system

Abstract

An object of a system according to an embodiment is to detect and filter inappropriate utterances in response to customers in real time.SOLUTION: A system according to an embodiment includes an edge device, an NLP analysis unit, a cache miss detection unit, and a filtering unit. The edge device analyzes the statement of the customer in detail. The NLP analysis unit analyzes the speech of the customer in detail. The speech detection unit detects an inappropriate speech from the speech analyzed by the NLP analysis unit. The filtering unit automatically filters the inappropriate speech detected by the speech detection unit.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, it is difficult to detect and filter inappropriate comments in real time when dealing with customers, which can increase the mental burden on operators.

[0005] The system according to the embodiment aims to detect and filter inappropriate comments in real time when dealing with customers. [Means for solving the problem]

[0006] The system according to the embodiment includes an edge device, an NLP analysis unit, a customer harassment detection unit, and a filtering unit. The edge device analyzes customer comments in detail. The NLP analysis unit analyzes customer comments in detail. The customer harassment detection unit detects inappropriate comments from the comments analyzed by the NLP analysis unit. The filtering unit automatically filters out inappropriate comments detected by the customer harassment detection unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect and filter inappropriate comments in customer interactions in real time. [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) A customer harassment detection system according to an embodiment of the present invention is a system that detects and responds to customer harassment in real time by integrating edge computing and advanced natural language processing (NLP) technology. As a result, the customer harassment detection system can significantly reduce the mental burden on operators and improve the quality of customer service.

[0029] A customer harassment detection system according to an embodiment includes an edge device, an NLP analysis unit, a customer harassment detection unit, and a filtering unit. The edge device analyzes customer utterances in real time. For example, the edge device converts customer utterances into text data using speech recognition technology. The edge device can also record customer utterances and analyze them later. The edge device can also analyze customer utterances in real time and provide immediate feedback. The NLP analysis unit performs detailed analysis of customer utterances acquired by the edge device. For example, the NLP analysis unit analyzes the meaning of customer utterances using natural language processing technology. The NLP analysis unit can also analyze the context of customer utterances to understand the intention of the utterance. The NLP analysis unit can also analyze the emotional tone of customer utterances to estimate the emotional state. The customer harassment detection unit detects inappropriate utterances from the utterances analyzed by the NLP analysis unit. For example, the customer harassment detection unit detects inappropriate utterances using a machine learning algorithm. The customer harassment detection unit can also detect inappropriate utterances using keyword-based filtering. The customer harassment detection unit can also detect inappropriate utterances based on past case data. The filtering unit automatically filters inappropriate comments detected by the customer harassment detection unit. For example, the filtering unit hides the inappropriate comments or replaces them with appropriate words. The filtering unit can also notify the operator of the inappropriate comments and encourage them to take an appropriate action. The filtering unit can also automatically correct the inappropriate comments made to the customer. This allows the customer harassment detection system according to the embodiment to reduce the mental burden on the operator and improve the quality of customer service. For example, the system provides the operator with advice to encourage them to respond calmly. The system also sends a message to the customer to refrain from making inappropriate comments. The system also monitors the operator's stress level and suggests taking a break if necessary.

[0030] When analyzing a customer's speech, the edge device simultaneously analyzes background and environmental sounds, allowing for a more accurate understanding of the intent of the speech. For example, when analyzing a customer's speech, the edge device simultaneously collects and analyzes surrounding background and environmental sounds. For example, if a customer is speaking in a noisy environment, the edge device can take that background sound into consideration to accurately understand the intent of the speech. The edge device can also analyze background and environmental sounds to understand the context of the customer's speech. The edge device can also analyze background and environmental sounds to estimate the customer's emotional state. This allows for a more accurate understanding of the intent of the customer's speech.

