system

Abstract

The system according to this embodiment aims to automatically generate and update a glossary of terms, ensuring accuracy while preventing obsolescence. [Solution] The system according to the embodiment comprises an extraction unit, an approval unit, an update unit, a scoring unit, and a utilization unit. The extraction unit extracts terms. The approval unit approves the terms extracted by the extraction unit. The update unit adds the terms approved by the approval unit to the term dictionary. The scoring unit utilizes the terms pending approval by the approval unit based on their scores. The utilization unit utilizes the term dictionary updated by the update unit.

Description

Technical Field

[0006] , , ,

[0005] , ,

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, since the update of the term dictionary is performed manually, there is a problem that it is prone to obsolescence and difficult to ensure accuracy.

[0005] The system according to the embodiment aims to automatically generate and update a term dictionary and prevent obsolescence while ensuring accuracy.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an extraction unit, an approval unit, an update unit, a scoring unit, and a utilization unit. The extraction unit extracts terms. The approval unit approves the terms extracted by the extraction unit. The update unit adds the terms approved by the approval unit to the term dictionary. The scoring unit utilizes the terms pending approval by the approval unit based on their scores. The utilization unit utilizes the term dictionary updated by the update unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically generate and update a glossary of terms, ensuring accuracy while preventing obsolescence. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The terminology dictionary generation system according to an embodiment of the present invention is a system that automatically generates a terminology dictionary, ensures accuracy by incorporating an approval process, and maintains a terminology dictionary that is prone to obsolescence by utilizing terms based on their scores even if approval is pending. This terminology dictionary generation system comprises an extraction unit for extracting terms, an approval unit for approving the extracted terms, an update unit for adding approved terms to the terminology dictionary, a scoring unit for utilizing terms pending approval based on their scores, and a utilization unit for utilizing the updated terminology dictionary. For example, the terminology dictionary generation system automatically extracts terms from online video conferences, instant messages (IMs), and posts. In this process, AI analyzes the content of conversations and posts to identify specialized terms and frequently used terms. For example, it extracts specialized terms used during meetings and terms frequently used in chats. Next, before adding the extracted terms to the terminology dictionary, they undergo an approval process. Specifically, experts review the extracted terms and evaluate their accuracy and appropriateness. Approved terms are added to the terminology dictionary, and terms pending approval are also utilized based on their scores. For example, even terms pending approval may be temporarily added to the terminology dictionary if they have a high score. This mechanism ensures the accuracy of the glossary while preventing obsolescence. Because the glossary is always kept up-to-date, recognition and processing by various AI tools improve. For example, when an AI creates meeting minutes, it can generate accurate minutes by referring to the latest glossary. Furthermore, maintaining the glossary enhances the overall utilization of AI. For instance, by referring to the glossary and accurately recognizing technical terms, the AI ​​can accurately understand the meeting content and provide appropriate suggestions and advice. This improves work efficiency and increases the productivity of the entire team. In short, the glossary generation system ensures the accuracy of the glossary while preventing obsolescence.

[0029] The terminology dictionary generation system according to this embodiment comprises an extraction unit, an approval unit, an update unit, a scoring unit, and a utilization unit. The extraction unit extracts terms. The extraction unit extracts terms from, for example, online video conferences, instant messages, and posts. The extraction unit uses AI to analyze conversations and posts and identify specialized terms and frequently used terms. For example, it extracts specialized terms used during meetings and terms frequently used in chats. The approval unit approves the terms extracted by the extraction unit. The approval unit, for example, has experts review the extracted terms and evaluate their accuracy and appropriateness. The approval unit can also use AI to evaluate the extracted terms. The update unit adds the terms approved by the approval unit to the terminology dictionary. For example, the update unit adds approved terms to the terminology dictionary according to specific procedures and criteria for adding them to the terminology dictionary. The scoring unit utilizes terms that have been pending approval by the approval unit based on their scores. For example, the scoring unit temporarily adds terms that have been pending approval to the terminology dictionary if they have a high score. The utilization unit utilizes the terminology dictionary updated by the update unit. The user unit, for example, uses a glossary to allow the AI ​​tool to recognize specialized terms. This ensures the accuracy of the glossary while preventing obsolescence.

[0030] The extraction unit extracts terminology. For example, it extracts terminology from online video conferences, instant messages, and posts. Specifically, the extraction unit uses natural language processing (NLP) technology to analyze conversations and posts to identify specialized and frequently used terms. For example, it extracts specialized terminology used during meetings or terms frequently used in chats. The extraction unit uses speech recognition technology to convert meeting audio data into text and analyzes that text data to extract important terms. Similarly, it applies NLP technology to text data from instant messages and posts to identify frequently used and specialized terms. Furthermore, the extraction unit uses an AI model to understand the context and evaluate the importance and relevance of terms. For example, it can be configured to prioritize the extraction of terms frequently used in a particular industry or field. This allows the extraction unit to analyze conversations and posts in detail and efficiently extract appropriate terminology.

[0031] The approval department approves the terms extracted by the extraction department. For example, the approval department has experts review the extracted terms and evaluate their accuracy and appropriateness. Specifically, the approval department lists the extracted terms and presents them to the experts. The experts evaluate the accuracy and appropriateness of the terms based on their meaning, frequency of use, and context. The approval department can also use AI to evaluate the extracted terms. The AI ​​has an algorithm that automatically evaluates the accuracy and appropriateness of terms based on past data and expertise. For example, the AI ​​analyzes the frequency of use and context of terms and scores their importance and reliability. Furthermore, the approval department can implement a feedback loop to streamline the term evaluation process. The experts' evaluation results are fed back to the AI, continuously improving the AI's evaluation accuracy. This allows the approval department to evaluate the accuracy and appropriateness of extracted terms with high precision and ensure the quality of the term dictionary.

[0032] The Update Department adds terms approved by the Approval Department to the glossary. The Update Department adds terms according to specific procedures and criteria, such as those outlined for adding approved terms to the glossary. Specifically, the Update Department registers approved terms in the glossary database and adds definitions, usage examples, and related information. The Update Department appropriately classifies and organizes terms according to the structure and format of the glossary. Furthermore, the Update Department manages the versioning of the glossary and records the update history to track changes. In addition, the Update Department regularly maintains the glossary, deleting old and unnecessary terms and adding new ones to maintain its up-to-dateness and accuracy. This allows the Update Department to efficiently and accurately add approved terms to the glossary and maintain its quality.

