System

Abstract

The system according to the embodiment aims to provide a quick and personalized response to an inquiry from a user.SOLUTION: A system according to an embodiment includes a reception unit, an answer unit, a feature reflection unit, and a cooperation unit. The reception unit receives an inquiry from a user. The answerer provides an answer to the inquiry received by the receiver. The feature reflection unit reflects the feature of the actual salesperson of the avatar based on the answer provided by the answer unit. The cooperation unit performs cooperation between the avatar and the actual salesperson based on the feature reflected by the feature reflection unit.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 have had the problem of making it difficult to respond to user inquiries in a prompt and personalized manner.

[0005] The system according to the embodiment aims to provide a quick and personalized response to inquiries from users. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a response unit, a feature reflection unit, and a linking unit. The reception unit receives inquiries from users. The response unit allows an avatar to provide an answer to the inquiry received by the reception unit. The feature reflection unit reflects the features of a real sales representative in the avatar based on the answer provided by the response unit. The linking unit links the avatar with the real sales representative based on the features reflected by the feature reflection unit. [Effects of the Invention]

[0007] The system according to the embodiment can provide a quick and personalized response to inquiries from users. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) In a system according to an embodiment of the present invention, when a user makes an inquiry about a company's products or services, an avatar that inherits the characteristics of the company's actual salesperson responds in a chat-style manner. In this system, when a user asks a question about a company's products or services, the avatar provides a real-time answer. The avatar reflects the characteristics of the actual salesperson, allowing the user to experience speaking with a real salesperson. Furthermore, through chat interactions with the avatar, the user can conduct a business negotiation with the actual salesperson. For example, if a user wants to know more about a specific product, the avatar provides information about the product and, if necessary, arranges a business negotiation with a real salesperson. This system is expected to enable users to efficiently obtain information and facilitate smooth communication with companies. This system allows users to efficiently obtain information about a company's products and services, thereby facilitating smooth communication with companies.

[0029] An information provision system according to an embodiment includes a reception unit, a response unit, a feature reflection unit, and a linking unit. The reception unit receives an inquiry from a user. The inquiry may include, but is not limited to, text, voice, or image. The reception unit may receive, for example, a text-based inquiry. The reception unit may also receive voice-based inquiries. The reception unit may also receive image-based inquiries. For example, the reception unit receives a text message sent by a user and inputs it into the system. In the case of a voice message, the message is converted into text using voice recognition technology. In the case of an image message, the message content is analyzed using image analysis technology. The response unit provides an avatar with a response to the user's inquiry. The response unit may generate a response by utilizing, for example, a database of products and services provided by a company. For example, the response unit may retrieve product information from a database and provide it to the user. The response unit may also retrieve service information from a database and provide it to the user. The response unit may also use natural language processing technology to generate an appropriate response to the user's question. For example, the response unit may analyze the user's question and generate an appropriate response. The feature reflection unit reflects the features of a real salesperson in the avatar. The feature reflection unit, for example, learns the voice, speaking style, facial expressions, etc. of the salesperson. For example, the feature reflection unit collects voice data of the salesperson and reflects it in the avatar. The feature reflection unit can also learn the speaking style characteristics of the salesperson and reflect them in the avatar. The feature reflection unit can also learn the facial expression characteristics of the salesperson and reflect them in the avatar. For example, the feature reflection unit inputs the voice data of the salesperson into the generation AI and extracts the voice features. The collaboration unit collaborates between the avatar and the real salesperson. For example, the collaboration unit records the avatar's interactions with the user and provides that information to the real salesperson. For example, the collaboration unit records information provided by the avatar in response to the user's questions and the user's interests, and provides that information to the real salesperson. The collaboration unit can also arrange business meetings between the avatar and the real salesperson. For example, if a user wants to know more about a particular product, the collaboration unit arranges a business meeting with a real sales representative.As a result, the information providing system according to the embodiment allows the avatar to respond to the user's inquiries in real time, enabling smooth collaboration with real sales representatives.

[0030] The answering unit includes a database utilization unit that utilizes a database related to the company's products and services. The database utilization unit utilizes the database related to the company's products and services. The database includes, for example, product information, service information, search algorithms, etc., but is not limited to these examples. The database utilization unit, for example, obtains product information from the database and provides it to the user. The database utilization unit can also obtain service information from the database and provide it to the user. The database utilization unit can also use a search algorithm to search for information appropriate to the user's question. For example, the database utilization unit analyzes the user's question and searches the database for related information. In this way, by utilizing the database, it is possible to provide the user with a quick and accurate answer.

[0031] The collaboration unit includes a recording unit that records the avatar's interactions with the user. The recording unit records the avatar's interactions with the user. Recording includes, but is not limited to, for example, a text log, an audio recording, and a method for saving the records. For example, the recording unit records a text log. The recording unit can also perform audio recording. The recording unit can also provide a method for saving the recorded information. For example, the recording unit records a text message sent by the user and saves it in the system. In the case of an audio message, the audio is recorded and saved in the system. In this way, by recording interactions with the user, a real sales representative can smoothly proceed with the sales negotiations.

[0032] The recording unit includes an information providing unit that provides the recorded information to a real sales representative. The information providing unit provides the recorded information to the real sales representative. The information providing includes, for example, the type of information to be provided and the method of providing it, but is not limited to these examples. For example, the information providing unit provides the real sales representative with information provided in response to a user's question. The information providing unit can also provide the real sales representative with the user's interests, etc. The information providing unit can also provide a method for providing the recorded information to the real sales representative. For example, the information providing unit provides the real sales representative with a recorded text log. In the case of an audio recording, the recorded audio is provided to the real sales representative. In this way, by providing the recorded information to the real sales representative, preparation for a business negotiation can be efficiently carried out.

[0033] The feature reflection unit can learn the voice, speaking style, facial expressions, etc. of the sales representative. The feature reflection unit can learn, for example, the voice, speaking style, facial expressions, etc. of the sales representative. Learning can include, for example, machine learning algorithms, types of learning data, etc., but is not limited to these examples. The feature reflection unit can, for example, collect voice data of the sales representative and reflect it in the avatar. The feature reflection unit can also learn the speaking style characteristics of the sales representative and reflect them in the avatar. The feature reflection unit can also learn the facial expressions of the sales representative and reflect them in the avatar. For example, the feature reflection unit inputs the voice data of the sales representative into the generation AI and extracts the voice characteristics. In this way, by learning the characteristics of the sales representative, the avatar can respond more realistically.

[0034] The collaboration unit can arrange a business meeting between an avatar and a real sales representative. For example, the collaboration unit arranges a business meeting between an avatar and a real sales representative. The business meeting includes, for example, the format of the business meeting and the method of proceeding with the business meeting, but is not limited to these examples. For example, the collaboration unit arranges a business meeting with a real sales representative when the user wants to know more about a specific product. The collaboration unit can also arrange the format of the business meeting. The collaboration unit can also arrange the method of proceeding with the business meeting. For example, the collaboration unit arranges a business meeting with a real sales representative based on the format of the business meeting desired by the user. In this way, by arranging a business meeting between an avatar and a real sales representative, the user can conduct the business meeting smoothly.

[0035] The reception unit can analyze the user's past inquiry history and select the optimal reception method. The reception unit, for example, analyzes the user's past inquiry history and selects the optimal reception method. The past inquiry history includes, for example, a history storage method, an analysis algorithm, etc., but is not limited to these examples. The reception unit, for example, automatically displays the content of inquiries the user has frequently made in the past as candidates. The reception unit can also prioritize and suggest input methods (voice, text, etc.) that the user has used in the past. The reception unit can also predict and suggest the content of inquiries to be made during a specific time period based on the user's past inquiry history. For example, the reception unit inputs the user's past inquiry history into a generation AI and selects the optimal reception method. In this way, the optimal reception method can be provided to the user by analyzing the past inquiry history.

[0036] The reception unit may filter inquiries based on the user's current areas of interest when receiving the inquiries. For example, the reception unit may filter inquiries based on the user's current areas of interest when receiving the inquiries. Identification of areas of interest may include, but is not limited to, survey results, past behavioral history, etc. For example, the reception unit may preferentially display related inquiries based on keywords recently searched by the user. The reception unit may also suggest related inquiries based on products or services in which the user has shown interest in the past. The reception unit may also analyze the user's social media activity and display inquiries related to the user's current areas of interest. For example, the reception unit may input the user's social media activity into a generation AI to identify areas of interest. By filtering based on the user's current areas of interest, it is possible to preferentially receive highly relevant inquiries.

[0037] The reception unit can select the optimal reception means depending on the user's input method when receiving an inquiry. For example, the reception unit selects the optimal reception means depending on the user's input method (voice, text, image, etc.) when receiving an inquiry. The selection of the input method includes, but is not limited to, voice input, text input, image input, etc. For example, when a user makes an inquiry by voice, the reception unit uses voice recognition technology to quickly receive the inquiry. Furthermore, when a user makes an inquiry by text, the reception unit can also use text analysis technology to accurately receive the inquiry. Furthermore, when a user makes an inquiry using an image, the reception unit can extract related information using image recognition technology and receive the inquiry. For example, the reception unit inputs the user's voice data into a generation AI and performs voice recognition. This enables efficient inquiry reception by selecting the optimal reception means depending on the user's input method.

[0038] When receiving an inquiry, the reception unit can prioritize receiving highly relevant inquiries by taking into account the user's geographical location information. For example, when receiving an inquiry, the reception unit prioritizes receiving highly relevant inquiries by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data, location information services, etc. For example, when the user is in a specific area, the reception unit prioritizes receiving inquiries related to that area. Furthermore, when the user is traveling, the reception unit can prioritize receiving inquiries related to the user's travel destination. Furthermore, when the user is at home, the reception unit can prioritize receiving inquiries related to services around the user's home. For example, the reception unit inputs the user's location information data into a generation AI to identify highly relevant inquiries. In this way, highly relevant inquiries can be prioritized by taking into account the user's geographical location information.

[0039] The reception unit can analyze the user's social media activity when receiving an inquiry and receive related inquiries. For example, the reception unit analyzes the user's social media activity when receiving an inquiry and receives related inquiries. Analysis of social media activity includes, but is not limited to, analysis of post content and follower analysis. For example, the reception unit preferentially receives inquiries related to products or services mentioned by the user on social media. The reception unit can also analyze the user's social media posts and receive related inquiries. The reception unit can also receive related inquiries by referring to the activities of the user's friends on social media. For example, the reception unit inputs the user's social media data into a generation AI to identify related inquiries. In this way, by analyzing the user's social media activity, it is possible to preferentially receive highly relevant inquiries.

[0040] The reception unit can customize the reception method by reflecting the user's past feedback when receiving an inquiry. For example, the reception unit customizes the reception method by reflecting the user's past feedback when receiving an inquiry. Examples of feedback collection include, but are not limited to, questionnaires and user reviews. For example, the reception unit suggests an optimal reception method based on feedback provided by the user in the past. The reception unit can also preferentially suggest a specific reception method based on the user's past feedback. The reception unit can also analyze the user's past feedback and customize the reception method. For example, the reception unit inputs the user's feedback data into a generation AI to select the optimal reception method. In this way, the optimal reception method can be provided by reflecting the user's past feedback.

[0041] The answering unit can adjust the level of detail of the answer based on the importance of the inquiry when answering. For example, the answering unit adjusts the level of detail of the answer based on the importance of the inquiry when answering. The evaluation of the importance includes, but is not limited to, for example, the content of the inquiry and the attributes of the user. For example, the answering unit provides an answer including detailed information for an important inquiry. The answering unit can also provide a concise answer for a general inquiry. The answering unit can also provide an answer that focuses on the main points for a quick response to an urgent inquiry. For example, the answering unit inputs the user's inquiry data into a generation AI and evaluates the importance. As a result, the level of detail of the answer can be adjusted based on the importance of the inquiry, thereby providing appropriate information.

[0042] The answering unit can apply different answering algorithms depending on the category of the inquiry when answering. For example, the answering unit applies different answering algorithms depending on the category of the inquiry when answering. Category classifications include, but are not limited to, product categories and service categories. For example, the answering unit applies an answering algorithm based on a product database to an inquiry about a product. The answering unit can also apply an answering algorithm based on a service database to an inquiry about a service. The answering unit can also apply an answering algorithm based on a technical database to a technical inquiry. For example, the answering unit inputs the user's inquiry data into a generation AI to identify the category. This allows a more accurate answer to be provided by applying an appropriate answering algorithm depending on the category of the inquiry.

