System

Abstract

An object of a system according to an embodiment is to accurately grasp a query intention of an incoming caller and appropriately respond to the query intention.SOLUTION: A system according to an embodiment includes a voice recognition unit, a question analysis unit, an automatic answer generation unit, a transfer unit, and a work support unit. The voice recognition unit recognizes a voice of an incoming caller. The question analysis unit analyzes the voice recognized by the voice recognition unit. The automatic answer generation unit automatically generates an answer to the question analyzed by the question analysis unit. The transfer unit transfers the answer generated by the automatic answer generation unit to the department in charge when the answer is inappropriate. The business support unit provides the query intention or the proposed solution analyzed by the query analysis unit to the operator.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 techniques, there was a problem in telephone answering work in that it was difficult to accurately understand the intent of the caller's question and respond appropriately.

[0005] The system according to the embodiment aims to accurately understand the intent of the caller's question and respond appropriately. [Means for solving the problem]

[0006] The system according to the embodiment includes a voice recognition unit, a question analysis unit, an automatic answer generation unit, a transfer unit, and a business support unit. The voice recognition unit recognizes the voice of the caller. The question analysis unit analyzes the voice recognized by the voice recognition unit. The automatic answer generation unit automatically generates an answer to the question analyzed by the question analysis unit. The transfer unit transfers the answer generated by the automatic answer generation unit to the relevant department if it is inappropriate. The business support unit provides the operator with the intent of the question or a solution proposed by the question analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can accurately grasp the intent of the caller's question and respond appropriately. [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 nonvolatile storage devices that store various programs, various parameters, etc. Examples of nonvolatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The telephone-related work efficiency improvement system according to an embodiment of the present invention is a system that automatically recognizes the caller's voice, analyzes the intent of the question using a generation AI, automatically generates an answer, and transfers the answer to the relevant department as necessary to support the operator. As a result, the telephone-related work efficiency system can respond to the caller's questions quickly and accurately, reduce the operator's burden, and improve the caller's satisfaction.

[0029] A telephone-related business efficiency improvement system according to an embodiment includes a voice recognition unit, a question analysis unit, an automatic answer generation unit, a transfer unit, and a business support unit. The voice recognition unit recognizes the voice of a caller. For example, the voice recognition unit recognizes telephone voice in real time and converts it into text data. The voice recognition unit can also analyze recorded voice and convert it into text data. The voice recognition unit performs highly accurate voice recognition using a voice recognition algorithm. The question analysis unit analyzes the voice recognized by the voice recognition unit. For example, the question analysis unit analyzes the intent of the question using natural language processing technology. The question analysis unit can also analyze the content of the voice data and identify the type of question. The question analysis unit can also evaluate the importance of the question using an analysis algorithm. The automatic answer generation unit automatically generates an answer to the question analyzed by the question analysis unit. For example, the automatic answer generation unit generates an appropriate answer using an answer generation algorithm. The automatic answer generation unit can also obtain related information from a database and generate an answer. The automatic answer generation unit generates an answer in natural language using a generation AI. The forwarding unit forwards the call to a responsible department if the answer generated by the automatic answer generation unit is inappropriate. For example, the forwarding unit selects an appropriate responsible department based on the forwarding conditions and forwards the call. The forwarding unit can also quickly forward the call using a forwarding system. The forwarding unit also records the forwarding history so that it can be referenced later. The business support unit provides the operator with the question intent and proposed solutions analyzed by the question analysis unit. For example, the business support unit presents proposed solutions to the operator in real time. The business support unit can also refer to the operator's past response history to suggest an optimal response method. The business support unit also provides tools to reduce the operator's burden. As a result, the telephone-related business efficiency system according to the embodiment can quickly and accurately respond to callers' questions, reduce the operator's burden, and improve the caller's satisfaction. For example, the caller can receive a quick answer, thereby shortening waiting time. Furthermore, the reduced burden on the operator can provide higher quality service.Furthermore, the system can analyze the caller's emotional state and suggest appropriate responses, further improving the caller's satisfaction.

[0030] The voice recognition unit can refer to the caller's past inquiry history and generate an answer that is individually customized. For example, the voice recognition unit retrieves the caller's past inquiries from a database and quickly generates an answer if a similar question arises again. For example, if a caller who previously asked a question about an invoice asks the same question again, the voice recognition unit can respond quickly by referring to the past answers. The voice recognition unit can also generate an answer that is individually customized based on the caller's past inquiry history. For example, if the caller asks about a specific product, detailed information about that product can be provided. This makes it possible to provide a more personalized response to the caller.

[0031] The automatic answer generation unit can automatically provide relevant videos or images in response to the caller's question, thereby providing visual support. For example, the automatic answer generation unit can automatically provide relevant videos in response to the caller's question. For example, in response to a question about how to use a product, it can provide a video explaining how to use the product. The automatic answer generation unit can also automatically provide relevant images in response to the caller's question. For example, it can provide detailed images of the product. The automatic answer generation unit can also build a system that uses videos and images to provide visual support. For example, it can explain how to use a product through a video, making it easier to understand visually. This can help the caller understand by providing visual information.

[0032] The automatic answer generation unit can generate an answer to the caller's question by referring to the ratings or feedback of other users. The automatic answer generation unit generates an answer to the caller's question, for example, based on the ratings and feedback of other users. For example, the automatic answer generation unit explains the features and advantages of a product by referring to product reviews and ratings. The automatic answer generation unit can also generate an optimal answer to the caller's question based on feedback from other users. For example, it explains how to use a product by referring to past user feedback. The automatic answer generation unit can also build a system that retrieves ratings and feedback from a database and reflects them in the answer. For example, it can automatically retrieve user reviews and reflect them in the answer. This makes it possible to provide more reliable information to the caller.

[0033] The business support department can refer to the operator's past response history and propose the optimal response method. For example, the business support department retrieves the operator's past response history from a database and proposes the optimal response method when a similar case occurs. For example, the business support department proposes the current response based on response methods that have been successful in the past. The business support department can also automatically propose the optimal response method based on the operator's past response history. For example, the business support department can propose the current response by referring to past successful cases. The business support department can also build a system that saves the response history in a database and allows it to be referenced later. For example, the business support department can search past response history and propose the optimal response method. This can improve the quality of the operator's response.

[0034] The business support department can automatically record the responses of operators and use them later for training or evaluation. For example, the business support department can automatically record the responses of operators and use them later for training. For example, good response examples can be used as training materials. The business support department can also automatically record the responses of operators and use them later for evaluation. For example, past response history can be referenced to evaluate operator performance. The business support department can also build a system that stores response history in a database and makes it possible to reference it later. For example, past response history can be searched and used for training or evaluation. This can improve operator skills and increase the accuracy of evaluation.

