System

Abstract

To provide a system that provides product explanations and demonstrations according to the emotions of a customer.SOLUTION: A system according to an embodiment comprises an acquisition unit, an estimation unit, and an explanation unit. The acquisition unit acquires emotion estimation information for estimating the emotions of a customer. The estimation unit estimates the emotions of the customer on the basis of the emotion estimation information acquired by the acquisition unit. The explanation unit provides product explanations and demonstrations according to the emotions of the customer as estimated by the estimation unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to provide product explanations and demonstrations that responded to the customer's emotions, and the effectiveness of sales support was limited.

[0005] The system according to the embodiment aims to provide product explanations and demonstrations that correspond to the emotions of the customer. [Means for solving the problem]

[0006] A system according to an embodiment includes an acquisition unit, an estimation unit, and an explanation unit. The acquisition unit acquires emotion estimation information for estimating an emotion of a customer. The estimation unit estimates an emotion of the customer based on the emotion estimation information acquired by the acquisition unit. The explanation unit provides a product explanation or demonstration according to the emotion of the customer estimated by the estimation unit. Effect of the Invention

[0007] The system according to the embodiment can provide product explanations and demonstrations that correspond to the emotions of the customer. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the 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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The system according to the embodiment of the present invention is a system that uses an agent having an emotion engine as a robot for product explanation in a mobile phone shop. This system realizes more effective sales support by reading the emotions of the customer and providing appropriate product explanations and demonstrations. For example, the agent can explain how to use a terminal or an app and its functions, and can actually perform demonstrations. In addition, the agent can respond to the customer's questions and concerns in a polite and friendly manner. Specifically, the system is composed of the following steps. First, emotion estimation information for estimating the customer's emotions is acquired. Next, the customer's emotions are estimated based on the acquired information. Depending on the estimated emotions, the agent explains the product and provides a demonstration. This mechanism enables appropriate responses according to the customer's emotions, and sales support is effectively performed. For example, information such as the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwaves, body temperature, breathing, and posted content is acquired. This information is input to the emotion engine. Next, the emotion engine analyzes the acquired information and estimates the customer's emotions. For example, if the customer is smiling, it is estimated that the customer has positive emotions. In this way, the customer's emotions can be estimated in real time. Depending on the estimated emotion, the agent will explain the product and give a demonstration. For example, if the customer is interested, the agent will give a detailed explanation. On the other hand, if the customer is anxious, the agent will respond politely and kindly. In this way, it is possible to respond appropriately according to the customer's emotion. Furthermore, the agent can adjust the content of the explanation according to the customer's reaction. For example, if the customer finds it difficult to understand, the agent will simplify the explanation. Also, if the customer is interested, the agent will provide detailed information. In this way, it is possible to respond flexibly according to the customer's reaction. With this mechanism, the agent can be effectively used as a product explanation robot in a mobile phone shop. It is possible to respond appropriately according to the customer's emotion, and sales support is effectively performed. For example, the agent can explain how to use and the functions of the terminal or app, and can actually demonstrate it. In addition, the agent can respond politely and kindly to the customer's questions and anxiety.This improves customer satisfaction and promotes sales. The agent system can therefore respond appropriately to the customer's emotions, providing effective sales support.

[0029] The agent system according to the embodiment includes an acquisition unit, an estimation unit, and an explanation unit. The acquisition unit acquires emotion estimation information for estimating the emotion of a customer. The emotion estimation information for estimating the emotion of a customer includes, for example, the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content, but is not limited to such examples. For example, the acquisition unit captures the customer's facial expression using a camera and acquires it as emotion estimation information. The acquisition unit can also detect the customer's movement using a sensor and acquire it as emotion estimation information. Furthermore, the acquisition unit can capture the customer's voice using a microphone and acquire it as emotion estimation information. For example, the acquisition unit captures the customer's facial expression with a camera and analyzes the facial expression using face recognition technology. The sensor detects the customer's movement and analyzes the movement using a movement analysis algorithm. The microphone captures the customer's voice and analyzes the voice using voice recognition technology. The estimation unit estimates the customer's emotion based on the emotion estimation information acquired by the acquisition unit. The estimation unit, for example, uses AI to analyze the emotion estimation information and estimate the emotion of the customer. For example, the estimation unit inputs the emotion estimation information into an AI model and outputs the emotion of the customer. For example, the estimation unit estimates that the customer has a positive emotion when the customer smiles. The estimation unit can also estimate that the customer has a negative emotion when the customer frowns. Furthermore, the estimation unit can estimate that the customer has a neutral emotion when the customer has a blank expression. The explanation unit performs a product explanation or demonstration according to the emotion of the customer estimated by the estimation unit. For example, when the customer shows interest, the explanation unit performs a detailed product explanation. Furthermore, when the customer feels anxious, the explanation unit can also provide a polite and friendly response. Furthermore, when the customer is in a hurry, the explanation unit can provide a concise and to the point explanation. For example, when the customer shows interest, the explanation unit explains the features and advantages of the product in detail. When the customer feels anxious, the explanation unit provides a polite and to the point response to give a sense of security. When the customer is in a hurry, the explanation unit provides a concise and to the point explanation to quickly provide information.This allows the agent system according to the embodiment to provide an appropriate product explanation or demonstration in accordance with the customer's emotions. A part or all of the above-described processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can provide an explanation or demonstration using an AI model that receives the customer's emotions estimated by the estimation unit as input and outputs a product explanation or demonstration. This allows the agent system to provide an appropriate product explanation or demonstration in accordance with the customer's emotions.

[0030] The acquisition unit acquires emotion estimation information for estimating the emotion of the customer. The emotion estimation information for estimating the emotion of the customer includes, for example, the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content, but is not limited to such examples. For example, the acquisition unit captures the customer's facial expression using a camera and acquires it as emotion estimation information. The acquisition unit can also detect the customer's movement using a sensor and acquire it as emotion estimation information. Furthermore, the acquisition unit can capture the customer's voice using a microphone and acquire it as emotion estimation information. For example, the acquisition unit captures the customer's facial expression with a camera and analyzes the facial expression using face recognition technology. The sensor detects the customer's movement and analyzes the movement using a movement analysis algorithm. The microphone captures the customer's voice and analyzes the voice using voice recognition technology. This allows the acquisition unit to collect various emotion estimation information and provide basic data for accurately estimating the customer's emotion. Furthermore, the acquisition unit can collect these data in real time and immediately transmit them to the analysis unit. For example, the camera captures high-resolution video and uses facial recognition technology to detect subtle changes in facial expressions. The sensor records the customer's movements in detail and analyzes the movement patterns using a motion analysis algorithm. The microphone captures the customer's voice with high accuracy and analyzes the tone and pitch of the voice using voice recognition technology. This allows the acquisition unit to capture the customer's emotions from multiple angles and more accurately estimate their emotions. The acquisition unit can also centrally manage these data and link with other systems and departments as necessary. For example, the collected data is stored on a cloud server and made accessible to the analysis unit and estimation unit. In addition, by adjusting the frequency and accuracy of data collection, flexible responses according to specific situations and conditions are possible. This allows the acquisition unit to efficiently and effectively collect data and improve the performance of the entire system.

[0031] The estimation unit estimates the customer's emotion based on the emotion estimation information acquired by the acquisition unit. The estimation unit, for example, uses AI to analyze the emotion estimation information and estimate the customer's emotion. Specifically, the estimation unit inputs the emotion estimation information to an AI model and outputs the customer's emotion. For example, the estimation unit estimates that the customer has a positive emotion when the customer smiles. The estimation unit can also estimate that the customer has a negative emotion when the customer frowns. Furthermore, the estimation unit can estimate that the customer has a neutral emotion when the customer has no expression. The estimation unit analyzes various emotion estimation information such as facial expressions, movements, and voice using an AI model to estimate the customer's emotion with high accuracy. For example, the estimation unit detects subtle changes in the customer's facial expressions using facial expression recognition technology and estimates the type and intensity of the emotion. The motion analysis algorithm is used to analyze the customer's motion patterns and capture changes in emotion. The voice recognition technology is used to analyze the tone and pitch of the customer's voice and estimate the emotional state. This allows the estimation unit to capture the customer's emotions from multiple angles and perform more accurate emotion estimation. Furthermore, the estimation unit can also analyze long-term emotional fluctuations and trends by utilizing past data and statistical information. For example, based on past emotional data, it can predict the emotional fluctuation pattern of a specific customer and plan future countermeasures. The estimation unit can also use an anomaly detection algorithm to detect unusual emotional changes and abnormal data and issue an early warning. This allows the estimation unit to handle not only real-time emotion estimation, but also long-term emotion management and anomaly detection, improving the reliability and safety of the entire system.

[0032] The explanation unit performs a product explanation or demonstration according to the customer's emotions estimated by the estimation unit. For example, when the customer shows interest, the explanation unit performs a detailed product explanation. In addition, when the customer feels anxious, the explanation unit can also provide a polite and friendly response. Furthermore, when the customer is in a hurry, the explanation unit can provide a brief and to the point explanation. For example, when the customer shows interest, the explanation unit explains the features and advantages of the product in detail. When the customer feels anxious, the explanation unit provides a polite and friendly response to give a sense of security. When the customer is in a hurry, the explanation unit provides a brief and to the point explanation and provides information quickly. As a result, the agent system according to the embodiment can perform an appropriate product explanation or demonstration according to the customer's emotions. A part or all of the above-mentioned processing in the explanation unit may be performed using, for example, AI, or may be performed without using AI. For example, the explanation unit can perform an explanation or demonstration using an AI model that inputs the customer's emotions estimated by the estimation unit and outputs a product explanation or demonstration. Specifically, the AI ​​model generates optimal explanation content according to the customer's emotions and provides appropriate information to the customer. For example, if a customer shows interest, the AI ​​model generates a detailed description of the product and explains the product's features and advantages to the customer. If the customer is anxious, the AI ​​model generates a polite explanation to reassure the customer and provides a friendly response to the customer. If the customer is in a hurry, the AI ​​model generates a concise and to-the-point explanation and provides information quickly. This allows the explanation department to provide appropriate product explanations and demonstrations according to the customer's emotions, thereby improving customer satisfaction. Furthermore, the explanation department can collect customer feedback and continuously improve the accuracy and effectiveness of the explanation content. For example, based on the customer's reactions and opinions, the explanation content is reviewed and improved to provide a more effective explanation. Furthermore, the explanation department can reliably transmit information using multiple communication methods. For example, important information is reliably delivered to the customer by using not only face-to-face explanations but also online chat, video calls, emails, etc. in combination. This allows the explanation department to provide information quickly and reliably to customers and improve customer satisfaction.