[0043] The answering unit can improve the accuracy of the answer by referring to the user's past answer results when providing an answer. For example, the answering unit can improve the accuracy of the answer by referring to the user's past answer results when providing an answer. The use of past answer results includes, but is not limited to, the accuracy of the answer and the user's satisfaction. For example, the answering unit provides an optimal answer based on answers the user has received in the past. The answering unit can also provide related information from the user's past answer results. The answering unit can also analyze the user's past answer history to improve the accuracy of the answer. For example, the answering unit inputs the user's past answer data into a generation AI to generate an optimal answer. In this way, the accuracy of the answer can be improved by referring to the user's past answer results.

[0044] The answering unit can determine the priority of the answer based on the time of submission of the inquiry when making an answer. For example, the answering unit determines the priority of the answer based on the time of submission of the inquiry when making an answer. Acquiring the submission time includes, but is not limited to, for example, the submission date and time, the submission frequency, etc. For example, the answering unit provides a quick answer to an urgent inquiry. Furthermore, the answering unit can provide an answer with a normal priority to a normal inquiry. Furthermore, the answering unit can provide an answer with a lower priority to an inquiry submitted in the past. For example, the answering unit inputs the user's inquiry data into the generation AI and identifies the time of submission. This enables a quick response by determining the priority of the answer based on the time of submission of the inquiry.

[0045] The answering unit can adjust the order of answers based on the relevance of the inquiry when answering. For example, the answering unit adjusts the order of answers based on the relevance of the inquiry when answering. Evaluation of relevance includes, but is not limited to, for example, the degree of agreement with the inquiry content and the user's interest. For example, the answering unit provides answers preferentially to highly relevant inquiries. The answering unit can also provide answers to less relevant inquiries at a later date. The answering unit can also group related inquiries and provide answers all at once. For example, the answering unit inputs the user's inquiry data into a generation AI and evaluates the relevance. This enables efficient responses by adjusting the order of answers based on the relevance of the inquiry.

[0046] The answering unit can adjust the use of technical terms in the answer depending on the user's level of expertise when answering. For example, the answering unit can adjust the use of technical terms in the answer depending on the user's level of expertise when answering. Evaluation of the level of expertise includes, but is not limited to, the user's occupation, past inquiry content, etc. For example, if the user has specialized knowledge, the answering unit can provide an answer that uses a lot of technical terms. Furthermore, if the user has general knowledge, the answering unit can also provide an answer that avoids technical terms. Furthermore, the answering unit can estimate the user's level of expertise and provide an answer accordingly. For example, the answering unit inputs the user's inquiry data into a generation AI and evaluates the level of expertise. This allows the provision of appropriate information by adjusting the use of technical terms in the answer depending on the user's level of expertise.

[0047] The feature reflection unit can optimize the features by referring to the sales representative's past negotiation history when reflecting the features. For example, the feature reflection unit optimizes the features by referring to the sales representative's past negotiation history when reflecting the features. Use of the negotiation history includes, for example, the content and results of the negotiation, but is not limited to such examples. For example, the feature reflection unit reflects the features of the sales representative's successful negotiations in the avatar. The feature reflection unit can also adjust the avatar to avoid the features of the sales representative's unsuccessful negotiations in the past. The feature reflection unit can also analyze the sales representative's past negotiation history and reflect optimal features in the avatar. For example, the feature reflection unit inputs the sales representative's negotiation history data into the generation AI to optimize the features. In this way, the avatar's features can be optimized by referring to the sales representative's past negotiation history.

[0048] The feature reflection unit can customize the features based on the sales representative's current work situation when reflecting the features. For example, the feature reflection unit customizes the features based on the sales representative's current work situation when reflecting the features. Acquiring the work situation includes, but is not limited to, for example, the progress of the work and the priority of the work. For example, the feature reflection unit can make the avatar respond quickly when the sales representative is busy. Furthermore, the feature reflection unit can also make the avatar respond carefully when the sales representative has time to spare. Furthermore, the feature reflection unit can analyze the sales representative's current work situation and reflect optimal features in the avatar. For example, the feature reflection unit inputs the sales representative's work situation data into the generation AI and customizes the features. In this way, customizing the features based on the sales representative's current work situation enables more appropriate responses.

[0049] The feature reflection unit can improve the features of the avatar by reflecting user feedback when reflecting the features. For example, the feature reflection unit improves the features of the avatar by reflecting user feedback when reflecting the features. Examples of collecting feedback include, but are not limited to, questionnaires and user reviews. For example, the feature reflection unit adjusts the facial expression of the avatar based on feedback provided by the user. The feature reflection unit can also improve the way the avatar speaks based on user feedback. The feature reflection unit can also analyze user feedback and optimize the features of the avatar. For example, the feature reflection unit inputs user feedback data into a generation AI to improve the features. In this way, the avatar's features can be improved by reflecting user feedback.

[0050] The feature reflection unit can optimize the features by taking into account the geographical location information of the salesperson when reflecting the features. For example, the feature reflection unit optimizes the features by taking into account the geographical location information of the salesperson when reflecting the features. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, if the salesperson is in a specific region, the feature reflection unit reflects features that match the culture and customs of that region in the avatar. Furthermore, if the salesperson is on a business trip, the feature reflection unit can also reflect information about the business trip destination in the avatar. Furthermore, the feature reflection unit can reflect optimal features in the avatar based on the geographical location information of the salesperson. For example, the feature reflection unit inputs the salesperson's location information data into the generation AI to optimize the features. In this way, the avatar's features can be optimized by taking into account the salesperson's geographical location information.

[0051] The feature reflection unit can analyze the sales representative's social media activity and reflect the feature when reflecting the feature. For example, the feature reflection unit analyzes the sales representative's social media activity and reflects the feature when reflecting the feature. Analysis of social media activity includes, but is not limited to, analysis of post content and analysis of followers. For example, the feature reflection unit adjusts the avatar's features based on information posted by the sales representative on social media. The feature reflection unit can also analyze the sales representative's social media activity and reflect the results in the avatar's speaking style and facial expressions. The feature reflection unit can also optimize the avatar's features based on the reactions of the sales representative's followers on social media. For example, the feature reflection unit inputs the sales representative's social media data into a generation AI and reflects the feature. In this way, the avatar's features can be optimized by analyzing the sales representative's social media activity.

[0052] The feature reflection unit can customize the features by reflecting the sales representative's past feedback when reflecting the features. For example, the feature reflection unit customizes the features by reflecting the sales representative's past feedback when reflecting the features. Examples of feedback collection include, but are not limited to, questionnaires and user reviews. For example, the feature reflection unit adjusts the avatar's facial expression based on feedback the sales representative has received in the past. The feature reflection unit can also improve the avatar's speaking style based on the sales representative's past feedback. The feature reflection unit can also analyze the sales representative's past feedback and optimize the avatar's features. For example, the feature reflection unit inputs the sales representative's feedback data into the generation AI to customize the features. In this way, the avatar's features can be optimized by reflecting the sales representative's past feedback.

[0053] The collaboration unit can select the optimal collaboration method by referring to the past collaboration history between the avatar and the sales representative when collaborating. For example, the collaboration unit selects the optimal collaboration method by referring to the past collaboration history between the avatar and the sales representative when collaborating. Use of the collaboration history includes, for example, the content of the collaboration and the results of the collaboration, but is not limited to such examples. For example, the collaboration unit selects the optimal collaboration method based on collaboration methods that have been successful between the avatar and the sales representative in the past. The collaboration unit can also adjust to avoid collaboration methods that have failed between the avatar and the sales representative in the past. The collaboration unit can also analyze the past collaboration history between the avatar and the sales representative and select the optimal collaboration method. For example, the collaboration unit inputs collaboration history data between the avatar and the sales representative into the generation AI and selects the optimal collaboration method. In this way, the optimal collaboration method can be selected by referring to the past collaboration history.

[0054] The collaboration unit can customize the collaboration method based on the current work status of the avatar and the sales representative during collaboration. For example, the collaboration unit customizes the collaboration method based on the current work status of the avatar and the sales representative during collaboration. Acquiring the work status includes, but is not limited to, the progress of the work and the priority of the work. For example, if the sales representative is busy, the collaboration unit allows the avatar to respond quickly to facilitate collaboration. Furthermore, if the sales representative has time, the collaboration unit can allow the avatar to respond carefully to facilitate collaboration. Furthermore, the collaboration unit can analyze the current work status of the sales representative and customize the optimal collaboration method. For example, the collaboration unit inputs the work status data of the sales representative into the generation AI and customizes the collaboration method. In this way, customizing the collaboration method based on the current work status enables more appropriate responses.

[0055] The collaboration unit can improve the collaboration method by reflecting user feedback during collaboration. For example, the collaboration unit improves the collaboration method by reflecting user feedback during collaboration. Examples of collecting feedback include, but are not limited to, surveys and user reviews. For example, the collaboration unit improves the collaboration method between the avatar and the sales representative based on feedback provided by the user. The collaboration unit can also optimize the collaboration means from the user feedback. The collaboration unit can also analyze the user feedback and optimize the collaboration method between the avatar and the sales representative. For example, the collaboration unit inputs user feedback data into the generation AI to improve the collaboration method. In this way, the collaboration method can be improved by reflecting user feedback.

[0056] The collaboration unit can select the optimal collaboration method by taking into account the geographical location information of the avatar and the sales representative during collaboration. For example, the collaboration unit selects the optimal collaboration method by taking into account the geographical location information of the avatar and the sales representative during collaboration. Examples of obtaining geographical location information include, but are not limited to, GPS data and location information services. For example, if the sales representative is in a specific area, the collaboration unit can provide the avatar with information related to that area. Furthermore, if the sales representative is on a business trip, the collaboration unit can also provide the avatar with information about the business trip destination. Furthermore, the collaboration unit can select the optimal collaboration method based on the geographical location information of the sales representative. For example, the collaboration unit inputs the sales representative's location information data into the generation AI and selects the optimal collaboration method. In this way, the optimal collaboration method can be selected by taking into account the geographical location information.

[0057] The collaboration unit can analyze the social media activities of the avatar and the sales representative at the time of collaboration and suggest collaboration methods. For example, the collaboration unit analyzes the social media activities of the avatar and the sales representative at the time of collaboration and suggest collaboration methods. Analysis of social media activities includes, but is not limited to, analysis of post content and analysis of followers, for example. For example, the collaboration unit allows the avatar to suggest collaboration methods based on information posted by the sales representative on social media. The collaboration unit can also analyze the sales representative's social media activities and suggest collaboration methods. The collaboration unit can also allow the avatar to suggest collaboration methods based on the reactions of the sales representative's followers on social media. For example, the collaboration unit inputs the sales representative's social media data into a generation AI and suggests collaboration methods. In this way, the optimal collaboration methods can be suggested by analyzing social media activities.

[0058] The collaboration unit can customize the collaboration method by reflecting past feedback between the avatar and the sales representative during collaboration. For example, the collaboration unit customizes the collaboration method by reflecting past feedback between the avatar and the sales representative during collaboration. Examples of feedback collection include, but are not limited to, surveys and user reviews. For example, the collaboration unit customizes the collaboration method of the avatar based on feedback the sales representative has received in the past. The collaboration unit can also optimize the collaboration method from the sales representative's past feedback. The collaboration unit can also analyze the sales representative's past feedback and optimize the collaboration method of the avatar. For example, the collaboration unit inputs the sales representative's feedback data into the generation AI to customize the collaboration method. In this way, the collaboration method can be customized by reflecting past feedback.

[0059] The database utilization unit can apply an optimal search algorithm by referring to past search history when searching the database. For example, the database utilization unit can apply an optimal search algorithm by referring to past search history when searching the database. Utilization of search history includes, but is not limited to, past search keywords and evaluations of search results. For example, the database utilization unit applies an optimal search algorithm based on keywords previously searched by the user. The database utilization unit can also prioritize displaying related information from the user's past search history. The database utilization unit can also analyze the user's past search history and provide optimal search results. For example, the database utilization unit inputs the user's search history data into a generation AI and applies an optimal search algorithm. This allows the optimal search algorithm to be applied by referring to the past search history.

[0060] The database utilization unit can filter search results based on the user's current areas of interest when searching a database. For example, the database utilization unit filters search results based on the user's current areas of interest when searching a database. Identification of areas of interest includes, but is not limited to, survey results, past behavioral history, etc. For example, the database utilization unit preferentially displays related information based on keywords recently searched by the user. The database utilization unit can also display related information based on products and services in which the user has shown interest in the past. The database utilization unit can also analyze the user's social media activity and display information related to the user's current areas of interest. For example, the database utilization unit inputs the user's social media data into a generation AI to identify areas of interest. This makes it possible to provide highly relevant information by filtering search results based on the user's current areas of interest.