[0035] The business support department can automatically provide relevant documents or manuals in response to caller questions, thereby reducing the burden on operators. For example, the business support department can automatically provide relevant documents in response to caller questions. For example, in response to a question about how to use a product, it can provide a usage manual. The business support department can also automatically provide relevant manuals in response to caller questions. For example, it can provide a troubleshooting guide for the product. The business support department can also build a system that retrieves documents and manuals from a database and provides them to operators. For example, it can automatically search for and provide relevant documents in response to the caller's question. This can improve the work efficiency of operators.

[0036] The automatic answer generation unit can generate multiple answer candidates for a caller's question and select the most appropriate answer. For example, the automatic answer generation unit generates multiple answer candidates for a caller's question and selects the most appropriate answer. For example, for a question about how to use a product, the automatic answer generation unit can suggest multiple ways of using the product and select the most appropriate one. The automatic answer generation unit can also generate multiple answer candidates using an answer generation algorithm. For example, it can obtain related information from a database and generate multiple answers. The automatic answer generation unit can also build a system that selects the most appropriate answer from the generated answer candidates. For example, it can select the optimal answer based on the accuracy of the answer and the user's needs. This makes it possible to provide the caller with the optimal answer.

[0037] The automatic answer generation unit can generate an answer to a caller's question by referencing relevant legal information or regulations. For example, the automatic answer generation unit generates an appropriate answer by referencing relevant legal information to a caller's question. For example, in response to a question about returning a product, the automatic answer generation unit provides an answer based on consumer protection laws. The automatic answer generation unit can also generate an appropriate answer by referencing relevant regulations. For example, it provides an answer based on industry regulations. The automatic answer generation unit can also build a system that retrieves legal information and regulations from a database and reflects them in the answer. For example, it can automatically retrieve relevant legal provisions and reflect them in the answer. This makes it possible to provide a legally appropriate answer.

[0038] The automatic answer generation unit can generate answers to callers' questions by referencing related FAQs or community forum information. For example, the automatic answer generation unit generates an appropriate answer to a caller's question by referencing related FAQs. For example, in response to a question about how to use a product, it provides usage information from the FAQs. The automatic answer generation unit can also generate answers to callers' questions by referencing related community forum information. For example, it can explain the features and advantages of a product by referring to user posts. The automatic answer generation unit can also build a system that retrieves information from FAQs and community forums from a database and reflects it in the answer. For example, it can automatically retrieve related FAQs and reflect them in the answer. This makes it possible to provide a wider variety of information to callers.

[0039] The automatic answer generation unit can generate an answer to the caller's question by referring to the ratings or feedback of other users. The automatic answer generation unit generates an answer to the caller's question, for example, based on the ratings and feedback of other users. For example, the automatic answer generation unit explains the features and advantages of a product by referring to product reviews and ratings. The automatic answer generation unit can also generate an optimal answer to the caller's question based on feedback from other users. For example, it explains how to use a product by referring to past user feedback. The automatic answer generation unit can also build a system that retrieves ratings and feedback from a database and reflects them in the answer. For example, it can automatically retrieve user reviews and reflect them in the answer. This makes it possible to provide more reliable information to the caller.

[0040] The forwarding unit can automatically select and forward the most appropriate person based on the content of the caller's question. The forwarding unit, for example, analyzes the content of the caller's question and automatically selects the most appropriate person. For example, for a technical question, it may forward the call to a technical support person. The forwarding unit can also select the relevant department or person based on the content of the caller's question. For example, for a question about returning a product, it may forward the call to the customer support department. The forwarding unit can also build a system that analyzes the content of the question and selects the most appropriate person. For example, it may automatically select and forward a person based on the type and content of the question. This enables the caller to respond quickly and appropriately.

[0041] The forwarding unit can refer to the caller's past inquiry history and select an appropriate department in charge. The forwarding unit, for example, refers to the caller's past inquiry history and selects an appropriate department in charge. For example, if a caller who has received technical support in the past asks another technical question, the call is forwarded to the technical support department. The forwarding unit can also select an appropriate department in charge based on the caller's past inquiry history. For example, the call is forwarded to the relevant department based on the content of the past inquiry. The forwarding unit can also build a system that retrieves inquiry history from a database and selects a department in charge. For example, the past inquiry history is automatically retrieved and a department in charge is selected. This enables a more appropriate response to the caller.

[0042] The forwarding unit can refer to the caller's past inquiry history and select an appropriate department in charge. The forwarding unit, for example, refers to the caller's past inquiry history and selects an appropriate department in charge. For example, if a caller who has received technical support in the past asks another technical question, the call is forwarded to the technical support department. The forwarding unit can also select an appropriate department in charge based on the caller's past inquiry history. For example, the call is forwarded to the relevant department based on the content of the past inquiry. The forwarding unit can also build a system that retrieves inquiry history from a database and selects a department in charge. For example, the past inquiry history is automatically retrieved and a department in charge is selected. This enables a more appropriate response to the caller.

[0043] The transfer unit can automatically adjust the schedule of the relevant department or person in charge based on the content of the caller's question and transfer the call. The transfer unit, for example, analyzes the content of the caller's question and automatically adjusts the schedule of the relevant department or person in charge. For example, if technical support is required, the transfer unit adjusts the schedule of a technical support person and transfers the call. The transfer unit can also adjust the person's schedule based on the content of the caller's question. For example, it checks the person's free time and transfers the call at the optimal time. The transfer unit can also use a schedule adjustment system to build a system that automatically adjusts the person's schedule. For example, it checks the person's schedule in real time and transfers the call at the optimal time. This enables a quick and appropriate response to the caller.

[0044] The forwarding unit can select the most suitable representative based on the content of the caller's question, by referring to the evaluations or feedback of related departments and personnel. The forwarding unit, for example, analyzes the content of the caller's question and selects the most suitable representative based on the evaluations of related departments and personnel. For example, if technical support is required, the call is transferred to a highly rated technical support representative. The forwarding unit can also refer to the feedback of personnel based on the content of the caller's question. For example, the most suitable representative is selected based on past feedback. The forwarding unit can also build a system that obtains evaluations and feedback from a database and selects a representative. For example, the system automatically obtains past evaluations and feedback and selects a representative. This enables a more appropriate response to the caller.

[0045] The question analysis unit can analyze the caller's conversation content and tone of voice and suggest the optimal response method by referring to past response history. The question analysis unit, for example, analyzes the caller's conversation content and tone of voice and suggests the optimal response method based on the past response history. For example, it can suggest a response by referring to successful cases when similar questions were received in the past. The question analysis unit can also analyze the caller's conversation content and tone of voice and refer to the past response history. For example, it can suggest the optimal response method based on the past response history. The question analysis unit can also combine data on the conversation content and tone of voice to build a system that refers to past response history. For example, if the conversation content matches a specific pattern and the voice tone is high, it can suggest a response by referring to past successful cases. This makes it possible to respond based on past successful cases.

