System

Abstract

An object of a system according to an embodiment is to efficiently respond to a customer's unreasonable conversation or complaint.SOLUTION: A system according to an embodiment includes a remark analysis unit, a scoring unit, a warning unit, and a termination unit. The statement analysis unit analyzes the statement content of the customer. The scoring unit scores the remark content analyzed by the remark analysis unit. The warning unit issues a warning based on a result of scoring by the scoring unit. The termination portion automatically terminates the call if it is not remedied after the warning is issued by the warning portion.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, dealing with unreasonable customer conversations and complaints takes time and effort, making it difficult to handle efficiently.

[0005] The system according to the embodiment aims to efficiently deal with unreasonable conversations and complaints from customers. [Means for solving the problem]

[0006] The system according to the embodiment includes a utterance analysis unit, a scoring unit, a warning unit, and a termination unit. The utterance analysis unit analyzes the content of the customer's utterance. The scoring unit scores the utterance content analyzed by the utterance analysis unit. The warning unit issues a warning based on the results of scoring by the scoring unit. The termination unit automatically terminates the call if the situation does not improve even after the warning is issued by the warning unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently deal with unreasonable conversations and complaints from customers. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The maliciousness scoring system according to an embodiment of the present invention analyzes the content of customer comments, scores the degree of maliciousness, issues a warning if the score exceeds a certain level, and automatically terminates the call if the customer does not improve. This allows the maliciousness scoring system to efficiently respond to unreasonable comments made by customers and reduce the burden on operators.

[0029] The maliciousness scoring system according to the embodiment includes a statement analysis unit, a scoring unit, a warning unit, and a termination unit. The statement analysis unit analyzes the content of a customer's statement. For example, the statement analysis unit analyzes the content of a customer's statement in real time using natural language processing technology. The statement analysis unit can also convert voice data into text data using voice recognition technology and analyze the content. The statement analysis unit can also analyze the content of a customer's statement on a keyword-by-keyword basis and measure the frequency of occurrence of specific keywords. For example, the statement analysis unit converts the content of a customer's statement into text data using voice recognition technology and analyzes it using natural language processing technology. The statement analysis unit can also analyze the content on a keyword-by-keyword basis and measure the frequency of occurrence of specific keywords. The scoring unit scores the content of a customer's statement analyzed by the statement analysis unit. For example, the scoring unit scores the intensity and type of emotion in the content of a customer's statement using sentiment analysis technology. The scoring unit can also score based on the frequency of occurrence of keywords. The scoring unit can also analyze the context of the content of a customer's statement and perform a comprehensive score. For example, the scoring unit scores the intensity and type of emotion in the content of the customer's comments using sentiment analysis technology. The scoring unit can also score based on the frequency of keyword appearances. The warning unit issues a warning based on the result of scoring by the scoring unit. For example, the warning unit issues a voice warning when the score exceeds a certain threshold. The warning unit can also issue a text message warning. The warning unit can also issue a warning by email. For example, the warning unit issues a voice warning when the score exceeds a certain threshold. The warning unit can also issue a text message warning. The termination unit automatically ends the call if the customer's behavior does not improve even after the warning unit issues a warning. For example, the termination unit automatically ends the call if the customer's behavior does not improve after issuing three warnings. The termination unit can also immediately end the call if the score exceeds a certain threshold. The termination unit can also optimize the timing of termination based on the content of the customer's comments.For example, the termination unit automatically terminates the call if the customer's remarks do not improve after issuing three warnings. The termination unit can also immediately terminate the call if the score exceeds a certain threshold. This allows the maliciousness scoring system according to the embodiment to efficiently respond to unreasonable remarks made by customers and reduce the burden on operators. For example, operators can respond appropriately to unreasonable remarks made by customers, thereby reducing stress. Furthermore, by quickly responding to unreasonable remarks made by customers, work efficiency can be improved. Furthermore, by appropriately responding to unreasonable remarks made by customers, customer satisfaction can be improved.

[0030] The utterance analysis unit can also analyze voice features such as tone of voice, speaking speed, and pauses, and comprehensively score the degree of maliciousness. The utterance analysis unit, for example, analyzes not only the content of the customer's utterance, but also tone of voice and speaking speed, and scores the degree of maliciousness. For example, if the voice tone is high and the speaking speed is fast, it is likely that the customer is angered or irritated, so the degree of maliciousness is scored high. The utterance analysis unit can also analyze pauses and score the degree of maliciousness. For example, if there is short silence between utterances, it is likely that the customer is impatient, so the degree of maliciousness is scored high. The utterance analysis unit can also comprehensively analyze voice features and score the degree of maliciousness. For example, it can analyze voice features using voice waveform or spectrum analysis, and score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by analyzing voice features.

