System

Abstract

An object of a system according to an embodiment is to propose an optimum insurance product based on the needs of a customer and support a salesperson.SOLUTION: A system includes a customer needs analysis part, an insurance product proposal part, a sales support part, and a material generation part. A customer need analysis part analyzes the input contents of the customer. The insurance product proposal unit proposes an optimum insurance product based on the customer's needs analyzed by the customer needs analysis unit. The sales support unit provides advice to the salesperson based on the insurance product proposed by the insurance product proposal unit. A material generation part generates sales words and materials on the basis of the advice provided by the sales support part.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately support sales representatives by efficiently proposing insurance products that meet customer needs, and there is room for improvement.

[0005] The system according to the embodiment aims to propose optimal insurance products based on customer needs and support sales representatives. [Means for solving the problem]

[0006] The system according to the embodiment includes a customer needs analysis unit, an insurance product proposal unit, a sales support unit, and a material generation unit. The customer needs analysis unit analyzes the customer's input. The insurance product proposal unit proposes the most suitable insurance product based on the customer's needs analyzed by the customer needs analysis unit. The sales support unit provides advice to sales representatives based on the insurance products proposed by the insurance product proposal unit. The material generation unit generates sales language and materials based on the advice provided by the sales support unit. [Effects of the Invention]

[0007] The system according to the embodiment can propose optimal insurance products based on the needs of customers and support sales representatives. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An insurance sales system according to an embodiment of the present invention utilizes generative AI to propose insurance products that meet customer needs. This allows the insurance sales system to propose optimal insurance products based on customer needs, provide advice to sales representatives, and generate sales language and materials.

[0029] An insurance sales system according to an embodiment includes a customer needs analysis unit, an insurance product proposal unit, a sales support unit, and a material generation unit. The customer needs analysis unit analyzes customer input. For example, if a customer inputs, "I want insurance that covers my entire family," the generation AI analyzes the customer's needs and proposes insurance products that cover the entire family. The customer needs analysis unit can also analyze the customer's input using text mining technology. For example, the text mining technology can be used to extract and analyze customer needs. The insurance product proposal unit proposes optimal insurance products based on the customer's needs analyzed by the customer needs analysis unit. For example, if a customer inputs, "I want both health insurance and life insurance," the generation AI proposes insurance products that cover both health insurance and life insurance based on the customer's needs. The insurance product proposal unit can also refer to a database of insurance products to select products that best meet the customer's needs. For example, the insurance product proposal unit refers to a database of insurance products and selects products that meet the customer's needs. The sales support unit provides advice to sales representatives based on the insurance products proposed by the insurance product proposal unit. For example, the generation AI analyzes customer needs and provides the results to a sales representative, allowing the sales representative to provide more accurate advice to the customer. The sales support unit can also suggest optimal sales language and approaches to the customer to the sales representative. For example, the generation AI suggests optimal sales language and approaches to the customer to the sales representative. The material generation unit generates sales language and materials based on the advice provided by the sales support unit. For example, the generation AI generates sales language that clearly explains the features and benefits of an insurance product based on the customer's needs. The material generation unit can also create materials to provide to the customer, which the sales representative can use to explain the product to the customer. For example, the generation AI creates materials to provide to the customer, which the sales representative can use to explain the product to the customer. As a result, the insurance sales system according to the embodiment can suggest optimal insurance products based on customer needs, provide advice to the sales representative, and generate sales language and materials.For example, customers can quickly find insurance products that meet their needs, sales representatives can provide more accurate advice, and sales language and materials created by generative AI can be used to explain things to customers more easily, improving the success rate of contracts.

[0030] The customer needs analysis unit can predict potential needs by analyzing purchase history and behavioral patterns based on the customer's input. For example, the customer needs analysis unit uses a generation AI to analyze past purchase history based on the content entered by the customer and predicts potential needs by referring to data on other customers with similar purchasing patterns. For example, the customer needs analysis unit predicts what kind of insurance product a customer who previously purchased family insurance will seek next. The customer needs analysis unit can also collect website browsing history and clickstream data to analyze customer behavioral patterns in order to analyze behavioral patterns. For example, it can analyze what pages a customer views and what links they click to predict potential needs. The customer needs analysis unit can also use a machine learning algorithm to analyze customer behavioral patterns and predict potential needs. For example, it can use a machine learning algorithm to analyze customer behavioral patterns and predict potential needs. By predicting the customer's potential needs, it can propose more appropriate insurance products.

[0031] The customer needs analysis unit can predict future needs by taking into account the customer's life events. For example, the customer needs analysis unit predicts future needs by having the generation AI take into account life events such as marriage and childbirth based on the information entered by the customer. For example, it can propose family insurance products to a customer who is about to get married. The customer needs analysis unit can also analyze the customer's life stage and long-term goals to take life events into account. For example, it can analyze the customer's life stage and long-term goals to predict future needs. The customer needs analysis unit can also predict future needs by taking into account the customer's life events from the perspective of risk management. For example, it can analyze the risks the customer may face and predict future needs. In this way, it can predict future needs by taking the customer's life events into account and propose more appropriate insurance products.

[0032] The customer needs analysis unit can also accept voice and image input, allowing it to understand needs from a wider variety of information sources. For example, the customer needs analysis unit analyzes what the customer inputs via voice, and the generation AI understands their needs from that voice data. For example, if a customer says, "I want insurance that covers my entire family," the voice data is analyzed to suggest appropriate insurance products. The customer needs analysis unit can also accept image input, allowing it to analyze what the customer inputs via image. For example, if a customer uploads an image of their insurance policy, the image data is analyzed to suggest appropriate insurance products. The customer needs analysis unit can also use voice recognition technology to convert the customer's voice data into text data and analyze that text data. For example, it can use voice recognition technology to convert the customer's voice data into text data and analyze that text data to understand their needs. This allows it to accept voice and image input, allowing it to understand customer needs from a wider variety of information sources.

[0033] The customer needs analysis unit compares the needs of the customer with those of other customers and identifies common needs, thereby enabling more general proposals to be made. For example, the customer needs analysis unit compares the results of the customer's needs analysis with those of other customers and identifies common needs. For example, if multiple customers input "I want insurance that covers my entire family," the customer needs analysis unit proposes general insurance products based on that common need. The customer needs analysis unit can also use clustering technology to group customer needs and identify common needs. For example, the customer needs analysis unit can use clustering technology to group customer needs and identify common needs. The customer needs analysis unit can also use pattern recognition technology to analyze customer needs and identify common needs. For example, the customer needs analysis unit can use pattern recognition technology to analyze customer needs and identify common needs. This allows more general proposals to be made by comparing the needs of the customer with those of other customers.

