System

Abstract

The system provided by the embodiment of the invention aims to prevent information misregistration and errors during customer response. A system according to an embodiment includes a reading unit, an analysis unit, a comparison unit, a warning unit, and a reception unit. The reading part is used for reading conversation content with a client. The analysis part is used for analyzing the call content read by the reading part. And the comparison part is used for comparing the PC picture information registered by the staff. And the warning part gives a warning when the information compared by the comparison part is different. The reception reading part is used for reading reception content of the shop head.

Description

Technical Field

[0001] The technology disclosed herein relates to a system. Background Technology

[0002] Patent Document 1 discloses a personalized chatbot control method executed by at least one processor, the method comprising: receiving user speech; adding the user speech to a prompt containing instructions related to a chatbot role; encoding the prompt; and inputting the encoded prompt into a language model to generate chatbot speech in response to the user speech.

[0003] Patent document 1: Japanese Patent Application Publication No. 2022-180282. Summary of the Invention

[0004] In the existing technology, there is a lack of effective means to prevent customers from misregistering or making mistakes when responding to information, and there is room for improvement.

[0005] The system involved in this technical solution is designed to prevent customers from making mistakes in registering information.

[0006] The system involved in this technical solution includes a reading unit, a parsing unit, a comparison unit, an alert unit, and a reception reading unit. The reading unit reads the content of calls with customers. The parsing unit parses the call content read by the reading unit. The comparison unit compares the content with the PC screen information registered by staff. The alert unit issues an alert when discrepancies are found in the information compared by the comparison unit. The reception reading unit reads the reception information from the store.

[0007] The system involved in this technical solution can prevent customers from making mistakes in information registration. Attached Figure Description

[0008] Figure 1 This is a conceptual diagram illustrating an example of the configuration of a data processing system according to the first embodiment.

[0009] Figure 2 This is a conceptual diagram illustrating an example of the main functions of the data processing apparatus and smart device according to the first embodiment.

[0010] Figure 3 This is a conceptual diagram illustrating an example of the data processing system configuration in the second embodiment.

[0011] Figure 4 This is a conceptual diagram illustrating an example of the main functions of the data processing device and smart glasses according to the second embodiment.

[0012] Figure 5 This is a conceptual diagram illustrating an example of the data processing system configuration in the third embodiment.

[0013] Figure 6 This is a conceptual diagram illustrating an example of the main functions of the data processing device and head-mounted terminal according to the third embodiment.

[0014] Figure 7 This is a conceptual diagram illustrating an example of the data processing system configuration in the fourth embodiment.

[0015] Figure 8 This is a conceptual diagram illustrating an example of the functions of the main parts of the data processing device and robot according to the fourth embodiment.

[0016] Figure 9 It represents an emotion graph that maps multiple emotions.

[0017] Figure 10 It represents an emotion graph that maps multiple emotions.

[0018] Explanation of reference numerals in the attached figures

[0019] Data processing systems 10, 210, 310, and 410

[0020] 12 Data processing devices

[0021] 14 Smart devices

[0022] 214 Smart Glasses

[0023] 314 Head-mounted terminal

[0024] 414 Robot. Detailed Implementation

[0025] Hereinafter, an example of an implementation of the system involved in this disclosure will be described with reference to the accompanying drawings.

[0026] First, let's explain the terms used in the following description.

[0027] In the following embodiments, the processor (hereinafter referred to as "processor"), as indicated by the reference numerals, can be a single computing device or a combination of multiple computing devices. Furthermore, a processor can be a single computing device or a combination of multiple computing devices. Examples of computing devices 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), etc.

[0028] In the following embodiments, RAM (Random Access Memory), as indicated in the figures, is a memory for temporary information storage that is used by the processor as working memory.

[0029] In the following embodiments, the memory, as indicated by the reference numerals, is one or more non-volatile storage devices used to store various programs and parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), disks (e.g., hard disks), or magnetic tapes, etc.

[0030] In the following embodiments, the communication I / F (Interface) with reference numerals is an interface including a communication processor and an antenna, etc. The communication I / F is responsible for 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).

[0031] In the following implementation, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it can be only A, only B, or a combination of A and B. Furthermore, in this specification, when "and / or" connects more than three items, the same approach as "A and / or B" applies.

[0032] First Implementation Method

[0033] Figure 1 An example of the configuration of the data processing system 10 according to the first embodiment is shown.

[0034] like Figure 1 As shown, the data processing system 10 includes a data processing device 12 and an intelligent device 14. An example of the data processing device 12 is a server.

[0035] 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, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0036] The smart device 14 includes a computer 36, a receiver 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. In addition, the receiver 38, output device 40, and camera 42 are also connected to the bus 52.

[0037] The receiving device 38 includes a touchscreen 38A and a microphone 38B, etc., for receiving user input. The touchscreen 38A receives user input generated by contact with an indicator (e.g., a pen or finger). The microphone 38B receives user input generated by sound by detecting the user's voice. The control unit 46A sends data representing user input received via the touchscreen 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, a specific processing unit 290 (see reference...) Figure 2 Get the data that represents the user input.

[0038] The output device 40 includes a display 40A and a speaker 40B, etc., and presents data to the user by outputting data in a user-perceptible form (e.g., sound and / or text). The display 40A displays visual information such as text and images according to instructions from the processor 46. The speaker 40B outputs sound 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 imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0039] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for sending and receiving various information between processor 46 and processor 28 via network 54.

[0040] Figure 2 An example of the main functions of the data processing device 12 and the smart device 14 is shown.

[0041] like Figure 2 As shown, in the data processing apparatus 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the memory 32. The specific processing program 56 is an example of a "program" as understood in this disclosure. The processor 28 reads the specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. Specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0042] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes inferring and predicting the user's emotions, performing various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0043] In the smart device 14, specific processing is performed by the processor 46. A specific processing program 60 is stored in the memory 50. The specific processing program 60 is used in conjunction with the data processing system 10. The processor 46 reads the specific processing program 60 from the memory 50 and executes the read specific processing program 60 on the RAM 48. Specific processing is implemented by the processor 46 operating as a control unit 46A based on the specific processing program 60 executed on the RAM 48. Furthermore, the smart device 14 may also have the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and use these models to perform the same processing as the specific processing unit 290.

[0044] 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 the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. Furthermore, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of the processing performed by the data processing system 10 of the first embodiment will be described.

[0045] Implementation Method 1

[0046] The information incident prevention system of this invention utilizes AI to prevent information incidents during customer interactions. This system first allows AI to read the content of a customer's call. Then, the AI ​​compares this content with the PC screen information recorded by staff. If there is a discrepancy between the call information and the recorded content, the AI ​​will issue a warning. This prevents errors and reduces information incidents. For example, if customer A says, "Because I'm moving, please change my address from Tokyo to Fukuoka Prefecture," the AI ​​reads the call content and compares it with the PC screen information recorded by staff. If staff mistakenly record the information as customer B, the AI ​​will issue a warning to prevent errors. Through this mechanism, AI can automatically verify the content without relying on manual double-checking, preventing errors. This reduces information incidents and shortens the time required for recovery and countermeasures. Furthermore, it can also be applied to in-store reception to prevent similar incidents. Therefore, the information incident prevention system can prevent information incidents during customer interactions and reduce errors.

[0047] The information incident prevention system according to this embodiment includes a reading unit, a parsing unit, a comparison unit, a warning unit, and a reception reading unit. The reading unit reads the content of calls with customers. For example, the reading unit can read the content of voice calls, video calls, and text chats. The parsing unit parses the call content read by the reading unit. For example, the parsing unit can parse the call content using methods such as speech recognition, sentiment analysis, and keyword extraction. The comparison unit compares the information with the PC screen information registered by staff. For example, the comparison unit can perform the comparison based on standards such as consistency rate or similarity calculation with a database. The warning unit issues a warning when discrepancies are found in the information compared by the comparison unit. The warning unit can display the warning through pop-up notifications or voice alarms. The reception reading unit reads the reception content at the store. For example, the reception reading unit can read the reception content of face-to-face reception, online reception, and chat responses. Therefore, the information incident prevention system according to this embodiment can prevent information incidents during customer responses and reduce errors.

[0048] The reading unit is used to read the content of conversations with customers. It can read content from various types of calls, such as voice calls, video calls, and text chats. Specifically, during voice calls, voice data is acquired through a microphone; during video calls, image and voice data are acquired through a camera and microphone. During text chats, chat logs are acquired and saved in real time. This data is sent to a central server for storage via a secure communication protocol. The reading unit can utilize noise reduction technology to remove background noise, improving the clarity of the call content. Furthermore, voice data is converted into text data by a speech recognition engine for easier processing by the parsing unit. During video calls, image data is preprocessed using facial recognition technology to capture customer expressions and movements. During text chats, natural language processing technology is used to understand the context and extract important keywords and phrases. Thus, the reading unit can accurately and efficiently collect data for various call formats. Furthermore, the reading unit can flexibly respond to specific situations or conditions by adjusting the data collection frequency and precision. For example, when important dialogues or specific keywords are detected, the collection frequency can be increased to obtain detailed data. Therefore, the reading unit can collect data efficiently and effectively, improving the overall performance of the system.

[0049] The analysis unit is used to analyze the call content read by the reading unit. The analysis unit can analyze the call content using methods such as speech recognition, sentiment analysis, and keyword extraction. Specifically, speech recognition technology converts speech data into text data, and natural language processing technology is used to analyze the text data. During sentiment analysis, the emotional state of the customer is inferred based on the tone, speed, and context of the speech. For example, a high tone and fast speech may indicate anger or excitement. During keyword extraction, preset important keywords or phrases are detected to grasp the key points of the call. Thus, the analysis unit can perform detailed analysis of the call content and extract important information. Furthermore, the analysis unit can utilize machine learning algorithms to improve analysis accuracy based on historical data. For example, by learning from past call data, specific patterns or trends can be detected to predict future call content or assess risks. The analysis unit can also use anomaly detection algorithms to detect abnormal patterns or data and issue timely warnings. Therefore, the analysis unit can not only monitor the situation in real time but also handle long-term risk management and anomaly detection, improving the overall reliability and security of the system.

[0050] The comparison department compares PC screen information registered by staff. The comparison department can perform comparisons based on standards such as consistency rate or similarity calculation with a database. Specifically, it acquires screenshots of staff PC screens or operation logs and compares them with the legitimate information stored in the database. During comparison, image recognition or text mining technologies are used to analyze the screen information and calculate the consistency rate or similarity. For example, it confirms whether the customer information entered by the staff matches the information in the database, issuing a warning if there is a discrepancy. It can also analyze operation logs to detect improper operations or abnormal patterns. Thus, the comparison department can monitor staff operations in real time to ensure information accuracy. Furthermore, the comparison department can dynamically adjust the comparison benchmark based on historical data. For example, when mis-inputs occur frequently during specific periods or under certain circumstances, a corresponding comparison benchmark can be set to improve accuracy. The comparison department can also use anomaly detection algorithms to detect abnormal patterns or data and issue timely warnings. Therefore, the comparison department can not only monitor the situation in real time but also handle long-term risk management and anomaly detection, improving the overall reliability and security of the system.