[0031] Edge devices can share information in real time among multiple operators, learn patterns of customer harassment, and evolve countermeasures. For example, edge devices can share information in real time among multiple operators and learn patterns of customer harassment. For example, an operator can share cases of customer harassment that he or she has experienced with other operators and evolve countermeasures. Edge devices can also learn patterns of customer harassment and evolve countermeasures based on data from past cases. Edge devices can also learn patterns of customer harassment and evolve countermeasures using machine learning algorithms. In this way, it is possible to learn patterns of customer harassment and evolve countermeasures.

[0032] Edge devices can detect customer harassment by analyzing not only what customers say but also text communications such as chat and email in real time. For example, if a customer sends an offensive message in chat, the content can be analyzed immediately and a response can be made. Edge devices can also analyze text communications to understand the context of what customers say. Edge devices can also analyze text communications to estimate the emotional state of customers. This makes it possible to detect customer harassment in text communications in real time.

[0033] The edge device can monitor the operator's biometric information and provide countermeasures according to the operator's condition. For example, the edge device can monitor the operator's heart rate and stress level and provide countermeasures based on that data. For example, if the operator's stress level is high, the edge device can suggest taking a break. The edge device can also monitor the operator's biometric information and provide advice according to the operator's condition. The edge device can also monitor the operator's biometric information and adjust work. This makes it possible to provide appropriate countermeasures based on the operator's biometric information.

[0034] The NLP analysis unit analyzes the context of a customer's comments and compares it with past comment history to detect signs of customer harassment early on. The NLP analysis unit, for example, analyzes the context of a customer's comments and compares it with past comment history to detect signs of customer harassment early on. For example, if a customer has made aggressive comments in the past, signs of customer harassment can be detected based on that history. The NLP analysis unit can also analyze the context of a customer's comments to understand the customer's intentions. The NLP analysis unit can also analyze the context of a customer's comments and estimate the customer's emotional state. This allows for early detection of signs of customer harassment.

[0035] The NLP analysis unit can analyze the emotional tone of a customer's speech and issue a warning to an operator if the aggressive tone persists. For example, the NLP analysis unit analyzes the emotional tone of a customer's speech and issue a warning to an operator if the aggressive tone persists. For example, if a customer speaks in an angry tone, the NLP analysis unit detects that emotion and notifies the operator. The NLP analysis unit can also analyze the emotional tone of a customer's speech and estimate the customer's emotional state. The NLP analysis unit can also analyze the emotional tone of a customer's speech and prompt the customer to take an appropriate action. This makes it possible to issue a warning to an operator if the aggressive tone persists.

[0036] The NLP analysis unit analyzes customer comments in multiple languages, enabling international responses to customer harassment. The NLP analysis unit, for example, analyzes customer comments in multiple languages, enabling international responses to customer harassment. For example, it analyzes comments in multiple languages, such as English, French, and Chinese, to detect customer harassment. The NLP analysis unit can also respond to customer harassment based on a multilingual manual. The NLP analysis unit can also respond to customer harassment while complying with international laws and regulations. This enables international responses to customer harassment.

[0037] The NLP analysis unit can summarize what customers say in real time, allowing the operator to respond quickly. The NLP analysis unit, for example, summarizes what customers say in real time, allowing the operator to respond quickly. For example, it can summarize long statements in a short form and present the important points to the operator. The NLP analysis unit can also summarize what customers say and notify the operator in real time. The NLP analysis unit can also summarize what customers say and set priorities for the operator. This allows the operator to summarize what customers say in real time, allowing the operator to respond quickly.

[0038] When customer harassment is detected, the customer harassment detection unit can provide a specific response manual to the operator, thereby supporting a prompt and appropriate response. For example, when customer harassment is detected, the customer harassment detection unit can provide a specific response manual to the operator. For example, it can present an appropriate way to respond to offensive remarks. The customer harassment detection unit can also notify the operator in real time based on the response manual. The customer harassment detection unit can also set priorities for operators based on the response manual. This makes it possible to support a prompt and appropriate response when customer harassment is detected.