[0034] The insurance product proposal unit can select the most suitable insurance product by taking into consideration the customer's health condition and lifestyle. For example, the insurance product proposal unit uses a generation AI to select the most suitable insurance product by taking into consideration the customer's health condition and lifestyle. For example, the insurance product proposal unit can propose a health insurance product based on health checkup results and lifestyle data. The insurance product proposal unit can also set criteria for evaluating the customer's health condition and lifestyle and select the most suitable insurance product based on those criteria. For example, the insurance product proposal unit can evaluate the health checkup results and lifestyle data and select the most suitable insurance product based on the evaluation results. The insurance product proposal unit can also analyze data collected from a wearable device to evaluate the customer's health condition and lifestyle. For example, the insurance product proposal unit can analyze data collected from a wearable device to evaluate the customer's health condition and lifestyle, and select the most suitable insurance product based on the evaluation results. This allows the most suitable insurance product to be selected by taking into consideration the customer's health condition and lifestyle.

[0035] The insurance product proposal unit can compare products from different insurance companies and select the most suitable product. For example, the generation AI in the insurance product proposal unit compares products from different insurance companies and selects the most suitable insurance product. For example, it refers to the databases of multiple insurance companies and proposes the most suitable product. The insurance product proposal unit can also compare the features and advantages of products offered by insurance companies and select the most suitable product based on the comparison results. For example, it compares the features and advantages of products offered by insurance companies and selects the most suitable product based on the comparison results. The insurance product proposal unit can also analyze evaluation data of insurance companies and select the most suitable product based on the evaluation results. For example, it analyzes evaluation data of insurance companies and selects the most suitable product based on the evaluation results. This makes it possible to compare products from different insurance companies and select the most suitable product.

[0036] The insurance product proposal unit can propose optimal products from a long-term perspective, taking into account the customer's family structure and future plans. For example, the generative AI in the insurance product proposal unit proposes optimal insurance products from a long-term perspective, taking into account the customer's family structure and future plans. For example, it proposes insurance products that take into account children's growth and education expenses. The insurance product proposal unit can also set criteria for evaluating the customer's family structure and future plans and propose optimal products based on those criteria. For example, it evaluates the customer's family structure and future plans and proposes optimal products based on the evaluation results. The insurance product proposal unit can also analyze the customer's life plan and career plan and propose optimal products based on the analysis results. For example, it analyzes the customer's life plan and career plan and proposes optimal products based on the analysis results. In this way, it is possible to propose optimal products from a long-term perspective by taking into account the customer's family structure and future plans.

[0037] The sales support department can analyze past sales data and propose approach methods with a high success rate. For example, the sales support department uses generative AI to analyze past sales data and propose approach methods with a high success rate. For example, the sales support department proposes the optimal approach method to customers based on sales methods that have been successful in the past. The sales support department can also set criteria for evaluating approach methods to customers based on sales data and propose the optimal approach method based on those criteria. For example, the sales support department can evaluate approach methods to customers based on sales data and propose the optimal approach method based on the evaluation results. The sales support department can also analyze sales data and develop algorithms for proposing approach methods with a high success rate. For example, the sales support department can develop algorithms for analyzing sales data and proposing approach methods with a high success rate. This makes it possible to propose approach methods with a high success rate by analyzing past sales data.

[0038] The sales support department can provide personalized advice by taking into account a customer's purchasing history and behavioral patterns. For example, the sales support department uses a generative AI to provide personalized advice by taking into account a customer's purchasing history and behavioral patterns. For example, the sales support department can suggest the optimal approach to a customer based on past purchase history. The sales support department can also set criteria for evaluating a customer's purchasing history and behavioral patterns and provide personalized advice based on those criteria. For example, the sales support department can evaluate a customer's purchasing history and behavioral patterns and provide personalized advice based on the evaluation results. The sales support department can also analyze a customer's purchasing history and behavioral patterns and develop an algorithm for providing personalized advice. For example, the sales support department can analyze a customer's purchasing history and behavioral patterns and develop an algorithm for providing personalized advice. This makes it possible to provide personalized advice by taking into account a customer's purchasing history and behavioral patterns.

[0039] The sales support department can propose a region-specific approach method by taking into account the customer's region and cultural background. For example, the sales support department uses generative AI to propose a region-specific approach method by taking into account the customer's region and cultural background. For example, it proposes sales methods that are tailored to the local culture and customs. The sales support department can also set criteria for evaluating the customer's region and cultural background and propose a region-specific approach method based on those criteria. For example, it can evaluate the customer's region and cultural background and propose a region-specific approach method based on the evaluation results. The sales support department can also develop an algorithm for analyzing the local culture and customs and proposing a region-specific approach method. For example, it can develop an algorithm for analyzing the local culture and customs and proposing a region-specific approach method. This makes it possible to propose a region-specific approach method by taking into account the customer's region and cultural background.

[0040] The material generation unit can generate effective sales language by referring to past success cases. In the material generation unit, for example, a generation AI refers to past success cases to generate effective sales language. For example, new language is generated based on sales language that has been successful in the past. The material generation unit can also set criteria for evaluating effective sales language based on success cases and generate language based on those criteria. For example, effective sales language is evaluated based on success cases and language is generated based on the evaluation results. The material generation unit can also analyze success cases and develop an algorithm for generating effective sales language. For example, an algorithm for analyzing success cases and generating effective sales language is developed. In this way, effective sales language can be generated by referring to past success cases.

[0041] The material generation unit can create materials that make use of easy-to-understand expressions and plenty of illustrations, taking into account the customer's level of understanding. For example, the generation AI in the material generation unit creates materials that make use of easy-to-understand expressions and plenty of illustrations, taking into account the customer's level of understanding. For example, the features of an insurance product are explained using illustrations. The material generation unit can also set criteria for evaluating the customer's level of understanding and create materials that make use of easy-to-understand expressions and plenty of illustrations based on those criteria. For example, it can evaluate the customer's level of understanding and create materials that make use of easy-to-understand expressions and plenty of illustrations based on the evaluation results. The material generation unit can also analyze the customer's level of understanding and develop an algorithm for creating materials that make use of easy-to-understand expressions and plenty of illustrations. For example, it can analyze the customer's level of understanding and develop an algorithm for creating materials that make use of easy-to-understand expressions and plenty of illustrations. This makes it possible to create materials that make use of easy-to-understand expressions and plenty of illustrations, taking into account the customer's level of understanding.

