System

Abstract

An object of the system according to the embodiment is to analyze statements in a company and provide important knowledge in real time.SOLUTION: A system includes a collection unit, an analysis unit, a provision unit, and a learning unit. The collection unit collects comments in a company. The analysis unit analyzes the speech collected by the collection unit and extracts important knowledge. The providing unit provides the knowledge extracted by the analysis unit in real time. The learning unit continuously performs learning.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 has room for improvement, as it has issues with work delays and information sharing when people with specific skills are absent.

[0005] The system according to the embodiment aims to analyze comments made within a company and provide important knowledge in real time. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a provision unit, and a learning unit. The collection unit collects comments within the company. The analysis unit analyzes the comments collected by the collection unit and extracts important knowledge. The provision unit provides the knowledge extracted by the analysis unit in real time. The learning unit continuously learns. [Effects of the Invention]

[0007] The system according to the embodiment can analyze internal company comments and provide important knowledge in real time. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A knowledge provision system according to an embodiment of the present invention learns from company internal comments and provides them as usable knowledge in real time. The knowledge provision system collects company internal comments, analyzes them using AI, extracts important knowledge, and provides it in real time. The knowledge provision system also continuously learns and adds new comments and information. For example, the knowledge provision system uses chat logs to collect company internal comments. This allows necessary knowledge to be extracted from past comments even when a person with a specific skill is not present. Next, the knowledge provision system uses AI to analyze the collected chat logs and extract important knowledge. The AI ​​understands the content of the comments and organizes related information. The knowledge provision system then provides the extracted knowledge in a usable form in real time. The AI ​​continuously learns and adds new comments and information. This allows the system to always maintain the latest information and provide it to users. By learning from company internal comments and providing it as usable knowledge in real time, the knowledge provision system can solve problems such as work delays and personalization issues when a person with a specific skill is not present, as well as problems with information sharing between system administrators and operators.

[0029] A knowledge provision system according to an embodiment includes a collection unit, an analysis unit, a provision unit, and a learning unit. The collection unit collects internal company utterances. Internal company utterances include, but are not limited to, utterances made in meetings, chat sessions, and emails. The collection unit collects, for example, chat logs. The chat logs include text formats, image and file attachments, and the like. The analysis unit analyzes the collected utterances and extracts important knowledge. Important knowledge includes, for example, business-related information, technical knowledge, and business strategies. The analysis unit analyzes the content of the utterances using, for example, natural language processing technology and extracts important knowledge. The provision unit provides the extracted knowledge in real time. A specific time range for real time is, for example, within a few seconds or within a few minutes. The provision unit immediately provides the extracted knowledge to a user, for example. The learning unit continuously learns new utterances and information, so that the system always maintains the latest information. Specific methods and frequencies of continuous learning include, for example, periodic data updates and real-time learning. The learning unit automatically learns new comments and information and reflects them in the system, thereby enabling the knowledge provision system according to the embodiment to efficiently collect, analyze, provide, and learn from comments within a company.

[0030] The collection unit can collect chat logs. Chat logs include, for example, text format, image and file attachments, etc., but are not limited to these examples. The collection unit can automatically collect logs, for example, from an in-company chat system. The collection unit can also collect chat logs periodically. For example, the collection unit collects chat logs at a certain time every day. The collection unit can also collect chat logs when a specific event occurs. For example, the collection unit collects chat logs after an important meeting has ended. In this way, by collecting chat logs, comments within the company can be collected efficiently.

[0031] The analysis unit can analyze the collected chat logs and extract important knowledge. Important knowledge includes, but is not limited to, business-related information, technical knowledge, and business strategies, for example. The analysis unit can analyze the contents of the chat logs using, for example, natural language processing technology and extract important knowledge. The analysis unit can also extract important knowledge from the chat logs using a machine learning algorithm. For example, the analysis unit can extract specific keywords from the chat logs and organize information related to them. The analysis unit can also understand the context of the chat logs and extract important knowledge. For example, the analysis unit can analyze comments before and after the chat log and extract important knowledge. This allows important knowledge to be extracted efficiently by analyzing the collected chat logs.

[0032] The providing unit can provide the extracted knowledge in real time. A specific time range of real time is, for example, within a few seconds or within a few minutes. The providing unit can, for example, instantly provide the extracted knowledge to the user. The providing unit can also display the extracted knowledge on a dashboard. For example, the providing unit visually displays the extracted knowledge as a graph or chart. The providing unit can also notify the extracted knowledge by email. For example, the providing unit sends important knowledge to the user by email. In this way, by providing the extracted knowledge in real time, the user can immediately utilize the knowledge.

[0033] The learning unit continuously learns new utterances or information, allowing the system to maintain the latest information. Specific methods and frequencies of continuous learning include, for example, periodic data updates and real-time learning. The learning unit, for example, automatically learns new utterances and information and reflects them in the system. The learning unit can also update the learning data based on feedback from the user. For example, the learning unit analyzes feedback provided by the user and reflects it in the learning data. The learning unit can also optimize the learning algorithm by referring to past learning data. For example, the learning unit selects the optimal learning algorithm based on past learning data. This allows the system to always provide the latest information by continuously learning new utterances and information.

[0034] The collection unit can determine the priority of collection based on the importance of the comments when collecting them. For example, the collection unit prioritizes collection of comments related to important projects. The collection unit can also prioritize collection of comments related to urgent issues. Furthermore, the collection unit can prioritize collection of comments related to corporate strategies. In this way, by determining the priority of collection based on the importance of the comments, important comments can be collected preferentially. The importance of a comment is evaluated, for example, by the frequency of keyword appearance, the position of the commenter, etc. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the importance of the comments into an AI model to determine the priority.

[0035] The collection unit can apply different collection algorithms depending on the category of the utterance during collection. For example, the collection unit can apply an algorithm that understands technical terms to technical utterances. The collection unit can also apply an algorithm that performs trend analysis to marketing-related utterances. The collection unit can also apply an algorithm that performs sentiment analysis to human resources-related utterances. This enables more accurate collection by applying different collection algorithms depending on the category of the utterance. The utterances are classified into categories such as technical utterances and business-related utterances. The collection algorithm can be implemented using, for example, a machine learning algorithm or a rule-based algorithm. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the category of the utterance into an AI model and apply an appropriate collection algorithm.