[0039] The customer harassment detection unit can learn customer harassment patterns and compare them with past cases to propose optimal countermeasures. The customer harassment detection unit, for example, learns customer harassment patterns and compares them with past cases to propose optimal countermeasures. For example, countermeasures are generated based on past successful cases. The customer harassment detection unit can also use machine learning algorithms to learn customer harassment patterns and evolve countermeasures. The customer harassment detection unit can also propose countermeasures based on past case data. This allows the unit to learn customer harassment patterns and propose optimal countermeasures.

[0040] When customer harassment is detected, the customer harassment detection unit can monitor the stress level of the operator and suggest a break as necessary. For example, when customer harassment is detected, the customer harassment detection unit can monitor the stress level of the operator and suggest a break as necessary. For example, if the stress level is high, it can suggest a short break. The customer harassment detection unit can also monitor the stress level of the operator and provide advice according to the operator's condition. The customer harassment detection unit can also monitor the stress level of the operator and adjust work. This makes it possible to monitor the stress level of the operator and suggest a break as necessary.

[0041] When customer harassment is detected, the customer harassment detection unit can notify other operators or administrators in real time and encourage a prompt response. For example, when customer harassment is detected, the customer harassment detection unit can notify other operators or administrators in real time and encourage a prompt response. For example, if an offensive remark is detected, the customer harassment detection unit can notify an administrator and request a response. The customer harassment detection unit can also notify other operators or administrators in real time and set priorities. The customer harassment detection unit can also notify other operators or administrators in real time and suggest countermeasures. This makes it possible to notify other operators or administrators in real time when customer harassment is detected and encourage a prompt response.

[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 customer harassment detection system can also be equipped with a cultural analysis unit that analyzes the cultural factors behind customer comments. For example, if a customer has a specific cultural background, the system can understand expressions and phrases unique to that culture and respond appropriately. The cultural analysis unit can also analyze the cultural factors behind the customer's comments and prompt the operator to respond in a culturally appropriate manner. The cultural analysis unit can also analyze the cultural factors behind the customer's comments and send a culturally appropriate message to the customer. This enables responses that take into account the customer's cultural background, thereby improving customer satisfaction.

[0044] The customer harassment detection system can also be equipped with a social analysis unit that analyzes the social factors behind customer comments. For example, if a customer has a specific social background, it can understand those social factors and respond appropriately. The social analysis unit can also analyze the social factors behind a customer's comments and prompt the operator to respond in a socially appropriate manner. Furthermore, the social analysis unit can analyze the social factors behind a customer's comments and send a socially appropriate message to the customer. This makes it possible to respond in a way that takes into account the customer's social background, thereby improving customer satisfaction.

[0045] The customer harassment detection system can also be equipped with an economic analysis unit that analyzes the economic factors behind customer comments. For example, if a customer is in a financially difficult situation, the system can understand their financial situation and respond appropriately. The economic analysis unit can also analyze the economic factors behind the customer's comments and prompt the operator to respond in an economically appropriate manner. The economic analysis unit can also analyze the economic factors behind the customer's comments and send an economically appropriate message to the customer. This makes it possible to respond in a way that takes into account the customer's financial situation, thereby improving customer satisfaction.

[0046] The customer harassment detection system can also be equipped with a health analysis unit that analyzes the health condition behind a customer's comments. For example, if a customer has a health problem, the system can understand that health condition and take appropriate action. The health analysis unit can also analyze the health condition behind a customer's comments and prompt the operator to take appropriate health-related action. Furthermore, the health analysis unit can analyze the health condition behind a customer's comments and send appropriate health-related messages to the customer. This makes it possible to take action that takes the customer's health condition into consideration, thereby improving customer satisfaction.

[0047] The processing flow of the first embodiment will be briefly explained below.