[0033] The scoring unit uses terms that have been put on hold for approval by the approval unit based on their scores. For example, if a term with a high score has been put on hold, the scoring unit will temporarily add it to the term dictionary. Specifically, the scoring unit uses AI to score terms that have been put on hold. The AI ​​analyzes the frequency of use, context, and relevance of the terms and scores their importance and reliability. Terms with high scores are temporarily added to the term dictionary and used by the user unit. The scoring unit regularly reviews its scoring criteria and algorithms to improve accuracy. The scoring unit also continuously monitors the scores of terms that have been put on hold and updates the term dictionary if the scores change. This allows the scoring unit to efficiently evaluate terms that have been put on hold and improve the flexibility and adaptability of the term dictionary.

[0034] The user unit utilizes the glossary updated by the update unit. For example, the user unit uses the glossary to enable AI tools to recognize technical terms. Specifically, the user unit provides the glossary to AI tools and other systems for use in the recognition and analysis of technical terms. For example, AI tools refer to the glossary to accurately recognize technical terms contained in conversations and posts, and provide appropriate responses and analyses. The user unit also integrates the glossary into other systems and applications to provide automatic completion, translation, and search functions for technical terms. Furthermore, the user unit monitors the usage of the glossary and collects user feedback to continuously improve its quality and usability. This allows the user unit to effectively utilize the updated glossary and improve the accuracy of technical term recognition and analysis.

[0035] The approval process includes a review of the extracted terms by experts. For example, experts review the extracted terms and evaluate their accuracy and appropriateness. The approval process can also use AI to evaluate the extracted terms, thereby assessing their accuracy and appropriateness.

[0036] The scoring unit temporarily uses the term "approval pending" based on its score. For example, if a term "approval pending" has a high score, the scoring unit temporarily adds it to the term dictionary. The scoring unit can also use AI to score the term "approval pending." This ensures that the term "approval pending" is also used based on its score.

[0037] The extraction unit extracts terminology from online video conferences, instant messages, and posts. For example, it extracts terminology from online video conferences, instant messages, and posts. The extraction unit uses AI to analyze conversations and posts, identifying specialized and frequently used terms. For instance, it extracts specialized terminology used during meetings or terms frequently used in chats. This allows for the automatic extraction of terminology from conversations and posts.

[0038] The user unit uses a glossary to enable the AI ​​tool to recognize technical terms. For example, the user unit can use AI to refer to a glossary and recognize technical terms. This allows the AI ​​tool to accurately recognize technical terms.

[0039] The update unit adds approved terms to the glossary. The update unit adds terms according to specific procedures and criteria, for example. The update unit can also use AI to add approved terms, thereby adding them to the glossary.

[0040] The extraction unit analyzes the context of conversations and posts and prioritizes extracting terms related to specific topics. For example, the extraction unit prioritizes extracting terms related to the agenda of a meeting. The extraction unit can also extract relevant terms based on keywords in the posts. The extraction unit can also analyze the flow of a conversation and extract terms related to important topics. This allows for the priority extraction of terms related to specific topics. Some or all of the above processing in the extraction unit may be performed using AI or not.

[0041] The extraction unit determines the extraction priority based on the frequency and importance of the terms used during the extraction process. For example, the extraction unit may prioritize the extraction of frequently used terms. The extraction unit may also prioritize the extraction of terms used in important meetings. The extraction unit may also prioritize the extraction of terms that are particularly emphasized in the content of the posts. This allows the extraction priority to be determined based on the frequency and importance of the terms used. Some or all of the above processing in the extraction unit may be performed using AI or not.

[0042] The extraction unit prioritizes extracting highly relevant terms while considering the user's geographical location. For example, if the user is in a specific region, the extraction unit prioritizes extracting terms related to that region. If the user is traveling, the extraction unit can also prioritize extracting terms related to the travel destination. If the user is participating in a specific event, the extraction unit can also prioritize extracting terms related to that event. This allows for the prioritization of highly relevant terms while considering the user's geographical location. Some or all of the above processing in the extraction unit may be performed using AI or not.

[0043] The extraction unit analyzes the user's social media activity during extraction and extracts relevant terms. For example, the extraction unit extracts terms that the user frequently uses on social media. The extraction unit can also extract terms based on the content of posts from accounts that the user follows. The extraction unit can also extract terms related to topics in groups that the user participates in. This allows for the analysis of the user's social media activity and the extraction of relevant terms. Some or all of the above processing in the extraction unit may be performed using AI or not.

[0044] The approval department dynamically changes the criteria for evaluating the accuracy and appropriateness of terms during the approval process. For example, the approval department may change the evaluation criteria based on the frequency of use of a term. The approval department may also change the evaluation criteria based on the importance of a term. The approval department may also change the evaluation criteria based on the context of a term. This allows for dynamic changes to the criteria for evaluating the accuracy and appropriateness of terms. Some or all of the above processes in the approval department may be performed using AI or not.

[0045] The approval unit improves the accuracy of approvals by referring to the usage history of terms during the approval process. For example, the approval unit refers to the usage history of terms that have been previously approved. The approval unit may also refer to the usage history of terms that have been previously put on hold. The approval unit may also refer to the usage history of terms that have been previously rejected. This allows the approval unit to improve the accuracy of approvals by referring to the usage history of terms. Some or all of the above processes in the approval unit may be performed using AI or not.

[0046] The approval department, when approving a term, determines the approval priority by considering the attribute information of the term submitter. The approval department may, for example, determine the approval priority based on the submitter's expertise. The approval department may also determine the approval priority based on the submitter's job title. The approval department may also determine the approval priority based on the submitter's past approval history. This allows the approval department to determine the approval priority by considering the attribute information of the term submitter. Some or all of the above processes in the approval department may be performed using AI or not.

[0047] The approval department improves the accuracy of its approval process by referring to relevant literature for the term. For example, the approval department may automatically search for relevant literature for the term and use it as a reference for approval. The approval department may also accept that the submitter provides the relevant literature for the term. The approval department may also accept that the approver reviews the relevant literature for the term. This allows the approval department to improve the accuracy of its approval process by referring to relevant literature for the term. Some or all of the above processes in the approval department may be performed using AI or not.

[0048] The update unit determines the update priority based on the importance of the terms during the update process. For example, the update unit prioritizes updating important terms. The update unit may also prioritize updating frequently used terms. The update unit may also prioritize updating technical terms. This allows the update priority to be determined based on the importance of the terms. Some or all of the above processing in the update unit may be performed using AI or not.