[0061] The database utilization unit can improve the search algorithm by reflecting user feedback during a database search. The database utilization unit, for example, improves the search algorithm by reflecting user feedback during a database search. Examples of collecting feedback include, but are not limited to, surveys and user reviews. The database utilization unit, for example, improves the search algorithm based on feedback provided by the user. The database utilization unit can also optimize search results from user feedback. The database utilization unit can also analyze user feedback and optimize the search algorithm. For example, the database utilization unit inputs user feedback data into a generation AI to improve the search algorithm. In this way, the search algorithm can be improved by reflecting user feedback.

[0062] The database utilization unit can prioritize displaying highly relevant information when searching a database, taking into account the user's geographical location information. For example, the database utilization unit prioritizes displaying highly relevant information when searching a database, taking into account the user's geographical location information. Examples of acquired geographical location information include, but are not limited to, GPS data, location information services, etc. For example, if the user is in a specific area, the database utilization unit can prioritize displaying information related to that area. Furthermore, if the user is traveling, the database utilization unit can prioritize displaying information related to the user's travel destination. Furthermore, if the user is at home, the database utilization unit can prioritize displaying information related to services around the user's home. For example, the database utilization unit inputs the user's location information data into a generation AI to identify highly relevant information. This allows highly relevant information to be prioritized by taking into account the user's geographical location information.

[0063] The database utilization unit can analyze the user's social media activity and display related information when searching the database. For example, the database utilization unit analyzes the user's social media activity and displays related information when searching the database. Analysis of social media activity includes, but is not limited to, analysis of posted content and follower analysis. For example, the database utilization unit can prioritize displaying information related to products and services mentioned by the user on social media. The database utilization unit can also analyze the content of the user's social media posts and display related information. The database utilization unit can also display related information by referring to the activity of the user's friends on social media. For example, the database utilization unit inputs the user's social media data into a generation AI to identify related information. This makes it possible to provide highly relevant information by analyzing the user's social media activity.

[0064] The database utilization unit can customize search results by reflecting the user's past feedback when searching the database. For example, the database utilization unit customizes search results by reflecting the user's past feedback when searching the database. Examples of feedback collection include, but are not limited to, surveys, user reviews, etc. The database utilization unit provides optimal search results, for example, based on feedback provided by the user in the past. The database utilization unit can also prioritize displaying specific information from the user's past feedback. The database utilization unit can also analyze the user's past feedback and customize the search results. For example, the database utilization unit inputs the user's feedback data into the generation AI to customize the search results. This allows the search results to be customized by reflecting the user's past feedback.

[0065] The recording unit can select the optimal recording method by referring to past recording history when recording. For example, the recording unit selects the optimal recording method by referring to past recording history when recording. Use of the recording history includes, for example, past recording content and recording evaluation, but is not limited to these examples. For example, the recording unit selects the optimal recording method based on content recorded by the user in the past. The recording unit can also prioritize recording related information from the user's past recording history. The recording unit can also analyze the user's past recording history and provide the optimal recording method. For example, the recording unit inputs the user's recording history data into a generation AI to select the optimal recording method. In this way, the optimal recording method can be selected by referring to the past recording history.

[0066] The recording unit can filter the recorded content based on the user's current areas of interest when recording. For example, the recording unit filters the recorded content based on the user's current areas of interest when recording. Identification of areas of interest includes, but is not limited to, survey results, past behavioral history, etc. For example, the recording unit preferentially records information related to areas in which the user has recently shown interest. The recording unit can also record related information based on areas in which the user has previously shown interest. The recording unit can also analyze the user's social media activity and record information related to the user's current areas of interest. For example, the recording unit inputs the user's social media data into a generation AI to identify the user's areas of interest. This allows highly relevant information to be recorded by filtering the recorded content based on the user's current areas of interest.

[0067] The recording unit can improve the recording method by reflecting user feedback during recording. For example, the recording unit improves the recording method by reflecting user feedback during recording. Examples of collecting feedback include, but are not limited to, questionnaires and user reviews. For example, the recording unit improves the recording method based on feedback provided by the user. The recording unit can also optimize the recording content from the user feedback. The recording unit can also analyze the user feedback and optimize the recording method. For example, the recording unit inputs user feedback data into a generation AI to improve the recording method. In this way, the recording method can be improved by reflecting user feedback.

[0068] The recording unit can prioritize recording highly relevant information by taking into account the user's geographical location information when recording. For example, the recording unit prioritizes recording highly relevant information by taking into account the user's geographical location information when recording. Examples of geographical location information include, but are not limited to, GPS data, location information services, etc. For example, when the user is in a specific area, the recording unit prioritizes recording information related to that area. Furthermore, when the user is traveling, the recording unit can prioritize recording information related to the travel destination. Furthermore, when the user is at home, the recording unit can prioritize recording information related to services around the home. For example, the recording unit inputs the user's location information data into a generation AI to identify highly relevant information. In this way, highly relevant information can be prioritized by taking into account the user's geographical location information.

[0069] The recording unit may analyze the user's social media activity and record related information during recording. For example, the recording unit may analyze the user's social media activity and record related information during recording. Analysis of social media activity may include, but is not limited to, analysis of posted content and follower analysis. For example, the recording unit may preferentially record information related to products or services mentioned by the user on social media. The recording unit may also analyze the user's social media posts and record related information. The recording unit may also record related information by referring to the activities of the user's friends on social media. For example, the recording unit may input the user's social media data into a generation AI to identify related information. This allows highly relevant information to be recorded by analyzing the user's social media activity.

[0070] The recording unit can customize the recording method by reflecting the user's past feedback when recording. For example, the recording unit customizes the recording method by reflecting the user's past feedback when recording. Examples of feedback collection include, but are not limited to, questionnaires and user reviews. For example, the recording unit suggests an optimal recording method based on feedback provided by the user in the past. The recording unit can also preferentially suggest a specific recording method based on the user's past feedback. The recording unit can also analyze the user's past feedback and customize the recording method. For example, the recording unit inputs the user's feedback data into the generation AI and customizes the recording method. In this way, the recording method can be customized by reflecting the user's past feedback.

[0071] The information providing unit can select the optimal information providing method by referring to the past information providing history when providing information. For example, the information providing unit selects the optimal information providing method by referring to the past information providing history when providing information. The use of the information providing history includes, for example, the content of past information provided and the results of the information provided, but is not limited to such examples. For example, the information providing unit selects the optimal information providing method based on the information provided to the user in the past. The information providing unit can also prioritize providing related information based on the user's past information providing history. The information providing unit can also analyze the user's past information providing history and provide the optimal information providing method. For example, the information providing unit inputs the user's information providing history data into a generation AI and selects the optimal information providing method. In this way, the optimal information providing method can be selected by referring to the past information providing history.

[0072] The information providing unit can filter the provided content based on the user's current areas of interest when providing information. For example, the information providing unit filters the provided content based on the user's current areas of interest when providing information. Identification of areas of interest includes, but is not limited to, survey results, past behavioral history, etc. For example, the information providing unit prioritizes providing information related to areas in which the user has recently shown interest. The information providing unit can also provide related information based on areas in which the user has previously shown interest. The information providing unit can also analyze the user's social media activity and provide information related to the user's current areas of interest. For example, the information providing unit inputs the user's social media data into a generation AI to identify the user's areas of interest. This allows the provision of highly relevant information by filtering the provided content based on the user's current areas of interest.

[0073] The information providing unit can improve the information providing method by reflecting user feedback when providing information. For example, the information providing unit improves the information providing method by reflecting user feedback when providing information. Examples of collecting feedback include, but are not limited to, questionnaires and user reviews. For example, the information providing unit improves the information providing method based on feedback provided by the user. The information providing unit can also optimize the content provided based on user feedback. The information providing unit can also analyze user feedback and optimize the information providing method. For example, the information providing unit inputs user feedback data into a generation AI to improve the information providing method. In this way, the information providing method can be improved by reflecting user feedback.

[0074] When providing information, the information providing unit can prioritize providing highly relevant information by taking into account the user's geographical location information. For example, when providing information, the information providing unit prioritizes providing highly relevant information by taking into account the user's geographical location information. Examples of obtaining geographical location information include, but are not limited to, GPS data, location information services, etc. For example, when the user is in a specific area, the information providing unit can prioritize providing information related to that area. Furthermore, when the user is traveling, the information providing unit can prioritize providing information related to the travel destination. Furthermore, when the user is at home, the information providing unit can prioritize providing information related to services around the user's home. For example, the information providing unit inputs the user's location information data into a generation AI to identify highly relevant information. In this way, highly relevant information can be prioritized by taking into account the user's geographical location information.

[0075] The information providing unit can analyze the user's social media activity and provide related information when providing information. For example, the information providing unit can analyze the user's social media activity and provide related information when providing information. Analysis of social media activity includes, but is not limited to, analysis of posted content and follower analysis. For example, the information providing unit can prioritize providing information related to products and services mentioned by the user on social media. The information providing unit can also analyze the content of the user's social media posts and provide related information. The information providing unit can also provide related information by referring to the activity of the user's friends on social media. For example, the information providing unit inputs the user's social media data into a generation AI to identify related information. This makes it possible to provide highly relevant information by analyzing the user's social media activity.

[0076] The information providing unit can customize the information providing method by reflecting the user's past feedback when providing information. For example, the information providing unit customizes the information providing method by reflecting the user's past feedback when providing information. Examples of collecting feedback include, but are not limited to, questionnaires and user reviews. For example, the information providing unit suggests an optimal information providing method based on feedback provided by the user in the past. The information providing unit can also preferentially suggest a specific information providing method based on the user's past feedback. The information providing unit can also analyze the user's past feedback and customize the information providing method. For example, the information providing unit inputs the user's feedback data into a generation AI and customizes the information providing method. In this way, the information providing method can be customized by reflecting the user's past feedback.

[0077] The business negotiation arrangement unit can select the optimal arrangement method by referring to past business negotiation history when arranging a business negotiation. For example, the business negotiation arrangement unit selects the optimal arrangement method by referring to past business negotiation history when arranging a business negotiation. The use of business negotiation history includes, for example, the content of the business negotiation and the results of the business negotiation, but is not limited to these examples. For example, the business negotiation arrangement unit selects the optimal arrangement method based on business negotiations conducted by the user in the past. The business negotiation arrangement unit can also prioritize providing related information from the user's past business negotiation history. The business negotiation arrangement unit can also analyze the user's past business negotiation history and provide the optimal business negotiation arrangement method. For example, the business negotiation arrangement unit inputs the user's business negotiation history data into a generation AI and selects the optimal arrangement method. In this way, the optimal business negotiation arrangement method can be selected by referring to the past business negotiation history.

[0078] The business negotiation arrangement unit can filter the arrangement content based on the user's current areas of interest when arranging a business negotiation. For example, the business negotiation arrangement unit filters the arrangement content based on the user's current areas of interest when arranging a business negotiation. Identification of areas of interest can include, but is not limited to, survey results, past behavioral history, etc. For example, the business negotiation arrangement unit prioritizes arranging business negotiations related to areas in which the user has recently shown interest. The business negotiation arrangement unit can also arrange related business negotiations based on areas in which the user has previously shown interest. The business negotiation arrangement unit can also analyze the user's social media activity and arrange business negotiations related to the user's current areas of interest. For example, the business negotiation arrangement unit inputs the user's social media data into a generation AI to identify the user's areas of interest. This makes it possible to arrange highly relevant business negotiations by filtering the arrangement content based on the user's current areas of interest.

[0079] The business negotiation arrangement unit can improve the arrangement method by reflecting user feedback when arranging a business negotiation. The business negotiation arrangement unit, for example, improves the arrangement method by reflecting user feedback when arranging a business negotiation. Examples of collecting feedback include, but are not limited to, surveys and user reviews. The business negotiation arrangement unit improves the business negotiation arrangement method, for example, based on feedback provided by the user. The business negotiation arrangement unit can also optimize the arrangement content from user feedback. The business negotiation arrangement unit can also analyze user feedback and optimize the business negotiation arrangement method. For example, the business negotiation arrangement unit inputs user feedback data into a generation AI to improve the arrangement method. In this way, the arrangement method can be improved by reflecting user feedback.

[0080] The business negotiation arrangement unit can prioritize relevant business negotiations by taking into account the user's geographical location information when arranging business negotiations. For example, the business negotiation arrangement unit prioritizes relevant business negotiations by taking into account the user's geographical location information when arranging business negotiations. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, if the user is in a specific area, the business negotiation arrangement unit prioritizes business negotiations related to that area. Furthermore, if the user is traveling, the business negotiation arrangement unit can prioritize business negotiations related to the user's travel destination. Furthermore, if the user is at home, the business negotiation arrangement unit can prioritize business negotiations related to services near the user's home. For example, the business negotiation arrangement unit inputs the user's location information data into a generation AI to identify relevant business negotiations. This allows for the user's geographical location information to be considered when arranging relevant business negotiations.