[0046] The question analysis unit can analyze the caller's conversation content and tone of voice and automatically provide relevant documents or manuals. The question analysis unit can, for example, analyze the caller's conversation content and tone of voice and automatically provide relevant documents. For example, in response to a question about how to use a product, a usage manual can be provided. The question analysis unit can also analyze the caller's conversation content and tone of voice and automatically provide relevant manuals. For example, a troubleshooting guide for the product can be provided. The question analysis unit can also combine data on the conversation content and tone of voice to build a system that provides relevant documents or manuals. For example, if the conversation content matches a specific pattern and the tone of voice is high, relevant documents can be automatically provided. This makes it possible to provide callers with prompt and appropriate information.

[0047] The question analysis unit can analyze the caller's conversation content and tone of voice and suggest a response method that takes into account the ratings or feedback of other users. For example, the question analysis unit can analyze the caller's conversation content and tone of voice and suggest a response method based on the ratings and feedback of other users. For example, the question analysis unit can explain the features and advantages of a product by referring to product reviews and ratings. The question analysis unit can also analyze the caller's conversation content and tone of voice and refer to feedback from other users. For example, the question analysis unit can suggest the optimal response method based on past feedback. The question analysis unit can also combine data on the conversation content and tone of voice to build a system that refers to the ratings and feedback of other users. For example, if the conversation content matches a specific pattern and the voice tone is high, a response method is suggested based on the ratings and feedback of other users. This enables a more reliable response to the caller.

[0048] The database providing unit can provide multiple pieces of information from the database in response to a caller's question and select the most appropriate information. For example, the database providing unit can provide multiple pieces of information from the database in response to a caller's question and select the most appropriate information. For example, in response to a question about how to use a product, the database providing unit can suggest multiple ways of using the product and select the most appropriate one. The database providing unit can also obtain related information from the database and provide multiple pieces of information. For example, it can provide detailed information about the product and how to use it. The database providing unit can also build a system that selects the most appropriate information from the provided information. For example, it can select the most appropriate information based on the accuracy of the information and the user's needs. This makes it possible to provide the most appropriate information to the caller.

[0049] The database providing unit can provide information that references relevant legal information or regulations in response to a caller's question. For example, the database providing unit references relevant legal information in response to a caller's question and provides appropriate information. For example, in response to a question about returning a product, it provides information based on the Consumer Protection Act. The database providing unit can also reference relevant regulations and provide appropriate information. For example, it can provide information based on industry regulations. The database providing unit can also build a system that retrieves legal information and regulations from a database and reflects them in the information. For example, it can automatically retrieve relevant legal provisions and reflect them in the information. This makes it possible to provide legally appropriate information.

[0050] The database providing unit can provide information by referencing related FAQs or community forum information in response to a caller's question. For example, the database providing unit can provide appropriate information by referencing related FAQs in response to a caller's question. For example, in response to a question about how to use a product, it can provide usage information from the FAQs. The database providing unit can also provide information by referencing related community forum information in response to a caller's question. For example, it can explain the features and advantages of a product by referring to user posts. The database providing unit can also build a system that retrieves FAQ and community forum information from a database and reflects it in the information. For example, it can automatically retrieve related FAQs and reflect them in the information. This makes it possible to provide a wider variety of information to callers.

[0051] The database providing unit can provide information in response to the caller's question that takes into account the ratings or feedback of other users. For example, the database providing unit provides information in response to the caller's question based on the ratings and feedback of other users. For example, the database providing unit can explain the features and advantages of a product by referring to product reviews and ratings. The database providing unit can also provide optimal information in response to the caller's question based on feedback from other users. For example, it can explain how to use a product by referring to past user feedback. The database providing unit can also build a system that retrieves ratings and feedback from a database and reflects them in the information. For example, it can automatically retrieve user reviews and reflect them in the information. This makes it possible to provide more reliable information to the caller.

[0052] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0053] The telephone-related work efficiency system can also refer to the caller's past inquiry history and generate individually customized answers. For example, it can retrieve the details of the caller's past inquiries from a database and quickly generate an answer if a similar question arises again. If a caller who previously asked a question about an invoice asks the same question again, it can respond quickly by referring to the past answers. It can also generate individually customized answers based on the caller's past inquiry history. This makes it possible to provide a more personalized response to callers.

[0054] The telephone-related work efficiency system can also provide visual support by automatically providing relevant videos or images in response to callers' questions. For example, in response to a question about how to use a product, a video explaining how to use the product can be provided. Detailed images of the product can also be provided. A system can also be built that provides visual support using videos and images. This can help callers understand by providing visual information.

[0055] The telephone-related work efficiency improvement system can also generate answers to callers' questions by referring to the ratings or feedback of other users. For example, it can explain the features and benefits of a product by referring to product reviews and ratings. It can also generate optimal answers to callers' questions based on feedback from other users. It can also build a system that retrieves ratings and feedback from a database and reflects them in the answers. This allows callers to be provided with more reliable information.

[0056] The telephone-related work efficiency system can also refer to the operator's past response history and suggest the optimal response method. For example, the operator's past response history can be retrieved from a database to suggest the optimal response method if a similar case occurs. Current responses can also be suggested based on responses that have been successful in the past. A system can also be built that stores response history in a database and allows it to be referenced later. This can improve the quality of operator responses.

[0057] The telephone-related work efficiency system can also generate answers to callers' questions by referencing relevant legal information or regulations. For example, it can generate an appropriate answer to a caller's question by referencing relevant legal information. It can provide an answer based on consumer protection laws to a question about returning a product. It can also generate an appropriate answer by referencing relevant regulations. It can also provide answers based on industry regulations. It can also build a system that retrieves legal information and regulations from a database and reflects them in answers. This makes it possible to provide legally appropriate answers.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The voice recognition unit recognizes the caller's voice. For example, the voice recognition unit recognizes telephone voice in real time and converts it into text data. The voice recognition unit can also analyze recorded voice and convert it into text data. The voice recognition unit performs highly accurate voice recognition using a voice recognition algorithm. Step 2: The question analysis unit analyzes the speech recognized by the speech recognition unit. For example, the question analysis unit analyzes the intent of the question using natural language processing technology. The question analysis unit can also analyze the content of the speech data to identify the type of question. Furthermore, the question analysis unit evaluates the importance of the question using an analysis algorithm. Step 3: The automatic answer generation unit automatically generates an answer to the question analyzed by the question analysis unit. For example, the automatic answer generation unit generates an appropriate answer using an answer generation algorithm. The automatic answer generation unit can also obtain related information from a database and generate an answer. Furthermore, the automatic answer generation unit generates an answer in natural language using generation AI. Step 4: If the answer generated by the automatic answer generation unit is inappropriate, the forwarding unit forwards it to the appropriate department. For example, the forwarding unit selects an appropriate department based on the forwarding conditions and forwards the answer. The forwarding unit can also quickly forward the answer using a forwarding system. Furthermore, the forwarding unit records the forwarding history so that it can be referenced later. Step 5: The business support department provides the operator with the question intent and proposed solutions analyzed by the question analysis department. For example, the business support department can present proposed solutions to the operator in real time. The business support department can also refer to the operator's past response history to suggest the optimal response method. Furthermore, the business support department provides tools to reduce the operator's workload.

