System

Abstract

An object of a system according to an embodiment is to automatically generate an optimal sales talk based on customer information and merchandise information.SOLUTION: A system includes a customer information inputting part, a commodity information inputting part, a sales talk generating part, and an editing part. The customer information input unit inputs customer information. The commodity information input unit inputs commodity information. The sales talk generating section generates a sales talk based on the information inputted by the customer information inputting section and the commodity information inputting section. The editing unit edits the sales talk generated by the sales talk generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the drawback that it takes time and effort for salespeople to create effective sales pitches based on customer and product information.

[0005] The system according to the embodiment aims to automatically generate optimal sales pitches based on customer information and product information. [Means for solving the problem]

[0006] The system according to the embodiment includes a customer information input unit, a product information input unit, a sales talk generation unit, and an editing unit. The customer information input unit inputs customer information. The product information input unit inputs product information. The sales talk generation unit generates a sales talk based on the information input by the customer information input unit and the product information input unit. The editing unit edits the sales talk generated by the sales talk generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically generate optimal sales pitches based on customer information and product information. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) The automatic sales talk generation system according to an embodiment of the present invention is a system that automatically generates optimal sales talks based on customer information, product information, sales objectives, etc. input by a sales representative. As a result, the automatic sales talk generation system can select appropriate topics, questions, humor, anecdotes, etc. according to the customer's personality, interests, and situation, and create effective sales talks.

[0029] A sales pitch automatic generation system according to an embodiment includes a customer information input unit, a product information input unit, a sales pitch generation unit, and an editing unit. The customer information input unit inputs customer information. For example, basic customer information (such as name, age, gender, and occupation) can be input. The customer's past purchase history and interests can also be input. For example, if the customer is interested in sports, that information can be input. The product information input unit inputs product information. For example, the product information input unit inputs the features, price, and advantages of a product to be sold. The sales objective (such as introducing a new product or upselling an existing product) can also be input. For example, if the objective is to introduce a new product, information emphasizing the features and advantages of the product can be input. The sales pitch generation unit generates a sales pitch based on the information input by the customer information input unit and the product information input unit. For example, the generation AI selects appropriate topics, questions, humor, anecdotes, etc. according to the customer's personality, interests, and situation to generate the sales pitch. For example, if the customer likes to travel, including a question such as, "Where was your most recent trip?" can increase familiarity with the customer. The editing unit edits the sales pitch generated by the sales pitch generation unit. For example, additional information can be added to the generated talk or specific parts can be modified. This allows salespeople to create talks that suit their own style. As a result, the sales talk automatic generation system according to the embodiment can generate and edit optimal sales talks based on customer information and product information.

[0030] The customer information input unit collects public information from the customer's social media account, and the generation AI analyzes that information to identify the customer's latest interests. The customer information input unit, for example, collects public posts and profile information from the customer's social media account, and the generation AI analyzes the content. For example, if the customer has recently posted many posts about "travel," the generation AI can incorporate travel-related topics into the sales pitch. The generation AI can also analyze the customer's social media behavior history, such as "likes" and "shares," to identify topics of interest. For example, if the customer has "liked" many sports-related posts, the generation AI can incorporate sports-related topics into the sales pitch. The generation AI can also identify the customer's hobbies and interests based on the information collected from the customer's social media account and generate a personalized sales pitch based on that information. For example, if the customer is interested in music festivals, the generation AI can include that topic in the pitch. This allows the customer's latest interests to be identified and reflected in the sales pitch.

[0031] The customer information input unit analyzes a customer's past purchase history, browsing history, and information on products added to their cart, allowing for a more detailed understanding of their interests. For example, the customer information input unit analyzes a customer's past purchase history to identify what products the customer is interested in. For example, if the customer has purchased many electronic devices in the past, the customer information input unit can incorporate topics related to the latest gadgets into their sales pitch. The customer information input unit can also analyze the customer's website browsing history to identify which pages the customer frequently visits. For example, if the customer frequently visits pages for outdoor equipment, the customer can incorporate topics related to outdoor activities into their sales pitch. The customer information input unit can also analyze information on products the customer added to their cart but did not purchase, allowing for a more detailed understanding of the customer's interests in those products. For example, the customer information input unit can include topics related to luxury watches the customer added to their cart but did not purchase in the sales pitch. This allows for a more detailed understanding of the customer's interests and reflects them in their sales pitch.

[0032] The customer information input unit enables voice input, allowing sales representatives to input information verbally. The customer information input unit, for example, builds a system that allows sales representatives to input customer information by voice. For example, using voice recognition technology, the sales representative verbally inputs information such as the customer's name and occupation. Also, using a voice input function, the sales representative can verbally input the customer's interests and past purchase history. For example, the sales representative verbally inputs, "This customer is interested in sports." Also, using voice input, a system is developed that allows sales representatives to quickly input customer information. For example, the sales representative verbally inputs, "This customer is a man in his 30s who has purchased many electronic devices in the past." This allows sales representatives to input customer information by voice.

[0033] The customer information input unit collects information about the customer's family structure and pets when entering customer information, making it possible to generate more personalized sales talks. The customer information input unit, for example, builds a system that collects information about the customer's family structure and pets when entering customer information. For example, a customer enters information such as "I have a wife and two children." Furthermore, based on the information about the family structure and pets, a more personalized sales talk is generated. For example, based on information such as "I have a dog," a topic about pets is included in the talk. Furthermore, information about the customer's family structure and pets is collected, and a personalized sales talk is generated based on that information. For example, based on information such as "My child plays soccer," a topic about soccer is included in the talk. In this way, a more personalized sales talk can be generated by collecting information about the customer's family structure and pets.