[0051] The Warning Department issues warnings when discrepancies arise in the information compared by the Comparison Department. Warnings can be displayed via pop-up notifications or voice alerts. Specifically, pop-up notifications are displayed on staff PCs to draw attention. Voice alerts can also be used to issue immediate warnings to staff. Furthermore, the Warning Department meticulously records warning details for later verification. For example, it records the time, content, and response to the warning for administrator review. This allows the Warning Department to issue real-time warnings to staff, preventing information incidents. The Warning Department can also dynamically adjust the frequency and content of warnings. For example, when warnings are frequent for specific staff or situations, corresponding warning benchmarks can be set to improve accuracy. The Warning Department can also collect user feedback to continuously improve the accuracy and effectiveness of warnings. For example, warning content can be adjusted and improved based on feedback from staff who receive warnings. Thus, the Warning Department can provide users with rapid and accurate warnings, minimizing information incidents.

[0052] The reception reading department is used to read reception content from the store. This department can read content from face-to-face reception, online reception, and chat responses. Specifically, for face-to-face reception, it acquires voice and video data through a microphone and camera; for online reception, it acquires voice and video data through a video call system. For chat responses, it acquires and saves chat logs in real time. This data is sent to a central server for storage via a secure communication protocol. The reception reading department can use noise reduction technology to remove background noise, improving the clarity of the reception content. Furthermore, voice data is converted into text data by a speech recognition engine for easier processing by the parsing department. Video data undergoes preprocessing of customer expressions and movements using facial recognition technology. For chat responses, natural language processing technology is used to understand the context and extract important keywords and phrases. Thus, the reception reading department can accurately and efficiently collect data for various reception methods. Furthermore, the reception reading department can adjust the data collection frequency and precision to flexibly respond to specific situations or conditions. For example, when important dialogues or specific keywords are detected, the collection frequency can be increased to obtain detailed data. Therefore, the reception reading department can collect data efficiently and effectively, improving the overall system performance.

[0053] The reading unit can be equipped with filtering capabilities to remove background noise and other sounds when reading call content. For example, the reading unit can analyze background noise generated during the call in real time, and use AI to remove the noise for clear call content reading. Furthermore, the reading unit can also filter noise in specific frequency bands, allowing AI to extract important voice information. The reading unit can also learn ambient sounds through AI and automatically remove specific noise patterns. Thus, by removing background noise and other sounds, the call content can be read clearly. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reading unit can input the voice data from the call into a generative AI, which will then perform noise removal.

[0054] The reading unit can emphasize specific keywords or phrases when reading call content. For example, the reading unit can use AI to automatically detect and emphasize important keywords in the call content. The reading unit can also use AI to prioritize extracting specific phrases and emphasize them according to their importance. Furthermore, the reading unit can use AI to emphasize important information based on a preset keyword list. Therefore, by emphasizing important keywords or phrases, important information can be avoided. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the reading unit can input the voice data of the call content into a generative AI, which will then emphasize keywords or phrases.

[0055] The reading unit can automatically record the start and end times of a call while reading its content. For example, the reading unit can automatically record the start time via AI at the instant the call begins. It can also automatically record the end time via AI and calculate the total call duration. Furthermore, the reading unit can record the start and end times of the call in real time while reading the content for easy review later. Therefore, by automatically recording the start and end times, the total call duration can be accurately determined. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reading unit can input the start and end times of the call into a generative AI, which will then perform the recording.

[0056] The reading unit can convert call content into text in real time while reading it. For example, the reading unit can use AI to convert the call content into text and display it instantly. The reading unit can also use AI to convert speech into text and record it in real time while reading the call content. The reading unit can also utilize speech recognition technology to have AI convert the call content into text in real time. Therefore, by converting the call content into text in real time, the content can be confirmed immediately. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reading unit can input the voice data of the call content into a generative AI, which will then perform text conversion.

[0057] The parsing unit can be equipped with the ability to consider the context of the call content during parsing to improve parsing accuracy. For example, the parsing unit can use AI to analyze the context of the call content and extract important information. Furthermore, the parsing unit can use AI to improve the accuracy of the parsing results based on considering the context of the call content. The parsing unit can also use AI to understand the context of the call content and accurately parse relevant information. Therefore, by considering the context of the call content, parsing accuracy can be improved. Some or all of the above processing can be implemented using AI, or AI can be omitted. For example, the parsing unit can input the text data of the call content into a generative AI, which will then perform context parsing.

[0058] The analysis unit can be equipped with the ability to apply different analysis algorithms based on the category of the call content during analysis. For example, when the call content is a complaint response, the analysis unit can use AI to apply a specific analysis algorithm. When the call content is an inquiry response, the analysis unit can also use AI to apply other analysis algorithms. Furthermore, when the call content is an order processing call, the analysis unit can use AI to select an appropriate analysis algorithm. Therefore, applying appropriate analysis algorithms based on the category of the call content can improve analysis accuracy. Some or all of the above processing can be achieved through AI, or it can be done without AI. For example, the analysis unit can input the text data of the call content into a generative AI, which can then perform category-based analysis.

[0059] The parsing unit can adjust the level of detail in the parsing based on the length of the call content. For example, when the call content is short, the parsing unit uses AI to perform detailed parsing and extract important information. When the call content is long, the parsing unit can also use AI to perform overall parsing and summarize key points. Furthermore, the parsing unit can adjust the level of detail in the parsing based on the length of the call content to provide appropriate information. Thus, adjusting the level of detail in the parsing based on the length of the call content can provide suitable information. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the parsing unit can input the text data of the call content into a generative AI, which will then perform length-based parsing.

[0060] The parsing unit can be equipped with the function of adjusting the order of parsing results based on the relevance of the call content during parsing. For example, the parsing unit can use AI to analyze the relevance of the call content and prioritize the display of important information. The parsing unit can also use AI to adjust the order of parsing results based on the relevance of the call content. Furthermore, the parsing unit can use AI to understand the relevance of the call content and display the parsing results in an appropriate order. Thus, by adjusting the order of parsing results based on the relevance of the call content, important information can be provided preferentially. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the parsing unit can input the text data of the call content into a generative AI, which will then perform relevance-based parsing.

[0061] The comparison unit can be equipped with the function of considering the change history of PC screen information during comparison to improve comparison accuracy. For example, the comparison unit can use AI to analyze the change history of PC screen information to improve comparison accuracy. The comparison unit can also use AI to consider the change history of PC screen information during comparison for accurate comparison. Furthermore, the comparison unit can use AI to learn from the change history of PC screen information to improve comparison accuracy. Therefore, by considering the change history of PC screen information, comparison accuracy can be improved. Some or all of the above processing can be implemented using AI, or AI can be omitted. For example, the comparison unit can input the change history data of PC screen information into a generative AI, which will then perform the comparison accuracy improvement.

[0062] The comparison unit can be equipped with the ability to apply different comparison algorithms based on the category of PC screen information during comparison. For example, when the PC screen information is customer information, the comparison unit uses AI to apply a specific comparison algorithm. When the PC screen information is order information, the comparison unit can also use AI to apply other comparison algorithms. Furthermore, when the PC screen information is inquiry information, the comparison unit can use AI to select an appropriate comparison algorithm. Therefore, by applying appropriate comparison algorithms based on the category of PC screen information, the comparison accuracy can be improved. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the comparison unit can input the PC screen information data into a generative AI, which will then perform category-based comparisons.

[0063] The comparison unit can determine the comparison priority based on the update frequency of the PC screen information during comparison. For example, the comparison unit can use AI to analyze the update frequency of the PC screen information and determine the comparison priority. The comparison unit can also use AI to consider the update frequency of the PC screen information during comparison and prioritize the comparison of important information. Furthermore, the comparison unit can adjust the comparison priority based on the update frequency of the PC screen information using AI. Therefore, by determining the comparison priority based on the update frequency of the PC screen information, important information can be compared preferentially. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the comparison unit can input the update frequency data of the PC screen information into a generative AI, which will then perform the priority determination.

[0064] The comparison unit can adjust the order of comparison results based on the relevance of PC screen information during comparison. For example, the comparison unit can use AI to analyze the relevance of PC screen information and prioritize the comparison of important information. The comparison unit can also use AI to consider the relevance of PC screen information and adjust the order of comparison results during comparison. Furthermore, the comparison unit can use AI to display the comparison results in a suitable order based on the relevance of PC screen information. Therefore, by adjusting the order of comparison results based on the relevance of PC screen information, important information can be displayed preferentially. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the comparison unit can input the relevance data of PC screen information into a generative AI, which will then perform the order adjustment.

[0065] The warning unit can improve warning accuracy by referencing past warning history when issuing a warning. For example, the warning unit can use AI to analyze past warning history to improve accuracy. The warning unit can also use AI to refer to past warning history to issue accurate warnings when issuing a warning. Furthermore, the warning unit can use AI to learn from past warning history to improve accuracy. Thus, by referring to past warning history, warning accuracy can be improved. Some or all of the above processes can be implemented using AI, or AI can be omitted. For example, the warning unit can input past warning history data into a generative AI, which will then perform accuracy improvement.

[0066] The warning unit can be equipped with the ability to apply different warning methods based on the severity of the warning. For example, for high-severity warnings, the warning unit can use AI to provide both voice and visual warnings simultaneously. For low-severity warnings, the warning unit can use AI to provide only visual warnings. Furthermore, the warning unit can use AI to select an appropriate warning method based on the severity of the warning. Thus, by selecting an appropriate warning method based on the severity of the warning, effective warnings can be provided. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the warning unit can input the severity data of the warning into a generative AI, which can then select the appropriate method.

[0067] The warning unit can be equipped with the function of adjusting the display order of warnings based on their frequency of occurrence. For example, the warning unit can use AI to analyze the frequency of warnings and prioritize the display of important warnings. The warning unit can also use AI to consider the frequency of warnings and prioritize the display of important information when a warning is issued. Furthermore, the warning unit can use AI to adjust the display order of warnings based on their frequency of occurrence. Thus, by adjusting the display order of warnings according to their frequency of occurrence, important information can be displayed preferentially. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the warning unit can input the warning frequency data into a generative AI, which will then perform the order adjustment.

[0068] The warning department can be equipped with the function of adjusting the order of warning content based on the relevance of warnings when a warning is issued. For example, the warning department can use AI to analyze the relevance of warnings and prioritize the display of important information. The warning department can also use AI to consider the relevance of warnings and adjust the order of warning content when a warning is issued. Furthermore, the warning department can use AI to display warning content in an appropriate order based on the relevance of warnings. Thus, by adjusting the order of warning content based on their relevance, important information can be prioritized. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the warning department can input the relevance data of warnings into a generative AI, which will then perform the order adjustment.