[0033] The explanation unit may include an adjustment unit that adjusts the content of the explanation according to the customer's reaction. The adjustment unit adjusts the content of the explanation according to the customer's reaction to the explanation or demonstration performed by the explanation unit. For example, if the customer feels that it is difficult to understand, the adjustment unit simplifies the explanation. In addition, if the customer is interested, the adjustment unit can also provide detailed information. Furthermore, if the customer feels anxious, the adjustment unit can provide an explanation that gives a sense of security. For example, if the customer feels that it is difficult to understand, the adjustment unit adjusts the level of detail of the explanation and uses simple words to provide an explanation. If the customer is interested, detailed information and advantages of the product are provided. If the customer feels anxious, a polite and friendly response is provided to give a sense of security. This enables the adjustment unit to respond flexibly according to the customer's reaction. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can adjust the content of the explanation using an AI model that uses customer reaction data as an input and adjusts the content of the explanation.

[0034] The explanation unit can perform a product explanation or demonstration in a manner according to the customer's emotions. The manner according to the customer's emotions includes, for example, at least one of the following: language, tone, topic, tone of voice, gestures, facial expressions, content, speed, timing, and pauses, but is not limited to such examples. For example, when the customer is relaxed, the explanation unit performs an explanation in a friendly manner. Also, when the customer is nervous, the explanation unit can perform an explanation in a calm tone. Furthermore, when the customer is excited, the explanation unit can perform an explanation in an energetic tone. For example, when the customer is relaxed, the explanation unit performs an explanation in a gentle tone of voice. When the customer is nervous, the explanation unit performs an explanation in a calm tone of voice. When the customer is excited, the explanation unit performs an explanation in a lively tone of voice. This enables the explanation unit to respond appropriately according to the customer's emotions. Part or all of the above-mentioned processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can perform an explanation or demonstration using an AI model that uses customer emotion data as input and performs a product explanation or demonstration in an appropriate manner.

[0035] The explanation unit can perform a product explanation or demonstration according to the customer's emotions and attributes. The customer's attributes include, but are not limited to, for example, age, sex, and purchase history. For example, if the customer is a young person, the explanation unit can perform the explanation using language and topics suitable for young people. In addition, if the customer is an elderly person, the explanation unit can also perform the explanation using language and topics suitable for elderly people. Furthermore, the explanation unit can suggest products that the customer is likely to be interested in based on the customer's purchase history. For example, if the customer is a young person, the explanation unit can perform the explanation using casual language and topics related to trends. If the customer is an elderly person, the explanation unit can perform the explanation using polite language and topics related to health. Based on the customer's purchase history, a new product related to a product that the customer has previously purchased is suggested. This enables the explanation unit to respond appropriately according to the customer's emotions and attributes. Part or all of the above-mentioned processing in the explanation unit may be performed using, for example, AI, or may be performed without using AI. For example, the explanation unit can perform an explanation or demonstration using an AI model that inputs the customer's emotion data and attribute data and performs an appropriate product explanation or demonstration.

[0036] The product explanation robot can function as a product explanation robot including an acquisition unit, an estimation unit, and an explanation unit. The product explanation robot includes an acquisition unit, an estimation unit, and an explanation unit. The acquisition unit acquires emotion estimation information for estimating the emotion of a customer. The estimation unit estimates the emotion of the customer based on the emotion estimation information acquired by the acquisition unit. The explanation unit performs a product explanation or demonstration according to the emotion of the customer estimated by the estimation unit. For example, the product explanation robot captures the facial expression of the customer using a camera and acquires it as emotion estimation information. The customer's movement can also be detected using a sensor and acquired as emotion estimation information. The customer's voice can also be captured using a microphone and acquired as emotion estimation information. The estimation unit analyzes the emotion estimation information using AI and estimates the emotion of the customer. The explanation unit performs a product explanation or demonstration according to the emotion of the customer estimated by the estimation unit. This enables the product explanation robot to respond appropriately according to the emotion of the customer, and sales support is effectively performed. A part or all of the above-mentioned processing in the product explanation robot may be performed using AI, for example, or may be performed without using AI. For example, a product explanation robot can provide explanations or demonstrations using an AI model that takes customer emotional data as input and delivers an appropriate product explanation or demonstration.

[0037] The acquisition unit can acquire one or more pieces of information among the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content as emotion estimation information. For example, the acquisition unit captures the customer's facial expression using a camera and acquires it as emotion estimation information. The acquisition unit can also detect the customer's movement using a sensor and acquire it as emotion estimation information. Furthermore, the acquisition unit can capture the customer's voice using a microphone and acquire it as emotion estimation information. For example, the acquisition unit captures the customer's facial expression with a camera and analyzes the facial expression using face recognition technology. The sensor detects the customer's movement and analyzes the movement using a movement analysis algorithm. The microphone captures the customer's voice and analyzes the voice using voice recognition technology. As a result, the acquisition unit acquires various information as emotion estimation information, thereby improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input facial expression data of a customer to the generation AI and have the generation AI execute emotion estimation information from the facial expression data.

[0038] The acquisition unit can acquire the facial expression of the customer and use it as emotion estimation information. For example, when the customer smiles, the acquisition unit captures the facial expression with a camera and acquires it as emotion estimation information. In addition, when the customer frowns, the acquisition unit can also capture the facial expression with a camera and acquire it as emotion estimation information. Furthermore, when the customer has no facial expression, the acquisition unit can capture the facial expression with a camera and acquire it as emotion estimation information. For example, the acquisition unit captures the facial expression of the customer with a camera and analyzes the facial expression using face recognition technology. As a result, the acquisition unit uses the facial expression of the customer as emotion estimation information, thereby improving the accuracy of emotion estimation. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI or may be performed without using AI. For example, the acquisition unit can input the facial expression data of the customer to the generation AI and cause the generation AI to execute the emotion estimation information from the facial expression data.

[0039] The acquisition unit can acquire the customer's motion and use it as emotion estimation information. For example, when the customer has folded his / her arms, the acquisition unit detects the motion with a sensor and acquires it as emotion estimation information. In addition, when the customer frequently scratches his / her head, the acquisition unit can also detect the motion with a sensor and acquire it as emotion estimation information. In addition, when the customer has crossed his / her legs, the acquisition unit can detect the motion with a sensor and acquire it as emotion estimation information. For example, the acquisition unit detects the customer's motion with a sensor and analyzes the motion using a motion analysis algorithm. As a result, the acquisition unit uses the customer's motion as emotion estimation information, thereby improving the accuracy of emotion estimation. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input the customer's motion data to the generation AI and cause the generation AI to execute emotion estimation information from the motion data.

[0040] The acquisition unit can acquire the voice of the customer and use it as emotion estimation information. For example, when the customer speaks in a high voice, the acquisition unit captures the voice with a microphone and acquires it as emotion estimation information. In addition, when the customer speaks in a low voice, the acquisition unit can also capture the voice with a microphone and acquire it as emotion estimation information. In addition, when the customer speaks quickly, the acquisition unit can capture the voice with a microphone and acquire it as emotion estimation information. For example, the acquisition unit captures the voice of the customer with a microphone and analyzes the voice using a voice recognition technology. As a result, the acquisition unit uses the voice of the customer as emotion estimation information, thereby improving the accuracy of emotion estimation. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input the voice data of the customer to a generation AI and cause the generation AI to execute emotion estimation information from the voice data.

[0041] The acquisition unit can acquire the heart rate of the customer and use it as emotion estimation information. For example, when the customer's heart rate is fast, the acquisition unit acquires the heart rate data with a sensor and uses it as emotion estimation information. When the customer's heart rate is slow, the acquisition unit can also acquire the heart rate data with a sensor and use it as emotion estimation information. When the customer's heart rate is irregular, the acquisition unit can acquire the heart rate data with a sensor and use it as emotion estimation information. For example, the acquisition unit detects the customer's heart rate with a sensor and analyzes the heart rate using a heart rate analysis algorithm. As a result, the acquisition unit uses the customer's heart rate as emotion estimation information, thereby improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input the customer's heart rate data to the generation AI and cause the generation AI to execute emotion estimation information from the heart rate data.

[0042] The acquisition unit can acquire the blood pressure of the customer and use it as emotion estimation information. For example, when the customer's blood pressure is high, the acquisition unit acquires the blood pressure data with a sensor and uses it as emotion estimation information. In addition, when the customer's blood pressure is low, the acquisition unit can acquire the blood pressure data with a sensor and use it as emotion estimation information. In addition, when the customer's blood pressure fluctuates, the acquisition unit can acquire the blood pressure data with a sensor and use it as emotion estimation information. For example, the acquisition unit detects the customer's blood pressure with a sensor and analyzes the blood pressure using a blood pressure analysis algorithm. As a result, the acquisition unit uses the customer's blood pressure as emotion estimation information, thereby improving the accuracy of emotion estimation. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input the customer's blood pressure data to the generation AI and cause the generation AI to execute emotion estimation information from the blood pressure data.

[0043] The acquisition unit can acquire the pupillary response of the customer and use it as emotion estimation information. For example, when the customer's pupil is dilated, the acquisition unit captures the pupillary response with a camera and uses it as emotion estimation information. In addition, when the customer's pupil is constricted, the acquisition unit can capture the pupillary response with a camera and use it as emotion estimation information. In addition, when the customer's pupil is fluctuating, the acquisition unit can capture the pupillary response with a camera and use it as emotion estimation information. For example, the acquisition unit captures the customer's pupillary response with a camera and analyzes the pupillary response using a pupillary response analysis algorithm. As a result, the acquisition unit uses the customer's pupillary response as emotion estimation information, thereby improving the accuracy of emotion estimation. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input the customer's pupillary response data to the generation AI and cause the generation AI to execute emotion estimation information from the pupillary response data.

[0044] The estimation unit can estimate the emotion based on the facial expression of the customer. For example, if the customer smiles, the estimation unit estimates that the customer has a positive emotion. Also, if the customer frowns, the estimation unit can estimate that the customer has a negative emotion. Furthermore, if the customer has no facial expression, the estimation unit can estimate that the customer has a neutral emotion. For example, the estimation unit uses AI to analyze facial expression data of the customer and estimate the emotion. As a result, the estimation unit estimates the emotion based on the customer's facial expression, thereby improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input facial expression data of the customer to a generation AI and estimate the emotion from the facial expression data.

[0045] The estimation unit can estimate the emotion based on the customer's behavior. For example, if the customer has folded arms, the estimation unit estimates that the customer has a defensive emotion. Also, if the customer frequently scratches his head, the estimation unit can estimate that the customer is confused. Furthermore, if the customer has crossed legs, the estimation unit can estimate that the customer is relaxed. For example, the estimation unit uses AI to analyze the customer's behavior data and estimate the emotion. As a result, the estimation unit estimates the emotion based on the customer's behavior, thereby improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the estimation unit may be performed using AI, for example, or may be performed without using AI. For example, the estimation unit can input the customer's behavior data to a generation AI and estimate the emotion from the behavior data.

