improve the accuracy of the advice of the generation AI. Based on feedback from contact persons, the accuracy of the advice of the generation AI is improved. Based on feedback from contact persons, the accuracy of the advice of the generation AI is continuously improved. In this way, by collecting feedback from contact persons, the accuracy of the advice of the generation AI can be improved.

[0053] The processing flow of the first embodiment will be briefly explained below.

[0054] Step 1: The information input unit inputs information about the person in charge of the business partner, such as the person's personality, past reactions, and behavior. Step 2: The analysis unit analyzes the information about the contact person entered by the information input unit. For example, the generation AI analyzes the data to understand the characteristics of the contact person. Step 3: The advice provider provides personalized advice based on the contact's characteristics analyzed by the analysis unit. For example, a generative AI suggests the optimal approach for the contact. Step 4: The simulation unit simulates a dialogue based on the advice provided by the advice providing unit. For example, the generation AI imitates the characteristics of the client and simulates a dialogue with the user. Step 5: The learning unit learns from actual meeting data and improves accuracy. For example, the generation AI learns from actual meeting data and reflects this in the next advice.

[0055] (Example 2) A client simulator according to an embodiment of the present invention is a system in which client information is input, and a generation AI understands the client's characteristics, provides personalized advice and proposal methods, simulates dialogue, learns from actual meeting data, and improves accuracy. As a result, the client simulator supports effective communication with client representatives and strengthens business.

[0056] A client simulator according to an embodiment includes an information input unit, an analysis unit, an advice providing unit, a simulation unit, and a learning unit. The information input unit inputs information about the client representative. For example, information such as the client representative's personality, past reactions, and behavior is input. The analysis unit analyzes the information about the client representative input by the information input unit. For example, a generation AI analyzes data to understand the client representative's characteristics. The advice providing unit provides personalized advice based on the client representative's characteristics analyzed by the analysis unit. For example, the generation AI suggests an optimal approach for the client representative. The simulation unit simulates a dialogue based on the advice provided by the advice providing unit. For example, the generation AI imitates the client representative's characteristics and simulates a dialogue with a user. The learning unit learns from actual meeting data to improve accuracy. For example, the generation AI learns from actual meeting data and reflects the learned data in the next advice. This enables the client simulator according to an embodiment to support effective communication with client representatives and strengthen business.

[0057] The information input unit analyzes the non-verbal behavior of the client representative, enabling a deeper understanding of the client representative's personality and reactions. The information input unit, for example, analyzes the client representative's facial expressions to identify emotions such as joy, anger, sadness, and happiness. For example, facial expressions such as a smile or furrowed brow during a meeting are captured with a camera, and the generation AI analyzes those emotions. The information input unit analyzes the client representative's gestures to identify their communication style. For example, hand movements and posture are captured with a camera, and the generation AI analyzes those gestures. The information input unit analyzes the client representative's gaze to identify points of interest. For example, eye movement is tracked, and the generation AI analyzes that gaze. This enables a deeper understanding by analyzing the client representative's non-verbal behavior.

[0058] The information input unit can analyze the contact person's past email and chat history to identify the contact person's communication style and preferences. For example, the information input unit can analyze the contact person's past emails to identify frequently used phrases and language. For example, the generation AI analyzes polite language and casual expressions. The information input unit can analyze the contact person's past chat history to identify the contact person's communication tone and style. For example, the generation AI analyzes whether the contact person prefers short exchanges or detailed explanations. The information input unit can identify the contact person's preferred topics and interests based on the contact person's past email and chat history. For example, the generation AI analyzes questions and comments about specific products and services. In this way, the contact person's communication style and preferences can be identified by analyzing past email and chat history.

[0059] The information input unit uses the emotion estimation function to analyze changes in the emotions of the client representative in real time and propose appropriate responses. For example, the information input unit analyzes the facial expressions of the client representative during a meeting in real time to identify changes in emotions. For example, the generation AI analyzes changes from a smile to a serious expression. The information input unit analyzes the tone of the client representative's voice in real time to identify changes in emotions. For example, the generation AI analyzes changes in voice pitch and speed. The information input unit analyzes the client representative's body temperature and heart rate in real time to identify changes in emotions. For example, the generation AI analyzes increases in body temperature and fluctuations in heart rate. In this way, by using the emotion estimation function, changes in the emotions of the client representative can be analyzed in real time and appropriate responses can be proposed.