[0069] The reception reading unit can be equipped with filtering functions to remove background noise and other sounds when reading reception content. For example, the reception reading unit can analyze background noise generated during reception in real time, and use AI to remove noise for clear reading of the reception content. The reception reading unit can also filter noise in specific frequency bands, and use AI to extract important speech information. Furthermore, the reception reading unit can learn ambient sounds through AI and automatically remove specific noise patterns. Thus, by removing background noise and other sounds, the reception content can be read clearly. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reception reading unit can input the speech data from the reception into a generative AI, which will then perform noise removal.

[0070] The reception reading department can be equipped with the ability to emphasize specific keywords or phrases when reading reception content. For example, the reception reading department can use AI to automatically detect and emphasize important keywords in the reception content. The reception reading department can also use AI to prioritize the extraction of specific phrases and emphasize them according to their importance. Furthermore, the reception reading department can use AI to emphasize important information based on a preset keyword list. Therefore, by emphasizing important keywords or phrases, important information can be avoided. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reception reading department can input the voice data of the reception content into a generative AI, which will then perform the emphasis of keywords or phrases.

[0071] The reception reading department can automatically record the start and end times of receptions while reading reception content. For example, the reception reading department can automatically record the start time via AI at the instant the reception begins. It can also automatically record the end time via AI and calculate the total reception duration. Furthermore, the reception reading department can record the start and end times of receptions in real time while reading reception content for easy review later. Therefore, by automatically recording the start and end times of receptions, the total reception duration can be accurately determined. Some or all of the above processing can be achieved through AI, or it can be done without AI. For example, the reception reading department can input the start and end times of receptions into a generative AI, which will then perform the recording.

[0072] The reception reading department can be equipped with the ability to convert reception content into text in real time while reading it. For example, the reception reading department can use AI to convert the reception content into text and display it instantly. The reception reading department can also use AI to convert speech into text and record it in real time while reading reception content. Furthermore, the reception reading department can utilize speech recognition technology to have AI convert reception content into text in real time. Therefore, by converting reception content into text in real time, the content can be confirmed immediately. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reception reading department can input the speech data of the reception content into a generative AI, which will then perform text conversion.

[0073] The system involved in this embodiment is not limited to the examples described above. For example, various modifications can be made as described below.

[0074] When analyzing call content, the parsing unit can consider the call context to improve parsing accuracy. For example, the parsing unit can use AI to analyze the context of the call content and extract important information. Furthermore, the parsing unit can use AI to improve the accuracy of the parsing results based on considering the call context. In addition, the parsing unit can use AI to understand the context of the call content and accurately analyze relevant information. Therefore, by considering the context of the call content, parsing accuracy can be improved. Some or all of the above processing can be achieved through AI, or AI can be used without it. For example, the parsing unit can input the text data of the call content into a generative AI, which will then perform contextual parsing.

[0075] When issuing a warning, the warning department can refer to past warning history to improve warning accuracy. For example, the warning department can use AI to analyze past warning history to improve accuracy. The warning department can also use AI to refer to past warning history to issue accurate warnings. Furthermore, the warning department can use AI to learn from past warning history to improve accuracy. Thus, by referring to past warning history, warning accuracy can be improved. Some or all of the above processes can be implemented using AI, or AI can be omitted. For example, the warning department can input past warning history data into a generative AI, which will then perform accuracy improvements.

[0076] During comparison, the comparison unit can consider the change history of the PC screen information to improve comparison accuracy. For example, the comparison unit can use AI to analyze the change history of the PC screen information to improve comparison accuracy. The comparison unit can also use AI to consider the change history of the PC screen information during comparison for accurate comparison. Furthermore, the comparison unit can use AI to learn from the change history of the PC screen information to improve comparison accuracy. Therefore, by considering the change history of the PC screen information, comparison accuracy can be improved. Some or all of the above processing can be implemented using AI, or AI can be omitted. For example, the comparison unit can input the change history data of the PC screen information into a generative AI, which will then perform the comparison accuracy improvement.

[0077] The reading unit can be equipped with filtering functions to remove background noise and other sounds when reading call content. For example, the reading unit can analyze background noise generated during the call in real time, and use AI to remove noise to clearly read the call content. The reading unit can also filter noise in specific frequency bands, and use AI to extract important voice information. Furthermore, the reading unit can learn ambient sounds through AI and automatically remove specific noise patterns. Thus, by removing background noise and other sounds, the call content can be read clearly. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reading unit can input the voice data from the call into a generative AI, which will then perform noise removal.

[0078] During the analysis process, the parsing unit can adjust the level of detail based on the length of the call content. For example, when the call content is short, the parsing unit uses AI to perform detailed analysis and extract important information. When the call content is long, the parsing unit can also use AI to perform overall analysis and summarize key points. Furthermore, the parsing unit can adjust the level of detail based on the call content length to provide appropriate information. Thus, adjusting the level of detail based on the call content length provides suitable information. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the parsing unit can input the text data of the call content into a generative AI, which will then perform length-based parsing.

[0079] The following is a brief description of the processing flow of Implementation Method 1.

[0080] Step 1: The reading unit reads the content of the call with the customer. The reading unit can read, for example, the content of voice calls, video calls, and text chats;

[0081] Step 2: The parsing unit analyzes the call content read by the reading unit. The parsing unit can analyze the call content using methods such as speech recognition, sentiment analysis, and keyword extraction.

[0082] Step 3: The comparison department compares the information on the PC screen registered by the staff. The comparison department can perform the comparison based on criteria such as consistency rate or similarity calculation with the database.

[0083] Step 4: The warning unit issues a warning when discrepancies arise in the information compared by the comparison unit. The warning unit may display the warning via pop-up notifications or voice alerts, for example.

[0084] Step 5: The reception reading department reads the reception information from the store. This department can read information such as face-to-face reception, online reception, and chat responses.

[0085] Implementation Method 2

[0086] The information incident prevention system of this invention utilizes AI to prevent information incidents during customer interactions. This system first allows AI to read the content of a customer's call. Then, the AI ​​compares this content with the PC screen information recorded by staff. If there is a discrepancy between the call information and the recorded content, the AI ​​will issue a warning. This prevents errors and reduces information incidents. For example, if customer A says, "Because I'm moving, please change my address from Tokyo to Fukuoka Prefecture," the AI ​​reads the call content and compares it with the PC screen information recorded by staff. If staff mistakenly record the information as customer B, the AI ​​will issue a warning to prevent errors. Through this mechanism, AI can automatically verify the content without relying on manual double-checking, preventing errors. This reduces information incidents and shortens the time required for recovery and countermeasures. Furthermore, it can also be applied to in-store reception to prevent similar incidents. Therefore, the information incident prevention system can prevent information incidents during customer interactions and reduce errors.

[0087] The information incident prevention system according to this embodiment includes a reading unit, a parsing unit, a comparison unit, a warning unit, and a reception reading unit. The reading unit reads the content of calls with customers. For example, the reading unit can read the content of voice calls, video calls, and text chats. The parsing unit parses the call content read by the reading unit. For example, the parsing unit can parse the call content using methods such as speech recognition, sentiment analysis, and keyword extraction. The comparison unit compares the information with the PC screen information registered by staff. For example, the comparison unit can perform the comparison based on standards such as consistency rate or similarity calculation with a database. The warning unit issues a warning when discrepancies are found in the information compared by the comparison unit. The warning unit can display the warning through pop-up notifications or voice alarms. The reception reading unit reads the reception content at the store. For example, the reception reading unit can read the reception content of face-to-face reception, online reception, and chat responses. Therefore, the information incident prevention system according to this embodiment can prevent information incidents during customer responses and reduce errors.

[0088] The reading unit is used to read the content of conversations with customers. It can read content from various types of calls, such as voice calls, video calls, and text chats. Specifically, during voice calls, voice data is acquired through a microphone; during video calls, image and voice data are acquired through a camera and microphone. During text chats, chat logs are acquired and saved in real time. This data is sent to a central server for storage via a secure communication protocol. The reading unit can utilize noise reduction technology to remove background noise, improving the clarity of the call content. Furthermore, voice data is converted into text data by a speech recognition engine for easier processing by the parsing unit. During video calls, image data is preprocessed using facial recognition technology to capture customer expressions and movements. During text chats, natural language processing technology is used to understand the context and extract important keywords and phrases. Thus, the reading unit can accurately and efficiently collect data for various call formats. Furthermore, the reading unit can flexibly respond to specific situations or conditions by adjusting the data collection frequency and precision. For example, when important dialogues or specific keywords are detected, the collection frequency can be increased to obtain detailed data. Therefore, the reading unit can collect data efficiently and effectively, improving the overall performance of the system.

[0089] The analysis unit is used to analyze the call content read by the reading unit. The analysis unit can analyze the call content using methods such as speech recognition, sentiment analysis, and keyword extraction. Specifically, speech recognition technology converts speech data into text data, and natural language processing technology is used to analyze the text data. During sentiment analysis, the emotional state of the customer is inferred based on the tone, speed, and context of the speech. For example, a high tone and fast speech may indicate anger or excitement. During keyword extraction, preset important keywords or phrases are detected to grasp the key points of the call. Thus, the analysis unit can perform detailed analysis of the call content and extract important information. Furthermore, the analysis unit can utilize machine learning algorithms to improve analysis accuracy based on historical data. For example, by learning from past call data, specific patterns or trends can be detected to predict future call content or assess risks. The analysis unit can also use anomaly detection algorithms to detect abnormal patterns or data and issue timely warnings. Therefore, the analysis unit can not only monitor the situation in real time but also handle long-term risk management and anomaly detection, improving the overall reliability and security of the system.

[0090] The comparison department compares PC screen information registered by staff. The comparison department can perform comparisons based on standards such as consistency rate or similarity calculation with a database. Specifically, it acquires screenshots of staff PC screens or operation logs and compares them with the legitimate information stored in the database. During comparison, image recognition or text mining technologies are used to analyze the screen information and calculate the consistency rate or similarity. For example, it confirms whether the customer information entered by the staff matches the information in the database, issuing a warning if there is a discrepancy. It can also analyze operation logs to detect improper operations or abnormal patterns. Thus, the comparison department can monitor staff operations in real time to ensure information accuracy. Furthermore, the comparison department can dynamically adjust the comparison benchmark based on historical data. For example, when mis-inputs occur frequently during specific periods or under certain circumstances, a corresponding comparison benchmark can be set to improve accuracy. The comparison department can also use anomaly detection algorithms to detect abnormal patterns or data and issue timely warnings. Therefore, the comparison department can not only monitor the situation in real time but also handle long-term risk management and anomaly detection, improving the overall reliability and security of the system.

