System

Abstract

An object of a system according to an embodiment is to interactively generate and evaluate responses based on utterances of subjects.SOLUTION: A system according to an embodiment includes a remark analysis unit, a response generation unit, and a response evaluation unit. The speech analysis unit analyzes the speech of the subject in real time. The response generation unit generates an appropriate response on the basis of the speech of the subject analyzed by the speech analysis unit. The response evaluation unit analyzes and evaluates the response content of the subject.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to create a large number of response patterns in VR simulations for the service industry, making it difficult to achieve interactive responses.

[0005] The system according to the embodiment aims to interactively generate and evaluate responses based on the utterances of subjects. [Means for solving the problem]

[0006] The system according to the embodiment includes a utterance analysis unit, a response generation unit, and a response evaluation unit. The utterance analysis unit analyzes the subject's utterances in real time. The response generation unit generates an appropriate response based on the subject's utterances analyzed by the utterance analysis unit. The response evaluation unit analyzes and evaluates the content of the subject's response. [Effects of the Invention]

[0007] The system according to the embodiment can interactively generate and evaluate responses based on the utterances of the subject. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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 VR simulation system according to the embodiment of the present invention is a system that interactively generates responses based on the utterances of a subject and evaluates the responses of the subject. This allows the VR simulation system to generate appropriate responses based on the utterances of the subject and evaluate the responses of the subject.

[0029] The VR simulation system according to the embodiment includes a utterance analysis unit, a response generation unit, and a response evaluation unit. The utterance analysis unit analyzes the subject's utterances in real time. For example, the utterance analysis unit converts the subject's utterances into text data using speech recognition technology. The utterance analysis unit can also analyze the meaning of the utterances using natural language processing technology. The utterance analysis unit can also classify the content of the subject's utterances and provide information for generating an appropriate response. For example, speech recognition technology converts the subject's utterances into text data with high accuracy. Natural language processing technology analyzes the context and intention of the utterances and provides information for generating an appropriate response. The utterance content classification categorizes the subject's utterances and provides appropriate information to the response generation unit. The response generation unit generates an appropriate response based on the subject's utterances analyzed by the utterance analysis unit. For example, the response generation unit generates a response using a generation AI (e.g., a text generation AI or a multimodal generation AI). The response generation unit can also select an appropriate response depending on the content of the subject's utterance. The response generation unit can also generate responses to the subject's utterances in real time. For example, the generation AI generates an appropriate response based on the subject's utterance. Response selection selects the optimal response depending on the content of the subject's utterance. Real-time response generation is a technology for instantly responding to the subject's utterance. The response evaluation unit analyzes and evaluates the content of the subject's response. For example, the response evaluation unit makes an appropriate evaluation based on the content of the subject's response. The response evaluation unit can also score the content of the subject's response and provide the evaluation result. The response evaluation unit can also provide feedback on areas for improvement based on the content of the subject's response. For example, the response evaluation unit analyzes the content of the subject's response and makes an appropriate evaluation. Scoring quantifies the content of the subject's response and provides the evaluation result. Feedback on areas for improvement points out areas for improvement based on the content of the subject's response. As a result, the VR simulation system according to the embodiment can generate an appropriate response based on the subject's utterance and evaluate the subject's response. For example, the system evaluates the content of the subject's response and provides feedback. The system also scores the subject's responses and provides the evaluation results.Furthermore, the system points out areas for improvement based on the subject's response.

[0030] The response generation unit can learn the subject's past response history and generate a response optimized for the subject. For example, the response generation unit uses a generation AI to store the subject's past response history in a database and learn the subject's characteristics and tendencies based on that data. For example, it analyzes what responses have been effective in the past and generates the optimal response for similar situations. The response generation unit also analyzes the subject's past response history and extracts specific patterns and tendencies. For example, it learns how the subject responded to a specific complaint and generates the optimal response for a similar complaint. The response generation unit also builds a system in which the generation AI generates responses optimized for individual subjects based on the subject's past response history. For example, it learns the subject's response style and language and generates a response that matches that. This makes it possible to learn the subject's past response history and generate optimized responses.