[0031] The utterance analysis unit can refer to the customer's past utterance history and behavioral patterns and score the degree of maliciousness by comparing it with past data. The utterance analysis unit, for example, stores the customer's past utterance history in a database and compares it with the current content of the utterance to score the degree of maliciousness. For example, if a customer who has made abusive remarks in the past makes a similar remark again, the utterance analysis unit can score the degree of maliciousness higher. The utterance analysis unit can also analyze the customer's behavioral patterns and score the degree of maliciousness. For example, a customer who frequently makes complaints can be scored higher in the degree of maliciousness. The utterance analysis unit can also score the degree of maliciousness by comparing it with past data. For example, the current content of the utterance is evaluated based on the content of past utterances and behavioral patterns. In this way, the accuracy of scoring the degree of maliciousness is improved by referring to past data.

[0032] The utterance analysis unit can simultaneously analyze text messages and chat logs and score the degree of maliciousness from multimodal data. The utterance analysis unit, for example, analyzes not only the content of customer utterances but also text messages and chat logs and scores the degree of maliciousness. For example, it compares utterances made over the phone with utterances made in chat, and assigns a high score if the content is consistently malicious. The utterance analysis unit can also integrate and analyze multimodal data and score the degree of maliciousness. For example, it integrates and analyzes data such as audio, text, and images. The utterance analysis unit can also analyze text messages and chat logs and score the degree of maliciousness. For example, it analyzes the content of text messages and chat logs and scores the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by analyzing multimodal data.

[0033] The comment analysis unit can integrate customer interaction data from different industries and services and develop a common maliciousness scoring standard. The comment analysis unit, for example, collects customer interaction data from different industries and develops a common maliciousness scoring standard. For example, data from the financial industry and the telecommunications industry can be integrated to set a common standard. The comment analysis unit can also integrate customer interaction data from different services and develop a common scoring standard. For example, data from customer support and technical support can be integrated to set a common standard. The comment analysis unit can also integrate data from different industries and services and develop a common scoring standard. For example, data from different industries and services can be integrated to set a common standard. This makes it possible to develop a common scoring standard by integrating data from different industries and services.

[0034] The warning unit can monitor customer reactions in real time and issue a warning at an appropriate timing. The warning unit, for example, builds a system that monitors customer reactions in real time and issues a warning at the optimal timing. For example, it issues a warning immediately after a customer makes abusive remark. The warning unit can also analyze customer reactions and optimize the timing of issuing a warning. For example, it issues a warning based on the customer's reaction time or scoring results. The warning unit can also monitor customer reactions in real time and issue a warning at an appropriate timing. For example, it analyzes customer reactions in real time and issues a warning at the optimal timing. This makes it possible to issue a warning at the optimal timing according to the customer's reaction.

[0035] The warning unit can customize the content of the warning based on the customer's past behavior history and the content of their statements, and can take individual measures. The warning unit, for example, customizes the content of the warning by referring to the customer's past behavior history and the content of their statements. For example, it generates a stern warning message for a customer who has used abusive language in the past. The warning unit can also adjust the content of the warning based on the customer's past behavior history and the content of their statements. For example, it adjusts the message based on the customer's past behavior history. The warning unit can also customize the content of the warning based on the customer's past behavior history and the content of their statements, and can take individual measures. For example, it sets special countermeasures for each customer. This makes it possible to customize the content of the warning based on the customer's past behavior history and the content of their statements.

[0036] The warning unit can issue warnings not only by voice but also by text message or email, and can communicate warnings through multiple channels. The warning unit, for example, builds a system that issues warnings not only by voice but also by text message or email. For example, in addition to warnings by telephone, warnings are sent by text message. The warning unit can also communicate warnings through multiple channels. For example, channels such as voice calls, text messages, and emails are used. The warning unit can also issue warnings through multiple channels. For example, a warning is issued by a combination of voice calls and text messages. In this way, warnings can be communicated reliably to customers by communicating warnings through multiple channels.

[0037] The warning unit can automatically translate the warning text to accommodate different languages ​​and cultural areas, and provide the most appropriate warning for each region. The warning unit, for example, automatically translates the warning text to build a system that accommodates different languages ​​and cultural areas. For example, the warning unit translates into multiple languages, such as English, French, and Chinese. The warning unit can also provide the most appropriate warning for each region. For example, it generates a warning text that takes into account differences in cultural background and language. The warning unit can also automatically translate the warning text to provide the most appropriate warning for each region. For example, it generates a warning text that takes into account differences in cultural background and language. This allows the system to accommodate different languages ​​and cultural areas, and provide the most appropriate warning for each region.

[0038] The termination unit can analyze the customer's comments and reactions in real time and determine the optimal timing for termination. The termination unit, for example, builds a system that analyzes the customer's comments and reactions in real time and optimizes the timing for automatic termination. For example, automatic termination is performed immediately after a customer makes an abusive remark. The termination unit can also analyze the customer's comments and reactions and determine the optimal timing for termination. For example, the termination timing is determined based on the customer's reaction time and scoring results. The termination unit can also analyze the customer's comments and reactions in real time and determine the optimal timing for termination. For example, the customer's reactions are analyzed in real time and automatic termination is performed at the optimal timing. This makes it possible to automatically terminate at the optimal timing based on the customer's comments and reactions.