[0091] The Warning Department issues warnings when discrepancies arise in the information compared by the Comparison Department. Warnings can be displayed via pop-up notifications or voice alerts. Specifically, pop-up notifications are displayed on staff PCs to draw attention. Voice alerts can also be used to issue immediate warnings to staff. Furthermore, the Warning Department meticulously records warning details for later verification. For example, it records the time, content, and response to the warning for administrator review. This allows the Warning Department to issue real-time warnings to staff, preventing information incidents. The Warning Department can also dynamically adjust the frequency and content of warnings. For example, when warnings are frequent for specific staff or situations, corresponding warning benchmarks can be set to improve accuracy. The Warning Department can also collect user feedback to continuously improve the accuracy and effectiveness of warnings. For example, warning content can be adjusted and improved based on feedback from staff who receive warnings. Thus, the Warning Department can provide users with rapid and accurate warnings, minimizing information incidents.

[0092] The reception reading department is used to read reception content from the store. This department can read content from face-to-face reception, online reception, and chat responses. Specifically, for face-to-face reception, it acquires voice and video data through a microphone and camera; for online reception, it acquires voice and video data through a video call system. For chat responses, it acquires and saves chat logs in real time. This data is sent to a central server for storage via a secure communication protocol. The reception reading department can use noise reduction technology to remove background noise, improving the clarity of the reception content. Furthermore, voice data is converted into text data by a speech recognition engine for easier processing by the parsing department. Video data undergoes preprocessing of customer expressions and movements using facial recognition technology. For chat responses, natural language processing technology is used to understand the context and extract important keywords and phrases. Thus, the reception reading department can accurately and efficiently collect data for various reception methods. Furthermore, the reception reading department can adjust the data collection frequency and precision to flexibly respond to specific situations or conditions. For example, when important dialogues or specific keywords are detected, the collection frequency can be increased to obtain detailed data. Therefore, the reception reading department can collect data efficiently and effectively, improving the overall system performance.

[0093] The reading unit can infer the customer's emotions and adjust the accuracy of reading the call content based on the inferred emotions. For example, when the customer is nervous, the AI ​​can improve the accuracy of reading the call content by adjusting the tone and speed of the voice. When the customer is relaxed, the AI ​​can maintain the accuracy of reading the call content while focusing on a natural conversation flow. When the customer is anxious, the AI ​​can prioritize reading the important parts of the call content. Thus, adjusting the accuracy of reading the call content according to the customer's emotions can obtain more accurate information. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these. Some or all of the above processing can be done by AI, or AI can be used without AI. For example, the reading unit can input the customer's voice data into generative AI, which will then perform emotion inference.

[0094] The reading unit can be equipped with filtering capabilities to remove background noise and other sounds when reading call content. For example, the reading unit can analyze background noise generated during the call in real time, and use AI to remove the noise for clear call content reading. Furthermore, the reading unit can also filter noise in specific frequency bands, allowing AI to extract important voice information. The reading unit can also learn ambient sounds through AI and automatically remove specific noise patterns. Thus, by removing background noise and other sounds, the call content can be read clearly. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reading unit can input the voice data from the call into a generative AI, which will then perform noise removal.

[0095] The reading unit can emphasize specific keywords or phrases when reading call content. For example, the reading unit can use AI to automatically detect and emphasize important keywords in the call content. The reading unit can also use AI to prioritize extracting specific phrases and emphasize them according to their importance. Furthermore, the reading unit can use AI to emphasize important information based on a preset keyword list. Therefore, by emphasizing important keywords or phrases, important information can be avoided. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the reading unit can input the voice data of the call content into a generative AI, which will then emphasize keywords or phrases.

[0096] The reading unit can infer the customer's emotions and prioritize the reading of call content based on these inferred emotions. For example, when the customer is anxious, the AI ​​can prioritize reading important parts of the call based on that emotion. When the customer is excited, the AI ​​can prioritize reading calmer parts of the call based on that emotion. When the customer is calm, the AI ​​can read all parts of the call evenly based on that emotion. Thus, prioritizing call content based on the customer's emotions allows for the acquisition of important information first. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these. Some or all of the above processing can be achieved through AI, or AI can be used without it. For example, the reading unit can input the customer's voice data into generative AI, which will then perform emotion inference.

[0097] The reading unit can automatically record the start and end times of a call while reading its content. For example, the reading unit can automatically record the start time via AI at the instant the call begins. It can also automatically record the end time via AI and calculate the total call duration. Furthermore, the reading unit can record the start and end times of the call in real time while reading the content for easy review later. Therefore, by automatically recording the start and end times, the total call duration can be accurately determined. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reading unit can input the start and end times of the call into a generative AI, which will then perform the recording.

[0098] The reading unit can convert call content into text in real time while reading it. For example, the reading unit can use AI to convert the call content into text and display it instantly. The reading unit can also use AI to convert speech into text and record it in real time while reading the call content. The reading unit can also utilize speech recognition technology to have AI convert the call content into text in real time. Therefore, by converting the call content into text in real time, the content can be confirmed immediately. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reading unit can input the voice data of the call content into a generative AI, which will then perform text conversion.

[0099] The analysis department can infer the customer's emotions and adjust the expression of the analysis results based on the inferred emotions. For example, when the customer is anxious, the AI ​​can express the analysis results in an easy-to-understand and reassuring way. When the customer is excited, the AI ​​can express the analysis results in a calm and objective way. When the customer is relaxed, the AI ​​can express the analysis results in detail and nuance. Thus, by adjusting the expression of the analysis results according to the customer's emotions, more suitable analysis results can be provided. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these. Some or all of the above processing can be achieved by AI, or AI can be used without AI. For example, the analysis department can input the customer's voice data into generative AI, which will then perform emotion inference.

[0100] The parsing unit can be equipped with the ability to consider the context of the call content during parsing to improve parsing accuracy. For example, the parsing unit can use AI to analyze the context of the call content and extract important information. Furthermore, the parsing unit can use AI to improve the accuracy of the parsing results based on considering the context of the call content. The parsing unit can also use AI to understand the context of the call content and accurately parse relevant information. Therefore, by considering the context of the call content, parsing accuracy can be improved. Some or all of the above processing can be implemented using AI, or AI can be omitted. For example, the parsing unit can input the text data of the call content into a generative AI, which will then perform context parsing.

[0101] The analysis unit can be equipped with the ability to apply different analysis algorithms based on the category of the call content during analysis. For example, when the call content is a complaint response, the analysis unit can use AI to apply a specific analysis algorithm. When the call content is an inquiry response, the analysis unit can also use AI to apply other analysis algorithms. Furthermore, when the call content is an order processing call, the analysis unit can use AI to select an appropriate analysis algorithm. Therefore, applying appropriate analysis algorithms based on the category of the call content can improve analysis accuracy. Some or all of the above processing can be achieved through AI, or it can be done without AI. For example, the analysis unit can input the text data of the call content into a generative AI, which can then perform category-based analysis.

[0102] The analysis unit can infer the customer's emotions and prioritize the analysis results based on these inferred emotions. For example, when the customer is anxious, the AI ​​can prioritize displaying important analysis results based on that emotion. When the customer is excited, the AI ​​can prioritize displaying calm analysis results based on that emotion. When the customer is relaxed, the AI ​​can display all analysis results evenly based on that emotion. Thus, prioritizing analysis results based on the customer's emotions allows for the provision of important information first. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these. Some or all of the above processing can be achieved through AI, or AI can be used without it. For example, the analysis unit can input the customer's voice data into the generative AI, which will then perform emotion inference.

[0103] The parsing unit can adjust the level of detail in the parsing based on the length of the call content. For example, when the call content is short, the parsing unit uses AI to perform detailed parsing and extract important information. When the call content is long, the parsing unit can also use AI to perform overall parsing and summarize key points. Furthermore, the parsing unit can adjust the level of detail in the parsing based on the length of the call content to provide appropriate information. Thus, adjusting the level of detail in the parsing based on the length of the call content can provide suitable information. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the parsing unit can input the text data of the call content into a generative AI, which will then perform length-based parsing.

[0104] The parsing unit can be equipped with the function of adjusting the order of parsing results based on the relevance of the call content during parsing. For example, the parsing unit can use AI to analyze the relevance of the call content and prioritize the display of important information. The parsing unit can also use AI to adjust the order of parsing results based on the relevance of the call content. Furthermore, the parsing unit can use AI to understand the relevance of the call content and display the parsing results in an appropriate order. Thus, by adjusting the order of parsing results based on the relevance of the call content, important information can be provided preferentially. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the parsing unit can input the text data of the call content into a generative AI, which will then perform relevance-based parsing.

[0105] The comparison department can infer the customer's emotions and adjust the comparison benchmark based on the inferred emotions. For example, when the customer is anxious, the AI ​​can strictly set the comparison benchmark to prevent errors. When the customer is relaxed, the AI ​​can flexibly set the comparison benchmark, focusing on natural responses. When the customer is anxious, the AI ​​can quickly set the comparison benchmark for efficient responses. Thus, adjusting the comparison benchmark according to the customer's emotions can achieve more accurate comparisons. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these. Some or all of the above processing can be achieved by AI, or AI can be used without AI. For example, the comparison department can input the customer's voice data into the generative AI, which will then perform emotion inference.

[0106] The comparison unit can be equipped with the function of considering the change history of PC screen information during comparison to improve comparison accuracy. For example, the comparison unit can use AI to analyze the change history of PC screen information to improve comparison accuracy. The comparison unit can also use AI to consider the change history of PC screen information during comparison for accurate comparison. Furthermore, the comparison unit can use AI to learn from the change history of PC screen information to improve comparison accuracy. Therefore, by considering the change history of PC screen information, comparison accuracy can be improved. Some or all of the above processing can be implemented using AI, or AI can be omitted. For example, the comparison unit can input the change history data of PC screen information into a generative AI, which will then perform the comparison accuracy improvement.

[0107] The comparison unit can be equipped with the ability to apply different comparison algorithms based on the category of PC screen information during comparison. For example, when the PC screen information is customer information, the comparison unit uses AI to apply a specific comparison algorithm. When the PC screen information is order information, the comparison unit can also use AI to apply other comparison algorithms. Furthermore, when the PC screen information is inquiry information, the comparison unit can use AI to select an appropriate comparison algorithm. Therefore, by applying appropriate comparison algorithms based on the category of PC screen information, the comparison accuracy can be improved. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the comparison unit can input the PC screen information data into a generative AI, which will then perform category-based comparisons.

[0108] The comparison unit can infer the customer's emotions and adjust the display order of the comparison results based on the inferred emotions. For example, when the customer is anxious, the AI ​​can prioritize displaying important comparison results. When the customer is relaxed, the AI ​​can display all comparison results evenly. When the customer is anxious, the AI ​​can quickly display comparison results. Thus, adjusting the display order of comparison results based on the customer's emotions prioritizes important information. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these. Some or all of the above processing can be achieved by AI, or AI can be used without AI. For example, the comparison unit can input the customer's voice data into the generative AI, which will then perform emotion inference.