[0042] The material generation unit generates sales language that corresponds to different languages ​​and cultures, thereby enabling the unit to accommodate international customers. For example, the material generation unit uses a generation AI to generate sales language that corresponds to different languages ​​and cultures, thereby enabling the unit to accommodate international customers. For example, the unit generates language that corresponds to multiple languages, such as English and Chinese. The material generation unit can also set standards for accommodating different languages ​​and cultures, and generate sales language based on those standards. For example, the material generation unit can set standards for accommodating different languages ​​and cultures, and generate sales language based on those standards. The material generation unit can also develop algorithms for generating sales language that corresponds to different languages ​​and cultures. For example, the unit develops algorithms for generating sales language that corresponds to different languages ​​and cultures. This allows the unit to accommodate different languages ​​and cultures, thereby enabling the unit to accommodate international customers.

[0043] The material generation unit can add digital interactive elements to create materials that allow customers to deepen their understanding by operating them themselves. The material generation unit, for example, adds digital interactive elements to materials created by the generation AI, allowing customers to deepen their understanding by operating them themselves. For example, it adds interactive graphs and charts. The material generation unit can also set standards for adding digital interactive elements and create materials based on those standards. For example, it can set standards for adding digital interactive elements and create materials based on those standards. The material generation unit can also develop algorithms for adding digital interactive elements. For example, it develops algorithms for adding digital interactive elements. This makes it possible to create materials that allow customers to deepen their understanding by operating them themselves by adding digital interactive elements.

[0044] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0045] The insurance sales system may further include a health management unit that monitors the customer's health condition. The health management unit, for example, collects health data from wearable devices that the customer uses daily and analyzes the data to understand the customer's health condition. For example, it collects data such as heart rate, number of steps, and sleep patterns to evaluate the customer's health condition. The health management unit may also provide the customer with advice on maintaining their health based on the collected data. For example, it may propose an appropriate exercise plan to a customer who is not getting enough exercise. The health management unit may also suggest appropriate insurance products based on the customer's health condition. For example, it may suggest insurance products with health discounts to a customer who is in good health. In this way, by monitoring the customer's health condition, more appropriate insurance products can be suggested.

[0046] The insurance sales system may further include a lifestyle analysis unit that analyzes a customer's lifestyle. The lifestyle analysis unit, for example, collects data from smartphones and smart home devices that the customer uses on a daily basis and analyzes the data to understand the customer's lifestyle. For example, it collects data such as eating patterns, exercise habits, and hobbies, and evaluates the customer's lifestyle. The lifestyle analysis unit can also provide the customer with advice for improving their lifestyle based on the collected data. For example, it can propose a balanced meal plan to a customer with an unbalanced diet. The lifestyle analysis unit can also suggest appropriate insurance products based on the customer's lifestyle. For example, it can propose sports insurance to a customer with an active lifestyle. In this way, by analyzing the customer's lifestyle, more appropriate insurance products can be suggested.

[0047] The insurance sales system can further include a financial analysis unit that analyzes the customer's financial situation. The financial analysis unit, for example, analyzes the customer's bank account and credit card transaction history to understand the customer's financial situation. For example, it analyzes income and expenditure patterns and evaluates the financial situation. The financial analysis unit can also provide the customer with financial management advice based on the collected data. For example, it can provide savings advice to a customer who spends a lot wastefully. The financial analysis unit can also suggest appropriate insurance products based on the customer's financial situation. For example, it can suggest expensive insurance products to a customer with a stable income. In this way, by analyzing the customer's financial situation, it is possible to suggest more appropriate insurance products.

[0048] The insurance sales system can further include a hobby analysis unit that analyzes the hobbies and interests of a customer. The hobby analysis unit, for example, analyzes information shared by the customer on social media and online shopping history to understand the customer's hobbies and interests. For example, it analyzes what hobbies the customer has and proposes appropriate insurance products based on those hobbies. The hobby analysis unit can also provide advice related to hobbies to customers based on the collected data. For example, it proposes insurance products related to outdoor activities to a customer who likes the outdoors. The hobby analysis unit can also propose appropriate insurance products based on the customer's hobbies and interests. For example, it proposes travel insurance to a customer who likes traveling. In this way, by analyzing the customer's hobbies and interests, more appropriate insurance products can be proposed.

[0049] The insurance sales system can further include a network analysis unit that analyzes a customer's social network. The network analysis unit, for example, analyzes information about friends and family members with whom the customer is connected on social media to understand the customer's social network. For example, it analyzes the types of people the customer is connected to and suggests appropriate insurance products based on that network. The network analysis unit can also advise the customer on how to utilize their social network based on the collected data. For example, it can suggest insurance products that the customer can share with friends and family. The network analysis unit can also suggest appropriate insurance products based on the customer's social network. For example, it can suggest insurance products that cover the entire family. In this way, by analyzing the customer's social network, more appropriate insurance products can be suggested.

[0050] The processing flow of the first embodiment will be briefly explained below.

[0051] Step 1: The customer needs analysis unit analyzes the customer's input. For example, if a customer inputs, "I want insurance that covers my entire family," the generation AI analyzes those needs and suggests insurance products that cover the entire family. The customer needs analysis unit can also analyze the customer's input using text mining technology. For example, it uses text mining technology to extract and analyze customer needs. Step 2: The insurance product proposal unit proposes the optimal insurance product based on the customer needs analyzed by the customer needs analysis unit. For example, if a customer inputs, "I want both health insurance and life insurance," the generation AI will propose an insurance product that covers both health insurance and life insurance based on that need. The insurance product proposal unit can also refer to a database of insurance products to select the product that best suits the customer's needs. For example, it refers to a database of insurance products and selects a product that meets the customer's needs. Step 3: The sales support department provides advice to the sales representative based on the insurance products proposed by the insurance product proposal department. For example, the generation AI analyzes the customer's needs and provides the results to the sales representative, allowing the sales representative to provide more accurate advice to the customer. The sales support department can also suggest to the sales representative the optimal sales language and approach method for the customer. For example, the generation AI suggests to the sales representative the optimal sales language and approach method for the customer. Step 4: The material generation unit generates sales language and materials based on the advice provided by the sales support unit. For example, the generation AI generates sales language that clearly explains the features and benefits of an insurance product based on the customer's needs. The material generation unit also creates materials to be provided to customers, which can be used by sales representatives to explain the product to customers. For example, the generation AI creates materials to be provided to customers, which can be used by sales representatives to explain the product to customers.