[0060] The information input unit can analyze the social media activity of the contact person to identify the contact person's interests. For example, the information input unit can analyze the contact person's social media posts to identify frequently mentioned topics. For example, the generation AI can analyze hobbies and interests. The information input unit can analyze the contact person's likes and comments on social media to identify content of interest. For example, the generation AI can analyze reactions to specific brands and products. The information input unit can analyze the contact person's followers and following accounts to identify areas of interest. For example, the generation AI can analyze whether the contact person follows industry influencers or experts. In this way, the contact person's interests can be identified by analyzing social media activity.

[0061] The information input unit can analyze industry news and trends for the client and provide related information. For example, the information input unit automatically collects news related to the client's industry and provides the latest trends. For example, the generation AI analyzes the latest technology and market trends in the industry. The information input unit analyzes trends related to the client's industry and provides related information. For example, the generation AI analyzes growth areas and new business opportunities in the industry. The information input unit analyzes trends of competitors related to the client's industry and provides related information. For example, the generation AI analyzes new products and services from competitors. In this way, by analyzing industry news and trends, it is possible to provide information related to the client.

[0062] The information input unit can use the emotion estimation function to generate customized presentation materials based on the emotions of the client. The information input unit, for example, customizes the content of the presentation materials based on the client's emotion data. For example, the generation AI selects images and graphs that elicit positive emotions. The information input unit customizes the tone and style of the presentation materials based on the client's emotion data. For example, the generation AI selects colors and fonts to create a relaxed atmosphere. The information input unit adjusts the content of the presentation materials based on the client's emotion data. For example, detailed data and specific examples can be added to attract the client's attention. In this way, the emotion estimation function can be used to generate customized presentation materials based on the client's emotions.

[0063] The advice providing unit can analyze the past purchasing history of the client and make optimal suggestions. For example, the advice providing unit analyzes the past purchasing history of the client and identifies frequently purchased products and services. For example, the generation AI analyzes interest in a specific product category. The advice providing unit optimizes the next proposal based on the client's past purchasing history. For example, it proposes new products or services related to products previously purchased. The advice providing unit makes suggestions at specific times based on the client's past purchasing history. For example, it suggests the timing of repeat purchases for products that are purchased regularly. In this way, by analyzing past purchasing history, it is possible to make optimal suggestions to the client.

[0064] The advice providing unit can provide advice that takes into account the position and role of the client representative within the industry. For example, the advice providing unit analyzes the client representative's position within the industry and provides advice according to that role. For example, the generation AI makes strategic proposals for management. The advice providing unit analyzes the client representative's role within the industry and provides advice according to that role. For example, the generation AI makes technical proposals for technical personnel. The advice providing unit proposes the optimal approach based on the client representative's position and role within the industry. For example, the generation AI proposes a sales strategy for sales personnel. In this way, by providing advice that takes into account the client representative's position and role within the industry, it is possible to make the optimal proposal to the client representative.

[0065] The advice providing unit can use the emotion estimation function to provide advice in real time that corresponds to the emotions of the client representative. The advice providing unit, for example, analyzes the emotions of the client representative in real time and provides advice that corresponds to those emotions. For example, if the client is nervous, the generation AI will make a suggestion to help them relax. The advice providing unit analyzes the emotions of the client representative in real time and proposes an approach that corresponds to those emotions. For example, the generation AI will suggest a topic that will bring out positive emotions. The advice providing unit analyzes the emotions of the client representative in real time and proposes a response that corresponds to those emotions. For example, if the client is feeling angry, the generation AI will suggest a way to respond calmly. In this way, by using the emotion estimation function, advice that corresponds to the emotions of the client representative can be provided in real time.

[0066] The advice providing unit can provide advice that takes into account the cultural background of the client representative. For example, the advice providing unit analyzes the client representative's cultural background and provides advice that is appropriate to that culture. For example, the generation AI suggests business etiquette in a specific culture. The advice providing unit adjusts the communication style based on the client representative's cultural background. For example, the generation AI suggests the use of honorific language and how to greet. The advice providing unit suggests an appropriate approach based on the client representative's cultural background. For example, the generation AI suggests how to proceed with business negotiations and how to negotiate in a specific culture. In this way, by providing advice that takes cultural background into account, it is possible to make optimal suggestions to the client representative.