[0109] The comparison unit can determine the comparison priority based on the update frequency of the PC screen information during comparison. For example, the comparison unit can use AI to analyze the update frequency of the PC screen information and determine the comparison priority. The comparison unit can also use AI to consider the update frequency of the PC screen information during comparison and prioritize the comparison of important information. Furthermore, the comparison unit can adjust the comparison priority based on the update frequency of the PC screen information using AI. Therefore, by determining the comparison priority based on the update frequency of the PC screen information, important information can be compared preferentially. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the comparison unit can input the update frequency data of the PC screen information into a generative AI, which will then perform the priority determination.

[0110] The comparison unit can adjust the order of comparison results based on the relevance of PC screen information during comparison. For example, the comparison unit can use AI to analyze the relevance of PC screen information and prioritize the comparison of important information. The comparison unit can also use AI to consider the relevance of PC screen information and adjust the order of comparison results during comparison. Furthermore, the comparison unit can use AI to display the comparison results in a suitable order based on the relevance of PC screen information. Therefore, by adjusting the order of comparison results based on the relevance of PC screen information, important information can be displayed preferentially. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the comparison unit can input the relevance data of PC screen information into a generative AI, which will then perform the order adjustment.

[0111] The warning system can infer a customer's emotions and adjust the way warnings are displayed based on these inferences. For example, when a customer is anxious, the AI ​​can display the warning in an easy-to-understand and reassuring way. When a customer is excited, the AI ​​can display the warning in a calm and objective way. When a customer is relaxed, the AI ​​can display the warning in detail and with finesse. Thus, adjusting the warning display based on the customer's emotions provides more appropriate warnings. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these. Some or all of the above processing can be achieved through AI, or AI can be used without it. For example, the warning system can input the customer's voice data into generative AI, which will then perform emotion inference.

[0112] The warning unit can improve warning accuracy by referencing past warning history when issuing a warning. For example, the warning unit can use AI to analyze past warning history to improve accuracy. The warning unit can also use AI to refer to past warning history to issue accurate warnings when issuing a warning. Furthermore, the warning unit can use AI to learn from past warning history to improve accuracy. Thus, by referring to past warning history, warning accuracy can be improved. Some or all of the above processes can be implemented using AI, or AI can be omitted. For example, the warning unit can input past warning history data into a generative AI, which will then perform accuracy improvement.

[0113] The warning unit can be equipped with the ability to apply different warning methods based on the severity of the warning. For example, for high-severity warnings, the warning unit can use AI to provide both voice and visual warnings simultaneously. For low-severity warnings, the warning unit can use AI to provide only visual warnings. Furthermore, the warning unit can use AI to select an appropriate warning method based on the severity of the warning. Thus, by selecting an appropriate warning method based on the severity of the warning, effective warnings can be provided. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the warning unit can input the severity data of the warning into a generative AI, which can then select the appropriate method.

[0114] The alerting department can infer the customer's emotions and determine the priority of alerts based on these inferred emotions. For example, when a customer is anxious, the AI ​​can prioritize displaying important alerts based on that emotion. When a customer is excited, the AI ​​can prioritize displaying calming alerts based on that emotion. When a customer is relaxed, the AI ​​can display all alerts evenly based on that emotion. Thus, prioritizing alerts based on the customer's emotions allows for the display of important alerts. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the alerting department can input the customer's voice data into generative AI, which will then perform emotion inference.

[0115] The warning unit can be equipped with the function of adjusting the display order of warnings based on their frequency of occurrence. For example, the warning unit can use AI to analyze the frequency of warnings and prioritize the display of important warnings. The warning unit can also use AI to consider the frequency of warnings and prioritize the display of important information when a warning is issued. Furthermore, the warning unit can use AI to adjust the display order of warnings based on their frequency of occurrence. Thus, by adjusting the display order of warnings according to their frequency of occurrence, important information can be displayed preferentially. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the warning unit can input the warning frequency data into a generative AI, which will then perform the order adjustment.

[0116] The warning department can be equipped with the function of adjusting the order of warning content based on the relevance of warnings when a warning is issued. For example, the warning department can use AI to analyze the relevance of warnings and prioritize the display of important information. The warning department can also use AI to consider the relevance of warnings and adjust the order of warning content when a warning is issued. Furthermore, the warning department can use AI to display warning content in an appropriate order based on the relevance of warnings. Thus, by adjusting the order of warning content based on their relevance, important information can be prioritized. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the warning department can input the relevance data of warnings into a generative AI, which will then perform the order adjustment.

[0117] The reception reading department can infer a customer's emotional state and adjust the accuracy of its reading of the reception content based on this inference. For example, when a customer is nervous, the AI ​​can improve the accuracy of the reading by adjusting the tone and speed of their voice. When a customer is relaxed, the AI ​​can maintain accuracy while focusing on a natural conversation flow. When a customer is anxious, the AI ​​can prioritize reading important parts of the reception content. Thus, adjusting the accuracy of the reading based on the customer's emotional state yields more accurate information. Emotional inference can be achieved, for example, through emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these. Some or all of the above processing can be achieved through AI, or it can be done without AI. For example, the reception reading department can input the customer's voice data into a generative AI, which will then perform the emotion inference.

[0118] The reception reading unit can be equipped with filtering functions to remove background noise and other sounds when reading reception content. For example, the reception reading unit can analyze background noise generated during reception in real time, and use AI to remove noise for clear reading of the reception content. The reception reading unit can also filter noise in specific frequency bands, and use AI to extract important speech information. Furthermore, the reception reading unit can learn ambient sounds through AI and automatically remove specific noise patterns. Thus, by removing background noise and other sounds, the reception content can be read clearly. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reception reading unit can input the speech data from the reception into a generative AI, which will then perform noise removal.

[0119] The reception reading department can be equipped with the ability to emphasize specific keywords or phrases when reading reception content. For example, the reception reading department can use AI to automatically detect and emphasize important keywords in the reception content. The reception reading department can also use AI to prioritize the extraction of specific phrases and emphasize them according to their importance. Furthermore, the reception reading department can use AI to emphasize important information based on a preset keyword list. Therefore, by emphasizing important keywords or phrases, important information can be avoided. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reception reading department can input the voice data of the reception content into a generative AI, which will then perform the emphasis of keywords or phrases.

[0120] The reception reading department can infer a customer's emotional state and prioritize the reading of reception content based on this inferred emotion. For example, when a customer is anxious, the AI ​​can prioritize reading important reception content based on this emotion. Similarly, when a customer is excited, the AI ​​can prioritize reading calmer sections of the reception content based on this emotion. Furthermore, when a customer is calm, the AI ​​can read all reception content evenly based on this emotion. Thus, prioritizing reception content based on the customer's emotion allows for the acquisition of important information first. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these. Some or all of the above processing can be achieved through AI, or it can be done without AI. For example, the reception reading department can input the customer's voice data into a generative AI, which will then perform emotion inference.

[0121] The reception reading department can automatically record the start and end times of receptions while reading reception content. For example, the reception reading department can automatically record the start time via AI at the instant the reception begins. It can also automatically record the end time via AI and calculate the total reception duration. Furthermore, the reception reading department can record the start and end times of receptions in real time while reading reception content for easy review later. Therefore, by automatically recording the start and end times of receptions, the total reception duration can be accurately determined. Some or all of the above processing can be achieved through AI, or it can be done without AI. For example, the reception reading department can input the start and end times of receptions into a generative AI, which will then perform the recording.

[0122] The reception reading department can be equipped with the ability to convert reception content into text in real time while reading it. For example, the reception reading department can use AI to convert the reception content into text and display it instantly. The reception reading department can also use AI to convert speech into text and record it in real time while reading reception content. Furthermore, the reception reading department can utilize speech recognition technology to have AI convert reception content into text in real time. Therefore, by converting reception content into text in real time, the content can be confirmed immediately. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reception reading department can input the speech data of the reception content into a generative AI, which will then perform text conversion.

[0123] The system involved in this embodiment is not limited to the examples described above. For example, various modifications can be made as described below.

[0124] When analyzing call content, the parsing unit can consider the call context to improve parsing accuracy. For example, the parsing unit can use AI to analyze the context of the call content and extract important information. Furthermore, the parsing unit can use AI to improve the accuracy of the parsing results based on considering the call context. In addition, the parsing unit can use AI to understand the context of the call content and accurately analyze relevant information. Therefore, by considering the context of the call content, parsing accuracy can be improved. Some or all of the above processing can be achieved through AI, or AI can be used without it. For example, the parsing unit can input the text data of the call content into a generative AI, which will then perform contextual parsing.

[0125] When issuing a warning, the warning department can refer to past warning history to improve warning accuracy. For example, the warning department can use AI to analyze past warning history to improve accuracy. The warning department can also use AI to refer to past warning history to issue accurate warnings. Furthermore, the warning department can use AI to learn from past warning history to improve accuracy. Thus, by referring to past warning history, warning accuracy can be improved. Some or all of the above processes can be implemented using AI, or AI can be omitted. For example, the warning department can input past warning history data into a generative AI, which will then perform accuracy improvements.

[0126] During comparison, the comparison unit can consider the change history of the PC screen information to improve comparison accuracy. For example, the comparison unit can use AI to analyze the change history of the PC screen information to improve comparison accuracy. The comparison unit can also use AI to consider the change history of the PC screen information during comparison for accurate comparison. Furthermore, the comparison unit can use AI to learn from the change history of the PC screen information to improve comparison accuracy. Therefore, by considering the change history of the PC screen information, comparison accuracy can be improved. Some or all of the above processing can be implemented using AI, or AI can be omitted. For example, the comparison unit can input the change history data of the PC screen information into a generative AI, which will then perform the comparison accuracy improvement.

[0127] The reading unit can be equipped with filtering functions to remove background noise and other sounds when reading call content. For example, the reading unit can analyze background noise generated during the call in real time, and use AI to remove noise to clearly read the call content. The reading unit can also filter noise in specific frequency bands, and use AI to extract important voice information. Furthermore, the reading unit can learn ambient sounds through AI and automatically remove specific noise patterns. Thus, by removing background noise and other sounds, the call content can be read clearly. Some or all of the above processing can be achieved using AI, or it can be done without AI. For example, the reading unit can input the voice data from the call into a generative AI, which will then perform noise removal.

[0128] During the analysis process, the parsing unit can adjust the level of detail based on the length of the call content. For example, when the call content is short, the parsing unit uses AI to perform detailed analysis and extract important information. When the call content is long, the parsing unit can also use AI to perform overall analysis and summarize key points. Furthermore, the parsing unit can adjust the level of detail based on the call content length to provide appropriate information. Thus, adjusting the level of detail based on the call content length provides suitable information. Some or all of the above processing can be implemented using AI, or it can be done without AI. For example, the parsing unit can input the text data of the call content into a generative AI, which will then perform length-based parsing.