[0052] (Example 2) An insurance sales system according to an embodiment of the present invention utilizes generative AI to propose insurance products that meet customer needs. This allows the insurance sales system to propose optimal insurance products based on customer needs, provide advice to sales representatives, and generate sales language and materials.

[0053] An insurance sales system according to an embodiment includes a customer needs analysis unit, an insurance product proposal unit, a sales support unit, and a material generation unit. The customer needs analysis unit analyzes customer input. For example, if a customer inputs, "I want insurance that covers my entire family," the generation AI analyzes the customer's needs and proposes insurance products that cover the entire family. The customer needs analysis unit can also analyze the customer's input using text mining technology. For example, the text mining technology can be used to extract and analyze customer needs. The insurance product proposal unit proposes optimal insurance products based on the customer's needs analyzed by the customer needs analysis unit. For example, if a customer inputs, "I want both health insurance and life insurance," the generation AI proposes insurance products that cover both health insurance and life insurance based on the customer's needs. The insurance product proposal unit can also refer to a database of insurance products to select products that best meet the customer's needs. For example, the insurance product proposal unit refers to a database of insurance products and selects products that meet the customer's needs. The sales support unit provides advice to sales representatives based on the insurance products proposed by the insurance product proposal unit. For example, the generation AI analyzes customer needs and provides the results to a sales representative, allowing the sales representative to provide more accurate advice to the customer. The sales support unit can also suggest optimal sales language and approaches to the customer to the sales representative. For example, the generation AI suggests optimal sales language and approaches to the customer to the sales representative. The material generation unit generates sales language and materials based on the advice provided by the sales support unit. For example, the generation AI generates sales language that clearly explains the features and benefits of an insurance product based on the customer's needs. The material generation unit can also create materials to provide to the customer, which the sales representative can use to explain the product to the customer. For example, the generation AI creates materials to provide to the customer, which the sales representative can use to explain the product to the customer. As a result, the insurance sales system according to the embodiment can suggest optimal insurance products based on customer needs, provide advice to the sales representative, and generate sales language and materials.For example, customers can quickly find insurance products that meet their needs, sales representatives can provide more accurate advice, and sales language and materials created by generative AI can be used to explain things to customers more easily, improving the success rate of contracts.

[0054] The customer needs analysis unit can predict potential needs by analyzing purchase history and behavioral patterns based on the customer's input. For example, the customer needs analysis unit uses a generation AI to analyze past purchase history based on the content entered by the customer and predicts potential needs by referring to data on other customers with similar purchasing patterns. For example, the customer needs analysis unit predicts what kind of insurance product a customer who previously purchased family insurance will seek next. The customer needs analysis unit can also collect website browsing history and clickstream data to analyze customer behavioral patterns in order to analyze behavioral patterns. For example, it can analyze what pages a customer views and what links they click to predict potential needs. The customer needs analysis unit can also use a machine learning algorithm to analyze customer behavioral patterns and predict potential needs. For example, it can use a machine learning algorithm to analyze customer behavioral patterns and predict potential needs. By predicting the customer's potential needs, it can propose more appropriate insurance products.

[0055] The customer needs analysis unit can predict future needs by taking into account the customer's life events. For example, the customer needs analysis unit predicts future needs by having the generation AI take into account life events such as marriage and childbirth based on the information entered by the customer. For example, it can propose family insurance products to a customer who is about to get married. The customer needs analysis unit can also analyze the customer's life stage and long-term goals to take life events into account. For example, it can analyze the customer's life stage and long-term goals to predict future needs. The customer needs analysis unit can also predict future needs by taking into account the customer's life events from the perspective of risk management. For example, it can analyze the risks the customer may face and predict future needs. In this way, it can predict future needs by taking the customer's life events into account and propose more appropriate insurance products.

[0056] The customer needs analysis unit can use an emotion estimation function to estimate emotions from the customer's input content and perform emotion-based needs analysis. For example, the customer needs analysis unit uses the emotion estimation function to analyze the emotions of the content entered by the customer using a generation AI and predicts needs based on those emotions. For example, the customer needs analysis unit can suggest insurance products with a relaxing effect to a customer who is feeling stressed. The customer needs analysis unit can also use natural language processing technology to analyze customer emotions using the emotion estimation function. For example, natural language processing technology can be used to analyze emotions from the customer's input content and predict needs based on those emotions. The customer needs analysis unit can also use voice analysis technology to analyze customer emotions. For example, it can analyze customer voice data and predict needs based on those emotions. In this way, by analyzing needs based on the customer's emotions, more appropriate insurance products can be suggested.

[0057] The customer needs analysis unit can also accept voice and image input, allowing it to understand needs from a wider variety of information sources. For example, the customer needs analysis unit analyzes what the customer inputs via voice, and the generation AI understands their needs from that voice data. For example, if a customer says, "I want insurance that covers my entire family," the voice data is analyzed to suggest appropriate insurance products. The customer needs analysis unit can also accept image input, allowing it to analyze what the customer inputs via image. For example, if a customer uploads an image of their insurance policy, the image data is analyzed to suggest appropriate insurance products. The customer needs analysis unit can also use voice recognition technology to convert the customer's voice data into text data and analyze that text data. For example, it can use voice recognition technology to convert the customer's voice data into text data and analyze that text data to understand their needs. This allows it to accept voice and image input, allowing it to understand customer needs from a wider variety of information sources.

[0058] The customer needs analysis unit compares the needs of the customer with those of other customers and identifies common needs, thereby enabling more general proposals to be made. For example, the customer needs analysis unit compares the results of the customer's needs analysis with those of other customers and identifies common needs. For example, if multiple customers input "I want insurance that covers my entire family," the customer needs analysis unit proposes general insurance products based on that common need. The customer needs analysis unit can also use clustering technology to group customer needs and identify common needs. For example, the customer needs analysis unit can use clustering technology to group customer needs and identify common needs. The customer needs analysis unit can also use pattern recognition technology to analyze customer needs and identify common needs. For example, the customer needs analysis unit can use pattern recognition technology to analyze customer needs and identify common needs. This allows more general proposals to be made by comparing the needs of the customer with those of other customers.