[0081] The business negotiation arrangement unit can arrange related business negotiations by analyzing the user's social media activity when arranging a business negotiation. For example, the business negotiation arrangement unit can arrange related business negotiations by analyzing the user's social media activity when arranging a business negotiation. Analysis of social media activity includes, but is not limited to, analysis of post content and follower analysis. For example, the business negotiation arrangement unit prioritizes arranging business negotiations related to products or services mentioned by the user on social media. The business negotiation arrangement unit can also analyze the user's social media posts to arrange related business negotiations. The business negotiation arrangement unit can also arrange related business negotiations by referring to the activity of the user's friends on social media. For example, the business negotiation arrangement unit inputs the user's social media data into a generation AI to identify related business negotiations. This makes it possible to arrange highly relevant business negotiations by analyzing the user's social media activity.

[0082] The business negotiation arrangement unit can customize the arrangement method by reflecting the user's past feedback when arranging a business negotiation. For example, the business negotiation arrangement unit customizes the arrangement method by reflecting the user's past feedback when arranging a business negotiation. Examples of collecting feedback include, but are not limited to, surveys and user reviews. For example, the business negotiation arrangement unit proposes the optimal business negotiation arrangement method based on feedback provided by the user in the past. The business negotiation arrangement unit can also preferentially propose a specific business negotiation arrangement method based on the user's past feedback. The business negotiation arrangement unit can also analyze the user's past feedback and customize the business negotiation arrangement method. For example, the business negotiation arrangement unit inputs the user's feedback data into a generation AI to customize the arrangement method. In this way, the arrangement method can be customized by reflecting the user's past feedback.

[0083] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0084] The reception unit can analyze the user's past inquiry history and select the optimal reception method. For example, it can automatically display the contents of inquiries that the user has frequently made in the past as candidates. The reception unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception unit can predict and suggest the contents of inquiries that will be made during a specific time period based on the user's past inquiry history. In this way, by analyzing the past inquiry history, it is possible to provide the user with the optimal reception method.

[0085] The answering unit can adjust the use of technical terms in the answer depending on the user's level of expertise. For example, if the user has technical knowledge, the answer provided can be full of technical terms. On the other hand, if the user has general knowledge, the answer provided can avoid technical terms. Furthermore, the answering unit can estimate the user's level of expertise and provide an answer accordingly. This makes it possible to provide appropriate information by adjusting the use of technical terms in the answer depending on the user's level of expertise.

[0086] The collaboration unit can select the optimal collaboration method by referring to the past collaboration history between the avatar and the actual sales representative. For example, the optimal collaboration method can be selected based on collaboration methods that have been successful between the avatar and the sales representative in the past. It can also adjust the collaboration method to avoid collaboration methods that have failed between the avatar and the sales representative in the past. Furthermore, the collaboration unit can analyze the past collaboration history between the avatar and the sales representative and select the optimal collaboration method. In this way, the optimal collaboration method can be selected by referring to the past collaboration history.

[0087] The feature reflection unit can optimize the features by referring to the sales representative's past negotiation history. For example, the feature of the sales representative's successful negotiations in the past can be reflected in the avatar. The feature reflection unit can also adjust the avatar to avoid the feature of the sales representative's unsuccessful negotiations in the past. Furthermore, the feature reflection unit can analyze the sales representative's past negotiation history and reflect the optimal feature in the avatar. In this way, the avatar's features can be optimized by referring to the sales representative's past negotiation history.

[0088] The database utilization unit can apply the optimal search algorithm by referring to the user's past search history. For example, the optimal search algorithm is applied based on keywords the user has searched for in the past. It can also prioritize displaying related information based on the user's past search history. Furthermore, the database utilization unit can analyze the user's past search history and provide optimal search results. This makes it possible to apply the optimal search algorithm by referring to the past search history.

[0089] The processing flow of the first embodiment will be briefly explained below.

[0090] Step 1: The reception unit receives an inquiry from a user. The inquiry may be in the form of text, voice, or image. For example, the reception unit receives a text message sent by the user and inputs it into the system. In the case of a voice message, it is converted into text using voice recognition technology, and in the case of an image message, its content is analyzed using image analysis technology. Step 2: In the answering section, the avatar provides an answer to the user's inquiry. The answering section generates an answer by utilizing a database of the company's products and services. For example, it retrieves product and service information from the database and provides it to the user. The answering section also uses natural language processing technology to analyze the user's question and generate an appropriate answer. Step 3: The feature reflection unit reflects the characteristics of a real salesperson in the avatar. For example, it learns the voice, speaking style, and facial expressions of the salesperson and reflects them in the avatar. The feature reflection unit collects voice data of the salesperson and reflects it in the avatar. It can also learn the characteristics of the speaking style and facial expressions of the salesperson and reflect them in the avatar. Step 4: The linking unit links the avatar with a real salesperson. For example, the avatar records interactions with the user and provides that information to the real salesperson. The linking unit records information provided by the avatar in response to the user's questions and the user's interests, and provides this information to the real salesperson. If the user wants to know more about a specific product, the linking unit arranges a business meeting with a real salesperson.

[0091] (Example 2) In a system according to an embodiment of the present invention, when a user makes an inquiry about a company's products or services, an avatar that inherits the characteristics of the company's actual salesperson responds in a chat-style manner. In this system, when a user asks a question about a company's products or services, the avatar provides a real-time answer. The avatar reflects the characteristics of the actual salesperson, allowing the user to experience speaking with a real salesperson. Furthermore, through chat interactions with the avatar, the user can conduct a business negotiation with the actual salesperson. For example, if a user wants to know more about a specific product, the avatar provides information about the product and, if necessary, arranges a business negotiation with a real salesperson. This system is expected to enable users to efficiently obtain information and facilitate smooth communication with companies. This system allows users to efficiently obtain information about a company's products and services, thereby facilitating smooth communication with companies.

[0092] An information provision system according to an embodiment includes a reception unit, a response unit, a feature reflection unit, and a linking unit. The reception unit receives an inquiry from a user. The inquiry may include, but is not limited to, text, voice, or image. The reception unit may receive, for example, a text-based inquiry. The reception unit may also receive voice-based inquiries. The reception unit may also receive image-based inquiries. For example, the reception unit receives a text message sent by a user and inputs it into the system. In the case of a voice message, the message is converted into text using voice recognition technology. In the case of an image message, the message content is analyzed using image analysis technology. The response unit provides an avatar with a response to the user's inquiry. The response unit may generate a response by utilizing, for example, a database of products and services provided by a company. For example, the response unit may retrieve product information from a database and provide it to the user. The response unit may also retrieve service information from a database and provide it to the user. The response unit may also use natural language processing technology to generate an appropriate response to the user's question. For example, the response unit may analyze the user's question and generate an appropriate response. The feature reflection unit reflects the features of a real salesperson in the avatar. The feature reflection unit, for example, learns the voice, speaking style, facial expressions, etc. of the salesperson. For example, the feature reflection unit collects voice data of the salesperson and reflects it in the avatar. The feature reflection unit can also learn the speaking style characteristics of the salesperson and reflect them in the avatar. The feature reflection unit can also learn the facial expression characteristics of the salesperson and reflect them in the avatar. For example, the feature reflection unit inputs the voice data of the salesperson into the generation AI and extracts the voice features. The collaboration unit collaborates between the avatar and the real salesperson. For example, the collaboration unit records the avatar's interactions with the user and provides that information to the real salesperson. For example, the collaboration unit records information provided by the avatar in response to the user's questions and the user's interests, and provides that information to the real salesperson. The collaboration unit can also arrange business meetings between the avatar and the real salesperson. For example, if a user wants to know more about a particular product, the collaboration unit arranges a business meeting with a real sales representative.As a result, the information providing system according to the embodiment allows the avatar to respond to the user's inquiries in real time, enabling smooth collaboration with real sales representatives.

[0093] The answering unit includes a database utilization unit that utilizes a database related to the company's products and services. The database utilization unit utilizes the database related to the company's products and services. The database includes, for example, product information, service information, search algorithms, etc., but is not limited to these examples. The database utilization unit, for example, obtains product information from the database and provides it to the user. The database utilization unit can also obtain service information from the database and provide it to the user. The database utilization unit can also use a search algorithm to search for information appropriate to the user's question. For example, the database utilization unit analyzes the user's question and searches the database for related information. In this way, by utilizing the database, it is possible to provide the user with a quick and accurate answer.

[0094] The collaboration unit includes a recording unit that records the avatar's interactions with the user. The recording unit records the avatar's interactions with the user. Recording includes, but is not limited to, for example, a text log, an audio recording, and a method for saving the records. For example, the recording unit records a text log. The recording unit can also perform audio recording. The recording unit can also provide a method for saving the recorded information. For example, the recording unit records a text message sent by the user and saves it in the system. In the case of an audio message, the audio is recorded and saved in the system. In this way, by recording interactions with the user, a real sales representative can smoothly proceed with the sales negotiations.

[0095] The recording unit includes an information providing unit that provides the recorded information to a real sales representative. The information providing unit provides the recorded information to the real sales representative. The information providing includes, for example, the type of information to be provided and the method of providing it, but is not limited to these examples. For example, the information providing unit provides the real sales representative with information provided in response to a user's question. The information providing unit can also provide the real sales representative with the user's interests, etc. The information providing unit can also provide a method for providing the recorded information to the real sales representative. For example, the information providing unit provides the real sales representative with a recorded text log. In the case of an audio recording, the recorded audio is provided to the real sales representative. In this way, by providing the recorded information to the real sales representative, preparation for a business negotiation can be efficiently carried out.

[0096] The feature reflection unit can learn the voice, speaking style, facial expressions, etc. of the sales representative. The feature reflection unit can learn, for example, the voice, speaking style, facial expressions, etc. of the sales representative. Learning can include, for example, machine learning algorithms, types of learning data, etc., but is not limited to these examples. The feature reflection unit can, for example, collect voice data of the sales representative and reflect it in the avatar. The feature reflection unit can also learn the speaking style characteristics of the sales representative and reflect them in the avatar. The feature reflection unit can also learn the facial expressions of the sales representative and reflect them in the avatar. For example, the feature reflection unit inputs the voice data of the sales representative into the generation AI and extracts the voice characteristics. In this way, by learning the characteristics of the sales representative, the avatar can respond more realistically.

[0097] The collaboration unit can arrange a business meeting between an avatar and a real sales representative. For example, the collaboration unit arranges a business meeting between an avatar and a real sales representative. The business meeting includes, for example, the format of the business meeting and the method of proceeding with the business meeting, but is not limited to these examples. For example, the collaboration unit arranges a business meeting with a real sales representative when the user wants to know more about a specific product. The collaboration unit can also arrange the format of the business meeting. The collaboration unit can also arrange the method of proceeding with the business meeting. For example, the collaboration unit arranges a business meeting with a real sales representative based on the format of the business meeting desired by the user. In this way, by arranging a business meeting between an avatar and a real sales representative, the user can conduct the business meeting smoothly.

[0098] The reception unit can estimate a user's emotions and adjust the inquiry reception method based on the estimated user emotions. For example, the reception unit can estimate a user's emotions and adjust the inquiry reception method based on the estimated user emotions. Emotion estimation includes, but is not limited to, emotion recognition algorithms, emotion types, and the like. For example, if the user is feeling stressed, the reception unit can provide a simple interface and minimize input steps. Furthermore, if the user is relaxed, the reception unit can provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input to quickly accept inquiries. For example, the reception unit can input the user's facial expression data into a generation AI and estimate emotions. This allows for more appropriate responses by adjusting the inquiry reception method according to the user's emotions.

[0099] The reception unit can analyze the user's past inquiry history and select the optimal reception method. The reception unit, for example, analyzes the user's past inquiry history and selects the optimal reception method. The past inquiry history includes, for example, a history storage method, an analysis algorithm, etc., but is not limited to these examples. The reception unit, for example, automatically displays the content of inquiries the user has frequently made in the past as candidates. The reception unit can also prioritize and suggest input methods (voice, text, etc.) that the user has used in the past. The reception unit can also predict and suggest the content of inquiries to be made during a specific time period based on the user's past inquiry history. For example, the reception unit inputs the user's past inquiry history into a generation AI and selects the optimal reception method. In this way, the optimal reception method can be provided to the user by analyzing the past inquiry history.

[0100] The reception unit may filter inquiries based on the user's current areas of interest when receiving the inquiries. For example, the reception unit may filter inquiries based on the user's current areas of interest when receiving the inquiries. Identification of areas of interest may include, but is not limited to, survey results, past behavioral history, etc. For example, the reception unit may preferentially display related inquiries based on keywords recently searched by the user. The reception unit may also suggest related inquiries based on products or services in which the user has shown interest in the past. The reception unit may also analyze the user's social media activity and display inquiries related to the user's current areas of interest. For example, the reception unit may input the user's social media activity into a generation AI to identify areas of interest. By filtering based on the user's current areas of interest, it is possible to preferentially receive highly relevant inquiries.

