system

Abstract

The system according to this embodiment aims to check the accuracy of the store clerk's explanation in real time and provide accurate information. [Solution] The system according to the embodiment comprises a monitoring unit, an analysis unit, and a provision unit. The monitoring unit monitors conversations in real time and transcribes them into text. The analysis unit analyzes the conversations transcribed by the monitoring unit and checks the accuracy of the store clerk's statements. The provision unit provides accurate information based on the results obtained by the analysis unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. '

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that the explanation of the store clerk may contain errors or inaccurate information, making it difficult to obtain accurate information.

[0005] The system according to the embodiment aims to check the accuracy of the store clerk's explanation in real time and provide accurate information.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a monitoring unit, an analysis unit, and a provision unit. The monitoring unit monitors conversations in real time and transcribes them into text. The analysis unit analyzes the conversations transcribed by the monitoring unit and checks the accuracy of the store clerk's statements. The provision unit provides accurate information based on the results obtained by the analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can check the accuracy of the store clerk's explanation in real time and provide accurate information. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The support concierge AI system according to an embodiment of the present invention is a system that uses a specialized support AI to deepen the user's understanding of products and services through conversations with store staff, thereby supporting purchases without regret. When a user converses with a store staff member about a product or service, the support AI monitors the conversation in real time and transcribes it into text. Next, the support AI analyzes the transcribed conversation to check the accuracy of the staff member's statements. If the staff member's statements contain errors or inaccurate information, the support AI points them out and provides correct information. This allows the user to gain a correct understanding and make purchases without regret. For example, if a user is considering purchasing a computer, smartphone, home, or insurance, they ask a store staff member a question. At this time, the support AI monitors the conversation in real time and transcribes it into text. For example, if the staff member says, "This computer is equipped with the latest processor," that statement is transcribed into text. Next, the support AI analyzes the transcribed conversation. The support AI uses natural language processing technology to check the accuracy of the staff member's statements. For example, if a salesperson says, "This computer has the latest processor," the support AI will cross-reference that information with the product database to verify its accuracy. If the salesperson's statement contains errors or inaccuracies, the support AI will point them out. For example, it might say, "This computer does not have the latest processor." Furthermore, the support AI will provide correct information, such as, "This computer has a previous generation processor." This allows users to gain a correct understanding and make purchases without regret. This system enables users to gain a correct understanding of products and services and make purchases without regret. In addition, knowing that a third party (the support AI) is monitoring the conversation encourages salespeople to be more careful about what they say and to provide accurate information based on evidence. For example, if a salesperson says, "This insurance covers all illnesses," the support AI will check the statement and point out any errors. This encourages salespeople to provide accurate information.This AI-powered support concierge can be used when purchasing a variety of products and services, such as computers, smartphones, homes, and insurance. For example, when purchasing a computer, it provides accurate information about specifications and functions, and when purchasing a home, it provides accurate information about property details and loan conditions. This allows users to make purchases with confidence. In this way, the AI ​​support concierge system enables users to gain a correct understanding of products and services and make purchases without regret.

[0029] The support concierge AI system according to this embodiment comprises a monitoring unit, an analysis unit, and a provision unit. The monitoring unit monitors conversations in real time and transcribes them into text. For example, when a user converses with a store clerk about products or services, the monitoring unit monitors the conversation in real time and transcribes it into text. The monitoring unit can transcribe conversations using, for example, speech recognition technology. The monitoring unit can also analyze the content of the conversation in real time and extract important information. For example, the monitoring unit can detect specific keywords in the conversation and highlight those parts. The analysis unit analyzes the transcribed conversation and checks the accuracy of the store clerk's statements. The analysis unit analyzes the transcribed conversation using, for example, natural language processing technology. The analysis unit can perform, for example, morphological analysis to analyze the meaning of the store clerk's statements. The analysis unit can also perform grammatical analysis to analyze the structure of the store clerk's statements. Furthermore, the analysis unit can perform semantic analysis to understand the content of the store clerk's statements. The provision unit provides accurate information based on the results obtained by the analysis unit. The service provider can, for example, point out errors or inaccuracies in a store clerk's statements and provide correct information. The service provider can also evaluate the accuracy of a store clerk's statements and provide correct information to the user. Furthermore, the service provider can provide the user with the basis for the store clerk's statements, increasing their credibility. In addition, the service provider can provide the user with recommendations based on the store clerk's statements. As a result, the support concierge AI system according to this embodiment allows users to gain a correct understanding of products and services and make purchases without regret.

[0030] The monitoring unit monitors conversations in real time and transcribes them into text. Specifically, when a user converses with a store employee about a product or service, the monitoring unit uses speech recognition technology to transcribe the conversation into text. For example, a deep learning-based speech recognition model is used. This model learns from a large amount of audio data to achieve highly accurate speech recognition. The monitoring unit can also analyze the content of conversations in real time and extract important information. For example, it can detect specific keywords in the conversation and highlight those parts. A keyword extraction algorithm using natural language processing technology is used for keyword detection. This algorithm can understand the context of the conversation and accurately extract important keywords. Furthermore, the monitoring unit can also perform sentiment analysis of the conversation. Sentiment analysis uses an emotion recognition model to grasp the emotional state of the user and the store employee. As a result, the monitoring unit can grasp not only the content of the conversation but also changes in emotions in real time and provide more detailed information. By combining these functions, the monitoring unit can accurately monitor conversations between users and store employees, extract important information, and transcribe it into text.

[0031] The analysis unit analyzes the transcribed conversation and checks the accuracy of the store clerk's statements. Specifically, it uses natural language processing techniques to analyze the transcribed conversation. The analysis unit can perform morphological analysis to analyze the meaning of the store clerk's statements. A morphological analyzer is used for morphological analysis, which divides the text into words and analyzes the meaning of each word. Furthermore, the analysis unit can also perform grammatical analysis to analyze the structure of the store clerk's statements. A grammatical analyzer is used for grammatical analysis, which analyzes the grammatical structure of the text and understands the structure of the sentences. Furthermore, the analysis unit can perform semantic analysis to understand the content of the store clerk's statements. A semantic analysis model is used for semantic analysis, which analyzes the meaning of the text and understands the content of the statements. Based on these analysis results, the analysis unit checks the accuracy of the store clerk's statements. For example, it verifies whether the store clerk's statements are based on facts and do not contain errors. The analysis unit can also refer to past data and knowledge bases to evaluate the reliability of the store clerk's statements. This allows the analysis unit to analyze the transcribed conversation with high accuracy and check the accuracy of the store clerk's statements.

[0032] The information delivery unit provides accurate information based on the results obtained by the analysis unit. Specifically, if a store employee's statement contains errors or inaccuracies, the unit will point them out and provide correct information. For example, the information delivery unit can evaluate the accuracy of a store employee's statement and provide the user with correct information. The information delivery unit can also provide users with the basis for a store employee's statement to increase its reliability. For example, the information delivery unit can provide the basis for a store employee's statement based on information from knowledge bases and databases referenced by the analysis unit. The information delivery unit can also provide users with recommendations based on a store employee's statement. For example, if a user asks about a specific product, the information delivery unit will provide detailed information and recommendations about that product. Furthermore, the information delivery unit can collect user feedback and continuously improve the accuracy and effectiveness of the information it provides. For example, it can evaluate whether users are satisfied with the information provided and whether the information was helpful, and improve the information provided based on the results. In this way, the information delivery unit provides users with accurate and reliable information, enabling users to gain a correct understanding of products and services.