[0129] The reading unit can infer the customer's emotions and adjust the accuracy of reading the call content based on the inferred emotions. For example, when the customer is nervous, the AI ​​can improve the accuracy of reading the call content by adjusting the tone and speed of the voice. When the customer is relaxed, the AI ​​can maintain the accuracy of reading the call content while focusing on a natural conversation flow. In addition, when the customer is anxious, the AI ​​can prioritize reading the important parts of the call content. Thus, adjusting the accuracy of reading the call content according to the customer's emotions can obtain more accurate information. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these. Some or all of the above processing can be done by AI, or AI can be used without AI. For example, the reading unit can input the customer's voice data into generative AI, which will then perform emotion inference.

[0130] The analysis department can infer the customer's emotions and adjust the expression of the analysis results based on the inferred emotions. For example, when the customer is anxious, the AI ​​can express the analysis results in an easy-to-understand and reassuring way. When the customer is excited, the AI ​​can express the analysis results in a calm and objective way. Furthermore, when the customer is relaxed, the AI ​​can express the analysis results in detail and nuance. Thus, by adjusting the expression of the analysis results according to the customer's emotions, more suitable analysis results can be provided. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text generation AI (such as LLM) or multimodal generation AI, but is not limited to these. Some or all of the above processing can be achieved by AI, or AI can be used without AI. For example, the analysis department can input the customer's voice data into generative AI, which will then perform emotion inference.

[0131] The comparison department can infer the customer's emotions and adjust the comparison benchmark based on the inferred emotions. For example, when the customer is anxious, the AI ​​can strictly set the comparison benchmark to prevent errors. When the customer is relaxed, the AI ​​can flexibly set the comparison benchmark, emphasizing natural responses. Furthermore, when the customer is anxious, the AI ​​can quickly set the comparison benchmark for efficient responses. Therefore, adjusting the comparison benchmark according to the customer's emotions allows for more accurate comparisons. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these. Some or all of the above processing can be achieved through AI, or AI can be used without it. For example, the comparison department can input the customer's voice data into the generative AI, which will then perform emotion inference.

[0132] The warning system can infer a customer's emotions and adjust the way warnings are displayed based on these inferences. For example, when a customer is anxious, the AI ​​can display the warning in an easy-to-understand and reassuring way. When a customer is excited, the AI ​​can display the warning in a calm and objective way. Furthermore, when a customer is relaxed, the AI ​​can display the warning in detail and with finesse. Thus, adjusting the warning display based on the customer's emotions provides more appropriate warnings. Emotion inference can be achieved, for example, through emotion inference functions such as emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these. Some or all of the above processing can be achieved through AI, or AI can be used without it. For example, the warning system can input the customer's voice data into generative AI, which will then perform emotion inference.

[0133] The reception reading department can infer a customer's emotional state and adjust the accuracy of its reading of the reception content based on this inference. For example, when a customer is nervous, the AI ​​can improve the accuracy of the reading by adjusting the tone and speed of their voice. When a customer is relaxed, the AI ​​can maintain accuracy while focusing on a natural conversation flow. Furthermore, when a customer is anxious, the AI ​​can prioritize reading important parts of the reception content. Thus, adjusting the accuracy of the reading based on the customer's emotional state yields more accurate information. Emotional inference can be achieved, for example, through emotion engines or generative AI. Generative AI can be text-generating AI (such as LLM) or multimodal generative AI, but is not limited to these. Some or all of the above processing can be achieved through AI, or it can be done without AI. For example, the reception reading department can input the customer's voice data into a generative AI, which will then perform the emotion inference.

[0134] The following is a brief description of the processing flow of Implementation Method 2.

[0135] Step 1: The reading unit reads the content of the call with the customer. The reading unit can read, for example, the content of voice calls, video calls, and text chats;

[0136] Step 2: The parsing unit analyzes the call content read by the reading unit. The parsing unit can analyze the call content using methods such as speech recognition, sentiment analysis, and keyword extraction.

[0137] Step 3: The comparison department compares the information on the PC screen registered by the staff. The comparison department can perform the comparison based on criteria such as consistency rate or similarity calculation with the database.

[0138] Step 4: The warning unit issues a warning when discrepancies arise in the information compared by the comparison unit. The warning unit may display the warning via pop-up notifications or voice alerts, for example.

[0139] Step 5: The reception reading department reads the reception information from the store. This department can read information such as face-to-face reception, online reception, and chat responses.

[0140] The specific processing unit 290 sends 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 voice representing the user's input to the result of the specific processing. The control unit 46A sends the voice data representing the user's 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 voice data.

[0141] Data generation model 58 is what is known as generative AI (Artificial Intelligence). An example of data generation model 58 includes ChatGPT (registered trademark) (Internet search).<URL:https: / / openai.com / blog / chatgpt> Generative AI, such as data generation model 58, is obtained by deep learning through a neural network. The data generation model 58 is input with a prompt containing instructions, and with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data of still images or data of moving images). The data generation model 58 infers the input inference data according to the instructions shown in the prompt, and outputs the inference result in one or more data forms such as speech 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 above-described specific processing while using the data generation model 58. The data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, the data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes multiple data generation models 58, including AI other than generative AI. AI other than generative AI includes, but is not limited to, 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. Furthermore, AI can also act as an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to this example. Moreover, processing performed by AI, including generative AI, can be replaced by rule-based processing, and vice versa.

[0142] Furthermore, the processing performed by the aforementioned data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Additionally, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or external devices, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or external devices.

[0143] Each of the aforementioned elements, including the reading unit, parsing unit, comparison unit, warning unit, and reception reading unit, can be implemented, for example, in at least one of the smart device 14 and the data processing device 12. For example, the reading unit can use the microphone 38B or camera 42 of the smart device 14 to read call content. The parsing unit, for example, is implemented by a specific processing unit 290 of the data processing device 12, performing speech recognition and emotion analysis. The comparison unit, for example, is implemented by a specific processing unit 290 of the data processing device 12, calculating the consistency rate or similarity with PC screen information. The warning unit, for example, is implemented by the control unit 46A of the smart device 14, displaying pop-up notifications or voice alerts. The reception reading unit, for example, can use the camera 42 or microphone 38B of the smart device 14 to read reception content at the store. The correspondence between each unit and the device or control unit is not limited to the above examples and can be varied.

[0144] Second Implementation Method

[0145] Figure 3 An example of the configuration of the data processing system 210 according to the second embodiment is shown.

[0146] like Figure 3 As shown, the data processing system 210 includes a data processing device 12 and smart glasses 214. One example of the data processing device 12 is a server.

[0147] 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, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN and / or LAN, etc.

[0148] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0149] Microphone 238 receives user commands by receiving the user's voice. Microphone 238 captures the user's voice, converts the captured sound into speech data, and outputs it to processor 46. Speaker 240 outputs sound according to commands from processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, used to capture the user's surroundings (e.g., the shooting range defined by an angle of view equivalent to the field of vision of an average healthy person).

[0151] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F 44 and 26 is performed in a secure state.

[0152] Figure 4 An example of the main functions of the data processing device 12 and the smart glasses 214 is shown. Figure 4 As shown, in the data processing device 12, specific processing is performed by the processor 28. The memory 32 stores a specific processing program 56.

[0153] The processor 28 reads a specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0154] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes inferring and predicting the user's emotions, performing various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0155] In the smart glasses 214, specific processing is performed by the processor 46. A specific processing program 60 is stored in the memory 50. The processor 46 reads the specific processing program 60 from the memory 50 and executes the read specific processing program 60 on the RAM 48. Specific processing is implemented by the processor 46 operating as a control unit 46A based on the specific processing program 60 executed on the RAM 48. Furthermore, the smart glasses 214 may also have the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and use these models to perform the same processing as the specific processing unit 290.

[0156] 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 the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.).

[0157] The specific processing unit 290 sends 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 voice input representing the user's input to the specific processing result. The control unit 46A sends the voice data representing the user's input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0158] Data generation model 58 is a so-called generative AI. An example of data generation model 58 includes generative AIs such as ChatGPT. Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing instructions is input to data generation model 58, along with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data from still images or moving images). Data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech data, text data, and image data. 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. Specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. Data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes various data generation models 58, which include AI other than generative AI. These AIs include, 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 are capable of various processing methods, but are not limited to these examples. Furthermore, AI can also be an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to these examples. Moreover, processing performed by AI including generative AI can be replaced by rule-based processing, and vice versa.

[0159] The data processing system 210 of the second embodiment performs the same processing as the data processing system 10 of the first embodiment. The processing performed by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or external devices, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or external devices.

[0160] Each of the aforementioned elements, including the reading unit, parsing unit, comparison unit, warning unit, and reception reading unit, can be implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the reading unit can use the microphone 238 or camera 42 of the smart glasses 214 to read call content. The parsing unit, for example, is implemented by a specific processing unit 290 of the data processing device 12, performing speech recognition and emotion analysis. The comparison unit, for example, is implemented by a specific processing unit 290 of the data processing device 12, calculating the consistency rate or similarity with PC screen information. The warning unit, for example, is implemented by the control unit 46A of the smart glasses 214, displaying pop-up notifications or voice alerts. The reception reading unit, for example, can use the camera 42 or microphone 238 of the smart glasses 214 to read the reception content at the store. The correspondence between each unit and the device or control unit is not limited to the above examples and can be modified in various ways.

[0161] Third Implementation Method

[0162] Figure 5 An example of the configuration of the data processing system 310 according to the third embodiment is shown.

[0163] like Figure 5 As shown, the data processing system 310 includes a data processing device 12 and a head-mounted terminal 314. An example of the data processing device 12 is a server.

[0164] 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, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN and / or LAN, etc.

[0165] The head-mounted terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0166] Microphone 238 receives user commands by receiving the user's voice. Microphone 238 captures the user's voice, converts the captured sound into speech data, and outputs it to processor 46. Speaker 240 outputs sound according to commands from processor 46.

[0167] Camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, used to capture the user's surroundings (e.g., the shooting range defined by an angle of view equivalent to the field of vision of an average healthy person).

[0168] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F 44 and 26 is performed in a secure state.

[0169] Figure 6 An example of the main functions of the data processing device 12 and the head-mounted terminal 314 is shown. Figure 6 As shown, in the data processing device 12, specific processing is performed by the processor 28. The memory 32 stores a specific processing program 56.

[0170] The processor 28 reads a specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0171] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes inferring and predicting the user's emotions, performing various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0172] In the head-mounted terminal 314, specific processing is performed by the processor 46. A specific program 60 is stored in the memory 50. The processor 46 reads the specific program 60 from the memory 50 and executes the read specific program 60 on the RAM 48. Specific processing is implemented by the processor 46 operating as a control unit 46A based on the specific program 60 executed on the RAM 48. Furthermore, the head-mounted terminal 314 may also have the same data generation model and emotion-specific model as the data generation model 58 and the emotion-specific model 59, and use these models to perform the same processing as the specific processing unit 290.