[0046] The estimation unit can estimate the emotion based on the customer's voice. For example, if the customer speaks in a high-pitched voice, the estimation unit estimates that the customer is excited. Also, if the customer speaks in a low-pitched voice, the estimation unit can estimate that the customer is calm. Furthermore, if the customer speaks quickly, the estimation unit can estimate that the customer is nervous. For example, the estimation unit uses AI to analyze the customer's voice data and estimate the emotion. As a result, the estimation unit estimates the emotion based on the customer's voice, improving the accuracy of the emotion estimation. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input the customer's voice data to a generation AI and estimate the emotion from the voice data.

[0047] The estimation unit can estimate the emotion based on the customer's heart rate. For example, if the customer's heart rate is fast, the estimation unit estimates that the customer is excited. Also, if the customer's heart rate is slow, the estimation unit can estimate that the customer is relaxed. Furthermore, if the customer's heart rate is irregular, the estimation unit can estimate that the customer is nervous. For example, the estimation unit uses AI to analyze the customer's heart rate data and estimate the emotion. As a result, the estimation unit estimates the emotion based on the customer's heart rate, thereby improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the estimation unit may be performed using AI, for example, or may be performed without using AI. For example, the estimation unit can input the customer's heart rate data to the generation AI and estimate the emotion from the heart rate data.

[0048] The estimation unit can estimate the emotion based on the customer's blood pressure. For example, when the customer's blood pressure is high, the estimation unit estimates that the customer is stressed. In addition, when the customer's blood pressure is low, the estimation unit can estimate that the customer is relaxed. Furthermore, when the customer's blood pressure fluctuates, the estimation unit can estimate that the customer is nervous. For example, the estimation unit uses AI to analyze the customer's blood pressure data and estimate the emotion. As a result, the estimation unit estimates the emotion based on the customer's blood pressure, improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input the customer's blood pressure data to the generation AI and estimate the emotion from the blood pressure data.

[0049] The estimation unit can estimate the emotion based on the customer's pupil response. For example, the estimation unit estimates that the customer is excited when the customer's pupil is dilated. The estimation unit can also estimate that the customer is relaxed when the customer's pupil is constricted. Furthermore, the estimation unit can estimate that the customer is nervous when the customer's pupil is fluctuating. For example, the estimation unit uses AI to analyze the customer's pupil response data and estimate the emotion. As a result, the estimation unit estimates the emotion based on the customer's pupil response, thereby improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the estimation unit may be performed using AI, for example, or may be performed without using AI. For example, the estimation unit can input the customer's pupil response data to the generation AI and estimate the emotion from the pupil response data.

[0050] The explanation unit can provide a product explanation according to the customer's emotions. For example, when the customer shows interest, the explanation unit provides a detailed product explanation. In addition, when the customer feels anxious, the explanation unit can also provide a polite and friendly response. Furthermore, when the customer is in a hurry, the explanation unit can provide a concise and to the point explanation. For example, when the customer shows interest, the explanation unit explains the features and advantages of the product in detail. When the customer feels anxious, the explanation unit provides a polite and friendly response to give a sense of security. When the customer is in a hurry, the explanation unit provides a concise and to the point explanation and provides information quickly. As a result, the explanation unit provides a product explanation according to the customer's emotions, thereby improving customer satisfaction. Part or all of the above-mentioned processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can provide an explanation using an AI model that uses customer emotion data as input and provides an appropriate product explanation.

[0051] The explanation unit can perform a demonstration according to the customer's emotions. For example, when the customer shows interest, the explanation unit performs a detailed demonstration. In addition, when the customer feels anxious, the explanation unit can also perform a polite and friendly demonstration. Furthermore, when the customer is in a hurry, the explanation unit can perform a concise and to the point demonstration. For example, when the customer shows interest, the explanation unit performs a detailed demonstration of the use method and advantages of the product. When the customer feels anxious, the explanation unit performs a polite and friendly demonstration to give a sense of security. When the customer is in a hurry, the explanation unit performs a concise and to the point demonstration to provide information quickly. As a result, the explanation unit performs a demonstration according to the customer's emotions, thereby improving customer satisfaction. Part or all of the above-mentioned processing in the explanation unit may be performed using, for example, AI, or may be performed without using AI. For example, the explanation unit can perform a demonstration using an AI model that inputs customer emotion data and performs an appropriate demonstration.

[0052] The explanation unit can explain the product in a manner that corresponds to the customer's emotions. For example, when the customer is relaxed, the explanation unit explains the product in a friendly manner. Also, when the customer is nervous, the explanation unit can explain the product in a calm manner. Furthermore, when the customer is excited, the explanation unit can explain the product in an energetic manner. For example, when the customer is relaxed, the explanation unit explains the product in a calm manner. When the customer is nervous, the explanation unit explains the product in a calm manner. When the customer is excited, the explanation unit explains the product in a lively manner. As a result, the explanation unit explains the product in a manner that corresponds to the customer's emotions, thereby improving customer satisfaction. Part or all of the above-mentioned processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can explain the product using an AI model that uses customer emotion data as input and explains the product in appropriate language.

[0053] The explanation unit can explain the product in a tone of voice according to the customer's emotions. For example, when the customer is relaxed, the explanation unit explains in a calm tone. Also, when the customer is nervous, the explanation unit can explain in a calm tone. Furthermore, when the customer is excited, the explanation unit can explain in a lively tone. For example, when the customer is relaxed, the explanation unit explains in a calm tone of voice. When the customer is nervous, the explanation unit explains in a calm tone of voice. When the customer is excited, the explanation unit explains in a lively tone of voice. As a result, the explanation unit explains the product in a tone of voice according to the customer's emotions, thereby improving customer satisfaction. Part or all of the above-mentioned processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can explain the product using an AI model that uses customer emotion data as input and explains the product in an appropriate tone.

[0054] The explanation unit can explain the product using a topic according to the customer's emotions. For example, when the customer shows interest, the explanation unit introduces a related topic to explain. In addition, when the customer feels anxious, the explanation unit can also introduce a topic that gives a sense of security to explain. Furthermore, when the customer is in a hurry, the explanation unit can also explain using a topic that focuses on the main points. For example, when the customer shows interest, the explanation unit introduces a topic related to the features and advantages of the product to explain. When the customer feels anxious, the explanation unit introduces a polite and friendly topic to give a sense of security to explain. When the customer is in a hurry, the explanation unit introduces a concise topic that focuses on the main points to provide information quickly. As a result, the explanation unit explains the product using a topic according to the customer's emotions, thereby improving customer satisfaction. Part or all of the above-mentioned processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can explain the product using an AI model that uses customer emotion data as input and explains the product using appropriate topics.

[0055] The explanation unit can explain the product in a tone of voice according to the customer's emotions. For example, when the customer is relaxed, the explanation unit explains in a calm tone of voice. Also, when the customer is nervous, the explanation unit can explain in a calm tone of voice. Furthermore, when the customer is excited, the explanation unit can explain in a lively tone of voice. For example, when the customer is relaxed, the explanation unit explains in a calm tone of voice. When the customer is nervous, the explanation unit explains in a calm tone of voice. When the customer is excited, the explanation unit explains in a lively tone of voice. As a result, the explanation unit explains the product in a tone of voice according to the customer's emotions, thereby improving customer satisfaction. Part or all of the above-mentioned processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can explain the product using an AI model that uses customer emotion data as input and explains the product in an appropriate tone of voice.

[0056] The adjustment unit can adjust the content of the explanation according to the customer's reaction. For example, if the customer feels that it is difficult to understand, the adjustment unit simplifies the explanation. In addition, if the customer is interested, the adjustment unit can also provide detailed information. Furthermore, if the customer feels anxious, the adjustment unit can provide an explanation that gives a sense of security. For example, if the customer feels that it is difficult to understand, the adjustment unit adjusts the level of detail of the explanation and uses simple words to provide an explanation. If the customer is interested, detailed information and advantages of the product are provided. If the customer feels anxious, a polite and friendly response is provided to give a sense of security. This enables the adjustment unit to adjust the content of the explanation according to the customer's reaction. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can adjust the content of the explanation using an AI model that uses customer reaction data as an input and adjusts the content of the explanation.

[0057] The adjustment unit can adjust the speed of the explanation according to the customer's reaction. For example, when the customer is in a hurry, the adjustment unit speeds up the speed of the explanation. Also, when the customer is relaxed, the adjustment unit can slow down the speed of the explanation. Furthermore, when the customer feels that it is difficult to understand, the adjustment unit can adjust the speed of the explanation. For example, when the customer is in a hurry, the adjustment unit speeds up the speed of the explanation to provide information quickly. When the customer is relaxed, the adjustment unit slows down the speed of the explanation to provide a careful explanation. When the customer feels that it is difficult to understand, the adjustment unit adjusts the speed of the explanation to make it easy to understand. This enables the adjustment unit to adjust the speed of the explanation according to the customer's reaction. A part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can adjust the speed of the explanation using an AI model that uses customer reaction data as input and adjusts the speed of the explanation.

[0058] The adjustment unit can adjust the timing of the explanation according to the customer's reaction. For example, when the customer asks a question, the adjustment unit provides an explanation at that timing. In addition, when the customer shows interest, the adjustment unit can also provide a detailed explanation at that timing. Furthermore, when the customer feels that it is difficult to understand, the adjustment unit can also simplify the explanation at that timing. For example, when the customer asks a question, the adjustment unit provides an explanation at that timing to resolve the customer's doubts. When the customer shows interest, the adjustment unit provides a detailed explanation at that timing to keep the customer's interest. When the customer feels that it is difficult to understand, the adjustment unit simplifies the explanation at that timing to make it easier to understand. This enables the adjustment unit to adjust the timing of the explanation according to the customer's reaction. A part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can adjust the timing of the explanation using an AI model that uses customer reaction data as an input and adjusts the timing of the explanation.

[0059] The adjustment unit can adjust the interval between explanations according to the customer's reaction. For example, when the customer is thinking deeply, the adjustment unit lengthens the interval between explanations. In addition, when the customer is in a hurry, the adjustment unit can also shorten the interval between explanations. Furthermore, when the customer feels that it is difficult to understand, the adjustment unit can adjust the interval between explanations. For example, when the customer is thinking deeply, the adjustment unit lengthens the interval between explanations to give the customer time to think. When the customer is in a hurry, the adjustment unit shortens the interval between explanations to provide information quickly. When the customer feels that it is difficult to understand, the adjustment unit adjusts the interval between explanations to make it easier to understand. This enables the adjustment unit to adjust the interval between explanations according to the customer's reaction. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can adjust the interval between explanations using an AI model that uses customer reaction data as input and adjusts the interval between explanations.