[0031] The response generation unit can automatically generate responses in different languages, enabling multilingual customer service training. For example, the response generation unit can build a system in which a generation AI is equipped with a multilingual support function and automatically translates what the subject says to generate a response. For example, responses are generated in multiple languages, such as English, French, and Chinese. Furthermore, even if the subject speaks in a different language, the response generation unit generates a response corresponding to that language using the generation AI. For example, if the subject speaks in English, a response is generated in English. Furthermore, the response generation unit uses a multilingual generation AI to develop a system that automatically generates responses in different languages. For example, if the subject speaks in Japanese, a response is generated in Japanese. This allows responses in different languages ​​to be automatically generated, enabling multilingual customer service training.

[0032] The response generation unit can analyze the subject's motion data and generate a response according to the motion. The response generation unit, for example, analyzes the subject's motion data in real time and builds a system that generates a response based on the results. For example, if the subject is waving, a greeting response is generated. The response generation unit also uses motion recognition technology to analyze the subject's motion and generate a response based on that data. For example, if the subject is sitting, a relaxed response is generated. The response generation unit also collects the subject's motion data and develops a system in which a generation AI generates a response according to the motion based on that data. For example, if the subject is standing, a standing conversation response is generated. This makes it possible to analyze the subject's motion data and generate a response according to the motion.

[0033] The response evaluation unit can analyze the content of the subject's response over time and evaluate the consistency of the response. For example, the response evaluation unit constructs a system in which the generation AI analyzes the content of the subject's response over time and evaluates the consistency of the response. For example, it evaluates whether the subject consistently responds calmly. The response evaluation unit also analyzes the content of the subject's response over time and evaluates changes in the response over a specific period of time. For example, if the subject is calm at first but becomes emotional later on, it evaluates that change. The response evaluation unit also develops a system in which the generation AI analyzes the content of the subject's response over time and evaluates the consistency of the response. For example, it evaluates whether the subject consistently uses appropriate language. This makes it possible to analyze the content of the subject's response over time and evaluate the consistency of the response.

[0034] The response evaluation unit can evaluate the subject's response content under different scenarios and evaluate their adaptability for each scenario. For example, the response evaluation unit constructs a system in which a generation AI evaluates the subject's response content under different scenarios and evaluates their adaptability for each scenario. For example, it evaluates scenarios such as handling complaints, sales promotion, and customer support. The response evaluation unit also analyzes the subject's response content under different scenarios and evaluates its adaptability. For example, it evaluates whether the subject consistently responds appropriately in different scenarios. The response evaluation unit also develops a system in which a generation AI evaluates the subject's response content under different scenarios and evaluates their adaptability for each scenario. For example, it evaluates whether the subject can respond flexibly in different scenarios. This makes it possible to evaluate the subject's response content under different scenarios and evaluate their adaptability for each scenario.

[0035] The response evaluation unit can compare the response content of the subject with other subjects and perform a relative evaluation. The response evaluation unit, for example, builds a system that compares the response content of the subject with other subjects and performs a relative evaluation. For example, it compares the response content in the same scenario and evaluates its merits and demerits. The response evaluation unit also compares the response content with that of other subjects and performs a relative evaluation based on that data. For example, it evaluates whether the subject is providing a more appropriate response than other subjects. The response evaluation unit also develops a system that compares the response content of the subject with other subjects and performs a relative evaluation. For example, it evaluates how much better the subject is compared to other subjects. This makes it possible to compare the response content of the subject with other subjects and perform a relative evaluation.

[0036] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0037] The VR simulation system may further include an environmental information acquisition unit that acquires environmental information about the subject. The environmental information acquisition unit may acquire environmental information, such as the temperature, humidity, and noise level of the location where the subject is, in real time and generate a response based on that data. For example, if the temperature is high, the subject may feel uncomfortable, so the response generation unit may generate a calm and collected response. Also, if the noise level is high, the subject may find it difficult to hear, so the response generation unit may generate a clear and slow response. This allows for the generation of more appropriate responses based on the subject's environmental information.