[0059] The customer needs analysis unit can use an emotion estimation function to collect real-time emotional responses to customer input content, thereby improving the accuracy of needs analysis. For example, the customer needs analysis unit uses a generation AI to collect emotional responses in real time to content input by a customer, and improves the accuracy of needs analysis based on that data. For example, the customer needs analysis unit analyzes the customer's emotional score for the input content and suggests more appropriate insurance products. The customer needs analysis unit can also collect customer emotional responses using real-time data streaming technology. For example, the customer needs analysis unit can collect customer emotional responses using real-time data streaming technology, and improve the accuracy of needs analysis based on that data. The customer needs analysis unit can also analyze customer emotional responses using an emotion analysis algorithm. For example, the customer needs analysis unit can analyze customer emotional responses using an emotion analysis algorithm, and improve the accuracy of needs analysis based on that data. In this way, by collecting real-time emotional responses, the accuracy of needs analysis can be improved.

[0060] The insurance product proposal unit can select the most suitable insurance product by taking into consideration the customer's health condition and lifestyle. For example, the insurance product proposal unit uses a generation AI to select the most suitable insurance product by taking into consideration the customer's health condition and lifestyle. For example, the insurance product proposal unit can propose a health insurance product based on health checkup results and lifestyle data. The insurance product proposal unit can also set criteria for evaluating the customer's health condition and lifestyle and select the most suitable insurance product based on those criteria. For example, the insurance product proposal unit can evaluate the health checkup results and lifestyle data and select the most suitable insurance product based on the evaluation results. The insurance product proposal unit can also analyze data collected from a wearable device to evaluate the customer's health condition and lifestyle. For example, the insurance product proposal unit can analyze data collected from a wearable device to evaluate the customer's health condition and lifestyle, and select the most suitable insurance product based on the evaluation results. This allows the most suitable insurance product to be selected by taking into consideration the customer's health condition and lifestyle.

[0061] The insurance product proposal unit can use the emotion estimation function to predict a customer's emotional response to a proposed insurance product and propose a product that will receive a positive response. The insurance product proposal unit, for example, uses the emotion estimation function to predict a customer's emotional response to a proposed insurance product and proposes a product that will receive a positive response. For example, the insurance product proposal unit selects a product that receives a large number of positive responses based on past emotion data. The insurance product proposal unit can also use the emotion estimation function to set criteria for evaluating a customer's emotional response and propose a product that will receive a positive response based on the criteria. For example, the insurance product proposal unit evaluates a customer's emotional response and proposes a product that will receive a positive response based on the evaluation result. The insurance product proposal unit can also predict a customer's emotional response using an emotion estimation algorithm. For example, the insurance product proposal unit can predict a customer's emotional response using an emotion estimation algorithm and propose a product that will receive a positive response based on the prediction result. In this way, by predicting a customer's emotional response, it is possible to propose a product that will receive a positive response.

[0062] The insurance product proposal unit can compare products from different insurance companies and select the most suitable product. For example, the generation AI in the insurance product proposal unit compares products from different insurance companies and selects the most suitable insurance product. For example, it refers to the databases of multiple insurance companies and proposes the most suitable product. The insurance product proposal unit can also compare the features and advantages of products offered by insurance companies and select the most suitable product based on the comparison results. For example, it compares the features and advantages of products offered by insurance companies and selects the most suitable product based on the comparison results. The insurance product proposal unit can also analyze evaluation data of insurance companies and select the most suitable product based on the evaluation results. For example, it analyzes evaluation data of insurance companies and selects the most suitable product based on the evaluation results. This makes it possible to compare products from different insurance companies and select the most suitable product.

[0063] The insurance product proposal unit can propose optimal products from a long-term perspective, taking into account the customer's family structure and future plans. For example, the generative AI in the insurance product proposal unit proposes optimal insurance products from a long-term perspective, taking into account the customer's family structure and future plans. For example, it proposes insurance products that take into account children's growth and education expenses. The insurance product proposal unit can also set criteria for evaluating the customer's family structure and future plans and propose optimal products based on those criteria. For example, it evaluates the customer's family structure and future plans and proposes optimal products based on the evaluation results. The insurance product proposal unit can also analyze the customer's life plan and career plan and propose optimal products based on the analysis results. For example, it analyzes the customer's life plan and career plan and proposes optimal products based on the analysis results. In this way, it is possible to propose optimal products from a long-term perspective by taking into account the customer's family structure and future plans.

[0064] The insurance product proposal unit can use the emotion estimation function to monitor the customer's emotional reaction to the proposed insurance product in real time and adjust the proposal content. The insurance product proposal unit, for example, uses the emotion estimation function to monitor the customer's emotional reaction to the proposed insurance product in real time and adjust the proposal content. For example, if the customer has a negative reaction, the insurance product proposal unit proposes a different insurance product. The insurance product proposal unit can also monitor the customer's emotional reaction using real-time data streaming technology. For example, the real-time data streaming technology can be used to monitor the customer's emotional reaction and adjust the proposal content based on the data. The insurance product proposal unit can also use an emotion estimation algorithm to analyze the customer's emotional reaction and adjust the proposal content based on the analysis results. For example, the emotion estimation algorithm can be used to analyze the customer's emotional reaction and adjust the proposal content based on the analysis results. In this way, the proposal content can be adjusted by monitoring the customer's emotional reaction in real time.

[0065] The sales support department can analyze past sales data and propose approach methods with a high success rate. For example, the sales support department uses generative AI to analyze past sales data and propose approach methods with a high success rate. For example, the sales support department proposes the optimal approach method to customers based on sales methods that have been successful in the past. The sales support department can also set criteria for evaluating approach methods to customers based on sales data and propose the optimal approach method based on those criteria. For example, the sales support department can evaluate approach methods to customers based on sales data and propose the optimal approach method based on the evaluation results. The sales support department can also analyze sales data and develop algorithms for proposing approach methods with a high success rate. For example, the sales support department can develop algorithms for analyzing sales data and proposing approach methods with a high success rate. This makes it possible to propose approach methods with a high success rate by analyzing past sales data.