[0033] The monitoring unit can monitor and transcribe conversations between users and store staff in real time when users talk about products or services. The monitoring unit can transcribe conversations using, for example, speech recognition technology. For example, the monitoring unit can record conversations between users and store staff in real time and transcribe them using speech recognition technology. The monitoring unit can also analyze the content of conversations in real time and extract important information. For example, the monitoring unit can detect specific keywords in the conversation and highlight those parts. This creates a foundation for providing accurate information by transcribing conversations between users and store staff in real time. Some or all of the above processing in the monitoring unit may be performed using, for example, AI, or not using AI. For example, the monitoring unit can have a generating AI perform the process of recording conversations between users and store staff in real time and transcribe them using speech recognition technology.

[0034] The analysis unit can analyze transcribed conversations using natural language processing technology and check the accuracy of the store clerk's statements. For example, the analysis unit can perform morphological analysis to analyze the meaning of the store clerk's statements. For example, the analysis unit can extract morphemes such as nouns and verbs from the transcribed conversation and analyze the meaning of the statements. The analysis unit can also perform grammatical analysis to analyze the structure of the store clerk's statements. For example, the analysis unit can analyze the grammatical structure of the transcribed conversation and check the accuracy of the statements. Furthermore, the analysis unit can perform semantic analysis to understand the content of the store clerk's statements. For example, the analysis unit can analyze the meaning of the transcribed conversation and check the accuracy of the statements. In this way, the accuracy of the store clerk's statements can be checked with high precision by using natural language processing technology. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the transcribed conversation into a generating AI and have the generating AI perform a check of the accuracy of the statements.

[0035] The information provider can point out errors or inaccuracies in the employee's statements and provide correct information. For example, the information provider can evaluate the accuracy of the employee's statements and provide correct information to the user. For example, the information provider can point out errors in the employee's statements and provide correct information. The information provider can also increase the reliability of the employee's statements by showing the basis for them to the user. For example, the information provider can gain the user's trust by evaluating the accuracy of the employee's statements and showing the basis for it. Furthermore, the information provider can provide the user with recommendations based on the employee's statements. For example, the information provider can recommend appropriate products or services to the user based on the employee's statements. In this way, by pointing out incorrect information and providing correct information, the user can obtain accurate information. Some or all of the above processes in the information provider may be performed using AI, for example, or not using AI. For example, the information provider can have a generating AI perform the process of evaluating the accuracy of the employee's statements and providing correct information.

[0036] The information provision unit can provide accurate information when purchasing various products and services, such as personal computers, smartphones, homes, and insurance. For example, when purchasing a personal computer, the information provision unit can provide accurate information about the specifications and functions of the computer. For example, the information provision unit can provide accurate information about the property details and loan conditions when purchasing a home. For example, the information provision unit can provide accurate information about the property details and loan conditions of the home. Furthermore, when purchasing insurance, the information provision unit can provide accurate information about the content and conditions of the insurance. For example, the information provision unit can provide accurate information about various products and services, allowing users to make purchases with confidence. Some or all of the above processing in the information provision unit may be performed using AI, for example, or not using AI. For example, the information provision unit can have a generating AI perform the provision of information about the specifications and functions of a personal computer.

[0037] The monitoring unit can add a filtering function to remove background and ambient noise when monitoring conversations. For example, the monitoring unit can remove background noise from the store and monitor only the conversation between the store clerk and the user. For example, the monitoring unit can remove background noise from the store using noise cancellation technology. The monitoring unit can also analyze ambient noise in real time and filter out sounds that are unnecessary for the conversation. For example, the monitoring unit can analyze ambient noise in real time using filtering technology and remove unnecessary sounds. The monitoring unit can also distinguish between the voice of the store clerk and the voice of the user and remove other sounds. For example, the monitoring unit can distinguish between the voice of the store clerk and the voice of the user using speech recognition technology and remove other sounds. This improves the accuracy of conversation monitoring by removing background and ambient noise. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can have a generating AI perform noise cancellation technology.

[0038] The monitoring unit can prioritize the transcription of specific keywords by referring to the user's past conversation history when monitoring a conversation. For example, the monitoring unit can prioritize the transcription of keywords that the user has frequently used in the past. For example, the monitoring unit can store the user's past conversation history in a database and extract specific keywords by performing frequency analysis. The monitoring unit can also extract important keywords from the user's past conversation history and prioritize their transcription. For example, the monitoring unit can analyze the user's past conversation history and extract keywords based on importance scores. Furthermore, when the user talks about a specific topic, the monitoring unit can prioritize the transcription of keywords related to that topic. For example, the monitoring unit can refer to the user's past conversation history and prioritize the transcription of keywords related to that topic. This ensures that important keywords are not missed by referring to the user's past conversation history. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the user's past conversation history into a generating AI and have the generating AI perform the extraction of specific keywords.

[0039] The monitoring unit can prioritize the transcription of highly relevant information by considering the user's geographical location when monitoring conversations. For example, if the user is in a specific region, the monitoring unit will prioritize the transcription of information related to that region. For example, the monitoring unit can obtain the user's geographical location from GPS data and prioritize the transcription of information related to that region. The monitoring unit can also prioritize the transcription of information related to the travel destination if the user is traveling. For example, the monitoring unit can obtain the user's geographical location from location information services and prioritize the transcription of information related to the travel destination. The monitoring unit can also prioritize the transcription of information related to the products and services of a store if the user is in a specific store. For example, the monitoring unit can refer to the user's geographical location and prioritize the transcription of information related to the products and services of that store. In this way, by considering the user's geographical location, highly relevant information can be prioritized for transcription. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without using AI. For example, the monitoring unit can input the user's geographical location information into the generating AI and have the AI ​​perform the task of converting highly relevant information into text.

[0040] The monitoring unit can analyze the user's social media activity when monitoring conversations and prioritize monitoring relevant conversations. For example, the monitoring unit can prioritize monitoring conversations related to topics that the user frequently mentions on social media. For example, the monitoring unit can store the user's social media activity in a database and extract relevant topics through frequency analysis. The monitoring unit can also extract topics of interest from the user's social media activity and prioritize monitoring relevant conversations. For example, the monitoring unit can analyze the user's social media activity and extract topics based on importance scores. The monitoring unit can also prioritize monitoring conversations related to accounts that the user follows on social media. For example, the monitoring unit can refer to the user's social media activity and prioritize monitoring conversations related to followed accounts. In this way, by analyzing the user's social media activity, relevant conversations can be prioritized. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the user's social media activity into a generating AI and have the generating AI perform the monitoring of relevant conversations.

[0041] The analysis unit can add a function to refer to past statements to evaluate the reliability of the employee's statements during analysis. For example, the analysis unit can analyze the employee's past statements and prioritize evaluating highly reliable statements. For example, the analysis unit can store the employee's past statements in a database and extract highly reliable statements by performing frequency analysis. The analysis unit can also identify statements with many errors from the employee's past statements and evaluate their reliability low. For example, the analysis unit can analyze the employee's past statements and identify statements with many errors. The analysis unit can also evaluate the reliability of the employee's current statements based on the employee's past statements. For example, the analysis unit can refer to the employee's past statements and evaluate the reliability of the current statements. This makes it possible to improve the reliability of statements by referring to the employee's past statements. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the employee's past statements into a generating AI and have the generating AI perform the reliability evaluation.