[0067] The advice providing unit can also analyze information about the client's team members and make suggestions to the entire team. The advice providing unit, for example, analyzes information about the client's team members and makes suggestions to the entire team. For example, the generation AI analyzes the team's division of roles and communication style. The advice providing unit analyzes the skill sets of the client's team members and makes optimal suggestions. For example, it can suggest members who are suitable for a particular project. The advice providing unit analyzes the past project history of the client's team members and makes suggestions to the entire team. For example, the generation AI makes suggestions based on past success stories. In this way, by analyzing team member information, it is possible to make optimal suggestions to the entire team.

[0068] The advice providing unit can use the emotion estimation function to generate a follow-up email template based on the emotions of the client representative. The advice providing unit, for example, customizes the follow-up email template based on the client representative's emotion data. For example, the generation AI selects expressions that will elicit positive emotions. The advice providing unit adjusts the content of the follow-up email based on the client representative's emotion data. For example, it suggests expressions to express gratitude and next actions. The advice providing unit customizes the tone and style of the follow-up email based on the client representative's emotion data. For example, the generation AI selects wording and formatting that will create a relaxed atmosphere. In this way, by using the emotion estimation function, a follow-up email template can be generated based on the client representative's emotions.

[0069] The simulation unit can perform more realistic simulations using past dialogue data of the business partner. The simulation unit, for example, analyzes the business partner's past dialogue data and performs a simulation based on that data. For example, it recreates past questions and reactions. The simulation unit creates a simulation scenario based on the business partner's past dialogue data. For example, it recreates the business partner's reaction in a specific situation. The simulation unit improves the accuracy of the simulation based on the business partner's past dialogue data. For example, it learns from the past dialogue data and generates more natural dialogue. In this way, by using past dialogue data, more realistic simulations can be performed.

[0070] The simulation unit can use the emotion estimation function to analyze the user's emotions during the simulation and provide appropriate feedback. For example, the simulation unit analyzes the user's facial expressions during the simulation in real time to identify changes in emotions. For example, the generation AI analyzes states of tension and relaxation. The simulation unit analyzes the user's tone of voice during the simulation in real time to identify changes in emotions. For example, the generation AI analyzes changes in voice pitch and speed. The simulation unit analyzes the user's biometric data (heart rate and electrodermal activity) during the simulation in real time to identify changes in emotions. For example, the generation AI analyzes fluctuations in heart rate. In this way, the emotion estimation function can be used to analyze the user's emotions during the simulation and provide appropriate feedback.

[0071] The simulation unit can set different scenarios and simulate multiple dialogue patterns. For example, the simulation unit sets scenarios in which the client asks different questions, and the user practices appropriate responses. For example, it simulates price negotiations or technical questions. The simulation unit sets scenarios in which the client reacts differently, and the user practices appropriate responses. For example, it simulates positive and negative reactions. The simulation unit sets scenarios in which the client is placed in different situations, and the user practices appropriate approaches. For example, it simulates the introduction of a new product or problem solving. In this way, by setting different scenarios, multiple dialogue patterns can be simulated.

[0072] The simulation unit can save the simulation results so that they can be reviewed later. For example, the simulation unit can record the content of the dialogue during the simulation and play it back later. For example, the user can check what they have said and find areas for improvement. The simulation unit can convert the content of the dialogue during the simulation into text so that it can be referenced later. For example, the flow of the dialogue and important points can be recorded in text. The simulation unit can save the simulation results in a database so that they can be analyzed later. For example, it can evaluate performance based on past simulation results. In this way, saving the simulation results makes it possible to review them later.

[0073] The simulation unit can use the emotion estimation function to display the emotions of the business partner during the simulation in real time, allowing the user to respond appropriately. The simulation unit, for example, analyzes the facial expressions of the business partner during the simulation in real time and displays changes in emotions. For example, it displays a smile or a serious expression in real time. The simulation unit analyzes the tone of voice of the business partner during the simulation in real time and displays changes in emotions. For example, it displays changes in voice pitch and speed in real time. The simulation unit analyzes the biometric data (heart rate and electrodermal activity) of the business partner during the simulation in real time and displays changes in emotions. For example, it displays fluctuations in heart rate in real time. In this way, by using the emotion estimation function, the emotions of the business partner during the simulation can be displayed in real time, allowing the user to respond appropriately.