[0066] The sales support department can provide personalized advice by taking into account a customer's purchasing history and behavioral patterns. For example, the sales support department uses a generative AI to provide personalized advice by taking into account a customer's purchasing history and behavioral patterns. For example, the sales support department can suggest the optimal approach to a customer based on past purchase history. The sales support department can also set criteria for evaluating a customer's purchasing history and behavioral patterns and provide personalized advice based on those criteria. For example, the sales support department can evaluate a customer's purchasing history and behavioral patterns and provide personalized advice based on the evaluation results. The sales support department can also analyze a customer's purchasing history and behavioral patterns and develop an algorithm for providing personalized advice. For example, the sales support department can analyze a customer's purchasing history and behavioral patterns and develop an algorithm for providing personalized advice. This makes it possible to provide personalized advice by taking into account a customer's purchasing history and behavioral patterns.

[0067] The sales support unit can use the emotion estimation function to analyze emotional reactions during a conversation with a customer and provide advice to the sales representative in real time. For example, the sales support unit can use the emotion estimation function to analyze emotional reactions during a conversation with a customer and provide advice to the sales representative in real time. For example, if the customer has a negative reaction, the sales support unit can suggest an alternative approach. The sales support unit can also use real-time data streaming technology to analyze the emotional reactions of customers. For example, the sales support unit can use real-time data streaming technology to analyze the emotional reactions of customers and provide advice to the sales representative in real time based on the data. The sales support unit can also use an emotion estimation algorithm to analyze the emotional reactions of customers and provide advice to the sales representative in real time based on the analysis results. For example, the sales support unit can use the emotion estimation algorithm to analyze the emotional reactions of customers and provide advice to the sales representative in real time based on the analysis results. In this way, advice can be provided to the sales representative in real time by analyzing the emotional reactions during a conversation with a customer.

[0068] The sales support department can propose a region-specific approach method by taking into account the customer's region and cultural background. For example, the sales support department uses generative AI to propose a region-specific approach method by taking into account the customer's region and cultural background. For example, it proposes sales methods that are tailored to the local culture and customs. The sales support department can also set criteria for evaluating the customer's region and cultural background and propose a region-specific approach method based on those criteria. For example, it can evaluate the customer's region and cultural background and propose a region-specific approach method based on the evaluation results. The sales support department can also develop an algorithm for analyzing the local culture and customs and proposing a region-specific approach method. For example, it can develop an algorithm for analyzing the local culture and customs and proposing a region-specific approach method. This makes it possible to propose a region-specific approach method by taking into account the customer's region and cultural background.

[0069] The sales support unit can use the emotion estimation function to predict emotional reactions to proposals made by sales representatives to customers and propose an optimal approach. For example, the sales support unit can use the emotion estimation function to predict emotional reactions to proposals made by sales representatives to customers and propose an optimal approach. For example, the sales support unit selects proposals that will elicit a positive reaction. The sales support unit can also use the emotion estimation function to set criteria for evaluating customers' emotional reactions and propose an optimal approach based on the criteria. For example, the sales support unit evaluates the customers' emotional reactions and proposes an optimal approach based on the evaluation results. The sales support unit can also use an emotion estimation algorithm to predict the customers' emotional reactions and propose an optimal approach based on the prediction results. For example, the sales support unit can use the emotion estimation algorithm to predict the customers' emotional reactions and propose an optimal approach based on the prediction results. In this way, the optimal approach can be proposed by predicting emotional reactions to proposals made by sales representatives to customers.

[0070] The material generation unit can generate effective sales language by referring to past success cases. In the material generation unit, for example, a generation AI refers to past success cases to generate effective sales language. For example, new language is generated based on sales language that has been successful in the past. The material generation unit can also set criteria for evaluating effective sales language based on success cases and generate language based on those criteria. For example, effective sales language is evaluated based on success cases and language is generated based on the evaluation results. The material generation unit can also analyze success cases and develop an algorithm for generating effective sales language. For example, an algorithm for analyzing success cases and generating effective sales language is developed. In this way, effective sales language can be generated by referring to past success cases.

[0071] The material generation unit can create materials that make use of easy-to-understand expressions and plenty of illustrations, taking into account the customer's level of understanding. For example, the generation AI in the material generation unit creates materials that make use of easy-to-understand expressions and plenty of illustrations, taking into account the customer's level of understanding. For example, the features of an insurance product are explained using illustrations. The material generation unit can also set criteria for evaluating the customer's level of understanding and create materials that make use of easy-to-understand expressions and plenty of illustrations based on those criteria. For example, it can evaluate the customer's level of understanding and create materials that make use of easy-to-understand expressions and plenty of illustrations based on the evaluation results. The material generation unit can also analyze the customer's level of understanding and develop an algorithm for creating materials that make use of easy-to-understand expressions and plenty of illustrations. For example, it can analyze the customer's level of understanding and develop an algorithm for creating materials that make use of easy-to-understand expressions and plenty of illustrations. This makes it possible to create materials that make use of easy-to-understand expressions and plenty of illustrations, taking into account the customer's level of understanding.

[0072] The material generation unit can use the emotion estimation function to predict the emotional response of a customer and generate words and materials that elicit positive emotions. The material generation unit, for example, uses the emotion estimation function to predict the emotional response of a customer and generate words and materials that elicit positive emotions. For example, the material generation unit generates words that make the customer feel happy. The material generation unit can also use the emotion estimation function to set criteria for evaluating the emotional response of a customer and generate words and materials that elicit positive emotions based on the criteria. For example, the material generation unit evaluates the emotional response of a customer and generates words and materials that elicit positive emotions based on the evaluation results. The material generation unit can also use an emotion estimation algorithm to predict the emotional response of a customer and generate words and materials that elicit positive emotions based on the prediction results. For example, the material generation unit can use the emotion estimation algorithm to predict the emotional response of a customer and generate words and materials that elicit positive emotions based on the prediction results. In this way, it is possible to generate words and materials that elicit positive emotions by predicting the emotional response of a customer.