[0049] The update unit applies different update algorithms depending on the category of the term during the update process. For example, the update unit may apply a specialized update algorithm to technical terms, a simplified update algorithm to general terms, and an adaptive update algorithm to terms in new categories. This allows for the application of different update algorithms depending on the category of the term. Some or all of the above-described processes in the update unit may be performed using AI or not.

[0050] The update unit determines the update priority based on the submission date of the terms during the update process. For example, the update unit prioritizes updating recently submitted terms. The update unit may also prioritize updating older terms. The update unit can also dynamically change the update priority according to the submission date. This allows the update priority to be determined based on the submission date of the terms. Some or all of the above processing in the update unit may be performed using AI or not.

[0051] The update unit adjusts the order of updates based on the relevance of the terms during the update process. For example, the update unit prioritizes updating highly relevant terms. The update unit may also postpone updating less relevant terms. The update unit can also dynamically change the order of updates according to the relevance of the terms. This allows the update order to be adjusted based on the relevance of the terms. Some or all of the above processing in the update unit may be performed using AI or not.

[0052] The scoring unit improves the accuracy of scoring by considering the interrelationships between terms during the scoring process. For example, the scoring unit comprehensively evaluates the scores of related terms. The scoring unit can also analyze the interrelationships between terms and reflect them in the scoring. The scoring unit can also perform scoring while considering the context of the terms. This allows for improved scoring accuracy by considering the interrelationships between terms. Some or all of the above-described processes in the scoring unit may be performed using AI or not.

[0053] The scoring unit considers the attribute information of the term submitter when scoring. For example, the scoring unit may score based on the submitter's expertise. The scoring unit may also score based on the submitter's job title. The scoring unit may also score based on the submitter's past scoring history. This allows the scoring to take into account the attribute information of the term submitter. Some or all of the above processing in the scoring unit may be performed using AI or not.

[0054] The scoring unit performs scoring while considering the geographical distribution of terms. For example, the scoring unit may give higher scores to terms that are frequently used in a particular region. The scoring unit may also give higher scores to terms that are used over a wide geographical area. The scoring unit may also perform scoring while considering the frequency of use of terms in each region. This allows for scoring that takes into account the geographical distribution of terms. Some or all of the above processing in the scoring unit may be performed using AI or not.

[0055] The scoring unit improves the accuracy of scoring by referring to relevant literature for terms during the scoring process. For example, the scoring unit automatically searches for relevant literature for terms and uses it as a reference for scoring. The scoring unit may also use relevant literature provided by the submitter. The scoring unit can also check the relevant literature for terms during the scoring process. This allows the scoring unit to improve the accuracy of scoring by referring to relevant literature for terms. Some or all of the above processes in the scoring unit may be performed using AI or not.

[0056] The user unit selects the optimal usage method by referring to the term usage history when the term is used. For example, the user unit prioritizes displaying terms that have been used frequently in the past. The user unit can also suggest relevant terms based on past usage history. The user unit can also analyze past usage history and select the optimal usage method. This allows the user unit to select the optimal usage method by referring to the term usage history. Some or all of the above processing in the user unit may be performed using AI or not.

[0057] The utilization unit applies different utilization algorithms depending on the category of the term at the time of utilization. For example, the utilization unit may apply a specialized utilization algorithm to technical terms. The utilization unit may also apply a simplified utilization algorithm to general terms. The utilization unit may also apply an adaptive utilization algorithm to terms in new categories. This allows different utilization algorithms to be applied depending on the category of the term. Some or all of the processing described above in the utilization unit may be performed using AI or not using AI.

[0058] The user unit selects the optimal usage method when a term is used, taking into account its geographical location. For example, if the user is in a specific region, the user unit will prioritize displaying terms related to that region. If the user is traveling, the user unit may also prioritize displaying terms related to the travel destination. If the user is participating in a specific event, the user unit may also prioritize displaying terms related to that event. This allows the user unit to select the optimal usage method, taking into account the geographical location of the term. Some or all of the processing described above in the user unit may be performed using AI, or not.

[0059] The user unit improves the accuracy of its use by referring to related literature for the term during use. For example, the user unit automatically searches for related literature for the term and uses it as a reference. The user unit may also receive related literature for the term from the submitter. The user unit can also check related literature for the term during use. This allows for improved accuracy of use by referring to related literature for the term. Some or all of the above processing in the user unit may be performed using AI or not.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The extraction unit can prioritize the extraction of highly relevant terms by considering the user's geographical location. For example, if the user is in a specific region, it can prioritize the extraction of terms related to that region. Similarly, if the user is traveling, it can prioritize the extraction of terms related to their travel destination. Furthermore, if the user is participating in a specific event, it can prioritize the extraction of terms related to that event. This allows for the prioritization of highly relevant terms by considering the user's geographical location.

[0062] The approval department can improve the accuracy of approvals by referring to the usage history of terms during the approval process. For example, it can refer to the usage history of terms that have been previously approved. It can also refer to the usage history of terms that have been previously put on hold. Furthermore, it can refer to the usage history of terms that have been previously rejected. This allows for improved approval accuracy by referring to the usage history of terms.

[0063] The scoring unit can improve the accuracy of scoring by considering the interrelationships between terms during the scoring process. For example, it can comprehensively evaluate the scores of related terms. It can also analyze the interrelationships between terms and reflect them in the scoring. Furthermore, it can perform scoring while considering the context of the terms. This allows for improved scoring accuracy by taking into account the interrelationships between terms.

[0064] The update unit can apply different update algorithms depending on the category of the term during the update process. For example, a specialized update algorithm can be applied to technical terms, while a simpler algorithm can be applied to general terms. Furthermore, an adaptive update algorithm can be applied to terms in new categories. This allows for the application of different update algorithms depending on the category of the term.

[0065] The user unit can improve the accuracy of its use by referring to related literature for the term during use. For example, it can automatically search for related literature for the term and use it as a reference. Furthermore, the submitter can provide related literature for the term. In addition, users can check related literature for the term during use. This allows for improved accuracy of use by referring to related literature.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The extraction unit extracts terminology. The extraction unit extracts terminology from, for example, online video conferences, instant messages, and posts. The extraction unit uses AI to analyze conversations and posts and identify specialized terminology and frequently used terms. For example, it extracts specialized terminology used during meetings or terms frequently used in chats. Step 2: The approval department approves the terms extracted by the extraction department. The approval department, for example, has experts review the extracted terms and evaluate their accuracy and appropriateness. The approval department can also use AI to evaluate the extracted terms. Step 3: The Update Department adds the terms approved by the Approval Department to the glossary. The Update Department adds the terms according to specific procedures and criteria for adding approved terms to the glossary, for example. Step 4: The scoring unit uses the term "approval pending" based on the score assigned by the approval unit. For example, if a term "approval pending" has a high score, the scoring unit will temporarily add it to the term dictionary. Step 5: The user unit utilizes the glossary updated by the update unit. For example, the user unit refers to the glossary so that the AI ​​tool can recognize specialized terminology.