[0038] The VR simulation system may further include a behavioral learning unit that learns the subject's past behavioral data. The behavioral learning unit may, for example, store the subject's past behavior in a database and learn the subject's behavioral patterns based on that data. For example, it may learn how the subject behaved in specific situations in the past and generate the optimal response for similar situations. The behavioral learning unit may also analyze the subject's behavioral patterns and extract specific patterns and trends. For example, it may learn how the subject responded to a specific complaint and generate the optimal response for a similar complaint. This makes it possible to learn the subject's past behavioral data and generate an optimized response.

[0039] The VR simulation system may further include a motion analysis unit that analyzes the motion data of the subject. The motion analysis unit may, for example, analyze the motion data of the subject in real time and generate a response based on the results. For example, if the subject is waving, a greeting response may be generated. Also, if the subject is sitting, a relaxed response may be generated. This allows the motion data of the subject to be analyzed and a response based on the motion to be generated.

[0040] The VR simulation system can further include a response consistency evaluation unit that analyzes the content of the subject's responses over time and evaluates the consistency of the responses. The response consistency evaluation unit can, for example, analyze the content of the subject's responses over time and evaluate changes in the responses over a specific time period. For example, if the subject is calm at first but becomes emotional later, this change can be evaluated. It can also evaluate whether the subject consistently uses appropriate language. This makes it possible to analyze the content of the subject's responses over time and evaluate the consistency of the responses.

[0041] The VR simulation system can further include a response comparison evaluation unit that compares the content of the subject's responses with other subjects and performs a relative evaluation. The response comparison evaluation unit can, for example, compare the content of responses in the same scenario and evaluate their merits and demerits. For example, it can evaluate whether the subject's responses are more appropriate than other subjects. It can also evaluate how much better the subject is compared to other subjects. This allows the content of the subject's responses to be compared with other subjects and a relative evaluation to be performed.

[0042] The VR simulation system can further include a scenario adaptation evaluation unit that evaluates the subject's response in different scenarios and evaluates the adaptability for each scenario. The scenario adaptation evaluation unit can evaluate scenarios such as complaint handling, sales promotion, and customer support. For example, it can evaluate whether the subject consistently responds appropriately in different scenarios. It can also evaluate whether the subject can respond flexibly in different scenarios. This makes it possible to evaluate the subject's response in different scenarios and evaluate the adaptability for each scenario.

[0043] The processing flow of the first embodiment will be briefly explained below.

[0044] Step 1: The utterance analysis unit analyzes the subject's utterances in real time. For example, the utterance analysis unit converts the subject's utterances into text data using speech recognition technology and analyzes the meaning of the utterances using natural language processing technology. It also classifies the content of the utterances and provides information for generating an appropriate response. Step 2: The response generation unit generates an appropriate response based on the subject's utterances analyzed by the utterance analysis unit. For example, the response generation unit uses a generation AI to select an appropriate response based on the subject's utterances and generate the response in real time. Step 3: The response evaluation unit analyzes and evaluates the content of the test subject's response. For example, it makes an appropriate evaluation based on the content of the response, scores the evaluation results, and provides feedback on areas for improvement.

[0045] (Example 2) The VR simulation system according to the embodiment of the present invention is a system that interactively generates responses based on the utterances of a subject and evaluates the responses of the subject. This allows the VR simulation system to generate appropriate responses based on the utterances of the subject and evaluate the responses of the subject.

