system

Abstract

The system according to this embodiment aims to efficiently and accurately manage multilingual meeting content. [Solution] The system according to the embodiment comprises a recording unit, a conversion unit, a translation unit, an extraction unit, and a management unit. The recording unit automatically records the content of a meeting. The conversion unit converts the audio data recorded by the recording unit into text. The translation unit translates the text converted by the conversion unit. The extraction unit extracts key points from the text translated by the translation unit. The management unit manages the key points extracted by the extraction unit.

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques have had the problem that it is difficult to efficiently and accurately manage multilingual conference content.

[0005] The system according to this embodiment aims to efficiently and accurately manage multilingual meeting content. [Means for solving the problem]

[0006] The system according to the embodiment includes a recording unit, a conversion unit, a translation unit, an extraction unit, and a management unit. The recording unit automatically records the contents of a meeting. The conversion unit converts the audio data recorded by the recording unit into text. The translation unit translates the text converted by the conversion unit. The extraction unit extracts key points from the text translated by the translation unit. The management unit manages the key points extracted by the extraction unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently and accurately manage multilingual conference content. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The business negotiation management system according to an embodiment of the present invention is a system for improving the challenges faced by companies conducting overseas transactions and business expansion in multilingual business negotiations. This business negotiation management system automatically records, translates, and extracts key points from meeting content, thereby improving the efficiency and accuracy of business negotiations. First, when a business negotiation begins, the system automatically records the meeting content. The recorded audio data is translated in real time. For example, if a business negotiation conducted in the first language is to be translated into the second language, the system converts the audio data into text and translates that text. The translated text is provided to the business negotiation participants in real time. Next, key points are extracted from the translated text. The system uses natural language processing technology to automatically extract important points and decisions from the business negotiation. For example, agreed-upon contract terms and the date of the next meeting are extracted as key points. The extracted key points are provided to the business negotiation participants, facilitating the smooth progress of the negotiation. This system improves the efficiency and accuracy of business negotiations. Because the content of the business negotiation is automatically recorded and translated in real time, smooth communication is possible, transcending language barriers. Furthermore, because key points are automatically extracted, important points in business negotiations are not overlooked, allowing for efficient negotiations. In addition, this system also includes a function for managing the history of business negotiations. Recorded audio data, translated text, and extracted key points are stored within the system and can be referenced later. This allows for easy review of past negotiation content and understanding of the progress of negotiations. Thus, the business negotiation management system of this invention is a useful tool for companies engaged in overseas transactions or business expansion, enabling them to improve the efficiency and accuracy of their negotiations. In this way, the business negotiation management system can achieve improved efficiency and accuracy in business negotiations.

[0029] The business negotiation management system according to this embodiment comprises a recording unit, a conversion unit, a translation unit, an extraction unit, and a management unit. The recording unit automatically records the meeting content at the start of the business negotiation. The recording unit can, for example, use a schedule linkage function to detect the start of a business negotiation. The recording unit can also detect the start of a business negotiation using voice detection technology. Furthermore, the recording unit can also detect the start of a business negotiation through manual operation. The conversion unit converts the recorded audio data into text in real time. The conversion unit converts the audio data into text using, for example, speech recognition technology. Speech recognition technology analyzes the audio data using natural language processing technology and converts it into text data. The translation unit translates the converted text from the first language to the second language. The translation unit translates the text using, for example, machine translation technology. Machine translation technology performs highly accurate translation using neural network translation technology. The extraction unit automatically extracts important points and decisions from the translated text. The extraction unit extracts important points using, for example, keyword extraction technology. Keyword extraction technology extracts frequently occurring keywords from text data and identifies key points. The management unit stores the recorded audio data, translated text, and extracted key points within the system for later reference. The management unit stores the data using, for example, a database management system. The database management system has access control functions and allows setting the data retention period. As a result, the sales negotiation management system according to this embodiment can achieve increased efficiency and improved accuracy in sales negotiations.

[0030] The recording unit can automatically record the contents of a meeting as soon as a business meeting begins. The recording unit can use a schedule linking function, for example, to detect the start of a business meeting. The schedule linking function allows the start time of the business meeting to be set in advance and recording to start automatically at that time. The recording unit can also detect the start of a business meeting using voice detection technology. Voice detection technology detects the voice generated at the start of a business meeting and automatically starts recording. Furthermore, the recording unit can also detect the start of a business meeting through manual operation. Manual operation starts recording when the user presses the recording start button at the start of a business meeting. This allows recording to start automatically as soon as the business meeting begins, so that important information is not missed.

[0031] The conversion unit can convert recorded voice data into text in real time. The conversion unit converts voice data into text using, for example, voice recognition technology. Voice recognition technology analyzes voice data using natural language processing technology and converts it into text data. For example, voice recognition technology analyzes voice data in real time and converts it into text data. The conversion unit can also support multiple languages ​​using voice recognition technology. For example, the conversion unit can convert voice data in multiple languages, such as English, Japanese, and French, into text data. Furthermore, the conversion unit has a function of learning the voice characteristics of specific speakers using voice recognition technology. For example, the conversion unit accumulates voice data of participants in a business meeting and improves the accuracy of voice recognition by learning the voice characteristics of each participant. This allows the content to be checked instantly by converting voice data into text in real time.

[0032] The translation unit can translate converted text from a first language to a second language. The translation unit translates text using, for example, machine translation technology. Machine translation technology uses neural network translation technology to achieve high accuracy. For example, machine translation technology analyzes text written in a first language and translates it into a second language. Furthermore, the translation unit can handle multiple language pairs. For example, it can translate between multiple language pairs, such as Japanese to English, or English to Chinese. In addition, the translation unit has a dictionary function to handle specialized and industry-specific terminology. For example, the translation unit can accurately translate specialized terms using a specific industry-specific dictionary. This allows for the resolution of challenges in multilingual business negotiations by translating from a first language to a second language.

[0033] The extraction unit can automatically extract key points and decisions from translated text. For example, it can use keyword extraction technology to extract key points. Keyword extraction technology extracts frequently occurring keywords from text data to identify key points. The extraction unit can also extract the essentials of a deal using a summarization algorithm. The summarization algorithm analyzes text data and summarizes and extracts important information. Furthermore, the extraction unit can also extract key points of a deal using contextual analysis technology. Contextual analysis technology analyzes the context of text data to identify key points. This enables efficient deal management by automatically extracting key points and decisions from a deal.

[0034] The management department can store recorded audio data, translated text, and extracted key points within the system for later reference. For example, the management department can use a database management system to store the data. The database management system includes access control features and allows for setting data retention periods. The management department also has a search function, allowing for easy searching of stored data. For example, the management department can use a keyword search function to find data containing specific keywords. Furthermore, the management department has a tagging function, allowing for the classification of data by tagging it. For example, the management department can tag data by type of deal or date. This allows for the management of deal history and subsequent reference to understand the progress of deals.

[0035] The recording unit can automatically adjust the sound quality of the recording according to the progress of the business negotiation. For example, the recording unit can use voice analysis technology to detect the progress of the business negotiation. Voice analysis technology analyzes the progress of the business negotiation and automatically adjusts the sound quality of the recording. The recording unit can also adjust the sound quality of the recording using noise cancellation technology. Noise cancellation technology detects and filters out background noise during the business negotiation in real time to record clear audio. Furthermore, the recording unit can also adjust the sound quality of the recording using volume adjustment technology. Volume adjustment technology automatically adjusts the volume according to the progress of the business negotiation, ensuring that important statements are recorded clearly. In this way, by adjusting the sound quality of the recording according to the progress of the business negotiation, important information can be recorded clearly. For example, in the initial stages of the business negotiation, a wide range of sounds can be recorded to capture the overall atmosphere. When the business negotiation moves on to important topics, the sound quality can be improved for a clearer recording. Furthermore, near the end of the business negotiation, a wide range of sounds can be recorded again to capture the overall summary.

[0036] The recording unit can automatically filter background noise during a business meeting to obtain clear audio data during recording. The recording unit filters background noise, for example, using noise reduction technology. The noise reduction technology detects noise during a business meeting in real time and filters it to record clear audio. The recording unit can also remove background noise using a filtering algorithm. The filtering algorithm emphasizes only the voices of the business meeting participants and suppresses background noise. The recording unit also has a function to automatically remove sudden noise. For example, the recording unit can detect and remove sudden noise that occurs during a business meeting in real time. This allows clear audio data to be obtained by filtering background noise. For example, the recording unit can detect and filter noise during a business meeting in real time to record clear audio. The noise reduction technology can also emphasize only the voices of the business meeting participants and suppress background noise. The recording unit can also automatically remove sudden noise that occurs during a business meeting.