[0060] (Example 2) The telephone-related work efficiency improvement system according to an embodiment of the present invention is a system that automatically recognizes the caller's voice, analyzes the intent of the question using a generation AI, automatically generates an answer, and transfers the answer to the relevant department as necessary to support the operator. As a result, the telephone-related work efficiency system can respond to the caller's questions quickly and accurately, reduce the operator's burden, and improve the caller's satisfaction.

[0061] A telephone-related business efficiency improvement system according to an embodiment includes a voice recognition unit, a question analysis unit, an automatic answer generation unit, a transfer unit, and a business support unit. The voice recognition unit recognizes the voice of a caller. For example, the voice recognition unit recognizes telephone voice in real time and converts it into text data. The voice recognition unit can also analyze recorded voice and convert it into text data. The voice recognition unit performs highly accurate voice recognition using a voice recognition algorithm. The question analysis unit analyzes the voice recognized by the voice recognition unit. For example, the question analysis unit analyzes the intent of the question using natural language processing technology. The question analysis unit can also analyze the content of the voice data and identify the type of question. The question analysis unit can also evaluate the importance of the question using an analysis algorithm. The automatic answer generation unit automatically generates an answer to the question analyzed by the question analysis unit. For example, the automatic answer generation unit generates an appropriate answer using an answer generation algorithm. The automatic answer generation unit can also obtain related information from a database and generate an answer. The automatic answer generation unit generates an answer in natural language using a generation AI. The forwarding unit forwards the call to a responsible department if the answer generated by the automatic answer generation unit is inappropriate. For example, the forwarding unit selects an appropriate responsible department based on the forwarding conditions and forwards the call. The forwarding unit can also quickly forward the call using a forwarding system. The forwarding unit also records the forwarding history so that it can be referenced later. The business support unit provides the operator with the question intent and proposed solutions analyzed by the question analysis unit. For example, the business support unit presents proposed solutions to the operator in real time. The business support unit can also refer to the operator's past response history to suggest an optimal response method. The business support unit also provides tools to reduce the operator's burden. As a result, the telephone-related business efficiency system according to the embodiment can quickly and accurately respond to callers' questions, reduce the operator's burden, and improve the caller's satisfaction. For example, the caller can receive a quick answer, thereby shortening waiting time. Furthermore, the reduced burden on the operator can provide higher quality service.Furthermore, the system can analyze the caller's emotional state and suggest appropriate responses, further improving the caller's satisfaction.

[0062] The voice recognition unit can refer to the caller's past inquiry history and generate an answer that is individually customized. For example, the voice recognition unit retrieves the caller's past inquiries from a database and quickly generates an answer if a similar question arises again. For example, if a caller who previously asked a question about an invoice asks the same question again, the voice recognition unit can respond quickly by referring to the past answers. The voice recognition unit can also generate an answer that is individually customized based on the caller's past inquiry history. For example, if the caller asks about a specific product, detailed information about that product can be provided. This makes it possible to provide a more personalized response to the caller.

[0063] The question analysis unit can analyze the caller's tone of voice and speaking rate and generate a response that corresponds to the caller's level of urgency and emotional state. The question analysis unit, for example, analyzes the caller's tone of voice and responds quickly if the caller's level of urgency is high. For example, if the caller speaks in a panicked voice, the question analysis unit notifies the operator that an emergency response is required. The question analysis unit can also analyze the caller's speaking rate and evaluate the caller's emotional state. For example, if the caller speaks quickly, the question analysis unit determines that the caller's level of urgency is high and responds quickly. The question analysis unit also combines data on the caller's tone of voice and speaking rate to comprehensively analyze the caller's emotional state. For example, if the caller's voice tone is high and speaking rate is fast, the question analysis unit determines that the caller is nervous and provides a reassuring response. This enables an appropriate response that corresponds to the caller's emotional state.

[0064] The question analysis unit can use the emotion estimation function to estimate the emotion of the caller in real time and generate an answer that elicits positive emotion. The question analysis unit, for example, uses the emotion estimation function to analyze the emotion of the caller in real time and generate an answer that elicits positive emotion. For example, if the caller speaks in an anxious voice, an answer that gives a sense of security is provided. The question analysis unit can also analyze the caller's emotional state and suggest an appropriate response. For example, if the caller is angry, a calm response is suggested. The question analysis unit can also use the emotion estimation function to monitor the caller's emotion in real time and provide appropriate feedback. For example, if the caller is happy, positive feedback is provided. This makes it possible to respond in accordance with the caller's emotions.

[0065] The automatic answer generation unit can automatically provide relevant videos or images in response to the caller's question, thereby providing visual support. For example, the automatic answer generation unit can automatically provide relevant videos in response to the caller's question. For example, in response to a question about how to use a product, it can provide a video explaining how to use the product. The automatic answer generation unit can also automatically provide relevant images in response to the caller's question. For example, it can provide detailed images of the product. The automatic answer generation unit can also build a system that uses videos and images to provide visual support. For example, it can explain how to use a product through a video, making it easier to understand visually. This can help the caller understand by providing visual information.

[0066] The automatic answer generation unit can generate an answer to the caller's question by referring to the ratings or feedback of other users. The automatic answer generation unit generates an answer to the caller's question, for example, based on the ratings and feedback of other users. For example, the automatic answer generation unit explains the features and advantages of a product by referring to product reviews and ratings. The automatic answer generation unit can also generate an optimal answer to the caller's question based on feedback from other users. For example, it explains how to use a product by referring to past user feedback. The automatic answer generation unit can also build a system that retrieves ratings and feedback from a database and reflects them in the answer. For example, it can automatically retrieve user reviews and reflect them in the answer. This makes it possible to provide more reliable information to the caller.

[0067] The automatic response generation unit can use the emotion estimation function to provide music or a voice message that corresponds to the emotion of the caller, thereby relaxing the caller. The automatic response generation unit can, for example, use the emotion estimation function to provide music that corresponds to the emotion of the caller. For example, if the caller is nervous, relaxing music can be played. The automatic response generation unit can also provide a voice message that corresponds to the emotion of the caller. For example, if the caller is anxious, a voice message that gives a sense of security can be provided. The automatic response generation unit can also use the emotion estimation function to build a system that analyzes the emotional state of the caller and provides appropriate music or a voice message. For example, relaxing music or an encouraging message can be provided depending on the emotional state of the caller. This can ease the caller's emotions.