[0042] The analysis unit can more accurately identify errors and inaccurate information by considering the context of the employee's statements during analysis. For example, the analysis unit can identify errors by analyzing the context before and after the employee's statements. For example, the analysis unit can identify errors by analyzing the context before and after the transcribed conversation. The analysis unit can also identify errors and inaccurate information by considering the context of the employee's statements. For example, the analysis unit can identify errors and inaccurate information by analyzing the context of the transcribed conversation. The analysis unit can also identify errors and inaccurate information based on the context of the employee's statements. For example, the analysis unit can identify errors and inaccurate information by analyzing the context of the transcribed conversation. This allows for more accurate identification of errors and inaccurate information by considering the context of the employee's statements. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the context of the transcribed conversation into a generating AI and have the generating AI perform the identification of errors and inaccurate information.

[0043] The analysis unit can improve the accuracy of its analysis by considering the geographical background of the employee's statements during analysis. For example, the analysis unit can improve the accuracy of its analysis by considering the geographical background of the employee's statements. For example, the analysis unit can store the geographical background of the employee's statements in a database and refer to it during analysis. The analysis unit can also improve the accuracy of its analysis based on the geographical background of the employee's statements. For example, the analysis unit can analyze the geographical background of the employee's statements and improve the accuracy of its analysis. The analysis unit can also improve the accuracy of its analysis by referring to the geographical background of the employee's statements. For example, the analysis unit can store the geographical background of the employee's statements in a database and refer to it during analysis. This improves the accuracy of the analysis by considering the geographical background of the employee's statements. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the geographical background of the employee's statements into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0044] The analysis unit can improve the accuracy of its analysis by referring to relevant industry news and trend information during the analysis process. For example, the analysis unit can improve the accuracy of its analysis by referring to relevant industry news. For example, the analysis unit can store industry news in a database and refer to it during the analysis. The analysis unit can also improve the accuracy of its analysis by referring to trend information. For example, the analysis unit can store trend information in a database and refer to it during the analysis. The analysis unit can also improve the accuracy of its analysis based on industry news and trend information. For example, the analysis unit can store industry news and trend information in a database and refer to it during the analysis. This improves the accuracy of the analysis by referring to relevant industry news and trend information. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input industry news and trend information into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0045] The service provider can provide more appropriate information by referring to the user's past purchase history at the time of delivery. For example, the service provider can refer to the user's past purchase history and provide relevant information. For example, the service provider can store the user's past purchase history in a database and extract relevant information. The service provider can also provide appropriate information based on the user's past purchase history. For example, the service provider can analyze the user's past purchase history and provide appropriate information. The service provider can also analyze the user's past purchase history and provide optimal information. For example, the service provider can store the user's past purchase history in a database and extract optimal information. This allows the service provider to provide more appropriate information by referring to the user's past purchase history. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's past purchase history into a generating AI and have the generating AI perform the task of providing appropriate information.

[0046] The information provider can adjust the priority of information based on the user's current areas of interest at the time of delivery. For example, the information provider can adjust the priority of information based on the user's current areas of interest. For example, the information provider can obtain the user's areas of interest from survey results and adjust the priority of information. The information provider can also adjust the priority of information based on the user's areas of interest. For example, the information provider can analyze the user's behavior history, identify areas of interest, and adjust the priority of information. The information provider can also adjust the priority of information by referring to the user's areas of interest. For example, the information provider can save the user's behavior history in a database, identify areas of interest, and adjust the priority of information. This allows for the provision of more relevant information by adjusting the priority of information based on the user's current areas of interest. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the information provider can input the user's areas of interest into a generating AI and have the generating AI perform the adjustment of information priority.

[0047] The service provider can prioritize providing highly relevant information by considering the user's geographical location information at the time of provision. For example, the service provider can provide highly relevant information based on the user's geographical location information. For example, the service provider can obtain the user's geographical location information from GPS data and provide highly relevant information. The service provider can also provide highly relevant information by considering the user's geographical location information. For example, the service provider can obtain the user's geographical location information from a location information service and provide highly relevant information. The service provider can also provide highly relevant information by referring to the user's geographical location information. For example, the service provider can store the user's geographical location information in a database and provide highly relevant information. This allows the service provider to prioritize providing highly relevant information by considering the user's geographical location information. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI. For example, the service provider can input the user's geographical location information into a generating AI and have the generating AI perform the provision of highly relevant information.

[0048] The service provider can analyze the user's social media activity and provide relevant information at the time of service provision. For example, the service provider can analyze the user's social media activity and provide relevant information. For example, the service provider can store the user's social media activity in a database and extract relevant information. The service provider can also provide relevant information based on the user's social media activity. For example, the service provider can analyze the user's social media activity and provide relevant information. The service provider can also provide relevant information by referring to the user's social media activity. For example, the service provider can store the user's social media activity in a database and extract relevant information. This allows the service provider to provide relevant information by analyzing the user's social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's social media activity into a generating AI and have the generating AI perform the provision of relevant information.

[0049] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0050] The AI ​​support concierge system can refer to a user's purchase history and provide product recommendations based on past purchasing patterns. For example, if a user has previously purchased a computer from a specific brand, it can recommend new products and related accessories from the same brand. It can also refer to reviews and ratings of products the user has previously purchased and recommend products with similar ratings. Furthermore, it can analyze a user's purchase history and recommend products tailored to the season or events. This makes it easier for users to find products that suit their preferences and needs.

[0051] The AI ​​support concierge system can use the user's geographical location to provide region-specific information. For example, if the user is in a specific area, it can recommend popular products and services in that area. It can also provide information on local events and sales. Furthermore, if the user is traveling, it can provide information on tourist attractions and restaurants in their destination. This allows users to obtain useful information relevant to their current location.

[0052] The AI ​​support concierge system can analyze a user's social media activity and recommend relevant products and services. For example, it can recommend brands and products that the user frequently mentions on social media. It can also recommend products and services recommended by the user's followers and friends. Furthermore, it can extract topics of interest from the user's social media activity and recommend related products and services. This makes it easier for users to find products and services that are based on their interests.

[0053] The support concierge AI system can analyze a user's purchase history and provide customized coupons and discount information based on past purchasing patterns. For example, if a user frequently purchases products from a particular brand in the past, it can provide discount coupons for products from that brand. It can also provide discount information for products in a specific category if the user frequently purchases items within that category. Furthermore, it can analyze a user's purchase history and provide discount information tailored to specific events or seasons. This allows users to receive advantageous information that matches their purchasing patterns.

[0054] The support concierge AI system can refer to a user's past conversation history and prioritize the transcription of specific keywords. For example, it can prioritize the transcription of keywords that the user has frequently used in the past. It can also extract important keywords from the user's past conversation history and prioritize their transcription. Furthermore, when a user talks about a specific topic, it can prioritize the transcription of keywords related to that topic. In this way, by referring to the user's past conversation history, important keywords can be transcribed without being missed.