[0048] Step 1: The edge device analyzes what the customer says in real time. For example, the edge device can convert what the customer says into text data using voice recognition technology. The edge device can also record what the customer says and analyze it later. The edge device can also analyze what the customer says in real time and provide immediate feedback. Step 2: The NLP analysis unit performs a detailed analysis of the customer's utterances acquired by the edge device. For example, the NLP analysis unit uses natural language processing technology to analyze the meaning of the customer's utterances. The NLP analysis unit can also analyze the context of the customer's utterances to understand their intentions. The NLP analysis unit can also analyze the emotional tone of the customer's utterances to estimate their emotional state. Step 3: The customer harassment detection unit detects inappropriate remarks from the remarks analyzed by the NLP analysis unit. For example, the customer harassment detection unit detects inappropriate remarks using a machine learning algorithm. The customer harassment detection unit can also detect inappropriate remarks using keyword-based filtering. The customer harassment detection unit can also detect inappropriate remarks based on past case data. Step 4: The filtering unit automatically filters out inappropriate comments detected by the customer harassment detection unit. For example, the filtering unit hides the inappropriate comments or replaces them with appropriate words. The filtering unit can also notify an operator of the inappropriate comments and prompt them to take appropriate action. The filtering unit can also automatically correct the inappropriate comments for the customer.

[0049] (Example 2) A customer harassment detection system according to an embodiment of the present invention is a system that detects and responds to customer harassment in real time by integrating edge computing and advanced natural language processing (NLP) technology. As a result, the customer harassment detection system can significantly reduce the mental burden on operators and improve the quality of customer service.

[0050] A customer harassment detection system according to an embodiment includes an edge device, an NLP analysis unit, a customer harassment detection unit, and a filtering unit. The edge device analyzes customer utterances in real time. For example, the edge device converts customer utterances into text data using speech recognition technology. The edge device can also record customer utterances and analyze them later. The edge device can also analyze customer utterances in real time and provide immediate feedback. The NLP analysis unit performs detailed analysis of customer utterances acquired by the edge device. For example, the NLP analysis unit analyzes the meaning of customer utterances using natural language processing technology. The NLP analysis unit can also analyze the context of customer utterances to understand the intention of the utterance. The NLP analysis unit can also analyze the emotional tone of customer utterances to estimate the emotional state. The customer harassment detection unit detects inappropriate utterances from the utterances analyzed by the NLP analysis unit. For example, the customer harassment detection unit detects inappropriate utterances using a machine learning algorithm. The customer harassment detection unit can also detect inappropriate utterances using keyword-based filtering. The customer harassment detection unit can also detect inappropriate utterances based on past case data. The filtering unit automatically filters inappropriate comments detected by the customer harassment detection unit. For example, the filtering unit hides the inappropriate comments or replaces them with appropriate words. The filtering unit can also notify the operator of the inappropriate comments and encourage them to take an appropriate action. The filtering unit can also automatically correct the inappropriate comments made to the customer. This allows the customer harassment detection system according to the embodiment to reduce the mental burden on the operator and improve the quality of customer service. For example, the system provides the operator with advice to encourage them to respond calmly. The system also sends a message to the customer to refrain from making inappropriate comments. The system also monitors the operator's stress level and suggests taking a break if necessary.

[0051] When analyzing a customer's speech, the edge device simultaneously analyzes background and environmental sounds, allowing for a more accurate understanding of the intent of the speech. For example, when analyzing a customer's speech, the edge device simultaneously collects and analyzes surrounding background and environmental sounds. For example, if a customer is speaking in a noisy environment, the edge device can take that background sound into consideration to accurately understand the intent of the speech. The edge device can also analyze background and environmental sounds to understand the context of the customer's speech. The edge device can also analyze background and environmental sounds to estimate the customer's emotional state. This allows for a more accurate understanding of the intent of the customer's speech.

[0052] Edge devices can share information in real time among multiple operators, learn patterns of customer harassment, and evolve countermeasures. For example, edge devices can share information in real time among multiple operators and learn patterns of customer harassment. For example, an operator can share cases of customer harassment that he or she has experienced with other operators and evolve countermeasures. Edge devices can also learn patterns of customer harassment and evolve countermeasures based on data from past cases. Edge devices can also learn patterns of customer harassment and evolve countermeasures using machine learning algorithms. In this way, it is possible to learn patterns of customer harassment and evolve countermeasures.