[0068] The business support department can refer to the operator's past response history and propose the optimal response method. For example, the business support department retrieves the operator's past response history from a database and proposes the optimal response method when a similar case occurs. For example, the business support department proposes the current response based on response methods that have been successful in the past. The business support department can also automatically propose the optimal response method based on the operator's past response history. For example, the business support department can propose the current response by referring to past successful cases. The business support department can also build a system that saves the response history in a database and allows it to be referenced later. For example, the business support department can search past response history and propose the optimal response method. This can improve the quality of the operator's response.

[0069] The business support department can analyze the caller's tone of voice or speaking rate and suggest an appropriate response to the operator in real time. For example, the business support department can analyze the caller's tone of voice and suggest an appropriate response to the operator in real time. For example, if the caller is angry, the business support department can suggest a calm response. The business support department can also analyze the caller's speaking rate and suggest an appropriate response to the operator in real time. For example, if the caller is speaking quickly, the business support department can suggest a quick response. The business support department can also combine data on voice tone and speaking rate to build a system that suggests the optimal response to the operator in real time. For example, if the caller's voice tone is high and the speaking rate is fast, the business support department can suggest an emergency response. This allows the operator to quickly respond according to the caller's emotional state.

[0070] The business support department can use the emotion estimation function to estimate the caller's emotions in real time and suggest to the operator a response method that suits the emotion. For example, the business support department can use the emotion estimation function to analyze the caller's emotions in real time and suggest to the operator a response that suits the emotion. For example, if the caller is anxious, the business support department can suggest a response that gives the caller a sense of security. The business support department can also analyze the caller's emotional state and suggest an appropriate response. For example, if the caller is angry, the business support department can suggest a calm response. The business support department can also use the emotion estimation function to monitor the caller's emotions in real time and provide appropriate feedback. For example, if the caller is happy, the business support department can provide positive feedback. This allows the operator to respond according to the caller's emotions.

[0071] The business support department can automatically record the responses of operators and use them later for training or evaluation. For example, the business support department can automatically record the responses of operators and use them later for training. For example, good response examples can be used as training materials. The business support department can also automatically record the responses of operators and use them later for evaluation. For example, past response history can be referenced to evaluate operator performance. The business support department can also build a system that stores response history in a database and makes it possible to reference it later. For example, past response history can be searched and used for training or evaluation. This can improve operator skills and increase the accuracy of evaluation.

[0072] The business support department can automatically provide relevant documents or manuals in response to caller questions, thereby reducing the burden on operators. For example, the business support department can automatically provide relevant documents in response to caller questions. For example, in response to a question about how to use a product, it can provide a usage manual. The business support department can also automatically provide relevant manuals in response to caller questions. For example, it can provide a troubleshooting guide for the product. The business support department can also build a system that retrieves documents and manuals from a database and provides them to operators. For example, it can automatically search for and provide relevant documents in response to the caller's question. This can improve the work efficiency of operators.

[0073] The business support department can use the emotion estimation function to monitor the emotional state of the operator and make suggestions to reduce stress. For example, the business support department uses the emotion estimation function to monitor the emotional state of the operator in real time. For example, if the operator is feeling stressed, the business support department can suggest taking a break. The business support department can also analyze the emotional state of the operator and make suggestions to reduce stress. For example, the business support department can suggest relaxation techniques. The business support department can also use the emotion estimation function to build a system that monitors the emotional state of the operator and provides appropriate feedback. For example, if the operator is tired, the business support department can make suggestions to refresh themselves. This can reduce the operator's stress and improve work efficiency.

[0074] The automatic answer generation unit can generate multiple answer candidates for a caller's question and select the most appropriate answer. For example, the automatic answer generation unit generates multiple answer candidates for a caller's question and selects the most appropriate answer. For example, for a question about how to use a product, the automatic answer generation unit can suggest multiple ways of using the product and select the most appropriate one. The automatic answer generation unit can also generate multiple answer candidates using an answer generation algorithm. For example, it can obtain related information from a database and generate multiple answers. The automatic answer generation unit can also build a system that selects the most appropriate answer from the generated answer candidates. For example, it can select the optimal answer based on the accuracy of the answer and the user's needs. This makes it possible to provide the caller with the optimal answer.

[0075] The automatic answer generation unit can generate an answer to a caller's question by referencing relevant legal information or regulations. For example, the automatic answer generation unit generates an appropriate answer by referencing relevant legal information to a caller's question. For example, in response to a question about returning a product, the automatic answer generation unit provides an answer based on consumer protection laws. The automatic answer generation unit can also generate an appropriate answer by referencing relevant regulations. For example, it provides an answer based on industry regulations. The automatic answer generation unit can also build a system that retrieves legal information and regulations from a database and reflects them in the answer. For example, it can automatically retrieve relevant legal provisions and reflect them in the answer. This makes it possible to provide a legally appropriate answer.

[0076] The automatic reply generation unit can use the emotion estimation function to generate a reply in a tone or language that corresponds to the emotion of the caller. The automatic reply generation unit, for example, uses the emotion estimation function to generate a reply in a tone that corresponds to the emotion of the caller. For example, if the caller is anxious, the automatic reply generation unit provides a reply in a tone that gives a sense of security. The automatic reply generation unit can also generate a reply in language that corresponds to the emotion of the caller. For example, if the caller is angry, the automatic reply generation unit provides a reply in calm language. The automatic reply generation unit can also use the emotion estimation function to build a system that analyzes the emotional state of the caller and generates a reply in an appropriate tone or language. For example, the automatic reply generation unit selects formal or casual language depending on the emotional state of the caller. This makes it possible to respond appropriately to the caller's emotions.

[0077] The automatic answer generation unit can generate answers to callers' questions by referencing related FAQs or community forum information. For example, the automatic answer generation unit generates an appropriate answer to a caller's question by referencing related FAQs. For example, in response to a question about how to use a product, it provides usage information from the FAQs. The automatic answer generation unit can also generate answers to callers' questions by referencing related community forum information. For example, it can explain the features and advantages of a product by referring to user posts. The automatic answer generation unit can also build a system that retrieves information from FAQs and community forums from a database and reflects it in the answer. For example, it can automatically retrieve related FAQs and reflect them in the answer. This makes it possible to provide a wider variety of information to callers.

[0078] The automatic answer generation unit can generate an answer to the caller's question by referring to the ratings or feedback of other users. The automatic answer generation unit generates an answer to the caller's question, for example, based on the ratings and feedback of other users. For example, the automatic answer generation unit explains the features and advantages of a product by referring to product reviews and ratings. The automatic answer generation unit can also generate an optimal answer to the caller's question based on feedback from other users. For example, it explains how to use a product by referring to past user feedback. The automatic answer generation unit can also build a system that retrieves ratings and feedback from a database and reflects them in the answer. For example, it can automatically retrieve user reviews and reflect them in the answer. This makes it possible to provide more reliable information to the caller.