[0037] The recording unit analyzes the frequency of speech made by business meeting participants during recording, and can prioritize recording of important speech. The recording unit, for example, analyzes the frequency of speech made by business meeting participants in real time. The analysis of speech frequency is performed based on the number of times a business meeting participant speaks and the duration of the speech. The recording unit can also analyze the content of speech and prioritize recording of speech containing important keywords. The analysis of speech content is performed using text analysis technology. Furthermore, the recording unit can also determine recording priorities taking into account the length of speech. The length of speech is evaluated based on the duration of speech made by business meeting participants. In this way, by analyzing the frequency of speech, important speech can be prioritized for recording. For example, the recording unit can analyze the frequency of speech made by business meeting participants in real time, and prioritize recording of frequently spoken speech. The recording unit can also analyze the content of speech made by business meeting participants, and prioritize recording of speech containing important keywords. Furthermore, the recording unit can consider the length of speech made by business meeting participants and prioritize recording of long speech.

[0038] The recording unit can optimize recording settings by considering the location information of the business negotiation participants during recording. For example, the recording unit can automatically set the optimal microphone placement based on the location information of the business negotiation participants. Location information is obtained using GPS data or indoor location information. Furthermore, if the business negotiation participants move, the recording unit can update the location information in real time and adjust the recording settings accordingly. Real-time updates of location information are performed using technology to track the movement of business negotiation participants. In addition, the recording unit can record while considering the direction of sound. The direction of sound is evaluated based on the location information of the business negotiation participants. This makes it possible to optimize recording settings by considering location information. For example, it can automatically set the optimal microphone placement based on the location information of the business negotiation participants. Furthermore, if the business negotiation participants move, it can update the location information in real time and adjust the recording settings accordingly. Furthermore, it can record while considering the direction of sound based on the location information of the business negotiation participants.

[0039] The conversion unit can automatically optimize the conversion algorithm according to the noise level of the audio data. For example, the conversion unit measures the noise level of the audio data in real time. This noise level measurement is performed using speech analysis technology. The conversion unit can also reduce the noise level using noise reduction technology. Noise reduction technology detects and filters noise in the audio data in real time to produce clear audio. Furthermore, the conversion unit can automatically adjust the parameters of the conversion algorithm according to the noise level. This parameter adjustment is based on the noise level of the audio data. This allows for highly accurate text conversion by optimizing the conversion algorithm according to the noise level. For example, if the noise level of the audio data is high, noise reduction is enhanced for text conversion. If the noise level of the audio data is low, the normal conversion algorithm is applied. Furthermore, the parameters of the conversion algorithm can be automatically adjusted according to the noise level of the audio data.

[0040] The conversion unit can improve accuracy by applying different conversion algorithms to each speaker in the audio data. For example, the conversion unit analyzes the voice characteristics of each speaker in the audio data. This voice characteristic analysis is performed using speech analysis technology. Furthermore, the conversion unit can adjust the conversion algorithm to take into account the different accents and pronunciations of each speaker. This consideration of accents and pronunciations is based on the analysis results of the audio data. In addition, the conversion unit can apply a conversion algorithm that takes into account the different speaking speeds of each speaker. This consideration of speaking speed is based on the analysis results of the audio data. This enables highly accurate text conversion by applying the optimal conversion algorithm for each speaker. For example, the conversion unit analyzes the voice characteristics of each speaker in the audio data and applies the optimal conversion algorithm. Furthermore, it can adjust the conversion algorithm to take into account the different accents and pronunciations of each speaker in the audio data. Furthermore, it can apply a conversion algorithm that takes into account the different speaking speeds of each speaker in the audio data.

[0041] The conversion unit can determine the conversion priority based on the recording time of the audio data. For example, the conversion unit determines the conversion priority based on the recording time of the audio data. The recording time is obtained using a timestamp attached to the audio data. The conversion unit can also prioritize the transcription of important statements based on the recording time. The priority of important statements is determined based on the recording time and the importance of the statement's content. Furthermore, the conversion unit can also adjust the order of text transcription based on the recording time. The order of text transcription is performed in a logical order based on the recording time. This allows important statements to be prioritized for transcription by determining the conversion priority based on the recording time. For example, text transcription can be performed in order of earliest recording time. Alternatively, text transcription can be performed in order of latest recording time. Furthermore, important statements can be prioritized for text transcription based on the recording time.

[0042] The conversion unit can adjust the order of the converted text based on the content of the audio data. For example, the conversion unit can analyze the content of the audio data and transcribe important statements first. The content analysis of the audio data is performed using natural language processing techniques. The conversion unit can also transcribe related statements together. This grouping of related statements is based on the content analysis results of the audio data. Furthermore, the conversion unit can transcribe text in a logical order. The logical order is determined based on the content analysis results of the audio data. This allows for transcription in a logical order by adjusting the text order based on the content of the audio data. For example, it can analyze the content of the audio data and transcribe important statements first. It can also transcribe related statements together based on the content of the audio data. Furthermore, it can analyze the content of the audio data and transcribe text in a logical order.

[0043] The translation unit can optimize its translation algorithm based on the frequency of technical terms during translation. For example, the unit measures the frequency of technical terms in real time. This measurement is performed using text analysis techniques. The unit can also improve translation accuracy by using a technical term dictionary. This dictionary contains specific industry-specific terminology and is referenced during translation. Furthermore, the unit can automatically adjust the parameters of the translation algorithm based on the frequency of technical terms. This parameter adjustment is based on the frequency of technical terms. This improves translation accuracy by optimizing the translation algorithm according to the frequency of technical terms. For example, if there are many technical terms, the technical term dictionary is used to improve translation accuracy. If there are few technical terms, the standard translation algorithm is applied. Furthermore, the parameters of the translation algorithm can be automatically adjusted based on the frequency of technical terms.

[0044] The translation unit can apply different translation algorithms depending on the context of the business negotiations during translation. The translation unit, for example, analyzes the context of the business negotiations and selects an appropriate translation algorithm. The context analysis is performed using natural language processing technology. The translation unit can also appropriately translate technical terms and industry jargon depending on the context of the business negotiations. The translation of technical terms and industry jargon is performed based on the results of the context analysis. Furthermore, the translation unit can also perform translations that include natural expressions by taking the context of the business negotiations into consideration. The translation of natural expressions is performed based on the results of the context analysis. This makes it possible to perform translations that include natural expressions by applying an appropriate translation algorithm depending on the context of the business negotiations. For example, the translation unit analyzes the context of the business negotiations and selects an appropriate translation algorithm. Furthermore, the translation unit can appropriately translate technical terms and industry jargon depending on the context of the business negotiations. Furthermore, the translation unit can perform translations that include natural expressions by taking the context of the business negotiations into consideration.

[0045] The translation department can determine the priority of translations based on the progress of the business negotiations during translation. The translation department, for example, analyzes the progress of the business negotiations and prioritizes the translation of important remarks. The analysis of the progress of the business negotiations is performed using natural language processing technology. The translation department can also prioritize translations when important business negotiations begin. The priority of important topics is determined based on the progress of the business negotiations. Furthermore, the translation department can also prioritize translation of an overall summary as the business negotiations draw to a close. The priority of the overall summary is determined based on the progress of the business negotiations. In this way, by determining the priority of translations based on the progress of the business negotiations, important remarks can be prioritized for translation. For example, translations are prioritized when important business negotiations begin. Furthermore, important remarks can be prioritized for translation depending on the progress of the business negotiations. Furthermore, the translation department can prioritize translation of an overall summary as the business negotiations draw to a close.

[0046] The translation department can improve the accuracy of translations by referring to relevant documents related to business negotiations during the translation process. For example, the translation department can automatically refer to relevant documents related to business negotiations. This referencing is done using a document database. Furthermore, the translation department can improve the accuracy of translations of technical and industry-specific terms based on these documents. Translations of technical and industry-specific terms are based on the content of the relevant documents. In addition, the translation department can perform contextually appropriate translations based on the relevant documents. Contextually appropriate translations are also based on the content of the relevant documents. This means that by referring to relevant documents, the accuracy of translations of technical and industry-specific terms is improved. For example, it can automatically refer to relevant documents related to business negotiations to improve the accuracy of translations of technical and industry-specific terms. It can also perform contextually appropriate translations based on relevant documents related to business negotiations. Furthermore, it can perform translations that include natural expressions by referring to relevant documents related to business negotiations.