[0036] The collection unit can improve the accuracy of collection by referring to the user's past speech history when collecting data. For example, the collection unit prioritizes collection of content that the user has frequently spoken in the past. The collection unit can also predict and collect important statements from the user's past speech history. Furthermore, the collection unit can analyze the user's past speech patterns and improve the accuracy of collection. This improves the accuracy of collection by referring to the user's past speech history. The past speech history is referenced, for example, to statements from the past year, statements related to a specific project, etc. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's past speech history into an AI model to improve the accuracy of collection.

[0037] The collection unit can determine the priority of collection based on the time of submission of the comments during collection. For example, the collection unit prioritizes collection of the most recent comments. The collection unit can also prioritize collection of comments made during a specific time period. Furthermore, the collection unit can prioritize collection of important comments by referring to past comment history. In this way, by determining the priority of collection based on the time of submission of the comments, the most recent comments can be collected preferentially. The time of submission of the comments is evaluated, for example, based on the elapsed time since submission, before or after a specific event, etc. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the time of submission of the comments into an AI model to determine the priority.

[0038] The collection unit can adjust the order of collection based on the relevance of the utterances during collection. For example, the collection unit prioritizes collection of utterances related to important projects. The collection unit can also prioritize collection of utterances related to urgent issues. Furthermore, the collection unit can prioritize collection of utterances related to corporate strategies. In this way, by adjusting the order of collection based on the relevance of the utterances, important utterances can be collected preferentially. The relevance of the utterances is evaluated, for example, by keyword co-occurrence, a topic model, etc. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the relevance of the utterances into an AI model and adjust the order of collection.

[0039] The collection unit can adjust the collection method according to the user's level of expertise when collecting data. For example, the collection unit prioritizes collection of utterances from users with high levels of expertise. The collection unit can also simplify and collect utterances from users with low levels of expertise. Furthermore, the collection unit can adjust the collection algorithm according to the user's level of expertise. This allows more appropriate utterances to be collected by adjusting the collection method according to the user's level of expertise. The level of expertise is evaluated, for example, based on qualifications, past utterance content, etc. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's level of expertise into an AI model and adjust the collection method.

[0040] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the statement. For example, the analysis unit performs a detailed analysis of important statements. The analysis unit can also perform a quick analysis of statements that are highly urgent. Furthermore, the analysis unit can perform an in-depth analysis of statements related to corporate strategy. In this way, by adjusting the level of detail of the analysis based on the importance of the statement, important statements can be analyzed in detail. The importance of a statement is evaluated, for example, by the frequency of keyword appearances, the position of the speaker, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the importance of a statement into an AI model and adjust the level of detail.

[0041] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the comment. For example, the analysis unit applies an algorithm that understands technical terms to technical comments. The analysis unit can also apply an algorithm that performs trend analysis to marketing-related comments. The analysis unit can also apply an algorithm that performs sentiment analysis to human resources-related comments. This enables more accurate analysis by applying different analysis algorithms depending on the category of the comment. Comment categories are classified, for example, into technical comments, business-related comments, etc. The analysis algorithm is implemented, for example, by a machine learning algorithm, a rule-based algorithm, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the category of the comment into an AI model and apply an appropriate analysis algorithm.

[0042] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit performs a current analysis by referring to the user's past analysis results. The analysis unit can also analyze the user's past analysis patterns to improve the accuracy of the analysis. Furthermore, the analysis unit can select an optimal analysis algorithm based on the user's past analysis history. This improves the accuracy of the analysis by referring to the user's past analysis results. Past analysis results are referenced, for example, analysis results from the past year or analysis results related to a specific project. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's past analysis results into an AI model to improve the accuracy of the analysis.

[0043] During analysis, the analysis unit can determine the priority of analysis based on the time when the comment was submitted. For example, the analysis unit prioritizes analysis of the most recent comment. The analysis unit can also prioritize analysis of comments made during a specific time period. Furthermore, the analysis unit can prioritize analysis of important comments by referring to past comment history. In this way, by determining the priority of analysis based on the time when the comment was submitted, the most recent comment can be analyzed with priority. The time when the comment was submitted is evaluated, for example, based on the elapsed time since submission, before or after a specific event, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the time when the comment was submitted into an AI model to determine the priority.

[0044] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the statements. For example, the analysis unit prioritizes analysis of statements related to important projects. The analysis unit can also prioritize analysis of statements related to urgent issues. Furthermore, the analysis unit can prioritize analysis of statements related to corporate strategies. In this way, by adjusting the order of analysis based on the relevance of the statements, important statements can be analyzed preferentially. The relevance of the statements is evaluated, for example, by keyword co-occurrence, a topic model, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance of the statements into an AI model and adjust the order of analysis.

[0045] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, the analysis unit can provide analysis results that use a lot of technical terms to a user with high levels of expertise. The analysis unit can also provide analysis results in simpler language to a user with low levels of expertise. Furthermore, the analysis unit can adjust the way the analysis results are expressed according to the user's level of expertise. This allows for more appropriate analysis results to be provided by adjusting the use of technical terms in the analysis according to the user's level of expertise. The level of expertise is evaluated, for example, based on qualifications, past comments, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's level of expertise into an AI model to adjust the use of technical terms.

[0046] The providing unit can adjust the level of detail of the provided knowledge based on the importance of the knowledge when providing the knowledge. For example, the providing unit provides detailed information for important knowledge. The providing unit can also quickly provide information for knowledge that is highly urgent. Furthermore, the providing unit can provide in-depth information for knowledge related to a company's strategy. In this way, by adjusting the level of detail of the provided knowledge based on the importance of the knowledge, important knowledge can be provided in detail. The importance of knowledge is evaluated, for example, based on information related to business, technical knowledge, business strategy, etc. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the importance of knowledge into an AI model and adjust the level of detail.

[0047] The providing unit can apply different provision algorithms depending on the category of knowledge when providing the information. For example, the providing unit can apply an algorithm that understands technical terms to technical knowledge. The providing unit can also apply an algorithm that performs trend analysis to marketing knowledge. The providing unit can also apply an algorithm that performs sentiment analysis to human resources knowledge. This enables more accurate information provision by applying different provision algorithms depending on the category of knowledge. Knowledge categories are classified, for example, into technical knowledge, business-related knowledge, etc. The provision algorithm is implemented, for example, by a machine learning algorithm, a rule-based algorithm, etc. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the knowledge category into an AI model and apply an appropriate provision algorithm.