[0039] The termination unit can improve customer satisfaction by automatically sending a follow-up email or message to the customer after automatic termination. The termination unit, for example, builds a system that automatically sends a follow-up email or message to the customer after automatic termination. For example, an apology email is sent after termination. The termination unit can also improve customer satisfaction by automatically sending a follow-up email or message. For example, a customer satisfaction survey or additional support information is provided. The termination unit can also improve customer satisfaction by automatically sending a follow-up email or message to the customer after automatic termination. For example, an apology email is sent after termination. In this way, customer satisfaction can be improved by following up after automatic termination.

[0040] The termination unit applies the automatic telephone call termination function to chat and email responses as well, allowing for consistent responses across all customer support channels. The termination unit, for example, builds a system that applies the automatic telephone call termination function to chat and email responses as well. For example, it automatically terminates calls in response to inappropriate comments made in chat. The termination unit can also provide consistent responses across all customer support channels. For example, it provides consistent responses across channels such as voice calls, text messages, and email. The termination unit can also apply the automatic telephone call termination function to chat and email responses as well, allowing for consistent responses across all customer support channels. For example, it automatically terminates calls in response to inappropriate comments made in chat. This allows for consistent responses across all customer support channels, thereby improving the quality of customer support.

[0041] After automatic completion, the termination unit records the customer's comments and the scoring results in a database, which can be used to improve future responses. For example, the termination unit builds a system that records the customer's comments and the scoring results in a database after automatic completion. For example, the comments are saved as text data after completion. The termination unit can also analyze the data recorded in the database and use it to improve future responses. For example, it performs data analysis and identifies areas for improvement in customer response. The termination unit can also record the customer's comments and the scoring results in a database after automatic completion, which can be used to improve future responses. For example, it saves the comments as text data after completion. In this way, by recording data after automatic completion and using it to improve future responses, the quality of customer response can be improved.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The utterance analysis unit can not only analyze the content of a customer's utterances, but also analyze the customer's background and environmental sounds to score the degree of maliciousness. For example, if the background sounds include noise or yelling, the degree of maliciousness is scored high. The utterance analysis unit can also analyze the customer's environmental sounds and score the degree of maliciousness high if there is a possibility that the customer is in a stressful environment. Furthermore, the utterance analysis unit can comprehensively analyze the background and environmental sounds to score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by analyzing the background and environmental sounds.

[0044] When analyzing the content of a customer's comments, the comment analysis unit can score the degree of maliciousness by taking into account the customer's social and cultural background. For example, if an expression that is acceptable in a particular cultural sphere is considered inappropriate in another cultural sphere, the score can be determined by taking that difference into account. The comment analysis unit can also analyze the customer's social background and appropriately evaluate the content of the comment based on that particular social background. Furthermore, the comment analysis unit can comprehensively analyze cultural and social backgrounds and score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by taking social and cultural backgrounds into account.

[0045] When analyzing the content of a customer's comments, the comment analysis unit can take into account the customer's health and psychological state and score the degree of maliciousness. For example, if a customer is ill or stressed, the score can be determined taking these conditions into consideration. The comment analysis unit can also analyze the customer's psychological state and appropriately evaluate the content of comments based on a specific psychological state. Furthermore, the comment analysis unit can comprehensively analyze the customer's health and psychological state and score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by taking into account the customer's health and psychological state.

[0046] When analyzing the content of a customer's statements, the statement analysis unit can detect consistency or inconsistency in the customer's statements and score the degree of maliciousness. For example, if a customer repeatedly makes contradictory statements, the degree of maliciousness is scored high. The statement analysis unit can also analyze the consistency of the customer's statements and appropriately evaluate inconsistent statements. Furthermore, the statement analysis unit can comprehensively analyze the consistency and inconsistency of the statements and score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by taking into account the consistency and inconsistency of the statements.

[0047] When analyzing the content of a customer's utterances, the utterance analysis unit can evaluate the grammar and language usage of the customer's utterances and score the degree of maliciousness. For example, if the customer uses inappropriate grammar or language, the utterance analysis unit can assign a high score to the degree of maliciousness. The utterance analysis unit can also analyze the customer's language usage and appropriately evaluate the inappropriate language usage. Furthermore, the utterance analysis unit can comprehensively analyze the grammar and language usage and score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by taking grammar and language usage into consideration.

[0048] The processing flow of the first embodiment will be briefly explained below.