[0073] The material generation unit generates sales language that corresponds to different languages ​​and cultures, thereby enabling the unit to accommodate international customers. For example, the material generation unit uses a generation AI to generate sales language that corresponds to different languages ​​and cultures, thereby enabling the unit to accommodate international customers. For example, the unit generates language that corresponds to multiple languages, such as English and Chinese. The material generation unit can also set standards for accommodating different languages ​​and cultures, and generate sales language based on those standards. For example, the material generation unit can set standards for accommodating different languages ​​and cultures, and generate sales language based on those standards. The material generation unit can also develop algorithms for generating sales language that corresponds to different languages ​​and cultures. For example, the unit develops algorithms for generating sales language that corresponds to different languages ​​and cultures. This allows the unit to accommodate different languages ​​and cultures, thereby enabling the unit to accommodate international customers.

[0074] The material generation unit can add digital interactive elements to create materials that allow customers to deepen their understanding by operating them themselves. The material generation unit, for example, adds digital interactive elements to materials created by the generation AI, allowing customers to deepen their understanding by operating them themselves. For example, it adds interactive graphs and charts. The material generation unit can also set standards for adding digital interactive elements and create materials based on those standards. For example, it can set standards for adding digital interactive elements and create materials based on those standards. The material generation unit can also develop algorithms for adding digital interactive elements. For example, it develops algorithms for adding digital interactive elements. This makes it possible to create materials that allow customers to deepen their understanding by operating them themselves by adding digital interactive elements.

[0075] The material generation unit can use the emotion estimation function to monitor the customer's emotional reaction to sales language and materials in real time and adjust the content to the optimum. The material generation unit, for example, uses the emotion estimation function to monitor the customer's emotional reaction to sales language and materials in real time and adjust the content to the optimum. For example, if the customer has a negative reaction, the material generation unit modifies the language and materials. The material generation unit can also use real-time data streaming technology to monitor the customer's emotional reaction. For example, the real-time data streaming technology can be used to monitor the customer's emotional reaction and adjust the language and materials based on the data. The material generation unit can also use an emotion estimation algorithm to analyze the customer's emotional reaction and adjust the language and materials based on the analysis results. For example, the emotion estimation algorithm can be used to analyze the customer's emotional reaction and adjust the language and materials based on the analysis results. In this way, the content can be adjusted to the optimum by monitoring the customer's emotional reaction in real time.

[0076] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0077] The insurance sales system may further include a health management unit that monitors the customer's health condition. The health management unit, for example, collects health data from wearable devices that the customer uses daily and analyzes the data to understand the customer's health condition. For example, it collects data such as heart rate, number of steps, and sleep patterns to evaluate the customer's health condition. The health management unit may also provide the customer with advice on maintaining their health based on the collected data. For example, it may propose an appropriate exercise plan to a customer who is not getting enough exercise. The health management unit may also suggest appropriate insurance products based on the customer's health condition. For example, it may suggest insurance products with health discounts to a customer who is in good health. In this way, by monitoring the customer's health condition, more appropriate insurance products can be suggested.

[0078] The insurance sales system may further include a lifestyle analysis unit that analyzes a customer's lifestyle. The lifestyle analysis unit, for example, collects data from smartphones and smart home devices that the customer uses on a daily basis and analyzes the data to understand the customer's lifestyle. For example, it collects data such as eating patterns, exercise habits, and hobbies, and evaluates the customer's lifestyle. The lifestyle analysis unit can also provide the customer with advice for improving their lifestyle based on the collected data. For example, it can propose a balanced meal plan to a customer with an unbalanced diet. The lifestyle analysis unit can also suggest appropriate insurance products based on the customer's lifestyle. For example, it can propose sports insurance to a customer with an active lifestyle. In this way, by analyzing the customer's lifestyle, more appropriate insurance products can be suggested.

[0079] The insurance sales system can further include a financial analysis unit that analyzes the customer's financial situation. The financial analysis unit, for example, analyzes the customer's bank account and credit card transaction history to understand the customer's financial situation. For example, it analyzes income and expenditure patterns and evaluates the financial situation. The financial analysis unit can also provide the customer with financial management advice based on the collected data. For example, it can provide savings advice to a customer who spends a lot wastefully. The financial analysis unit can also suggest appropriate insurance products based on the customer's financial situation. For example, it can suggest expensive insurance products to a customer with a stable income. In this way, by analyzing the customer's financial situation, it is possible to suggest more appropriate insurance products.

[0080] The insurance sales system can further include a hobby analysis unit that analyzes the hobbies and interests of a customer. The hobby analysis unit, for example, analyzes information shared by the customer on social media and online shopping history to understand the customer's hobbies and interests. For example, it analyzes what hobbies the customer has and proposes appropriate insurance products based on those hobbies. The hobby analysis unit can also provide advice related to hobbies to customers based on the collected data. For example, it proposes insurance products related to outdoor activities to a customer who likes the outdoors. The hobby analysis unit can also propose appropriate insurance products based on the customer's hobbies and interests. For example, it proposes travel insurance to a customer who likes traveling. In this way, by analyzing the customer's hobbies and interests, more appropriate insurance products can be proposed.

[0081] The insurance sales system can further include a network analysis unit that analyzes a customer's social network. The network analysis unit, for example, analyzes information about friends and family members with whom the customer is connected on social media to understand the customer's social network. For example, it analyzes the types of people the customer is connected to and suggests appropriate insurance products based on that network. The network analysis unit can also advise the customer on how to utilize their social network based on the collected data. For example, it can suggest insurance products that the customer can share with friends and family. The network analysis unit can also suggest appropriate insurance products based on the customer's social network. For example, it can suggest insurance products that cover the entire family. In this way, by analyzing the customer's social network, more appropriate insurance products can be suggested.

[0082] The insurance sales system may further include an emotion analysis unit that estimates the customer's emotions and proposes insurance products based on those emotions. The emotion analysis unit, for example, analyzes the content entered by the customer or voice data to estimate the customer's emotions. For example, if the customer is feeling stressed, it may propose an insurance product with a relaxing effect based on that emotion. The emotion analysis unit may also provide the customer with advice on emotion management based on the collected data. For example, it may provide advice on reducing stress. The emotion analysis unit may also propose appropriate insurance products based on the customer's emotions. For example, it may propose insurance products that provide a sense of security. In this way, by analyzing the customer's emotions, it is possible to propose more appropriate insurance products.