[0101] The reception unit can select the optimal reception means depending on the user's input method when receiving an inquiry. For example, the reception unit selects the optimal reception means depending on the user's input method (voice, text, image, etc.) when receiving an inquiry. The selection of the input method includes, but is not limited to, voice input, text input, image input, etc. For example, when a user makes an inquiry by voice, the reception unit uses voice recognition technology to quickly receive the inquiry. Furthermore, when a user makes an inquiry by text, the reception unit can also use text analysis technology to accurately receive the inquiry. Furthermore, when a user makes an inquiry using an image, the reception unit can extract related information using image recognition technology and receive the inquiry. For example, the reception unit inputs the user's voice data into a generation AI and performs voice recognition. This enables efficient inquiry reception by selecting the optimal reception means depending on the user's input method.

[0102] The reception unit can estimate the user's emotions and determine the priority of inquiries to be received based on the estimated user emotions. The reception unit, for example, estimates the user's emotions and determines the priority of inquiries to be received based on the estimated user emotions. Emotion estimation includes, but is not limited to, emotion recognition algorithms, types of emotions, and the like. For example, the reception unit prioritizes inquiries when the user is making an urgent inquiry. Furthermore, the reception unit can also receive inquiries with normal priority when the user is relaxed. Furthermore, the reception unit can increase the priority when the user is feeling stressed in order to respond quickly. For example, the reception unit inputs the user's facial expression data into a generation AI to estimate emotions. This enables more appropriate responses by determining the priority of inquiries based on the user's emotions.

[0103] When receiving an inquiry, the reception unit can prioritize receiving highly relevant inquiries by taking into account the user's geographical location information. For example, when receiving an inquiry, the reception unit prioritizes receiving highly relevant inquiries by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data, location information services, etc. For example, when the user is in a specific area, the reception unit prioritizes receiving inquiries related to that area. Furthermore, when the user is traveling, the reception unit can prioritize receiving inquiries related to the user's travel destination. Furthermore, when the user is at home, the reception unit can prioritize receiving inquiries related to services around the user's home. For example, the reception unit inputs the user's location information data into a generation AI to identify highly relevant inquiries. In this way, highly relevant inquiries can be prioritized by taking into account the user's geographical location information.

[0104] The reception unit can analyze the user's social media activity when receiving an inquiry and receive related inquiries. For example, the reception unit analyzes the user's social media activity when receiving an inquiry and receives related inquiries. Analysis of social media activity includes, but is not limited to, analysis of post content and follower analysis. For example, the reception unit preferentially receives inquiries related to products or services mentioned by the user on social media. The reception unit can also analyze the user's social media posts and receive related inquiries. The reception unit can also receive related inquiries by referring to the activities of the user's friends on social media. For example, the reception unit inputs the user's social media data into a generation AI to identify related inquiries. In this way, by analyzing the user's social media activity, it is possible to preferentially receive highly relevant inquiries.

[0105] The reception unit can customize the reception method by reflecting the user's past feedback when receiving an inquiry. For example, the reception unit customizes the reception method by reflecting the user's past feedback when receiving an inquiry. Examples of feedback collection include, but are not limited to, questionnaires and user reviews. For example, the reception unit suggests an optimal reception method based on feedback provided by the user in the past. The reception unit can also preferentially suggest a specific reception method based on the user's past feedback. The reception unit can also analyze the user's past feedback and customize the reception method. For example, the reception unit inputs the user's feedback data into a generation AI to select the optimal reception method. In this way, the optimal reception method can be provided by reflecting the user's past feedback.

[0106] The answering unit can estimate the user's emotions and adjust the way the answer is expressed based on the estimated user's emotions. The answering unit, for example, estimates the user's emotions and adjusts the way the answer is expressed based on the estimated user's emotions. Emotion estimation includes, but is not limited to, emotion recognition algorithms, types of emotions, and the like. For example, if the user is nervous, the answering unit can provide a simple, highly visible answer. Furthermore, if the user is relaxed, the answering unit can provide an answer that includes detailed information. Furthermore, if the user is in a hurry, the answering unit can provide a concise answer that focuses on the main points. For example, the answering unit inputs the user's facial expression data into a generation AI to estimate the user's emotions. This allows the answering unit to adjust the way the answer is expressed based on the user's emotions, thereby providing a more appropriate answer.

[0107] The answering unit can adjust the level of detail of the answer based on the importance of the inquiry when answering. For example, the answering unit adjusts the level of detail of the answer based on the importance of the inquiry when answering. The evaluation of the importance includes, but is not limited to, for example, the content of the inquiry and the attributes of the user. For example, the answering unit provides an answer including detailed information for an important inquiry. The answering unit can also provide a concise answer for a general inquiry. The answering unit can also provide an answer that focuses on the main points for a quick response to an urgent inquiry. For example, the answering unit inputs the user's inquiry data into a generation AI and evaluates the importance. As a result, the level of detail of the answer can be adjusted based on the importance of the inquiry, thereby providing appropriate information.

[0108] The answering unit can apply different answering algorithms depending on the category of the inquiry when answering. For example, the answering unit applies different answering algorithms depending on the category of the inquiry when answering. Category classifications include, but are not limited to, product categories and service categories. For example, the answering unit applies an answering algorithm based on a product database to an inquiry about a product. The answering unit can also apply an answering algorithm based on a service database to an inquiry about a service. The answering unit can also apply an answering algorithm based on a technical database to a technical inquiry. For example, the answering unit inputs the user's inquiry data into a generation AI to identify the category. This allows a more accurate answer to be provided by applying an appropriate answering algorithm depending on the category of the inquiry.

[0109] The answering unit can improve the accuracy of the answer by referring to the user's past answer results when providing an answer. For example, the answering unit can improve the accuracy of the answer by referring to the user's past answer results when providing an answer. The use of past answer results includes, but is not limited to, the accuracy of the answer and the user's satisfaction. For example, the answering unit provides an optimal answer based on answers the user has received in the past. The answering unit can also provide related information from the user's past answer results. The answering unit can also analyze the user's past answer history to improve the accuracy of the answer. For example, the answering unit inputs the user's past answer data into a generation AI to generate an optimal answer. In this way, the accuracy of the answer can be improved by referring to the user's past answer results.

[0110] The answering unit can estimate the user's emotions and adjust the length of the answer based on the estimated user emotions. The answering unit, for example, estimates the user's emotions and adjusts the length of the answer based on the estimated user emotions. Emotion estimation includes, but is not limited to, emotion recognition algorithms, types of emotions, and the like. For example, if the user is in a hurry, the answering unit can provide a short, to-the-point answer. Furthermore, if the user is relaxed, the answering unit can provide a longer answer with detailed explanations. Furthermore, if the user is excited, the answering unit can provide an answer with a visually stimulating effect. For example, the answering unit inputs the user's facial expression data into a generation AI to estimate the user's emotions. This allows the length of the answer to be adjusted according to the user's emotions, thereby providing a more appropriate answer.

[0111] The answering unit can determine the priority of the answer based on the time of submission of the inquiry when making an answer. For example, the answering unit determines the priority of the answer based on the time of submission of the inquiry when making an answer. Acquiring the submission time includes, but is not limited to, for example, the submission date and time, the submission frequency, etc. For example, the answering unit provides a quick answer to an urgent inquiry. Furthermore, the answering unit can provide an answer with a normal priority to a normal inquiry. Furthermore, the answering unit can provide an answer with a lower priority to an inquiry submitted in the past. For example, the answering unit inputs the user's inquiry data into the generation AI and identifies the time of submission. This enables a quick response by determining the priority of the answer based on the time of submission of the inquiry.

[0112] The answering unit can adjust the order of answers based on the relevance of the inquiry when answering. For example, the answering unit adjusts the order of answers based on the relevance of the inquiry when answering. Evaluation of relevance includes, but is not limited to, for example, the degree of agreement with the inquiry content and the user's interest. For example, the answering unit provides answers preferentially to highly relevant inquiries. The answering unit can also provide answers to less relevant inquiries at a later date. The answering unit can also group related inquiries and provide answers all at once. For example, the answering unit inputs the user's inquiry data into a generation AI and evaluates the relevance. This enables efficient responses by adjusting the order of answers based on the relevance of the inquiry.

[0113] The answering unit can adjust the use of technical terms in the answer depending on the user's level of expertise when answering. For example, the answering unit can adjust the use of technical terms in the answer depending on the user's level of expertise when answering. Evaluation of the level of expertise includes, but is not limited to, the user's occupation, past inquiry content, etc. For example, if the user has specialized knowledge, the answering unit can provide an answer that uses a lot of technical terms. Furthermore, if the user has general knowledge, the answering unit can also provide an answer that avoids technical terms. Furthermore, the answering unit can estimate the user's level of expertise and provide an answer accordingly. For example, the answering unit inputs the user's inquiry data into a generation AI and evaluates the level of expertise. This allows the provision of appropriate information by adjusting the use of technical terms in the answer depending on the user's level of expertise.

[0114] The feature reflection unit can estimate the user's emotion and adjust the avatar's features based on the estimated user's emotion. The feature reflection unit, for example, estimates the user's emotion and adjusts the avatar's features based on the estimated user's emotion. Emotion estimation includes, but is not limited to, emotion recognition algorithms, types of emotions, and the like. For example, the feature reflection unit can calm the avatar's facial expression when the user is nervous. The feature reflection unit can also brighten the avatar's facial expression when the user is relaxed. The feature reflection unit can also liven up the avatar's facial expression when the user is excited. For example, the feature reflection unit inputs the user's facial expression data into a generation AI to estimate the emotion. This allows the avatar's features to be adjusted according to the user's emotion, enabling a more realistic response.

[0115] The feature reflection unit can optimize the features by referring to the sales representative's past negotiation history when reflecting the features. For example, the feature reflection unit optimizes the features by referring to the sales representative's past negotiation history when reflecting the features. Use of the negotiation history includes, for example, the content and results of the negotiation, but is not limited to such examples. For example, the feature reflection unit reflects the features of the sales representative's successful negotiations in the avatar. The feature reflection unit can also adjust the avatar to avoid the features of the sales representative's unsuccessful negotiations in the past. The feature reflection unit can also analyze the sales representative's past negotiation history and reflect optimal features in the avatar. For example, the feature reflection unit inputs the sales representative's negotiation history data into the generation AI to optimize the features. In this way, the avatar's features can be optimized by referring to the sales representative's past negotiation history.

[0116] The feature reflection unit can customize the features based on the sales representative's current work situation when reflecting the features. For example, the feature reflection unit customizes the features based on the sales representative's current work situation when reflecting the features. Acquiring the work situation includes, but is not limited to, for example, the progress of the work and the priority of the work. For example, the feature reflection unit can make the avatar respond quickly when the sales representative is busy. Furthermore, the feature reflection unit can also make the avatar respond carefully when the sales representative has time to spare. Furthermore, the feature reflection unit can analyze the sales representative's current work situation and reflect optimal features in the avatar. For example, the feature reflection unit inputs the sales representative's work situation data into the generation AI and customizes the features. In this way, customizing the features based on the sales representative's current work situation enables more appropriate responses.

[0117] The feature reflection unit can improve the features of the avatar by reflecting user feedback when reflecting the features. For example, the feature reflection unit improves the features of the avatar by reflecting user feedback when reflecting the features. Examples of collecting feedback include, but are not limited to, questionnaires and user reviews. For example, the feature reflection unit adjusts the facial expression of the avatar based on feedback provided by the user. The feature reflection unit can also improve the way the avatar speaks based on user feedback. The feature reflection unit can also analyze user feedback and optimize the features of the avatar. For example, the feature reflection unit inputs user feedback data into a generation AI to improve the features. In this way, the avatar's features can be improved by reflecting user feedback.

[0118] The feature reflection unit can estimate the user's emotions and prioritize the avatar's features based on the estimated user emotions. The feature reflection unit, for example, estimates the user's emotions and prioritizes the avatar's features based on the estimated user emotions. Estimating emotions includes, but is not limited to, emotion recognition algorithms, types of emotions, and the like. For example, if the user is nervous, the feature reflection unit can prioritize making the avatar's facial expression calm. Furthermore, if the user is relaxed, the feature reflection unit can prioritize making the avatar's speech natural. Furthermore, if the user is excited, the feature reflection unit can prioritize making the avatar's movements more active. For example, the feature reflection unit inputs the user's facial expression data into a generation AI to estimate the emotions. This enables more appropriate responses by prioritizing the avatar's features according to the user's emotions.