[0074] The learning unit can analyze audio data during meetings and learn the tone and pace of the client representative. For example, the learning unit records audio data during meetings and analyzes the tone and pace of the client representative's voice. For example, the generation AI analyzes the speaking speed and pitch of the voice. The learning unit learns the speaking characteristics of the client representative based on the audio data during meetings. For example, the generation AI analyzes the points to emphasize and the flow of the conversation. The learning unit learns the communication style of the client representative based on the audio data during meetings. For example, the generation AI analyzes how questions are asked and how responses are made. In this way, the tone and pace of the client representative can be learned by analyzing the audio data during meetings.

[0075] The learning unit also learns non-verbal reactions during meetings and can reflect them in the next advice. For example, the learning unit records the facial expressions of the client representative during a meeting and analyzes the non-verbal reactions. For example, the generation AI analyzes facial expressions such as smiles and frowns. The learning unit records the gestures of the client representative during a meeting and analyzes the non-verbal reactions. For example, the generation AI analyzes hand movements and posture. The learning unit records the gaze of the client representative during a meeting and analyzes the non-verbal reactions. For example, the gaze movement is tracked and the generation AI analyzes that gaze. In this way, non-verbal reactions during meetings can be learned and reflected in the next advice.

[0076] The learning unit uses the emotion estimation function to learn changes in the emotions of the client representative during a meeting and reflect this in the next advice. For example, the learning unit analyzes the facial expressions of the client representative during a meeting in real time to learn changes in emotions. For example, the generation AI analyzes changes from a smile to a serious expression. The learning unit analyzes the tone of the client representative's voice during a meeting in real time to learn changes in emotions. For example, the generation AI analyzes changes in voice pitch and speed. The learning unit analyzes the client representative's biometric data (heart rate and electrodermal activity) during a meeting in real time to learn changes in emotions. For example, the generation AI analyzes fluctuations in heart rate. In this way, the emotion estimation function can learn changes in the client representative's emotions during a meeting and reflect this in the next advice.

[0077] The learning unit can automatically generate meeting minutes so that they can be referenced later. For example, the learning unit converts audio data from a meeting into text and automatically generates minutes. For example, it records what is said and important points in text. The learning unit summarizes the content of the dialogue during the meeting and automatically generates minutes. For example, it summarizes the flow of the conversation and the conclusions. The learning unit saves meeting minutes in a database so that they can be referenced later. For example, it searches past minutes and obtains the necessary information. In this way, meeting minutes can be automatically generated so that they can be referenced later.

[0078] The learning unit can analyze the questions and interests of the contact person during a meeting and use the information to help prepare for the next meeting. For example, the learning unit can analyze the questions and interests of the contact person during a meeting and use the information to help prepare for the next meeting. For example, it can prepare materials based on the questions asked. The learning unit can analyze the interests of the contact person during a meeting and use the information to help prepare for the next meeting. For example, it can collect information on a specific topic. The learning unit can create an agenda for the next meeting based on the questions and interests of the contact person during a meeting. For example, it can prioritize important topics. In this way, analyzing the questions and interests of the contact person during a meeting can be used to help prepare for the next meeting.

[0079] The learning unit can use the emotion estimation function to suggest follow-up actions based on the emotions of the client representative during a meeting. For example, the learning unit analyzes the emotions of the client representative during a meeting in real time and suggests follow-up actions. For example, it suggests closing the deal the moment positive emotions rise. The learning unit analyzes the emotions of the client representative during a meeting in real time and uses this information to help prepare for the next meeting. For example, it suggests actions to resolve the problem when negative emotions rise. The learning unit analyzes the emotions of the client representative during a meeting in real time and suggests appropriate follow-up actions. For example, it suggests sending an email expressing gratitude. In this way, the emotion estimation function can be used to suggest follow-up actions based on the emotions of the client representative during a meeting.

[0080] The learning unit can analyze communication history with the client representative and identify successful patterns. For example, the learning unit analyzes past communication history with the client representative and identifies successful patterns. For example, the generation AI analyzes cases where a specific approach was successful. The learning unit identifies successful patterns based on past communication history with the client representative. For example, the generation AI analyzes cases where a proposal made at a specific timing was successful. The learning unit identifies the optimal approach based on past communication history with the client representative. For example, the generation AI analyzes cases where a specific topic or issue was successful. In this way, successful patterns can be identified by analyzing communication history.