[0046] The VR simulation system according to the embodiment includes a utterance analysis unit, a response generation unit, and a response evaluation unit. The utterance analysis unit analyzes the subject's utterances in real time. For example, the utterance analysis unit converts the subject's utterances into text data using speech recognition technology. The utterance analysis unit can also analyze the meaning of the utterances using natural language processing technology. The utterance analysis unit can also classify the content of the subject's utterances and provide information for generating an appropriate response. For example, speech recognition technology converts the subject's utterances into text data with high accuracy. Natural language processing technology analyzes the context and intention of the utterances and provides information for generating an appropriate response. The utterance content classification categorizes the subject's utterances and provides appropriate information to the response generation unit. The response generation unit generates an appropriate response based on the subject's utterances analyzed by the utterance analysis unit. For example, the response generation unit generates a response using a generation AI (e.g., a text generation AI or a multimodal generation AI). The response generation unit can also select an appropriate response depending on the content of the subject's utterance. The response generation unit can also generate responses to the subject's utterances in real time. For example, the generation AI generates an appropriate response based on the subject's utterance. Response selection selects the optimal response depending on the content of the subject's utterance. Real-time response generation is a technology for instantly responding to the subject's utterance. The response evaluation unit analyzes and evaluates the content of the subject's response. For example, the response evaluation unit makes an appropriate evaluation based on the content of the subject's response. The response evaluation unit can also score the content of the subject's response and provide the evaluation result. The response evaluation unit can also provide feedback on areas for improvement based on the content of the subject's response. For example, the response evaluation unit analyzes the content of the subject's response and makes an appropriate evaluation. Scoring quantifies the content of the subject's response and provides the evaluation result. Feedback on areas for improvement points out areas for improvement based on the content of the subject's response. As a result, the VR simulation system according to the embodiment can generate an appropriate response based on the subject's utterance and evaluate the subject's response. For example, the system evaluates the content of the subject's response and provides feedback. The system also scores the subject's responses and provides the evaluation results.Furthermore, the system points out areas for improvement based on the subject's response.

[0047] The response generation unit can learn the subject's past response history and generate a response optimized for the subject. For example, the response generation unit uses a generation AI to store the subject's past response history in a database and learn the subject's characteristics and tendencies based on that data. For example, it analyzes what responses have been effective in the past and generates the optimal response for similar situations. The response generation unit also analyzes the subject's past response history and extracts specific patterns and tendencies. For example, it learns how the subject responded to a specific complaint and generates the optimal response for a similar complaint. The response generation unit also builds a system in which the generation AI generates responses optimized for individual subjects based on the subject's past response history. For example, it learns the subject's response style and language and generates a response that matches that. This makes it possible to learn the subject's past response history and generate optimized responses.

[0048] The response generation unit can analyze the subject's facial expressions using facial recognition technology in addition to the content of the subject's remarks, and generate a response that corresponds to their emotions. For example, the response generation unit will build a system that uses a camera to analyze the subject's facial expressions in real time, simultaneously with the content of the subject's remarks. For example, if the subject is angry, it will generate a calm and collected response. The response generation unit will also use facial recognition technology to analyze the subject's emotional state and generate a response based on the results. For example, if the subject is sad, it will generate an empathetic response. The response generation unit will also collect the subject's facial expression data, and develop a system in which a generation AI will use that data to generate a response that corresponds to their emotions. For example, if the subject is smiling, it will generate a friendly response. This makes it possible to analyze the subject's remarks and facial expressions and generate a response that corresponds to their emotions.

[0049] The response generation unit can use the emotion estimation function to estimate the subject's emotion in real time and generate a response corresponding to the emotion. For example, the response generation unit uses the emotion estimation function to analyze the content of the subject's speech and tone of voice, and build a system that estimates the emotion in real time. For example, if the subject is feeling anxious, a reassuring response is generated. The response generation unit also estimates the subject's emotion in real time and generates a response based on the result. For example, if the subject is excited, a calm and collected response is generated. The response generation unit also uses the emotion estimation function to analyze the subject's emotional state, and develops a system that generates a response corresponding to the emotion based on the data. For example, if the subject is happy, a positive response is generated. This makes it possible to estimate the subject's emotion in real time and generate a response corresponding to the emotion.

[0050] The response generation unit can automatically generate responses in different languages, enabling multilingual customer service training. For example, the response generation unit can build a system in which a generation AI is equipped with a multilingual support function and automatically translates what the subject says to generate a response. For example, responses are generated in multiple languages, such as English, French, and Chinese. Furthermore, even if the subject speaks in a different language, the response generation unit generates a response corresponding to that language using the generation AI. For example, if the subject speaks in English, a response is generated in English. Furthermore, the response generation unit uses a multilingual generation AI to develop a system that automatically generates responses in different languages. For example, if the subject speaks in Japanese, a response is generated in Japanese. This allows responses in different languages ​​to be automatically generated, enabling multilingual customer service training.