[0048] The providing unit can improve the accuracy of the provision by referring to the user's past provision results when providing information. The providing unit, for example, refers to information the user received in the past to provide the current information. The providing unit can also analyze the user's past provision results to improve the accuracy of the provision. Furthermore, the providing unit can select an optimal provision algorithm based on the user's past provision history. This improves the accuracy of the provision by referring to the user's past provision results. The past provision results are referenced, for example, from the provision results for the past year or from the provision results related to a specific project. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's past provision results into an AI model to improve the accuracy of the provision.

[0049] The providing unit can determine the priority of knowledge provision based on the time of knowledge submission at the time of knowledge provision. For example, the providing unit can provide the most recent knowledge with priority. The providing unit can also provide knowledge submitted during a specific time period with priority. Furthermore, the providing unit can refer to past knowledge history to provide important knowledge with priority. In this way, by determining the priority of knowledge provision based on the time of knowledge submission, the most recent knowledge can be provided with priority. The time of knowledge submission is evaluated, for example, based on the elapsed time since submission, before or after a specific event, etc. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the time of knowledge submission into an AI model to determine the priority.

[0050] The providing unit can adjust the order of knowledge provision based on the relevance of the knowledge when providing the knowledge. For example, the providing unit can prioritize providing knowledge related to important projects. The providing unit can also prioritize providing knowledge related to urgent issues. Furthermore, the providing unit can prioritize providing knowledge related to corporate strategies. In this way, important knowledge can be provided preferentially by adjusting the order of knowledge provision based on the relevance of the knowledge. The relevance of knowledge is evaluated, for example, by keyword co-occurrence, a topic model, or the like. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the relevance of knowledge into an AI model and adjust the order of knowledge provision.

[0051] The providing unit can adjust the use of technical terminology provided in accordance with the user's level of expertise when providing the information. For example, the providing unit can provide information that uses a lot of technical terminology to a user with high levels of expertise. The providing unit can also provide information in simple language to a user with low levels of expertise. Furthermore, the providing unit can adjust the way information is expressed in accordance with the user's level of expertise. This enables more appropriate information to be provided by adjusting the use of technical terminology provided in accordance with the user's level of expertise. The level of expertise is evaluated, for example, based on qualification information, past comments, etc. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's level of expertise into an AI model to adjust the use of technical terminology.

[0052] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data to improve the accuracy of the learning algorithm. Furthermore, the learning unit can also adjust the learning algorithm by referring to past learning data. In this way, the accuracy of the learning algorithm is improved by referring to past learning data. Past learning data is referenced, for example, learning data from the past year, learning data related to a specific project, etc. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input past learning data into an AI model to optimize the learning algorithm.

[0053] The learning unit can update the learning data by reflecting user feedback during learning. The learning unit updates the learning data based on, for example, user feedback. The learning unit can also analyze user feedback and improve the accuracy of the learning data. Furthermore, the learning unit can adjust the learning data by referring to user feedback. This improves the accuracy of the learning data by reflecting user feedback. User feedback is collected, for example, from survey results, usage logs, etc. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input user feedback into an AI model and update the learning data.

[0054] During learning, the learning unit can weight the learning data based on the time of submission of the utterance. For example, the learning unit weights the learning data by prioritizing the most recent utterance. The learning unit can also weight the learning data by prioritizing utterances made during a specific time period. Furthermore, the learning unit can weight the learning data by prioritizing important utterances with reference to past utterance history. In this way, weighting the learning data based on the time of submission of the utterance enables learning that emphasizes the most recent information. The time of submission of the utterance is evaluated, for example, based on the elapsed time since submission, before or after a specific event, etc. The weighting of the learning data is performed, for example, based on the novelty and relevance of the data. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the time of submission of the utterance into an AI model and weight the learning data.

[0055] During learning, the learning unit can integrate information from different data sources to enrich the learning data. For example, the learning unit can enrich the learning data by collecting information not only from chat logs but also from emails and documents. The learning unit can also enrich the learning data by collecting information from an internal database. Furthermore, the learning unit can enrich the learning data by collecting information from external information sources. This improves the quality of the learning data by integrating information from different data sources. Different data sources are integrated, for example, via an internal database, an external API, etc. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can enrich the learning data by inputting information from different data sources into an AI model.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] The knowledge provision system may further include a behavior analysis unit that analyzes the user's behavior history. The behavior analysis unit may, for example, analyze what information the user frequently references and what time of day the user is most active. This allows knowledge to be provided at the optimal timing based on the user's behavioral patterns. For example, if the user tends to reference a lot of information in the morning, important knowledge may be provided preferentially in the morning. Also, if the user frequently references information about a specific project, the latest knowledge related to that project may be provided preferentially. Furthermore, the behavior analysis unit may record what knowledge the user has referenced in the past and provide similar knowledge, thereby improving user convenience.

[0058] The knowledge provision system may further include an expertise adjustment unit that estimates the user's expertise level and adjusts the content of the knowledge to be provided based on the estimated expertise level. The expertise adjustment unit, for example, provides detailed, specialized information to users with high expertise. It may also provide concise, easy-to-understand information to users with low expertise. Furthermore, the expertise adjustment unit estimates the user's expertise level based on the user's past statements and behavior history, and provides appropriate information to deepen the user's understanding. This makes it possible to provide optimal knowledge according to the user's expertise level.

[0059] The knowledge provision system may further include a feedback collection unit that collects user feedback and improves the knowledge provision method based on the collected feedback. The feedback collection unit, for example, records how the user evaluated the provided knowledge. It may also analyze the extent to which the user utilized the provided knowledge. Furthermore, the feedback collection unit can improve the knowledge provision method based on the user feedback and provide more appropriate information. This makes it possible to provide optimal knowledge according to the user's needs.

[0060] The knowledge provision system may further include a behavior optimization unit that analyzes the user's behavior history and optimizes the knowledge provision method based on the analysis results. The behavior optimization unit, for example, analyzes what information the user frequently references and what time of day the user is most active. This allows knowledge to be provided at the optimal timing based on the user's behavioral patterns. For example, if the user tends to reference a lot of information in the morning, important knowledge can be provided preferentially in the morning. Also, if the user frequently references information about a specific project, the latest knowledge related to that project can be provided preferentially. Furthermore, the behavior optimization unit records what knowledge the user has referenced in the past and provides similar knowledge, thereby improving user convenience.