[0173] 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 the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.).

[0174] The specific processing unit 290 sends the result of the specific processing to the head-mounted terminal 314. In the head-mounted 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 voice representing the user's input to the specific processing result. The control unit 46A sends the voice data representing the user's input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0175] Data generation model 58 is a so-called generative AI. An example of data generation model 58 includes generative AIs such as ChatGPT. Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing instructions is input to data generation model 58, along with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data from still images or moving images). Data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech data, text data, and image data. 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. Specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. Data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes various data generation models 58, which include AI other than generative AI. These AIs include, 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 are capable of various processing methods, but are not limited to these examples. Furthermore, AI can also be an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to these examples. Moreover, processing performed by AI including generative AI can be replaced by rule-based processing, and vice versa.

[0176] The data processing system 310 of the third embodiment performs the same processing as the data processing system 10 of the first embodiment. The processing performed by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the head-mounted terminal 314, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the head-mounted terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the head-mounted terminal 314 or external devices, and the head-mounted terminal 314 acquires or collects information required for processing from the data processing device 12 or external devices.

[0177] Each of the aforementioned elements, including the reading unit, parsing unit, comparison unit, warning unit, and reception reading unit, can be implemented, for example, in at least one of the headset terminal 314 and the data processing device 12. For example, the reading unit can use the microphone 238 or camera 42 of the headset terminal 314 to read call content. The parsing unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, performing speech recognition and emotion analysis. The comparison unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, calculating the consistency rate or similarity with PC screen information. The warning unit, for example, is implemented by the control unit 46A of the headset terminal 314, displaying pop-up notifications or voice alarms. The reception reading unit, for example, can use the camera 42 or microphone 238 of the headset terminal 314 to read the reception content at the store. The correspondence between each unit and the device or control unit is not limited to the above examples and can be modified in various ways.

[0178] Fourth Implementation Method

[0179] Figure 7 An example of the configuration of the data processing system 410 according to the fourth embodiment is shown.

[0180] like Figure 7 As shown, 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.

[0181] 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, RAM 30, and memory 32. The processor 28, RAM 30, and memory 32 are connected to a bus 34. Furthermore, the database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. An example of the network 54 includes a WAN and / or LAN, etc.

[0182] Robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control object 443. Computer 36 includes a processor 46, RAM 48, and memory 50. The processor 46, RAM 48, and memory 50 are connected to a bus 52. Furthermore, the microphone 238, speaker 240, camera 42, and control object 443 are also connected to the bus 52.

[0183] Microphone 238 receives user commands by receiving the user's voice. Microphone 238 captures the user's voice, converts the captured sound into speech data, and outputs it to processor 46. Speaker 240 outputs sound according to commands from processor 46.

[0184] The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, used to photograph the user's surroundings (e.g., the shooting range defined by an angle of view equivalent to the field of vision of an average healthy person).

[0185] Communication I / F 44 is connected to network 54. Communication I / F 44 and 26 are responsible for the transmission and reception of various information between processor 46 and processor 28 via network 54. The transmission and reception of various information between processor 46 and processor 28 using communication I / F 44 and 26 is performed in a secure state.

[0186] The controlled object 443 includes a display device, LEDs for the eyes, and motors for driving the arms, hands, and feet. The posture and movements of the robot 414 are controlled by controlling the motors for the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. In addition, facial expressions of the robot 414 can also be expressed by controlling the illumination state of the LEDs for the robot 414's eyes.

[0187] Figure 8 An example of the main functions of the data processing device 12 and the robot 414 is shown. For example... Figure 8 As shown, in the data processing device 12, specific processing is performed by the processor 28. The memory 32 stores a specific processing program 56.

[0188] The processor 28 reads a specific processing program 56 from the memory 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is implemented by the processor 28 operating as a specific processing unit 290 based on the specific processing program 56 executed on the RAM 30.

[0189] The memory 32 stores a data generation model 58 and an emotion-specific model 59. The data generation model 58 and the emotion-specific model 59 are used by the specific processing unit 290. The specific processing unit 290 can use the emotion-specific model 59 to infer the user's emotions and perform specific processing based on the user's emotions. The emotion inference function using the emotion-specific model 59 (emotion-specific function) includes inferring and predicting the user's emotions, performing various inferences and predictions related to the user's emotions, but is not limited to this example. Furthermore, emotion inference and prediction also include, for example, emotion analysis (analysis).

[0190] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in memory 50. Processor 46 reads the specific program 60 from memory 50 and executes the read specific program 60 on RAM 48. Specific processing is achieved by processor 46 acting as control unit 46A based on the specific program 60 executed on RAM 48. Furthermore, robot 414 may also have the same data generation model and emotion-specific model as data generation model 58 and emotion-specific model 59, and use these models to perform the same processing as specific processing unit 290.

[0191] 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 the processing results (prediction results, etc.) using the data generation model 58 by communicating with the server device that has the data generation model 58. In addition, the data processing device 12 may be a server device or a user-owned terminal device (e.g., a mobile phone, robot, home appliance, etc.).

[0192] The specific processing unit 290 sends 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 voice representing the user's input regarding the result of the specific processing. The control unit 46A sends the voice data representing the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0193] Data generation model 58 is a so-called generative AI. An example of data generation model 58 includes generative AIs such as ChatGPT. Data generation model 58 is obtained by performing deep learning on a neural network. A prompt containing instructions is input to data generation model 58, along with inference data such as speech data representing speech, text data representing text, and image data representing images (e.g., data from still images or moving images). Data generation model 58 infers the inference data based on the instructions shown in the prompt and outputs the inference result in one or more data forms such as speech data, text data, and image data. 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. Specific processing unit 290 performs the aforementioned specific processing while using data generation model 58. Data generation model 58 can also be a fine-tuned model to output inference results from prompts without instructions; in this case, data generation model 58 can output inference results from prompts without instructions. The data processing device 12, etc., includes various data generation models 58, which include AI other than generative AI. These AIs include, 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 are capable of various processing methods, but are not limited to these examples. Furthermore, AI can also be an AI agent. Additionally, when the processing described above is performed by AI, this processing may be partially or entirely performed by AI, but is not limited to these examples. Moreover, processing performed by AI including generative AI can be replaced by rule-based processing, and vice versa.

[0194] The data processing system 410 of the fourth embodiment performs the same processing as the data processing system 10 of the first embodiment. The processing performed by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it can also be executed jointly by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or external devices, and the robot 414 acquires or collects information required for processing from the data processing device 12 or external devices.

[0195] Each of the aforementioned elements, including the reading unit, parsing unit, comparison unit, warning unit, and reception reading unit, can be implemented, for example, in at least one of the robot 414 and the data processing device 12. For example, the reading unit can use the robot 414's microphone 238 or camera 42 to read call content. The parsing unit, for example, is implemented by a specific processing unit 290 of the data processing device 12, performing speech recognition and emotion analysis. The comparison unit, for example, is implemented by the specific processing unit 290 of the data processing device 12, calculating the consistency rate or similarity with PC screen information. The warning unit, for example, is implemented by the robot 414's control unit 46A, displaying pop-up notifications or voice alerts. The reception reading unit, for example, can use the robot 414's camera 42 or microphone 238 to read the store's reception content. The correspondence between each unit and the device or control unit is not limited to the above examples and can be modified in various ways.

[0196] Furthermore, the emotion-specific model 59, acting as an emotion engine, can determine the user's emotion based on a specific mapping. Specifically, the emotion-specific model 59 can determine the user's emotion based on an emotion graph that serves as a specific mapping (see...). Figure 9 The robot's emotions can be determined by the emotion-specific model 59. In addition, the emotion-specific model 59 can also determine the robot's emotions in the same way, and the specific processing unit 290 can also perform specific processing using the robot's emotions.

[0197] Figure 9 This is a diagram representing an emotion map 400 that maps various emotions. In the emotion map 400, emotions are arranged radially from the center in concentric circles. The closer to the center of the concentric circles, the more primitive the emotion is. Further out on the concentric circles, emotions are arranged representing states or actions arising from mood. Emotion is a concept that includes both feelings and mental states. To the left of the concentric circles, emotions generated by reactions occurring in the brain are arranged roughly. To the right of the concentric circles, emotions guided by situational judgments are arranged roughly. Above and below the concentric circles, emotions generated by reactions occurring in the brain and guided by situational judgments are arranged roughly. Furthermore, the emotion of "pleasure" is arranged above the concentric circles, and the emotion of "unpleasantness" is arranged below. Thus, in the emotion map 400, various emotions are mapped according to the structure of emotion generation, while easily generated emotions are mapped nearby.

[0198] These emotions are distributed at the 3 o'clock position on the Emotion Chart 400, and usually fluctuate between peace and unease. In the right half of the Emotion Chart 400, because situational awareness is more dominant than internal feelings, it gives a sense of calm.

[0199] The inner side of the emotion diagram 400 represents the mind, and the outer side of the emotion diagram 400 represents actions. Therefore, the further you go to the outer side of the emotion diagram 400, the more the emotion can be seen (manifested in actions).

[0200] Here, human emotions are based on a balance of various factors such as posture and blood sugar levels. When these balances deviate from the ideal, it indicates unhappiness; when they approach the ideal, it indicates pleasure. In robots, cars, and motorcycles, emotions can also be created based on a balance of factors such as posture and remaining battery power. When these balances deviate from the ideal, it indicates unhappiness; when they approach the ideal, it indicates pleasure. Emotion maps can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Speech Emotion Recognition and Brain Physiological Signal Analysis Systems for Emotion, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). In the left half of the emotion map, emotions belonging to the "Reaction" domain, where sensation is dominant, are arranged. Furthermore, in the right half of the emotion map, emotions belonging to the "Situation" domain, where situational cognition is dominant, are arranged.

[0201] The emotion map defines two types of emotions that promote learning. One is a negative emotion located near the middle of "repentance" or "reflection" on the situation side. That is, when the robot experiences negative emotions such as "I never want to feel this way again" or "I never want to be scolded again." The other is a positive emotion located near "desire" on the response side. That is, when the robot experiences positive feelings such as "wanting more" or "wanting to know more."

[0202] The emotion-specific model 59 feeds user input into a pre-learned neural network to obtain emotion values ​​representing each emotion shown in the emotion graph 400, and determines the user's emotion. This neural network is pre-learned based on multiple learning data sets that combine user input with emotion values ​​representing each emotion shown in the emotion graph 400. Furthermore, this neural network is learned to... Figure 10 As shown in sentiment graph 900, nearby sentiment values ​​are similar to each other. Figure 10 Examples show how emotions such as "peace of mind," "stability," and "reassurance" can be associated with similar emotional values.

[0203] In the above embodiments, a specific processing is described by a single computer 22, but the technology disclosed herein is not limited to this, and distributed processing by multiple computers, including computer 22, is also possible.