[0049] Step 1: The utterance analysis unit analyzes the content of customer utterances. For example, the utterance analysis unit uses natural language processing technology to analyze the content of customer utterances in real time. It can also use voice recognition technology to convert voice data into text data and analyze the content. It can also perform keyword-based analysis and measure the frequency of occurrence of specific keywords. Step 2: The scoring unit scores the comments analyzed by the comment analysis unit. For example, it uses sentiment analysis technology to score the intensity and type of emotion in the customer's comments. It can also score based on the frequency of keyword appearances. It is also possible to analyze the context of the customer's comments and perform a comprehensive score. Step 3: The warning unit issues a warning based on the results of the scoring by the scoring unit. For example, if the score exceeds a certain threshold, a warning may be issued by voice. It may also be possible to issue a warning by text message or email. Step 4: The termination unit automatically terminates the call if the customer's behavior remains unchanged even after the warning unit issues a warning. For example, the call can be automatically terminated if the customer's comments do not improve after three warnings have been issued. It can also terminate the call immediately if the score exceeds a certain threshold. Furthermore, it is possible to optimize the timing of termination based on the content of the customer's comments.

[0050] (Example 2) The maliciousness scoring system according to an embodiment of the present invention analyzes the content of customer comments, scores the degree of maliciousness, issues a warning if the score exceeds a certain level, and automatically terminates the call if the customer does not improve. This allows the maliciousness scoring system to efficiently respond to unreasonable comments made by customers and reduce the burden on operators.

[0051] The maliciousness scoring system according to the embodiment includes a statement analysis unit, a scoring unit, a warning unit, and a termination unit. The statement analysis unit analyzes the content of a customer's statement. For example, the statement analysis unit analyzes the content of a customer's statement in real time using natural language processing technology. The statement analysis unit can also convert voice data into text data using voice recognition technology and analyze the content. The statement analysis unit can also analyze the content of a customer's statement on a keyword-by-keyword basis and measure the frequency of occurrence of specific keywords. For example, the statement analysis unit converts the content of a customer's statement into text data using voice recognition technology and analyzes it using natural language processing technology. The statement analysis unit can also analyze the content on a keyword-by-keyword basis and measure the frequency of occurrence of specific keywords. The scoring unit scores the content of a customer's statement analyzed by the statement analysis unit. For example, the scoring unit scores the intensity and type of emotion in the content of a customer's statement using sentiment analysis technology. The scoring unit can also score based on the frequency of occurrence of keywords. The scoring unit can also analyze the context of the content of a customer's statement and perform a comprehensive score. For example, the scoring unit scores the intensity and type of emotion in the content of the customer's comments using sentiment analysis technology. The scoring unit can also score based on the frequency of keyword appearances. The warning unit issues a warning based on the result of scoring by the scoring unit. For example, the warning unit issues a voice warning when the score exceeds a certain threshold. The warning unit can also issue a text message warning. The warning unit can also issue a warning by email. For example, the warning unit issues a voice warning when the score exceeds a certain threshold. The warning unit can also issue a text message warning. The termination unit automatically ends the call if the customer's behavior does not improve even after the warning unit issues a warning. For example, the termination unit automatically ends the call if the customer's behavior does not improve after issuing three warnings. The termination unit can also immediately end the call if the score exceeds a certain threshold. The termination unit can also optimize the timing of termination based on the content of the customer's comments.For example, the termination unit automatically terminates the call if the customer's remarks do not improve after issuing three warnings. The termination unit can also immediately terminate the call if the score exceeds a certain threshold. This allows the maliciousness scoring system according to the embodiment to efficiently respond to unreasonable remarks made by customers and reduce the burden on operators. For example, operators can respond appropriately to unreasonable remarks made by customers, thereby reducing stress. Furthermore, by quickly responding to unreasonable remarks made by customers, work efficiency can be improved. Furthermore, by appropriately responding to unreasonable remarks made by customers, customer satisfaction can be improved.

[0052] The utterance analysis unit can perform sentiment analysis using the generation AI and score the degree of maliciousness based on the intensity and type of emotion. For example, the utterance analysis unit analyzes the content of customer utterances in real time and performs sentiment analysis using the generation AI. For example, if a customer makes a statement expressing anger or irritation, the intensity and type of emotion are quantified and the degree of maliciousness is scored. The utterance analysis unit can also use the generation AI to classify and score the intensity and type of emotion in the content of customer utterances. For example, the generation AI performs sentiment analysis using a text generation AI (e.g., GPT-3). The utterance analysis unit can also use the generation AI to classify and score the intensity and type of emotion in the content of customer utterances. This improves the accuracy of scoring the degree of maliciousness through sentiment analysis.