[0060] The adjustment unit can adjust the content of the explanation according to the customer's reaction. For example, if the customer feels that it is difficult to understand, the adjustment unit simplifies the content of the explanation. In addition, if the customer is interested, the adjustment unit can also provide detailed information. Furthermore, if the customer feels anxious, the adjustment unit can provide an explanation that gives a sense of security. For example, if the customer feels that it is difficult to understand, the adjustment unit simplifies the content of the explanation to make it easier to understand. If the customer is interested, detailed information and advantages of the product are provided. If the customer feels anxious, a polite and friendly response is provided to give a sense of security. This enables the adjustment unit to adjust the content of the explanation according to the customer's reaction. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can adjust the content of the explanation using an AI model that uses customer reaction data as an input and adjusts the content of the explanation.

[0061] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0062] The agent system may further include a history analysis unit that analyzes the purchase history of the customer. The history analysis unit acquires the past purchase history of the customer and estimates the customer's interests and concerns. For example, the history analysis unit may analyze data on products and services purchased by the customer in the past and estimate products that the customer may be interested in. The estimation unit may estimate the customer's emotions in a complementary manner based on the customer's interests estimated by the history analysis unit. For example, the estimation unit may estimate the customer's emotions more accurately when proposing a new product related to a product purchased by the customer in the past. This allows the agent system to provide a more personalized product explanation or demonstration based on the customer's purchase history.

[0063] The adjustment unit can not only adjust the content of the explanation according to the customer's reaction, but also customize the information to be provided at the customer's next visit based on the customer's reaction. For example, if the customer shows interest in a particular product, the adjustment unit can record that information and provide related information on new products and services at the customer's next visit. Also, if the customer finds it difficult to understand a particular function, the adjustment unit can record that information and provide a more easily understandable explanation at the customer's next visit. Furthermore, if the customer asks a particular question, the adjustment unit can provide a detailed answer to that question at the customer's next visit. This allows the adjustment unit to continuously customize based on the customer's reaction.

[0064] The explanation department can not only provide product explanations or demonstrations according to the customer's emotions and attributes, but also provide special offers and discounts based on the customer's attributes. For example, the explanation department can provide student discounts and special offers for new customers to younger customers. Also, the explanation department can suggest senior discounts and health-related products to older customers. Furthermore, the explanation department can provide special discounts and point programs for repeat customers based on the customer's purchase history. In this way, the explanation department can improve customer satisfaction by providing special offers according to the customer's attributes.

[0065] The product explanation robot may not only include an acquisition unit, an estimation unit, and an explanation unit, but also may be provided with a feedback collection unit that collects customer feedback. The feedback collection unit may collect how the customer felt about the product explanation or demonstration, and use the collected information to improve the system. For example, the feedback collection unit may collect in the form of a questionnaire whether the customer is satisfied with the product explanation. It may also collect which parts the customer found interesting and which parts were difficult to understand. It may also collect improvements and new ideas suggested by the customer. This allows the product explanation robot to be continuously improved based on customer feedback.

[0066] The acquisition unit can acquire one or more pieces of information from among the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content as emotion estimation information, and can also acquire the customer's location information and environmental information. For example, the acquisition unit can acquire the area in which the customer is located by GPS and provide information related to the area. The acquisition unit can also acquire the temperature and humidity of the environment in which the customer is located by a sensor and estimate the customer's comfort level based on the information. Furthermore, the acquisition unit can acquire the noise level in the location in which the customer is located and provide a description of a quiet environment. In this way, the acquisition unit can perform emotion estimation with higher accuracy by using the customer's location information and environmental information.

[0067] The acquisition unit can not only acquire the facial expression of the customer and use it as emotion estimation information, but also monitor changes in the customer's facial expression in real time. For example, when a customer changes from a smile to a serious expression, the acquisition unit can detect the change in real time and use it as emotion estimation information. Also, when a customer frowns and then smiles, the acquisition unit can detect the change and estimate the emotion change. Furthermore, when a customer changes from a neutral expression to a surprised expression, the acquisition unit can detect the change and estimate the emotion change. In this way, the acquisition unit can perform more accurate emotion estimation by monitoring the change in the customer's facial expression in real time.

[0068] The acquisition unit can acquire the customer's movements and use them as emotion estimation information, as well as analyze the customer's movement patterns. For example, if the customer frequently crosses his / her arms, the acquisition unit can analyze the movement pattern and estimate a defensive emotion. If the customer frequently scratches his / her head, the acquisition unit can analyze the movement pattern and estimate that the customer is confused. If the customer frequently crosses his / her legs, the acquisition unit can analyze the movement pattern and estimate that the customer is relaxed. In this way, the acquisition unit can perform more accurate emotion estimation by analyzing the customer's movement patterns.

[0069] The acquisition unit can acquire the voice of the customer and use it as emotion estimation information, and can also analyze the tone and rhythm of the customer's voice. For example, if the customer speaks in a high-pitched voice, the acquisition unit can analyze the tone of the voice and estimate that the customer is excited. Also, if the customer speaks in a low-pitched voice, the acquisition unit can analyze the tone of the voice and estimate that the customer is calm. Furthermore, if the customer speaks quickly, the acquisition unit can analyze the rhythm of the voice and estimate that the customer is nervous. In this way, the acquisition unit can perform more accurate emotion estimation by analyzing the tone and rhythm of the customer's voice.

[0070] The acquisition unit can not only acquire the heart rate of the customer and use it as emotion estimation information, but also monitor the fluctuations in the customer's heart rate in real time. For example, if the customer's heart rate suddenly speeds up, the acquisition unit can detect the fluctuations in real time and estimate that the customer is excited. Also, if the customer's heart rate suddenly slows down, the acquisition unit can detect the fluctuations and estimate that the customer is relaxed. Furthermore, if the customer's heart rate becomes irregular, the acquisition unit can detect the fluctuations and estimate that the customer is nervous. In this way, the acquisition unit can perform more accurate emotion estimation by monitoring the fluctuations in the customer's heart rate in real time.

[0071] The process flow of the first embodiment will be briefly described below.

[0072] Step 1: The acquisition unit acquires emotion estimation information for estimating the emotion of a customer. The emotion estimation information includes the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwaves, body temperature, breathing, and posted content. For example, the customer's facial expression is captured using a camera, the customer's movement is detected using a sensor, and the customer's voice is captured using a microphone. Step 2: The estimation unit estimates the customer's emotions based on the emotion estimation information acquired by the acquisition unit. For example, the estimation unit uses AI to analyze the emotion estimation information and estimate the customer's emotions. If the customer smiles, it is estimated that the customer has a positive emotion, if the customer frowns, it is estimated that the customer has a negative emotion, and if the customer has no expression, it is estimated that the customer has a neutral emotion. Step 3: The explanation unit performs a product explanation or demonstration according to the customer's emotions estimated by the estimation unit. For example, if the customer is interested, a detailed product explanation is performed, if the customer is anxious, a polite and friendly response is performed, and if the customer is in a hurry, a brief explanation is performed that focuses on the main points.

[0073] (Example 2) The system according to the embodiment of the present invention is a system that uses an agent having an emotion engine as a robot for product explanation in a mobile phone shop. This system realizes more effective sales support by reading the emotions of the customer and providing appropriate product explanations and demonstrations. For example, the agent can explain how to use a terminal or an app and its functions, and can actually perform demonstrations. In addition, the agent can respond to the customer's questions and concerns in a polite and friendly manner. Specifically, the system is composed of the following steps. First, emotion estimation information for estimating the customer's emotions is acquired. Next, the customer's emotions are estimated based on the acquired information. Depending on the estimated emotions, the agent explains the product and provides a demonstration. This mechanism enables appropriate responses according to the customer's emotions, and sales support is effectively performed. For example, information such as the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwaves, body temperature, breathing, and posted content is acquired. This information is input to the emotion engine. Next, the emotion engine analyzes the acquired information and estimates the customer's emotions. For example, if the customer is smiling, it is estimated that the customer has positive emotions. In this way, the customer's emotions can be estimated in real time. Depending on the estimated emotion, the agent will explain the product and give a demonstration. For example, if the customer is interested, the agent will give a detailed explanation. On the other hand, if the customer is anxious, the agent will respond politely and kindly. In this way, it is possible to respond appropriately according to the customer's emotion. Furthermore, the agent can adjust the content of the explanation according to the customer's reaction. For example, if the customer finds it difficult to understand, the agent will simplify the explanation. Also, if the customer is interested, the agent will provide detailed information. In this way, it is possible to respond flexibly according to the customer's reaction. With this mechanism, the agent can be effectively used as a product explanation robot in a mobile phone shop. It is possible to respond appropriately according to the customer's emotion, and sales support is effectively performed. For example, the agent can explain how to use and the functions of the terminal or app, and can actually demonstrate it. In addition, the agent can respond politely and kindly to the customer's questions and anxiety.This improves customer satisfaction and promotes sales. The agent system can therefore respond appropriately to the customer's emotions, providing effective sales support.

[0074] The agent system according to the embodiment includes an acquisition unit, an estimation unit, and an explanation unit. The acquisition unit acquires emotion estimation information for estimating the emotion of a customer. The emotion estimation information for estimating the emotion of a customer includes, for example, the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content, but is not limited to such examples. For example, the acquisition unit captures the customer's facial expression using a camera and acquires it as emotion estimation information. The acquisition unit can also detect the customer's movement using a sensor and acquire it as emotion estimation information. Furthermore, the acquisition unit can capture the customer's voice using a microphone and acquire it as emotion estimation information. For example, the acquisition unit captures the customer's facial expression with a camera and analyzes the facial expression using face recognition technology. The sensor detects the customer's movement and analyzes the movement using a movement analysis algorithm. The microphone captures the customer's voice and analyzes the voice using voice recognition technology. The estimation unit estimates the customer's emotion based on the emotion estimation information acquired by the acquisition unit. The estimation unit, for example, uses AI to analyze the emotion estimation information and estimate the emotion of the customer. For example, the estimation unit inputs the emotion estimation information into an AI model and outputs the emotion of the customer. For example, the estimation unit estimates that the customer has a positive emotion when the customer smiles. The estimation unit can also estimate that the customer has a negative emotion when the customer frowns. Furthermore, the estimation unit can estimate that the customer has a neutral emotion when the customer has a blank expression. The explanation unit performs a product explanation or demonstration according to the emotion of the customer estimated by the estimation unit. For example, when the customer shows interest, the explanation unit performs a detailed product explanation. Furthermore, when the customer feels anxious, the explanation unit can also provide a polite and friendly response. Furthermore, when the customer is in a hurry, the explanation unit can provide a concise and to the point explanation. For example, when the customer shows interest, the explanation unit explains the features and advantages of the product in detail. When the customer feels anxious, the explanation unit provides a polite and to the point response to give a sense of security. When the customer is in a hurry, the explanation unit provides a concise and to the point explanation to quickly provide information.This allows the agent system according to the embodiment to provide an appropriate product explanation or demonstration in accordance with the customer's emotions. A part or all of the above-described processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can provide an explanation or demonstration using an AI model that receives the customer's emotions estimated by the estimation unit as input and outputs a product explanation or demonstration. This allows the agent system to provide an appropriate product explanation or demonstration in accordance with the customer's emotions.