[0061] The knowledge provision system may further include a specialized knowledge provision unit that estimates the user's level of specialized knowledge and adjusts the method of providing knowledge based on the estimated level of specialized knowledge. The specialized knowledge provision unit may, for example, provide detailed, specialized information to users with high levels of specialized knowledge. It may also provide concise, easy-to-understand information to users with low levels of specialized knowledge. Furthermore, the specialized knowledge provision unit may estimate the user's level of specialized knowledge based on the user's past statements and behavioral history, and provide appropriate information to deepen the user's understanding. This makes it possible to provide optimal knowledge according to the user's level of specialized knowledge.

[0062] The knowledge provision system may further include a behavior frequency optimization unit that analyzes the user's behavior history and optimizes the frequency of knowledge provision based on the analysis results. The behavior frequency optimization unit, for example, analyzes what information the user frequently references and what time of day the user is most active. This allows knowledge to be provided at an optimal frequency based on the user's behavior patterns. For example, if the user tends to reference a lot of information in the morning, important knowledge can be provided preferentially in the morning. Also, if the user frequently references information about a specific project, the latest knowledge related to that project can be provided preferentially. Furthermore, the behavior frequency optimization unit records what knowledge the user has referenced in the past and provides similar knowledge, thereby improving user convenience.

[0063] The processing flow of the first embodiment will be briefly explained below.

[0064] Step 1: The collection unit collects internal company communications. Internal company communications include conference communications, chat communications, email content, etc. The collection unit collects, for example, chat logs, including text format, image and file attachments, etc. Step 2: The analysis unit analyzes the collected comments and extracts important knowledge. Important knowledge includes business-related information, technical knowledge, business strategies, etc. The analysis unit analyzes the content of the comments using natural language processing technology, for example, and extracts important knowledge. Step 3: The providing unit provides the knowledge extracted by the analysis unit in real time. The specific time range of real time is within a few seconds, a few minutes, etc., and the extracted knowledge is immediately provided to the user. Step 4: The learning unit continuously learns new comments and information, and the system always maintains the latest information. The specific method and frequency of continuous learning can be periodic data updates or real-time learning, and new comments and information are automatically learned and reflected in the system.

[0065] (Example 2) A knowledge provision system according to an embodiment of the present invention learns from company internal comments and provides them as usable knowledge in real time. The knowledge provision system collects company internal comments, analyzes them using AI, extracts important knowledge, and provides it in real time. The knowledge provision system also continuously learns and adds new comments and information. For example, the knowledge provision system uses chat logs to collect company internal comments. This allows necessary knowledge to be extracted from past comments even when a person with a specific skill is not present. Next, the knowledge provision system uses AI to analyze the collected chat logs and extract important knowledge. The AI ​​understands the content of the comments and organizes related information. The knowledge provision system then provides the extracted knowledge in a usable form in real time. The AI ​​continuously learns and adds new comments and information. This allows the system to always maintain the latest information and provide it to users. By learning from company internal comments and providing it as usable knowledge in real time, the knowledge provision system can solve problems such as work delays and personalization issues when a person with a specific skill is not present, as well as problems with information sharing between system administrators and operators.

[0066] A knowledge provision system according to an embodiment includes a collection unit, an analysis unit, a provision unit, and a learning unit. The collection unit collects internal company utterances. Internal company utterances include, but are not limited to, utterances made in meetings, chat sessions, and emails. The collection unit collects, for example, chat logs. The chat logs include text formats, image and file attachments, and the like. The analysis unit analyzes the collected utterances and extracts important knowledge. Important knowledge includes, for example, business-related information, technical knowledge, and business strategies. The analysis unit analyzes the content of the utterances using, for example, natural language processing technology and extracts important knowledge. The provision unit provides the extracted knowledge in real time. A specific time range for real time is, for example, within a few seconds or within a few minutes. The provision unit immediately provides the extracted knowledge to a user, for example. The learning unit continuously learns new utterances and information, so that the system always maintains the latest information. Specific methods and frequencies of continuous learning include, for example, periodic data updates and real-time learning. The learning unit automatically learns new comments and information and reflects them in the system, thereby enabling the knowledge provision system according to the embodiment to efficiently collect, analyze, provide, and learn from comments within a company.

[0067] The collection unit can collect chat logs. Chat logs include, for example, text format, image and file attachments, etc., but are not limited to these examples. The collection unit can automatically collect logs, for example, from an in-company chat system. The collection unit can also collect chat logs periodically. For example, the collection unit collects chat logs at a certain time every day. The collection unit can also collect chat logs when a specific event occurs. For example, the collection unit collects chat logs after an important meeting has ended. In this way, by collecting chat logs, comments within the company can be collected efficiently.

[0068] The analysis unit can analyze the collected chat logs and extract important knowledge. Important knowledge includes, but is not limited to, business-related information, technical knowledge, and business strategies, for example. The analysis unit can analyze the contents of the chat logs using, for example, natural language processing technology and extract important knowledge. The analysis unit can also extract important knowledge from the chat logs using a machine learning algorithm. For example, the analysis unit can extract specific keywords from the chat logs and organize information related to them. The analysis unit can also understand the context of the chat logs and extract important knowledge. For example, the analysis unit can analyze comments before and after the chat log and extract important knowledge. This allows important knowledge to be extracted efficiently by analyzing the collected chat logs.

[0069] The providing unit can provide the extracted knowledge in real time. A specific time range of real time is, for example, within a few seconds or within a few minutes. The providing unit can, for example, instantly provide the extracted knowledge to the user. The providing unit can also display the extracted knowledge on a dashboard. For example, the providing unit visually displays the extracted knowledge as a graph or chart. The providing unit can also notify the extracted knowledge by email. For example, the providing unit sends important knowledge to the user by email. In this way, by providing the extracted knowledge in real time, the user can immediately utilize the knowledge.