[0053] The edge device incorporates an emotion estimation function, which allows it to estimate the emotional state of a customer in real time and take appropriate action. The edge device, for example, incorporates an emotion estimation function and analyzes the content and tone of a customer's speech to estimate the emotional state in real time. For example, if a customer is angry, the edge device can instantly detect that emotion and notify an operator. The edge device can also estimate the emotional state of a customer and provide advice on how to take appropriate action. The edge device can also estimate the emotional state of a customer and send an appropriate message to the customer. This allows it to estimate the emotional state of a customer in real time and take appropriate action.

[0054] Edge devices can detect customer harassment by analyzing not only what customers say but also text communications such as chat and email in real time. For example, if a customer sends an offensive message in chat, the content can be analyzed immediately and a response can be made. Edge devices can also analyze text communications to understand the context of what customers say. Edge devices can also analyze text communications to estimate the emotional state of customers. This makes it possible to detect customer harassment in text communications in real time.

[0055] The edge device can monitor the operator's biometric information and provide countermeasures according to the operator's condition. For example, the edge device can monitor the operator's heart rate and stress level and provide countermeasures based on that data. For example, if the operator's stress level is high, the edge device can suggest taking a break. The edge device can also monitor the operator's biometric information and provide advice according to the operator's condition. The edge device can also monitor the operator's biometric information and adjust work. This makes it possible to provide appropriate countermeasures based on the operator's biometric information.

[0056] The edge device can estimate a customer's emotions in real time and make suggestions to elicit positive emotions. The edge device can, for example, estimate a customer's emotions in real time and make suggestions to elicit positive emotions. For example, if a customer is dissatisfied, the edge device can detect that emotion and prompt an operator to respond in a positive manner. The edge device can also estimate a customer's emotions and send a positive message to the customer. The edge device can also estimate a customer's emotions and offer a special benefit to the customer. This makes it possible to make suggestions to elicit positive emotions in the customer.

[0057] The NLP analysis unit analyzes the context of a customer's comments and compares it with past comment history to detect signs of customer harassment early on. The NLP analysis unit, for example, analyzes the context of a customer's comments and compares it with past comment history to detect signs of customer harassment early on. For example, if a customer has made aggressive comments in the past, signs of customer harassment can be detected based on that history. The NLP analysis unit can also analyze the context of a customer's comments to understand the customer's intentions. The NLP analysis unit can also analyze the context of a customer's comments and estimate the customer's emotional state. This allows for early detection of signs of customer harassment.

[0058] The NLP analysis unit can analyze the emotional tone of a customer's speech and issue a warning to an operator if the aggressive tone persists. For example, the NLP analysis unit analyzes the emotional tone of a customer's speech and issue a warning to an operator if the aggressive tone persists. For example, if a customer speaks in an angry tone, the NLP analysis unit detects that emotion and notifies the operator. The NLP analysis unit can also analyze the emotional tone of a customer's speech and estimate the customer's emotional state. The NLP analysis unit can also analyze the emotional tone of a customer's speech and prompt the customer to take an appropriate action. This makes it possible to issue a warning to an operator if the aggressive tone persists.

[0059] The NLP analysis unit can integrate an emotion estimation function to estimate the emotional state of a customer and generate appropriate countermeasures. For example, the NLP analysis unit can integrate an emotion estimation function to analyze the content and tone of a customer's speech to estimate the emotional state and generate appropriate countermeasures. For example, if a customer is angry, the NLP analysis unit can detect that emotion and urge the operator to respond calmly. The NLP analysis unit can also estimate the emotional state of a customer and send an appropriate message to the customer. The NLP analysis unit can also estimate the emotional state of a customer and provide a special benefit to the customer. This makes it possible to estimate the emotional state of a customer and generate appropriate countermeasures.

[0060] The NLP analysis unit analyzes customer comments in multiple languages, enabling international responses to customer harassment. The NLP analysis unit, for example, analyzes customer comments in multiple languages, enabling international responses to customer harassment. For example, it analyzes comments in multiple languages, such as English, French, and Chinese, to detect customer harassment. The NLP analysis unit can also respond to customer harassment based on a multilingual manual. The NLP analysis unit can also respond to customer harassment while complying with international laws and regulations. This enables international responses to customer harassment.