[0047] The extraction unit can optimize its extraction algorithm according to the importance of the business opportunity when extracting key points. For example, the extraction unit can use text analysis technology to evaluate the importance of the business opportunity. Text analysis technology analyzes the content of the business opportunity and evaluates its importance. The extraction unit can also automatically adjust the parameters of the extraction algorithm according to the importance of the business opportunity. The parameter adjustment of the extraction algorithm is performed based on the importance of the business opportunity. Furthermore, the extraction unit can also apply an algorithm that extracts detailed key points according to the importance of the business opportunity. The extraction of detailed key points is performed based on the importance of the business opportunity. This allows for the accurate extraction of important key points by optimizing the extraction algorithm according to the importance of the business opportunity. For example, if the importance of the business opportunity is high, an algorithm that extracts detailed key points is applied. If the importance of the business opportunity is low, an algorithm that extracts concise key points is applied. Furthermore, the parameters of the extraction algorithm can be automatically adjusted according to the importance of the business opportunity.

[0048] The extraction unit can apply different extraction methods to each deal category when extracting key points. For example, the extraction unit can use text analysis technology to identify the deal category. Text analysis technology analyzes the content of the deal and identifies the category. The extraction unit can also extract key points based on different keywords for each deal category. Keyword extraction is performed based on the deal category. Furthermore, the extraction unit can highlight and extract important points according to the deal category. The highlighting of important points is performed based on the deal category. This allows for accurate extraction of important points by applying the appropriate extraction method according to the deal category. For example, the appropriate extraction method is selected according to the deal category. Furthermore, key points can be extracted based on different keywords for each deal category. Furthermore, important points can be highlighted and extracted according to the deal category.

[0049] The extraction unit can prioritize key points based on the progress of the business negotiation. For example, the extraction unit analyzes the progress of the business negotiation and prioritizes extracting important statements as key points. The analysis of the progress of the business negotiation is performed using natural language processing technology. The extraction unit can also prioritize extracting key points when the business negotiation reaches an important agenda item. The priority of important agenda items is determined based on the progress of the business negotiation. Furthermore, the extraction unit can also prioritize extracting an overall summary as key points near the end of the business negotiation. The priority of the overall summary is determined based on the progress of the business negotiation. In this way, by prioritizing key points based on the progress of the business negotiation, important statements can be prioritized for extraction. For example, when the business negotiation reaches an important agenda item, key points are prioritized for extraction. Furthermore, important statements can be prioritized for extraction as key points depending on the progress of the business negotiation. Furthermore, near the end of the business negotiation, an overall summary can be prioritized for extraction as key points.

[0050] The extraction unit can improve the accuracy of its extraction by referencing relevant data from the business negotiation when extracting key points. For example, the extraction unit automatically references relevant data from the business negotiation. This reference is performed using a database. Furthermore, the extraction unit can extract appropriate key points based on the relevant data, taking into account the context. This contextual extraction is based on the content of the relevant data. Additionally, the extraction unit can extract key points containing natural expressions by referencing the relevant data. This extraction of natural expressions is based on the content of the relevant data. This allows for the accurate extraction of important points by referencing relevant data. For example, it can automatically reference relevant data from the business negotiation and accurately extract important points. It can also extract appropriate key points based on relevant data from the business negotiation, taking into account the context. Furthermore, it can extract key points containing natural expressions by referencing relevant data from the business negotiation.

[0051] The management department can automatically set data retention periods based on the importance of each deal during data management. For example, the management department can use text analysis technology to assess the importance of each deal. Text analysis technology analyzes the content of the deal and assesses its importance. Furthermore, the management department can automatically set data retention periods based on the importance of each deal. The data retention period is set based on the importance of the deal. In addition, the management department can also set data retention periods based on legal requirements. Legal requirements are determined based on the content of the deal and industry regulations. This allows for proper management of important data by setting data retention periods according to the importance of each deal. For example, a long data retention period is set for highly important deals, and a short data retention period is set for less important deals. Furthermore, the data retention period can be automatically adjusted according to the importance of each deal.

[0052] The management department can apply different management methods to each opportunity category when managing data. For example, the management department can use text analysis technology to identify the opportunity category. Text analysis technology analyzes the content of the opportunity and identifies the category. Furthermore, the management department can apply different data storage methods to each opportunity category. The data storage method is determined based on the opportunity category. In addition, the management department can highlight and manage important data according to the opportunity category. This highlighting of important data is based on the opportunity category. This allows for accurate management of important data by applying appropriate management methods according to the opportunity category. For example, an appropriate data management method can be selected according to the opportunity category. Furthermore, different data storage methods can be applied to each opportunity category. In addition, important data can be highlighted and managed according to the opportunity category.

[0053] The management department can prioritize data based on the progress of a sales negotiation. For example, the management department can analyze the progress of a sales negotiation and prioritize the management of important data. The analysis of the progress of a sales negotiation is performed using natural language processing technology. Furthermore, the management department can prioritize the management of data when a sales negotiation reaches an important agenda item. The priority of important agenda items is determined based on the progress of the sales negotiation. In addition, the management department can prioritize the management of an overall summary as data when the sales negotiation is nearing its end. The priority of the overall summary is determined based on the progress of the sales negotiation. This allows for the priority management of important data by prioritizing data based on the progress of the sales negotiation. For example, data can be prioritized when a sales negotiation reaches an important agenda item. Furthermore, important data can be prioritized according to the progress of the sales negotiation. Furthermore, an overall summary can be prioritized as data when the sales negotiation is nearing its end.

[0054] The management unit can improve the accuracy of management by referring to the related data of business negotiations when managing data. The management unit, for example, automatically refers to the related data of business negotiations. The related data is referred to using a database. The management unit can also perform appropriate data management according to the context based on the related data. Data management according to the context is performed based on the content of the related data. Furthermore, the management unit can also perform data management including natural expressions by referring to the related data. Data management with natural expressions is performed based on the content of the related data. This allows important data to be managed accurately by referring to the related data. For example, the related data of business negotiations can be automatically referred to and important data can be managed accurately. Furthermore, appropriate data management according to the context can be performed based on the related data of business negotiations. Furthermore, data management including natural expressions can be performed by referring to the related data of business negotiations.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The recording unit can analyze the speech of business meeting participants in real time and automatically adjust the sound quality of the recording if certain keywords are included. For example, it can increase the sound quality when important keywords such as "contract" or "agreement" are included in speech. The recording unit can also analyze the tone and speed of the speech of business meeting participants and adjust the sound quality when emotions such as tension or excitement increase. Furthermore, the recording unit can adjust the sound quality of the recording according to the progress of the business meeting and increase the sound quality when important topics are discussed.

[0057] The conversion unit can analyze the speech content of business meeting participants in real time and automatically optimize the conversion algorithm when specific keywords are included. For example, it optimizes the conversion algorithm when important keywords such as "contract" or "agreement" are included in speech. The conversion unit can also analyze the tone and speed of speech of business meeting participants and adjust the conversion algorithm when emotions such as tension or excitement increase. Furthermore, the conversion unit can adjust the conversion algorithm according to the progress of the business meeting and optimize it when important topics are discussed.

[0058] The translation department can analyze the speech of business meeting participants in real time and automatically optimize the translation algorithm when specific keywords are included. For example, the translation algorithm is optimized when important keywords such as "contract" or "agreement" are included in speech. The translation department can also analyze the tone and speed of speech of business meeting participants and adjust the translation algorithm when emotions such as tension or excitement increase. Furthermore, the translation department can adjust the translation algorithm according to the progress of the business meeting and optimize it when important topics are discussed.

[0059] The extraction unit can analyze the content of speeches made by participants in a business meeting in real time and automatically optimize the key point extraction algorithm when specific keywords are included. For example, the extraction unit optimizes the key point extraction algorithm when speech contains important keywords such as "contract" or "agreement." The extraction unit can also analyze the tone and speed of speech made by participants in a business meeting and adjust the key point extraction algorithm when emotions such as tension or excitement increase. Furthermore, the extraction unit can adjust the key point extraction algorithm according to the progress of the business meeting and optimize it when important topics are discussed.