[0070] The learning unit continuously learns new utterances or information, allowing the system to maintain the latest information. Specific methods and frequencies of continuous learning include, for example, periodic data updates and real-time learning. The learning unit, for example, automatically learns new utterances and information and reflects them in the system. The learning unit can also update the learning data based on feedback from the user. For example, the learning unit analyzes feedback provided by the user and reflects it in the learning data. The learning unit can also optimize the learning algorithm by referring to past learning data. For example, the learning unit selects the optimal learning algorithm based on past learning data. This allows the system to always provide the latest information by continuously learning new utterances and information.

[0071] The collection unit can estimate the user's emotions and adjust the timing of utterance collection based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit delays the collection timing to collect utterances when the user is relaxed. Furthermore, if the user is relaxed, the collection unit can immediately collect utterances and analyze them in real time. Furthermore, if the user is in a hurry, the collection unit can prioritize collecting important utterances and analyze them quickly. This allows utterances to be collected at a more appropriate time by adjusting the utterance collection timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the collection unit may be performed using, for example, an AI. For example, the collection unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0072] The collection unit can determine the priority of collection based on the importance of the comments when collecting them. For example, the collection unit prioritizes collection of comments related to important projects. The collection unit can also prioritize collection of comments related to urgent issues. Furthermore, the collection unit can prioritize collection of comments related to corporate strategies. In this way, by determining the priority of collection based on the importance of the comments, important comments can be collected preferentially. The importance of a comment is evaluated, for example, by the frequency of keyword appearance, the position of the commenter, etc. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the importance of the comments into an AI model to determine the priority.

[0073] The collection unit can apply different collection algorithms depending on the category of the utterance during collection. For example, the collection unit can apply an algorithm that understands technical terms to technical utterances. The collection unit can also apply an algorithm that performs trend analysis to marketing-related utterances. The collection unit can also apply an algorithm that performs sentiment analysis to human resources-related utterances. This enables more accurate collection by applying different collection algorithms depending on the category of the utterance. The utterances are classified into categories such as technical utterances and business-related utterances. The collection algorithm can be implemented using, for example, a machine learning algorithm or a rule-based algorithm. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the category of the utterance into an AI model and apply an appropriate collection algorithm.

[0074] The collection unit can improve the accuracy of collection by referring to the user's past speech history when collecting data. For example, the collection unit prioritizes collection of content that the user has frequently spoken in the past. The collection unit can also predict and collect important statements from the user's past speech history. Furthermore, the collection unit can analyze the user's past speech patterns and improve the accuracy of collection. This improves the accuracy of collection by referring to the user's past speech history. The past speech history is referenced, for example, to statements from the past year, statements related to a specific project, etc. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's past speech history into an AI model to improve the accuracy of collection.

[0075] The collection unit can estimate the user's emotions and determine the priority of utterances to be collected based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit can prioritize collecting utterances aimed at reducing stress. Furthermore, if the user is relaxed, the collection unit can also prioritize collecting normal utterances. Furthermore, if the user is in a hurry, the collection unit can prioritize collecting urgent utterances. By determining the priority of utterances to be collected based on the user's emotions, more appropriate utterances can be collected preferentially. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit can be performed using, for example, an AI, or without an AI. For example, the collection unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0076] The collection unit can determine the priority of collection based on the time of submission of the comments during collection. For example, the collection unit prioritizes collection of the most recent comments. The collection unit can also prioritize collection of comments made during a specific time period. Furthermore, the collection unit can prioritize collection of important comments by referring to past comment history. In this way, by determining the priority of collection based on the time of submission of the comments, the most recent comments can be collected preferentially. The time of submission of the comments is evaluated, for example, based on the elapsed time since submission, before or after a specific event, etc. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the time of submission of the comments into an AI model to determine the priority.

[0077] The collection unit can adjust the order of collection based on the relevance of the utterances during collection. For example, the collection unit prioritizes collection of utterances related to important projects. The collection unit can also prioritize collection of utterances related to urgent issues. Furthermore, the collection unit can prioritize collection of utterances related to corporate strategies. In this way, by adjusting the order of collection based on the relevance of the utterances, important utterances can be collected preferentially. The relevance of the utterances is evaluated, for example, by keyword co-occurrence, a topic model, etc. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the relevance of the utterances into an AI model and adjust the order of collection.

[0078] The collection unit can adjust the collection method according to the user's level of expertise when collecting data. For example, the collection unit prioritizes collection of utterances from users with high levels of expertise. The collection unit can also simplify and collect utterances from users with low levels of expertise. Furthermore, the collection unit can adjust the collection algorithm according to the user's level of expertise. This allows more appropriate utterances to be collected by adjusting the collection method according to the user's level of expertise. The level of expertise is evaluated, for example, based on qualifications, past utterance content, etc. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input the user's level of expertise into an AI model and adjust the collection method.

[0079] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user's emotions. For example, if the user is relaxed, the analysis unit can provide detailed analysis results. Furthermore, if the user is stressed, the analysis unit can provide concise analysis results. Furthermore, if the user is in a hurry, the analysis unit can provide analysis results that focus on the main points. By adjusting the way the analysis is presented based on the user's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, an AI, or without an AI. For example, the analysis unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0080] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the statement. For example, the analysis unit performs a detailed analysis of important statements. The analysis unit can also perform a quick analysis of statements that are highly urgent. Furthermore, the analysis unit can perform an in-depth analysis of statements related to corporate strategy. In this way, by adjusting the level of detail of the analysis based on the importance of the statement, important statements can be analyzed in detail. The importance of a statement is evaluated, for example, by the frequency of keyword appearances, the position of the speaker, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the importance of a statement into an AI model and adjust the level of detail.

[0081] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the comment. For example, the analysis unit applies an algorithm that understands technical terms to technical comments. The analysis unit can also apply an algorithm that performs trend analysis to marketing-related comments. The analysis unit can also apply an algorithm that performs sentiment analysis to human resources-related comments. This enables more accurate analysis by applying different analysis algorithms depending on the category of the comment. Comment categories are classified, for example, into technical comments, business-related comments, etc. The analysis algorithm is implemented, for example, by a machine learning algorithm, a rule-based algorithm, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the category of the comment into an AI model and apply an appropriate analysis algorithm.