[0075] The acquisition unit acquires emotion estimation information for estimating the emotion of the customer. The emotion estimation information for estimating the emotion of the customer includes, for example, the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content, but is not limited to such examples. For example, the acquisition unit captures the customer's facial expression using a camera and acquires it as emotion estimation information. The acquisition unit can also detect the customer's movement using a sensor and acquire it as emotion estimation information. Furthermore, the acquisition unit can capture the customer's voice using a microphone and acquire it as emotion estimation information. For example, the acquisition unit captures the customer's facial expression with a camera and analyzes the facial expression using face recognition technology. The sensor detects the customer's movement and analyzes the movement using a movement analysis algorithm. The microphone captures the customer's voice and analyzes the voice using voice recognition technology. This allows the acquisition unit to collect various emotion estimation information and provide basic data for accurately estimating the customer's emotion. Furthermore, the acquisition unit can collect these data in real time and immediately transmit them to the analysis unit. For example, the camera captures high-resolution video and uses facial recognition technology to detect subtle changes in facial expressions. The sensor records the customer's movements in detail and analyzes the movement patterns using a motion analysis algorithm. The microphone captures the customer's voice with high accuracy and analyzes the tone and pitch of the voice using voice recognition technology. This allows the acquisition unit to capture the customer's emotions from multiple angles and more accurately estimate their emotions. The acquisition unit can also centrally manage these data and link with other systems and departments as necessary. For example, the collected data is stored on a cloud server and made accessible to the analysis unit and estimation unit. In addition, by adjusting the frequency and accuracy of data collection, flexible responses according to specific situations and conditions are possible. This allows the acquisition unit to efficiently and effectively collect data and improve the performance of the entire system.

[0076] The estimation unit estimates the customer's emotion based on the emotion estimation information acquired by the acquisition unit. The estimation unit, for example, uses AI to analyze the emotion estimation information and estimate the customer's emotion. Specifically, the estimation unit inputs the emotion estimation information to an AI model and outputs the customer's emotion. For example, the estimation unit estimates that the customer has a positive emotion when the customer smiles. The estimation unit can also estimate that the customer has a negative emotion when the customer frowns. Furthermore, the estimation unit can estimate that the customer has a neutral emotion when the customer has no expression. The estimation unit analyzes various emotion estimation information such as facial expressions, movements, and voice using an AI model to estimate the customer's emotion with high accuracy. For example, the estimation unit detects subtle changes in the customer's facial expressions using facial expression recognition technology and estimates the type and intensity of the emotion. The motion analysis algorithm is used to analyze the customer's motion patterns and capture changes in emotion. The voice recognition technology is used to analyze the tone and pitch of the customer's voice and estimate the emotional state. This allows the estimation unit to capture the customer's emotions from multiple angles and perform more accurate emotion estimation. Furthermore, the estimation unit can also analyze long-term emotional fluctuations and trends by utilizing past data and statistical information. For example, based on past emotional data, it can predict the emotional fluctuation pattern of a specific customer and plan future countermeasures. The estimation unit can also use an anomaly detection algorithm to detect unusual emotional changes and abnormal data and issue an early warning. This allows the estimation unit to handle not only real-time emotion estimation, but also long-term emotion management and anomaly detection, improving the reliability and safety of the entire system.

[0077] The explanation unit performs a product explanation or demonstration according to the customer's emotions estimated by the estimation unit. For example, when the customer shows interest, the explanation unit performs a detailed product explanation. In addition, when the customer feels anxious, the explanation unit can also provide a polite and friendly response. Furthermore, when the customer is in a hurry, the explanation unit can provide a brief and to the point explanation. For example, when the customer shows interest, the explanation unit explains the features and advantages of the product in detail. When the customer feels anxious, the explanation unit provides a polite and friendly response to give a sense of security. When the customer is in a hurry, the explanation unit provides a brief and to the point explanation and provides information quickly. As a result, the agent system according to the embodiment can perform an appropriate product explanation or demonstration according to the customer's emotions. A part or all of the above-mentioned processing in the explanation unit may be performed using, for example, AI, or may be performed without using AI. For example, the explanation unit can perform an explanation or demonstration using an AI model that inputs the customer's emotions estimated by the estimation unit and outputs a product explanation or demonstration. Specifically, the AI ​​model generates optimal explanation content according to the customer's emotions and provides appropriate information to the customer. For example, if a customer shows interest, the AI ​​model generates a detailed description of the product and explains the product's features and advantages to the customer. If the customer is anxious, the AI ​​model generates a polite explanation to reassure the customer and provides a friendly response to the customer. If the customer is in a hurry, the AI ​​model generates a concise and to-the-point explanation and provides information quickly. This allows the explanation department to provide appropriate product explanations and demonstrations according to the customer's emotions, thereby improving customer satisfaction. Furthermore, the explanation department can collect customer feedback and continuously improve the accuracy and effectiveness of the explanation content. For example, based on the customer's reactions and opinions, the explanation content is reviewed and improved to provide a more effective explanation. Furthermore, the explanation department can reliably transmit information using multiple communication methods. For example, important information is reliably delivered to the customer by using not only face-to-face explanations but also online chat, video calls, emails, etc. in combination. This allows the explanation department to provide information quickly and reliably to customers and improve customer satisfaction.

[0078] The explanation unit may include an adjustment unit that adjusts the content of the explanation according to the customer's reaction. The adjustment unit adjusts the content of the explanation according to the customer's reaction to the explanation or demonstration performed by the explanation unit. For example, if the customer feels that it is difficult to understand, the adjustment unit simplifies the explanation. In addition, if the customer is interested, the adjustment unit can also provide detailed information. Furthermore, if the customer feels anxious, the adjustment unit can provide an explanation that gives a sense of security. For example, if the customer feels that it is difficult to understand, the adjustment unit adjusts the level of detail of the explanation and uses simple words to provide an explanation. If the customer is interested, detailed information and advantages of the product are provided. If the customer feels anxious, a polite and friendly response is provided to give a sense of security. This enables the adjustment unit to respond flexibly according to the customer's reaction. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can adjust the content of the explanation using an AI model that uses customer reaction data as an input and adjusts the content of the explanation.

[0079] The explanation unit can perform a product explanation or demonstration in a manner according to the customer's emotions. The manner according to the customer's emotions includes, for example, at least one of the following: language, tone, topic, tone of voice, gestures, facial expressions, content, speed, timing, and pauses, but is not limited to such examples. For example, when the customer is relaxed, the explanation unit performs an explanation in a friendly manner. Also, when the customer is nervous, the explanation unit can perform an explanation in a calm tone. Furthermore, when the customer is excited, the explanation unit can perform an explanation in an energetic tone. For example, when the customer is relaxed, the explanation unit performs an explanation in a gentle tone of voice. When the customer is nervous, the explanation unit performs an explanation in a calm tone of voice. When the customer is excited, the explanation unit performs an explanation in a lively tone of voice. This enables the explanation unit to respond appropriately according to the customer's emotions. Part or all of the above-mentioned processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can perform an explanation or demonstration using an AI model that uses customer emotion data as input and performs a product explanation or demonstration in an appropriate manner.

[0080] The explanation unit can perform a product explanation or demonstration according to the customer's emotions and attributes. The customer's attributes include, but are not limited to, for example, age, sex, and purchase history. For example, if the customer is a young person, the explanation unit can perform the explanation using language and topics suitable for young people. In addition, if the customer is an elderly person, the explanation unit can also perform the explanation using language and topics suitable for elderly people. Furthermore, the explanation unit can suggest products that the customer is likely to be interested in based on the customer's purchase history. For example, if the customer is a young person, the explanation unit can perform the explanation using casual language and topics related to trends. If the customer is an elderly person, the explanation unit can perform the explanation using polite language and topics related to health. Based on the customer's purchase history, a new product related to a product that the customer has previously purchased is suggested. This enables the explanation unit to respond appropriately according to the customer's emotions and attributes. Part or all of the above-mentioned processing in the explanation unit may be performed using, for example, AI, or may be performed without using AI. For example, the explanation unit can perform an explanation or demonstration using an AI model that inputs the customer's emotion data and attribute data and performs an appropriate product explanation or demonstration.

[0081] The product explanation robot can function as a product explanation robot including an acquisition unit, an estimation unit, and an explanation unit. The product explanation robot includes an acquisition unit, an estimation unit, and an explanation unit. The acquisition unit acquires emotion estimation information for estimating the emotion of a customer. The estimation unit estimates the emotion of the customer based on the emotion estimation information acquired by the acquisition unit. The explanation unit performs a product explanation or demonstration according to the emotion of the customer estimated by the estimation unit. For example, the product explanation robot captures the facial expression of the customer using a camera and acquires it as emotion estimation information. The customer's movement can also be detected using a sensor and acquired as emotion estimation information. The customer's voice can also be captured using a microphone and acquired as emotion estimation information. The estimation unit analyzes the emotion estimation information using AI and estimates the emotion of the customer. The explanation unit performs a product explanation or demonstration according to the emotion of the customer estimated by the estimation unit. This enables the product explanation robot to respond appropriately according to the emotion of the customer, and sales support is effectively performed. A part or all of the above-mentioned processing in the product explanation robot may be performed using AI, for example, or may be performed without using AI. For example, a product explanation robot can provide explanations or demonstrations using an AI model that takes customer emotional data as input and delivers an appropriate product explanation or demonstration.

[0082] The acquisition unit can acquire one or more pieces of information among the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content as emotion estimation information. For example, the acquisition unit captures the customer's facial expression using a camera and acquires it as emotion estimation information. The acquisition unit can also detect the customer's movement using a sensor and acquire it as emotion estimation information. Furthermore, the acquisition unit can capture the customer's voice using a microphone and acquire it as emotion estimation information. For example, the acquisition unit captures the customer's facial expression with a camera and analyzes the facial expression using face recognition technology. The sensor detects the customer's movement and analyzes the movement using a movement analysis algorithm. The microphone captures the customer's voice and analyzes the voice using voice recognition technology. As a result, the acquisition unit acquires various information as emotion estimation information, thereby improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input facial expression data of a customer to the generation AI and have the generation AI execute emotion estimation information from the facial expression data.