[0053] The utterance analysis unit can also analyze voice features such as tone of voice, speaking speed, and pauses, and comprehensively score the degree of maliciousness. The utterance analysis unit, for example, analyzes not only the content of the customer's utterance, but also tone of voice and speaking speed, and scores the degree of maliciousness. For example, if the voice tone is high and the speaking speed is fast, it is likely that the customer is angered or irritated, so the degree of maliciousness is scored high. The utterance analysis unit can also analyze pauses and score the degree of maliciousness. For example, if there is short silence between utterances, it is likely that the customer is impatient, so the degree of maliciousness is scored high. The utterance analysis unit can also comprehensively analyze voice features and score the degree of maliciousness. For example, it can analyze voice features using voice waveform or spectrum analysis, and score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by analyzing voice features.

[0054] The utterance analysis unit can refer to the customer's past utterance history and behavioral patterns and score the degree of maliciousness by comparing it with past data. The utterance analysis unit, for example, stores the customer's past utterance history in a database and compares it with the current content of the utterance to score the degree of maliciousness. For example, if a customer who has made abusive remarks in the past makes a similar remark again, the utterance analysis unit can score the degree of maliciousness higher. The utterance analysis unit can also analyze the customer's behavioral patterns and score the degree of maliciousness. For example, a customer who frequently makes complaints can be scored higher in the degree of maliciousness. The utterance analysis unit can also score the degree of maliciousness by comparing it with past data. For example, the current content of the utterance is evaluated based on the content of past utterances and behavioral patterns. In this way, the accuracy of scoring the degree of maliciousness is improved by referring to past data.

[0055] The utterance analysis unit can simultaneously analyze text messages and chat logs and score the degree of maliciousness from multimodal data. The utterance analysis unit, for example, analyzes not only the content of customer utterances but also text messages and chat logs and scores the degree of maliciousness. For example, it compares utterances made over the phone with utterances made in chat, and assigns a high score if the content is consistently malicious. The utterance analysis unit can also integrate and analyze multimodal data and score the degree of maliciousness. For example, it integrates and analyzes data such as audio, text, and images. The utterance analysis unit can also analyze text messages and chat logs and score the degree of maliciousness. For example, it analyzes the content of text messages and chat logs and scores the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by analyzing multimodal data.

[0056] The comment analysis unit can integrate customer interaction data from different industries and services and develop a common maliciousness scoring standard. The comment analysis unit, for example, collects customer interaction data from different industries and develops a common maliciousness scoring standard. For example, data from the financial industry and the telecommunications industry can be integrated to set a common standard. The comment analysis unit can also integrate customer interaction data from different services and develop a common scoring standard. For example, data from customer support and technical support can be integrated to set a common standard. The comment analysis unit can also integrate data from different industries and services and develop a common scoring standard. For example, data from different industries and services can be integrated to set a common standard. This makes it possible to develop a common scoring standard by integrating data from different industries and services.

[0057] The utterance analysis unit can use the emotion estimation function to analyze the emotional reaction of the agent to the content of the customer's utterance and set scoring criteria for reducing the agent's stress level. The utterance analysis unit, for example, uses the emotion estimation function to analyze the emotional reaction of the agent to the content of the customer's utterance. For example, a high score is set for a utterance that causes the agent to feel highly stressed. The utterance analysis unit can also analyze the emotional reaction of the agent and set scoring criteria for reducing the stress level. For example, a high score is set for a utterance that causes the agent to feel stressed. The utterance analysis unit can also use the emotion estimation function to analyze the emotional reaction of the agent and set scoring criteria. For example, a high score is set for a utterance that causes the agent to feel stressed. In this way, by analyzing the emotional reaction of the agent, scoring criteria for reducing the stress level can be set.

[0058] The warning unit can use the generation AI to estimate the customer's emotions and automatically generate the most effective warning message. The warning unit, for example, uses the generation AI to estimate the customer's emotions and automatically generate the most effective warning message. For example, if the customer is showing signs of anger, the warning unit generates a warning message in a calm tone. The warning unit can also use the generation AI to estimate the customer's emotions and customize the warning message. For example, it generates a customized message according to the customer's emotional state. The warning unit can also use the generation AI to estimate the customer's emotions and generate the most effective warning message. For example, it generates a customized message according to the customer's emotional state. This makes it possible to generate the optimal warning message according to the customer's emotions.

[0059] The warning unit can monitor customer reactions in real time and issue a warning at an appropriate timing. The warning unit, for example, builds a system that monitors customer reactions in real time and issues a warning at the optimal timing. For example, it issues a warning immediately after a customer makes abusive remark. The warning unit can also analyze customer reactions and optimize the timing of issuing a warning. For example, it issues a warning based on the customer's reaction time or scoring results. The warning unit can also monitor customer reactions in real time and issue a warning at an appropriate timing. For example, it analyzes customer reactions in real time and issues a warning at the optimal timing. This makes it possible to issue a warning at the optimal timing according to the customer's reaction.