[0082] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit performs a current analysis by referring to the user's past analysis results. The analysis unit can also analyze the user's past analysis patterns to improve the accuracy of the analysis. Furthermore, the analysis unit can select an optimal analysis algorithm based on the user's past analysis history. This improves the accuracy of the analysis by referring to the user's past analysis results. Past analysis results are referenced, for example, analysis results from the past year or analysis results related to a specific project. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can input the user's past analysis results into an AI model to improve the accuracy of the analysis.

[0083] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, the analysis unit can provide detailed analysis results when the user is relaxed. The analysis unit can also provide concise analysis results when the user is stressed. Furthermore, the analysis unit can provide analysis results that focus on the main points when the user is in a hurry. By adjusting the length of the analysis based on the user's emotions, more appropriate analysis results can be provided. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the analysis unit can be performed using AI, or without AI. For example, the analysis unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0084] During analysis, the analysis unit can determine the priority of analysis based on the time when the comment was submitted. For example, the analysis unit prioritizes analysis of the most recent comment. The analysis unit can also prioritize analysis of comments made during a specific time period. Furthermore, the analysis unit can prioritize analysis of important comments by referring to past comment history. In this way, by determining the priority of analysis based on the time when the comment was submitted, the most recent comment can be analyzed with priority. The time when the comment was submitted is evaluated, for example, based on the elapsed time since submission, before or after a specific event, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the time when the comment was submitted into an AI model to determine the priority.

[0085] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the statements. For example, the analysis unit prioritizes analysis of statements related to important projects. The analysis unit can also prioritize analysis of statements related to urgent issues. Furthermore, the analysis unit can prioritize analysis of statements related to corporate strategies. In this way, by adjusting the order of analysis based on the relevance of the statements, important statements can be analyzed preferentially. The relevance of the statements is evaluated, for example, by keyword co-occurrence, a topic model, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the relevance of the statements into an AI model and adjust the order of analysis.

[0086] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, the analysis unit can provide analysis results that use a lot of technical terms to a user with high levels of expertise. The analysis unit can also provide analysis results in simpler language to a user with low levels of expertise. Furthermore, the analysis unit can adjust the way the analysis results are expressed according to the user's level of expertise. This allows for more appropriate analysis results to be provided by adjusting the use of technical terms in the analysis according to the user's level of expertise. The level of expertise is evaluated, for example, based on qualifications, past comments, etc. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's level of expertise into an AI model to adjust the use of technical terms.

[0087] The providing unit can estimate the user's emotions and adjust the method of providing information based on the estimated user's emotions. For example, the providing unit can provide detailed information when the user is relaxed. The providing unit can also provide concise information when the user is stressed. Furthermore, the providing unit can provide information that focuses on the main points when the user is in a hurry. This allows for more appropriate information provision by adjusting the method of providing information based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the providing unit can be performed using AI, for example, or without AI. For example, the providing unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0088] The providing unit can adjust the level of detail of the provided knowledge based on the importance of the knowledge when providing the knowledge. For example, the providing unit provides detailed information for important knowledge. The providing unit can also quickly provide information for knowledge that is highly urgent. Furthermore, the providing unit can provide in-depth information for knowledge related to a company's strategy. In this way, by adjusting the level of detail of the provided knowledge based on the importance of the knowledge, important knowledge can be provided in detail. The importance of knowledge is evaluated, for example, based on information related to business, technical knowledge, business strategy, etc. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the importance of knowledge into an AI model and adjust the level of detail.

[0089] The providing unit can apply different provision algorithms depending on the category of knowledge when providing the information. For example, the providing unit can apply an algorithm that understands technical terms to technical knowledge. The providing unit can also apply an algorithm that performs trend analysis to marketing knowledge. The providing unit can also apply an algorithm that performs sentiment analysis to human resources knowledge. This enables more accurate information provision by applying different provision algorithms depending on the category of knowledge. Knowledge categories are classified, for example, into technical knowledge, business-related knowledge, etc. The provision algorithm is implemented, for example, by a machine learning algorithm, a rule-based algorithm, etc. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the knowledge category into an AI model and apply an appropriate provision algorithm.

[0090] The providing unit can improve the accuracy of the provision by referring to the user's past provision results when providing information. The providing unit, for example, refers to information the user received in the past to provide the current information. The providing unit can also analyze the user's past provision results to improve the accuracy of the provision. Furthermore, the providing unit can select an optimal provision algorithm based on the user's past provision history. This improves the accuracy of the provision by referring to the user's past provision results. The past provision results are referenced, for example, from the provision results for the past year or from the provision results related to a specific project. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's past provision results into an AI model to improve the accuracy of the provision.

[0091] The providing unit can estimate the user's emotions and adjust the length of the information provided based on the estimated user's emotions. For example, if the user is relaxed, the providing unit can provide more detailed information at a longer length. Furthermore, if the user is stressed, the providing unit can also provide more concise information in a shorter length. Furthermore, if the user is in a hurry, the providing unit can provide more relevant information in a shorter length. This enables more appropriate information to be provided by adjusting the length of the information provided based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate the emotion.

[0092] The providing unit can determine the priority of knowledge provision based on the time of knowledge submission at the time of knowledge provision. For example, the providing unit can provide the most recent knowledge with priority. The providing unit can also provide knowledge submitted during a specific time period with priority. Furthermore, the providing unit can refer to past knowledge history to provide important knowledge with priority. In this way, by determining the priority of knowledge provision based on the time of knowledge submission, the most recent knowledge can be provided with priority. The time of knowledge submission is evaluated, for example, based on the elapsed time since submission, before or after a specific event, etc. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the time of knowledge submission into an AI model to determine the priority.

[0093] The providing unit can adjust the order of knowledge provision based on the relevance of the knowledge when providing the knowledge. For example, the providing unit can prioritize providing knowledge related to important projects. The providing unit can also prioritize providing knowledge related to urgent issues. Furthermore, the providing unit can prioritize providing knowledge related to corporate strategies. In this way, important knowledge can be provided preferentially by adjusting the order of knowledge provision based on the relevance of the knowledge. The relevance of knowledge is evaluated, for example, by keyword co-occurrence, a topic model, or the like. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the relevance of knowledge into an AI model and adjust the order of knowledge provision.