[0119] The feature reflection unit can optimize the features by taking into account the geographical location information of the salesperson when reflecting the features. For example, the feature reflection unit optimizes the features by taking into account the geographical location information of the salesperson when reflecting the features. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, if the salesperson is in a specific region, the feature reflection unit reflects features that match the culture and customs of that region in the avatar. Furthermore, if the salesperson is on a business trip, the feature reflection unit can also reflect information about the business trip destination in the avatar. Furthermore, the feature reflection unit can reflect optimal features in the avatar based on the geographical location information of the salesperson. For example, the feature reflection unit inputs the salesperson's location information data into the generation AI to optimize the features. In this way, the avatar's features can be optimized by taking into account the salesperson's geographical location information.

[0120] The feature reflection unit can analyze the sales representative's social media activity and reflect the feature when reflecting the feature. For example, the feature reflection unit analyzes the sales representative's social media activity and reflects the feature when reflecting the feature. Analysis of social media activity includes, but is not limited to, analysis of post content and analysis of followers. For example, the feature reflection unit adjusts the avatar's features based on information posted by the sales representative on social media. The feature reflection unit can also analyze the sales representative's social media activity and reflect the results in the avatar's speaking style and facial expressions. The feature reflection unit can also optimize the avatar's features based on the reactions of the sales representative's followers on social media. For example, the feature reflection unit inputs the sales representative's social media data into a generation AI and reflects the feature. In this way, the avatar's features can be optimized by analyzing the sales representative's social media activity.

[0121] The feature reflection unit can customize the features by reflecting the sales representative's past feedback when reflecting the features. For example, the feature reflection unit customizes the features by reflecting the sales representative's past feedback when reflecting the features. Examples of feedback collection include, but are not limited to, questionnaires and user reviews. For example, the feature reflection unit adjusts the avatar's facial expression based on feedback the sales representative has received in the past. The feature reflection unit can also improve the avatar's speaking style based on the sales representative's past feedback. The feature reflection unit can also analyze the sales representative's past feedback and optimize the avatar's features. For example, the feature reflection unit inputs the sales representative's feedback data into the generation AI to customize the features. In this way, the avatar's features can be optimized by reflecting the sales representative's past feedback.

[0122] The collaboration unit can estimate the user's emotions and adjust the collaboration method between the avatar and the salesperson based on the estimated user emotions. The collaboration unit, for example, estimates the user's emotions and adjusts the collaboration method between the avatar and the salesperson based on the estimated user emotions. Emotion estimation includes, but is not limited to, emotion recognition algorithms, types of emotions, and the like. For example, if the user is nervous, the collaboration unit can have the avatar respond calmly to facilitate collaboration with the salesperson. Furthermore, if the user is relaxed, the collaboration unit can have the avatar respond naturally to facilitate collaboration with the salesperson. Furthermore, if the user is excited, the collaboration unit can have the avatar respond actively to facilitate collaboration with the salesperson. For example, the collaboration unit can input the user's facial expression data into a generation AI and estimate the user's emotions. This allows for smoother collaboration by adjusting the collaboration method according to the user's emotions.

[0123] The collaboration unit can select the optimal collaboration method by referring to the past collaboration history between the avatar and the sales representative when collaborating. For example, the collaboration unit selects the optimal collaboration method by referring to the past collaboration history between the avatar and the sales representative when collaborating. Use of the collaboration history includes, for example, the content of the collaboration and the results of the collaboration, but is not limited to such examples. For example, the collaboration unit selects the optimal collaboration method based on collaboration methods that have been successful between the avatar and the sales representative in the past. The collaboration unit can also adjust to avoid collaboration methods that have failed between the avatar and the sales representative in the past. The collaboration unit can also analyze the past collaboration history between the avatar and the sales representative and select the optimal collaboration method. For example, the collaboration unit inputs collaboration history data between the avatar and the sales representative into the generation AI and selects the optimal collaboration method. In this way, the optimal collaboration method can be selected by referring to the past collaboration history.

[0124] The collaboration unit can customize the collaboration method based on the current work status of the avatar and the sales representative during collaboration. For example, the collaboration unit customizes the collaboration method based on the current work status of the avatar and the sales representative during collaboration. Acquiring the work status includes, but is not limited to, the progress of the work and the priority of the work. For example, if the sales representative is busy, the collaboration unit allows the avatar to respond quickly to facilitate collaboration. Furthermore, if the sales representative has time, the collaboration unit can allow the avatar to respond carefully to facilitate collaboration. Furthermore, the collaboration unit can analyze the current work status of the sales representative and customize the optimal collaboration method. For example, the collaboration unit inputs the work status data of the sales representative into the generation AI and customizes the collaboration method. In this way, customizing the collaboration method based on the current work status enables more appropriate responses.

[0125] The collaboration unit can improve the collaboration method by reflecting user feedback during collaboration. For example, the collaboration unit improves the collaboration method by reflecting user feedback during collaboration. Examples of collecting feedback include, but are not limited to, surveys and user reviews. For example, the collaboration unit improves the collaboration method between the avatar and the sales representative based on feedback provided by the user. The collaboration unit can also optimize the collaboration means from the user feedback. The collaboration unit can also analyze the user feedback and optimize the collaboration method between the avatar and the sales representative. For example, the collaboration unit inputs user feedback data into the generation AI to improve the collaboration method. In this way, the collaboration method can be improved by reflecting user feedback.

[0126] The collaboration unit can estimate the user's emotions and determine collaboration priorities based on the estimated user emotions. The collaboration unit, for example, estimates the user's emotions and determines collaboration priorities based on the estimated user emotions. Emotion estimation includes, but is not limited to, emotion recognition algorithms, emotion types, and the like. For example, the collaboration unit prioritizes collaboration when the user is making an urgent inquiry. The collaboration unit can also prioritize collaboration when the user is relaxed. The collaboration unit can also increase the priority when the user is stressed to respond quickly. For example, the collaboration unit inputs the user's facial expression data into a generation AI to estimate emotions. This enables more appropriate responses by determining collaboration priorities based on the user's emotions.

[0127] The collaboration unit can select the optimal collaboration method by taking into account the geographical location information of the avatar and the sales representative during collaboration. For example, the collaboration unit selects the optimal collaboration method by taking into account the geographical location information of the avatar and the sales representative during collaboration. Examples of obtaining geographical location information include, but are not limited to, GPS data and location information services. For example, if the sales representative is in a specific area, the collaboration unit can provide the avatar with information related to that area. Furthermore, if the sales representative is on a business trip, the collaboration unit can also provide the avatar with information about the business trip destination. Furthermore, the collaboration unit can select the optimal collaboration method based on the geographical location information of the sales representative. For example, the collaboration unit inputs the sales representative's location information data into the generation AI and selects the optimal collaboration method. In this way, the optimal collaboration method can be selected by taking into account the geographical location information.

[0128] The collaboration unit can analyze the social media activities of the avatar and the sales representative at the time of collaboration and suggest collaboration methods. For example, the collaboration unit analyzes the social media activities of the avatar and the sales representative at the time of collaboration and suggest collaboration methods. Analysis of social media activities includes, but is not limited to, analysis of post content and analysis of followers, for example. For example, the collaboration unit allows the avatar to suggest collaboration methods based on information posted by the sales representative on social media. The collaboration unit can also analyze the sales representative's social media activities and suggest collaboration methods. The collaboration unit can also allow the avatar to suggest collaboration methods based on the reactions of the sales representative's followers on social media. For example, the collaboration unit inputs the sales representative's social media data into a generation AI and suggests collaboration methods. In this way, the optimal collaboration methods can be suggested by analyzing social media activities.

[0129] The collaboration unit can customize the collaboration method by reflecting past feedback between the avatar and the sales representative during collaboration. For example, the collaboration unit customizes the collaboration method by reflecting past feedback between the avatar and the sales representative during collaboration. Examples of feedback collection include, but are not limited to, surveys and user reviews. For example, the collaboration unit customizes the collaboration method of the avatar based on feedback the sales representative has received in the past. The collaboration unit can also optimize the collaboration method from the sales representative's past feedback. The collaboration unit can also analyze the sales representative's past feedback and optimize the collaboration method of the avatar. For example, the collaboration unit inputs the sales representative's feedback data into the generation AI to customize the collaboration method. In this way, the collaboration method can be customized by reflecting past feedback.

[0130] The database utilization unit can estimate a user's emotion and adjust a database search method based on the estimated user emotion. The database utilization unit, for example, estimates a user's emotion and adjusts a database search method based on the estimated user emotion. Emotion estimation includes, but is not limited to, emotion recognition algorithms, emotion types, and the like. For example, if a user is nervous, the database utilization unit can provide simple, highly visible search results. Furthermore, if a user is relaxed, the database utilization unit can provide search results that include detailed information. Furthermore, if a user is in a hurry, the database utilization unit can provide concise search results that focus on the main points. For example, the database utilization unit inputs the user's facial expression data into a generation AI to estimate the emotion. This allows the database search method to be adjusted according to the user's emotion, thereby providing more appropriate search results.

[0131] The database utilization unit can apply an optimal search algorithm by referring to past search history when searching the database. For example, the database utilization unit can apply an optimal search algorithm by referring to past search history when searching the database. Utilization of search history includes, but is not limited to, past search keywords and evaluations of search results. For example, the database utilization unit applies an optimal search algorithm based on keywords previously searched by the user. The database utilization unit can also prioritize displaying related information from the user's past search history. The database utilization unit can also analyze the user's past search history and provide optimal search results. For example, the database utilization unit inputs the user's search history data into a generation AI and applies an optimal search algorithm. This allows the optimal search algorithm to be applied by referring to the past search history.

[0132] The database utilization unit can filter search results based on the user's current areas of interest when searching a database. For example, the database utilization unit filters search results based on the user's current areas of interest when searching a database. Identification of areas of interest includes, but is not limited to, survey results, past behavioral history, etc. For example, the database utilization unit preferentially displays related information based on keywords recently searched by the user. The database utilization unit can also display related information based on products and services in which the user has shown interest in the past. The database utilization unit can also analyze the user's social media activity and display information related to the user's current areas of interest. For example, the database utilization unit inputs the user's social media data into a generation AI to identify areas of interest. This makes it possible to provide highly relevant information by filtering search results based on the user's current areas of interest.

[0133] The database utilization unit can improve the search algorithm by reflecting user feedback during a database search. The database utilization unit, for example, improves the search algorithm by reflecting user feedback during a database search. Examples of collecting feedback include, but are not limited to, surveys and user reviews. The database utilization unit, for example, improves the search algorithm based on feedback provided by the user. The database utilization unit can also optimize search results from user feedback. The database utilization unit can also analyze user feedback and optimize the search algorithm. For example, the database utilization unit inputs user feedback data into a generation AI to improve the search algorithm. In this way, the search algorithm can be improved by reflecting user feedback.

[0134] The database utilization unit can estimate a user's emotion and adjust the display method of search results based on the estimated user emotion. The database utilization unit, for example, estimates a user's emotion and adjusts the display method of search results based on the estimated user emotion. Emotion estimation includes, but is not limited to, emotion recognition algorithms, types of emotions, and the like. For example, if the user is nervous, the database utilization unit provides a simple, highly visible display method. Furthermore, if the user is relaxed, the database utilization unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the database utilization unit can provide a concise display method that focuses on the main points. For example, the database utilization unit inputs the user's facial expression data into a generation AI to estimate the emotion. This allows for more appropriate information to be provided by adjusting the display method of search results according to the user's emotion.

[0135] The database utilization unit can prioritize displaying highly relevant information when searching a database, taking into account the user's geographical location information. For example, the database utilization unit prioritizes displaying highly relevant information when searching a database, taking into account the user's geographical location information. Examples of acquired geographical location information include, but are not limited to, GPS data, location information services, etc. For example, if the user is in a specific area, the database utilization unit can prioritize displaying information related to that area. Furthermore, if the user is traveling, the database utilization unit can prioritize displaying information related to the user's travel destination. Furthermore, if the user is at home, the database utilization unit can prioritize displaying information related to services around the user's home. For example, the database utilization unit inputs the user's location information data into a generation AI to identify highly relevant information. This allows highly relevant information to be prioritized by taking into account the user's geographical location information.

[0136] The database utilization unit can analyze the user's social media activity and display related information when searching the database. For example, the database utilization unit analyzes the user's social media activity and displays related information when searching the database. Analysis of social media activity includes, but is not limited to, analysis of posted content and follower analysis. For example, the database utilization unit can prioritize displaying information related to products and services mentioned by the user on social media. The database utilization unit can also analyze the content of the user's social media posts and display related information. The database utilization unit can also display related information by referring to the activity of the user's friends on social media. For example, the database utilization unit inputs the user's social media data into a generation AI to identify related information. This makes it possible to provide highly relevant information by analyzing the user's social media activity.