[0060] The warning unit can customize the content of the warning based on the customer's past behavior history and the content of their statements, and can take individual measures. The warning unit, for example, customizes the content of the warning by referring to the customer's past behavior history and the content of their statements. For example, it generates a stern warning message for a customer who has used abusive language in the past. The warning unit can also adjust the content of the warning based on the customer's past behavior history and the content of their statements. For example, it adjusts the message based on the customer's past behavior history. The warning unit can also customize the content of the warning based on the customer's past behavior history and the content of their statements, and can take individual measures. For example, it sets special countermeasures for each customer. This makes it possible to customize the content of the warning based on the customer's past behavior history and the content of their statements.

[0061] The warning unit can issue warnings not only by voice but also by text message or email, and can communicate warnings through multiple channels. The warning unit, for example, builds a system that issues warnings not only by voice but also by text message or email. For example, in addition to warnings by telephone, warnings are sent by text message. The warning unit can also communicate warnings through multiple channels. For example, channels such as voice calls, text messages, and emails are used. The warning unit can also issue warnings through multiple channels. For example, a warning is issued by a combination of voice calls and text messages. In this way, warnings can be communicated reliably to customers by communicating warnings through multiple channels.

[0062] The warning unit can automatically translate the warning text to accommodate different languages ​​and cultural areas, and provide the most appropriate warning for each region. The warning unit, for example, automatically translates the warning text to build a system that accommodates different languages ​​and cultural areas. For example, the warning unit translates into multiple languages, such as English, French, and Chinese. The warning unit can also provide the most appropriate warning for each region. For example, it generates a warning text that takes into account differences in cultural background and language. The warning unit can also automatically translate the warning text to provide the most appropriate warning for each region. For example, it generates a warning text that takes into account differences in cultural background and language. This allows the system to accommodate different languages ​​and cultural areas, and provide the most appropriate warning for each region.

[0063] The warning unit can use the emotion estimation function to evaluate the effectiveness of the warning in real time and continuously improve the content of the warning message and the method of issuing the warning. The warning unit, for example, uses the emotion estimation function to build a system that evaluates the effectiveness of the warning in real time. For example, the emotional reaction of the customer is analyzed and the effectiveness of the warning message is quantified. The warning unit can also continuously improve the content of the warning message and the method of issuing the warning. For example, the content of the warning message is adjusted using a feedback loop. The warning unit can also use the emotion estimation function to evaluate the effectiveness of the warning in real time and continuously improve the content of the warning message and the method of issuing the warning. For example, the emotional reaction of the customer is analyzed and the effectiveness of the warning message is quantified. In this way, the effectiveness of the warning can be evaluated in real time and continuously improved, thereby maximizing the effectiveness of the warning.

[0064] The termination unit can use the generation AI to estimate the customer's emotions and send a message as a final warning that takes into consideration the customer's emotions. The termination unit, for example, can use the generation AI to estimate the customer's emotions and send a message as a final warning that takes into consideration the customer's emotions. For example, if the customer is showing signs of anger, the termination unit can issue a final warning in a calm tone. The termination unit can also use the generation AI to estimate the customer's emotions and send a message as a final warning that takes into consideration the customer's emotions. For example, the termination unit can generate a customized message according to the customer's emotional state. The termination unit can also use the generation AI to estimate the customer's emotions and send a message as a final warning that takes into consideration the customer's emotions. For example, the termination unit can generate a customized message according to the customer's emotional state. In this way, customer dissatisfaction can be reduced by issuing a final warning that takes into consideration the customer's emotions.

[0065] The termination unit can analyze the customer's comments and reactions in real time and determine the optimal timing for termination. The termination unit, for example, builds a system that analyzes the customer's comments and reactions in real time and optimizes the timing for automatic termination. For example, automatic termination is performed immediately after a customer makes an abusive remark. The termination unit can also analyze the customer's comments and reactions and determine the optimal timing for termination. For example, the termination timing is determined based on the customer's reaction time and scoring results. The termination unit can also analyze the customer's comments and reactions in real time and determine the optimal timing for termination. For example, the customer's reactions are analyzed in real time and automatic termination is performed at the optimal timing. This makes it possible to automatically terminate at the optimal timing based on the customer's comments and reactions.

[0066] The termination unit can improve customer satisfaction by automatically sending a follow-up email or message to the customer after automatic termination. The termination unit, for example, builds a system that automatically sends a follow-up email or message to the customer after automatic termination. For example, an apology email is sent after termination. The termination unit can also improve customer satisfaction by automatically sending a follow-up email or message. For example, a customer satisfaction survey or additional support information is provided. The termination unit can also improve customer satisfaction by automatically sending a follow-up email or message to the customer after automatic termination. For example, an apology email is sent after termination. In this way, customer satisfaction can be improved by following up after automatic termination.