[0034] The sales talk generation unit inputs information about competing products in addition to product information, and the generation AI can compare them and generate talk that emphasizes their superiority. The sales talk generation unit builds a system in which, for example, product information and information about competing products are input, and the generation AI compares them and generates talk that emphasizes their superiority. For example, it emphasizes the features and advantages of one's own product. Also, based on information about competing products, the generation AI generates talk that emphasizes the superiority of one's own product. For example, it emphasizes the lower price and superior functionality compared to competing products. Also, product information and information about competing products are input, and the generation AI compares them and generates talk that emphasizes their superiority. For example, it emphasizes the higher durability and superior design compared to competing products. This makes it possible to generate talk that emphasizes the superiority of one's own product compared to competing products.

[0035] The sales talk generation unit can input product usage scenarios and case studies and generate talks that include specific usage scenarios. The sales talk generation unit builds a system in which, for example, product usage scenarios and case studies are input and a generation AI generates talks that include specific usage scenarios. For example, it specifically explains how to use the product and its effects. Furthermore, based on the case study, the generation AI generates talks that include specific usage scenarios. For example, it creates talks based on past success stories and customer feedback. Furthermore, product usage scenarios are input and the generation AI generates talks that include specific usage scenarios. For example, it specifically explains how to use the product and its effects. This makes it possible to generate talks that include specific usage scenarios.

[0036] The sales talk generation unit can attach videos and images when entering product information, and use visual information for analysis. The sales talk generation unit will build a system that allows videos and images to be attached when entering product information. For example, a promotional video for the product or product images can be uploaded. In addition, a system will be developed in which a generation AI analyzes visual information based on videos and images and reflects it in sales talks. For example, a talk will be created based on a video that shows how to use the product. In addition, a system will be built in which videos and images can be attached when entering product information, and visual information will be used for analysis. For example, a talk will be created based on an image that shows the product's features. This will allow visual information to be used for analysis and reflected in sales talks.

[0037] The sales talk generation unit can select different talk styles (e.g., casual, formal) depending on the sales purpose. The sales talk generation unit builds a system that can select different talk styles depending on the sales purpose. For example, it selects a casual talk style or a formal talk style. Also, a system is developed in which the generation AI selects the optimal talk style depending on the sales purpose. For example, it selects a casual talk style for introducing a new product. Also, a system is built in which a different talk style can be selected depending on the sales purpose. For example, it selects a formal talk style for upselling an existing product. This makes it possible to select a talk style depending on the sales purpose.

[0038] The sales talk generation unit can refer to a database of past successful sales talks and incorporate the most effective patterns. For example, the sales talk generation unit builds a system in which the generation AI refers to a database of past successful sales talks and incorporates the most effective patterns. For example, it generates new talks based on talk patterns that have boasted high closing rates in the past. It also analyzes the database of successful sales talks and extracts common effective elements. For example, if a particular phrase or question is used frequently, it can incorporate it into the new talk. The generation AI also learns from past success stories and generates the optimal sales talk based on that knowledge. For example, it can reflect talk patterns that were effective with a particular customer demographic in the new talk. In this way, effective talks can be generated by incorporating patterns from past successful sales talks.

[0039] The sales talk generation unit can generate talk that is specific to a region, taking into account the customer's cultural background and regional characteristics. The sales talk generation unit, for example, builds a system in which the generation AI generates talk that is specific to a region, taking into account the customer's cultural background and regional characteristics. For example, topics related to local events and culture are included in the talk. The generation AI also generates optimal talk based on the customer's regional characteristics. For example, talk that incorporates local dialects and unique expressions is created. A system is also developed in which the generation AI generates talk that is familiar to customers, taking into account their cultural background. For example, topics related to local traditions and customs are included in the talk. This makes it possible to generate talk that takes into account the customer's cultural background and regional characteristics.

[0040] When generating a sales talk, the sales talk generation unit can simultaneously generate multiple variations, allowing sales representatives to choose from. For example, the sales talk generation unit will build a system in which a generation AI simultaneously generates multiple sales talk variations, allowing sales representatives to choose from. For example, it will generate both casual and formal talk. It will also generate sales talk variations, allowing sales representatives to select the most appropriate talk. For example, it will switch talks depending on the customer's reaction. It will also develop a system that generates multiple talk variations, allowing sales representatives to choose according to the situation. For example, it will prepare multiple talks that suit the customer's personality and interests. This will generate multiple talk variations, allowing sales representatives to choose from.

[0041] The sales talk generation unit can automatically insert the customer's name and specific information into the generated talk, thereby providing personalized talk. For example, the sales talk generation unit builds a system that automatically inserts the customer's name and specific information into the generated sales talk. For example, it includes a personalized greeting such as "Hello, Mr. / Ms. XX." In addition, the generation AI provides personalized talk based on the customer's specific information. For example, it generates talk based on the customer's past purchase history. In addition, it develops a system that automatically inserts the customer's name and specific information into the generated talk, thereby providing personalized talk. For example, it includes topics related to the customer's interests in the talk. This makes it possible to insert the customer's name and specific information and provide personalized talk.

