System

Abstract

An object of a system according to an embodiment is to efficiently organize and report information while saving time and effort of a salesperson.SOLUTION: A system includes an analysis unit, a summary generation unit, an input unit, and a question answering unit. The analysis part analyzes the schedule, the mail with the customer and the minutes of the business talk. The summary generation unit summarizes the information analyzed by the analysis unit. The input unit automatically inputs the summary generated by the summary generation unit to the Compass. The question answering unit answers the question based on the summary generated by the summary generation 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 technology had the problem that sales representatives had to manually organize and report schedules, emails with customers, and minutes of sales meetings, which was a time-consuming process.

[0005] The system according to the embodiment aims to reduce the workload of sales representatives and to efficiently organize and report information. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a summary generation unit, an input unit, and a question and answer unit. The analysis unit analyzes schedules, emails with customers, and minutes of business meetings. The summary generation unit summarizes the information analyzed by the analysis unit. The input unit automatically inputs the summaries generated by the summary generation unit into Compass. The question and answer unit answers questions based on the summaries generated by the summary generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can reduce the workload of sales representatives and efficiently organize and report information. [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) The automatic input system according to an embodiment of the present invention is a system that summarizes the outline of the target project and the content of the negotiation from schedules, emails with customers, minutes of business negotiations, etc., and automatically inputs the activity history and project status into Compass. As a result, the automatic input system saves sales representatives the trouble of inputting data into Compass, and enables them to instantly know the project status, sales, schedules, and the content (summary) of the meeting on a chat basis.

[0029] An automatic input system according to an embodiment includes an analysis unit, a summary generation unit, an input unit, and a question and answer unit. The analysis unit analyzes schedules, emails with customers, and minutes of business meetings. For example, the analysis unit analyzes the contents of schedules and extracts important events. The analysis unit can also analyze emails with customers and extract important exchanges. The analysis unit can also analyze minutes of business meetings and extract important points. The summary generation unit summarizes the information analyzed by the analysis unit. For example, the summary generation unit extracts important points from minutes of business meetings and generates a summary. The summary generation unit can also summarize the contents of emails with customers. The summary generation unit can also summarize the contents of schedules. The input unit automatically inputs the summaries generated by the summary generation unit into Compass. For example, the input unit inputs summaries of business meetings into Compass. The input unit can also input summaries of emails with customers into Compass. The input unit can also input summaries of schedules into Compass. The question answering unit answers questions based on the summary generated by the summary generating unit. For example, the question answering unit answers a question such as "Please tell me about the latest business negotiations for this project" based on the summary. The question answering unit can also answer a question such as "When is the next business negotiation scheduled?" based on the summary. The question answering unit can also answer a question such as "Please tell me about the progress of this project" based on the summary. As a result, the automatic input system according to the embodiment eliminates the need for sales representatives to enter data into Compass, and enables them to instantly obtain project status, sales, schedules, meeting contents (summaries), and the like via chat.

[0030] The analysis unit can predict the next action item based on the customer's past behavioral patterns and speech history, and include it in the summary. The analysis unit, for example, analyzes the customer's past emails and business negotiation history to predict the next action item to be taken. For example, the next step is included in the summary based on comments made in past business negotiations. The analysis unit also analyzes the customer's behavioral patterns to predict the next expected action. For example, the next suggestion is included in the summary based on the interests and concerns expressed by the customer in the past. The analysis unit also predicts the next action to be taken based on the customer's speech history, and reflects this in the summary. For example, the next step is included in the summary based on information or services the customer has requested in the past. In this way, by predicting the next action item based on the customer's past behavioral patterns and speech history, and including it in the summary, the next step can be effectively planned.

[0031] The analysis unit can extract information about competitors and market trends from the minutes of business meetings and reflect them in the summary. The analysis unit, for example, analyzes the minutes of business meetings and extracts information about competitors. For example, information about competitors' products and services is included in the summary. The analysis unit also extracts market trends from the content of business meetings and reflects them in the summary. For example, the latest industry trends and market changes are included in the summary. The analysis unit also extracts competitors' strategies and market trends from conversations with customers and reflects them in the summary. For example, the strengths and weaknesses of competitors are included in the summary. In this way, by extracting information about competitors and market trends from the minutes of business meetings and reflecting them in the summary, competitiveness can be improved.

[0032] The analysis unit can analyze the audio data of a business meeting and generate a summary using speech recognition technology. For example, the analysis unit analyzes the audio data of a business meeting and converts it into text using speech recognition technology. For example, it automatically extracts important points of the business meeting and generates a summary. The analysis unit also uses speech recognition technology to convert the content of the business meeting into text in real time and generate a summary. For example, it instantly analyzes comments made during the business meeting and reflects them in the summary. The analysis unit also analyzes the audio data of the business meeting and generates a summary by analyzing the speaker's tone and emotion. For example, it emphasizes positive comments and includes them in the summary. In this way, the content of the business meeting can be quickly understood by analyzing the audio data of the business meeting and generating a summary using speech recognition technology.

[0033] The analysis unit can analyze video data from a video conference with a customer and reflect non-verbal communication in the summary. The analysis unit, for example, analyzes the video data from the video conference and analyzes the gestures and facial expressions of the speaker. For example, the analysis unit reflects the customer's satisfaction and level of interest in the summary. The analysis unit also analyzes the video data and extracts non-verbal communication. For example, the analysis unit includes the customer's positive gestures and facial expressions in the summary. The analysis unit also analyzes the video data from the video conference and analyzes the speaker's emotions to generate a summary. For example, positive facial expressions and gestures are emphasized and included in the summary. In this way, by analyzing the video data from a video conference with a customer and reflecting non-verbal communication in the summary, the customer's intentions can be understood more accurately.

[0034] The input unit can evaluate the reliability of the data when inputting summary data and input only highly reliable data preferentially. The input unit, for example, develops an algorithm to evaluate the reliability of summary data and inputs only highly reliable data into Compass. For example, the input unit evaluates reliability based on the source of the data and the consistency of its content. The input unit also builds a system that evaluates the reliability of summary data in real time and filters out unreliable data. For example, the input unit selects data based on a reliability score. The input unit also checks consistency with past data to evaluate the reliability of the data. For example, only data that matches past sales negotiation history is input into Compass. In this way, the reliability of the data is evaluated and only highly reliable data is input, thereby improving the accuracy of the data.

[0035] The input unit can check the consistency of summary data with past data when it is input, and issue an alert if there is a discrepancy. For example, the input unit builds a system that checks the consistency of summary data with past data when it is input. For example, it issues an alert if it detects a data discrepancy. The input unit also develops a system that checks the consistency with past data in real time and automatically corrects any discrepancies. For example, it introduces an algorithm to maintain data consistency. The input unit also builds a database to check the consistency of summary data with past data when it is input. For example, it evaluates consistency based on past sales negotiation history and customer information. This makes it possible to maintain data consistency by checking consistency with past data and issuing an alert if there is a discrepancy.