[0079] The automatic response generation unit can use the emotion estimation function to provide music or a voice message that corresponds to the emotion of the caller, thereby relaxing the caller. The automatic response generation unit can, for example, use the emotion estimation function to provide music that corresponds to the emotion of the caller. For example, if the caller is nervous, relaxing music can be played. The automatic response generation unit can also provide a voice message that corresponds to the emotion of the caller. For example, if the caller is anxious, a voice message that gives a sense of security can be provided. The automatic response generation unit can also use the emotion estimation function to build a system that analyzes the emotional state of the caller and provides appropriate music or a voice message. For example, relaxing music or an encouraging message can be provided depending on the emotional state of the caller. This can ease the caller's emotions.

[0080] The forwarding unit can automatically select and forward the most appropriate person based on the content of the caller's question. The forwarding unit, for example, analyzes the content of the caller's question and automatically selects the most appropriate person. For example, for a technical question, it may forward the call to a technical support person. The forwarding unit can also select the relevant department or person based on the content of the caller's question. For example, for a question about returning a product, it may forward the call to the customer support department. The forwarding unit can also build a system that analyzes the content of the question and selects the most appropriate person. For example, it may automatically select and forward a person based on the type and content of the question. This enables the caller to respond quickly and appropriately.

[0081] The forwarding unit can refer to the caller's past inquiry history and select an appropriate department in charge. The forwarding unit, for example, refers to the caller's past inquiry history and selects an appropriate department in charge. For example, if a caller who has received technical support in the past asks another technical question, the call is forwarded to the technical support department. The forwarding unit can also select an appropriate department in charge based on the caller's past inquiry history. For example, the call is forwarded to the relevant department based on the content of the past inquiry. The forwarding unit can also build a system that retrieves inquiry history from a database and selects a department in charge. For example, the past inquiry history is automatically retrieved and a department in charge is selected. This enables a more appropriate response to the caller.

[0082] The forwarding unit can refer to the caller's past inquiry history and select an appropriate department in charge. The forwarding unit, for example, refers to the caller's past inquiry history and selects an appropriate department in charge. For example, if a caller who has received technical support in the past asks another technical question, the call is forwarded to the technical support department. The forwarding unit can also select an appropriate department in charge based on the caller's past inquiry history. For example, the call is forwarded to the relevant department based on the content of the past inquiry. The forwarding unit can also build a system that retrieves inquiry history from a database and selects a department in charge. For example, the past inquiry history is automatically retrieved and a department in charge is selected. This enables a more appropriate response to the caller.

[0083] The transfer unit can use the emotion estimation function to select and transfer the call to a department in charge according to the caller's emotional state. The transfer unit, for example, uses the emotion estimation function to analyze the caller's emotional state and select an appropriate department in charge. For example, if the caller is very anxious, the call is transferred to the customer support department. The transfer unit can also select a department in charge based on the caller's emotional state. For example, if the caller is angry, the call is transferred to the complaints department. The transfer unit can also use the emotion estimation function to build a system that analyzes the caller's emotional state in real time and selects a department in charge. For example, the optimal department in charge is selected and transferred according to the caller's emotional state. This makes it possible to respond appropriately according to the caller's emotional state.

[0084] The transfer unit can automatically adjust the schedule of the relevant department or person in charge based on the content of the caller's question and transfer the call. The transfer unit, for example, analyzes the content of the caller's question and automatically adjusts the schedule of the relevant department or person in charge. For example, if technical support is required, the transfer unit adjusts the schedule of a technical support person and transfers the call. The transfer unit can also adjust the person's schedule based on the content of the caller's question. For example, it checks the person's free time and transfers the call at the optimal time. The transfer unit can also use a schedule adjustment system to build a system that automatically adjusts the person's schedule. For example, it checks the person's schedule in real time and transfers the call at the optimal time. This enables a quick and appropriate response to the caller.

[0085] The forwarding unit can select the most suitable representative based on the content of the caller's question, by referring to the evaluations or feedback of related departments and personnel. The forwarding unit, for example, analyzes the content of the caller's question and selects the most suitable representative based on the evaluations of related departments and personnel. For example, if technical support is required, the call is transferred to a highly rated technical support representative. The forwarding unit can also refer to the feedback of personnel based on the content of the caller's question. For example, the most suitable representative is selected based on past feedback. The forwarding unit can also build a system that obtains evaluations and feedback from a database and selects a representative. For example, the system automatically obtains past evaluations and feedback and selects a representative. This enables a more appropriate response to the caller.

[0086] The forwarding unit can use the emotion estimation function to provide music or a voice message that corresponds to the caller's emotional state, thereby relaxing the caller. The forwarding unit can, for example, use the emotion estimation function to provide music that corresponds to the caller's emotions. For example, if the caller is nervous, relaxing music can be played. The forwarding unit can also provide a voice message that corresponds to the caller's emotions. For example, if the caller is anxious, a voice message that gives a sense of security can be provided. The forwarding unit can also use the emotion estimation function to build a system that analyzes the caller's emotional state and provides appropriate music or a voice message. For example, relaxing music or an encouraging message can be provided depending on the caller's emotional state. This can ease the caller's emotions.

[0087] The question analysis unit can analyze the caller's conversation content and tone of voice and suggest a response method based on the level of urgency or emotional state. The question analysis unit, for example, analyzes the caller's conversation content and tone of voice and suggests a quick response if the level of urgency is high. For example, if the caller speaks in a panicked voice, it notifies the operator that an emergency response is required. The question analysis unit can also analyze the caller's emotional state and suggest an appropriate response. For example, if the caller is angry, it suggests a calm response. The question analysis unit can also combine data on the conversation content and tone of voice to build a system that comprehensively analyzes the caller's emotional state. For example, if the conversation content indicates urgency and the tone of voice is high, it suggests an emergency response. This makes it possible to respond appropriately based on the caller's emotional state.

[0088] The question analysis unit can analyze the caller's conversation content and tone of voice and suggest the optimal response method by referring to past response history. The question analysis unit, for example, analyzes the caller's conversation content and tone of voice and suggests the optimal response method based on the past response history. For example, it can suggest a response by referring to successful cases when similar questions were received in the past. The question analysis unit can also analyze the caller's conversation content and tone of voice and refer to the past response history. For example, it can suggest the optimal response method based on the past response history. The question analysis unit can also combine data on the conversation content and tone of voice to build a system that refers to past response history. For example, if the conversation content matches a specific pattern and the voice tone is high, it can suggest a response by referring to past successful cases. This makes it possible to respond based on past successful cases.