[0061] The NLP analysis unit can summarize what customers say in real time, allowing the operator to respond quickly. The NLP analysis unit, for example, summarizes what customers say in real time, allowing the operator to respond quickly. For example, it can summarize long statements in a short form and present the important points to the operator. The NLP analysis unit can also summarize what customers say and notify the operator in real time. The NLP analysis unit can also summarize what customers say and set priorities for the operator. This allows the operator to summarize what customers say in real time, allowing the operator to respond quickly.

[0062] The NLP analysis unit can use the emotion estimation function to analyze customer emotions in real time and provide countermeasures to elicit positive emotions. The NLP analysis unit can, for example, use the emotion estimation function to analyze customer emotions in real time and provide countermeasures to elicit positive emotions. For example, if a customer is dissatisfied, the NLP analysis unit can detect that emotion and prompt the operator to respond in a positive manner. The NLP analysis unit can also analyze customer emotions and send positive messages to the customer. The NLP analysis unit can also analyze customer emotions and provide benefits to the customer. In this way, countermeasures to elicit positive emotions in the customer can be provided.

[0063] When customer harassment is detected, the customer harassment detection unit can provide a specific response manual to the operator, thereby supporting a prompt and appropriate response. For example, when customer harassment is detected, the customer harassment detection unit can provide a specific response manual to the operator. For example, it can present an appropriate way to respond to offensive remarks. The customer harassment detection unit can also notify the operator in real time based on the response manual. The customer harassment detection unit can also set priorities for operators based on the response manual. This makes it possible to support a prompt and appropriate response when customer harassment is detected.

[0064] The customer harassment detection unit can learn customer harassment patterns and compare them with past cases to propose optimal countermeasures. The customer harassment detection unit, for example, learns customer harassment patterns and compares them with past cases to propose optimal countermeasures. For example, countermeasures are generated based on past successful cases. The customer harassment detection unit can also use machine learning algorithms to learn customer harassment patterns and evolve countermeasures. The customer harassment detection unit can also propose countermeasures based on past case data. This allows the unit to learn customer harassment patterns and propose optimal countermeasures.

[0065] The customer harassment detection unit can use the emotion estimation function to estimate the emotional state of the customer in real time and generate appropriate countermeasures. The customer harassment detection unit can, for example, use the emotion estimation function to estimate the emotional state of the customer in real time and generate appropriate countermeasures. For example, if a customer is angry, the customer harassment detection unit can detect that emotion and urge the operator to respond calmly. The customer harassment detection unit can also estimate the emotional state of the customer and send an appropriate message to the customer. The customer harassment detection unit can also estimate the emotional state of the customer and provide a special benefit to the customer. In this way, the customer harassment detection unit can estimate the emotional state of the customer in real time and generate appropriate countermeasures.

[0066] When customer harassment is detected, the customer harassment detection unit can monitor the stress level of the operator and suggest a break as necessary. For example, when customer harassment is detected, the customer harassment detection unit can monitor the stress level of the operator and suggest a break as necessary. For example, if the stress level is high, it can suggest a short break. The customer harassment detection unit can also monitor the stress level of the operator and provide advice according to the operator's condition. The customer harassment detection unit can also monitor the stress level of the operator and adjust work. This makes it possible to monitor the stress level of the operator and suggest a break as necessary.

[0067] When customer harassment is detected, the customer harassment detection unit can notify other operators or administrators in real time and encourage a prompt response. For example, when customer harassment is detected, the customer harassment detection unit can notify other operators or administrators in real time and encourage a prompt response. For example, if an offensive remark is detected, the customer harassment detection unit can notify an administrator and request a response. The customer harassment detection unit can also notify other operators or administrators in real time and set priorities. The customer harassment detection unit can also notify other operators or administrators in real time and suggest countermeasures. This makes it possible to notify other operators or administrators in real time when customer harassment is detected and encourage a prompt response.