[0068] (Example of form 2) The terminology dictionary generation system according to an embodiment of the present invention is a system that automatically generates a terminology dictionary, ensures accuracy by incorporating an approval process, and maintains a terminology dictionary that is prone to obsolescence by utilizing terms based on their scores even if approval is pending. This terminology dictionary generation system comprises an extraction unit for extracting terms, an approval unit for approving the extracted terms, an update unit for adding approved terms to the terminology dictionary, a scoring unit for utilizing terms pending approval based on their scores, and a utilization unit for utilizing the updated terminology dictionary. For example, the terminology dictionary generation system automatically extracts terms from online video conferences, instant messages (IMs), and posts. In this process, AI analyzes the content of conversations and posts to identify specialized terms and frequently used terms. For example, it extracts specialized terms used during meetings and terms frequently used in chats. Next, before adding the extracted terms to the terminology dictionary, they undergo an approval process. Specifically, experts review the extracted terms and evaluate their accuracy and appropriateness. Approved terms are added to the terminology dictionary, and terms pending approval are also utilized based on their scores. For example, even terms pending approval may be temporarily added to the terminology dictionary if they have a high score. This mechanism ensures the accuracy of the glossary while preventing obsolescence. Because the glossary is always kept up-to-date, recognition and processing by various AI tools improve. For example, when an AI creates meeting minutes, it can generate accurate minutes by referring to the latest glossary. Furthermore, maintaining the glossary enhances the overall utilization of AI. For instance, by referring to the glossary and accurately recognizing technical terms, the AI ​​can accurately understand the meeting content and provide appropriate suggestions and advice. This improves work efficiency and increases the productivity of the entire team. In short, the glossary generation system ensures the accuracy of the glossary while preventing obsolescence.

[0069] The terminology dictionary generation system according to this embodiment comprises an extraction unit, an approval unit, an update unit, a scoring unit, and a utilization unit. The extraction unit extracts terms. The extraction unit extracts terms from, for example, online video conferences, instant messages, and posts. The extraction unit uses AI to analyze conversations and posts and identify specialized terms and frequently used terms. For example, it extracts specialized terms used during meetings and terms frequently used in chats. The approval unit approves the terms extracted by the extraction unit. The approval unit, for example, has experts review the extracted terms and evaluate their accuracy and appropriateness. The approval unit can also use AI to evaluate the extracted terms. The update unit adds the terms approved by the approval unit to the terminology dictionary. For example, the update unit adds approved terms to the terminology dictionary according to specific procedures and criteria for adding them to the terminology dictionary. The scoring unit utilizes terms that have been pending approval by the approval unit based on their scores. For example, the scoring unit temporarily adds terms that have been pending approval to the terminology dictionary if they have a high score. The utilization unit utilizes the terminology dictionary updated by the update unit. The user unit, for example, uses a glossary to allow the AI ​​tool to recognize specialized terms. This ensures the accuracy of the glossary while preventing obsolescence.

[0070] The extraction unit extracts terminology. For example, it extracts terminology from online video conferences, instant messages, and posts. Specifically, the extraction unit uses natural language processing (NLP) technology to analyze conversations and posts to identify specialized and frequently used terms. For example, it extracts specialized terminology used during meetings or terms frequently used in chats. The extraction unit uses speech recognition technology to convert meeting audio data into text and analyzes that text data to extract important terms. Similarly, it applies NLP technology to text data from instant messages and posts to identify frequently used and specialized terms. Furthermore, the extraction unit uses an AI model to understand the context and evaluate the importance and relevance of terms. For example, it can be configured to prioritize the extraction of terms frequently used in a particular industry or field. This allows the extraction unit to analyze conversations and posts in detail and efficiently extract appropriate terminology.

[0071] The approval department approves the terms extracted by the extraction department. For example, the approval department has experts review the extracted terms and evaluate their accuracy and appropriateness. Specifically, the approval department lists the extracted terms and presents them to the experts. The experts evaluate the accuracy and appropriateness of the terms based on their meaning, frequency of use, and context. The approval department can also use AI to evaluate the extracted terms. The AI ​​has an algorithm that automatically evaluates the accuracy and appropriateness of terms based on past data and expertise. For example, the AI ​​analyzes the frequency of use and context of terms and scores their importance and reliability. Furthermore, the approval department can implement a feedback loop to streamline the term evaluation process. The experts' evaluation results are fed back to the AI, continuously improving the AI's evaluation accuracy. This allows the approval department to evaluate the accuracy and appropriateness of extracted terms with high precision and ensure the quality of the term dictionary.

[0072] The Update Department adds terms approved by the Approval Department to the glossary. The Update Department adds terms according to specific procedures and criteria, such as those outlined for adding approved terms to the glossary. Specifically, the Update Department registers approved terms in the glossary database and adds definitions, usage examples, and related information. The Update Department appropriately classifies and organizes terms according to the structure and format of the glossary. Furthermore, the Update Department manages the versioning of the glossary and records the update history to track changes. In addition, the Update Department regularly maintains the glossary, deleting old and unnecessary terms and adding new ones to maintain its up-to-dateness and accuracy. This allows the Update Department to efficiently and accurately add approved terms to the glossary and maintain its quality.

[0073] The scoring unit uses terms that have been put on hold for approval by the approval unit based on their scores. For example, if a term with a high score has been put on hold, the scoring unit will temporarily add it to the term dictionary. Specifically, the scoring unit uses AI to score terms that have been put on hold. The AI ​​analyzes the frequency of use, context, and relevance of the terms and scores their importance and reliability. Terms with high scores are temporarily added to the term dictionary and used by the user unit. The scoring unit regularly reviews its scoring criteria and algorithms to improve accuracy. The scoring unit also continuously monitors the scores of terms that have been put on hold and updates the term dictionary if the scores change. This allows the scoring unit to efficiently evaluate terms that have been put on hold and improve the flexibility and adaptability of the term dictionary.