[0089] The question analysis unit can use the emotion estimation function to estimate the emotion of the caller in real time and suggest a response method according to the emotion. The question analysis unit, for example, uses the emotion estimation function to analyze the emotion of the caller in real time and suggest a response method according to the emotion. For example, if the caller is anxious, it suggests a response that gives the caller a sense of security. The question analysis unit can also analyze the caller's emotional state and suggest an appropriate response. For example, if the caller is angry, it suggests a calm response. The question analysis unit can also use the emotion estimation function to build a system that monitors the caller's emotions in real time and provides appropriate feedback. For example, if the caller is happy, it provides positive feedback. This makes it possible to respond appropriately according to the caller's emotions.

[0090] The question analysis unit can analyze the caller's conversation content and tone of voice and automatically provide relevant documents or manuals. The question analysis unit can, for example, analyze the caller's conversation content and tone of voice and automatically provide relevant documents. For example, in response to a question about how to use a product, a usage manual can be provided. The question analysis unit can also analyze the caller's conversation content and tone of voice and automatically provide relevant manuals. For example, a troubleshooting guide for the product can be provided. The question analysis unit can also combine data on the conversation content and tone of voice to build a system that provides relevant documents or manuals. For example, if the conversation content matches a specific pattern and the tone of voice is high, relevant documents can be automatically provided. This makes it possible to provide callers with prompt and appropriate information.

[0091] The question analysis unit can analyze the caller's conversation content and tone of voice and suggest a response method that takes into account the ratings or feedback of other users. For example, the question analysis unit can analyze the caller's conversation content and tone of voice and suggest a response method based on the ratings and feedback of other users. For example, the question analysis unit can explain the features and advantages of a product by referring to product reviews and ratings. The question analysis unit can also analyze the caller's conversation content and tone of voice and refer to feedback from other users. For example, the question analysis unit can suggest the optimal response method based on past feedback. The question analysis unit can also combine data on the conversation content and tone of voice to build a system that refers to the ratings and feedback of other users. For example, if the conversation content matches a specific pattern and the voice tone is high, a response method is suggested based on the ratings and feedback of other users. This enables a more reliable response to the caller.

[0092] The question analysis unit can use the emotion estimation function to provide music or a voice message that corresponds to the caller's emotional state, thereby relaxing the caller. The question analysis unit can, for example, use the emotion estimation function to provide music that corresponds to the caller's emotions. For example, if the caller is nervous, relaxing music can be played. The question analysis unit can also provide a voice message that corresponds to the caller's emotions. For example, if the caller is anxious, a voice message that gives a sense of security can be provided. The question analysis unit can also use the emotion estimation function to build a system that analyzes the caller's emotional state and provides appropriate music or a voice message. For example, relaxing music or an encouraging message can be provided depending on the caller's emotional state. This can ease the caller's emotions.

[0093] The database providing unit can provide multiple pieces of information from the database in response to a caller's question and select the most appropriate information. For example, the database providing unit can provide multiple pieces of information from the database in response to a caller's question and select the most appropriate information. For example, in response to a question about how to use a product, the database providing unit can suggest multiple ways of using the product and select the most appropriate one. The database providing unit can also obtain related information from the database and provide multiple pieces of information. For example, it can provide detailed information about the product and how to use it. The database providing unit can also build a system that selects the most appropriate information from the provided information. For example, it can select the most appropriate information based on the accuracy of the information and the user's needs. This makes it possible to provide the most appropriate information to the caller.

[0094] The database providing unit can provide information that references relevant legal information or regulations in response to a caller's question. For example, the database providing unit references relevant legal information in response to a caller's question and provides appropriate information. For example, in response to a question about returning a product, it provides information based on the Consumer Protection Act. The database providing unit can also reference relevant regulations and provide appropriate information. For example, it can provide information based on industry regulations. The database providing unit can also build a system that retrieves legal information and regulations from a database and reflects them in the information. For example, it can automatically retrieve relevant legal provisions and reflect them in the information. This makes it possible to provide legally appropriate information.

[0095] The database providing unit can use the emotion estimation function to provide information in a tone or language that corresponds to the emotion of the caller. The database providing unit, for example, uses the emotion estimation function to provide information in a tone that corresponds to the emotion of the caller. For example, if the caller is anxious, the database providing unit provides information in a tone that gives a sense of security. The database providing unit can also provide information in language that corresponds to the emotion of the caller. For example, if the caller is angry, the database providing unit provides information in calm language. The database providing unit can also use the emotion estimation function to build a system that analyzes the emotional state of the caller and provides information in an appropriate tone or language. For example, formal language or casual language is selected depending on the emotional state of the caller. This makes it possible to provide appropriate information that corresponds to the emotion of the caller.

[0096] The database providing unit can provide information by referencing related FAQs or community forum information in response to a caller's question. For example, the database providing unit can provide appropriate information by referencing related FAQs in response to a caller's question. For example, in response to a question about how to use a product, it can provide usage information from the FAQs. The database providing unit can also provide information by referencing related community forum information in response to a caller's question. For example, it can explain the features and advantages of a product by referring to user posts. The database providing unit can also build a system that retrieves FAQ and community forum information from a database and reflects it in the information. For example, it can automatically retrieve related FAQs and reflect them in the information. This makes it possible to provide a wider variety of information to callers.

[0097] The database providing unit can provide information in response to the caller's question that takes into account the ratings or feedback of other users. For example, the database providing unit provides information in response to the caller's question based on the ratings and feedback of other users. For example, the database providing unit can explain the features and advantages of a product by referring to product reviews and ratings. The database providing unit can also provide optimal information in response to the caller's question based on feedback from other users. For example, it can explain how to use a product by referring to past user feedback. The database providing unit can also build a system that retrieves ratings and feedback from a database and reflects them in the information. For example, it can automatically retrieve user reviews and reflect them in the information. This makes it possible to provide more reliable information to the caller.

[0098] The database providing unit can use the emotion estimation function to provide music or a voice message that corresponds to the caller's emotional state, thereby relaxing the caller. For example, the database providing unit can use the emotion estimation function to provide music that corresponds to the caller's emotions. For example, if the caller is nervous, relaxing music can be played. The database providing unit can also provide a voice message that corresponds to the caller's emotions. For example, if the caller is anxious, a voice message that gives a sense of security can be provided. The database providing unit can also use the emotion estimation function to build a system that analyzes the caller's emotional state and provides appropriate music or a voice message. For example, relaxing music or an encouraging message can be provided depending on the caller's emotional state. This can ease the caller's emotions.

[0099] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0100] The telephone-related work efficiency system can also analyze the caller's tone of voice and speaking speed, and respond accordingly based on the caller's level of urgency and emotional state. For example, if the caller sounds anxious, the system will notify the operator that an emergency response is required. If the caller speaks quickly, the system will determine that the call is urgent and respond quickly. Furthermore, by combining data on tone of voice and speaking speed, the system can comprehensively analyze the caller's emotional state and suggest an appropriate response. This makes it possible to respond appropriately based on the caller's emotional state.