[0051] The response generation unit can analyze the subject's motion data and generate a response according to the motion. The response generation unit, for example, analyzes the subject's motion data in real time and builds a system that generates a response based on the results. For example, if the subject is waving, a greeting response is generated. The response generation unit also uses motion recognition technology to analyze the subject's motion and generate a response based on that data. For example, if the subject is sitting, a relaxed response is generated. The response generation unit also collects the subject's motion data and develops a system in which a generation AI generates a response according to the motion based on that data. For example, if the subject is standing, a standing conversation response is generated. This makes it possible to analyze the subject's motion data and generate a response according to the motion.

[0052] The response generation unit uses the emotion estimation function to generate a response based on the subject's emotions, thereby eliciting emotional empathy. The response generation unit, for example, uses the emotion estimation function to analyze the subject's emotions in real time and generates a response that elicits emotional empathy based on the results. For example, if the subject is sad, it uses empathetic words. The response generation unit also estimates the subject's emotions and builds a system that generates a response that elicits emotional empathy based on that data. For example, if the subject is angry, it generates a calm and empathetic response. The response generation unit also uses the emotion estimation function to develop a system that generates a response based on the subject's emotions and elicits emotional empathy. For example, if the subject is happy, it generates an empathetic response. In this way, a response based on the subject's emotions can be generated and elicits emotional empathy.

[0053] The response evaluation unit can analyze the content of the subject's response over time and evaluate the consistency of the response. For example, the response evaluation unit constructs a system in which the generation AI analyzes the content of the subject's response over time and evaluates the consistency of the response. For example, it evaluates whether the subject consistently responds calmly. The response evaluation unit also analyzes the content of the subject's response over time and evaluates changes in the response over a specific period of time. For example, if the subject is calm at first but becomes emotional later on, it evaluates that change. The response evaluation unit also develops a system in which the generation AI analyzes the content of the subject's response over time and evaluates the consistency of the response. For example, it evaluates whether the subject consistently uses appropriate language. This makes it possible to analyze the content of the subject's response over time and evaluate the consistency of the response.

[0054] The response evaluation unit can use the emotion estimation function to analyze the emotions of the subject and evaluate the appropriateness of the response based on the emotions. The response evaluation unit, for example, uses the emotion estimation function to analyze the emotions of the subject in real time and builds a system to evaluate the appropriateness of the response based on the results. For example, it evaluates whether the subject responds calmly. The response evaluation unit also analyzes the emotions of the subject and evaluates the appropriateness of the response based on the emotions based on the data. For example, it evaluates whether the subject responds with empathy. The response evaluation unit also uses the emotion estimation function to analyze the emotions of the subject and develops a system to evaluate the appropriateness of the response based on the emotions. For example, it evaluates whether the subject suppresses anger and responds calmly. This makes it possible to analyze the emotions of the subject and evaluate the appropriateness of the response based on the emotions.

[0055] The response evaluation unit can evaluate the subject's response content under different scenarios and evaluate their adaptability for each scenario. For example, the response evaluation unit constructs a system in which a generation AI evaluates the subject's response content under different scenarios and evaluates their adaptability for each scenario. For example, it evaluates scenarios such as handling complaints, sales promotion, and customer support. The response evaluation unit also analyzes the subject's response content under different scenarios and evaluates its adaptability. For example, it evaluates whether the subject consistently responds appropriately in different scenarios. The response evaluation unit also develops a system in which a generation AI evaluates the subject's response content under different scenarios and evaluates their adaptability for each scenario. For example, it evaluates whether the subject can respond flexibly in different scenarios. This makes it possible to evaluate the subject's response content under different scenarios and evaluate their adaptability for each scenario.