[0068] The customer harassment detection unit can use the emotion estimation function to analyze customer emotions in real time and provide countermeasures to elicit positive emotions. The customer harassment detection unit can, for example, use the emotion estimation function to analyze customer emotions in real time and provide countermeasures to elicit positive emotions. For example, if a customer is dissatisfied, the customer harassment detection unit can detect that emotion and encourage the operator to respond in a positive manner. The customer harassment detection unit can also analyze customer emotions and send positive messages to the customer. The customer harassment detection unit can also analyze customer emotions and offer benefits to the customer. This makes it possible to provide countermeasures to elicit positive emotions in the customer.

[0069] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0070] The customer harassment detection system can also be equipped with a cultural analysis unit that analyzes the cultural factors behind customer comments. For example, if a customer has a specific cultural background, the system can understand expressions and phrases unique to that culture and respond appropriately. The cultural analysis unit can also analyze the cultural factors behind the customer's comments and prompt the operator to respond in a culturally appropriate manner. The cultural analysis unit can also analyze the cultural factors behind the customer's comments and send a culturally appropriate message to the customer. This enables responses that take into account the customer's cultural background, thereby improving customer satisfaction.

[0071] The customer harassment detection system can also be equipped with a psychology analysis unit that analyzes the psychological factors behind customer comments. For example, if a customer is feeling stressed, the system can understand their psychological state and respond appropriately. The psychology analysis unit can also analyze the psychological factors behind the customer's comments and prompt the operator to respond psychologically appropriately. The psychology analysis unit can also analyze the psychological factors behind the customer's comments and send a psychologically appropriate message to the customer. This makes it possible to respond in a way that takes the customer's psychological state into consideration, thereby improving customer satisfaction.

[0072] The customer harassment detection system can also be equipped with a social analysis unit that analyzes the social factors behind customer comments. For example, if a customer has a specific social background, it can understand those social factors and respond appropriately. The social analysis unit can also analyze the social factors behind a customer's comments and prompt the operator to respond in a socially appropriate manner. Furthermore, the social analysis unit can analyze the social factors behind a customer's comments and send a socially appropriate message to the customer. This makes it possible to respond in a way that takes into account the customer's social background, thereby improving customer satisfaction.

[0073] The customer harassment detection system can also be equipped with an economic analysis unit that analyzes the economic factors behind customer comments. For example, if a customer is in a financially difficult situation, the system can understand their financial situation and respond appropriately. The economic analysis unit can also analyze the economic factors behind the customer's comments and prompt the operator to respond in an economically appropriate manner. The economic analysis unit can also analyze the economic factors behind the customer's comments and send an economically appropriate message to the customer. This makes it possible to respond in a way that takes into account the customer's financial situation, thereby improving customer satisfaction.

[0074] The customer harassment detection system can also be equipped with a health analysis unit that analyzes the health condition behind a customer's comments. For example, if a customer has a health problem, the system can understand that health condition and take appropriate action. The health analysis unit can also analyze the health condition behind a customer's comments and prompt the operator to take appropriate health-related action. Furthermore, the health analysis unit can analyze the health condition behind a customer's comments and send appropriate health-related messages to the customer. This makes it possible to take action that takes the customer's health condition into consideration, thereby improving customer satisfaction.

[0075] The customer harassment detection system can also analyze the emotional state behind a customer's comments and respond accordingly. For example, if a customer is angry, it can understand that emotion and encourage the operator to respond calmly. It can also analyze the customer's emotional state and send an appropriate message to the customer. It can also analyze the customer's emotional state and offer the customer a special benefit. This makes it possible to respond in a way that takes the customer's emotional state into consideration, thereby improving customer satisfaction.

[0076] The customer harassment detection system can also analyze the emotional tone behind what a customer says and respond accordingly. For example, if a customer speaks in an aggressive tone, the system can understand that emotional tone and encourage the operator to respond calmly. It can also analyze the customer's emotional tone and send an appropriate message to the customer. It can also analyze the customer's emotional tone and offer the customer a special benefit. This makes it possible to respond in a way that takes the customer's emotional tone into consideration, thereby improving customer satisfaction.