[0074] The user unit utilizes the glossary updated by the update unit. For example, the user unit uses the glossary to enable AI tools to recognize technical terms. Specifically, the user unit provides the glossary to AI tools and other systems for use in the recognition and analysis of technical terms. For example, AI tools refer to the glossary to accurately recognize technical terms contained in conversations and posts, and provide appropriate responses and analyses. The user unit also integrates the glossary into other systems and applications to provide automatic completion, translation, and search functions for technical terms. Furthermore, the user unit monitors the usage of the glossary and collects user feedback to continuously improve its quality and usability. This allows the user unit to effectively utilize the updated glossary and improve the accuracy of technical term recognition and analysis.

[0075] The approval process includes a review of the extracted terms by experts. For example, experts review the extracted terms and evaluate their accuracy and appropriateness. The approval process can also use AI to evaluate the extracted terms, thereby assessing their accuracy and appropriateness.

[0076] The scoring unit temporarily uses the term "approval pending" based on its score. For example, if a term "approval pending" has a high score, the scoring unit temporarily adds it to the term dictionary. The scoring unit can also use AI to score the term "approval pending." This ensures that the term "approval pending" is also used based on its score.

[0077] The extraction unit extracts terminology from online video conferences, instant messages, and posts. For example, it extracts terminology from online video conferences, instant messages, and posts. The extraction unit uses AI to analyze conversations and posts, identifying specialized and frequently used terms. For instance, it extracts specialized terminology used during meetings or terms frequently used in chats. This allows for the automatic extraction of terminology from conversations and posts.

[0078] The user unit uses a glossary to enable the AI ​​tool to recognize technical terms. For example, the user unit can use AI to refer to a glossary and recognize technical terms. This allows the AI ​​tool to accurately recognize technical terms.

[0079] The update unit adds approved terms to the glossary. The update unit adds terms according to specific procedures and criteria, for example. The update unit can also use AI to add approved terms, thereby adding them to the glossary.

[0080] The extraction unit estimates the user's emotions and adjusts the timing of term extraction based on the estimated emotions. For example, if the user is stressed, the extraction unit will extract terms after the meeting has ended. If the user is relaxed, the extraction unit can also extract terms in real time. If the user is in a hurry, the extraction unit can extract only the important parts of the meeting. This allows the timing of term extraction to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0081] The extraction unit analyzes the context of conversations and posts and prioritizes extracting terms related to specific topics. For example, the extraction unit prioritizes extracting terms related to the agenda of a meeting. The extraction unit can also extract relevant terms based on keywords in the posts. The extraction unit can also analyze the flow of a conversation and extract terms related to important topics. This allows for the priority extraction of terms related to specific topics. Some or all of the above processing in the extraction unit may be performed using AI or not.

[0082] The extraction unit determines the extraction priority based on the frequency and importance of the terms used during the extraction process. For example, the extraction unit may prioritize the extraction of frequently used terms. The extraction unit may also prioritize the extraction of terms used in important meetings. The extraction unit may also prioritize the extraction of terms that are particularly emphasized in the content of the posts. This allows the extraction priority to be determined based on the frequency and importance of the terms used. Some or all of the above processing in the extraction unit may be performed using AI or not.

[0083] The extraction unit estimates the user's emotions and determines the priority of terms to extract based on the estimated emotions. For example, if the user is excited, the extraction unit will prioritize extracting terms related to those emotions. If the user is calm, the extraction unit may also prioritize extracting terms related to calm discussion. If the user is feeling anxious, the extraction unit may also prioritize extracting terms that provide a sense of security. This allows the system to determine the priority of terms to extract according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0084] The extraction unit prioritizes extracting highly relevant terms while considering the user's geographical location. For example, if the user is in a specific region, the extraction unit prioritizes extracting terms related to that region. If the user is traveling, the extraction unit can also prioritize extracting terms related to the travel destination. If the user is participating in a specific event, the extraction unit can also prioritize extracting terms related to that event. This allows for the prioritization of highly relevant terms while considering the user's geographical location. Some or all of the above processing in the extraction unit may be performed using AI or not.

[0085] The extraction unit analyzes the user's social media activity during extraction and extracts relevant terms. For example, the extraction unit extracts terms that the user frequently uses on social media. The extraction unit can also extract terms based on the content of posts from accounts that the user follows. The extraction unit can also extract terms related to topics in groups that the user participates in. This allows for the analysis of the user's social media activity and the extraction of relevant terms. Some or all of the above processing in the extraction unit may be performed using AI or not.

[0086] The approval unit estimates the user's emotions and adjusts the priority of the approval process based on the estimated emotions. For example, if the user is stressed, the approval unit may simplify the approval process. If the user is relaxed, the approval unit may also provide a detailed approval process. If the user is in a hurry, the approval unit may also provide a rapid approval process. This allows the approval process to be prioritized according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0087] The approval department dynamically changes the criteria for evaluating the accuracy and appropriateness of terms during the approval process. For example, the approval department may change the evaluation criteria based on the frequency of use of a term. The approval department may also change the evaluation criteria based on the importance of a term. The approval department may also change the evaluation criteria based on the context of a term. This allows for dynamic changes to the criteria for evaluating the accuracy and appropriateness of terms. Some or all of the above processes in the approval department may be performed using AI or not.

[0088] The approval unit improves the accuracy of approvals by referring to the usage history of terms during the approval process. For example, the approval unit refers to the usage history of terms that have been previously approved. The approval unit may also refer to the usage history of terms that have been previously put on hold. The approval unit may also refer to the usage history of terms that have been previously rejected. This allows the approval unit to improve the accuracy of approvals by referring to the usage history of terms. Some or all of the above processes in the approval unit may be performed using AI or not.

[0089] The approval unit estimates the user's emotions and adjusts the way approvals are displayed based on the estimated emotions. For example, if the user is nervous, the approval unit provides a simple and highly visible display. If the user is relaxed, the approval unit may also provide a display that includes detailed information. If the user is in a hurry, the approval unit may also provide a display that gets straight to the point. This allows the approval display to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The approval department, when approving a term, determines the approval priority by considering the attribute information of the term submitter. The approval department may, for example, determine the approval priority based on the submitter's expertise. The approval department may also determine the approval priority based on the submitter's job title. The approval department may also determine the approval priority based on the submitter's past approval history. This allows the approval department to determine the approval priority by considering the attribute information of the term submitter. Some or all of the above processes in the approval department may be performed using AI or not.