[0081] The learning unit can collect feedback from contact persons and improve the accuracy of the advice provided by the generation AI. The learning unit, for example, collects feedback from contact persons and improves the accuracy of the advice provided by the generation AI. For example, the learning unit adjusts the advice based on the content of the feedback. The learning unit improves the accuracy of the advice provided by the generation AI based on feedback from contact persons. For example, the learning unit generates new advice that reflects the feedback. The learning unit continuously improves the accuracy of the advice provided by the generation AI based on feedback from contact persons. For example, the feedback is stored in a database and reflected in the next advice. In this way, the accuracy of the advice provided by the generation AI can be improved by collecting feedback from contact persons.

[0082] The learning unit can use the emotion estimation function to formulate a long-term communication strategy based on the emotions of the client. The learning unit, for example, formulates a long-term communication strategy based on the emotion data of the client. For example, it proposes an approach to elicit positive emotions. The learning unit adjusts the long-term communication strategy based on the emotion data of the client. For example, it proposes an approach to reduce negative emotions. The learning unit optimizes the long-term communication strategy based on the emotion data of the client. For example, it proposes a flexible approach in response to changes in emotions. In this way, by using the emotion estimation function, a long-term communication strategy based on the emotions of the client can be formulated.

[0083] The learning unit can analyze the contact person's network within the industry and identify other potential business partners. For example, the learning unit analyzes the contact person's network within the industry and identifies related companies and personnel. For example, the generation AI analyzes the companies with which the contact person has relationships. The learning unit identifies other potential business partners based on the contact person's network within the industry. For example, the generation AI analyzes the companies and personnel that the contact person follows. The learning unit identifies business opportunities based on the contact person's network within the industry. For example, the generation AI analyzes the fields and markets in which the contact person is interested. In this way, other potential business partners can be identified by analyzing the network within the industry.

[0084] The learning unit can use the emotion estimation function to implement customized marketing campaigns based on the emotions of contact persons. The learning unit, for example, implements customized marketing campaigns based on the emotional data of contact persons. For example, the generation AI suggests messages that elicit positive emotions. The learning unit adjusts the content of the marketing campaign based on the emotional data of contact persons. For example, the generation AI suggests promotions and offers that correspond to the emotions. The learning unit optimizes the timing of the marketing campaign based on the emotional data of contact persons. For example, the generation AI suggests a campaign that coincides with the peak of emotions. In this way, by using the emotion estimation function, it is possible to implement customized marketing campaigns based on the emotions of contact persons.

[0085] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0086] The Account Simulator can also analyze the contact person's health data and provide advice based on their stress level and health condition. For example, it can analyze the contact person's sleep data and suggest adjusting meeting timing if fatigue is detected. It can analyze the contact person's exercise data and suggest relaxation methods if stress levels are high. It can also analyze the contact person's dietary data and provide advice based on their health condition. This allows for more personalized advice to be provided by analyzing the contact person's health data.

[0087] The client simulator can also provide advice that takes into account the client's cultural background. For example, it can suggest appropriate business etiquette and communication styles based on the client's country or region. It can also consider the client's religious background and make suggestions that take into account specific religious ceremonies and customs. It can also suggest appropriate expressions and wording based on the client's language or dialect. By providing advice that takes cultural background into account, communication with the client can proceed smoothly.

[0088] The Account Simulator can also analyze a contact's network within the industry to identify other potential business partners. For example, it can analyze the companies and individuals with whom the contact has relationships and suggest new business opportunities. It can also analyze industry events and conferences that the contact attends to identify related companies and individuals. It can also analyze the contact's social media activity to make suggestions for expanding the contact's network within the industry. By analyzing the network within the industry, it can identify other potential business partners and expand business opportunities.

[0089] The customer simulator can also analyze the past purchasing history of the customer contact and make optimal proposals. For example, it can analyze the customer contact's past purchasing history and identify frequently purchased products and services. It can optimize the next proposal based on the customer contact's past purchasing history. It can also make proposals at specific times based on the customer contact's past purchasing history. In this way, by analyzing past purchasing history, it is possible to make optimal proposals to the customer contact.

[0090] The account simulator can also collect feedback from contact persons to improve the accuracy of the advice of the generation AI. For example, feedback from contact persons is collected to improve the accuracy of the advice of the generation AI. Based on feedback from contact persons, the accuracy of the advice of the generation AI is improved. Based on feedback from contact persons, the accuracy of the advice of the generation AI is continuously improved. In this way, by collecting feedback from contact persons, the accuracy of the advice of the generation AI can be improved.