[0036] The input unit can automatically record the history of changes to the data after the summary data is input, making it possible to trace the change history. For example, the input unit builds a system that automatically records the history of changes to the data after the summary data is input. For example, it records the date and time of data changes and the details of the changes. The input unit also builds a database that makes the history of changes to the data traceable. For example, it adds a function to display the change history in chronological order. The input unit also develops a system that automatically records the history of changes to the summary data and allows the user to check the changes. For example, it displays the change history in a graph or chart. In this way, the history of changes to the data can be automatically recorded and made traceable, making it possible to manage the history of changes to the data.

[0037] The input unit can also link with other CRM systems when entering summary data, allowing data to be managed centrally. For example, the input unit builds a system that links with other CRM systems when entering summary data. For example, it links with Salesforce or HubSpot to centrally manage data. The input unit also develops a system that links data with other CRM systems in real time and maintains data consistency. For example, it automatically synchronizes data. The input unit also builds a system that automatically imports data from other CRM systems when entering summary data. For example, it centrally manages customer information and sales negotiation history. This allows it to link with other CRM systems and centrally manage data, improving data consistency and efficiency.

[0038] The input unit provides an interface that requests confirmation from the user before inputting summary data, thereby preventing erroneous input. The input unit, for example, builds a system that provides an interface that requests confirmation from the user before inputting summary data. For example, a preview of the input content is displayed so that the user can confirm it. The input unit also develops an interface that allows the user to confirm the summary data and prevent erroneous input. For example, a confirmation button is provided so that the user can approve the input content. The input unit also builds a system that displays an alert that requests confirmation from the user before inputting summary data. For example, a message is displayed to confirm that the input content is correct. In this way, erroneous input can be prevented by requesting confirmation from the user before inputting summary data.

[0039] When storing detailed histories, the question answering unit can prioritize data according to its importance, enabling important data to be searched for quickly. For example, the question answering unit builds a system that prioritizes data according to its importance when storing detailed histories. For example, important business negotiation details and customer information are saved preferentially. The question answering unit also develops a system that evaluates the importance of data and enables important data to be searched for quickly. For example, the data is classified based on its importance score. The question answering unit also builds a system that sets search priorities according to the importance of data when storing detailed histories. For example, important data is displayed at the top of search results. This allows data to be prioritized according to its importance, enabling important data to be searched for quickly, thereby enabling necessary information to be obtained quickly.

[0040] The question answering unit can provide more accurate answers by referring to past similar questions and their answers when answering a question. For example, the question answering unit builds a system that automatically searches for and references past similar questions and their answers when answering a question. For example, it provides the optimal answer based on the past question history. The question answering unit also develops a search algorithm for similar questions and builds a system that provides highly accurate answers based on past questions and answers. For example, it searches for similar questions based on keywords in the question content. The question answering unit also develops a system that refers to past similar questions and their answers when answering a question, improving the accuracy of the answers. For example, it generates the optimal answer based on past answers. In this way, it is possible to provide more accurate answers by referring to past similar questions and their answers.

[0041] The question answering unit analyzes the question and answer history, learns the user's question patterns, and can improve the accuracy of answers from the next time onwards. The question and answering unit, for example, analyzes the question and answer history and builds a system that learns the user's question patterns. For example, it identifies frequently asked questions and improves the accuracy of answers. The question and answering unit also learns the user's question patterns and develops an algorithm that improves the accuracy of answers from the next time onwards. For example, it provides optimal answers based on the past question history. The question and answering unit also analyzes the question and answer history, learns the user's question patterns, and builds a system that improves the accuracy of answers. For example, it analyzes the user's question trends and generates predicted answers. In this way, by analyzing the question and answer history and learning the user's question patterns, it is possible to improve the accuracy of answers from the next time onwards.

[0042] The question answering unit can support voice input during question answering, allowing the user to ask questions by voice. The question answering unit, for example, builds a system that supports voice input during question answering. For example, a user inputs a question by voice, and a generation AI analyzes the voice and provides an answer. The question answering unit also uses voice recognition technology to develop an interface that allows the user to ask questions by voice. For example, the voice input is converted into text, and a generation AI generates an answer. The question answering unit also supports voice input during question answering, building a system that allows the user to ask questions by voice. For example, the voice command is analyzed and the optimal answer is provided. In this way, by supporting voice input, the user can ask questions by voice, improving convenience.

[0043] The question answering unit can generate visual data when answering questions and provide information visually. The question answering unit, for example, builds a system that generates visual data when answering questions. For example, it displays the progress of business negotiations in graphs or charts. The question answering unit also generates visual data and develops an interface that provides information visually. For example, it displays sales data or project status in charts. The question answering unit also builds a system that generates visual data when answering questions and provides information visually. For example, it shows data fluctuations in graphs. In this way, generating visual data and providing information visually makes it easier to understand the information.

[0044] The question answering unit can analyze interactions on the chat interface, predict the user's intentions, and make proactive suggestions. The question answering unit, for example, analyzes interactions on the chat interface and builds a system that predicts the user's intentions. For example, it automatically generates the next suggestion based on the content of the user's question. The question answering unit also develops an algorithm that predicts the user's intentions and makes proactive suggestions. For example, it provides the user with information they are looking for in advance. The question answering unit also analyzes interactions on the chat interface and builds a system that predicts the user's intentions and makes proactive suggestions. For example, it generates suggestions based on the user's past question history. This makes it possible to analyze interactions on the chat interface, predict the user's intentions, and make proactive suggestions, thereby improving user convenience.

[0045] The question and answering unit can record interactions on the chat interface so that they can be referenced later. For example, the question and answering unit builds a system that automatically records interactions on the chat interface so that they can be referenced later. For example, it stores the chat log in a database. The question and answering unit also records chat interactions and develops an interface that allows users to reference them later. For example, it provides a function that allows users to search past chat history. The question and answering unit also builds a system that records interactions on the chat interface so that they can be referenced later. For example, it tags and saves important interactions. This allows interactions on the chat interface to be recorded so that they can be referenced later, making it easy to check past interactions.

[0046] The question answering unit can analyze interactions on the chat interface and provide answers customized to the user's needs. The question answering unit, for example, analyzes interactions on the chat interface and builds a system that provides answers customized to the user's needs. For example, it generates an optimal answer based on the content of the user's question. The question answering unit also analyzes user needs in real time and develops an algorithm that provides customized answers. For example, it adjusts answers based on the user's past question history. The question answering unit also analyzes interactions on the chat interface and builds a system that provides answers customized to the user's needs. For example, it generates answers based on the user's profile information. In this way, by analyzing interactions on the chat interface and providing answers customized to the user's needs, it is possible to improve user satisfaction.