[0091] The approval department improves the accuracy of its approval process by referring to relevant literature for the term. For example, the approval department may automatically search for relevant literature for the term and use it as a reference for approval. The approval department may also accept that the submitter provides the relevant literature for the term. The approval department may also accept that the approver reviews the relevant literature for the term. This allows the approval department to improve the accuracy of its approval process by referring to relevant literature for the term. Some or all of the above processes in the approval department may be performed using AI or not.

[0092] The update unit estimates the user's emotions and adjusts the timing of glossary updates based on the estimated emotions. For example, if the user is stressed, the update unit may delay the update. If the user is relaxed, the update unit may update immediately. If the user is in a hurry, the update unit may prioritize updating only the most important terms. This allows the timing of glossary updates to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0093] The update unit determines the update priority based on the importance of the terms during the update process. For example, the update unit prioritizes updating important terms. The update unit may also prioritize updating frequently used terms. The update unit may also prioritize updating technical terms. This allows the update priority to be determined based on the importance of the terms. Some or all of the above processing in the update unit may be performed using AI or not.

[0094] The update unit applies different update algorithms depending on the category of the term during the update process. For example, the update unit may apply a specialized update algorithm to technical terms, a simplified update algorithm to general terms, and an adaptive update algorithm to terms in new categories. This allows for the application of different update algorithms depending on the category of the term. Some or all of the above-described processes in the update unit may be performed using AI or not.

[0095] The update unit estimates the user's emotions and adjusts how updates are displayed based on the estimated emotions. For example, if the user is stressed, the update unit provides a simple and highly visible display. If the user is relaxed, the update unit may also provide a display that includes detailed information. If the user is in a hurry, the update unit may also provide a concise display. This allows the update display to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The update unit determines the update priority based on the submission date of the terms during the update process. For example, the update unit prioritizes updating recently submitted terms. The update unit may also prioritize updating older terms. The update unit can also dynamically change the update priority according to the submission date. This allows the update priority to be determined based on the submission date of the terms. Some or all of the above processing in the update unit may be performed using AI or not.

[0097] The update unit adjusts the order of updates based on the relevance of the terms during the update process. For example, the update unit prioritizes updating highly relevant terms. The update unit may also postpone updating less relevant terms. The update unit can also dynamically change the order of updates according to the relevance of the terms. This allows the update order to be adjusted based on the relevance of the terms. Some or all of the above processing in the update unit may be performed using AI or not.

[0098] The scoring unit estimates the user's emotions and adjusts the scoring criteria based on the estimated emotions. For example, if the user is relaxed, the scoring unit will score based on a relaxed criterion. If the user is in a hurry, the scoring unit can also score based on a fast criterion. If the user is excited, the scoring unit can also score based on a visually stimulating criterion. This allows the scoring criteria to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0099] The scoring unit improves the accuracy of scoring by considering the interrelationships between terms during the scoring process. For example, the scoring unit comprehensively evaluates the scores of related terms. The scoring unit can also analyze the interrelationships between terms and reflect them in the scoring. The scoring unit can also perform scoring while considering the context of the terms. This allows for improved scoring accuracy by considering the interrelationships between terms. Some or all of the above-described processes in the scoring unit may be performed using AI or not.

[0100] The scoring unit considers the attribute information of the term submitter when scoring. For example, the scoring unit may score based on the submitter's expertise. The scoring unit may also score based on the submitter's job title. The scoring unit may also score based on the submitter's past scoring history. This allows the scoring to take into account the attribute information of the term submitter. Some or all of the above processing in the scoring unit may be performed using AI or not.

[0101] The scoring unit estimates the user's emotions and adjusts the order in which the scoring results are displayed based on the estimated emotions. For example, if the user is nervous, the scoring unit provides a simple and highly visible display method. If the user is relaxed, the scoring unit can also provide a display method that includes detailed information. If the user is in a hurry, the scoring unit can also provide a concise display method. This allows the order in which the scoring results are displayed to be adjusted according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0102] The scoring unit performs scoring while considering the geographical distribution of terms. For example, the scoring unit may give higher scores to terms that are frequently used in a particular region. The scoring unit may also give higher scores to terms that are used over a wide geographical area. The scoring unit may also perform scoring while considering the frequency of use of terms in each region. This allows for scoring that takes into account the geographical distribution of terms. Some or all of the above processing in the scoring unit may be performed using AI or not.

[0103] The scoring unit improves the accuracy of scoring by referring to relevant literature for terms during the scoring process. For example, the scoring unit automatically searches for relevant literature for terms and uses it as a reference for scoring. The scoring unit may also use relevant literature provided by the submitter. The scoring unit can also check the relevant literature for terms during the scoring process. This allows the scoring unit to improve the accuracy of scoring by referring to relevant literature for terms. Some or all of the above processes in the scoring unit may be performed using AI or not.

[0104] The user unit estimates the user's emotions and adjusts how the glossary is used based on the estimated emotions. For example, if the user is stressed, the user unit provides the glossary with a simple interface. If the user is relaxed, the user unit can also provide the glossary with an interface containing detailed information. If the user is in a hurry, the user unit can also provide the glossary with a quickly accessible interface. This allows the user to adjust how the glossary is used according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0105] The user unit selects the optimal usage method by referring to the term usage history when the term is used. For example, the user unit prioritizes displaying terms that have been used frequently in the past. The user unit can also suggest relevant terms based on past usage history. The user unit can also analyze past usage history and select the optimal usage method. This allows the user unit to select the optimal usage method by referring to the term usage history. Some or all of the above processing in the user unit may be performed using AI or not.

[0106] The utilization unit applies different utilization algorithms depending on the category of the term at the time of utilization. For example, the utilization unit may apply a specialized utilization algorithm to technical terms. The utilization unit may also apply a simplified utilization algorithm to general terms. The utilization unit may also apply an adaptive utilization algorithm to terms in new categories. This allows different utilization algorithms to be applied depending on the category of the term. Some or all of the processing described above in the utilization unit may be performed using AI or not using AI.

[0107] The user unit estimates the user's emotions and determines the priority of the glossary based on the estimated emotions. For example, if the user is nervous, the user unit will prioritize displaying simple and easily recognizable terms. If the user is relaxed, the user unit may also prioritize displaying terms containing detailed information. If the user is in a hurry, the user unit may also prioritize displaying terms that get straight to the point. This allows the system to determine the priority of the glossary according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] The user unit selects the optimal usage method when a term is used, taking into account its geographical location. For example, if the user is in a specific region, the user unit will prioritize displaying terms related to that region. If the user is traveling, the user unit may also prioritize displaying terms related to the travel destination. If the user is participating in a specific event, the user unit may also prioritize displaying terms related to that event. This allows the user unit to select the optimal usage method, taking into account the geographical location of the term. Some or all of the processing described above in the user unit may be performed using AI, or not.