[0204] In the above embodiments, an example of storing a specific processing program 56 in memory 32 is illustrated, but the technology disclosed herein is not limited thereto. For example, the specific processing program 56 may also be stored in a portable computer-readable non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed into the computer 22 of the data processing device 12. The processor 28 performs specific processing according to the specific processing program 56.

[0205] Alternatively, the specific processing program 56 can be stored in a storage device such as a server connected to the data processing device 12 via a network 54, and the specific processing program 56 can be downloaded and installed into the computer 22 upon request from the data processing device 12.

[0206] Furthermore, it is not necessary to store the entire specific process 56 in a storage device such as a server connected to the data processing device 12 via the network 54, nor is it necessary to store the entire specific process 56 in the memory 32; a portion of the specific process 56 may also be stored.

[0207] As a hardware resource for performing specific processing, various processors can be used. For example, a CPU is a general-purpose processor that functions as a hardware resource for performing specific processing by executing software, i.e., programs. Additionally, a dedicated circuit can be listed as a processor; it is a processor with a circuit structure specifically designed for performing specific processing, such as a FPGA (Field-Programmable Gate Array), PLD (Programmable Logic Device), or ASIC (Application Specific Integrated Circuit). Every processor has built-in or connected memory, and every processor executes specific processing by using that memory.

[0208] The hardware resources for performing a specific process can consist of one of these various processors, or a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Furthermore, the hardware resources for performing a specific process can also be a single processor.

[0209] As an example of a single processor, the first type consists of a combination of one or more CPUs and software, which functions as a hardware resource to perform specific processing. The second type uses a processor, such as a System-on-a-chip (SoC), which implements the entire system functionality, including multiple hardware resources for performing specific processing, using a single IC chip. In this case, the specific processing is implemented using one or more of the aforementioned processors that serve as hardware resources.

[0210] Furthermore, as the hardware architecture of these various processors, more specifically, circuits combining semiconductor elements and other circuit components can be used. Moreover, the specific process described above is merely an example. Therefore, it goes without saying that, without departing from the main point, unnecessary steps can be removed, new steps can be added, or the processing order can be changed.

[0211] Furthermore, although the above examples have been described in terms of first to fourth embodiments, some or all of these embodiments can be combined. Additionally, the smart device 14, smart glasses 214, head-mounted terminal 314, and robot 414 are just examples and can be combined separately, or other devices may be used. Furthermore, although the above examples have been described in terms of morphological example 1 and morphological example 2, these can also be combined.

[0212] The foregoing descriptions and illustrations are detailed explanations of the parts covered by this disclosure and are merely one example of this disclosure. For instance, the descriptions of the above-described structure, function, role, and effect are just one example of the structure, function, role, and effect of the parts covered by this disclosure. Therefore, it goes without saying that, without departing from the spirit of this disclosure, unnecessary parts can be deleted, new elements can be added, or replacements can be made to the foregoing descriptions and illustrations. Furthermore, to avoid confusion and facilitate understanding of the parts covered by this disclosure, explanations of technical common sense that does not require special explanation for implementing this disclosure have been omitted from the foregoing descriptions and illustrations.

[0213] All documents, patent applications and technical standards described in this specification are incorporated herein by reference as if they were specifically and individually described as incorporated by reference.

[0214] [Postscript 1]

[0215] A system characterized in that,

[0216] include:

[0217] The reading unit is used to read the content of conversations with customers;

[0218] The parsing unit is used to parse the call content read by the reading unit;

[0219] The comparison department is used to compare the PC screen information registered by staff.

[0220] A warning unit is used to issue a warning when a difference occurs based on the information compared by the comparison unit.

[0221] The reception and reading department is used to read the reception information from the store.

[0222] [Postscript 2]

[0223] The system as described in Appendix 1 is characterized in that,

[0224] The reading unit is used to estimate the customer's emotions and adjust the reading accuracy of the call content according to the estimated customer emotions.

[0225] [Postscript 3]

[0226] The system as described in Appendix 1 is characterized in that,

[0227] The reading unit has a filtering function that removes background noise and other sounds when reading call content.

[0228] [Postscript 4]

[0229] The system as described in Appendix 1 is characterized in that,

[0230] The reading unit has the function of emphasizing specific keywords or phrases when reading call content.

[0231] [Postscript 5]

[0232] The system as described in Appendix 1 is characterized in that,

[0233] The reading unit is used to infer the customer's emotions and determine the priority of reading the call content based on the inferred customer emotions.

[0234] [Postscript 6]

[0235] The system as described in Appendix 1 is characterized in that,

[0236] The reading unit has the function of automatically recording the start and end times of the call when reading the call content.

[0237] [Postscript 7]

[0238] The system as described in Appendix 1 is characterized in that,

[0239] The reading unit has the function of converting the call content into text in real time when reading the call content.

[0240] [Postscript 8]

[0241] The system as described in Appendix 1 is characterized in that,

[0242] The analysis unit is used to infer the customer's emotions and adjust the expression of the analysis results according to the inferred customer emotions.

[0243] [Postscript 9]

[0244] The system as described in Appendix 1 is characterized in that,

[0245] The parsing unit has the function of considering the context of the call content during parsing to improve parsing accuracy.

[0246] [Postscript 10]

[0247] The system as described in Appendix 1 is characterized in that,

[0248] The parsing unit has the function of applying different parsing algorithms according to the category of the call content during parsing.

[0249] [Postscript 11]

[0250] The system as described in Appendix 1 is characterized in that,

[0251] The analysis unit is used to infer the customer's emotions and determine the priority of the analysis results based on the inferred customer emotions.

[0252] [Postscript 12]

[0253] The system as described in Appendix 1 is characterized in that,

[0254] The parsing unit has the function of adjusting the level of detail of the parsing according to the length of the call content during parsing.

[0255] [Postscript 13]

[0256] The system as described in Appendix 1 is characterized in that,

[0257] The parsing unit has the function of adjusting the order of parsing results according to the relevance of the call content during parsing.

[0258] [Postscript 14]

[0259] The system as described in Appendix 1 is characterized in that,

[0260] The comparison unit is used to estimate the customer's emotions and adjust the comparison benchmark based on the estimated customer emotions.

[0261] [Postscript 15]

[0262] The system as described in Appendix 1 is characterized in that,

[0263] The comparison unit has the function of considering the change history of PC screen information during comparison to improve the comparison accuracy.

[0264] [Postscript 16]

[0265] The system as described in Appendix 1 is characterized in that,

[0266] The comparison unit has the function of applying different comparison algorithms according to the category of PC screen information during comparison.

[0267] [Postscript 17]

[0268] The system as described in Appendix 1 is characterized in that,

[0269] The comparison unit is used to infer the customer's emotions and adjust the display order of the comparison results according to the inferred customer emotions.

[0270] [Postscript 18]

[0271] The system as described in Appendix 1 is characterized in that,

[0272] The comparison unit has the function of determining the comparison priority based on the update frequency of the PC screen information during comparison.

[0273] [Postscript 19]

[0274] The system as described in Appendix 1 is characterized in that,

[0275] The comparison unit has the function of adjusting the order of comparison results based on the relevance of PC screen information during comparison.

[0276] [Postscript 20]

[0277] The system as described in Appendix 1 is characterized in that,

[0278] The warning unit is used to infer the customer's emotions and adjust the display method of the warning according to the inferred customer emotions.

[0279] [Postscript 21]

[0280] The system as described in Appendix 1 is characterized in that,

[0281] The warning unit has the function of referring to past warning history to improve the accuracy of warnings when issuing a warning.

[0282] [Postscript 22]

[0283] The system as described in Appendix 1 is characterized in that,

[0284] The warning unit has the function of applying different warning methods according to the importance of the warning when a warning is issued.

[0285] [Postscript 23]

[0286] The system as described in Appendix 1 is characterized in that,

[0287] The warning unit is used to infer the customer's emotions and determine the priority of the warning based on the inferred customer emotions.

[0288] [Postscript 24]

[0289] The system as described in Appendix 1 is characterized in that,

[0290] The warning unit has the function of adjusting the warning display order according to the frequency of warning occurrence when a warning is issued.

[0291] [Postscript 25]

[0292] The system as described in Appendix 1 is characterized in that,

[0293] The warning unit has the function of adjusting the order of warning content according to the relevance of the warning when a warning is issued.

[0294] [Postscript 26]

[0295] The system as described in Appendix 1 is characterized in that,

[0296] The reception reading unit is used to infer the customer's emotions and adjust the reading accuracy of the reception content according to the inferred customer emotions.

[0297] [Postscript 27]

[0298] The system as described in Appendix 1 is characterized in that,

[0299] The reception reading unit has a filtering function to remove background noise and other sounds when reading reception content.

[0300] [Postscript 28]

[0301] The system as described in Appendix 1 is characterized in that,

[0302] The reception reading unit has the function of emphasizing specific keywords or phrases when reading reception content.

[0303] [Postscript 29]

[0304] The system as described in Appendix 1 is characterized in that,

[0305] The reception reading unit is used to infer the customer's emotions and determine the priority of the reception content to be read based on the inferred customer emotions.

[0306] [Postscript 30]

[0307] The system as described in Appendix 1 is characterized in that,

[0308] The reception reading unit has the function of automatically recording the reception start time and end time when reading reception content.

[0309] [Postscript 31]

[0310] The system as described in Appendix 1 is characterized in that,

[0311] The reception reading unit has the function of converting reception content into text in real time when reading reception content.

Claims

1. A system, characterized in that, include: The reading unit is used to read the content of conversations with customers; The parsing unit is used to parse the call content read by the reading unit; The comparison department is used to compare the PC screen information registered by staff. A warning unit is used to issue a warning when a difference occurs based on the information compared by the comparison unit. The reception and reading department is used to read the reception information from the store.

2. The system as described in claim 1, characterized in that, The reading unit is used to estimate the customer's emotions and adjust the reading accuracy of the call content according to the estimated customer emotions.

3. The system as described in claim 1, characterized in that, The reading unit has a filtering function that removes background noise and other sounds when reading call content.

4. The system as described in claim 1, characterized in that, The reading unit has the function of emphasizing specific keywords or phrases when reading call content.

5. The system as described in claim 1, characterized in that, The reading unit is used to infer the customer's emotions and determine the priority of reading the call content based on the inferred customer emotions.

6. The system as described in claim 1, characterized in that, The reading unit has the function of automatically recording the start and end times of the call when reading the call content.

7. The system as described in claim 1, characterized in that, The reading unit has the function of converting the call content into text in real time when reading the call content.

8. The system as described in claim 1, characterized in that, The analysis unit is used to infer the customer's emotions and adjust the expression of the analysis results according to the inferred customer emotions.

9. The system as described in claim 1, characterized in that, The parsing unit has the function of considering the context of the call content during parsing to improve parsing accuracy.

10. The system as claimed in claim 1, characterized in that, The parsing unit has the function of applying different parsing algorithms according to the category of the call content during parsing.

Images