[0042] The editorial department will build a system in which, for example, when a sales representative edits a talk, the generation AI will provide feedback in real time and suggest optimal revisions. For example, it will suggest areas for improvement in the content of the talk. The editorial department will also develop a system in which the generation AI will analyze the edits made by the sales representative and suggest optimal revisions in real time. For example, it will make suggestions to make the flow of the talk smoother. The generation AI will also provide feedback in real time when a sales representative edits a talk and suggest optimal revisions. For example, it will suggest revisions to the talk to match the customer's interests. This will enable the editorial department to provide feedback in real time and suggest optimal revisions when a sales representative edits a talk.

[0043] The editorial department can add a function to save the editing history and analyze which edits were most effective. For example, the editorial department will build a system that saves the editing history of sales talks and analyzes which edits were most effective. For example, it will identify the edited content of talks that had a high conversion rate. It will also develop a system that uses the editing history to enable the generative AI to learn the most effective editing patterns. For example, if a particular phrase or question was effective, it will reflect that in the next talk. It will also add a function to save the editing history of sales talks and analyze which edits were most effective. For example, it will identify the edits that received a good response from customers. This will allow it to save the editing history and analyze effective edits.

[0044] The editing department can display examples of edits made by other sales representatives on the sales talk editing screen, allowing them to use them as reference. The editing department, for example, builds a system that displays examples of edits made by other sales representatives on the sales talk editing screen. For example, they can use the edited content of successful talks as reference. They also develop a system that displays examples of edits made by other sales representatives, allowing sales representatives to use them as reference. For example, they can display edited content that was effective for a specific customer demographic. They can also display examples of edits made by other sales representatives on the sales talk editing screen, allowing them to use them as reference. For example, they can present editing suggestions based on past success stories. This allows them to use the edited content made by other sales representatives as reference.

[0045] The editorial department will build a system in which the generation AI automatically suggests synonyms and synonyms when editing, increasing the variety of conversations. For example, the editorial department will build a system in which the generation AI automatically suggests synonyms and synonyms when editing. For example, it will suggest replacing "purchase" with a synonym such as "acquire." The editorial department will also develop a system in which the generation AI automatically suggests synonyms and synonyms to increase the variety of conversations. For example, it will suggest replacing "effective" with a synonym such as "effective." The generation AI will also automatically suggest synonyms and synonyms when editing, increasing the variety of conversations. For example, it will suggest replacing "customer" with a synonym such as "client." This will suggest synonyms and synonyms, increasing the variety of conversations.

[0046] The sales talk generation unit can develop an algorithm that analyzes feedback information in detail and identifies which elements contributed to success. The sales talk generation unit, for example, analyzes feedback information in detail and develops an algorithm that identifies which elements contributed to success. For example, it identifies the factors that led to a particular phrase or question increasing the closing rate. It also builds a system in which the generation AI analyzes the factors for success based on the feedback information. For example, it identifies the factors for success based on customer reactions and the closing rate. It also analyzes feedback information in detail and develops an algorithm that identifies which elements contributed to success. For example, it identifies the factors that led to a particular talk pattern contributing to success. This makes it possible to develop an algorithm that analyzes feedback information in detail and identifies the factors for success.

[0047] The sales talk generation unit is capable of having the generation AI automatically evaluate the effectiveness of a sales talk after it has been conducted and generate a report proposing improvements. The sales talk generation unit, for example, builds a system in which the generation AI automatically evaluates the effectiveness of a sales talk after it has been conducted and generates a report proposing improvements. For example, it evaluates based on the closing rate and customer response. It also develops a system that automatically evaluates the effectiveness of a talk and generates a report proposing improvements. For example, it evaluates whether specific phrases or questions were effective. It also develops a system in which the generation AI automatically evaluates the effectiveness of a sales talk after it has been conducted and generates a report proposing improvements. For example, it proposes improvements based on customer response and closing rate. This makes it possible to evaluate the effectiveness of a sales talk after it has been conducted and generate a report proposing improvements.

[0048] The sales talk generation unit can share feedback information with other sales representatives and build a platform for improving overall sales skills. The sales talk generation unit, for example, shares feedback information with other sales representatives and builds a platform for improving overall sales skills. For example, it shares success stories and areas for improvement. It also develops a platform from which other sales representatives can learn based on the feedback information. For example, it shares cases where specific talk patterns or phrases were effective. It also shares feedback information with other sales representatives and builds a platform for improving overall sales skills. For example, it shares success stories and areas for improvement. In this way, it is possible to build a platform from which feedback information can be shared and overall sales skills can be improved.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The sales talk generation unit can automatically insert the customer's name and specific information into the generated talk, providing personalized talk. For example, we will build a system that automatically inserts the customer's name and specific information into the generated sales talk. For example, we will include a personalized greeting such as "Hello, Mr. / Ms. XX." The generation AI will also provide personalized talk based on the customer's specific information. For example, we will generate talk based on the customer's past purchase history. We will also develop a system that automatically inserts the customer's name and specific information into the generated talk, providing personalized talk. For example, we will include topics related to the customer's interests in the talk. This will allow us to insert the customer's name and specific information and provide personalized talk.