[0060] The management department can analyze the content of what participants in a business negotiation say in real time and automatically optimize the data management algorithm when specific keywords are included. For example, it optimizes the data management algorithm when the data contains important keywords such as "contract" or "agreement." The management department can also analyze the tone and speed of the participants' voices and adjust the data management algorithm when emotions such as tension or excitement increase. Furthermore, the management department can adjust the data management algorithm according to the progress of the business negotiation and optimize it when important topics are discussed.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The recording unit automatically records the meeting content as soon as the business meeting starts. The recording unit can detect the start of the business meeting using a schedule linkage function, voice detection technology, or manual operation. Step 2: The conversion unit converts the recorded voice data into text in real time. The conversion unit analyzes the voice data using voice recognition technology and converts it into text data. Step 3: The translation unit translates the converted text from the first language to the second language. The translation unit uses machine translation technology to translate the text and neural network translation technology to provide high-precision translation. Step 4: The extraction unit automatically extracts key points and decisions from the translated text. The extraction unit uses keyword extraction technology to extract key points. Step 5: The management department stores the recorded audio data, translated text, and extracted key points in the system for future reference. The management department uses a database management system to store the data and can set access control functions and data retention periods.

[0063] (Example 2) The business negotiation management system according to an embodiment of the present invention is a system for improving the challenges faced by companies conducting overseas transactions and business expansion in multilingual business negotiations. This business negotiation management system automatically records, translates, and extracts key points from meeting content, thereby improving the efficiency and accuracy of business negotiations. First, when a business negotiation begins, the system automatically records the meeting content. The recorded audio data is translated in real time. For example, if a business negotiation conducted in the first language is to be translated into the second language, the system converts the audio data into text and translates that text. The translated text is provided to the business negotiation participants in real time. Next, key points are extracted from the translated text. The system uses natural language processing technology to automatically extract important points and decisions from the business negotiation. For example, agreed-upon contract terms and the date of the next meeting are extracted as key points. The extracted key points are provided to the business negotiation participants, facilitating the smooth progress of the negotiation. This system improves the efficiency and accuracy of business negotiations. Because the content of the business negotiation is automatically recorded and translated in real time, smooth communication is possible, transcending language barriers. Furthermore, because key points are automatically extracted, important points in business negotiations are not overlooked, allowing for efficient negotiations. In addition, this system also includes a function for managing the history of business negotiations. Recorded audio data, translated text, and extracted key points are stored within the system and can be referenced later. This allows for easy review of past negotiation content and understanding of the progress of negotiations. Thus, the business negotiation management system of this invention is a useful tool for companies engaged in overseas transactions or business expansion, enabling them to improve the efficiency and accuracy of their negotiations. In this way, the business negotiation management system can achieve improved efficiency and accuracy in business negotiations.

[0064] The business negotiation management system according to this embodiment comprises a recording unit, a conversion unit, a translation unit, an extraction unit, and a management unit. The recording unit automatically records the meeting content at the start of the business negotiation. The recording unit can, for example, use a schedule linkage function to detect the start of a business negotiation. The recording unit can also detect the start of a business negotiation using voice detection technology. Furthermore, the recording unit can also detect the start of a business negotiation through manual operation. The conversion unit converts the recorded audio data into text in real time. The conversion unit converts the audio data into text using, for example, speech recognition technology. Speech recognition technology analyzes the audio data using natural language processing technology and converts it into text data. The translation unit translates the converted text from the first language to the second language. The translation unit translates the text using, for example, machine translation technology. Machine translation technology performs highly accurate translation using neural network translation technology. The extraction unit automatically extracts important points and decisions from the translated text. The extraction unit extracts important points using, for example, keyword extraction technology. Keyword extraction technology extracts frequently occurring keywords from text data and identifies key points. The management unit stores the recorded audio data, translated text, and extracted key points within the system for later reference. The management unit stores the data using, for example, a database management system. The database management system has access control functions and allows setting the data retention period. As a result, the sales negotiation management system according to this embodiment can achieve increased efficiency and improved accuracy in sales negotiations.

[0065] The recording unit can automatically record the contents of a meeting as soon as a business meeting begins. The recording unit can use a schedule linking function, for example, to detect the start of a business meeting. The schedule linking function allows the start time of the business meeting to be set in advance and recording to start automatically at that time. The recording unit can also detect the start of a business meeting using voice detection technology. Voice detection technology detects the voice generated at the start of a business meeting and automatically starts recording. Furthermore, the recording unit can also detect the start of a business meeting through manual operation. Manual operation starts recording when the user presses the recording start button at the start of a business meeting. This allows recording to start automatically as soon as the business meeting begins, so that important information is not missed.

[0066] The conversion unit can convert recorded voice data into text in real time. The conversion unit converts voice data into text using, for example, voice recognition technology. Voice recognition technology analyzes voice data using natural language processing technology and converts it into text data. For example, voice recognition technology analyzes voice data in real time and converts it into text data. The conversion unit can also support multiple languages ​​using voice recognition technology. For example, the conversion unit can convert voice data in multiple languages, such as English, Japanese, and French, into text data. Furthermore, the conversion unit has a function of learning the voice characteristics of specific speakers using voice recognition technology. For example, the conversion unit accumulates voice data of participants in a business meeting and improves the accuracy of voice recognition by learning the voice characteristics of each participant. This allows the content to be checked instantly by converting voice data into text in real time.

[0067] The translation unit can translate converted text from a first language to a second language. The translation unit translates text using, for example, machine translation technology. Machine translation technology uses neural network translation technology to achieve high accuracy. For example, machine translation technology analyzes text written in a first language and translates it into a second language. Furthermore, the translation unit can handle multiple language pairs. For example, it can translate between multiple language pairs, such as Japanese to English, or English to Chinese. In addition, the translation unit has a dictionary function to handle specialized and industry-specific terminology. For example, the translation unit can accurately translate specialized terms using a specific industry-specific dictionary. This allows for the resolution of challenges in multilingual business negotiations by translating from a first language to a second language.

[0068] The extraction unit can automatically extract key points and decisions from translated text. For example, it can use keyword extraction technology to extract key points. Keyword extraction technology extracts frequently occurring keywords from text data to identify key points. The extraction unit can also extract the essentials of a deal using a summarization algorithm. The summarization algorithm analyzes text data and summarizes and extracts important information. Furthermore, the extraction unit can also extract key points of a deal using contextual analysis technology. Contextual analysis technology analyzes the context of text data to identify key points. This enables efficient deal management by automatically extracting key points and decisions from a deal.

[0069] The management department can store recorded audio data, translated text, and extracted key points within the system for later reference. For example, the management department can use a database management system to store the data. The database management system includes access control features and allows for setting data retention periods. The management department also has a search function, allowing for easy searching of stored data. For example, the management department can use a keyword search function to find data containing specific keywords. Furthermore, the management department has a tagging function, allowing for the classification of data by tagging it. For example, the management department can tag data by type of deal or date. This allows for the management of deal history and subsequent reference to understand the progress of deals.

[0070] The recording unit can estimate the emotions of the participants in a business negotiation and adjust the recording start time based on the estimated emotions. For example, the recording unit can use voice analysis technology to estimate the emotions of the participants. Voice analysis technology analyzes the tone and speed of the participants' voices to estimate their emotions. The recording unit can also use facial recognition technology to estimate the emotions of the participants. Facial recognition technology analyzes the facial expressions of the participants to estimate their emotions. Furthermore, the recording unit can also use text analysis technology to estimate the emotions of the participants. Text analysis technology analyzes the content of what the participants say to estimate their emotions. This allows for more appropriate recording by adjusting the recording start time according to the emotions of the participants. For example, if a participant is nervous, the recording can be delayed until they are relaxed. If a participant is excited, recording can be started immediately to avoid missing important statements. Furthermore, if a participant is calm, recording can be started in accordance with the progress of the negotiation.

[0071] The recording unit can automatically adjust the sound quality of the recording according to the progress of the business negotiation. For example, the recording unit can use voice analysis technology to detect the progress of the business negotiation. Voice analysis technology analyzes the progress of the business negotiation and automatically adjusts the sound quality of the recording. The recording unit can also adjust the sound quality of the recording using noise cancellation technology. Noise cancellation technology detects and filters out background noise during the business negotiation in real time to record clear audio. Furthermore, the recording unit can also adjust the sound quality of the recording using volume adjustment technology. Volume adjustment technology automatically adjusts the volume according to the progress of the business negotiation, ensuring that important statements are recorded clearly. In this way, by adjusting the sound quality of the recording according to the progress of the business negotiation, important information can be recorded clearly. For example, in the initial stages of the business negotiation, a wide range of sounds can be recorded to capture the overall atmosphere. When the business negotiation moves on to important topics, the sound quality can be improved for a clearer recording. Furthermore, near the end of the business negotiation, a wide range of sounds can be recorded again to capture the overall summary.