[0047] The question and answering unit can make the chat interface multilingual so that it can also accommodate international users. The question and answering unit, for example, builds a system that makes the chat interface multilingual. For example, it supports communication in multiple languages ​​such as English, French, and Chinese. The question and answering unit also develops a multilingual chat interface so that it can also accommodate international users. For example, it introduces a real-time translation function. The question and answering unit also makes the chat interface multilingual so that it can also accommodate international users. For example, it prepares templates corresponding to each language. In this way, the chat interface can be made multilingual so that it can also accommodate international users.

[0048] The question and answering unit can add a function to the chat interface that allows images and videos to be sent, making it possible to share visual information as well. For example, the question and answering unit builds a system that adds a function to the chat interface that allows images and videos to be sent. For example, product photos and demo videos can be shared. The question and answering unit can also develop a chat interface that allows images and videos to be sent, making it possible to share visual information as well. For example, sending presentation materials. The question and answering unit can also add a function to the chat interface that allows images and videos to be sent, making it possible to share visual information as well. For example, providing visual content that meets customer requests. In this way, by adding a function to the chat interface that allows images and videos to be sent, it becomes possible to share visual information as well.

[0049] The question and answering unit can refer to data on similar past cases and provide reference information when a supervisor is understanding a case. For example, the question and answering unit builds a system that automatically refers to data on similar past cases when a supervisor is understanding a case. For example, reference information is provided based on past success stories and failure stories. The question and answering unit also develops an algorithm that refers to data on similar cases and provides reference information for the supervisor when understanding a case. For example, optimal information is provided based on past case history. The question and answering unit also builds a system that refers to data on similar past cases and provides reference information when a supervisor is understanding a case. For example, the progress and results of similar cases are displayed. This allows the supervisor to refer to data on similar past cases and provide reference information when understanding a case, thereby supporting the supervisor's decision-making.

[0050] The question and answering unit can automatically extract important points when a supervisor conducts a review, thereby improving the efficiency of the review. The question and answering unit, for example, builds a system that automatically extracts important points when a supervisor conducts a review. For example, it extracts the main points of a business negotiation and the next action items. The question and answering unit also develops an algorithm that automatically extracts important points and improves the efficiency of a supervisor's review. For example, it extracts important remarks and decisions made in a business negotiation. The question and answering unit also builds a system that automatically extracts important points when a supervisor conducts a review, thereby improving the efficiency of the review. For example, it automatically generates a summary of a business negotiation. This allows the efficiency of a supervisor's review to be improved by automatically extracting important points when the supervisor conducts a review.

[0051] The question and answering unit can evaluate the reliability of data and preferentially display highly reliable data when a supervisor is understanding a case. The question and answering unit, for example, builds a system that evaluates the reliability of data when a supervisor is understanding a case. For example, the reliability is evaluated based on the source of the data and the consistency of the content, and highly reliable data is preferentially displayed. The question and answering unit also develops a system that evaluates the reliability of data in real time and filters out low-reliability data. For example, the system selects data based on a reliability score and displays it to the supervisor. The question and answering unit also builds a system that evaluates the reliability of data when a supervisor is understanding a case and preferentially displays highly reliable data. For example, the system checks consistency with past data and displays highly reliable data. This allows the supervisor to evaluate the reliability of data and preferentially display highly reliable data when understanding a case, thereby supporting decision-making based on accurate information.

[0052] The question and answering unit can generate visual data and provide information visually when a supervisor is trying to understand a project. The question and answering unit, for example, builds a system that generates visual data when a supervisor is trying to understand a project. For example, it displays the progress of a business negotiation in graphs and charts. The question and answering unit also develops an interface that generates visual data and provides information visually. For example, it displays sales data and project status in charts. The question and answering unit also builds a system that generates visual data and provides information visually when a supervisor is trying to understand a project. For example, it shows data fluctuations in a graph. In this way, by generating visual data and providing information visually, the supervisor can understand the project more quickly and accurately.

[0053] The question and answering unit can automatically collect feedback from other departments when a supervisor conducts a review and make a comprehensive evaluation. For example, the question and answering unit builds a system that automatically collects feedback from other departments when a supervisor conducts a review. For example, it integrates feedback from the marketing department and the technical department. The question and answering unit also develops an algorithm that automatically collects feedback from other departments and makes a comprehensive evaluation. For example, it calculates an overall evaluation based on the evaluations of each department. The question and answering unit also builds a system that automatically collects feedback from other departments when a supervisor conducts a review and makes a comprehensive evaluation. For example, it collects feedback in real time and reflects it in the evaluation. In this way, by automatically collecting feedback from other departments and making a comprehensive evaluation, the accuracy and efficiency of the supervisor's review can be improved.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The analysis unit can extract information about competitors and market trends from the minutes of business meetings and reflect them in the summary. For example, it can analyze the minutes of business meetings and include information about competitors' products and services in the summary. The analysis unit can also extract market trends from the content of business meetings and reflect them in the summary. For example, it can include the latest industry trends and market changes in the summary. The analysis unit can also extract competitors' strategies and market trends from conversations with customers and reflect them in the summary. For example, it can include the strengths and weaknesses of competitors in the summary. In this way, by extracting information about competitors and market trends from the minutes of business meetings and reflecting them in the summary, competitiveness can be improved.

[0056] The analysis unit can predict the next action item based on the customer's past behavioral patterns and speech history, and include it in the summary. For example, it can analyze the customer's past emails and business negotiation history to predict the next action item to be taken. For example, it can include the next step in the summary based on comments made in past business negotiations. The analysis unit can also analyze the customer's behavioral patterns to predict the next expected action. For example, it can include the next suggestion in the summary based on the interests and concerns expressed by the customer in the past. The analysis unit can also predict the next action to be taken based on the customer's speech history, and reflect this in the summary. For example, it can include the next step in the summary based on information or services the customer has requested in the past. In this way, by predicting the next action item based on the customer's past behavioral patterns and speech history, and including it in the summary, the next step can be effectively planned.

[0057] When inputting summary data, the input unit can evaluate the reliability of the data and prioritize the input of only highly reliable data. For example, an algorithm can be developed to evaluate the reliability of summary data, and only highly reliable data can be input into Compass. For example, reliability can be evaluated based on the source of the data and the consistency of its content. The input unit can also build a system to evaluate the reliability of summary data in real time and filter out unreliable data. For example, it can select data based on a reliability score. The input unit can also check the consistency with past data to evaluate the reliability of the data. For example, it can input only data that matches past sales negotiation history into Compass. This improves data accuracy by evaluating the reliability of the data and inputting only highly reliable data.