[0051] The sales talk generation unit can share feedback information with other sales representatives and build a platform for improving overall sales skills. For example, feedback information can be shared with other sales representatives to build a platform for improving overall sales skills. For example, success stories and areas for improvement can be shared. In addition, a platform can be developed based on the feedback information from which other sales representatives can learn. For example, cases in which specific talk patterns or phrases were effective can be shared. In addition, feedback information can be shared with other sales representatives to build a platform for improving overall sales skills. For example, success stories and areas for improvement can be shared. In this way, a platform can be built for sharing feedback information and improving overall sales skills.

[0052] The sales talk generation unit can automatically insert the customer's name and specific information into the generated talk, providing personalized talk. For example, we will build a system that automatically inserts the customer's name and specific information into the generated sales talk. For example, we will include a personalized greeting such as "Hello, Mr. / Ms. XX." The generation AI will also provide personalized talk based on the customer's specific information. For example, we will generate talk based on the customer's past purchase history. We will also develop a system that automatically inserts the customer's name and specific information into the generated talk, providing personalized talk. For example, we will include topics related to the customer's interests in the talk. This will allow us to insert the customer's name and specific information and provide personalized talk.

[0053] The sales talk generation unit can share feedback information with other sales representatives and build a platform for improving overall sales skills. For example, feedback information can be shared with other sales representatives to build a platform for improving overall sales skills. For example, success stories and areas for improvement can be shared. In addition, a platform can be developed based on the feedback information from which other sales representatives can learn. For example, cases in which specific talk patterns or phrases were effective can be shared. In addition, feedback information can be shared with other sales representatives to build a platform for improving overall sales skills. For example, success stories and areas for improvement can be shared. In this way, a platform can be built for sharing feedback information and improving overall sales skills.

[0054] The sales talk generation unit can automatically insert the customer's name and specific information into the generated talk, providing personalized talk. For example, we will build a system that automatically inserts the customer's name and specific information into the generated sales talk. For example, we will include a personalized greeting such as "Hello, Mr. / Ms. XX." The generation AI will also provide personalized talk based on the customer's specific information. For example, we will generate talk based on the customer's past purchase history. We will also develop a system that automatically inserts the customer's name and specific information into the generated talk, providing personalized talk. For example, we will include topics related to the customer's interests in the talk. This will allow us to insert the customer's name and specific information and provide personalized talk.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The customer information input unit inputs customer information. For example, basic customer information (such as name, age, gender, and occupation), past purchase history, and interests are input. For example, if a customer is interested in sports, that information is input. Step 2: The product information input section inputs product information. For example, the features, price, and advantages of the product to be sold are input. The purpose of the sales (introduction of a new product, upselling of an existing product, etc.) can also be input. For example, if the purpose is to introduce a new product, information emphasizing the features and advantages of the product is input. Step 3: The sales pitch generation unit generates a sales pitch based on the information entered by the customer information input unit and the product information input unit. For example, the generation AI generates a sales pitch by selecting appropriate topics, questions, humor, anecdotes, etc. according to the customer's personality, interests, and situation. For example, if the customer likes to travel, including a question such as "Where was your most recent trip?" can increase affinity with the customer. Step 4: The editing department edits the sales talk generated by the sales talk generator. For example, they can add additional information to the generated talk or modify specific parts. This allows salespeople to create talks that suit their own style.

[0057] (Example 2) The automatic sales talk generation system according to an embodiment of the present invention is a system that automatically generates optimal sales talks based on customer information, product information, sales objectives, etc. input by a sales representative. As a result, the automatic sales talk generation system can select appropriate topics, questions, humor, anecdotes, etc. according to the customer's personality, interests, and situation, and create effective sales talks.

[0058] A sales pitch automatic generation system according to an embodiment includes a customer information input unit, a product information input unit, a sales pitch generation unit, and an editing unit. The customer information input unit inputs customer information. For example, basic customer information (such as name, age, gender, and occupation) can be input. The customer's past purchase history and interests can also be input. For example, if the customer is interested in sports, that information can be input. The product information input unit inputs product information. For example, the product information input unit inputs the features, price, and advantages of a product to be sold. The sales objective (such as introducing a new product or upselling an existing product) can also be input. For example, if the objective is to introduce a new product, information emphasizing the features and advantages of the product can be input. The sales pitch generation unit generates a sales pitch based on the information input by the customer information input unit and the product information input unit. For example, the generation AI selects appropriate topics, questions, humor, anecdotes, etc. according to the customer's personality, interests, and situation to generate the sales pitch. For example, if the customer likes to travel, including a question such as, "Where was your most recent trip?" can increase familiarity with the customer. The editing unit edits the sales pitch generated by the sales pitch generation unit. For example, additional information can be added to the generated talk or specific parts can be modified. This allows salespeople to create talks that suit their own style. As a result, the sales talk automatic generation system according to the embodiment can generate and edit optimal sales talks based on customer information and product information.

[0059] The customer information input unit collects public information from the customer's social media account, and the generation AI analyzes that information to identify the customer's latest interests. The customer information input unit, for example, collects public posts and profile information from the customer's social media account, and the generation AI analyzes the content. For example, if the customer has recently posted many posts about "travel," the generation AI can incorporate travel-related topics into the sales pitch. The generation AI can also analyze the customer's social media behavior history, such as "likes" and "shares," to identify topics of interest. For example, if the customer has "liked" many sports-related posts, the generation AI can incorporate sports-related topics into the sales pitch. The generation AI can also identify the customer's hobbies and interests based on the information collected from the customer's social media account and generate a personalized sales pitch based on that information. For example, if the customer is interested in music festivals, the generation AI can include that topic in the pitch. This allows the customer's latest interests to be identified and reflected in the sales pitch.