[0056] The response evaluation unit can compare the response content of the subject with other subjects and perform a relative evaluation. The response evaluation unit, for example, builds a system that compares the response content of the subject with other subjects and performs a relative evaluation. For example, it compares the response content in the same scenario and evaluates its merits and demerits. The response evaluation unit also compares the response content with that of other subjects and performs a relative evaluation based on that data. For example, it evaluates whether the subject is providing a more appropriate response than other subjects. The response evaluation unit also develops a system that compares the response content of the subject with other subjects and performs a relative evaluation. For example, it evaluates how much better the subject is compared to other subjects. This makes it possible to compare the response content of the subject with other subjects and perform a relative evaluation.

[0057] The response evaluation unit uses the emotion estimation function to evaluate the response based on the subject's emotions and can measure the degree of emotional empathy. The response evaluation unit, for example, uses the emotion estimation function to analyze the subject's emotions in real time and builds a system to evaluate the response based on the results. For example, it evaluates whether the subject responds with empathic emotions. The response evaluation unit also analyzes the subject's emotions and measures the degree of emotional empathy based on the data. For example, it evaluates how empathic the subject's response is. The response evaluation unit also uses the emotion estimation function to develop a system to evaluate the response based on the subject's emotions and measure the degree of emotional empathy. For example, it evaluates how easily the subject responds emotionally. This makes it possible to evaluate the response based on the subject's emotions and measure the degree of emotional empathy.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The VR simulation system may further include a biometric information acquisition unit that acquires biometric information of the subject. The biometric information acquisition unit may acquire biometric information, such as heart rate and electrodermal response, in real time and estimate the stress level of the subject based on that data. For example, if the heart rate rises sharply, the system may determine that the subject is tense, and the response generation unit may generate a response that relaxes the subject. Furthermore, if the electrodermal response increases, the system may determine that the subject is excited, and the response generation unit may generate a calm response. This allows for the generation of more appropriate responses based on the subject's biometric information.

[0060] The VR simulation system may further include an environmental information acquisition unit that acquires environmental information about the subject. The environmental information acquisition unit may acquire environmental information, such as the temperature, humidity, and noise level of the location where the subject is, in real time and generate a response based on that data. For example, if the temperature is high, the subject may feel uncomfortable, so the response generation unit may generate a calm and collected response. Also, if the noise level is high, the subject may find it difficult to hear, so the response generation unit may generate a clear and slow response. This allows for the generation of more appropriate responses based on the subject's environmental information.

[0061] The VR simulation system may further include a behavioral learning unit that learns the subject's past behavioral data. The behavioral learning unit may, for example, store the subject's past behavior in a database and learn the subject's behavioral patterns based on that data. For example, it may learn how the subject behaved in specific situations in the past and generate the optimal response for similar situations. The behavioral learning unit may also analyze the subject's behavioral patterns and extract specific patterns and trends. For example, it may learn how the subject responded to a specific complaint and generate the optimal response for a similar complaint. This makes it possible to learn the subject's past behavioral data and generate an optimized response.

[0062] The VR simulation system can further include an emotion estimation unit that estimates the emotion of the subject. The emotion estimation unit can estimate the emotion in real time by analyzing, for example, the content of the subject's speech, tone of voice, facial expression, etc. For example, if the subject is feeling anxious, the response generation unit can generate a reassuring response. Also, if the subject is excited, the response generation unit can generate a calm and collected response. In this way, the emotion of the subject can be estimated in real time and a response according to the emotion can be generated.

[0063] The VR simulation system may further include a motion analysis unit that analyzes the motion data of the subject. The motion analysis unit may, for example, analyze the motion data of the subject in real time and generate a response based on the results. For example, if the subject is waving, a greeting response may be generated. Also, if the subject is sitting, a relaxed response may be generated. This allows the motion data of the subject to be analyzed and a response based on the motion to be generated.

[0064] The VR simulation system may further include an emotional response generation unit that estimates the subject's emotions and generates a response based on those emotions. The emotional response generation unit may analyze, for example, the content of the subject's speech, tone of voice, facial expressions, etc., estimate the subject's emotions in real time, and generate a response based on the results. For example, if the subject is sad, an empathetic response may be generated. Also, if the subject is angry, a calm and empathetic response may be generated. This allows a response based on the subject's emotions to be generated, eliciting emotional empathy.