[0058] The input unit can check the consistency of summary data with past data when it is input, and issue an alert if there is a discrepancy. For example, a system is built that checks the consistency with past data when summary data is input. For example, an alert is issued if a data discrepancy is detected. The input unit also develops a system that checks the consistency with past data in real time and automatically corrects any discrepancies. For example, an algorithm is introduced to maintain data consistency. The input unit also builds a database to check the consistency with past data when summary data is input. For example, consistency is evaluated based on past sales negotiation history and customer information. This makes it possible to maintain data consistency by checking consistency with past data and issuing an alert if there is a discrepancy.

[0059] The input unit can automatically record the history of changes to the data after the summary data is input, making it possible to track them. For example, a system is constructed that automatically records the history of changes to the data after the summary data is input. For example, the date and time of the data change and the details of the change are recorded. The input unit also constructs a database that makes the history of changes to the data traceable. For example, a function is added to display the change history in chronological order. The input unit also develops a system that automatically records the history of changes to the summary data and allows the user to check the changes. For example, the change history is displayed in a graph or chart. In this way, the history of changes to the data can be automatically recorded and made traceable, making it possible to manage the history of changes to the data.

[0060] The input section can link with other CRM systems when entering summary data and centrally manage the data. For example, a system is built that links with other CRM systems when entering summary data. For example, it links with Salesforce or HubSpot to centrally manage data. The input section also develops a system that links data with other CRM systems in real time and maintains data consistency. For example, it automatically synchronizes data. The input section also builds a system that automatically imports data from other CRM systems when entering summary data. For example, it centrally manages customer information and sales negotiation history. This allows it to link with other CRM systems and centrally manage data, improving data consistency and efficiency.

[0061] The input unit provides an interface that requests confirmation from the user before inputting summary data, thereby preventing erroneous input. For example, a system is constructed that provides an interface that requests confirmation from the user before inputting summary data. For example, a preview of the input content is displayed so that the user can confirm it. The input unit also develops an interface that allows the user to confirm the summary data and prevent erroneous input. For example, a confirmation button is provided so that the user can approve the input content. The input unit also constructs a system that displays an alert that requests confirmation from the user before inputting summary data. For example, a message is displayed to confirm that the input content is correct. In this way, erroneous input can be prevented by requesting confirmation from the user before inputting summary data.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: The analysis unit analyzes schedules, emails with customers, and minutes of business meetings. For example, the analysis unit analyzes the contents of schedules and extracts important events. It can also analyze emails with customers and extract important exchanges. It can also analyze minutes of business meetings and extract important points. Step 2: The summary generator summarizes the information analyzed by the analyzer. For example, it can extract important points from minutes of a business meeting and generate a summary. It can also summarize the contents of emails with customers or schedules. Step 3: The input unit automatically inputs the summaries generated by the summary generation unit into Compass. For example, a summary of a business meeting, a summary of an email with a customer, or a summary of a schedule can be input into Compass. Step 4: The question answering unit answers questions based on the summary generated by the summary generating unit. For example, a question such as "Please tell me about the latest business negotiations for this project" can be answered based on the summary. Questions such as "When is the next business negotiation scheduled?" and "Please tell me about the progress of this project" can also be answered based on the summary.

[0064] (Example 2) The automatic input system according to an embodiment of the present invention is a system that summarizes the outline of the target project and the content of the negotiation from schedules, emails with customers, minutes of business negotiations, etc., and automatically inputs the activity history and project status into Compass. As a result, the automatic input system saves sales representatives the trouble of inputting data into Compass, and enables them to instantly know the project status, sales, schedules, and the content (summary) of the meeting on a chat basis.

[0065] An automatic input system according to an embodiment includes an analysis unit, a summary generation unit, an input unit, and a question and answer unit. The analysis unit analyzes schedules, emails with customers, and minutes of business meetings. For example, the analysis unit analyzes the contents of schedules and extracts important events. The analysis unit can also analyze emails with customers and extract important exchanges. The analysis unit can also analyze minutes of business meetings and extract important points. The summary generation unit summarizes the information analyzed by the analysis unit. For example, the summary generation unit extracts important points from minutes of business meetings and generates a summary. The summary generation unit can also summarize the contents of emails with customers. The summary generation unit can also summarize the contents of schedules. The input unit automatically inputs the summaries generated by the summary generation unit into Compass. For example, the input unit inputs summaries of business meetings into Compass. The input unit can also input summaries of emails with customers into Compass. The input unit can also input summaries of schedules into Compass. The question answering unit answers questions based on the summary generated by the summary generating unit. For example, the question answering unit answers a question such as "Please tell me about the latest business negotiations for this project" based on the summary. The question answering unit can also answer a question such as "When is the next business negotiation scheduled?" based on the summary. The question answering unit can also answer a question such as "Please tell me about the progress of this project" based on the summary. As a result, the automatic input system according to the embodiment eliminates the need for sales representatives to enter data into Compass, and enables them to instantly obtain project status, sales, schedules, meeting contents (summaries), and the like via chat.

[0066] The analysis unit can analyze the tone and emotions of a business negotiation and generate a summary that emphasizes positive elements. For example, the analysis unit analyzes minutes of a business negotiation and analyzes the tone and emotions of the speaker. For example, it emphasizes positive remarks and forward-looking opinions and reflects them in the summary. The analysis unit also analyzes the content of emails with customers and extracts parts that express positive emotions. For example, it includes parts that show high customer satisfaction in the summary. The analysis unit also analyzes the contents of a schedule and emphasizes positive events and successful business negotiations. For example, it reflects the key points of successful business negotiations in the summary. In this way, the content of a business negotiation can be communicated more effectively by analyzing the tone and emotions of a business negotiation and generating a summary that emphasizes positive elements.

[0067] The analysis unit can predict the next action item based on the customer's past behavioral patterns and speech history, and include it in the summary. The analysis unit, for example, analyzes the customer's past emails and business negotiation history to predict the next action item to be taken. For example, the next step is included in the summary based on comments made in past business negotiations. The analysis unit also analyzes the customer's behavioral patterns to predict the next expected action. For example, the next suggestion is included in the summary based on the interests and concerns expressed by the customer in the past. The analysis unit also predicts the next action to be taken based on the customer's speech history, and reflects this in the summary. For example, the next step is included in the summary based on information or services the customer has requested in the past. In this way, by predicting the next action item based on the customer's past behavioral patterns and speech history, and including it in the summary, the next step can be effectively planned.