[0083] The insurance sales system may further include a real-time emotion analysis unit that monitors customer emotions in real time and proposes insurance products based on those emotions. The real-time emotion analysis unit, for example, analyzes the content entered by the customer or voice data in real time to estimate the customer's emotions. For example, if the customer is feeling anxious, it proposes insurance products that will give the customer a sense of security based on the customer's emotions. The real-time emotion analysis unit can also provide the customer with advice on emotion management in real time based on the collected data. For example, it provides advice on reducing anxiety in real time. The real-time emotion analysis unit can also propose appropriate insurance products in real time based on the customer's emotions. For example, it proposes insurance products that give the customer a sense of security in real time. In this way, by analyzing the customer's emotions in real time, more appropriate insurance products can be proposed.

[0084] The insurance sales system may further include a long-term emotion analysis unit that monitors a customer's emotions over the long term and proposes insurance products based on changes in those emotions. The long-term emotion analysis unit, for example, analyzes the content entered by the customer and voice data over the long term to understand changes in those emotions. For example, if a customer has been feeling stressed for a long period of time, it proposes an insurance product that has a stress-reducing effect based on that emotion. The long-term emotion analysis unit can also provide the customer with advice for long-term emotion management based on the collected data. For example, it provides advice for long-term stress management. The long-term emotion analysis unit can also propose appropriate insurance products based on changes in the customer's emotions. For example, it proposes insurance products that will give the customer a sense of security over the long term. In this way, by analyzing the customer's emotions over the long term, more appropriate insurance products can be proposed.

[0085] The insurance sales system can further include an emotional message generation unit that analyzes the customer's emotions and generates sales messages based on those emotions. The emotional message generation unit, for example, analyzes content entered by the customer or voice data to estimate the customer's emotions. For example, if the customer is feeling happy, it generates positive sales messages based on that emotion. The emotional message generation unit can also provide sales messages to the customer that match their emotions based on the collected data. For example, if the customer is feeling anxious, it generates sales messages that give a sense of security based on that emotion. The emotional message generation unit can also generate appropriate sales messages based on the customer's emotions. For example, it generates sales messages that make the customer feel excited. In this way, more appropriate sales messages can be generated by analyzing the customer's emotions.

[0086] The insurance sales system can further include an emotion data generation unit that analyzes the customer's emotions and generates materials based on those emotions. The emotion data generation unit, for example, analyzes the content and voice data entered by the customer and estimates the customer's emotions. For example, if the customer is seeking a sense of security, it generates materials that give the customer a sense of security based on that emotion. The emotion data generation unit can also provide materials that match the customer's emotions based on the collected data. For example, if the customer is feeling excited, it generates materials that elicit excitement based on that emotion. The emotion data generation unit can also generate appropriate materials based on the customer's emotions. For example, it generates materials that make the customer feel relaxed. In this way, more appropriate materials can be generated by analyzing the customer's emotions.

[0087] The processing flow of the second embodiment will be briefly explained below.

[0088] Step 1: The customer needs analysis unit analyzes the customer's input. For example, if a customer inputs, "I want insurance that covers my entire family," the generation AI analyzes those needs and suggests insurance products that cover the entire family. The customer needs analysis unit can also analyze the customer's input using text mining technology. For example, it uses text mining technology to extract and analyze customer needs. Step 2: The insurance product proposal unit proposes the optimal insurance product based on the customer needs analyzed by the customer needs analysis unit. For example, if a customer inputs, "I want both health insurance and life insurance," the generation AI will propose an insurance product that covers both health insurance and life insurance based on that need. The insurance product proposal unit can also refer to a database of insurance products to select the product that best suits the customer's needs. For example, it refers to a database of insurance products and selects a product that meets the customer's needs. Step 3: The sales support department provides advice to the sales representative based on the insurance products proposed by the insurance product proposal department. For example, the generation AI analyzes the customer's needs and provides the results to the sales representative, allowing the sales representative to provide more accurate advice to the customer. The sales support department can also suggest to the sales representative the optimal sales language and approach method for the customer. For example, the generation AI suggests to the sales representative the optimal sales language and approach method for the customer. Step 4: The material generation unit generates sales language and materials based on the advice provided by the sales support unit. For example, the generation AI generates sales language that clearly explains the features and benefits of an insurance product based on the customer's needs. The material generation unit also creates materials to be provided to customers, which can be used by sales representatives to explain the product to customers. For example, the generation AI creates materials to be provided to customers, which can be used by sales representatives to explain the product to customers.

[0089] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0090] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0091] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0092] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0093] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0094] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0095] 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.

[0096] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0097] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0098] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0099] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0100] 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.

[0101] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0102] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0103] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0104] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0105] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0106] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0107] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0108] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0109] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0110] 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.

[0111] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0112] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0113] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0114] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0115] 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.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0117] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0118] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0122] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0123] 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.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] 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.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0130] 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.

[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 user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0133] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0137] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0138] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0139] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0140] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0141] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0142] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0143] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0144] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0145] 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.

[0146] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0147] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0148] 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.

[0149] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0150] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0151] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0152] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0153] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0154] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0155] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0156] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a customer needs analysis unit that analyzes the customer's input; an insurance product proposal unit that proposes optimal insurance products based on the customer needs analyzed by the customer needs analysis unit; a sales support unit that provides advice to sales personnel based on the insurance products proposed by the insurance product proposal unit; a material generation unit that generates sales statements and materials based on the advice provided by the sales support unit; A system characterized by:

2. The customer needs analysis unit An emotion estimation function is used to estimate emotions from the customer's input content, and a needs analysis is performed based on the emotions. The system of claim 1 .

3. The insurance product proposal unit Using an emotion estimation function, the customer's emotional reaction to the insurance product is predicted, and a product that will generate a positive reaction is proposed. The system of claim 1 .

4. The sales support department Using emotion estimation capabilities to analyze emotional responses during interactions with the customer and provide real-time advice to the sales representative. The system of claim 1 .

5. The material generation unit Using an emotion estimation function, the emotional response of the customer is predicted, and words and materials that evoke positive emotions are generated. The system of claim 1 .

6. The customer needs analysis unit Supports voice and image input to understand needs from a wider range of information sources The system of claim 1 .

7. The insurance product proposal unit Customer satisfaction data is referenced for the insurance products to be proposed, and products with high satisfaction are preferentially proposed. The system of claim 1 .

8. The sales support department Analyze sales data and propose approaches with a high success rate The system of claim 1 .

Images