[0072] The recording unit can automatically filter background noise during a business meeting to obtain clear audio data during recording. The recording unit filters background noise, for example, using noise reduction technology. The noise reduction technology detects noise during a business meeting in real time and filters it to record clear audio. The recording unit can also remove background noise using a filtering algorithm. The filtering algorithm emphasizes only the voices of the business meeting participants and suppresses background noise. The recording unit also has a function to automatically remove sudden noise. For example, the recording unit can detect and remove sudden noise that occurs during a business meeting in real time. This allows clear audio data to be obtained by filtering background noise. For example, the recording unit can detect and filter noise during a business meeting in real time to record clear audio. The noise reduction technology can also emphasize only the voices of the business meeting participants and suppress background noise. The recording unit can also automatically remove sudden noise that occurs during a business meeting.

[0073] The recording unit can estimate the emotions of the business meeting participants and determine the recording priority based on the estimated emotions. The recording unit can use, for example, voice analysis technology to estimate the emotions of the business meeting participants. The voice analysis technology analyzes the tone and speed of the voices of the business meeting participants to estimate their emotions. The recording unit can also estimate the emotions of the business meeting participants using facial expression recognition technology. The facial expression recognition technology analyzes the facial expressions of the business meeting participants to estimate their emotions. The recording unit can also estimate the emotions of the business meeting participants using text analysis technology. The text analysis technology analyzes the content of the speech of the business meeting participants to estimate their emotions. This allows important speech to be recorded preferentially by determining the recording priority according to the emotions of the business meeting participants. For example, if the business meeting participants are nervous, important speech can be recorded preferentially. Also, if the business meeting participants are relaxed, the entire conversation can be recorded evenly. Furthermore, if the business meeting participants are excited, the recording priority can be adjusted according to their heightened emotions.

[0074] The recording unit analyzes the frequency of speech made by business meeting participants during recording, and can prioritize recording of important speech. The recording unit, for example, analyzes the frequency of speech made by business meeting participants in real time. The analysis of speech frequency is performed based on the number of times a business meeting participant speaks and the duration of the speech. The recording unit can also analyze the content of speech and prioritize recording of speech containing important keywords. The analysis of speech content is performed using text analysis technology. Furthermore, the recording unit can also determine recording priorities taking into account the length of speech. The length of speech is evaluated based on the duration of speech made by business meeting participants. In this way, by analyzing the frequency of speech, important speech can be prioritized for recording. For example, the recording unit can analyze the frequency of speech made by business meeting participants in real time, and prioritize recording of frequently spoken speech. The recording unit can also analyze the content of speech made by business meeting participants, and prioritize recording of speech containing important keywords. Furthermore, the recording unit can consider the length of speech made by business meeting participants and prioritize recording of long speech.

[0075] The recording unit can optimize recording settings by considering the location information of the business negotiation participants during recording. For example, the recording unit can automatically set the optimal microphone placement based on the location information of the business negotiation participants. Location information is obtained using GPS data or indoor location information. Furthermore, if the business negotiation participants move, the recording unit can update the location information in real time and adjust the recording settings accordingly. Real-time updates of location information are performed using technology to track the movement of business negotiation participants. In addition, the recording unit can record while considering the direction of sound. The direction of sound is evaluated based on the location information of the business negotiation participants. This makes it possible to optimize recording settings by considering location information. For example, it can automatically set the optimal microphone placement based on the location information of the business negotiation participants. Furthermore, if the business negotiation participants move, it can update the location information in real time and adjust the recording settings accordingly. Furthermore, it can record while considering the direction of sound based on the location information of the business negotiation participants.

[0076] The conversion unit can estimate the emotions of the negotiation participants and adjust the expression of the text conversion based on the estimated emotions. For example, the conversion unit can use speech analysis technology to estimate the emotions of the negotiation participants. Speech analysis technology analyzes the tone and speed of the negotiation participants' voices and estimates their emotions. The conversion unit can also estimate the emotions of the negotiation participants using facial expression recognition technology. Facial expression recognition technology analyzes the facial expressions of the negotiation participants and estimates their emotions. Furthermore, the conversion unit can also estimate the emotions of the negotiation participants using text analysis technology. Text analysis technology analyzes the content of what the negotiation participants say and estimates their emotions. As a result, by adjusting the expression of the text conversion according to the emotions of the negotiation participants, more appropriate text is generated. For example, if a negotiation participant is nervous, the text is converted to be concise and clear. If a negotiation participant is relaxed, the text is converted to include detailed explanations. Furthermore, if a negotiation participant is excited, the text can be converted to include expressions that reflect their emotions.

[0077] The conversion unit can automatically optimize the conversion algorithm according to the noise level of the audio data. For example, the conversion unit measures the noise level of the audio data in real time. This noise level measurement is performed using speech analysis technology. The conversion unit can also reduce the noise level using noise reduction technology. Noise reduction technology detects and filters noise in the audio data in real time to produce clear audio. Furthermore, the conversion unit can automatically adjust the parameters of the conversion algorithm according to the noise level. This parameter adjustment is based on the noise level of the audio data. This allows for highly accurate text conversion by optimizing the conversion algorithm according to the noise level. For example, if the noise level of the audio data is high, noise reduction is enhanced for text conversion. If the noise level of the audio data is low, the normal conversion algorithm is applied. Furthermore, the parameters of the conversion algorithm can be automatically adjusted according to the noise level of the audio data.

[0078] The conversion unit can improve accuracy by applying different conversion algorithms to each speaker in the audio data. For example, the conversion unit analyzes the voice characteristics of each speaker in the audio data. This voice characteristic analysis is performed using speech analysis technology. Furthermore, the conversion unit can adjust the conversion algorithm to take into account the different accents and pronunciations of each speaker. This consideration of accents and pronunciations is based on the analysis results of the audio data. In addition, the conversion unit can apply a conversion algorithm that takes into account the different speaking speeds of each speaker. This consideration of speaking speed is based on the analysis results of the audio data. This enables highly accurate text conversion by applying the optimal conversion algorithm for each speaker. For example, the conversion unit analyzes the voice characteristics of each speaker in the audio data and applies the optimal conversion algorithm. Furthermore, it can adjust the conversion algorithm to take into account the different accents and pronunciations of each speaker in the audio data. Furthermore, it can apply a conversion algorithm that takes into account the different speaking speeds of each speaker in the audio data.

[0079] The conversion unit can estimate the emotions of the negotiation participants and adjust the length of the text conversion based on the estimated emotions. For example, the conversion unit can use speech analysis technology to estimate the emotions of the negotiation participants. Speech analysis technology analyzes the tone and speed of the negotiation participants' voices and estimates their emotions. The conversion unit can also estimate the emotions of the negotiation participants using facial expression recognition technology. Facial expression recognition technology analyzes the facial expressions of the negotiation participants and estimates their emotions. Furthermore, the conversion unit can also estimate the emotions of the negotiation participants using text analysis technology. Text analysis technology analyzes the content of what the negotiation participants say and estimates their emotions. This allows for the generation of more appropriate text by adjusting the length of the text conversion according to the emotions of the negotiation participants. For example, if a negotiation participant is nervous, the text can be converted to a short, concise version. If a negotiation participant is relaxed, the text can be converted to a longer version that includes detailed explanations. Furthermore, if a negotiation participant is excited, the text can be converted to include expressions that reflect their emotions.

[0080] The conversion unit can determine the conversion priority based on the recording time of the audio data. For example, the conversion unit determines the conversion priority based on the recording time of the audio data. The recording time is obtained using a timestamp attached to the audio data. The conversion unit can also prioritize the transcription of important statements based on the recording time. The priority of important statements is determined based on the recording time and the importance of the statement's content. Furthermore, the conversion unit can also adjust the order of text transcription based on the recording time. The order of text transcription is performed in a logical order based on the recording time. This allows important statements to be prioritized for transcription by determining the conversion priority based on the recording time. For example, text transcription can be performed in order of earliest recording time. Alternatively, text transcription can be performed in order of latest recording time. Furthermore, important statements can be prioritized for text transcription based on the recording time.