[0077] The customer harassment detection system can also analyze the emotional patterns behind customer comments and respond accordingly. For example, if a customer repeatedly expresses anger, it can understand this emotional pattern and encourage the operator to respond calmly. It can also analyze the customer's emotional patterns and send appropriate messages to the customer. It can also analyze the customer's emotional patterns and offer special benefits to the customer. This makes it possible to respond in a way that takes into account the customer's emotional patterns, thereby improving customer satisfaction.

[0078] The customer harassment detection system can also analyze the emotional history behind the customer's comments and respond accordingly. For example, if a customer has previously expressed anger, the system can understand that emotional history and encourage the operator to respond calmly. It can also analyze the customer's emotional history and send an appropriate message to the customer. It can also analyze the customer's emotional history and offer special benefits to the customer. This makes it possible to respond in a way that takes into account the customer's emotional history, thereby improving customer satisfaction.

[0079] The customer harassment detection system can also analyze the emotional tendencies behind the customer's comments and respond accordingly. For example, if a customer consistently displays positive emotions, it can understand this emotional tendency and encourage the operator to respond in a positive manner. It can also analyze the customer's emotional tendencies and send appropriate messages to the customer. It can also analyze the customer's emotional tendencies and offer special benefits to the customer. This makes it possible to respond in a way that takes the customer's emotional tendencies into account, thereby improving customer satisfaction.

[0080] The processing flow of the second embodiment will be briefly explained below.

[0081] Step 1: The edge device analyzes what the customer says in real time. For example, the edge device can convert what the customer says into text data using voice recognition technology. The edge device can also record what the customer says and analyze it later. The edge device can also analyze what the customer says in real time and provide immediate feedback. Step 2: The NLP analysis unit performs a detailed analysis of the customer's utterances acquired by the edge device. For example, the NLP analysis unit uses natural language processing technology to analyze the meaning of the customer's utterances. The NLP analysis unit can also analyze the context of the customer's utterances to understand their intentions. The NLP analysis unit can also analyze the emotional tone of the customer's utterances to estimate their emotional state. Step 3: The customer harassment detection unit detects inappropriate remarks from the remarks analyzed by the NLP analysis unit. For example, the customer harassment detection unit detects inappropriate remarks using a machine learning algorithm. The customer harassment detection unit can also detect inappropriate remarks using keyword-based filtering. The customer harassment detection unit can also detect inappropriate remarks based on past case data. Step 4: The filtering unit automatically filters out inappropriate comments detected by the customer harassment detection unit. For example, the filtering unit hides the inappropriate comments or replaces them with appropriate words. The filtering unit can also notify an operator of the inappropriate comments and prompt them to take appropriate action. The filtering unit can also automatically correct the inappropriate comments for the customer.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0086] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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).

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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).

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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."

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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]

[0149] 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. Edge devices; An NLP analysis section that analyzes customer comments in detail, a harassment detection unit that detects inappropriate comments from comments analyzed by the NLP analysis unit; a filtering unit that automatically filters out inappropriate comments detected by the harassment detection unit. A system characterized by:

2. The edge device When analyzing the customer's comments, background and environmental sounds are also analyzed at the same time to more accurately understand the intent of the comments.

2. The system of claim 1.

3. The edge device Not only the statements of the customer, but also text communications such as chats and emails are analyzed in real time to detect customer harassment.

2. The system of claim 1.

4. The NLP analysis unit Analyze the context of the customer's comments and compare them with past comment history to detect signs of customer harassment at an early stage.

2. The system of claim 1.

5. The customer harassment detection unit When customer harassment is detected, we provide operators with a specific response manual to help them respond quickly and appropriately.

2. The system of claim 1.

6. The edge device Incorporating an emotion estimation function to estimate the customer's emotional state in real time and respond appropriately 2. The system of claim 1.

Images