[0060] The customer information input unit analyzes a customer's past purchase history, browsing history, and information on products added to their cart, allowing for a more detailed understanding of their interests. For example, the customer information input unit analyzes a customer's past purchase history to identify what products the customer is interested in. For example, if the customer has purchased many electronic devices in the past, the customer information input unit can incorporate topics related to the latest gadgets into their sales pitch. The customer information input unit can also analyze the customer's website browsing history to identify which pages the customer frequently visits. For example, if the customer frequently visits pages for outdoor equipment, the customer can incorporate topics related to outdoor activities into their sales pitch. The customer information input unit can also analyze information on products the customer added to their cart but did not purchase, allowing for a more detailed understanding of the customer's interests in those products. For example, the customer information input unit can include topics related to luxury watches the customer added to their cart but did not purchase in the sales pitch. This allows for a more detailed understanding of the customer's interests and reflects them in their sales pitch.

[0061] The customer information input unit can use the emotion estimation function to analyze the customer's emotions at the time of past purchases and select topics that will elicit positive emotions. The customer information input unit, for example, analyzes reviews and feedback from the customer's past purchases and selects topics that will elicit positive emotions. For example, if the customer has given a high rating to a product they have purchased in the past, topics related to that product can be incorporated into the sales talk. The customer's emotions at the time of purchase can also be analyzed and anecdotes that will elicit positive emotions can be selected. For example, topics that emphasize the points about which the customer is particularly satisfied with products they have purchased in the past can be included in the talk. The emotion estimation function can also be used to analyze the customer's emotions at the time of past purchases and select questions that will elicit positive emotions. For example, questions that ask about the points about which the customer particularly liked about products they have purchased in the past can be included in the talk. In this way, topics that will elicit positive emotions from the customer can be selected and reflected in the sales talk.

[0062] The customer information input unit enables voice input, allowing sales representatives to input information verbally. The customer information input unit, for example, builds a system that allows sales representatives to input customer information by voice. For example, using voice recognition technology, the sales representative verbally inputs information such as the customer's name and occupation. Also, using a voice input function, the sales representative can verbally input the customer's interests and past purchase history. For example, the sales representative verbally inputs, "This customer is interested in sports." Also, using voice input, a system is developed that allows sales representatives to quickly input customer information. For example, the sales representative verbally inputs, "This customer is a man in his 30s who has purchased many electronic devices in the past." This allows sales representatives to input customer information by voice.

[0063] The customer information input unit collects information about the customer's family structure and pets when entering customer information, making it possible to generate more personalized sales talks. The customer information input unit, for example, builds a system that collects information about the customer's family structure and pets when entering customer information. For example, a customer enters information such as "I have a wife and two children." Furthermore, based on the information about the family structure and pets, a more personalized sales talk is generated. For example, based on information such as "I have a dog," a topic about pets is included in the talk. Furthermore, information about the customer's family structure and pets is collected, and a personalized sales talk is generated based on that information. For example, based on information such as "My child plays soccer," a topic about soccer is included in the talk. In this way, a more personalized sales talk can be generated by collecting information about the customer's family structure and pets.

[0064] The customer information input unit uses an emotion estimation function to analyze in real time what emotions a customer has toward the input information and adjust the input content. The customer information input unit, for example, uses the emotion estimation function to build a system that analyzes in real time what emotions a customer has toward the input information. For example, if a customer has positive emotions toward the input information, that information is emphasized. Also, a system is developed that analyzes a customer's emotional response in real time and adjusts the input content. For example, if a customer has negative emotions toward the input information, that information is corrected. Also, a system is built that uses the emotion estimation function to analyze what emotions a customer has toward the input information and optimizes the input content. For example, if a customer has positive emotions toward the input information, a sales pitch is generated based on that information. In this way, customer emotions can be analyzed in real time and the input content can be adjusted.

[0065] The sales talk generation unit inputs information about competing products in addition to product information, and the generation AI can compare them and generate talk that emphasizes their superiority. The sales talk generation unit builds a system in which, for example, product information and information about competing products are input, and the generation AI compares them and generates talk that emphasizes their superiority. For example, it emphasizes the features and advantages of one's own product. Also, based on information about competing products, the generation AI generates talk that emphasizes the superiority of one's own product. For example, it emphasizes the lower price and superior functionality compared to competing products. Also, product information and information about competing products are input, and the generation AI compares them and generates talk that emphasizes their superiority. For example, it emphasizes the higher durability and superior design compared to competing products. This makes it possible to generate talk that emphasizes the superiority of one's own product compared to competing products.

[0066] The sales talk generation unit can input product usage scenarios and case studies and generate talks that include specific usage scenarios. The sales talk generation unit builds a system in which, for example, product usage scenarios and case studies are input and a generation AI generates talks that include specific usage scenarios. For example, it specifically explains how to use the product and its effects. Furthermore, based on the case study, the generation AI generates talks that include specific usage scenarios. For example, it creates talks based on past success stories and customer feedback. Furthermore, product usage scenarios are input and the generation AI generates talks that include specific usage scenarios. For example, it specifically explains how to use the product and its effects. This makes it possible to generate talks that include specific usage scenarios.