[0081] The conversion unit can adjust the order of the converted text based on the content of the audio data. For example, the conversion unit can analyze the content of the audio data and transcribe important statements first. The content analysis of the audio data is performed using natural language processing techniques. The conversion unit can also transcribe related statements together. This grouping of related statements is based on the content analysis results of the audio data. Furthermore, the conversion unit can transcribe text in a logical order. The logical order is determined based on the content analysis results of the audio data. This allows for transcription in a logical order by adjusting the text order based on the content of the audio data. For example, it can analyze the content of the audio data and transcribe important statements first. It can also transcribe related statements together based on the content of the audio data. Furthermore, it can analyze the content of the audio data and transcribe text in a logical order.

[0082] The translation unit can estimate the emotions of the participants in a business negotiation and adjust the translation's expression based on those estimated emotions. For example, the translation unit can use speech analysis technology to estimate the emotions of the participants. Speech analysis technology analyzes the tone and speed of the participants' voices to estimate their emotions. The translation unit can also use facial expression recognition technology to estimate the emotions of the participants. Facial expression recognition technology analyzes the participants' facial expressions to estimate their emotions. Furthermore, the translation unit can also use text analysis technology to estimate the emotions of the participants. Text analysis technology analyzes the content of the participants' statements to estimate their emotions. This allows for the production of more appropriate translations by adjusting the translation's expression according to the emotions of the participants. For example, if a participant is nervous, the translation can be concise and clear. If a participant is relaxed, the translation can include detailed explanations. Furthermore, if a participant is excited, the translation can include expressions that reflect their emotions.

[0083] The translation unit can optimize its translation algorithm based on the frequency of technical terms during translation. For example, the unit measures the frequency of technical terms in real time. This measurement is performed using text analysis techniques. The unit can also improve translation accuracy by using a technical term dictionary. This dictionary contains specific industry-specific terminology and is referenced during translation. Furthermore, the unit can automatically adjust the parameters of the translation algorithm based on the frequency of technical terms. This parameter adjustment is based on the frequency of technical terms. This improves translation accuracy by optimizing the translation algorithm according to the frequency of technical terms. For example, if there are many technical terms, the technical term dictionary is used to improve translation accuracy. If there are few technical terms, the standard translation algorithm is applied. Furthermore, the parameters of the translation algorithm can be automatically adjusted based on the frequency of technical terms.

[0084] The translation unit can apply different translation algorithms depending on the context of the business negotiations during translation. The translation unit, for example, analyzes the context of the business negotiations and selects an appropriate translation algorithm. The context analysis is performed using natural language processing technology. The translation unit can also appropriately translate technical terms and industry jargon depending on the context of the business negotiations. The translation of technical terms and industry jargon is performed based on the results of the context analysis. Furthermore, the translation unit can also perform translations that include natural expressions by taking the context of the business negotiations into consideration. The translation of natural expressions is performed based on the results of the context analysis. This makes it possible to perform translations that include natural expressions by applying an appropriate translation algorithm depending on the context of the business negotiations. For example, the translation unit analyzes the context of the business negotiations and selects an appropriate translation algorithm. Furthermore, the translation unit can appropriately translate technical terms and industry jargon depending on the context of the business negotiations. Furthermore, the translation unit can perform translations that include natural expressions by taking the context of the business negotiations into consideration.

[0085] The translation unit can estimate the emotions of the participants in a business negotiation and adjust the length of the translation based on the estimated emotions. For example, the translation unit can use speech analysis technology to estimate the emotions of the participants. Speech analysis technology analyzes the tone and speed of the participants' voices to estimate their emotions. The translation unit can also use facial expression recognition technology to estimate the emotions of the participants. Facial expression recognition technology analyzes the facial expressions of the participants to estimate their emotions. Furthermore, the translation unit can also use text analysis technology to estimate the emotions of the participants. Text analysis technology analyzes the content of what the participants say to estimate their emotions. This allows for the generation of more appropriate translations by adjusting the length of the translation according to the emotions of the participants. For example, if a participant is nervous, a short, concise translation can be produced. If a participant is relaxed, a longer translation including detailed explanations can be produced. Furthermore, if a participant is excited, a translation that reflects their emotions can be produced.

[0086] The translation department can determine the priority of translations based on the progress of the business negotiations during translation. The translation department, for example, analyzes the progress of the business negotiations and prioritizes the translation of important remarks. The analysis of the progress of the business negotiations is performed using natural language processing technology. The translation department can also prioritize translations when important business negotiations begin. The priority of important topics is determined based on the progress of the business negotiations. Furthermore, the translation department can also prioritize translation of an overall summary as the business negotiations draw to a close. The priority of the overall summary is determined based on the progress of the business negotiations. In this way, by determining the priority of translations based on the progress of the business negotiations, important remarks can be prioritized for translation. For example, translations are prioritized when important business negotiations begin. Furthermore, important remarks can be prioritized for translation depending on the progress of the business negotiations. Furthermore, the translation department can prioritize translation of an overall summary as the business negotiations draw to a close.

[0087] The translation department can improve the accuracy of translations by referring to relevant documents related to business negotiations during the translation process. For example, the translation department can automatically refer to relevant documents related to business negotiations. This referencing is done using a document database. Furthermore, the translation department can improve the accuracy of translations of technical and industry-specific terms based on these documents. Translations of technical and industry-specific terms are based on the content of the relevant documents. In addition, the translation department can perform contextually appropriate translations based on the relevant documents. Contextually appropriate translations are also based on the content of the relevant documents. This means that by referring to relevant documents, the accuracy of translations of technical and industry-specific terms is improved. For example, it can automatically refer to relevant documents related to business negotiations to improve the accuracy of translations of technical and industry-specific terms. It can also perform contextually appropriate translations based on relevant documents related to business negotiations. Furthermore, it can perform translations that include natural expressions by referring to relevant documents related to business negotiations.

[0088] The extraction unit can estimate the emotions of the negotiation participants and adjust the criteria for extracting key points based on the estimated emotions. For example, the extraction unit can use speech analysis technology to estimate the emotions of the negotiation participants. Speech analysis technology analyzes the tone and speed of the negotiation participants' voices to estimate their emotions. The extraction unit can also use facial expression recognition technology to estimate the emotions of the negotiation participants. Facial expression recognition technology analyzes the facial expressions of the negotiation participants to estimate their emotions. Furthermore, the extraction unit can also use text analysis technology to estimate the emotions of the negotiation participants. Text analysis technology analyzes the content of the negotiation participants' statements to estimate their emotions. This allows for the extraction of more appropriate key points by adjusting the criteria for extracting key points according to the emotions of the negotiation participants. For example, if a negotiation participant is nervous, concise and clear key points will be extracted. If a negotiation participant is relaxed, key points including detailed explanations will be extracted. Furthermore, if a negotiation participant is excited, key points including expressions that reflect their emotions can be extracted.

[0089] The extraction unit can optimize its extraction algorithm according to the importance of the business opportunity when extracting key points. For example, the extraction unit can use text analysis technology to evaluate the importance of the business opportunity. Text analysis technology analyzes the content of the business opportunity and evaluates its importance. The extraction unit can also automatically adjust the parameters of the extraction algorithm according to the importance of the business opportunity. The parameter adjustment of the extraction algorithm is performed based on the importance of the business opportunity. Furthermore, the extraction unit can also apply an algorithm that extracts detailed key points according to the importance of the business opportunity. The extraction of detailed key points is performed based on the importance of the business opportunity. This allows for the accurate extraction of important key points by optimizing the extraction algorithm according to the importance of the business opportunity. For example, if the importance of the business opportunity is high, an algorithm that extracts detailed key points is applied. If the importance of the business opportunity is low, an algorithm that extracts concise key points is applied. Furthermore, the parameters of the extraction algorithm can be automatically adjusted according to the importance of the business opportunity.

[0090] The extraction unit can apply different extraction methods to each deal category when extracting key points. For example, the extraction unit can use text analysis technology to identify the deal category. Text analysis technology analyzes the content of the deal and identifies the category. The extraction unit can also extract key points based on different keywords for each deal category. Keyword extraction is performed based on the deal category. Furthermore, the extraction unit can highlight and extract important points according to the deal category. The highlighting of important points is performed based on the deal category. This allows for accurate extraction of important points by applying the appropriate extraction method according to the deal category. For example, the appropriate extraction method is selected according to the deal category. Furthermore, key points can be extracted based on different keywords for each deal category. Furthermore, important points can be highlighted and extracted according to the deal category.