[0101] The telephone-related work efficiency system can also refer to the caller's past inquiry history and generate individually customized answers. For example, it can retrieve the details of the caller's past inquiries from a database and quickly generate an answer if a similar question arises again. If a caller who previously asked a question about an invoice asks the same question again, it can respond quickly by referring to the past answers. It can also generate individually customized answers based on the caller's past inquiry history. This makes it possible to provide a more personalized response to callers.

[0102] The telephone-related work efficiency system can also provide visual support by automatically providing relevant videos or images in response to callers' questions. For example, in response to a question about how to use a product, a video explaining how to use the product can be provided. Detailed images of the product can also be provided. A system can also be built that provides visual support using videos and images. This can help callers understand by providing visual information.

[0103] The telephone-related work efficiency improvement system can also generate answers to callers' questions by referring to the ratings or feedback of other users. For example, it can explain the features and benefits of a product by referring to product reviews and ratings. It can also generate optimal answers to callers' questions based on feedback from other users. It can also build a system that retrieves ratings and feedback from a database and reflects them in the answers. This allows callers to be provided with more reliable information.

[0104] The telephone-related work efficiency improvement system can also use an emotion estimation function to provide music or a voice message that corresponds to the caller's emotions, helping them relax. For example, if the caller is nervous, relaxing music can be played. If the caller is anxious, a reassuring voice message can be provided. Using the emotion estimation function, a system can be constructed that analyzes the caller's emotional state and provides appropriate music or a voice message. This can ease the caller's emotions.

[0105] The telephone-related work efficiency system can also refer to the operator's past response history and suggest the optimal response method. For example, the operator's past response history can be retrieved from a database to suggest the optimal response method if a similar case occurs. Current responses can also be suggested based on responses that have been successful in the past. A system can also be built that stores response history in a database and allows it to be referenced later. This can improve the quality of operator responses.

[0106] The telephone-related work efficiency system can also analyze the caller's tone of voice or speaking speed and suggest appropriate ways of responding to the operator in real time. For example, the caller's tone of voice can be analyzed and appropriate ways of responding can be suggested to the operator in real time. If the caller is angry, a calm response can be suggested. The caller's speaking speed can also be analyzed and appropriate ways of responding can be suggested to the operator in real time. It is also possible to build a system that combines data on tone of voice and speaking speed to suggest optimal ways of responding to the operator in real time. This allows the operator to quickly respond according to the caller's emotional state.

[0107] The telephone-related work efficiency improvement system can further use an emotion estimation function to monitor the emotional state of the operator and make suggestions to reduce stress. For example, the emotion estimation function can be used to monitor the emotional state of the operator in real time. If the operator is feeling stressed, it can suggest taking a break. It can also analyze the operator's emotional state and make suggestions to reduce stress. It can also suggest relaxation techniques. A system can also be built using the emotion estimation function to monitor the emotional state of the operator and provide appropriate feedback. This can reduce operator stress and improve work efficiency.

[0108] The telephone-related work efficiency system can also generate answers to callers' questions by referencing relevant legal information or regulations. For example, it can generate an appropriate answer to a caller's question by referencing relevant legal information. It can provide an answer based on consumer protection laws to a question about returning a product. It can also generate an appropriate answer by referencing relevant regulations. It can also provide answers based on industry regulations. It can also build a system that retrieves legal information and regulations from a database and reflects them in answers. This makes it possible to provide legally appropriate answers.

[0109] The telephone-related work efficiency system can further use an emotion estimation function to generate a response in a tone or wording that corresponds to the caller's emotions. For example, the emotion estimation function can be used to generate a response in a tone that corresponds to the caller's emotions. If the caller is anxious, a response can be provided in a tone that gives a sense of security. It can also generate a response in wording that corresponds to the caller's emotions. If the caller is angry, a response can be provided in calm wording. The emotion estimation function can also be used to build a system that analyzes the caller's emotional state and generates a response in an appropriate tone or wording. This makes it possible to respond appropriately to the caller's emotions.

[0110] The processing flow of the second embodiment will be briefly explained below.

[0111] Step 1: The voice recognition unit recognizes the caller's voice. For example, the voice recognition unit recognizes telephone voice in real time and converts it into text data. The voice recognition unit can also analyze recorded voice and convert it into text data. The voice recognition unit performs highly accurate voice recognition using a voice recognition algorithm. Step 2: The question analysis unit analyzes the speech recognized by the speech recognition unit. For example, the question analysis unit analyzes the intent of the question using natural language processing technology. The question analysis unit can also analyze the content of the speech data to identify the type of question. Furthermore, the question analysis unit evaluates the importance of the question using an analysis algorithm. Step 3: The automatic answer generation unit automatically generates an answer to the question analyzed by the question analysis unit. For example, the automatic answer generation unit generates an appropriate answer using an answer generation algorithm. The automatic answer generation unit can also obtain related information from a database and generate an answer. Furthermore, the automatic answer generation unit generates an answer in natural language using generation AI. Step 4: If the answer generated by the automatic answer generation unit is inappropriate, the forwarding unit forwards it to the appropriate department. For example, the forwarding unit selects an appropriate department based on the forwarding conditions and forwards the answer. The forwarding unit can also quickly forward the answer using a forwarding system. Furthermore, the forwarding unit records the forwarding history so that it can be referenced later. Step 5: The business support department provides the operator with the question intent and proposed solutions analyzed by the question analysis department. For example, the business support department can present proposed solutions to the operator in real time. The business support department can also refer to the operator's past response history to suggest the optimal response method. Furthermore, the business support department provides tools to reduce the operator's workload.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0116] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[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 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.

[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 (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).

[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] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0146] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0147] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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."

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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]

[0179] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a voice recognition unit that recognizes the voice of the caller; a question analysis unit that analyzes the speech recognized by the speech recognition unit; an automatic answer generation unit that automatically generates an answer to the question analyzed by the question analysis unit; a transfer unit that transfers the answer generated by the automatic answer generation unit to a responsible department if the answer is inappropriate; a business support unit that provides an operator with the question intent or a solution that has been analyzed by the question analysis unit; A system characterized by:

2. The question analysis unit Analyzes the caller's tone of voice and speaking speed to generate a response that matches the level of urgency and emotional state 2. The system of claim 1.

3. The automatic answer generation unit Automatically provide relevant video or images to provide visual support for callers' questions 2. The system of claim 1.

4. The business support department Refer to the operator's past response history and suggest the best response method 2. The system of claim 1.

5. The transfer unit Automatically selects and transfers the call to the most appropriate person based on the caller's question 2. The system of claim 1.

6. The automatic answer generation unit Use emotion estimation to generate responses with a tone or wording that matches the caller's emotions 2. The system of claim 1.

7. The transfer unit Using emotion estimation functionality, the system selects and transfers the call to the appropriate department based on the caller's emotional state.

2. The system of claim 1.

8. The database provider: Uses emotion estimation to provide information in a tone or language that matches the caller's emotions 2. The system of claim 1.

Images