[0083] The acquisition unit can acquire the facial expression of the customer and use it as emotion estimation information. For example, when the customer smiles, the acquisition unit captures the facial expression with a camera and acquires it as emotion estimation information. In addition, when the customer frowns, the acquisition unit can also capture the facial expression with a camera and acquire it as emotion estimation information. Furthermore, when the customer has no facial expression, the acquisition unit can capture the facial expression with a camera and acquire it as emotion estimation information. For example, the acquisition unit captures the facial expression of the customer with a camera and analyzes the facial expression using face recognition technology. As a result, the acquisition unit uses the facial expression of the customer as emotion estimation information, thereby improving the accuracy of emotion estimation. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI or may be performed without using AI. For example, the acquisition unit can input the facial expression data of the customer to the generation AI and cause the generation AI to execute the emotion estimation information from the facial expression data.

[0084] The acquisition unit can acquire the customer's motion and use it as emotion estimation information. For example, when the customer has folded his / her arms, the acquisition unit detects the motion with a sensor and acquires it as emotion estimation information. In addition, when the customer frequently scratches his / her head, the acquisition unit can also detect the motion with a sensor and acquire it as emotion estimation information. In addition, when the customer has crossed his / her legs, the acquisition unit can detect the motion with a sensor and acquire it as emotion estimation information. For example, the acquisition unit detects the customer's motion with a sensor and analyzes the motion using a motion analysis algorithm. As a result, the acquisition unit uses the customer's motion as emotion estimation information, thereby improving the accuracy of emotion estimation. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input the customer's motion data to the generation AI and cause the generation AI to execute emotion estimation information from the motion data.

[0085] The acquisition unit can acquire the voice of the customer and use it as emotion estimation information. For example, when the customer speaks in a high voice, the acquisition unit captures the voice with a microphone and acquires it as emotion estimation information. In addition, when the customer speaks in a low voice, the acquisition unit can also capture the voice with a microphone and acquire it as emotion estimation information. In addition, when the customer speaks quickly, the acquisition unit can capture the voice with a microphone and acquire it as emotion estimation information. For example, the acquisition unit captures the voice of the customer with a microphone and analyzes the voice using a voice recognition technology. As a result, the acquisition unit uses the voice of the customer as emotion estimation information, thereby improving the accuracy of emotion estimation. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input the voice data of the customer to a generation AI and cause the generation AI to execute emotion estimation information from the voice data.

[0086] The acquisition unit can acquire the heart rate of the customer and use it as emotion estimation information. For example, when the customer's heart rate is fast, the acquisition unit acquires the heart rate data with a sensor and uses it as emotion estimation information. When the customer's heart rate is slow, the acquisition unit can also acquire the heart rate data with a sensor and use it as emotion estimation information. When the customer's heart rate is irregular, the acquisition unit can acquire the heart rate data with a sensor and use it as emotion estimation information. For example, the acquisition unit detects the customer's heart rate with a sensor and analyzes the heart rate using a heart rate analysis algorithm. As a result, the acquisition unit uses the customer's heart rate as emotion estimation information, thereby improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the acquisition unit can input the customer's heart rate data to the generation AI and cause the generation AI to execute emotion estimation information from the heart rate data.

[0087] The acquisition unit can acquire the blood pressure of the customer and use it as emotion estimation information. For example, when the customer's blood pressure is high, the acquisition unit acquires the blood pressure data with a sensor and uses it as emotion estimation information. In addition, when the customer's blood pressure is low, the acquisition unit can acquire the blood pressure data with a sensor and use it as emotion estimation information. In addition, when the customer's blood pressure fluctuates, the acquisition unit can acquire the blood pressure data with a sensor and use it as emotion estimation information. For example, the acquisition unit detects the customer's blood pressure with a sensor and analyzes the blood pressure using a blood pressure analysis algorithm. As a result, the acquisition unit uses the customer's blood pressure as emotion estimation information, thereby improving the accuracy of emotion estimation. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input the customer's blood pressure data to the generation AI and cause the generation AI to execute emotion estimation information from the blood pressure data.

[0088] The acquisition unit can acquire the pupillary response of the customer and use it as emotion estimation information. For example, when the customer's pupil is dilated, the acquisition unit captures the pupillary response with a camera and uses it as emotion estimation information. In addition, when the customer's pupil is constricted, the acquisition unit can capture the pupillary response with a camera and use it as emotion estimation information. In addition, when the customer's pupil is fluctuating, the acquisition unit can capture the pupillary response with a camera and use it as emotion estimation information. For example, the acquisition unit captures the customer's pupillary response with a camera and analyzes the pupillary response using a pupillary response analysis algorithm. As a result, the acquisition unit uses the customer's pupillary response as emotion estimation information, thereby improving the accuracy of emotion estimation. Part or all of the above-mentioned processing in the acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the acquisition unit can input the customer's pupillary response data to the generation AI and cause the generation AI to execute emotion estimation information from the pupillary response data.

[0089] The estimation unit can estimate the emotion based on the facial expression of the customer. For example, if the customer smiles, the estimation unit estimates that the customer has a positive emotion. Also, if the customer frowns, the estimation unit can estimate that the customer has a negative emotion. Furthermore, if the customer has no facial expression, the estimation unit can estimate that the customer has a neutral emotion. For example, the estimation unit uses AI to analyze facial expression data of the customer and estimate the emotion. As a result, the estimation unit estimates the emotion based on the customer's facial expression, thereby improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input facial expression data of the customer to a generation AI and estimate the emotion from the facial expression data.

[0090] The estimation unit can estimate the emotion based on the customer's behavior. For example, if the customer has folded arms, the estimation unit estimates that the customer has a defensive emotion. Also, if the customer frequently scratches his head, the estimation unit can estimate that the customer is confused. Furthermore, if the customer has crossed legs, the estimation unit can estimate that the customer is relaxed. For example, the estimation unit uses AI to analyze the customer's behavior data and estimate the emotion. As a result, the estimation unit estimates the emotion based on the customer's behavior, thereby improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the estimation unit may be performed using AI, for example, or may be performed without using AI. For example, the estimation unit can input the customer's behavior data to a generation AI and estimate the emotion from the behavior data.

[0091] The estimation unit can estimate the emotion based on the customer's voice. For example, if the customer speaks in a high-pitched voice, the estimation unit estimates that the customer is excited. Also, if the customer speaks in a low-pitched voice, the estimation unit can estimate that the customer is calm. Furthermore, if the customer speaks quickly, the estimation unit can estimate that the customer is nervous. For example, the estimation unit uses AI to analyze the customer's voice data and estimate the emotion. As a result, the estimation unit estimates the emotion based on the customer's voice, improving the accuracy of the emotion estimation. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input the customer's voice data to a generation AI and estimate the emotion from the voice data.

[0092] The estimation unit can estimate the emotion based on the customer's heart rate. For example, if the customer's heart rate is fast, the estimation unit estimates that the customer is excited. Also, if the customer's heart rate is slow, the estimation unit can estimate that the customer is relaxed. Furthermore, if the customer's heart rate is irregular, the estimation unit can estimate that the customer is nervous. For example, the estimation unit uses AI to analyze the customer's heart rate data and estimate the emotion. As a result, the estimation unit estimates the emotion based on the customer's heart rate, thereby improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the estimation unit may be performed using AI, for example, or may be performed without using AI. For example, the estimation unit can input the customer's heart rate data to the generation AI and estimate the emotion from the heart rate data.

[0093] The estimation unit can estimate the emotion based on the customer's blood pressure. For example, when the customer's blood pressure is high, the estimation unit estimates that the customer is stressed. In addition, when the customer's blood pressure is low, the estimation unit can estimate that the customer is relaxed. Furthermore, when the customer's blood pressure fluctuates, the estimation unit can estimate that the customer is nervous. For example, the estimation unit uses AI to analyze the customer's blood pressure data and estimate the emotion. As a result, the estimation unit estimates the emotion based on the customer's blood pressure, improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input the customer's blood pressure data to the generation AI and estimate the emotion from the blood pressure data.

[0094] The estimation unit can estimate the emotion based on the customer's pupil response. For example, the estimation unit estimates that the customer is excited when the customer's pupil is dilated. The estimation unit can also estimate that the customer is relaxed when the customer's pupil is constricted. Furthermore, the estimation unit can estimate that the customer is nervous when the customer's pupil is fluctuating. For example, the estimation unit uses AI to analyze the customer's pupil response data and estimate the emotion. As a result, the estimation unit estimates the emotion based on the customer's pupil response, thereby improving the accuracy of emotion estimation. A part or all of the above-mentioned processing in the estimation unit may be performed using AI, for example, or may be performed without using AI. For example, the estimation unit can input the customer's pupil response data to the generation AI and estimate the emotion from the pupil response data.

[0095] The explanation unit can provide a product explanation according to the customer's emotions. For example, when the customer shows interest, the explanation unit provides a detailed product explanation. In addition, when the customer feels anxious, the explanation unit can also provide a polite and friendly response. Furthermore, when the customer is in a hurry, the explanation unit can provide a concise and to the point explanation. For example, when the customer shows interest, the explanation unit explains the features and advantages of the product in detail. When the customer feels anxious, the explanation unit provides a polite and friendly response to give a sense of security. When the customer is in a hurry, the explanation unit provides a concise and to the point explanation and provides information quickly. As a result, the explanation unit provides a product explanation according to the customer's emotions, thereby improving customer satisfaction. Part or all of the above-mentioned processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can provide an explanation using an AI model that uses customer emotion data as input and provides an appropriate product explanation.

[0096] The explanation unit can perform a demonstration according to the customer's emotions. For example, when the customer shows interest, the explanation unit performs a detailed demonstration. In addition, when the customer feels anxious, the explanation unit can also perform a polite and friendly demonstration. Furthermore, when the customer is in a hurry, the explanation unit can perform a concise and to the point demonstration. For example, when the customer shows interest, the explanation unit performs a detailed demonstration of the use method and advantages of the product. When the customer feels anxious, the explanation unit performs a polite and friendly demonstration to give a sense of security. When the customer is in a hurry, the explanation unit performs a concise and to the point demonstration to provide information quickly. As a result, the explanation unit performs a demonstration according to the customer's emotions, thereby improving customer satisfaction. Part or all of the above-mentioned processing in the explanation unit may be performed using, for example, AI, or may be performed without using AI. For example, the explanation unit can perform a demonstration using an AI model that inputs customer emotion data and performs an appropriate demonstration.