[0067] The sales talk generation unit can use the emotion estimation function to predict the emotions a customer will have toward a product and generate talk that corresponds to those emotions. The sales talk generation unit, for example, uses the emotion estimation function to build a system that predicts the emotions a customer will have toward a product and generates talk that corresponds to those emotions. For example, topics related to products for which the customer has positive emotions are included in the talk. Also, a system is developed that predicts the emotional reactions of customers and generates talk that corresponds to those emotions. For example, topics related to products for which the customer has negative emotions are avoided. Also, the emotion estimation function is used to predict the emotions a customer will have toward a product and generate talk that corresponds to those emotions. For example, topics related to products for which the customer has positive emotions are included in the talk. In this way, talk that corresponds to the customer's emotions can be generated.

[0068] The sales talk generation unit can attach videos and images when entering product information, and use visual information for analysis. The sales talk generation unit will build a system that allows videos and images to be attached when entering product information. For example, a promotional video for the product or product images can be uploaded. In addition, a system will be developed in which a generation AI analyzes visual information based on videos and images and reflects it in sales talks. For example, a talk will be created based on a video that shows how to use the product. In addition, a system will be built in which videos and images can be attached when entering product information, and visual information will be used for analysis. For example, a talk will be created based on an image that shows the product's features. This will allow visual information to be used for analysis and reflected in sales talks.

[0069] The sales talk generation unit can select different talk styles (e.g., casual, formal) depending on the sales purpose. The sales talk generation unit builds a system that can select different talk styles depending on the sales purpose. For example, it selects a casual talk style or a formal talk style. Also, a system is developed in which the generation AI selects the optimal talk style depending on the sales purpose. For example, it selects a casual talk style for introducing a new product. Also, a system is built in which a different talk style can be selected depending on the sales purpose. For example, it selects a formal talk style for upselling an existing product. This makes it possible to select a talk style depending on the sales purpose.

[0070] The sales talk generation unit can use the emotion estimation function to predict the customer's emotional reaction to product information entered by a sales representative and adjust the talk content. The sales talk generation unit, for example, uses the emotion estimation function to build a system that predicts the customer's emotional reaction to product information entered by a sales representative and adjusts the talk content. For example, topics related to products for which the customer has positive feelings are included in the talk. A system is also developed that predicts the customer's emotional reaction and adjusts the talk content based on the results. For example, topics related to products for which the customer has negative feelings are avoided. A system is also built that uses the emotion estimation function to predict the customer's emotional reaction to product information entered by a sales representative and optimizes the talk content. For example, topics related to products for which the customer has positive feelings are included in the talk. This makes it possible to predict the customer's emotional reaction and adjust the talk content.

[0071] The sales talk generation unit can refer to a database of past successful sales talks and incorporate the most effective patterns. For example, the sales talk generation unit builds a system in which the generation AI refers to a database of past successful sales talks and incorporates the most effective patterns. For example, it generates new talks based on talk patterns that have boasted high closing rates in the past. It also analyzes the database of successful sales talks and extracts common effective elements. For example, if a particular phrase or question is used frequently, it can incorporate it into the new talk. The generation AI also learns from past success stories and generates the optimal sales talk based on that knowledge. For example, it can reflect talk patterns that were effective with a particular customer demographic in the new talk. In this way, effective talks can be generated by incorporating patterns from past successful sales talks.

[0072] The sales talk generation unit can generate talk that is specific to a region, taking into account the customer's cultural background and regional characteristics. The sales talk generation unit, for example, builds a system in which the generation AI generates talk that is specific to a region, taking into account the customer's cultural background and regional characteristics. For example, topics related to local events and culture are included in the talk. The generation AI also generates optimal talk based on the customer's regional characteristics. For example, talk that incorporates local dialects and unique expressions is created. A system is also developed in which the generation AI generates talk that is familiar to customers, taking into account their cultural background. For example, topics related to local traditions and customs are included in the talk. This makes it possible to generate talk that takes into account the customer's cultural background and regional characteristics.

[0073] The sales talk generation unit can use the emotion estimation function to select humor and anecdotes that correspond to the customer's emotions and incorporate them into the talk. The sales talk generation unit, for example, uses the emotion estimation function to build a system that selects humor and anecdotes that correspond to the customer's emotions and incorporates them into the talk. For example, if the customer has positive emotions, it generates a talk that includes humor. It also develops a system that analyzes the customer's emotional response and selects humor and anecdotes based on the results. For example, if the customer is relaxed, it creates a talk that includes light jokes. It also uses the emotion estimation function to select anecdotes that correspond to the customer's emotions and incorporate them into the talk. For example, it includes anecdotes that the customer is likely to be interested in. This makes it possible to incorporate humor and anecdotes that correspond to the customer's emotions into the talk.

[0074] When generating a sales talk, the sales talk generation unit can simultaneously generate multiple variations, allowing sales representatives to choose from. For example, the sales talk generation unit will build a system in which a generation AI simultaneously generates multiple sales talk variations, allowing sales representatives to choose from. For example, it will generate both casual and formal talk. It will also generate sales talk variations, allowing sales representatives to select the most appropriate talk. For example, it will switch talks depending on the customer's reaction. It will also develop a system that generates multiple talk variations, allowing sales representatives to choose according to the situation. For example, it will prepare multiple talks that suit the customer's personality and interests. This will generate multiple talk variations, allowing sales representatives to choose from.