[0094] The providing unit can adjust the use of technical terminology provided in accordance with the user's level of expertise when providing the information. For example, the providing unit can provide information that uses a lot of technical terminology to a user with high levels of expertise. The providing unit can also provide information in simple language to a user with low levels of expertise. Furthermore, the providing unit can adjust the way information is expressed in accordance with the user's level of expertise. This enables more appropriate information to be provided by adjusting the use of technical terminology provided in accordance with the user's level of expertise. The level of expertise is evaluated, for example, based on qualification information, past comments, etc. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the user's level of expertise into an AI model to adjust the use of technical terminology.

[0095] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is relaxed, the learning unit selects detailed training data. Furthermore, if the user is stressed, the learning unit can select concise training data. Furthermore, if the user is in a hurry, the learning unit can select training data that focuses on the main points. This selection of training data based on the user's emotions enables more appropriate learning. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0096] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, selects an optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data to improve the accuracy of the learning algorithm. Furthermore, the learning unit can also adjust the learning algorithm by referring to past learning data. In this way, the accuracy of the learning algorithm is improved by referring to past learning data. Past learning data is referenced, for example, learning data from the past year, learning data related to a specific project, etc. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input past learning data into an AI model to optimize the learning algorithm.

[0097] The learning unit can update the learning data by reflecting user feedback during learning. The learning unit updates the learning data based on, for example, user feedback. The learning unit can also analyze user feedback and improve the accuracy of the learning data. Furthermore, the learning unit can adjust the learning data by referring to user feedback. This improves the accuracy of the learning data by reflecting user feedback. User feedback is collected, for example, from survey results, usage logs, etc. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input user feedback into an AI model and update the learning data.

[0098] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. For example, the learning unit can increase the frequency of learning when the user is relaxed. The learning unit can also decrease the frequency of learning when the user is stressed. Furthermore, the learning unit can adjust the frequency of learning when the user is in a hurry. This allows for more appropriate learning by adjusting the frequency of learning based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the learning unit can be performed using AI, for example, or without AI. For example, the learning unit can input the user's facial expression data into the generation AI and cause the generation AI to estimate emotions.

[0099] During learning, the learning unit can weight the learning data based on the time of submission of the utterance. For example, the learning unit weights the learning data by prioritizing the most recent utterance. The learning unit can also weight the learning data by prioritizing utterances made during a specific time period. Furthermore, the learning unit can weight the learning data by prioritizing important utterances with reference to past utterance history. In this way, weighting the learning data based on the time of submission of the utterance enables learning that emphasizes the most recent information. The time of submission of the utterance is evaluated, for example, based on the elapsed time since submission, before or after a specific event, etc. The weighting of the learning data is performed, for example, based on the novelty and relevance of the data. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the time of submission of the utterance into an AI model and weight the learning data.

[0100] During learning, the learning unit can integrate information from different data sources to enrich the learning data. For example, the learning unit can enrich the learning data by collecting information not only from chat logs but also from emails and documents. The learning unit can also enrich the learning data by collecting information from an internal database. Furthermore, the learning unit can enrich the learning data by collecting information from external information sources. This improves the quality of the learning data by integrating information from different data sources. Different data sources are integrated, for example, via an internal database, an external API, etc. Some or all of the above-described processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can enrich the learning data by inputting information from different data sources into an AI model. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, provision unit, and learning unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects chat logs via the communication I / F 44 of the smart device 14. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the content of comments using natural language processing technology and extracts important knowledge. The provision unit is realized, for example, by the control unit 46A of the smart device 14, and provides the extracted knowledge to the user in real time. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and continuously learns new comments and information and reflects them in the system. === Hard Collateral 1-2 === Each of the multiple elements including the collection unit, analysis unit, provision unit, and learning unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects chat logs via the communication I / F 44 of the smart glasses 214. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the content of comments using natural language processing technology and extracts important knowledge. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214, and provides the extracted knowledge to the user in real time. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and continuously learns new comments and information and reflects them in the system. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, provision unit, and learning unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects chat logs via the communication I / F 44 of the headset type terminal 314. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the content of comments using natural language processing technology and extracts important knowledge. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314, and provides the extracted knowledge to the user in real time. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and continuously learns new comments and information and reflects them in the system. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, provision unit, and learning unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects chat logs via the communication I / F 44 of the robot 414. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the content of comments using natural language processing technology and extracts important knowledge. The provision unit is realized, for example, by the control unit 46A of the robot 414, and provides the extracted knowledge to the user in real time. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and continuously learns new comments and information and reflects them in the system.

[0101] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0102] The knowledge provision system may further include a behavior analysis unit that analyzes the user's behavior history. The behavior analysis unit may, for example, analyze what information the user frequently references and what time of day the user is most active. This allows knowledge to be provided at the optimal timing based on the user's behavioral patterns. For example, if the user tends to reference a lot of information in the morning, important knowledge may be provided preferentially in the morning. Also, if the user frequently references information about a specific project, the latest knowledge related to that project may be provided preferentially. Furthermore, the behavior analysis unit may record what knowledge the user has referenced in the past and provide similar knowledge, thereby improving user convenience.

[0103] The knowledge provision system may further include an emotion adjustment unit that estimates the user's emotion and adjusts the method of providing knowledge based on the estimated emotion. For example, if the user is feeling stressed, the emotion adjustment unit may provide concise, to-the-point knowledge. Alternatively, if the user is relaxed, the emotion adjustment unit may provide detailed information. Furthermore, if the user is in a hurry, the emotion adjustment unit may quickly provide the necessary information, thereby saving the user time. The emotion estimation is performed, for example, by analyzing the user's facial expression and tone of voice. This makes it possible to provide optimal knowledge according to the user's emotion.

[0104] The knowledge provision system may further include an expertise adjustment unit that estimates the user's expertise level and adjusts the content of the knowledge to be provided based on the estimated expertise level. The expertise adjustment unit, for example, provides detailed, specialized information to users with high expertise. It may also provide concise, easy-to-understand information to users with low expertise. Furthermore, the expertise adjustment unit estimates the user's expertise level based on the user's past statements and behavior history, and provides appropriate information to deepen the user's understanding. This makes it possible to provide optimal knowledge according to the user's expertise level.

[0105] The knowledge provision system may further include a feedback collection unit that collects user feedback and improves the knowledge provision method based on the collected feedback. The feedback collection unit, for example, records how the user evaluated the provided knowledge. It may also analyze the extent to which the user utilized the provided knowledge. Furthermore, the feedback collection unit can improve the knowledge provision method based on the user feedback and provide more appropriate information. This makes it possible to provide optimal knowledge according to the user's needs.