[0067] The termination unit applies the automatic telephone call termination function to chat and email responses as well, allowing for consistent responses across all customer support channels. The termination unit, for example, builds a system that applies the automatic telephone call termination function to chat and email responses as well. For example, it automatically terminates calls in response to inappropriate comments made in chat. The termination unit can also provide consistent responses across all customer support channels. For example, it provides consistent responses across channels such as voice calls, text messages, and email. The termination unit can also apply the automatic telephone call termination function to chat and email responses as well, allowing for consistent responses across all customer support channels. For example, it automatically terminates calls in response to inappropriate comments made in chat. This allows for consistent responses across all customer support channels, thereby improving the quality of customer support.

[0068] After automatic completion, the termination unit records the customer's comments and the scoring results in a database, which can be used to improve future responses. For example, the termination unit builds a system that records the customer's comments and the scoring results in a database after automatic completion. For example, the comments are saved as text data after completion. The termination unit can also analyze the data recorded in the database and use it to improve future responses. For example, it performs data analysis and identifies areas for improvement in customer response. The termination unit can also record the customer's comments and the scoring results in a database after automatic completion, which can be used to improve future responses. For example, it saves the comments as text data after completion. In this way, by recording data after automatic completion and using it to improve future responses, the quality of customer response can be improved.

[0069] The termination unit can use the emotion estimation function to monitor the emotional response of the customer after the automatic termination and provide additional follow-up as necessary. The termination unit, for example, uses the emotion estimation function to build a system that monitors the emotional response of the customer after the automatic termination. For example, it analyzes the customer's emotions after termination and determines whether follow-up is necessary. The termination unit can also analyze the customer's emotional response and provide additional follow-up as necessary. For example, it provides additional support information according to the customer's emotional state. The termination unit can also use the emotion estimation function to monitor the customer's emotional response after the automatic termination and provide additional follow-up as necessary. For example, it analyzes the customer's emotions after termination and determines whether follow-up is necessary. In this way, by monitoring the customer's emotional response after the automatic termination and providing additional follow-up as necessary, customer satisfaction can be improved.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The utterance analysis unit can not only analyze the content of a customer's utterances, but also analyze the customer's background and environmental sounds to score the degree of maliciousness. For example, if the background sounds include noise or yelling, the degree of maliciousness is scored high. The utterance analysis unit can also analyze the customer's environmental sounds and score the degree of maliciousness high if there is a possibility that the customer is in a stressful environment. Furthermore, the utterance analysis unit can comprehensively analyze the background and environmental sounds to score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by analyzing the background and environmental sounds.

[0072] When analyzing the content of a customer's comments, the comment analysis unit can score the degree of maliciousness by taking into account the customer's social and cultural background. For example, if an expression that is acceptable in a particular cultural sphere is considered inappropriate in another cultural sphere, the score can be determined by taking that difference into account. The comment analysis unit can also analyze the customer's social background and appropriately evaluate the content of the comment based on that particular social background. Furthermore, the comment analysis unit can comprehensively analyze cultural and social backgrounds and score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by taking social and cultural backgrounds into account.

[0073] When analyzing the content of a customer's comments, the comment analysis unit can take into account the customer's health and psychological state and score the degree of maliciousness. For example, if a customer is ill or stressed, the score can be determined taking these conditions into consideration. The comment analysis unit can also analyze the customer's psychological state and appropriately evaluate the content of comments based on a specific psychological state. Furthermore, the comment analysis unit can comprehensively analyze the customer's health and psychological state and score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by taking into account the customer's health and psychological state.

[0074] When analyzing the content of a customer's statements, the statement analysis unit can detect consistency or inconsistency in the customer's statements and score the degree of maliciousness. For example, if a customer repeatedly makes contradictory statements, the degree of maliciousness is scored high. The statement analysis unit can also analyze the consistency of the customer's statements and appropriately evaluate inconsistent statements. Furthermore, the statement analysis unit can comprehensively analyze the consistency and inconsistency of the statements and score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by taking into account the consistency and inconsistency of the statements.

[0075] When analyzing the content of a customer's utterances, the utterance analysis unit can evaluate the grammar and language usage of the customer's utterances and score the degree of maliciousness. For example, if the customer uses inappropriate grammar or language, the utterance analysis unit can assign a high score to the degree of maliciousness. The utterance analysis unit can also analyze the customer's language usage and appropriately evaluate the inappropriate language usage. Furthermore, the utterance analysis unit can comprehensively analyze the grammar and language usage and score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness by taking grammar and language usage into consideration.

[0076] When analyzing the content of a customer's comments, the comment analysis unit can estimate the customer's emotions and score the degree of maliciousness based on the estimated emotions. For example, if a customer makes a comment expressing anger or irritation, the intensity and type of the emotion can be quantified and the degree of maliciousness can be scored. The comment analysis unit can also estimate the customer's emotions, classify the intensity and type of emotions, and score the degree of maliciousness. Furthermore, the comment analysis unit can comprehensively analyze the intensity and type of emotions and score the degree of maliciousness. This improves the accuracy of scoring the degree of maliciousness through emotion estimation.