[0055] The AI ​​support concierge system can provide region-specific coupons and discounts by taking into account the user's geographical location. For example, if a user is in a specific region, it can provide coupons usable at stores in that region. It can also provide information on local events and sales. Furthermore, if a user is traveling, it can provide discount information on tourist attractions and restaurants in their travel destination. This allows users to obtain useful information relevant to their current location.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The monitoring unit monitors conversations in real time and transcribes them into text. For example, when a user talks to a store employee about a product or service, speech recognition technology is used to transcribe the conversation into text. It can also analyze the content of the conversation in real time and extract important information. For example, it can detect specific keywords and highlight those parts. Step 2: The analysis unit analyzes the transcribed conversation and checks the accuracy of the store clerk's statements. For example, it uses natural language processing techniques to perform morphological analysis, grammatical analysis, and semantic analysis to understand the meaning, structure, and content of the store clerk's statements. Step 3: The service provider provides accurate information based on the results obtained by the analysis unit. For example, if the employee's statements contain errors or inaccuracies, it will point them out and provide correct information. It will also evaluate the accuracy of the employee's statements for the user, provide evidence, and enhance their reliability. Furthermore, it can provide recommendations based on the employee's statements.

[0058] (Example of form 2) The support concierge AI system according to an embodiment of the present invention is a system that uses a specialized support AI to deepen the user's understanding of products and services through conversations with store staff, thereby supporting purchases without regret. When a user converses with a store staff member about a product or service, the support AI monitors the conversation in real time and transcribes it into text. Next, the support AI analyzes the transcribed conversation to check the accuracy of the staff member's statements. If the staff member's statements contain errors or inaccurate information, the support AI points them out and provides correct information. This allows the user to gain a correct understanding and make purchases without regret. For example, if a user is considering purchasing a computer, smartphone, home, or insurance, they ask a store staff member a question. At this time, the support AI monitors the conversation in real time and transcribes it into text. For example, if the staff member says, "This computer is equipped with the latest processor," that statement is transcribed into text. Next, the support AI analyzes the transcribed conversation. The support AI uses natural language processing technology to check the accuracy of the staff member's statements. For example, if a salesperson says, "This computer has the latest processor," the support AI will cross-reference that information with the product database to verify its accuracy. If the salesperson's statement contains errors or inaccuracies, the support AI will point them out. For example, it might say, "This computer does not have the latest processor." Furthermore, the support AI will provide correct information, such as, "This computer has a previous generation processor." This allows users to gain a correct understanding and make purchases without regret. This system enables users to gain a correct understanding of products and services and make purchases without regret. In addition, knowing that a third party (the support AI) is monitoring the conversation encourages salespeople to be more careful about what they say and to provide accurate information based on evidence. For example, if a salesperson says, "This insurance covers all illnesses," the support AI will check the statement and point out any errors. This encourages salespeople to provide accurate information.This AI-powered support concierge can be used when purchasing a variety of products and services, such as computers, smartphones, homes, and insurance. For example, when purchasing a computer, it provides accurate information about specifications and functions, and when purchasing a home, it provides accurate information about property details and loan conditions. This allows users to make purchases with confidence. In this way, the AI ​​support concierge system enables users to gain a correct understanding of products and services and make purchases without regret.

[0059] The support concierge AI system according to this embodiment comprises a monitoring unit, an analysis unit, and a provision unit. The monitoring unit monitors conversations in real time and transcribes them into text. For example, when a user converses with a store clerk about products or services, the monitoring unit monitors the conversation in real time and transcribes it into text. The monitoring unit can transcribe conversations using, for example, speech recognition technology. The monitoring unit can also analyze the content of the conversation in real time and extract important information. For example, the monitoring unit can detect specific keywords in the conversation and highlight those parts. The analysis unit analyzes the transcribed conversation and checks the accuracy of the store clerk's statements. The analysis unit analyzes the transcribed conversation using, for example, natural language processing technology. The analysis unit can perform, for example, morphological analysis to analyze the meaning of the store clerk's statements. The analysis unit can also perform grammatical analysis to analyze the structure of the store clerk's statements. Furthermore, the analysis unit can perform semantic analysis to understand the content of the store clerk's statements. The provision unit provides accurate information based on the results obtained by the analysis unit. The service provider can, for example, point out errors or inaccuracies in a store clerk's statements and provide correct information. The service provider can also evaluate the accuracy of a store clerk's statements and provide correct information to the user. Furthermore, the service provider can provide the user with the basis for the store clerk's statements, increasing their credibility. In addition, the service provider can provide the user with recommendations based on the store clerk's statements. As a result, the support concierge AI system according to this embodiment allows users to gain a correct understanding of products and services and make purchases without regret.

[0060] The monitoring unit monitors conversations in real time and transcribes them into text. Specifically, when a user converses with a store employee about a product or service, the monitoring unit uses speech recognition technology to transcribe the conversation into text. For example, a deep learning-based speech recognition model is used. This model learns from a large amount of audio data to achieve highly accurate speech recognition. The monitoring unit can also analyze the content of conversations in real time and extract important information. For example, it can detect specific keywords in the conversation and highlight those parts. A keyword extraction algorithm using natural language processing technology is used for keyword detection. This algorithm can understand the context of the conversation and accurately extract important keywords. Furthermore, the monitoring unit can also perform sentiment analysis of the conversation. Sentiment analysis uses an emotion recognition model to grasp the emotional state of the user and the store employee. As a result, the monitoring unit can grasp not only the content of the conversation but also changes in emotions in real time and provide more detailed information. By combining these functions, the monitoring unit can accurately monitor conversations between users and store employees, extract important information, and transcribe it into text.

[0061] The analysis unit analyzes the transcribed conversation and checks the accuracy of the store clerk's statements. Specifically, it uses natural language processing techniques to analyze the transcribed conversation. The analysis unit can perform morphological analysis to analyze the meaning of the store clerk's statements. A morphological analyzer is used for morphological analysis, which divides the text into words and analyzes the meaning of each word. Furthermore, the analysis unit can also perform grammatical analysis to analyze the structure of the store clerk's statements. A grammatical analyzer is used for grammatical analysis, which analyzes the grammatical structure of the text and understands the structure of the sentences. Furthermore, the analysis unit can perform semantic analysis to understand the content of the store clerk's statements. A semantic analysis model is used for semantic analysis, which analyzes the meaning of the text and understands the content of the statements. Based on these analysis results, the analysis unit checks the accuracy of the store clerk's statements. For example, it verifies whether the store clerk's statements are based on facts and do not contain errors. The analysis unit can also refer to past data and knowledge bases to evaluate the reliability of the store clerk's statements. This allows the analysis unit to analyze the transcribed conversation with high accuracy and check the accuracy of the store clerk's statements.

[0062] The information delivery unit provides accurate information based on the results obtained by the analysis unit. Specifically, if a store employee's statement contains errors or inaccuracies, the unit will point them out and provide correct information. For example, the information delivery unit can evaluate the accuracy of a store employee's statement and provide the user with correct information. The information delivery unit can also provide users with the basis for a store employee's statement to increase its reliability. For example, the information delivery unit can provide the basis for a store employee's statement based on information from knowledge bases and databases referenced by the analysis unit. The information delivery unit can also provide users with recommendations based on a store employee's statement. For example, if a user asks about a specific product, the information delivery unit will provide detailed information and recommendations about that product. Furthermore, the information delivery unit can collect user feedback and continuously improve the accuracy and effectiveness of the information it provides. For example, it can evaluate whether users are satisfied with the information provided and whether the information was helpful, and improve the information provided based on the results. In this way, the information delivery unit provides users with accurate and reliable information, enabling users to gain a correct understanding of products and services.