[0065] The VR simulation system can further include a response consistency evaluation unit that analyzes the content of the subject's responses over time and evaluates the consistency of the responses. The response consistency evaluation unit can, for example, analyze the content of the subject's responses over time and evaluate changes in the responses over a specific time period. For example, if the subject is calm at first but becomes emotional later, this change can be evaluated. It can also evaluate whether the subject consistently uses appropriate language. This makes it possible to analyze the content of the subject's responses over time and evaluate the consistency of the responses.

[0066] The VR simulation system can further include a response comparison evaluation unit that compares the content of the subject's responses with other subjects and performs a relative evaluation. The response comparison evaluation unit can, for example, compare the content of responses in the same scenario and evaluate their merits and demerits. For example, it can evaluate whether the subject's responses are more appropriate than other subjects. It can also evaluate how much better the subject is compared to other subjects. This allows the content of the subject's responses to be compared with other subjects and a relative evaluation to be performed.

[0067] The VR simulation system may further include an emotion evaluation unit that estimates the subject's emotions and evaluates the response based on those emotions. The emotion evaluation unit may, for example, analyze the subject's emotions in real time and evaluate the response based on the results. For example, it may evaluate whether the subject responded with empathy. It may also evaluate how empathic the subject responded. This allows the response to be evaluated based on the subject's emotions and the degree of emotional empathy to be measured.

[0068] The VR simulation system can further include a scenario adaptation evaluation unit that evaluates the subject's response in different scenarios and evaluates the adaptability for each scenario. The scenario adaptation evaluation unit can evaluate scenarios such as complaint handling, sales promotion, and customer support. For example, it can evaluate whether the subject consistently responds appropriately in different scenarios. It can also evaluate whether the subject can respond flexibly in different scenarios. This makes it possible to evaluate the subject's response in different scenarios and evaluate the adaptability for each scenario.

[0069] The processing flow of the second embodiment will be briefly explained below.

[0070] Step 1: The utterance analysis unit analyzes the subject's utterances in real time. For example, the utterance analysis unit converts the subject's utterances into text data using speech recognition technology and analyzes the meaning of the utterances using natural language processing technology. It also classifies the content of the utterances and provides information for generating an appropriate response. Step 2: The response generation unit generates an appropriate response based on the subject's utterances analyzed by the utterance analysis unit. For example, the response generation unit uses a generation AI to select an appropriate response based on the subject's utterances and generate the response in real time. Step 3: The response evaluation unit analyzes and evaluates the content of the test subject's response. For example, it makes an appropriate evaluation based on the content of the response, scores the evaluation results, and provides feedback on areas for improvement.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0075] 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.

[0076] 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.

[0077] 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.

[0078] 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.

[0079] 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).

[0080] 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.

[0081] 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.

[0082] 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.

[0083] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0084] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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.

[0089] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0090] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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).

[0095] 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.

[0096] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0097] 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.

[0098] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0099] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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).

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0115] In the robot 414, 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. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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."

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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]

[0138] 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 speech analysis unit that analyzes the speech of the subject in real time; a response generator that generates an appropriate response based on the utterance of the subject analyzed by the utterance analyzer; and a response evaluation unit that analyzes and evaluates the response content of the subject. A system characterized by:

2. The response generation unit The past response history of the subject is learned, and a response optimized for the subject is generated.

2. The system of claim 1.

3. The response generation unit In addition to the content of the subject's speech, facial expressions of the subject are analyzed using facial expression recognition technology, and a response is generated according to the subject's emotions.

2. The system of claim 1.

4. The response generation unit Estimating the subject's emotions in real time and generating a response according to the emotions 2. The system of claim 1.

5. The response generation unit Automatically generate responses in different languages ​​to realize multilingual customer service training 2. The system of claim 1.

6. The response generation unit Analyzing the motion data of the subject and generating a response according to the motion 2. The system of claim 1.

7. The response generation unit Generate a response based on the subject's emotions to elicit emotional empathy 2. The system of claim 1.

8. The response evaluation unit The content of the subject's responses is analyzed over time to evaluate the consistency of the responses.

2. The system of claim 1.

Images