[0075] The sales talk generation unit can automatically insert the customer's name and specific information into the generated talk, thereby providing personalized talk. For example, the sales talk generation unit builds a system that automatically inserts the customer's name and specific information into the generated sales talk. For example, it includes a personalized greeting such as "Hello, Mr. / Ms. XX." In addition, the generation AI provides personalized talk based on the customer's specific information. For example, it generates talk based on the customer's past purchase history. In addition, it develops a system that automatically inserts the customer's name and specific information into the generated talk, thereby providing personalized talk. For example, it includes topics related to the customer's interests in the talk. This makes it possible to insert the customer's name and specific information and provide personalized talk.

[0076] The sales talk generation unit can use the emotion estimation function to predict the customer's emotional response to the generated talk and select the optimal talk. The sales talk generation unit, for example, uses the emotion estimation function to predict the customer's emotional response to the generated talk and builds a system that selects the optimal talk. For example, talk in which the customer has positive emotions is preferentially selected. Also, a system is developed that predicts the customer's emotional response and selects the optimal talk based on the results. For example, if the customer is relaxed, talk that matches that emotion is selected. Also, the emotion estimation function is used to predict the customer's emotional response to the generated talk and select the optimal talk. For example, talk that is likely to interest the customer is preferentially selected. In this way, the customer's emotional response can be predicted and the optimal talk can be selected.

[0077] The editorial department will build a system in which, for example, when a sales representative edits a talk, the generation AI will provide feedback in real time and suggest optimal revisions. For example, it will suggest areas for improvement in the content of the talk. The editorial department will also develop a system in which the generation AI will analyze the edits made by the sales representative and suggest optimal revisions in real time. For example, it will make suggestions to make the flow of the talk smoother. The generation AI will also provide feedback in real time when a sales representative edits a talk and suggest optimal revisions. For example, it will suggest revisions to the talk to match the customer's interests. This will enable the editorial department to provide feedback in real time and suggest optimal revisions when a sales representative edits a talk.

[0078] The editorial department can add a function to save the editing history and analyze which edits were most effective. For example, the editorial department will build a system that saves the editing history of sales talks and analyzes which edits were most effective. For example, it will identify the edited content of talks that had a high conversion rate. It will also develop a system that uses the editing history to enable the generative AI to learn the most effective editing patterns. For example, if a particular phrase or question was effective, it will reflect that in the next talk. It will also add a function to save the editing history of sales talks and analyze which edits were most effective. For example, it will identify the edits that received a good response from customers. This will allow it to save the editing history and analyze effective edits.

[0079] The editorial department can use the emotion estimation function to predict the emotional impact that edited talk will have on customers and suggest optimal edits. The editorial department, for example, uses the emotion estimation function to build a system that predicts the emotional impact that edited talk will have on customers and suggests optimal edits. For example, it proposes editing suggestions that elicit positive emotions. The editorial department also develops a system that predicts the emotional impact of edited talk and suggests optimal edits based on the results. For example, it proposes editing suggestions that will relax customers. The editorial department also uses the emotion estimation function to predict the emotional impact that edited talk will have on customers and suggests optimal edits. For example, it proposes editing suggestions that will likely interest customers. This makes it possible to predict the emotional impact that edited talk will have on customers and suggest optimal edits.

[0080] The editing department can display examples of edits made by other sales representatives on the sales talk editing screen, allowing them to use them as reference. The editing department, for example, builds a system that displays examples of edits made by other sales representatives on the sales talk editing screen. For example, they can use the edited content of successful talks as reference. They also develop a system that displays examples of edits made by other sales representatives, allowing sales representatives to use them as reference. For example, they can display edited content that was effective for a specific customer demographic. They can also display examples of edits made by other sales representatives on the sales talk editing screen, allowing them to use them as reference. For example, they can present editing suggestions based on past success stories. This allows them to use the edited content made by other sales representatives as reference.

[0081] The editorial department will build a system in which the generation AI automatically suggests synonyms and synonyms when editing, increasing the variety of conversations. For example, the editorial department will build a system in which the generation AI automatically suggests synonyms and synonyms when editing. For example, it will suggest replacing "purchase" with a synonym such as "acquire." The editorial department will also develop a system in which the generation AI automatically suggests synonyms and synonyms to increase the variety of conversations. For example, it will suggest replacing "effective" with a synonym such as "effective." The generation AI will also automatically suggest synonyms and synonyms when editing, increasing the variety of conversations. For example, it will suggest replacing "customer" with a synonym such as "client." This will suggest synonyms and synonyms, increasing the variety of conversations.

[0082] The editorial department can use the emotion estimation function to predict customers' emotional reactions to edited talk in real time and encourage optimal editing. The editorial department, for example, uses the emotion estimation function to build a system that predicts customers' emotional reactions to edited talk in real time. For example, it presents editing suggestions that elicit positive emotions. The editorial department also develops a system that predicts the emotional impact of edited talk in real time and encourages optimal editing based on the results. For example, it presents editing suggestions that will relax customers. The editorial department also uses the emotion estimation function to predict customers' emotional reactions to edited talk in real time and encourages optimal editing. For example, it presents editing suggestions that will likely interest customers. In this way, it is possible to predict customers' emotional reactions to edited talk in real time and encourage optimal editing.