[0063] The monitoring unit can monitor and transcribe conversations between users and store staff in real time when users talk about products or services. The monitoring unit can transcribe conversations using, for example, speech recognition technology. For example, the monitoring unit can record conversations between users and store staff in real time and transcribe them using speech recognition technology. The monitoring unit can also analyze the content of conversations in real time and extract important information. For example, the monitoring unit can detect specific keywords in the conversation and highlight those parts. This creates a foundation for providing accurate information by transcribing conversations between users and store staff in real time. Some or all of the above processing in the monitoring unit may be performed using, for example, AI, or not using AI. For example, the monitoring unit can have a generating AI perform the process of recording conversations between users and store staff in real time and transcribe them using speech recognition technology.

[0064] The analysis unit can analyze transcribed conversations using natural language processing technology and check the accuracy of the store clerk's statements. For example, the analysis unit can perform morphological analysis to analyze the meaning of the store clerk's statements. For example, the analysis unit can extract morphemes such as nouns and verbs from the transcribed conversation and analyze the meaning of the statements. The analysis unit can also perform grammatical analysis to analyze the structure of the store clerk's statements. For example, the analysis unit can analyze the grammatical structure of the transcribed conversation and check the accuracy of the statements. Furthermore, the analysis unit can perform semantic analysis to understand the content of the store clerk's statements. For example, the analysis unit can analyze the meaning of the transcribed conversation and check the accuracy of the statements. In this way, the accuracy of the store clerk's statements can be checked with high precision by using natural language processing technology. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input the transcribed conversation into a generating AI and have the generating AI perform a check of the accuracy of the statements.

[0065] The information provider can point out errors or inaccuracies in the employee's statements and provide correct information. For example, the information provider can evaluate the accuracy of the employee's statements and provide correct information to the user. For example, the information provider can point out errors in the employee's statements and provide correct information. The information provider can also increase the reliability of the employee's statements by showing the basis for them to the user. For example, the information provider can gain the user's trust by evaluating the accuracy of the employee's statements and showing the basis for it. Furthermore, the information provider can provide the user with recommendations based on the employee's statements. For example, the information provider can recommend appropriate products or services to the user based on the employee's statements. In this way, by pointing out incorrect information and providing correct information, the user can obtain accurate information. Some or all of the above processes in the information provider may be performed using AI, for example, or not using AI. For example, the information provider can have a generating AI perform the process of evaluating the accuracy of the employee's statements and providing correct information.

[0066] The information provision unit can provide accurate information when purchasing various products and services, such as personal computers, smartphones, homes, and insurance. For example, when purchasing a personal computer, the information provision unit can provide accurate information about the specifications and functions of the computer. For example, the information provision unit can provide accurate information about the property details and loan conditions when purchasing a home. For example, the information provision unit can provide accurate information about the property details and loan conditions of the home. Furthermore, when purchasing insurance, the information provision unit can provide accurate information about the content and conditions of the insurance. For example, the information provision unit can provide accurate information about various products and services, allowing users to make purchases with confidence. Some or all of the above processing in the information provision unit may be performed using AI, for example, or not using AI. For example, the information provision unit can have a generating AI perform the provision of information about the specifications and functions of a personal computer.

[0067] The monitoring unit can estimate the user's emotions and adjust the accuracy of conversation monitoring based on the estimated emotions. For example, if the user is nervous, the monitoring unit can increase the monitoring accuracy to ensure that important information is not missed. For example, the monitoring unit can capture the user's facial expressions with a camera, detect the state of tension using an emotion estimation algorithm, and adjust the monitoring accuracy. Conversely, if the user is relaxed, the monitoring unit can maintain normal monitoring accuracy and prioritize natural conversation. For example, the monitoring unit can record the user's voice, detect the relaxed state using voice analysis technology, and adjust the monitoring accuracy. Furthermore, if the user is in a hurry, the monitoring unit can increase the monitoring accuracy to quickly capture important information. For example, the monitoring unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors, detect the hurried state using an emotion estimation algorithm, and adjust the monitoring accuracy. This allows for monitoring without missing important information by adjusting the monitoring accuracy according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the monitoring unit may be performed using AI, or not using AI. For example, the monitoring unit can input user emotion data into the generation AI and have the generation AI perform emotion estimation.

[0068] The monitoring unit can add a filtering function to remove background and ambient noise when monitoring conversations. For example, the monitoring unit can remove background noise from the store and monitor only the conversation between the store clerk and the user. For example, the monitoring unit can remove background noise from the store using noise cancellation technology. The monitoring unit can also analyze ambient noise in real time and filter out sounds that are unnecessary for the conversation. For example, the monitoring unit can analyze ambient noise in real time using filtering technology and remove unnecessary sounds. The monitoring unit can also distinguish between the voice of the store clerk and the voice of the user and remove other sounds. For example, the monitoring unit can distinguish between the voice of the store clerk and the voice of the user using speech recognition technology and remove other sounds. This improves the accuracy of conversation monitoring by removing background and ambient noise. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can have a generating AI perform noise cancellation technology.

[0069] The monitoring unit can prioritize the transcription of specific keywords by referring to the user's past conversation history when monitoring a conversation. For example, the monitoring unit can prioritize the transcription of keywords that the user has frequently used in the past. For example, the monitoring unit can store the user's past conversation history in a database and extract specific keywords by performing frequency analysis. The monitoring unit can also extract important keywords from the user's past conversation history and prioritize their transcription. For example, the monitoring unit can analyze the user's past conversation history and extract keywords based on importance scores. Furthermore, when the user talks about a specific topic, the monitoring unit can prioritize the transcription of keywords related to that topic. For example, the monitoring unit can refer to the user's past conversation history and prioritize the transcription of keywords related to that topic. This ensures that important keywords are not missed by referring to the user's past conversation history. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the user's past conversation history into a generating AI and have the generating AI perform the extraction of specific keywords.

[0070] The monitoring unit can estimate the user's emotions and determine the priority of conversations to monitor based on the estimated emotions. For example, if the user is feeling anxious, the monitoring unit will prioritize monitoring important conversations. For instance, the monitoring unit can capture the user's facial expressions with a camera, detect the state of anxiety using an emotion estimation algorithm, and determine the priority of conversations. Furthermore, if the user is excited, the monitoring unit can monitor all conversations equally. For example, the monitoring unit can record the user's voice, detect the state of excitement using voice analysis technology, and determine the priority of conversations. Also, if the user is relaxed, the monitoring unit can prioritize monitoring normal conversations. For example, the monitoring unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors, detect the state of relaxation using an emotion estimation algorithm, and determine the priority of conversations. This allows for prioritizing important conversations by determining the priority of conversations according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the monitoring unit may be performed using AI, or not using AI. For example, the monitoring unit can input user emotion data into the generation AI and have the generation AI perform emotion estimation.