[0137] The database utilization unit can customize search results by reflecting the user's past feedback when searching the database. For example, the database utilization unit customizes search results by reflecting the user's past feedback when searching the database. Examples of feedback collection include, but are not limited to, surveys, user reviews, etc. The database utilization unit provides optimal search results, for example, based on feedback provided by the user in the past. The database utilization unit can also prioritize displaying specific information from the user's past feedback. The database utilization unit can also analyze the user's past feedback and customize the search results. For example, the database utilization unit inputs the user's feedback data into the generation AI to customize the search results. This allows the search results to be customized by reflecting the user's past feedback.

[0138] The recording unit can estimate the user's emotions and adjust the recording method based on the estimated user emotions. For example, the recording unit can estimate the user's emotions and adjust the recording method based on the estimated user emotions. Emotion estimation can include, but is not limited to, emotion recognition algorithms, types of emotions, etc. For example, if the user is nervous, the recording unit can provide a simple, highly visible recording method. Furthermore, if the user is relaxed, the recording unit can provide a recording method that includes detailed information. Furthermore, if the user is in a hurry, the recording unit can provide a concise recording method that focuses on the main points. For example, the recording unit inputs the user's facial expression data into a generation AI to estimate emotions. This allows for more appropriate recording by adjusting the recording method according to the user's emotions.

[0139] The recording unit can select the optimal recording method by referring to past recording history when recording. For example, the recording unit selects the optimal recording method by referring to past recording history when recording. Use of the recording history includes, for example, past recording content and recording evaluation, but is not limited to these examples. For example, the recording unit selects the optimal recording method based on content recorded by the user in the past. The recording unit can also prioritize recording related information from the user's past recording history. The recording unit can also analyze the user's past recording history and provide the optimal recording method. For example, the recording unit inputs the user's recording history data into a generation AI to select the optimal recording method. In this way, the optimal recording method can be selected by referring to the past recording history.

[0140] The recording unit can filter the recorded content based on the user's current areas of interest when recording. For example, the recording unit filters the recorded content based on the user's current areas of interest when recording. Identification of areas of interest includes, but is not limited to, survey results, past behavioral history, etc. For example, the recording unit preferentially records information related to areas in which the user has recently shown interest. The recording unit can also record related information based on areas in which the user has previously shown interest. The recording unit can also analyze the user's social media activity and record information related to the user's current areas of interest. For example, the recording unit inputs the user's social media data into a generation AI to identify the user's areas of interest. This allows highly relevant information to be recorded by filtering the recorded content based on the user's current areas of interest.

[0141] The recording unit can improve the recording method by reflecting user feedback during recording. For example, the recording unit improves the recording method by reflecting user feedback during recording. Examples of collecting feedback include, but are not limited to, questionnaires and user reviews. For example, the recording unit improves the recording method based on feedback provided by the user. The recording unit can also optimize the recording content from the user feedback. The recording unit can also analyze the user feedback and optimize the recording method. For example, the recording unit inputs user feedback data into a generation AI to improve the recording method. In this way, the recording method can be improved by reflecting user feedback.

[0142] The recording unit can estimate the user's emotions and prioritize the recorded content based on the estimated user emotions. The recording unit, for example, estimates the user's emotions and prioritizes the recorded content based on the estimated user emotions. Estimation of emotions includes, but is not limited to, emotion recognition algorithms, types of emotions, and the like. For example, the recording unit prioritizes recording when the user is making an urgent inquiry. The recording unit can also record at a normal priority when the user is relaxed. The recording unit can also increase the priority when the user is stressed in order to respond quickly. For example, the recording unit inputs the user's facial expression data into a generation AI to estimate emotions. This enables more appropriate recording by prioritizing the recorded content according to the user's emotions.

[0143] The recording unit can prioritize recording highly relevant information by taking into account the user's geographical location information when recording. For example, the recording unit prioritizes recording highly relevant information by taking into account the user's geographical location information when recording. Examples of geographical location information include, but are not limited to, GPS data, location information services, etc. For example, when the user is in a specific area, the recording unit prioritizes recording information related to that area. Furthermore, when the user is traveling, the recording unit can prioritize recording information related to the travel destination. Furthermore, when the user is at home, the recording unit can prioritize recording information related to services around the home. For example, the recording unit inputs the user's location information data into a generation AI to identify highly relevant information. In this way, highly relevant information can be prioritized by taking into account the user's geographical location information.

[0144] The recording unit may analyze the user's social media activity and record related information during recording. For example, the recording unit may analyze the user's social media activity and record related information during recording. Analysis of social media activity may include, but is not limited to, analysis of posted content and follower analysis. For example, the recording unit may preferentially record information related to products or services mentioned by the user on social media. The recording unit may also analyze the user's social media posts and record related information. The recording unit may also record related information by referring to the activities of the user's friends on social media. For example, the recording unit may input the user's social media data into a generation AI to identify related information. This allows highly relevant information to be recorded by analyzing the user's social media activity.

[0145] The recording unit can customize the recording method by reflecting the user's past feedback when recording. For example, the recording unit customizes the recording method by reflecting the user's past feedback when recording. Examples of feedback collection include, but are not limited to, questionnaires and user reviews. For example, the recording unit suggests an optimal recording method based on feedback provided by the user in the past. The recording unit can also preferentially suggest a specific recording method based on the user's past feedback. The recording unit can also analyze the user's past feedback and customize the recording method. For example, the recording unit inputs the user's feedback data into the generation AI and customizes the recording method. In this way, the recording method can be customized by reflecting the user's past feedback.

[0146] The information providing unit can estimate the user's emotions and adjust the information provision method based on the estimated user emotions. The information providing unit, for example, estimates the user's emotions and adjusts the information provision method based on the estimated user emotions. Emotion estimation includes, but is not limited to, emotion recognition algorithms, emotion types, and the like. For example, if the user is nervous, the information providing unit can provide a simple, highly visible information provision method. Furthermore, if the user is relaxed, the information providing unit can provide an information provision method that includes detailed information. Furthermore, if the user is in a hurry, the information providing unit can provide a concise information provision method that focuses on the main points. For example, the information providing unit inputs the user's facial expression data into a generation AI to estimate the user's emotions. This allows for more appropriate information provision by adjusting the information provision method according to the user's emotions.

[0147] The information providing unit can select the optimal information providing method by referring to the past information providing history when providing information. For example, the information providing unit selects the optimal information providing method by referring to the past information providing history when providing information. The use of the information providing history includes, for example, the content of past information provided and the results of the information provided, but is not limited to such examples. For example, the information providing unit selects the optimal information providing method based on the information provided to the user in the past. The information providing unit can also prioritize providing related information based on the user's past information providing history. The information providing unit can also analyze the user's past information providing history and provide the optimal information providing method. For example, the information providing unit inputs the user's information providing history data into a generation AI and selects the optimal information providing method. In this way, the optimal information providing method can be selected by referring to the past information providing history.

[0148] The information providing unit can filter the provided content based on the user's current areas of interest when providing information. For example, the information providing unit filters the provided content based on the user's current areas of interest when providing information. Identification of areas of interest includes, but is not limited to, survey results, past behavioral history, etc. For example, the information providing unit prioritizes providing information related to areas in which the user has recently shown interest. The information providing unit can also provide related information based on areas in which the user has previously shown interest. The information providing unit can also analyze the user's social media activity and provide information related to the user's current areas of interest. For example, the information providing unit inputs the user's social media data into a generation AI to identify the user's areas of interest. This allows the provision of highly relevant information by filtering the provided content based on the user's current areas of interest.

[0149] The information providing unit can improve the information providing method by reflecting user feedback when providing information. For example, the information providing unit improves the information providing method by reflecting user feedback when providing information. Examples of collecting feedback include, but are not limited to, questionnaires and user reviews. For example, the information providing unit improves the information providing method based on feedback provided by the user. The information providing unit can also optimize the content provided based on user feedback. The information providing unit can also analyze user feedback and optimize the information providing method. For example, the information providing unit inputs user feedback data into a generation AI to improve the information providing method. In this way, the information providing method can be improved by reflecting user feedback.

[0150] The information providing unit can estimate the user's emotions and determine the priority of the content to be provided based on the estimated user emotions. The information providing unit, for example, estimates the user's emotions and determines the priority of the content to be provided based on the estimated user emotions. Emotion estimation includes, but is not limited to, emotion recognition algorithms, types of emotions, and the like. For example, the information providing unit can provide information with priority when the user is making an urgent inquiry. Furthermore, the information providing unit can provide information with normal priority when the user is relaxed. Furthermore, the information providing unit can increase the priority when the user is feeling stressed in order to respond quickly. For example, the information providing unit inputs the user's facial expression data into a generation AI to estimate emotions. This enables more appropriate information to be provided by determining the priority of the content to be provided based on the user's emotions.

[0151] When providing information, the information providing unit can prioritize providing highly relevant information by taking into account the user's geographical location information. For example, when providing information, the information providing unit prioritizes providing highly relevant information by taking into account the user's geographical location information. Examples of obtaining geographical location information include, but are not limited to, GPS data, location information services, etc. For example, when the user is in a specific area, the information providing unit can prioritize providing information related to that area. Furthermore, when the user is traveling, the information providing unit can prioritize providing information related to the travel destination. Furthermore, when the user is at home, the information providing unit can prioritize providing information related to services around the user's home. For example, the information providing unit inputs the user's location information data into a generation AI to identify highly relevant information. In this way, highly relevant information can be prioritized by taking into account the user's geographical location information.

[0152] The information providing unit can analyze the user's social media activity and provide related information when providing information. For example, the information providing unit can analyze the user's social media activity and provide related information when providing information. Analysis of social media activity includes, but is not limited to, analysis of posted content and follower analysis. For example, the information providing unit can prioritize providing information related to products and services mentioned by the user on social media. The information providing unit can also analyze the content of the user's social media posts and provide related information. The information providing unit can also provide related information by referring to the activity of the user's friends on social media. For example, the information providing unit inputs the user's social media data into a generation AI to identify related information. This makes it possible to provide highly relevant information by analyzing the user's social media activity.

[0153] The information providing unit can customize the information providing method by reflecting the user's past feedback when providing information. For example, the information providing unit customizes the information providing method by reflecting the user's past feedback when providing information. Examples of collecting feedback include, but are not limited to, questionnaires and user reviews. For example, the information providing unit suggests an optimal information providing method based on feedback provided by the user in the past. The information providing unit can also preferentially suggest a specific information providing method based on the user's past feedback. The information providing unit can also analyze the user's past feedback and customize the information providing method. For example, the information providing unit inputs the user's feedback data into a generation AI and customizes the information providing method. In this way, the information providing method can be customized by reflecting the user's past feedback.

[0154] The business negotiation arrangement unit can estimate a user's emotions and adjust the business negotiation arrangement method based on the estimated user emotions. The business negotiation arrangement unit, for example, estimates a user's emotions and adjusts the business negotiation arrangement method based on the estimated user emotions. Emotion estimation includes, but is not limited to, emotion recognition algorithms, types of emotions, etc. For example, if the user is nervous, the business negotiation arrangement unit provides a simple and highly visible business negotiation arrangement method. Furthermore, if the user is relaxed, the business negotiation arrangement unit can provide a business negotiation arrangement method that includes detailed information. Furthermore, if the user is in a hurry, the business negotiation arrangement unit can provide a concise business negotiation arrangement method that focuses on the main points. For example, the business negotiation arrangement unit inputs the user's facial expression data into a generation AI to estimate emotions. This allows for more appropriate business negotiation arrangement by adjusting the business negotiation arrangement method according to the user's emotions.

[0155] The business negotiation arrangement unit can select the optimal arrangement method by referring to past business negotiation history when arranging a business negotiation. For example, the business negotiation arrangement unit selects the optimal arrangement method by referring to past business negotiation history when arranging a business negotiation. The use of business negotiation history includes, for example, the content of the business negotiation and the results of the business negotiation, but is not limited to these examples. For example, the business negotiation arrangement unit selects the optimal arrangement method based on business negotiations conducted by the user in the past. The business negotiation arrangement unit can also prioritize providing related information from the user's past business negotiation history. The business negotiation arrangement unit can also analyze the user's past business negotiation history and provide the optimal business negotiation arrangement method. For example, the business negotiation arrangement unit inputs the user's business negotiation history data into a generation AI and selects the optimal arrangement method. In this way, the optimal business negotiation arrangement method can be selected by referring to the past business negotiation history.