[0106] The knowledge provision system may further include an emotion frequency adjustment unit that estimates the user's emotion and adjusts the frequency of knowledge provision based on the estimated emotion. For example, if the user is feeling stressed, the emotion frequency adjustment unit reduces the frequency of knowledge provision, thereby reducing the user's burden. Also, if the user is relaxed, the emotion frequency adjustment unit increases the frequency of knowledge provision, thereby increasing the user's motivation to learn. Furthermore, if the user is in a hurry, the emotion frequency adjustment unit can save the user's time by quickly providing necessary information. Emotion estimation is performed, for example, by analyzing the user's facial expressions and voice tone. This makes it possible to optimize the frequency of knowledge provision according to the user's emotion.

[0107] The knowledge provision system may further include a behavior optimization unit that analyzes the user's behavior history and optimizes the knowledge provision method based on the analysis results. The behavior optimization unit, for example, analyzes what information the user frequently references and what time of day the user is most active. This allows knowledge to be provided at the optimal timing based on the user's behavioral patterns. For example, if the user tends to reference a lot of information in the morning, important knowledge can be provided preferentially in the morning. Also, if the user frequently references information about a specific project, the latest knowledge related to that project can be provided preferentially. Furthermore, the behavior optimization unit records what knowledge the user has referenced in the past and provides similar knowledge, thereby improving user convenience.

[0108] The knowledge provision system may further include an emotion format adjustment unit that estimates the user's emotion and adjusts the format of knowledge provision based on the estimated emotion. For example, if the user is feeling stressed, the emotion format adjustment unit may provide knowledge in a visually easy-to-understand format. Alternatively, if the user is relaxed, the emotion format adjustment unit may provide knowledge in a detailed text format. Furthermore, if the user is in a hurry, the emotion format adjustment unit may provide knowledge in a bulleted list format that focuses on the main points, thereby saving the user time. Emotion estimation is performed, for example, by analyzing the user's facial expressions and tone of voice. This enables the optimal knowledge provision format to be selected according to the user's emotion.

[0109] The knowledge provision system may further include a specialized knowledge provision unit that estimates the user's level of specialized knowledge and adjusts the method of providing knowledge based on the estimated level of specialized knowledge. The specialized knowledge provision unit may, for example, provide detailed, specialized information to users with high levels of specialized knowledge. It may also provide concise, easy-to-understand information to users with low levels of specialized knowledge. Furthermore, the specialized knowledge provision unit may estimate the user's level of specialized knowledge based on the user's past statements and behavioral history, and provide appropriate information to deepen the user's understanding. This makes it possible to provide optimal knowledge according to the user's level of specialized knowledge.

[0110] The knowledge provision system may further include an emotion order adjustment unit that estimates the user's emotion and adjusts the order in which knowledge is provided based on the estimated emotion. For example, the emotion order adjustment unit may provide important information preferentially when the user is feeling stressed. Also, when the user is relaxed, the emotion order adjustment unit may provide detailed information in an orderly manner. Furthermore, when the user is in a hurry, the emotion order adjustment unit may quickly provide information that focuses on the main points, thereby saving the user time. Emotions are estimated by, for example, analyzing the user's facial expressions and tone of voice. This enables the optimal order in which knowledge is provided according to the user's emotion.

[0111] The knowledge provision system may further include a behavior frequency optimization unit that analyzes the user's behavior history and optimizes the frequency of knowledge provision based on the analysis results. The behavior frequency optimization unit, for example, analyzes what information the user frequently references and what time of day the user is most active. This allows knowledge to be provided at an optimal frequency based on the user's behavior patterns. For example, if the user tends to reference a lot of information in the morning, important knowledge can be provided preferentially in the morning. Also, if the user frequently references information about a specific project, the latest knowledge related to that project can be provided preferentially. Furthermore, the behavior frequency optimization unit records what knowledge the user has referenced in the past and provides similar knowledge, thereby improving user convenience.

[0112] The processing flow of the second embodiment will be briefly explained below.

[0113] Step 1: The collection unit collects internal company communications. Internal company communications include conference communications, chat communications, email content, etc. The collection unit collects, for example, chat logs, including text format, image and file attachments, etc. Step 2: The analysis unit analyzes the collected comments and extracts important knowledge. Important knowledge includes business-related information, technical knowledge, business strategies, etc. The analysis unit analyzes the content of the comments using natural language processing technology, for example, and extracts important knowledge. Step 3: The providing unit provides the knowledge extracted by the analysis unit in real time. The specific time range of real time is within a few seconds, a few minutes, etc., and the extracted knowledge is immediately provided to the user. Step 4: The learning unit continuously learns new comments and information, and the system always maintains the latest information. The specific method and frequency of continuous learning can be periodic data updates or real-time learning, and new comments and information are automatically learned and reflected in the system.

[0114] 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.

[0115] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] 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.

[0117] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0118] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0119] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0132] 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.

[0133] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0134] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0135] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0145] 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.

[0146] 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.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0148] 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.

[0149] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0150] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0162] 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.

[0163] 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.

[0164] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0165] 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.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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).

[0171] 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.

[0172] 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."

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] [Explanation of symbols]

[0186] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection department that collects comments from within the company; an analysis unit that analyzes the utterances collected by the collection unit and extracts important knowledge; a providing unit that provides the knowledge extracted by the analysis unit in real time; A learning unit that continuously learns A system characterized by:

2. The collecting unit Collect chat logs 2. The system of claim 1.

3. The analysis unit Analyze the collected chat logs and extract important knowledge 2. The system of claim 1.

4. The providing unit Delivering extracted knowledge in real time 2. The system of claim 1.

5. The learning unit Continuously learn new utterances or information to keep the system up to date 2. The system of claim 1.

6. The collecting unit Estimate user emotions and adjust the timing of utterance collection based on the estimated user emotions.

2. The system of claim 1.

7. The collecting unit When collecting, prioritize collection based on the importance of the comments.

2. The system of claim 1.

8. The collecting unit During collection, different collection algorithms are applied depending on the category of the utterance.

2. The system of claim 1.

Images