[0071] The monitoring unit can prioritize the transcription of highly relevant information by considering the user's geographical location when monitoring conversations. For example, if the user is in a specific region, the monitoring unit will prioritize the transcription of information related to that region. For example, the monitoring unit can obtain the user's geographical location from GPS data and prioritize the transcription of information related to that region. The monitoring unit can also prioritize the transcription of information related to the travel destination if the user is traveling. For example, the monitoring unit can obtain the user's geographical location from location information services and prioritize the transcription of information related to the travel destination. The monitoring unit can also prioritize the transcription of information related to the products and services of a store if the user is in a specific store. For example, the monitoring unit can refer to the user's geographical location and prioritize the transcription of information related to the products and services of that store. In this way, by considering the user's geographical location, highly relevant information can be prioritized for transcription. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without using AI. For example, the monitoring unit can input the user's geographical location information into the generating AI and have the AI ​​perform the task of converting highly relevant information into text.

[0072] The monitoring unit can analyze the user's social media activity when monitoring conversations and prioritize monitoring relevant conversations. For example, the monitoring unit can prioritize monitoring conversations related to topics that the user frequently mentions on social media. For example, the monitoring unit can store the user's social media activity in a database and extract relevant topics through frequency analysis. The monitoring unit can also extract topics of interest from the user's social media activity and prioritize monitoring relevant conversations. For example, the monitoring unit can analyze the user's social media activity and extract topics based on importance scores. The monitoring unit can also prioritize monitoring conversations related to accounts that the user follows on social media. For example, the monitoring unit can refer to the user's social media activity and prioritize monitoring conversations related to followed accounts. In this way, by analyzing the user's social media activity, relevant conversations can be prioritized. Some or all of the above processing in the monitoring unit may be performed using AI, for example, or without AI. For example, the monitoring unit can input the user's social media activity into a generating AI and have the generating AI perform the monitoring of relevant conversations.

[0073] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated emotions. For example, if the user is tense, the analysis unit can make the analysis algorithm more precise to minimize errors. For instance, the analysis unit can capture the user's facial expressions with a camera, detect the state of tension using an emotion estimation algorithm, and adjust the analysis algorithm accordingly. Conversely, if the user is relaxed, the analysis unit can maintain a normal analysis algorithm for a more natural result. For example, the analysis unit can record the user's voice, detect the relaxed state using voice analysis technology, and adjust the analysis algorithm accordingly. Furthermore, if the user is in a hurry, the analysis unit can speed up the analysis algorithm to provide results quickly. For example, the analysis unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors, detect the hurried state using an emotion estimation algorithm, and adjust the analysis algorithm accordingly. This improves the accuracy of the analysis by adjusting the analysis algorithm according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI perform emotion estimation.

[0074] The analysis unit can add a function to refer to past statements to evaluate the reliability of the employee's statements during analysis. For example, the analysis unit can analyze the employee's past statements and prioritize evaluating highly reliable statements. For example, the analysis unit can store the employee's past statements in a database and extract highly reliable statements by performing frequency analysis. The analysis unit can also identify statements with many errors from the employee's past statements and evaluate their reliability low. For example, the analysis unit can analyze the employee's past statements and identify statements with many errors. The analysis unit can also evaluate the reliability of the employee's current statements based on the employee's past statements. For example, the analysis unit can refer to the employee's past statements and evaluate the reliability of the current statements. This makes it possible to improve the reliability of statements by referring to the employee's past statements. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the employee's past statements into a generating AI and have the generating AI perform the reliability evaluation.

[0075] The analysis unit can more accurately identify errors and inaccurate information by considering the context of the employee's statements during analysis. For example, the analysis unit can identify errors by analyzing the context before and after the employee's statements. For example, the analysis unit can identify errors by analyzing the context before and after the transcribed conversation. The analysis unit can also identify errors and inaccurate information by considering the context of the employee's statements. For example, the analysis unit can identify errors and inaccurate information by analyzing the context of the transcribed conversation. The analysis unit can also identify errors and inaccurate information based on the context of the employee's statements. For example, the analysis unit can identify errors and inaccurate information by analyzing the context of the transcribed conversation. This allows for more accurate identification of errors and inaccurate information by considering the context of the employee's statements. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the context of the transcribed conversation into a generating AI and have the generating AI perform the identification of errors and inaccurate information.

[0076] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated emotions. For example, if the user is tense, the analysis unit can provide a simple and highly visible display method. For instance, the analysis unit can capture the user's facial expression with a camera, detect the state of tension using an emotion estimation algorithm, and provide a simple display method. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. For example, the analysis unit can record the user's voice, detect the relaxed state using voice analysis technology, and provide a detailed display method. Also, if the user is in a hurry, the analysis unit can provide a concise display method. For example, the analysis unit can collect the user's biometric data (heart rate and skin electrical activity) with sensors, detect the hurried state using an emotion estimation algorithm, and provide a concise display method. This improves visibility by adjusting the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the analysis unit may be performed using AI, or not using AI. For example, the analysis unit can input user emotion data into the generative AI and have the generative AI perform emotion estimation.

[0077] The analysis unit can improve the accuracy of its analysis by considering the geographical background of the employee's statements during analysis. For example, the analysis unit can improve the accuracy of its analysis by considering the geographical background of the employee's statements. For example, the analysis unit can store the geographical background of the employee's statements in a database and refer to it during analysis. The analysis unit can also improve the accuracy of its analysis based on the geographical background of the employee's statements. For example, the analysis unit can analyze the geographical background of the employee's statements and improve the accuracy of its analysis. The analysis unit can also improve the accuracy of its analysis by referring to the geographical background of the employee's statements. For example, the analysis unit can store the geographical background of the employee's statements in a database and refer to it during analysis. This improves the accuracy of the analysis by considering the geographical background of the employee's statements. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the geographical background of the employee's statements into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0078] The analysis unit can improve the accuracy of its analysis by referring to relevant industry news and trend information during the analysis process. For example, the analysis unit can improve the accuracy of its analysis by referring to relevant industry news. For example, the analysis unit can store industry news in a database and refer to it during the analysis. The analysis unit can also improve the accuracy of its analysis by referring to trend information. For example, the analysis unit can store trend information in a database and refer to it during the analysis. The analysis unit can also improve the accuracy of its analysis based on industry news and trend information. For example, the analysis unit can store industry news and trend information in a database and refer to it during the analysis. This improves the accuracy of the analysis by referring to relevant industry news and trend information. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input industry news and trend information into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0079] The information provider can estimate the user's emotions and adjust the way the information is presented based on the estimated emotions. For example, if the user is tense, the provider can provide simple and easily understandable information. For instance, the provider can capture the user's facial expression with a camera, detect the state of tension using an emotion estimation algorithm, and provide simple information. The provider can also provide detailed information if the user is relaxed. For example, the provider can record the user's voice, detect the state of relaxation using voice analysis technology, and provide detailed information. The provider can also provide concise information if the user is in a hurry. For example, the provider can collect the user's biometric data (heart rate and skin electrical activity) with sensors, detect the state of urgency using an emotion estimation algorithm, and provide concise information. This improves readability by adjusting the way information is presented according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the service provision unit may be performed using AI, for example, or without AI. For example, the service provision unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0080] The service provider can provide more appropriate information by referring to the user's past purchase history at the time of delivery. For example, the service provider can refer to the user's past purchase history and provide relevant information. For example, the service provider can store the user's past purchase history in a database and extract relevant information. The service provider can also provide appropriate information based on the user's past purchase history. For example, the service provider can analyze the user's past purchase history and provide appropriate information. The service provider can also analyze the user's past purchase history and provide optimal information. For example, the service provider can store the user's past purchase history in a database and extract optimal information. This allows the service provider to provide more appropriate information by referring to the user's past purchase history. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's past purchase history into a generating AI and have the generating AI perform the task of providing appropriate information.