[0091] The extraction unit can estimate the emotions of the negotiation participants and adjust the display method of key points based on the estimated emotions. For example, the extraction unit can use speech analysis technology to estimate the emotions of the negotiation participants. Speech analysis technology analyzes the tone and speed of the negotiation participants' voices to estimate their emotions. The extraction unit can also use facial expression recognition technology to estimate the emotions of the negotiation participants. Facial expression recognition technology analyzes the facial expressions of the negotiation participants to estimate their emotions. Furthermore, the extraction unit can also use text analysis technology to estimate the emotions of the negotiation participants. Text analysis technology analyzes the content of the negotiation participants' statements to estimate their emotions. This allows for more appropriate display by adjusting the display method of key points according to the emotions of the negotiation participants. For example, if a negotiation participant is nervous, a concise and highly visible display method can be provided. If a negotiation participant is relaxed, a display method including detailed information can be provided. Furthermore, if a negotiation participant is excited, a display method including expressions that reflect their emotions can be provided.

[0092] The extraction unit can prioritize key points based on the progress of the business negotiation. For example, the extraction unit analyzes the progress of the business negotiation and prioritizes extracting important statements as key points. The analysis of the progress of the business negotiation is performed using natural language processing technology. The extraction unit can also prioritize extracting key points when the business negotiation reaches an important agenda item. The priority of important agenda items is determined based on the progress of the business negotiation. Furthermore, the extraction unit can also prioritize extracting an overall summary as key points near the end of the business negotiation. The priority of the overall summary is determined based on the progress of the business negotiation. In this way, by prioritizing key points based on the progress of the business negotiation, important statements can be prioritized for extraction. For example, when the business negotiation reaches an important agenda item, key points are prioritized for extraction. Furthermore, important statements can be prioritized for extraction as key points depending on the progress of the business negotiation. Furthermore, near the end of the business negotiation, an overall summary can be prioritized for extraction as key points.

[0093] The extraction unit can improve the accuracy of its extraction by referencing relevant data from the business negotiation when extracting key points. For example, the extraction unit automatically references relevant data from the business negotiation. This reference is performed using a database. Furthermore, the extraction unit can extract appropriate key points based on the relevant data, taking into account the context. This contextual extraction is based on the content of the relevant data. Additionally, the extraction unit can extract key points containing natural expressions by referencing the relevant data. This extraction of natural expressions is based on the content of the relevant data. This allows for the accurate extraction of important points by referencing relevant data. For example, it can automatically reference relevant data from the business negotiation and accurately extract important points. It can also extract appropriate key points based on relevant data from the business negotiation, taking into account the context. Furthermore, it can extract key points containing natural expressions by referencing relevant data from the business negotiation.

[0094] The management department can estimate the emotions of negotiation participants and adjust data management methods based on the estimated emotions. For example, the management department can use voice analysis technology to estimate the emotions of negotiation participants. Voice analysis technology analyzes the tone and speed of the participants' voices to estimate their emotions. The management department can also use facial expression recognition technology to estimate the emotions of negotiation participants. Facial expression recognition technology analyzes the facial expressions of negotiation participants to estimate their emotions. Furthermore, the management department can also use text analysis technology to estimate the emotions of negotiation participants. Text analysis technology analyzes the content of what negotiation participants say to estimate their emotions. This allows for more appropriate data management by adjusting data management methods according to the emotions of negotiation participants. For example, if a negotiation participant is nervous, a concise and clear data management method can be provided. If a negotiation participant is relaxed, a data management method including detailed information can be provided. Furthermore, if a negotiation participant is excited, a data management method including expressions that reflect their emotions can be provided.

[0095] The management department can automatically set data retention periods based on the importance of each deal during data management. For example, the management department can use text analysis technology to assess the importance of each deal. Text analysis technology analyzes the content of the deal and assesses its importance. Furthermore, the management department can automatically set data retention periods based on the importance of each deal. The data retention period is set based on the importance of the deal. In addition, the management department can also set data retention periods based on legal requirements. Legal requirements are determined based on the content of the deal and industry regulations. This allows for proper management of important data by setting data retention periods according to the importance of each deal. For example, a long data retention period is set for highly important deals, and a short data retention period is set for less important deals. Furthermore, the data retention period can be automatically adjusted according to the importance of each deal.

[0096] The management department can apply different management methods to each opportunity category when managing data. For example, the management department can use text analysis technology to identify the opportunity category. Text analysis technology analyzes the content of the opportunity and identifies the category. Furthermore, the management department can apply different data storage methods to each opportunity category. The data storage method is determined based on the opportunity category. In addition, the management department can highlight and manage important data according to the opportunity category. This highlighting of important data is based on the opportunity category. This allows for accurate management of important data by applying appropriate management methods according to the opportunity category. For example, an appropriate data management method can be selected according to the opportunity category. Furthermore, different data storage methods can be applied to each opportunity category. In addition, important data can be highlighted and managed according to the opportunity category.

[0097] The management unit can estimate the emotions of the business meeting participants and adjust the data display method based on the estimated emotions. For example, the management unit can use voice analysis technology to estimate the emotions of the business meeting participants. The voice analysis technology analyzes the tone and speed of the voices of the business meeting participants to estimate their emotions. The management unit can also estimate the emotions of the business meeting participants using facial expression recognition technology. The facial expression recognition technology analyzes the facial expressions of the business meeting participants to estimate their emotions. Furthermore, the management unit can also estimate the emotions of the business meeting participants using text analysis technology. The text analysis technology analyzes the content of the speech of the business meeting participants to estimate their emotions. This enables more appropriate display by adjusting the data display method according to the emotions of the business meeting participants. For example, if the business meeting participants are nervous, a concise and highly visible display method can be provided. If the business meeting participants are relaxed, a display method including detailed information can be provided. Furthermore, if the business meeting participants are excited, a display method including expressions reflecting their emotions can be provided.

[0098] The management department can prioritize data based on the progress of a sales negotiation. For example, the management department can analyze the progress of a sales negotiation and prioritize the management of important data. The analysis of the progress of a sales negotiation is performed using natural language processing technology. Furthermore, the management department can prioritize the management of data when a sales negotiation reaches an important agenda item. The priority of important agenda items is determined based on the progress of the sales negotiation. In addition, the management department can prioritize the management of an overall summary as data when the sales negotiation is nearing its end. The priority of the overall summary is determined based on the progress of the sales negotiation. This allows for the priority management of important data by prioritizing data based on the progress of the sales negotiation. For example, data can be prioritized when a sales negotiation reaches an important agenda item. Furthermore, important data can be prioritized according to the progress of the sales negotiation. Furthermore, an overall summary can be prioritized as data when the sales negotiation is nearing its end.