[0109] The user unit improves the accuracy of its use by referring to related literature for the term during use. For example, the user unit automatically searches for related literature for the term and uses it as a reference. The user unit may also receive related literature for the term from the submitter. The user unit can also check related literature for the term during use. This allows for improved accuracy of use by referring to related literature for the term. Some or all of the above processing in the user unit may be performed using AI or not.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The extraction unit can estimate the user's emotions and adjust the term extraction method based on the estimated emotions. For example, if the user is stressed, the extraction unit can prioritize extracting terms that reduce stress in the conversation. If the user is relaxed, the extraction unit can extract terms that maintain relaxation in the conversation. Furthermore, if the user is excited, the extraction unit can extract terms that increase excitement in the conversation. In this way, the term extraction method can be adjusted according to the user's emotions.

[0112] The approval unit can estimate the user's emotions during the approval process and adjust the approval priority based on those emotions. For example, if the user is stressed, the approval unit can simplify the approval process and approve quickly. If the user is relaxed, the approval unit can provide a detailed approval process and approve carefully. Furthermore, if the user is in a hurry, the approval unit can prioritize approving only the most important terms. This allows the approval priority to be adjusted according to the user's emotions.

[0113] The scoring unit can estimate the user's emotions and adjust the scoring criteria based on those emotions. For example, if the user is relaxed, the scoring unit can score based on a relaxed standard. If the user is in a hurry, the scoring unit can score based on a fast standard. Furthermore, if the user is excited, the scoring unit can score based on a visually stimulating standard. This allows the scoring criteria to be adjusted according to the user's emotions.

[0114] The update unit can estimate the user's emotions and adjust the timing of glossary updates based on those emotions. For example, if the user is stressed, the update unit can delay updates. Conversely, if the user is relaxed, the update unit can perform updates immediately. Furthermore, if the user is in a hurry, the update unit can prioritize updating only the most important terms. This allows the timing of glossary updates to be adjusted according to the user's emotions.

[0115] The user interface can estimate the user's emotions and adjust how the glossary is used based on those emotions. For example, if the user is stressed, the interface can provide the glossary with a simple interface. If the user is relaxed, the interface can provide the glossary with a more detailed interface. Furthermore, if the user is in a hurry, the interface can provide the glossary with a quickly accessible interface. This allows the user to adjust how the glossary is used according to their emotions.

[0116] The extraction unit can prioritize the extraction of highly relevant terms by considering the user's geographical location. For example, if the user is in a specific region, it can prioritize the extraction of terms related to that region. Similarly, if the user is traveling, it can prioritize the extraction of terms related to their travel destination. Furthermore, if the user is participating in a specific event, it can prioritize the extraction of terms related to that event. This allows for the prioritization of highly relevant terms by considering the user's geographical location.

[0117] The approval department can improve the accuracy of approvals by referring to the usage history of terms during the approval process. For example, it can refer to the usage history of terms that have been previously approved. It can also refer to the usage history of terms that have been previously put on hold. Furthermore, it can refer to the usage history of terms that have been previously rejected. This allows for improved approval accuracy by referring to the usage history of terms.

[0118] The scoring unit can improve the accuracy of scoring by considering the interrelationships between terms during the scoring process. For example, it can comprehensively evaluate the scores of related terms. It can also analyze the interrelationships between terms and reflect them in the scoring. Furthermore, it can perform scoring while considering the context of the terms. This allows for improved scoring accuracy by taking into account the interrelationships between terms.

[0119] The update unit can apply different update algorithms depending on the category of the term during the update process. For example, a specialized update algorithm can be applied to technical terms, while a simpler algorithm can be applied to general terms. Furthermore, an adaptive update algorithm can be applied to terms in new categories. This allows for the application of different update algorithms depending on the category of the term.

[0120] The user unit can improve the accuracy of its use by referring to related literature for the term during use. For example, it can automatically search for related literature for the term and use it as a reference. Furthermore, the submitter can provide related literature for the term. In addition, users can check related literature for the term during use. This allows for improved accuracy of use by referring to related literature.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The extraction unit extracts terminology. The extraction unit extracts terminology from, for example, online video conferences, instant messages, and posts. The extraction unit uses AI to analyze conversations and posts and identify specialized terminology and frequently used terms. For example, it extracts specialized terminology used during meetings or terms frequently used in chats. Step 2: The approval department approves the terms extracted by the extraction department. The approval department, for example, has experts review the extracted terms and evaluate their accuracy and appropriateness. The approval department can also use AI to evaluate the extracted terms. Step 3: The Update Department adds the terms approved by the Approval Department to the glossary. The Update Department adds the terms according to specific procedures and criteria for adding approved terms to the glossary, for example. Step 4: The scoring unit uses the term "approval pending" based on the score assigned by the approval unit. For example, if a term "approval pending" has a high score, the scoring unit will temporarily add it to the term dictionary. Step 5: The user unit utilizes the glossary updated by the update unit. For example, the user unit refers to the glossary so that the AI ​​tool can recognize specialized terminology.