[0156] The business negotiation arrangement unit can filter the arrangement content based on the user's current areas of interest when arranging a business negotiation. For example, the business negotiation arrangement unit filters the arrangement content based on the user's current areas of interest when arranging a business negotiation. Identification of areas of interest can include, but is not limited to, survey results, past behavioral history, etc. For example, the business negotiation arrangement unit prioritizes arranging business negotiations related to areas in which the user has recently shown interest. The business negotiation arrangement unit can also arrange related business negotiations based on areas in which the user has previously shown interest. The business negotiation arrangement unit can also analyze the user's social media activity and arrange business negotiations related to the user's current areas of interest. For example, the business negotiation arrangement unit inputs the user's social media data into a generation AI to identify the user's areas of interest. This makes it possible to arrange highly relevant business negotiations by filtering the arrangement content based on the user's current areas of interest.

[0157] The business negotiation arrangement unit can improve the arrangement method by reflecting user feedback when arranging a business negotiation. The business negotiation arrangement unit, for example, improves the arrangement method by reflecting user feedback when arranging a business negotiation. Examples of collecting feedback include, but are not limited to, surveys and user reviews. The business negotiation arrangement unit improves the business negotiation arrangement method, for example, based on feedback provided by the user. The business negotiation arrangement unit can also optimize the arrangement content from user feedback. The business negotiation arrangement unit can also analyze user feedback and optimize the business negotiation arrangement method. For example, the business negotiation arrangement unit inputs user feedback data into a generation AI to improve the arrangement method. In this way, the arrangement method can be improved by reflecting user feedback.

[0158] The business negotiation arrangement unit can estimate a user's emotions and determine the priority of business negotiations based on the estimated user emotions. The business negotiation arrangement unit, for example, estimates a user's emotions and determines the priority of business negotiations based on the estimated user emotions. Emotion estimation includes, but is not limited to, emotion recognition algorithms, types of emotions, and the like. For example, if a user requests an urgent business negotiation, the business negotiation arrangement unit prioritizes the business negotiation. Furthermore, if the user is relaxed, the business negotiation arrangement unit can arrange the business negotiation with normal priority. Furthermore, if the user is feeling stressed, the business negotiation arrangement unit can increase the priority to respond quickly. For example, the business negotiation arrangement unit inputs the user's facial expression data into a generation AI to estimate emotions. This enables more appropriate business negotiation arrangement by determining the priority of business negotiations based on the user's emotions.

[0159] The business negotiation arrangement unit can prioritize relevant business negotiations by taking into account the user's geographical location information when arranging business negotiations. For example, the business negotiation arrangement unit prioritizes relevant business negotiations by taking into account the user's geographical location information when arranging business negotiations. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, if the user is in a specific area, the business negotiation arrangement unit prioritizes business negotiations related to that area. Furthermore, if the user is traveling, the business negotiation arrangement unit can prioritize business negotiations related to the user's travel destination. Furthermore, if the user is at home, the business negotiation arrangement unit can prioritize business negotiations related to services near the user's home. For example, the business negotiation arrangement unit inputs the user's location information data into a generation AI to identify relevant business negotiations. This allows for the user's geographical location information to be considered when arranging relevant business negotiations.

[0160] The business negotiation arrangement unit can arrange related business negotiations by analyzing the user's social media activity when arranging a business negotiation. For example, the business negotiation arrangement unit can arrange related business negotiations by analyzing the user's social media activity when arranging a business negotiation. Analysis of social media activity includes, but is not limited to, analysis of post content and follower analysis. For example, the business negotiation arrangement unit prioritizes arranging business negotiations related to products or services mentioned by the user on social media. The business negotiation arrangement unit can also analyze the user's social media posts to arrange related business negotiations. The business negotiation arrangement unit can also arrange related business negotiations by referring to the activity of the user's friends on social media. For example, the business negotiation arrangement unit inputs the user's social media data into a generation AI to identify related business negotiations. This makes it possible to arrange highly relevant business negotiations by analyzing the user's social media activity.

[0161] The business negotiation arrangement unit can customize the arrangement method by reflecting the user's past feedback when arranging a business negotiation. For example, the business negotiation arrangement unit customizes the arrangement method by reflecting the user's past feedback when arranging a business negotiation. Examples of collecting feedback include, but are not limited to, surveys and user reviews. For example, the business negotiation arrangement unit proposes the optimal business negotiation arrangement method based on feedback provided by the user in the past. The business negotiation arrangement unit can also preferentially propose a specific business negotiation arrangement method based on the user's past feedback. The business negotiation arrangement unit can also analyze the user's past feedback and customize the business negotiation arrangement method. For example, the business negotiation arrangement unit inputs the user's feedback data into a generation AI to customize the arrangement method. In this way, the arrangement method can be customized by reflecting the user's past feedback. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, response unit, feature reflection unit, and linking unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart device 14 and receives an inquiry from a user. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a response by utilizing a database of products and services of a company. The feature reflection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reflects the features of a real sales representative in an avatar. The linking unit is realized, for example, by the control unit 46A of the smart device 14 and links the avatar with a real sales representative. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, response unit, feature reflection unit, and linking unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the smart glasses 214 and receives an inquiry from a user. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a response by utilizing a database of products and services of a company. The feature reflection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reflects the features of a real sales representative in an avatar. The linking unit is realized, for example, by the control unit 46A of the smart glasses 214 and links the avatar with a real sales representative. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, response unit, feature reflection unit, and linking unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the headset type terminal 314 and receives an inquiry from a user. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a response by utilizing a database of products and services of a company. The feature reflection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reflects the features of a real sales representative in an avatar. The linking unit is realized, for example, by the control unit 46A of the headset type terminal 314 and links the avatar with a real sales representative. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, response unit, feature reflection unit, and linking unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit is realized by the control unit 46A of the robot 414 and receives an inquiry from a user. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and generates a response by utilizing a database related to a company's products and services. The feature reflection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reflects the features of a real sales representative in an avatar. The linking unit is realized, for example, by the control unit 46A of the robot 414 and links the avatar with a real sales representative.

[0162] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0163] The reception unit can analyze the user's past inquiry history and select the optimal reception method. For example, it can automatically display the contents of inquiries that the user has frequently made in the past as candidates. The reception unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception unit can predict and suggest the contents of inquiries that will be made during a specific time period based on the user's past inquiry history. In this way, by analyzing the past inquiry history, it is possible to provide the user with the optimal reception method.

[0164] The answering unit can adjust the use of technical terms in the answer depending on the user's level of expertise. For example, if the user has technical knowledge, the answer provided can be full of technical terms. On the other hand, if the user has general knowledge, the answer provided can avoid technical terms. Furthermore, the answering unit can estimate the user's level of expertise and provide an answer accordingly. This makes it possible to provide appropriate information by adjusting the use of technical terms in the answer depending on the user's level of expertise.

[0165] The collaboration unit can select the optimal collaboration method by referring to the past collaboration history between the avatar and the actual sales representative. For example, the optimal collaboration method can be selected based on collaboration methods that have been successful between the avatar and the sales representative in the past. It can also adjust the collaboration method to avoid collaboration methods that have failed between the avatar and the sales representative in the past. Furthermore, the collaboration unit can analyze the past collaboration history between the avatar and the sales representative and select the optimal collaboration method. In this way, the optimal collaboration method can be selected by referring to the past collaboration history.

[0166] The feature reflection unit can optimize the features by referring to the sales representative's past negotiation history. For example, the feature of the sales representative's successful negotiations in the past can be reflected in the avatar. The feature reflection unit can also adjust the avatar to avoid the feature of the sales representative's unsuccessful negotiations in the past. Furthermore, the feature reflection unit can analyze the sales representative's past negotiation history and reflect the optimal feature in the avatar. In this way, the avatar's features can be optimized by referring to the sales representative's past negotiation history.

[0167] The database utilization unit can apply the optimal search algorithm by referring to the user's past search history. For example, the optimal search algorithm is applied based on keywords the user has searched for in the past. It can also prioritize displaying related information based on the user's past search history. Furthermore, the database utilization unit can analyze the user's past search history and provide optimal search results. This makes it possible to apply the optimal search algorithm by referring to the past search history.

[0168] The reception unit can estimate the user's emotions and adjust the method of receiving inquiries based on the estimated user emotions. For example, if the user is feeling stressed, a simple interface can be provided to minimize input steps. Alternatively, if the user is relaxed, detailed input options can be provided and a customizable input method can be suggested. Furthermore, if the user is in a hurry, voice input can be prioritized to allow inquiries to be received quickly. This allows for more appropriate responses by adjusting the method of receiving inquiries according to the user's emotions.

[0169] The answering unit can estimate the user's emotions and adjust the way the answer is expressed based on the estimated user's emotions. For example, if the user is nervous, a simple, highly visible answer can be provided. If the user is relaxed, an answer including detailed information can be provided. Furthermore, if the user is in a hurry, a concise answer that hits the main points can be provided. In this way, by adjusting the way the answer is expressed according to the user's emotions, more appropriate answers can be provided.

[0170] The feature reflecting unit can estimate the user's emotions and adjust the avatar's features based on the estimated user's emotions. For example, if the user is nervous, the avatar's facial expression can be made calm. If the user is relaxed, the avatar's facial expression can be made brighter. Furthermore, if the user is excited, the avatar's facial expression can be made more lively. In this way, by adjusting the avatar's features according to the user's emotions, more realistic responses are possible.

[0171] The collaboration unit can estimate the user's emotions and adjust the collaboration method between the avatar and the sales representative based on the estimated user's emotions. For example, if the user is nervous, the avatar responds calmly, allowing for smooth collaboration with the sales representative. Alternatively, if the user is relaxed, the avatar responds naturally, allowing for smooth collaboration with the sales representative. Furthermore, if the user is excited, the avatar responds actively, allowing for quick collaboration with the sales representative. This allows for smoother collaboration by adjusting the collaboration method according to the user's emotions.

[0172] The recording unit can estimate the user's emotions and adjust the recording method based on the estimated user emotions. For example, if the user is nervous, a simple and highly visible recording method can be provided. If the user is relaxed, a recording method including detailed information can be provided. Furthermore, if the user is in a hurry, a concise recording method that focuses on the main points can be provided. This allows for more appropriate recording by adjusting the recording method according to the user's emotions.

[0173] The processing flow of the second embodiment will be briefly explained below.

[0174] Step 1: The reception unit receives an inquiry from a user. The inquiry may be in the form of text, voice, or image. For example, the reception unit receives a text message sent by the user and inputs it into the system. In the case of a voice message, it is converted into text using voice recognition technology, and in the case of an image message, its content is analyzed using image analysis technology. Step 2: In the answering section, the avatar provides an answer to the user's inquiry. The answering section generates an answer by utilizing a database of the company's products and services. For example, it retrieves product and service information from the database and provides it to the user. The answering section also uses natural language processing technology to analyze the user's question and generate an appropriate answer. Step 3: The feature reflection unit reflects the characteristics of a real salesperson in the avatar. For example, it learns the voice, speaking style, and facial expressions of the salesperson and reflects them in the avatar. The feature reflection unit collects voice data of the salesperson and reflects it in the avatar. It can also learn the characteristics of the speaking style and facial expressions of the salesperson and reflect them in the avatar. Step 4: The linking unit links the avatar with a real salesperson. For example, the avatar records interactions with the user and provides that information to the real salesperson. The linking unit records information provided by the avatar in response to the user's questions and the user's interests, and provides this information to the real salesperson. If the user wants to know more about a specific product, the linking unit arranges a business meeting with a real salesperson.

[0175] 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.

[0176] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0177] 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.

[0178] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0179] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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).

[0185] 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.

[0186] 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.

[0187] 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.

[0188] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0189] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0195] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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).

[0201] 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.

[0202] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0203] 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.

[0204] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0205] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0211] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0212] 7, a 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0222] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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."

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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.

[0246] [Explanation of symbols]

[0247] 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. a reception unit that receives inquiries from users; a reply unit that provides an answer to the inquiry received by the reception unit; a characteristic reflection unit that reflects characteristics of a real salesperson in an avatar based on the answer provided by the answering unit; a linking unit that links the avatar with a real salesperson based on the characteristics reflected by the characteristic reflecting unit; Equipped with A system characterized by:

2. The answering section Have a database utilization department that utilizes databases related to company products and services 2. The system of claim 1.

3. The linking unit is The avatar has a recording unit that records interactions with the user.

2. The system of claim 1.

4. The recording unit Equipped with an information providing section that provides recorded information to actual sales representatives 4. The system of claim 3.

5. The feature reflection unit Learn the voice, speaking style, and facial expressions of salespeople 2. The system of claim 1.

6. The linking unit is Arrange business meetings between your avatar and a real salesperson 2. The system of claim 1.

7. The reception unit Estimate user emotions and adjust the way inquiries are received based on the estimated user emotions 2. The system of claim 1.

8. The reception unit Analyze the user's past inquiry history and select the optimal reception method 2. The system of claim 1.

9. The reception unit Filtering inquiries based on the user's current interests when they arrive 2. The system of claim 1.

Images