[0081] The information provider can adjust the priority of information based on the user's current areas of interest at the time of delivery. For example, the information provider can adjust the priority of information based on the user's current areas of interest. For example, the information provider can obtain the user's areas of interest from survey results and adjust the priority of information. The information provider can also adjust the priority of information based on the user's areas of interest. For example, the information provider can analyze the user's behavior history, identify areas of interest, and adjust the priority of information. The information provider can also adjust the priority of information by referring to the user's areas of interest. For example, the information provider can save the user's behavior history in a database, identify areas of interest, and adjust the priority of information. This allows for the provision of more relevant information by adjusting the priority of information based on the user's current areas of interest. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the information provider can input the user's areas of interest into a generating AI and have the generating AI perform the adjustment of information priority.

[0082] The information provider can estimate the user's emotions and prioritize the information to be provided based on those emotions. For example, if the user is tense, the provider will prioritize providing important information. For instance, the provider might capture the user's facial expression with a camera, use an emotion estimation algorithm to detect the state of tension, and then prioritize providing important information. Similarly, if the user is relaxed, the provider can prioritize providing detailed information. For example, the provider might record the user's voice, use voice analysis technology to detect the relaxed state, and then prioritize providing detailed information. Furthermore, if the user is in a hurry, the provider can prioritize providing concise information. For example, the provider might collect the user's biometric data (heart rate and skin electrical activity) with sensors, use an emotion estimation algorithm to detect the hurried state, and then prioritize providing concise information. This allows the provider to prioritize information according to the user's emotions, thereby prioritizing the provision of important information. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the processing described above in the service provider may be performed using AI, or not using AI. For example, the service provider may input user emotion data into the generative AI and have the generative AI perform emotion estimation.

[0083] The service provider can prioritize providing highly relevant information by considering the user's geographical location information at the time of provision. For example, the service provider can provide highly relevant information based on the user's geographical location information. For example, the service provider can obtain the user's geographical location information from GPS data and provide highly relevant information. The service provider can also provide highly relevant information by considering the user's geographical location information. For example, the service provider can obtain the user's geographical location information from a location information service and provide highly relevant information. The service provider can also provide highly relevant information by referring to the user's geographical location information. For example, the service provider can store the user's geographical location information in a database and provide highly relevant information. This allows the service provider to prioritize providing highly relevant information by considering the user's geographical location information. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI. For example, the service provider can input the user's geographical location information into a generating AI and have the generating AI perform the provision of highly relevant information.

[0084] The service provider can analyze the user's social media activity and provide relevant information at the time of service provision. For example, the service provider can analyze the user's social media activity and provide relevant information. For example, the service provider can store the user's social media activity in a database and extract relevant information. The service provider can also provide relevant information based on the user's social media activity. For example, the service provider can analyze the user's social media activity and provide relevant information. The service provider can also provide relevant information by referring to the user's social media activity. For example, the service provider can store the user's social media activity in a database and extract relevant information. This allows the service provider to provide relevant information by analyzing the user's social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the user's social media activity into a generating AI and have the generating AI perform the provision of relevant information.

[0085] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0086] The AI ​​support concierge system can refer to a user's purchase history and provide product recommendations based on past purchasing patterns. For example, if a user has previously purchased a computer from a specific brand, it can recommend new products and related accessories from the same brand. It can also refer to reviews and ratings of products the user has previously purchased and recommend products with similar ratings. Furthermore, it can analyze a user's purchase history and recommend products tailored to the season or events. This makes it easier for users to find products that suit their preferences and needs.

[0087] The AI ​​support concierge system can estimate a user's emotions and personalize the purchasing process based on those emotions. For example, if a user is feeling anxious, the system will provide detailed explanations and additional support. If a user is excited, the system will support a quick purchase process. Furthermore, if a user is relaxed, the system can guide them through the purchasing process while maintaining a relaxed atmosphere. This allows users to receive optimal support tailored to their emotions.

[0088] The AI ​​support concierge system can use the user's geographical location to provide region-specific information. For example, if the user is in a specific area, it can recommend popular products and services in that area. It can also provide information on local events and sales. Furthermore, if the user is traveling, it can provide information on tourist attractions and restaurants in their destination. This allows users to obtain useful information relevant to their current location.

[0089] The AI ​​support concierge system can analyze a user's social media activity and recommend relevant products and services. For example, it can recommend brands and products that the user frequently mentions on social media. It can also recommend products and services recommended by the user's followers and friends. Furthermore, it can extract topics of interest from the user's social media activity and recommend related products and services. This makes it easier for users to find products and services that are based on their interests.

[0090] The AI ​​support concierge system can estimate a user's emotions and adjust how it explains products and services based on those emotions. For example, if a user is nervous, the system will provide a simple and easy-to-understand explanation. If the user is relaxed, it can provide more detailed information. Furthermore, if the user is in a hurry, it can provide a concise explanation that gets straight to the point. This allows users to receive the most relevant information based on their emotions.

[0091] The support concierge AI system can analyze a user's purchase history and provide customized coupons and discount information based on past purchasing patterns. For example, if a user frequently purchases products from a particular brand in the past, it can provide discount coupons for products from that brand. It can also provide discount information for products in a specific category if the user frequently purchases items within that category. Furthermore, it can analyze a user's purchase history and provide discount information tailored to specific events or seasons. This allows users to receive advantageous information that matches their purchasing patterns.

[0092] The AI ​​support concierge system can estimate a user's emotions and adjust its customer support response based on those emotions. For example, if a user is feeling anxious, the system will provide a polite and helpful response. If a user is agitated, it can provide a quick and efficient response. Furthermore, if a user is relaxed, it can maintain a relaxed atmosphere while providing support. This allows users to receive optimal customer support tailored to their emotions.

[0093] The support concierge AI system can refer to a user's past conversation history and prioritize the transcription of specific keywords. For example, it can prioritize the transcription of keywords that the user has frequently used in the past. It can also extract important keywords from the user's past conversation history and prioritize their transcription. Furthermore, when a user talks about a specific topic, it can prioritize the transcription of keywords related to that topic. In this way, by referring to the user's past conversation history, important keywords can be transcribed without being missed.

[0094] The support concierge AI system can estimate the user's emotions and adjust how recommended products are displayed based on those emotions. For example, if the user is stressed, it can provide a simple and highly visible display. If the user is relaxed, it can provide a display that includes more detailed information. Furthermore, if the user is in a hurry, it can provide a concise display. This allows users to view recommended products in the most suitable display format for their emotions.

[0095] The AI ​​support concierge system can provide region-specific coupons and discounts by taking into account the user's geographical location. For example, if a user is in a specific region, it can provide coupons usable at stores in that region. It can also provide information on local events and sales. Furthermore, if a user is traveling, it can provide discount information on tourist attractions and restaurants in their travel destination. This allows users to obtain useful information relevant to their current location.

[0096] The following briefly describes the processing flow for example form 2.