[0123] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0126] Each of the multiple elements described above, including the extraction unit, approval unit, update unit, scoring unit, and utilization unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the extraction unit is implemented by the processor 46 of the smart device 14 and extracts terms from online video conferences and instant messages. The approval unit is implemented by the identification processing unit 290 of the data processing unit 12 and evaluates the accuracy and appropriateness of the extracted terms. The update unit is implemented by the identification processing unit 290 of the data processing unit 12 and adds approved terms to the term dictionary. The scoring unit is implemented by the identification processing unit 290 of the data processing unit 12 and utilizes terms pending approval based on their scores. The utilization unit is implemented by the control unit 46A of the smart device 14 and allows the AI ​​tool to recognize specialized terminology by referring to the updated term dictionary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 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.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the extraction unit, approval unit, update unit, scoring unit, and utilization unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the extraction unit is implemented by the processor 46 of the smart glasses 214 and extracts terms from online video conferences and instant messages. The approval unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and evaluates the accuracy and appropriateness of the extracted terms. The update unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and adds approved terms to the term dictionary. The scoring unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and utilizes terms pending approval based on their scores. The utilization unit is implemented, for example, by the control unit 46A of the smart glasses 214 and allows the AI ​​tool to recognize specialized terminology by referring to the updated term dictionary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the extraction unit, approval unit, update unit, scoring unit, and utilization unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the extraction unit is implemented by the processor 46 of the headset terminal 314 and extracts terms from online video conferences and instant messages. The approval unit is implemented by the identification processing unit 290 of the data processing unit 12 and evaluates the accuracy and appropriateness of the extracted terms. The update unit is implemented by the identification processing unit 290 of the data processing unit 12 and adds approved terms to the term dictionary. The scoring unit is implemented by the identification processing unit 290 of the data processing unit 12 and utilizes terms pending approval based on their scores. The utilization unit is implemented by the control unit 46A of the headset terminal 314 and allows the AI ​​tool to recognize specialized terminology by referring to the updated term dictionary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 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.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the extraction unit, approval unit, update unit, scoring unit, and utilization unit, is implemented, for example, in at least one of the robot 414 and the data processing unit 12. For example, the extraction unit is implemented by the processor 46 of the robot 414 and extracts terms from online video conferences and instant messages. The approval unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and evaluates the accuracy and appropriateness of the extracted terms. The update unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and adds approved terms to the term dictionary. The scoring unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and utilizes terms pending approval based on their scores. The utilization unit is implemented, for example, by the control unit 46A of the robot 414 and allows the AI ​​tool to recognize technical terms by referring to the updated term dictionary. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0176] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] 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.

[0186] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) An extraction unit that extracts terms, An approval unit that approves the terms extracted by the extraction unit, An update unit that adds terms approved by the aforementioned approval unit to the term dictionary, The aforementioned approval unit uses the term "approval pending" based on a score, and the scoring unit uses this term based on a score. The system includes a user unit that utilizes the terminology dictionary updated by the update unit. A system characterized by the following features. (Note 2) The aforementioned approval unit, This process includes having experts review the extracted terms. The system described in Appendix 1, characterized by the features described herein. (Note 3) The scoring unit is, Use the term "approval pending" temporarily based on a score. The system described in Appendix 1, characterized by the features described herein. (Note 4) The extraction unit is Extract terminology from online video conferences, instant messages, and posts. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned utilization unit is, The AI ​​tool recognizes technical terms by referring to a glossary. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned update unit is Add approved terms to the glossary. The system described in Appendix 1, characterized by the features described herein. (Note 7) The extraction unit is It estimates the user's emotions and adjusts the timing of term extraction based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The extraction unit is Analyze the context of conversations and posts, and prioritize extracting terms related to specific topics. The system described in Appendix 1, characterized by the features described herein. (Note 9) The extraction unit is During extraction, the extraction priority is determined based on the frequency and importance of the terms used. The system described in Appendix 1, characterized by the features described herein. (Note 10) The extraction unit is It estimates the user's emotions and determines the priority of terms to extract based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The extraction unit is During extraction, the system prioritizes extracting highly relevant terms by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The extraction unit is During extraction, the system analyzes the user's social media activity and extracts relevant terms. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned approval unit, It estimates the user's emotions and adjusts the priority of the approval process based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned approval unit, During the approval process, the criteria for evaluating the accuracy and appropriateness of terminology are dynamically changed. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned approval unit, During the approval process, refer to the usage history of terms to improve the accuracy of approvals. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned approval unit, It estimates the user's sentiment and adjusts how approvals are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned approval unit, When approving a term, the priority of approval is determined by considering the attribute information of the term submitter. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned approval unit, During the approval process, we improve the accuracy of the approval by referring to relevant literature for the terminology. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned update unit is It estimates user sentiment and adjusts the timing of glossary updates based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned update unit is During updates, the priority of updates is determined based on the importance of the terms. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned update unit is When updating, different update algorithms are applied depending on the category of the term. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned update unit is It estimates the user's sentiment and adjusts how updates are displayed based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned update unit is When updating, the priority of updates will be determined based on when the terms were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned update unit is During updates, the order of updates will be adjusted based on the relevance of the terms. The system described in Appendix 1, characterized by the features described herein. (Note 25) The scoring unit is, The system estimates the user's emotions and adjusts the scoring criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The scoring unit is, When scoring, consider the interrelationships between terms to improve scoring accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 27) The scoring unit is, When scoring, the attribute information of the term submitter will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 28) The scoring unit is, It estimates the user's emotions and adjusts the order in which the scoring results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The scoring unit is, When scoring, the geographical distribution of terms should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 30) The scoring unit is, When scoring, refer to relevant literature for terms to improve scoring accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned utilization unit is, It estimates the user's emotions and adjusts how the glossary is used based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned utilization unit is, When using the service, refer to the usage history of the term to select the most appropriate usage method. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned utilization unit is, When using the term, different usage algorithms are applied depending on the term category. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned utilization unit is, It estimates the user's emotions and determines the priority of using the glossary based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned utilization unit is, When using the term, the optimal method of use will be selected, taking into account the geographical location information of the term. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned utilization unit is, When using the information, refer to related literature for terminology to improve accuracy. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An extraction unit that extracts terms, An approval unit that approves the terms extracted by the extraction unit, An update unit that adds terms approved by the aforementioned approval unit to the term dictionary, The aforementioned approval unit uses the term "approval pending" based on a score, and the scoring unit uses this term based on a score. The system includes a user unit that utilizes the terminology dictionary updated by the update unit. A system characterized by the following features.

2. The aforementioned approval unit, This process includes having experts review the extracted terms. The system according to feature 1.

3. The scoring unit is, Use the term "approval pending" temporarily based on a score. The system according to feature 1.

4. The extraction unit is Extract terminology from online video conferences, instant messages, and posts. The system according to feature 1.

5. The aforementioned utilization unit is, The AI ​​tool recognizes technical terms by referring to a glossary. The system according to feature 1.

6. The aforementioned update unit is Add approved terms to the glossary. The system according to feature 1.

7. The extraction unit is It estimates the user's emotions and adjusts the timing of term extraction based on the estimated user emotions. The system according to feature 1.

8. The extraction unit is Analyze the context of conversations and posts, and prioritize extracting terms related to specific topics. The system according to feature 1.

9. The extraction unit is During extraction, the extraction priority is determined based on the frequency and importance of the terms used. The system according to feature 1.

Images