[0077] When analyzing the content of a customer's comments, the utterance analysis unit can estimate the customer's emotions and suggest a response method for the operator based on the estimated emotions. For example, if the customer shows anger, the utterance analysis unit can suggest a calm response to the operator. The utterance analysis unit can also estimate the customer's emotions and suggest a response method based on the intensity and type of emotion. Furthermore, the utterance analysis unit can comprehensively analyze the intensity and type of emotion and suggest the optimal response method. This makes it possible to optimize the operator's response method through emotion estimation.

[0078] When analyzing the content of a customer's comments, the utterance analysis unit can estimate the customer's emotions and customize the content of the warning based on the estimated emotions. For example, if the customer is showing anger, the utterance analysis unit can generate a warning message in a calm tone. The utterance analysis unit can also estimate the customer's emotions and generate a warning message according to the intensity and type of emotion. Furthermore, the utterance analysis unit can comprehensively analyze the intensity and type of emotion and generate an optimal warning message. This makes it possible to optimize the content of the warning based on emotion estimation.

[0079] When analyzing the content of a customer's comments, the utterance analysis unit can estimate the customer's emotions and optimize the end timing based on the estimated emotions. For example, if the customer is angry, it can suggest ending the conversation early. The utterance analysis unit can also estimate the customer's emotions and suggest the end timing based on the intensity and type of emotion. Furthermore, the utterance analysis unit can comprehensively analyze the intensity and type of emotion and suggest the optimal end timing. This makes it possible to optimize the end timing through emotion estimation.

[0080] When analyzing the content of a customer's comments, the utterance analysis unit can estimate the customer's emotions and customize the content of follow-up based on the estimated emotions. For example, if the customer expresses dissatisfaction, an apology message can be sent. The utterance analysis unit can also estimate the customer's emotions and generate follow-up content according to the intensity and type of emotions. Furthermore, the utterance analysis unit can comprehensively analyze the intensity and type of emotions and generate optimal follow-up content. This makes it possible to optimize the content of follow-up based on emotion estimation.

[0081] The processing flow of the second embodiment will be briefly explained below.

[0082] Step 1: The utterance analysis unit analyzes the content of customer utterances. For example, the utterance analysis unit uses natural language processing technology to analyze the content of customer utterances in real time. It can also use voice recognition technology to convert voice data into text data and analyze the content. It can also perform keyword-based analysis and measure the frequency of occurrence of specific keywords. Step 2: The scoring unit scores the comments analyzed by the comment analysis unit. For example, it uses sentiment analysis technology to score the intensity and type of emotion in the customer's comments. It can also score based on the frequency of keyword appearances. It is also possible to analyze the context of the customer's comments and perform a comprehensive score. Step 3: The warning unit issues a warning based on the results of the scoring by the scoring unit. For example, if the score exceeds a certain threshold, a warning may be issued by voice. It may also be possible to issue a warning by text message or email. Step 4: The termination unit automatically terminates the call if the customer's behavior remains unchanged even after the warning unit issues a warning. For example, the call can be automatically terminated if the customer's comments do not improve after three warnings have been issued. It can also terminate the call immediately if the score exceeds a certain threshold. Furthermore, it is possible to optimize the timing of termination based on the content of the customer's comments.

[0083] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0084] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0085] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0086] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0087] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0088] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0089] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0090] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0091] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0092] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0093] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0094] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0095] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0096] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0097] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0100] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0101] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0102] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0108] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0111] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0115] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0116] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0117] 7, a 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.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0124] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0127] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0129] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0133] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0134] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0135] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0136] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0137] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0138] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0139] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0140] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0141] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0142] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0143] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0144] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0145] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0146] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0147] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0148] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0149] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0150] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a statement analysis unit that analyzes the content of customer statements; a scoring unit that scores the utterance content analyzed by the utterance analysis unit; a warning unit that issues a warning based on the result of the scoring by the scoring unit; and a termination unit that automatically terminates the call if the situation does not improve after the warning unit issues a warning. A system characterized by:

2. The utterance analysis unit Generative AI is used to analyze emotions and score maliciousness based on the intensity and type of emotion.

2. The system of claim 1.

3. The utterance analysis unit Simultaneously analyze text messages and chat logs to score maliciousness from multimodal data 2. The system of claim 1.

4. The warning unit Generative AI is used to estimate the customer's emotions and automatically generate the most effective warning message.

2. The system of claim 1.

5. The end portion is Using generative AI to estimate the customer's emotions, and send a message that takes the customer's emotions into consideration as a final warning.

2. The system of claim 1.

6. The utterance analysis unit Analyze the emotional response of operators to customer comments and set scoring criteria to reduce the stress level of operators 2. The system of claim 1.

7. The warning unit Evaluate the effectiveness of warnings in real time and continuously improve the content and issuance of warnings.

2. The system of claim 1.

8. The end portion is Monitor the customer's emotional response after the automated termination and follow up as needed 2. The system of claim 1.

Images