[0068] The analysis unit can extract information about competitors and market trends from the minutes of business meetings and reflect them in the summary. The analysis unit, for example, analyzes the minutes of business meetings and extracts information about competitors. For example, information about competitors' products and services is included in the summary. The analysis unit also extracts market trends from the content of business meetings and reflects them in the summary. For example, the latest industry trends and market changes are included in the summary. The analysis unit also extracts competitors' strategies and market trends from conversations with customers and reflects them in the summary. For example, the strengths and weaknesses of competitors are included in the summary. In this way, by extracting information about competitors and market trends from the minutes of business meetings and reflecting them in the summary, competitiveness can be improved.

[0069] The analysis unit can analyze the audio data of a business meeting and generate a summary using speech recognition technology. For example, the analysis unit analyzes the audio data of a business meeting and converts it into text using speech recognition technology. For example, it automatically extracts important points of the business meeting and generates a summary. The analysis unit also uses speech recognition technology to convert the content of the business meeting into text in real time and generate a summary. For example, it instantly analyzes comments made during the business meeting and reflects them in the summary. The analysis unit also analyzes the audio data of the business meeting and generates a summary by analyzing the speaker's tone and emotion. For example, it emphasizes positive comments and includes them in the summary. In this way, the content of the business meeting can be quickly understood by analyzing the audio data of the business meeting and generating a summary using speech recognition technology.

[0070] The analysis unit can analyze video data from a video conference with a customer and reflect non-verbal communication in the summary. The analysis unit, for example, analyzes the video data from the video conference and analyzes the gestures and facial expressions of the speaker. For example, the analysis unit reflects the customer's satisfaction and level of interest in the summary. The analysis unit also analyzes the video data and extracts non-verbal communication. For example, the analysis unit includes the customer's positive gestures and facial expressions in the summary. The analysis unit also analyzes the video data from the video conference and analyzes the speaker's emotions to generate a summary. For example, positive facial expressions and gestures are emphasized and included in the summary. In this way, by analyzing the video data from a video conference with a customer and reflecting non-verbal communication in the summary, the customer's intentions can be understood more accurately.

[0071] The analysis unit can use the emotion estimation function to analyze customer emotions and generate summaries based on the emotions. The analysis unit, for example, analyzes the content of emails or business negotiations with a customer and analyzes the customer's emotions using the emotion estimation function. For example, the analysis unit reflects the customer's satisfaction or dissatisfaction in the summary. The analysis unit also uses the emotion estimation function to generate summaries based on the customer's emotions. For example, it emphasizes parts with strong positive emotions and includes them in the summary. The analysis unit also analyzes customer emotions in real time and generates summaries based on the results. For example, it generates summaries that reflect changes in the customer's emotions. In this way, by analyzing customer emotions using the emotion estimation function and generating summaries based on emotions, it becomes possible to respond in consideration of the customer's emotions.

[0072] The input unit can evaluate the reliability of the data when inputting summary data and input only highly reliable data preferentially. The input unit, for example, develops an algorithm to evaluate the reliability of summary data and inputs only highly reliable data into Compass. For example, the input unit evaluates reliability based on the source of the data and the consistency of its content. The input unit also builds a system that evaluates the reliability of summary data in real time and filters out unreliable data. For example, the input unit selects data based on a reliability score. The input unit also checks consistency with past data to evaluate the reliability of the data. For example, only data that matches past sales negotiation history is input into Compass. In this way, the reliability of the data is evaluated and only highly reliable data is input, thereby improving the accuracy of the data.

[0073] The input unit can check the consistency of summary data with past data when it is input, and issue an alert if there is a discrepancy. For example, the input unit builds a system that checks the consistency of summary data with past data when it is input. For example, it issues an alert if it detects a data discrepancy. The input unit also develops a system that checks the consistency with past data in real time and automatically corrects any discrepancies. For example, it introduces an algorithm to maintain data consistency. The input unit also builds a database to check the consistency of summary data with past data when it is input. For example, it evaluates consistency based on past sales negotiation history and customer information. This makes it possible to maintain data consistency by checking consistency with past data and issuing an alert if there is a discrepancy.

[0074] The input unit can automatically record the history of changes to the data after the summary data is input, making it possible to trace the change history. For example, the input unit builds a system that automatically records the history of changes to the data after the summary data is input. For example, it records the date and time of data changes and the details of the changes. The input unit also builds a database that makes the history of changes to the data traceable. For example, it adds a function to display the change history in chronological order. The input unit also develops a system that automatically records the history of changes to the summary data and allows the user to check the changes. For example, it displays the change history in a graph or chart. In this way, the history of changes to the data can be automatically recorded and made traceable, making it possible to manage the history of changes to the data.

[0075] The input unit can also link with other CRM systems when entering summary data, allowing data to be managed centrally. For example, the input unit builds a system that links with other CRM systems when entering summary data. For example, it links with Salesforce or HubSpot to centrally manage data. The input unit also develops a system that links data with other CRM systems in real time and maintains data consistency. For example, it automatically synchronizes data. The input unit also builds a system that automatically imports data from other CRM systems when entering summary data. For example, it centrally manages customer information and sales negotiation history. This allows it to link with other CRM systems and centrally manage data, improving data consistency and efficiency.

[0076] The input unit provides an interface that requests confirmation from the user before inputting summary data, thereby preventing erroneous input. The input unit, for example, builds a system that provides an interface that requests confirmation from the user before inputting summary data. For example, a preview of the input content is displayed so that the user can confirm it. The input unit also develops an interface that allows the user to confirm the summary data and prevent erroneous input. For example, a confirmation button is provided so that the user can approve the input content. The input unit also builds a system that displays an alert that requests confirmation from the user before inputting summary data. For example, a message is displayed to confirm that the input content is correct. In this way, erroneous input can be prevented by requesting confirmation from the user before inputting summary data.

[0077] The input unit can use the emotion estimation function to analyze the user's emotion when inputting summary data, thereby improving the accuracy of the input. The input unit, for example, uses the emotion estimation function to build a system that analyzes the user's emotion when inputting summary data. For example, the input accuracy is improved based on the user's emotion score. The input unit also develops a system that analyzes the user's emotion in real time and improves the accuracy of the input. For example, input content is preferentially adopted when positive emotions are strong. The input unit also builds a system that improves the accuracy of the summary data input based on the emotion estimation data. For example, the input content is adjusted according to changes in the user's emotion. In this way, the emotion estimation function can be used to analyze the user's emotion and improve the accuracy of the input, thereby increasing the accuracy of the data.

[0078] When storing detailed histories, the question answering unit can prioritize data according to its importance, enabling important data to be searched for quickly. For example, the question answering unit builds a system that prioritizes data according to its importance when storing detailed histories. For example, important business negotiation details and customer information are saved preferentially. The question answering unit also develops a system that evaluates the importance of data and enables important data to be searched for quickly. For example, the data is classified based on its importance score. The question answering unit also builds a system that sets search priorities according to the importance of data when storing detailed histories. For example, important data is displayed at the top of search results. This allows data to be prioritized according to its importance, enabling important data to be searched for quickly, thereby enabling necessary information to be obtained quickly.