[0097] The explanation unit can explain the product in a manner that corresponds to the customer's emotions. For example, when the customer is relaxed, the explanation unit explains the product in a friendly manner. Also, when the customer is nervous, the explanation unit can explain the product in a calm manner. Furthermore, when the customer is excited, the explanation unit can explain the product in an energetic manner. For example, when the customer is relaxed, the explanation unit explains the product in a calm manner. When the customer is nervous, the explanation unit explains the product in a calm manner. When the customer is excited, the explanation unit explains the product in a lively manner. As a result, the explanation unit explains the product in a manner that corresponds to the customer's emotions, thereby improving customer satisfaction. Part or all of the above-mentioned processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can explain the product using an AI model that uses customer emotion data as input and explains the product in appropriate language.

[0098] The explanation unit can explain the product in a tone of voice according to the customer's emotions. For example, when the customer is relaxed, the explanation unit explains in a calm tone. Also, when the customer is nervous, the explanation unit can explain in a calm tone. Furthermore, when the customer is excited, the explanation unit can explain in a lively tone. For example, when the customer is relaxed, the explanation unit explains in a calm tone of voice. When the customer is nervous, the explanation unit explains in a calm tone of voice. When the customer is excited, the explanation unit explains in a lively tone of voice. As a result, the explanation unit explains the product in a tone of voice according to the customer's emotions, thereby improving customer satisfaction. Part or all of the above-mentioned processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can explain the product using an AI model that uses customer emotion data as input and explains the product in an appropriate tone.

[0099] The explanation unit can explain the product using a topic according to the customer's emotions. For example, when the customer shows interest, the explanation unit introduces a related topic to explain. In addition, when the customer feels anxious, the explanation unit can also introduce a topic that gives a sense of security to explain. Furthermore, when the customer is in a hurry, the explanation unit can also explain using a topic that focuses on the main points. For example, when the customer shows interest, the explanation unit introduces a topic related to the features and advantages of the product to explain. When the customer feels anxious, the explanation unit introduces a polite and friendly topic to give a sense of security to explain. When the customer is in a hurry, the explanation unit introduces a concise topic that focuses on the main points to provide information quickly. As a result, the explanation unit explains the product using a topic according to the customer's emotions, thereby improving customer satisfaction. Part or all of the above-mentioned processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can explain the product using an AI model that uses customer emotion data as input and explains the product using appropriate topics.

[0100] The explanation unit can explain the product in a tone of voice according to the customer's emotions. For example, when the customer is relaxed, the explanation unit explains in a calm tone of voice. Also, when the customer is nervous, the explanation unit can explain in a calm tone of voice. Furthermore, when the customer is excited, the explanation unit can explain in a lively tone of voice. For example, when the customer is relaxed, the explanation unit explains in a calm tone of voice. When the customer is nervous, the explanation unit explains in a calm tone of voice. When the customer is excited, the explanation unit explains in a lively tone of voice. As a result, the explanation unit explains the product in a tone of voice according to the customer's emotions, thereby improving customer satisfaction. Part or all of the above-mentioned processing in the explanation unit may be performed, for example, using AI, or may be performed without using AI. For example, the explanation unit can explain the product using an AI model that uses customer emotion data as input and explains the product in an appropriate tone of voice.

[0101] The adjustment unit can adjust the content of the explanation according to the customer's reaction. For example, if the customer feels that it is difficult to understand, the adjustment unit simplifies the explanation. In addition, if the customer is interested, the adjustment unit can also provide detailed information. Furthermore, if the customer feels anxious, the adjustment unit can provide an explanation that gives a sense of security. For example, if the customer feels that it is difficult to understand, the adjustment unit adjusts the level of detail of the explanation and uses simple words to provide an explanation. If the customer is interested, detailed information and advantages of the product are provided. If the customer feels anxious, a polite and friendly response is provided to give a sense of security. This enables the adjustment unit to adjust the content of the explanation according to the customer's reaction. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can adjust the content of the explanation using an AI model that uses customer reaction data as an input and adjusts the content of the explanation.

[0102] The adjustment unit can adjust the speed of the explanation according to the customer's reaction. For example, when the customer is in a hurry, the adjustment unit speeds up the speed of the explanation. Also, when the customer is relaxed, the adjustment unit can slow down the speed of the explanation. Furthermore, when the customer feels that it is difficult to understand, the adjustment unit can adjust the speed of the explanation. For example, when the customer is in a hurry, the adjustment unit speeds up the speed of the explanation to provide information quickly. When the customer is relaxed, the adjustment unit slows down the speed of the explanation to provide a careful explanation. When the customer feels that it is difficult to understand, the adjustment unit adjusts the speed of the explanation to make it easy to understand. This enables the adjustment unit to adjust the speed of the explanation according to the customer's reaction. A part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can adjust the speed of the explanation using an AI model that uses customer reaction data as input and adjusts the speed of the explanation.

[0103] The adjustment unit can adjust the timing of the explanation according to the customer's reaction. For example, when the customer asks a question, the adjustment unit provides an explanation at that timing. In addition, when the customer shows interest, the adjustment unit can also provide a detailed explanation at that timing. Furthermore, when the customer feels that it is difficult to understand, the adjustment unit can also simplify the explanation at that timing. For example, when the customer asks a question, the adjustment unit provides an explanation at that timing to resolve the customer's doubts. When the customer shows interest, the adjustment unit provides a detailed explanation at that timing to keep the customer's interest. When the customer feels that it is difficult to understand, the adjustment unit simplifies the explanation at that timing to make it easier to understand. This enables the adjustment unit to adjust the timing of the explanation according to the customer's reaction. A part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can adjust the timing of the explanation using an AI model that uses customer reaction data as an input and adjusts the timing of the explanation.

[0104] The adjustment unit can adjust the interval between explanations according to the customer's reaction. For example, when the customer is thinking deeply, the adjustment unit lengthens the interval between explanations. In addition, when the customer is in a hurry, the adjustment unit can also shorten the interval between explanations. Furthermore, when the customer feels that it is difficult to understand, the adjustment unit can adjust the interval between explanations. For example, when the customer is thinking deeply, the adjustment unit lengthens the interval between explanations to give the customer time to think. When the customer is in a hurry, the adjustment unit shortens the interval between explanations to provide information quickly. When the customer feels that it is difficult to understand, the adjustment unit adjusts the interval between explanations to make it easier to understand. This enables the adjustment unit to adjust the interval between explanations according to the customer's reaction. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can adjust the interval between explanations using an AI model that uses customer reaction data as input and adjusts the interval between explanations.

[0105] The adjustment unit can adjust the content of the explanation according to the customer's reaction. For example, if the customer feels that it is difficult to understand, the adjustment unit simplifies the content of the explanation. In addition, if the customer is interested, the adjustment unit can also provide detailed information. Furthermore, if the customer feels anxious, the adjustment unit can provide an explanation that gives a sense of security. For example, if the customer feels that it is difficult to understand, the adjustment unit simplifies the content of the explanation to make it easier to understand. If the customer is interested, detailed information and advantages of the product are provided. If the customer feels anxious, a polite and friendly response is provided to give a sense of security. This enables the adjustment unit to adjust the content of the explanation according to the customer's reaction. Part or all of the above-mentioned processing in the adjustment unit may be performed, for example, using AI, or may be performed without using AI. For example, the adjustment unit can adjust the content of the explanation using an AI model that uses customer reaction data as an input and adjusts the content of the explanation.

[0106] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0107] The agent system may further include a history analysis unit that analyzes the purchase history of the customer. The history analysis unit acquires the past purchase history of the customer and estimates the customer's interests and concerns. For example, the history analysis unit may analyze data on products and services purchased by the customer in the past and estimate products that the customer may be interested in. The estimation unit may estimate the customer's emotions in a complementary manner based on the customer's interests estimated by the history analysis unit. For example, the estimation unit may estimate the customer's emotions more accurately when proposing a new product related to a product purchased by the customer in the past. This allows the agent system to provide a more personalized product explanation or demonstration based on the customer's purchase history.

[0108] The adjustment unit can not only adjust the content of the explanation according to the customer's reaction, but also customize the information to be provided at the customer's next visit based on the customer's reaction. For example, if the customer shows interest in a particular product, the adjustment unit can record that information and provide related information on new products and services at the customer's next visit. Also, if the customer finds it difficult to understand a particular function, the adjustment unit can record that information and provide a more easily understandable explanation at the customer's next visit. Furthermore, if the customer asks a particular question, the adjustment unit can provide a detailed answer to that question at the customer's next visit. This allows the adjustment unit to continuously customize based on the customer's reaction.

[0109] The explanation unit can not only provide a product explanation or demonstration in a manner according to the customer's emotions, but also provide interactive quizzes and questionnaires according to the customer's emotions. For example, if the customer shows interest, the explanation unit can provide a quiz on the features and advantages of the product to check the customer's level of understanding. If the customer feels anxious, the explanation unit can provide a questionnaire to reassure the customer and reduce the customer's anxiety. Furthermore, if the customer feels relaxed, the explanation unit can provide a fun interactive game to keep the customer interested. In this way, the explanation unit can provide an interactive experience according to the customer's emotions.

[0110] The explanation department can not only provide product explanations or demonstrations according to the customer's emotions and attributes, but also provide special offers and discounts based on the customer's attributes. For example, the explanation department can provide student discounts and special offers for new customers to younger customers. Also, the explanation department can suggest senior discounts and health-related products to older customers. Furthermore, the explanation department can provide special discounts and point programs for repeat customers based on the customer's purchase history. In this way, the explanation department can improve customer satisfaction by providing special offers according to the customer's attributes.

[0111] The product explanation robot may not only include an acquisition unit, an estimation unit, and an explanation unit, but also may be provided with a feedback collection unit that collects customer feedback. The feedback collection unit may collect how the customer felt about the product explanation or demonstration, and use the collected information to improve the system. For example, the feedback collection unit may collect in the form of a questionnaire whether the customer is satisfied with the product explanation. It may also collect which parts the customer found interesting and which parts were difficult to understand. It may also collect improvements and new ideas suggested by the customer. This allows the product explanation robot to be continuously improved based on customer feedback.

[0112] The acquisition unit can acquire one or more pieces of information from among the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content as emotion estimation information, and can also acquire the customer's location information and environmental information. For example, the acquisition unit can acquire the area in which the customer is located by GPS and provide information related to the area. The acquisition unit can also acquire the temperature and humidity of the environment in which the customer is located by a sensor and estimate the customer's comfort level based on the information. Furthermore, the acquisition unit can acquire the noise level in the location in which the customer is located and provide a description of a quiet environment. In this way, the acquisition unit can perform emotion estimation with higher accuracy by using the customer's location information and environmental information.

[0113] The acquisition unit can not only acquire the facial expression of the customer and use it as emotion estimation information, but also monitor changes in the customer's facial expression in real time. For example, when a customer changes from a smile to a serious expression, the acquisition unit can detect the change in real time and use it as emotion estimation information. Also, when a customer frowns and then smiles, the acquisition unit can detect the change and estimate the emotion change. Furthermore, when a customer changes from a neutral expression to a surprised expression, the acquisition unit can detect the change and estimate the emotion change. In this way, the acquisition unit can perform more accurate emotion estimation by monitoring the change in the customer's facial expression in real time.