[0091] The customer simulator can also use the emotion estimation function to generate customized presentation materials based on the customer's emotions. For example, the content of the presentation materials can be customized based on the customer's emotion data. The tone and style of the presentation materials can be customized based on the customer's emotion data. The content of the presentation materials can be adjusted based on the customer's emotion data. In this way, the emotion estimation function can be used to generate customized presentation materials based on the customer's emotions.

[0092] The customer simulator can also use the emotion estimation function to provide advice in real time based on the emotions of the customer representative. For example, it can analyze the customer representative's emotions in real time and provide advice based on those emotions. It can analyze the customer representative's emotions in real time and suggest an approach based on those emotions. It can analyze the customer representative's emotions in real time and suggest a response based on those emotions. In this way, by using the emotion estimation function, it is possible to provide advice in real time based on the customer representative's emotions.

[0093] The Account Simulator can also use the emotion estimation function to generate follow-up email templates based on the emotions of the contact. For example, customize the follow-up email template based on the emotion data of the contact. Adjust the content of the follow-up email based on the emotion data of the contact. Customize the tone and style of the follow-up email based on the emotion data of the contact. Thus, by using the emotion estimation function, it is possible to generate follow-up email templates based on the emotions of the contact.

[0094] The trading partner simulator can also use the emotion estimation function to analyze the emotions of the user during the simulation and provide appropriate feedback. For example, the user's facial expressions during the simulation can be analyzed in real time to identify changes in emotions. The tone of the user's voice during the simulation can be analyzed in real time to identify changes in emotions. The user's biometric data (heart rate and electrodermal activity) can be analyzed in real time to identify changes in emotions. As a result, the emotion estimation function can be used to analyze the user's emotions during the simulation and provide appropriate feedback.

[0095] The customer simulator can also use the emotion estimation function to formulate a long-term communication strategy based on the emotions of the customer representative. For example, a long-term communication strategy is formulated based on the emotion data of the customer representative. A long-term communication strategy is adjusted based on the emotion data of the customer representative. A long-term communication strategy is optimized based on the emotion data of the customer representative. In this way, by using the emotion estimation function, a long-term communication strategy based on the emotions of the customer representative can be formulated.

[0096] The processing flow of the second embodiment will be briefly explained below.

[0097] Step 1: The information input unit inputs information about the person in charge of the business partner, such as the person's personality, past reactions, and behavior. Step 2: The analysis unit analyzes the information about the contact person entered by the information input unit. For example, the generation AI analyzes the data to understand the characteristics of the contact person. Step 3: The advice provider provides personalized advice based on the contact's characteristics analyzed by the analysis unit. For example, a generative AI suggests the optimal approach for the contact. Step 4: The simulation unit simulates a dialogue based on the advice provided by the advice providing unit. For example, the generation AI imitates the characteristics of the client and simulates a dialogue with the user. Step 5: The learning unit learns from actual meeting data and improves accuracy. For example, the generation AI learns from actual meeting data and reflects this in the next advice.

[0098] 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.

[0099] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<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.

[0100] 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.

[0101] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0102] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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).

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0111] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0124] 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.

[0125] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0126] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0142] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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."

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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. [Explanation of symbols]

[0165] 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 information input section for inputting information about the business contact; an analysis unit that analyzes the information of the person in charge of the business partner input by the information input unit; an advice providing unit that provides personalized advice based on the characteristics of the customer contact analyzed by the analysis unit; a simulation unit that simulates a dialogue based on the advice provided by the advice providing unit; A system characterized by comprising a learning unit that learns from actual meeting data and improves accuracy.

2. The information input unit The system according to claim 1, characterized in that it uses an emotion estimation function to analyze changes in the emotions of the customer representative in real time and propose appropriate responses.

3. The information input unit 10. The system of claim 1, further comprising analyzing the social media activity of the contact to identify the contact's interests.

4. The advice providing unit The system according to claim 1, characterized in that the system analyzes the past purchasing history of the person in charge of the business partner and makes optimal proposals.

5. The simulation unit 2. The system of claim 1, wherein past interaction data of the business contact is used to perform a more realistic simulation.

6. The learning unit 10. The system of claim 1, wherein audio data during a meeting is analyzed to learn the tone and pace of the contact.

7. The learning unit The system of claim 1 , further comprising: a sentiment estimation function for developing a long-term communication strategy based on the sentiment of the contact person.

8. The advice providing unit The system according to claim 1, wherein an emotion estimation function is used to provide advice in real time according to the emotion of the customer representative.

Images