[0079] The question answering unit can provide more accurate answers by referring to past similar questions and their answers when answering a question. For example, the question answering unit builds a system that automatically searches for and references past similar questions and their answers when answering a question. For example, it provides the optimal answer based on the past question history. The question answering unit also develops a search algorithm for similar questions and builds a system that provides highly accurate answers based on past questions and answers. For example, it searches for similar questions based on keywords in the question content. The question answering unit also develops a system that refers to past similar questions and their answers when answering a question, improving the accuracy of the answers. For example, it generates the optimal answer based on past answers. In this way, it is possible to provide more accurate answers by referring to past similar questions and their answers.

[0080] The question answering unit analyzes the question and answer history, learns the user's question patterns, and can improve the accuracy of answers from the next time onwards. The question and answering unit, for example, analyzes the question and answer history and builds a system that learns the user's question patterns. For example, it identifies frequently asked questions and improves the accuracy of answers. The question and answering unit also learns the user's question patterns and develops an algorithm that improves the accuracy of answers from the next time onwards. For example, it provides optimal answers based on the past question history. The question and answering unit also analyzes the question and answer history, learns the user's question patterns, and builds a system that improves the accuracy of answers. For example, it analyzes the user's question trends and generates predicted answers. In this way, by analyzing the question and answer history and learning the user's question patterns, it is possible to improve the accuracy of answers from the next time onwards.

[0081] The question answering unit can support voice input during question answering, allowing the user to ask questions by voice. The question answering unit, for example, builds a system that supports voice input during question answering. For example, a user inputs a question by voice, and a generation AI analyzes the voice and provides an answer. The question answering unit also uses voice recognition technology to develop an interface that allows the user to ask questions by voice. For example, the voice input is converted into text, and a generation AI generates an answer. The question answering unit also supports voice input during question answering, building a system that allows the user to ask questions by voice. For example, the voice command is analyzed and the optimal answer is provided. In this way, by supporting voice input, the user can ask questions by voice, improving convenience.

[0082] The question answering unit can generate visual data when answering questions and provide information visually. The question answering unit, for example, builds a system that generates visual data when answering questions. For example, it displays the progress of business negotiations in graphs or charts. The question answering unit also generates visual data and develops an interface that provides information visually. For example, it displays sales data or project status in charts. The question answering unit also builds a system that generates visual data when answering questions and provides information visually. For example, it shows data fluctuations in graphs. In this way, generating visual data and providing information visually makes it easier to understand the information.

[0083] The question answering unit uses the emotion estimation function to provide answers that correspond to the user's emotions, thereby improving user satisfaction. The question answering unit, for example, uses the emotion estimation function to build a system that provides answers that correspond to the user's emotions. For example, if the user is feeling dissatisfied, a polite answer is provided. The question answering unit also analyzes the user's emotions in real time and develops a system that provides answers that correspond to the emotions. For example, if the user has strong positive emotions, a positive answer is provided. The question answering unit also builds a system that provides answers that correspond to the user's emotions based on the emotion estimation data, thereby improving user satisfaction. For example, the content of the answer is adjusted according to changes in the user's emotions. In this way, user satisfaction can be improved by using the emotion estimation function to provide answers that correspond to the user's emotions.

[0084] The question answering unit can analyze interactions on the chat interface, predict the user's intentions, and make proactive suggestions. The question answering unit, for example, analyzes interactions on the chat interface and builds a system that predicts the user's intentions. For example, it automatically generates the next suggestion based on the content of the user's question. The question answering unit also develops an algorithm that predicts the user's intentions and makes proactive suggestions. For example, it provides the user with information they are looking for in advance. The question answering unit also analyzes interactions on the chat interface and builds a system that predicts the user's intentions and makes proactive suggestions. For example, it generates suggestions based on the user's past question history. This makes it possible to analyze interactions on the chat interface, predict the user's intentions, and make proactive suggestions, thereby improving user convenience.

[0085] The question and answering unit can record interactions on the chat interface so that they can be referenced later. For example, the question and answering unit builds a system that automatically records interactions on the chat interface so that they can be referenced later. For example, it stores the chat log in a database. The question and answering unit also records chat interactions and develops an interface that allows users to reference them later. For example, it provides a function that allows users to search past chat history. The question and answering unit also builds a system that records interactions on the chat interface so that they can be referenced later. For example, it tags and saves important interactions. This allows interactions on the chat interface to be recorded so that they can be referenced later, making it easy to check past interactions.

[0086] The question answering unit can analyze interactions on the chat interface and provide answers customized to the user's needs. The question answering unit, for example, analyzes interactions on the chat interface and builds a system that provides answers customized to the user's needs. For example, it generates an optimal answer based on the content of the user's question. The question answering unit also analyzes user needs in real time and develops an algorithm that provides customized answers. For example, it adjusts answers based on the user's past question history. The question answering unit also analyzes interactions on the chat interface and builds a system that provides answers customized to the user's needs. For example, it generates answers based on the user's profile information. In this way, by analyzing interactions on the chat interface and providing answers customized to the user's needs, it is possible to improve user satisfaction.

[0087] The question and answering unit can make the chat interface multilingual so that it can also accommodate international users. The question and answering unit, for example, builds a system that makes the chat interface multilingual. For example, it supports communication in multiple languages ​​such as English, French, and Chinese. The question and answering unit also develops a multilingual chat interface so that it can also accommodate international users. For example, it introduces a real-time translation function. The question and answering unit also makes the chat interface multilingual so that it can also accommodate international users. For example, it prepares templates corresponding to each language. In this way, the chat interface can be made multilingual so that it can also accommodate international users.

[0088] The question and answering unit can add a function to the chat interface that allows images and videos to be sent, making it possible to share visual information as well. For example, the question and answering unit builds a system that adds a function to the chat interface that allows images and videos to be sent. For example, product photos and demo videos can be shared. The question and answering unit can also develop a chat interface that allows images and videos to be sent, making it possible to share visual information as well. For example, sending presentation materials. The question and answering unit can also add a function to the chat interface that allows images and videos to be sent, making it possible to share visual information as well. For example, providing visual content that meets customer requests. In this way, by adding a function to the chat interface that allows images and videos to be sent, it becomes possible to share visual information as well.

[0089] The question answering unit can use the emotion estimation function to analyze the user's emotions during interactions on the chat interface and respond according to the emotions. The question answering unit, for example, uses the emotion estimation function to build a system that analyzes the user's emotions during interactions on the chat interface. For example, the response is adjusted based on the user's emotion score. The question answering unit also develops a system that analyzes the user's emotions in real time and responds according to the emotions. For example, if the user is dissatisfied, the system responds politely. The question answering unit also builds a system that responds according to the user's emotions during interactions on the chat interface based on the emotion estimation data. For example, the response content is adjusted according to changes in the user's emotions. In this way, by using the emotion estimation function to analyze the user's emotions during interactions on the chat interface and responding according to the emotions, user satisfaction can be improved.