[0099] The management unit can improve the accuracy of management by referring to the related data of business negotiations when managing data. The management unit, for example, automatically refers to the related data of business negotiations. The related data is referred to using a database. The management unit can also perform appropriate data management according to the context based on the related data. Data management according to the context is performed based on the content of the related data. Furthermore, the management unit can also perform data management including natural expressions by referring to the related data. Data management with natural expressions is performed based on the content of the related data. This allows important data to be managed accurately by referring to the related data. For example, the related data of business negotiations can be automatically referred to and important data can be managed accurately. Furthermore, appropriate data management according to the context can be performed based on the related data of business negotiations. Furthermore, data management including natural expressions can be performed by referring to the related data of business negotiations. === Hard Collateral 1-1 === Each of the multiple elements described above, including the recording unit, conversion unit, translation unit, extraction unit, and management unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the recording unit records the audio of a business negotiation using the microphone 38B of the smart device 14 and manages the recorded data with the control unit 46A. The conversion unit converts the audio data into text using, for example, the specific processing unit 290 of the data processing unit 12. The translation unit translates the text using, for example, the specific processing unit 290 of the data processing unit 12. The extraction unit extracts important points using, for example, the specific processing unit 290 of the data processing unit 12. The management unit stores the data in the database 24 of the data processing unit 12 so that it can be referenced later. === Hard Collateral 1-2 === Each of the multiple elements, including the recording unit, conversion unit, translation unit, extraction unit, and management unit, described above, is realized, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the recording unit records the audio of a business negotiation using the microphone 238 of the smart glasses 214 and manages the recorded data using the control unit 46A. The conversion unit converts the audio data into text using, for example, the specific processing unit 290 of the data processing device 12. The translation unit translates the text using, for example, the specific processing unit 290 of the data processing device 12. The extraction unit extracts important points using, for example, the specific processing unit 290 of the data processing device 12. The management unit stores the data in, for example, the database 24 of the data processing device 12 so that it can be referenced later. === Hard Collateral 1-3 === Each of the multiple elements including the recording unit, conversion unit, translation unit, extraction unit, and management unit described above is realized, for example, in at least one of the headset-type terminal 314 and the data processing device 12. For example, the recording unit records the audio of a business negotiation using the microphone 238 of the headset-type terminal 314 and manages the recorded data using the control unit 46A. The conversion unit converts the audio data into text using, for example, the specific processing unit 290 of the data processing device 12. The translation unit translates the text using, for example, the specific processing unit 290 of the data processing device 12. The extraction unit extracts important points using, for example, the specific processing unit 290 of the data processing device 12. The management unit stores the data in, for example, the database 24 of the data processing device 12 so that it can be referenced later. === Hard Collateral 1-4 === Each of the multiple elements including the recording unit, conversion unit, translation unit, extraction unit, and management unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the recording unit records the audio of the business negotiation using the microphone 238 of the robot 414 and manages the recorded data by the control unit 46A. The conversion unit converts the audio data into text by, for example, the specific processing unit 290 of the data processing device 12. The translation unit translates the text by, for example, the specific processing unit 290 of the data processing device 12. The extraction unit extracts important points by, for example, the specific processing unit 290 of the data processing device 12. The management unit stores the data in, for example, the database 24 of the data processing device 12 so that it can be referenced later.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The recording unit can analyze the speech of business meeting participants in real time and start recording when specific keywords are included. For example, if important keywords such as "contract" or "agreement" are uttered during a business meeting, recording will automatically begin. The recording unit can also analyze the tone and speed of the participants' speech and start recording when emotions such as tension or excitement increase. Furthermore, the recording unit can adjust the start timing of recording according to the progress of the business meeting and start recording when important topics are discussed.

[0102] The conversion unit analyzes speech content of business negotiation participants in real time and prioritizes text conversion when specific keywords are included. For example, speech containing important keywords such as "contract" or "agreement" is prioritized for conversion to text. The conversion unit can also analyze the tone and speed of speech of business negotiation participants and prioritize text conversion when emotions such as tension or excitement are high. Furthermore, the conversion unit can adjust the priority of text conversion according to the progress of the business negotiation, and prioritize text conversion when important topics are discussed.

[0103] The translation department can analyze the content of the business negotiation participants' statements in real time and prioritize translation when certain keywords are included. For example, it can prioritize translating statements containing important keywords such as "contract" or "agreement." The translation department can also analyze the tone and speed of the participants' voices and prioritize translation when emotions such as tension or excitement are heightened. Furthermore, the translation department can adjust the translation priority according to the progress of the business negotiation, prioritizing translation when important topics are discussed.

[0104] The extraction unit analyzes the content of what participants in a business negotiation say in real time and prioritizes extracting key points when specific keywords are included. For example, it prioritizes extracting key points from statements containing important keywords such as "contract" or "agreement." The extraction unit can also analyze the tone and speed of the participants' voices and prioritize extracting key points when emotions such as tension or excitement are heightened. Furthermore, the extraction unit can adjust the priority of key point extraction according to the progress of the business negotiation, prioritizing key point extraction when important topics are discussed.

[0105] The management department can analyze the content of participants' statements in negotiations in real time and prioritize data management when specific keywords are included. For example, it can prioritize the management of data containing important keywords such as "contract" or "agreement." The management department can also analyze the tone and speed of participants' voices and prioritize data management when emotions such as tension or excitement are heightened. Furthermore, the management department can adjust the priority of data management according to the progress of the negotiation, prioritizing data management when important topics are discussed.

[0106] The recording unit can analyze the speech of business meeting participants in real time and automatically adjust the sound quality of the recording if certain keywords are included. For example, it can increase the sound quality when important keywords such as "contract" or "agreement" are included in speech. The recording unit can also analyze the tone and speed of the speech of business meeting participants and adjust the sound quality when emotions such as tension or excitement increase. Furthermore, the recording unit can adjust the sound quality of the recording according to the progress of the business meeting and increase the sound quality when important topics are discussed.

[0107] The conversion unit can analyze the speech content of business meeting participants in real time and automatically optimize the conversion algorithm when specific keywords are included. For example, it optimizes the conversion algorithm when important keywords such as "contract" or "agreement" are included in speech. The conversion unit can also analyze the tone and speed of speech of business meeting participants and adjust the conversion algorithm when emotions such as tension or excitement increase. Furthermore, the conversion unit can adjust the conversion algorithm according to the progress of the business meeting and optimize it when important topics are discussed.

[0108] The translation department can analyze the speech of business meeting participants in real time and automatically optimize the translation algorithm when specific keywords are included. For example, the translation algorithm is optimized when important keywords such as "contract" or "agreement" are included in speech. The translation department can also analyze the tone and speed of speech of business meeting participants and adjust the translation algorithm when emotions such as tension or excitement increase. Furthermore, the translation department can adjust the translation algorithm according to the progress of the business meeting and optimize it when important topics are discussed.

[0109] The extraction unit can analyze the content of speeches made by participants in a business meeting in real time and automatically optimize the key point extraction algorithm when specific keywords are included. For example, the extraction unit optimizes the key point extraction algorithm when speech contains important keywords such as "contract" or "agreement." The extraction unit can also analyze the tone and speed of speech made by participants in a business meeting and adjust the key point extraction algorithm when emotions such as tension or excitement increase. Furthermore, the extraction unit can adjust the key point extraction algorithm according to the progress of the business meeting and optimize it when important topics are discussed.

[0110] The management department can analyze the content of what participants in a business negotiation say in real time and automatically optimize the data management algorithm when specific keywords are included. For example, it optimizes the data management algorithm when the data contains important keywords such as "contract" or "agreement." The management department can also analyze the tone and speed of the participants' voices and adjust the data management algorithm when emotions such as tension or excitement increase. Furthermore, the management department can adjust the data management algorithm according to the progress of the business negotiation and optimize it when important topics are discussed.

[0111] The processing flow of the second embodiment will be briefly explained below.

[0112] Step 1: The recording unit automatically records the meeting content as soon as the business meeting starts. The recording unit can detect the start of the business meeting using a schedule linkage function, voice detection technology, or manual operation. Step 2: The conversion unit converts the recorded voice data into text in real time. The conversion unit analyzes the voice data using voice recognition technology and converts it into text data. Step 3: The translation unit translates the converted text from the first language to the second language. The translation unit uses machine translation technology to translate the text and neural network translation technology to provide high-precision translation. Step 4: The extraction unit automatically extracts key points and decisions from the translated text. The extraction unit uses keyword extraction technology to extract key points. Step 5: The management department stores the recorded audio data, translated text, and extracted key points in the system for future reference. The management department uses a database management system to store the data and can set access control functions and data retention periods.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0115] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0117] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0118] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0124] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] 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.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0131] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0133] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0134] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0136] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0137] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0139] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0140] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0141] 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.

[0142] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0143] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0149] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0150] 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.

[0151] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0153] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0155] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0156] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0157] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0158] 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.

[0159] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0160] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0161] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0162] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0163] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0164] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0165] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0166] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0167] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0168] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0169] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0170] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0171] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0174] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0175] 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.

[0176] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0177] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0178] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0179] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0180] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0181] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0182] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0183] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0184] [Explanation of symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A recording unit that automatically records the contents of the meeting; a conversion unit that converts the voice data recorded by the recording unit into text; a translation unit that translates the text converted by the conversion unit; an extraction unit that extracts key points from the text translated by the translation unit; a management unit that manages the key points extracted by the extraction unit; A system characterized by:

2. The recording unit Automatically record meeting content as soon as a business meeting begins The system of claim 1 .

3. The conversion unit Converts recorded audio data into text in real time The system of claim 1 .

4. The translation unit Translate the converted text from the first language to the second language The system of claim 1 .

5. The extraction unit Automatically extract key points and decision points from translated text The system of claim 1 .

6. The management unit Recorded audio data, translated text, and extracted key points are stored in the system for later reference. The system of claim 1 .

7. The recording unit Estimate the emotions of meeting participants and adjust the start time of recording based on the estimated emotions The system of claim 1 .

8. The recording unit Automatically adjust the quality of your recordings based on the progress of the deal The system of claim 1 .

Images