[0114] The acquisition unit can acquire the customer's movements and use them as emotion estimation information, as well as analyze the customer's movement patterns. For example, if the customer frequently crosses his / her arms, the acquisition unit can analyze the movement pattern and estimate a defensive emotion. If the customer frequently scratches his / her head, the acquisition unit can analyze the movement pattern and estimate that the customer is confused. If the customer frequently crosses his / her legs, the acquisition unit can analyze the movement pattern and estimate that the customer is relaxed. In this way, the acquisition unit can perform more accurate emotion estimation by analyzing the customer's movement patterns.

[0115] The acquisition unit can acquire the voice of the customer and use it as emotion estimation information, and can also analyze the tone and rhythm of the customer's voice. For example, if the customer speaks in a high-pitched voice, the acquisition unit can analyze the tone of the voice and estimate that the customer is excited. Also, if the customer speaks in a low-pitched voice, the acquisition unit can analyze the tone of the voice and estimate that the customer is calm. Furthermore, if the customer speaks quickly, the acquisition unit can analyze the rhythm of the voice and estimate that the customer is nervous. In this way, the acquisition unit can perform more accurate emotion estimation by analyzing the tone and rhythm of the customer's voice.

[0116] The acquisition unit can not only acquire the heart rate of the customer and use it as emotion estimation information, but also monitor the fluctuations in the customer's heart rate in real time. For example, if the customer's heart rate suddenly speeds up, the acquisition unit can detect the fluctuations in real time and estimate that the customer is excited. Also, if the customer's heart rate suddenly slows down, the acquisition unit can detect the fluctuations and estimate that the customer is relaxed. Furthermore, if the customer's heart rate becomes irregular, the acquisition unit can detect the fluctuations and estimate that the customer is nervous. In this way, the acquisition unit can perform more accurate emotion estimation by monitoring the fluctuations in the customer's heart rate in real time.

[0117] The process flow of the second embodiment will be briefly described below.

[0118] Step 1: The acquisition unit acquires emotion estimation information for estimating the emotion of a customer. The emotion estimation information includes the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwaves, body temperature, breathing, and posted content. For example, the customer's facial expression is captured using a camera, the customer's movement is detected using a sensor, and the customer's voice is captured using a microphone. Step 2: The estimation unit estimates the customer's emotions based on the emotion estimation information acquired by the acquisition unit. For example, the estimation unit uses AI to analyze the emotion estimation information and estimate the customer's emotions. If the customer smiles, it is estimated that the customer has a positive emotion, if the customer frowns, it is estimated that the customer has a negative emotion, and if the customer has no expression, it is estimated that the customer has a neutral emotion. Step 3: The explanation unit performs a product explanation or demonstration according to the customer's emotions estimated by the estimation unit. For example, if the customer is interested, a detailed product explanation is performed, if the customer is anxious, a polite and friendly response is performed, and if the customer is in a hurry, a brief explanation is performed that focuses on the main points.

[0119] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0120] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0121] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0122] For example, the acquisition unit can acquire the facial expression and voice of the customer using the camera 42 and microphone 38B of the smart device 14. The estimation unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the acquired emotion estimation information to estimate the emotion of the customer. The explanation unit is realized by the control unit 46A of the smart device 14, and performs product explanation and demonstration based on the estimated emotion. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0123] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0124] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0125] 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, the RAM 30, and the 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.

[0126] 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.

[0127] 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 the voice according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0129] 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 performed in a secure state.

[0130] Fig. 4 shows an example of 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.

[0131] 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.

[0132] 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0133] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0134] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0135] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0136] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0137] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0138] For example, the acquisition unit can acquire the facial expression and voice of the customer using the camera 42 and microphone 238 of the smart glasses 214. The estimation unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the acquired emotion estimation information to estimate the emotion of the customer. The explanation unit is realized by the control unit 46A of the smart glasses 214, and performs product explanation and demonstration based on the estimated emotion. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0139] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0140] 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.

[0141] 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, the RAM 30, and the 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.

[0142] 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.

[0143] 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 the voice according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0145] 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 performed in a secure state.

[0146] 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.

[0147] 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.

[0148] 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0149] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 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 identification processing unit 290 using these models.

[0150] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0151] 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 voice indicating a user input for 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.

[0152] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0153] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0154] For example, the acquisition unit can acquire the facial expression and voice of the customer using the camera 42 and microphone 238 of the headset terminal 314. The estimation unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the acquired emotion estimation information to estimate the emotion of the customer. The explanation unit is realized by the control unit 46A of the headset terminal 314, and performs product explanation and demonstration based on the estimated emotion. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0155] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0156] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0157] 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, the RAM 30, and the 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.

[0158] 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.

[0159] 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 the voice according to instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0161] 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 performed in a secure state.

[0162] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0163] 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.

[0164] 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.

[0165] 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 emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0166] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0167] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0168] 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 a voice indicating a user input for 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.

[0169] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0170] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0171] For example, the acquisition unit can acquire the facial expression and voice of the customer using the camera 42 and microphone 238 of the robot 414. The estimation unit is realized by the specific processing unit 290 of the data processing device 12, and analyzes the acquired emotion estimation information to estimate the emotion of the customer. The explanation unit is realized by the control unit 46A of the robot 414, and performs product explanation and demonstration based on the estimated emotion. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0172] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0173] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0174] These emotions are distributed in the three o'clock direction of emotion map 400 and usually 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.

[0175] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0176] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0177] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0178] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0179] 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.

[0180] 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 Universal Serial Bus (USB) 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.

[0181] In addition, 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 upon request from the data processing device 12.

[0182] 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.

[0183] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0184] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0185] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0186] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0187] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0188] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0189] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0190] (Appendix 1) An acquisition unit that acquires emotion estimation information for estimating an emotion of a customer; an estimation unit that estimates an emotion of the customer based on the emotion estimation information acquired by the acquisition unit; An explanation unit that performs a product explanation or demonstration according to the emotion of the customer estimated by the estimation unit. system. (Appendix 2) An adjustment unit adjusts the content of the explanation in response to the customer's reaction to the explanation or demonstration performed by the explanation unit. system. (Appendix 3) The explanation section includes: Explain or demonstrate products in a way that responds to customer emotions 2. The system of claim 1, (Appendix 4) The explanation section includes: Provide product explanations or demonstrations that respond to customer emotions and attributes 2. The system of claim 1, (Appendix 5) The robot functions as a product explanation robot including the acquisition unit, the estimation unit, and the explanation unit. 2. The system of claim 1, (Appendix 6) The acquisition unit is One or more pieces of information among the customer's facial expressions, movements, voice, heart rate, blood pressure, pupil response, brain waves, body temperature, breathing, and posted content are acquired as emotion estimation information. 2. The system of claim 1, (Appendix 7) The acquisition unit is Acquire customer facial expressions and use them as emotion estimation information 2. The system of claim 1, (Appendix 8) The acquisition unit is Obtaining customer behavior and using it as emotion estimation information 2. The system of claim 1, (Appendix 9) The acquisition unit is Acquire customer voice and use it as information for estimating emotions 2. The system of claim 1, (Appendix 10) The acquisition unit is Obtaining the customer's heart rate and using it as information for estimating emotions 2. The system of claim 1, (Appendix 11) The acquisition unit is Obtaining the customer's blood pressure and using it as information for estimating emotions 2. The system of claim 1, (Appendix 12) The acquisition unit is Obtaining the customer's pupil response and using it as information for estimating emotions 2. The system of claim 1, (Appendix 13) The estimation unit is Inferring customer emotions based on facial expressions 2. The system of claim 1, (Appendix 14) The estimation unit is Inferring customer sentiment based on behavior 2. The system of claim 1, (Appendix 15) The estimation unit is Inferring sentiment based on customer voice 2. The system of claim 1, (Appendix 16) The estimation unit is Inferring customer sentiment based on their heart rate 2. The system of claim 1, (Appendix 17) The estimation unit is Inferring customer sentiment based on their blood pressure 2. The system of claim 1, (Appendix 18) The estimation unit is Infer customer emotions based on pupil response 2. The system of claim 1, (Appendix 19) The explanation section includes: Explain products based on customer emotions 2. The system of claim 1, (Appendix 20) The explanation section includes: Demonstrate customer emotions 2. The system of claim 1, (Appendix 21) The explanation section includes: Explain the product to customers using words that reflect their emotions 2. The system of claim 1, (Appendix 22) The explanation section includes: Explain the product to the customer in a tone that reflects their emotions 2. The system of claim 1, (Appendix 23) The explanation section includes: Explain the product to customers by using topics that respond to their emotions. 2. The system of claim 1, (Appendix 24) The explanation section includes: Explain products in a tone of voice that reflects the customer's emotions 2. The system of claim 1, (Appendix 25) The adjustment unit is Adapt your explanation based on customer response 3. The system of claim 2, (Appendix 26) The adjustment unit is Adjust the speed of your explanations based on customer responses 3. The system of claim 2, (Appendix 27) The adjustment unit is Adjust the timing of explanations according to customer reactions 3. The system of claim 2, (Appendix 28) The adjustment unit is Adjust the timing of your explanation based on the customer's response 3. The system of claim 2, (Appendix 29) The adjustment unit is Adjust your explanation based on customer response 3. The system of claim 2, [Explanation of symbols]

[0191] 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. An acquisition unit that acquires emotion estimation information for estimating an emotion of a customer; an estimation unit that estimates an emotion of the customer based on the emotion estimation information acquired by the acquisition unit; An explanation unit that performs a product explanation or demonstration according to the emotion of the customer estimated by the estimation unit. system.

2. An adjustment unit adjusts the content of the explanation in response to the customer's reaction to the explanation or demonstration performed by the explanation unit.

2. The system of claim 1 .

3. The explanation section includes: A product explanation or demonstration is performed in a manner that corresponds to the customer's emotions.

2. The system of claim 1 .

4. The explanation section includes: Provide a product explanation or demonstration according to the customer's emotions and attributes 2. The system of claim 1 .

5. The robot functions as a product explanation robot including the acquisition unit, the estimation unit, and the explanation unit.

2. The system of claim 1 .

6. The acquisition unit is One or more pieces of information among the customer's facial expression, movement, voice, heart rate, blood pressure, pupil response, brain wave, body temperature, respiration, and posted content are acquired as the emotion estimation information.

2. The system of claim 1 .

7. The acquisition unit is The facial expression of the customer is acquired and used as the emotion estimation information.

2. The system of claim 1 .

8. The acquisition unit is The customer's actions are acquired and used as emotion estimation information.

2. The system of claim 1 .

Images