[0090] The question and answering unit can refer to data on similar past cases and provide reference information when a supervisor is understanding a case. For example, the question and answering unit builds a system that automatically refers to data on similar past cases when a supervisor is understanding a case. For example, reference information is provided based on past success stories and failure stories. The question and answering unit also develops an algorithm that refers to data on similar cases and provides reference information for the supervisor when understanding a case. For example, optimal information is provided based on past case history. The question and answering unit also builds a system that refers to data on similar past cases and provides reference information when a supervisor is understanding a case. For example, the progress and results of similar cases are displayed. This allows the supervisor to refer to data on similar past cases and provide reference information when understanding a case, thereby supporting the supervisor's decision-making.

[0091] The question and answering unit can automatically extract important points when a supervisor conducts a review, thereby improving the efficiency of the review. The question and answering unit, for example, builds a system that automatically extracts important points when a supervisor conducts a review. For example, it extracts the main points of a business negotiation and the next action items. The question and answering unit also develops an algorithm that automatically extracts important points and improves the efficiency of a supervisor's review. For example, it extracts important remarks and decisions made in a business negotiation. The question and answering unit also builds a system that automatically extracts important points when a supervisor conducts a review, thereby improving the efficiency of the review. For example, it automatically generates a summary of a business negotiation. This allows the efficiency of a supervisor's review to be improved by automatically extracting important points when the supervisor conducts a review.

[0092] The question and answering unit can evaluate the reliability of data and preferentially display highly reliable data when a supervisor is understanding a case. The question and answering unit, for example, builds a system that evaluates the reliability of data when a supervisor is understanding a case. For example, the reliability is evaluated based on the source of the data and the consistency of the content, and highly reliable data is preferentially displayed. The question and answering unit also develops a system that evaluates the reliability of data in real time and filters out low-reliability data. For example, the system selects data based on a reliability score and displays it to the supervisor. The question and answering unit also builds a system that evaluates the reliability of data when a supervisor is understanding a case and preferentially displays highly reliable data. For example, the system checks consistency with past data and displays highly reliable data. This allows the supervisor to evaluate the reliability of data and preferentially display highly reliable data when understanding a case, thereby supporting decision-making based on accurate information.

[0093] The question and answering unit can generate visual data and provide information visually when a supervisor is trying to understand a project. The question and answering unit, for example, builds a system that generates visual data when a supervisor is trying to understand a project. For example, it displays the progress of a business negotiation in graphs and charts. The question and answering unit also develops an interface that generates visual data and provides information visually. For example, it displays sales data and project status in charts. The question and answering unit also builds a system that generates visual data and provides information visually when a supervisor is trying to understand a project. For example, it shows data fluctuations in a graph. In this way, by generating visual data and providing information visually, the supervisor can understand the project more quickly and accurately.

[0094] The question and answering unit can automatically collect feedback from other departments when a supervisor conducts a review and make a comprehensive evaluation. For example, the question and answering unit builds a system that automatically collects feedback from other departments when a supervisor conducts a review. For example, it integrates feedback from the marketing department and the technical department. The question and answering unit also develops an algorithm that automatically collects feedback from other departments and makes a comprehensive evaluation. For example, it calculates an overall evaluation based on the evaluations of each department. The question and answering unit also builds a system that automatically collects feedback from other departments when a supervisor conducts a review and makes a comprehensive evaluation. For example, it collects feedback in real time and reflects it in the evaluation. In this way, by automatically collecting feedback from other departments and making a comprehensive evaluation, the accuracy and efficiency of the supervisor's review can be improved.

[0095] The question answering unit uses the emotion estimation function to analyze the user's emotions when the supervisor is reviewing a case, and can respond according to the emotions. The question answering unit, for example, uses the emotion estimation function to build a system that analyzes the user's emotions when the supervisor is reviewing a case. For example, the response is adjusted based on the user's emotion score. The question answering unit also develops a system that analyzes the user's emotions in real time and responds according to the emotions. For example, if the user is dissatisfied, the question answering unit also builds a system that responds according to the user's emotions when the supervisor is reviewing a case, based on the emotion estimation data. For example, the response content is adjusted according to changes in the user's emotions. In this way, the emotion estimation function can be used to analyze the user's emotions when the supervisor is reviewing a case, and the response is adjusted according to the emotions, thereby improving user satisfaction.

[0096] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0097] The analysis unit can extract information about competitors and market trends from the minutes of business meetings and reflect them in the summary. For example, it can analyze the minutes of business meetings and include information about competitors' products and services in the summary. The analysis unit can also extract market trends from the content of business meetings and reflect them in the summary. For example, it can include the latest industry trends and market changes in the summary. The analysis unit can also extract competitors' strategies and market trends from conversations with customers and reflect them in the summary. For example, it can include the strengths and weaknesses of competitors in the summary. In this way, by extracting information about competitors and market trends from the minutes of business meetings and reflecting them in the summary, competitiveness can be improved.

[0098] The analysis unit can predict the next action item based on the customer's past behavioral patterns and speech history, and include it in the summary. For example, it can analyze the customer's past emails and business negotiation history to predict the next action item to be taken. For example, it can include the next step in the summary based on comments made in past business negotiations. The analysis unit can also analyze the customer's behavioral patterns to predict the next expected action. For example, it can include the next suggestion in the summary based on the interests and concerns expressed by the customer in the past. The analysis unit can also predict the next action to be taken based on the customer's speech history, and reflect this in the summary. For example, it can include the next step in the summary based on information or services the customer has requested in the past. In this way, by predicting the next action item based on the customer's past behavioral patterns and speech history, and including it in the summary, the next step can be effectively planned.

[0099] The analysis unit can analyze the tone and emotions of a business meeting and generate a summary that emphasizes positive elements. For example, it analyzes the minutes of a business meeting and analyzes the tone and emotions of the speaker. For example, it emphasizes positive comments and forward-looking opinions and reflects them in the summary. The analysis unit also analyzes the content of emails with customers and extracts parts that express positive emotions. For example, it includes parts that show high customer satisfaction in the summary. The analysis unit also analyzes the contents of a schedule and emphasizes positive events and successful business meetings. For example, it reflects the key points of successful business meetings in the summary. In this way, by analyzing the tone and emotions of a business meeting and generating a summary that emphasizes positive elements, the content of the business meeting can be communicated more effectively.