[0097] Step 1: The monitoring unit monitors conversations in real time and transcribes them into text. For example, when a user talks to a store employee about a product or service, speech recognition technology is used to transcribe the conversation into text. It can also analyze the content of the conversation in real time and extract important information. For example, it can detect specific keywords and highlight those parts. Step 2: The analysis unit analyzes the transcribed conversation and checks the accuracy of the store clerk's statements. For example, it uses natural language processing techniques to perform morphological analysis, grammatical analysis, and semantic analysis to understand the meaning, structure, and content of the store clerk's statements. Step 3: The service provider provides accurate information based on the results obtained by the analysis unit. For example, if the employee's statements contain errors or inaccuracies, it will point them out and provide correct information. It will also evaluate the accuracy of the employee's statements for the user, provide evidence, and enhance their reliability. Furthermore, it can provide recommendations based on the employee's statements.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0100] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0101] Each of the multiple elements described above, including the monitoring unit, analysis unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the monitoring unit monitors the conversation in real time using the camera 42 and microphone 38B of the smart device 14 and transcribes it into text using the control unit 46A. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the transcribed conversation using natural language processing technology to check the accuracy of the store clerk's statements. The provision unit is implemented in the specific processing unit 290 of the data processing unit 12 and provides accurate information based on the analysis results. The monitoring unit, analysis unit, and provision unit may also be implemented in the control unit 46A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0102] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0103] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0104] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0105] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0106] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0107] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0108] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0109] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0110] 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.

[0111] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0112] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0113] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0114] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0115] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0116] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0117] Each of the multiple elements described above, including the monitoring unit, analysis unit, and provision unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the monitoring unit monitors the conversation in real time using the camera 42 and microphone 238 of the smart glasses 214 and transcribes it into text using the control unit 46A. The analysis unit is implemented, for example, in the specific processing unit 290 of the data processing unit 12, which analyzes the transcribed conversation using natural language processing technology and checks the accuracy of the store clerk's statements. The provision unit is implemented, for example, in the specific processing unit 290 of the data processing unit 12, which provides accurate information based on the analysis results. The monitoring unit, analysis unit, and provision unit may also be implemented, for example, in the control unit 46A of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0118] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0119] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0120] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0121] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0122] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0124] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0125] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0126] 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.

[0127] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0128] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0129] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0130] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0131] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0132] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0133] Each of the multiple elements described above, including the monitoring unit, analysis unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the monitoring unit monitors the conversation in real time using the camera 42 and microphone 238 of the headset terminal 314 and transcribes it into text using the control unit 46A. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the transcribed conversation using natural language processing technology to check the accuracy of the store clerk's statements. The provision unit is implemented in the specific processing unit 290 of the data processing unit 12 and provides accurate information based on the analysis results. The monitoring unit, analysis unit, and provision unit may also be implemented in the control unit 46A of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0134] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0135] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0136] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0137] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0138] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0140] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0141] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0142] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0143] 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.

[0144] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0145] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0146] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0147] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0148] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0149] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements described above, including the monitoring unit, analysis unit, and provision unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the monitoring unit monitors the conversation in real time using the camera 42 and microphone 238 of the robot 414 and transcribes it into text using the control unit 46A. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the transcribed conversation using natural language processing technology to check the accuracy of the store clerk's statements. The provision unit is implemented in the specific processing unit 290 of the data processing unit 12 and provides accurate information based on the analysis results. The monitoring unit, analysis unit, and provision unit may also be implemented in the control unit 46A of the robot 414. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0151] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0152] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0153] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0154] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0155] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0156] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0157] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0158] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0159] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0160] 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.

[0161] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0162] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0163] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0164] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0165] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0166] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0167] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0168] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0169] (Note 1) A monitoring unit that monitors conversations in real time and transcribes them into text, The aforementioned monitoring unit analyzes the conversation transcribed into text and checks the accuracy of the store clerk's statements. The system includes a providing unit that provides accurate information based on the results obtained by the analysis unit. A system characterized by the following features. (Note 2) The monitoring unit, When users talk to store staff about products or services, the conversation is monitored in real time and transcribed into text. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Using natural language processing technology, the transcribed conversation is analyzed to check the accuracy of the store clerk's statements. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned supply unit is, If a store employee's statement contains errors or inaccurate information, point it out and provide correct information. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, Providing accurate information when purchasing various products and services such as personal computers, smartphones, homes, and insurance. The system described in Appendix 1, characterized by the features described herein. (Note 6) The monitoring unit, It estimates the user's emotions and adjusts the accuracy of conversation monitoring based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The monitoring unit, Add a filtering function to remove background noise and ambient sounds when monitoring conversations. The system described in Appendix 1, characterized by the features described herein. (Note 8) The monitoring unit, When monitoring conversations, the system prioritizes the transcription of specific keywords by referencing the user's past conversation history. The system described in Appendix 1, characterized by the features described herein. (Note 9) The monitoring unit, It estimates the user's emotions and determines the priority of conversations to monitor based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The monitoring unit, When monitoring conversations, the system prioritizes transcribing relevant information by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The monitoring unit, When monitoring conversations, analyze users' social media activity and prioritize monitoring relevant conversations. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, It estimates the user's emotions and adjusts the analysis algorithm based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, To evaluate the reliability of employee statements during analysis, we will add a function that references past statement history. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, the context of the store clerk's statements is taken into consideration to more accurately identify errors and inaccurate information. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, the geographical context of the store clerk's statements is taken into consideration to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, we refer to relevant industry news and trend information to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned supply unit is, It estimates the user's emotions and adjusts how the information provided is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, When providing information, we refer to the user's past purchase history to provide more relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, When providing information, we adjust the priority of the information based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, It estimates the user's emotions and prioritizes the information provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, When providing information, we prioritize providing highly relevant information, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing the service, we analyze the user's social media activity and provide relevant information. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A monitoring unit that monitors conversations in real time and transcribes them into text, The aforementioned monitoring unit analyzes the conversation transcribed into text and checks the accuracy of the store clerk's statements. The system includes a providing unit that provides accurate information based on the results obtained by the analysis unit. A system characterized by the following features.

2. The monitoring unit, When users talk to store staff about products or services, the conversation is monitored in real time and transcribed into text. The system according to feature 1.

3. The aforementioned analysis unit, Using natural language processing technology, the transcribed conversation is analyzed to check the accuracy of the store clerk's statements. The system according to feature 1.

4. The aforementioned supply unit is, If a store employee's statement contains errors or inaccurate information, point it out and provide correct information. The system according to feature 1.

5. The aforementioned supply unit is, Providing accurate information when purchasing various products and services such as personal computers, smartphones, homes, and insurance. The system according to feature 1.

6. The monitoring unit, It estimates the user's emotions and adjusts the accuracy of conversation monitoring based on the estimated user emotions. The system according to feature 1.

7. The monitoring unit, Add a filtering function to remove background noise and ambient sounds when monitoring conversations. The system according to feature 1.

8. The monitoring unit, When monitoring conversations, the system prioritizes the transcription of specific keywords by referencing the user's past conversation history. The system according to feature 1.

9. The monitoring unit, It estimates the user's emotions and determines the priority of conversations to monitor based on the estimated user emotions. The system according to feature 1.

10. The monitoring unit, When monitoring conversations, the system prioritizes transcribing relevant information by considering the user's geographical location. The system according to feature 1.

Images