[0100] The analysis unit can analyze video data from a video conference with a customer and reflect non-verbal communication in the summary. For example, the video data from the video conference can be analyzed to analyze the gestures and facial expressions of the speaker. For example, the customer's satisfaction and level of interest can be reflected in the summary. The analysis unit also analyzes the video data to extract non-verbal communication. For example, positive gestures and facial expressions of the customer can be included in the summary. The analysis unit also analyzes the video data from the video conference and generates a summary by analyzing the speaker's emotions. For example, positive facial expressions and gestures can be emphasized and included in the summary. In this way, by analyzing the video data from a video conference with a customer and reflecting non-verbal communication in the summary, the customer's intentions can be understood more accurately.

[0101] The analysis unit can use the emotion estimation function to analyze customer emotions and generate summaries based on those emotions. For example, it analyzes the content of emails or business negotiations with a customer and uses the emotion estimation function to analyze the customer's emotions. For example, it reflects the customer's satisfaction or dissatisfaction in the summary. The analysis unit also uses the emotion estimation function to generate summaries based on the customer's emotions. For example, it emphasizes parts with strong positive emotions and includes them in the summary. The analysis unit also analyzes customer emotions in real time and generates summaries based on the results. For example, it generates summaries that reflect changes in the customer's emotions. In this way, by using the emotion estimation function to analyze customer emotions and generating summaries based on emotions, it becomes possible to respond in a way that takes customer emotions into consideration.

[0102] When inputting summary data, the input unit can evaluate the reliability of the data and prioritize the input of only highly reliable data. For example, an algorithm can be developed to evaluate the reliability of summary data, and only highly reliable data can be input into Compass. For example, reliability can be evaluated based on the source of the data and the consistency of its content. The input unit can also build a system to evaluate the reliability of summary data in real time and filter out unreliable data. For example, it can select data based on a reliability score. The input unit can also check the consistency with past data to evaluate the reliability of the data. For example, it can input only data that matches past sales negotiation history into Compass. This improves data accuracy by evaluating the reliability of the data and inputting only highly reliable data.

[0103] The input unit can check the consistency of summary data with past data when it is input, and issue an alert if there is a discrepancy. For example, a system is built that checks the consistency with past data when summary data is input. For example, an alert is issued if a data discrepancy is detected. The input unit also develops a system that checks the consistency with past data in real time and automatically corrects any discrepancies. For example, an algorithm is introduced to maintain data consistency. The input unit also builds a database to check the consistency with past data when summary data is input. For example, consistency is evaluated based on past sales negotiation history and customer information. This makes it possible to maintain data consistency by checking consistency with past data and issuing an alert if there is a discrepancy.

[0104] The input unit can automatically record the history of changes to the data after the summary data is input, making it possible to track them. For example, a system is constructed that automatically records the history of changes to the data after the summary data is input. For example, the date and time of the data change and the details of the change are recorded. The input unit also constructs a database that makes the history of changes to the data traceable. For example, a function is added to display the change history in chronological order. The input unit also develops a system that automatically records the history of changes to the summary data and allows the user to check the changes. For example, the change history is displayed in a graph or chart. In this way, the history of changes to the data can be automatically recorded and made traceable, making it possible to manage the history of changes to the data.

[0105] The input section can link with other CRM systems when entering summary data and centrally manage the data. For example, a system is built that links with other CRM systems when entering summary data. For example, it links with Salesforce or HubSpot to centrally manage data. The input section also develops a system that links data with other CRM systems in real time and maintains data consistency. For example, it automatically synchronizes data. The input section also builds a system that automatically imports data from other CRM systems when entering summary data. For example, it centrally manages customer information and sales negotiation history. This allows it to link with other CRM systems and centrally manage data, improving data consistency and efficiency.

[0106] The input unit provides an interface that requests confirmation from the user before inputting summary data, thereby preventing erroneous input. For example, a system is constructed that provides an interface that requests confirmation from the user before inputting summary data. For example, a preview of the input content is displayed so that the user can confirm it. The input unit also develops an interface that allows the user to confirm the summary data and prevent erroneous input. For example, a confirmation button is provided so that the user can approve the input content. The input unit also constructs a system that displays an alert that requests confirmation from the user before inputting summary data. For example, a message is displayed to confirm that the input content is correct. In this way, erroneous input can be prevented by requesting confirmation from the user before inputting summary data.

[0107] The processing flow of the second embodiment will be briefly explained below.

[0108] Step 1: The analysis unit analyzes schedules, emails with customers, and minutes of business meetings. For example, the analysis unit analyzes the contents of schedules and extracts important events. It can also analyze emails with customers and extract important exchanges. It can also analyze minutes of business meetings and extract important points. Step 2: The summary generator summarizes the information analyzed by the analyzer. For example, it can extract important points from minutes of a business meeting and generate a summary. It can also summarize the contents of emails with customers or schedules. Step 3: The input unit automatically inputs the summaries generated by the summary generation unit into Compass. For example, a summary of a business meeting, a summary of an email with a customer, or a summary of a schedule can be input into Compass. Step 4: The question answering unit answers questions based on the summary generated by the summary generating unit. For example, a question such as "Please tell me about the latest business negotiations for this project" can be answered based on the summary. Questions such as "When is the next business negotiation scheduled?" and "Please tell me about the progress of this project" can also be answered based on the summary.

[0109] 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.

[0110] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0111] 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.

[0112] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0113] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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).

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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 AI 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.

[0126] 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.

[0127] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0128] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the 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 specific processing unit 290 using these models.

[0138] 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.

[0139] 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.

[0140] 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 AI 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.

[0141] 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.

[0142] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0143] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] In the robot 414, 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 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 processing similar to that of the specific processing unit 290 using these models.

[0154] 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.

[0155] 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.

[0156] 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 AI 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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."

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0176] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. An analysis department that analyzes schedules, emails with customers, and minutes of business meetings, a summary generation unit that summarizes the information analyzed by the analysis unit; an input unit that automatically inputs the summary generated by the summary generation unit into Compass; a question answering unit that answers questions based on the summary generated by the summary generating unit. A system characterized by:

2. The analysis unit Analyze the tone and sentiment of the meeting and generate a summary highlighting the positive aspects 2. The system of claim 1.

3. The analysis unit Based on the customer's past behavioral patterns and comment history, predict the next action item and include it in the summary.

2. The system of claim 1.

4. The analysis unit Extract information about competitors and market trends from the minutes of the business negotiations and reflect them in the summary.

2. The system of claim 1.

5. The analysis unit Analyzing the voice data of the business negotiation and generating the summary using voice recognition technology 2. The system of claim 1.

6. The analysis unit Analyze video data from the video conference with the customer and reflect non-verbal communication in the summary.

2. The system of claim 1.

7. The analysis unit Analyzing the customer's sentiment and generating the sentiment-based summary 2. The system of claim 1.

Images