[0083] The sales talk generation unit uses a generation AI to analyze customer reactions in real time while a sales talk is being conducted and suggest adjustments to the talk. The sales talk generation unit, for example, builds a system in which a generation AI analyzes customer reactions in real time while a sales talk is being conducted and suggests adjustments to the talk. For example, it emphasizes topics that interest the customer. It also develops a system that analyzes customer reactions in real time and suggests adjustments to the talk based on the results. For example, if a customer has a negative reaction, it changes the topic. It also analyzes customer reactions in real time while a sales talk is being conducted and suggests adjustments to the talk. For example, if a customer has a positive reaction, it delves deeper into that topic. This makes it possible to analyze customer reactions in real time while a sales talk is being conducted and suggest adjustments to the talk.

[0084] The sales talk generation unit can develop an algorithm that analyzes feedback information in detail and identifies which elements contributed to success. The sales talk generation unit, for example, analyzes feedback information in detail and develops an algorithm that identifies which elements contributed to success. For example, it identifies the factors that led to a particular phrase or question increasing the closing rate. It also builds a system in which the generation AI analyzes the factors for success based on the feedback information. For example, it identifies the factors for success based on customer reactions and the closing rate. It also analyzes feedback information in detail and develops an algorithm that identifies which elements contributed to success. For example, it identifies the factors that led to a particular talk pattern contributing to success. This makes it possible to develop an algorithm that analyzes feedback information in detail and identifies the factors for success.

[0085] The sales talk generation unit can use the emotion estimation function to analyze the customer's emotions from the feedback information and reflect them in the next talk. The sales talk generation unit, for example, uses the emotion estimation function to build a system that analyzes the customer's emotions from the feedback information and reflects them in the next talk. For example, talk that elicits positive emotions can be incorporated into the next talk. A system can also be developed that analyzes the customer's emotions based on the feedback information and reflects the results in the next talk. For example, talk that avoids negative emotions can be incorporated into the next talk. The emotion estimation function can also be used to analyze the customer's emotions from the feedback information and reflect them in the next talk. For example, topics that are likely to interest the customer can be incorporated into the next talk. This makes it possible to analyze the customer's emotions from the feedback information and reflect them in the next talk.

[0086] The sales talk generation unit is capable of having the generation AI automatically evaluate the effectiveness of a sales talk after it has been conducted and generate a report proposing improvements. The sales talk generation unit, for example, builds a system in which the generation AI automatically evaluates the effectiveness of a sales talk after it has been conducted and generates a report proposing improvements. For example, it evaluates based on the closing rate and customer response. It also develops a system that automatically evaluates the effectiveness of a talk and generates a report proposing improvements. For example, it evaluates whether specific phrases or questions were effective. It also develops a system in which the generation AI automatically evaluates the effectiveness of a sales talk after it has been conducted and generates a report proposing improvements. For example, it proposes improvements based on customer response and closing rate. This makes it possible to evaluate the effectiveness of a sales talk after it has been conducted and generate a report proposing improvements.

[0087] The sales talk generation unit can share feedback information with other sales representatives and build a platform for improving overall sales skills. The sales talk generation unit, for example, shares feedback information with other sales representatives and builds a platform for improving overall sales skills. For example, it shares success stories and areas for improvement. It also develops a platform from which other sales representatives can learn based on the feedback information. For example, it shares cases where specific talk patterns or phrases were effective. It also shares feedback information with other sales representatives and builds a platform for improving overall sales skills. For example, it shares success stories and areas for improvement. In this way, it is possible to build a platform from which feedback information can be shared and overall sales skills can be improved.

[0088] The sales talk generation unit can use the emotion estimation function to track changes in customer emotions from feedback information and use the results to build long-term relationships. The sales talk generation unit, for example, uses the emotion estimation function to build a system that tracks changes in customer emotions from feedback information and uses the results to build long-term relationships. For example, the sales talk generation unit adjusts the talk based on changes in customer emotions. A system is also developed that tracks changes in customer emotions based on feedback information and uses the results to build long-term relationships. For example, the sales talk generation unit adjusts the talk based on changes in customer emotions. A system is also developed that tracks changes in customer emotions from feedback information and uses the results to build long-term relationships. For example, the sales talk generation unit adjusts the talk based on changes in customer emotions. The sales talk generation unit can use the emotion estimation function to track changes in customer emotions from feedback information and use the results to build long-term relationships. For example, the sales talk generation unit adjusts the talk based on changes in customer emotions. This makes it possible to track changes in customer emotions from feedback information and use the results to build long-term relationships.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The sales talk generation unit can automatically insert the customer's name and specific information into the generated talk, providing personalized talk. For example, we will build a system that automatically inserts the customer's name and specific information into the generated sales talk. For example, we will include a personalized greeting such as "Hello, Mr. / Ms. XX." The generation AI will also provide personalized talk based on the customer's specific information. For example, we will generate talk based on the customer's past purchase history. We will also develop a system that automatically inserts the customer's name and specific information into the generated talk, providing personalized talk. For example, we will include topics related to the customer's interests in the talk. This will allow us to insert the customer's name and specific information and provide personalized talk.

[0091] The sales talk generation unit uses a generation AI to analyze customer reactions in real time while a sales talk is being conducted and suggest adjustments to the talk. For example, we will build a system in which a generation AI analyzes customer reactions in real time while a sales talk is being conducted and suggests adjustments to the talk. For example, it may highlight topics that interest the customer. We will also develop a system that analyzes customer reactions in real time and suggests adjustments to the talk based on the results. For example, if a customer has a negative reaction, it will change the topic. Furthermore, while a sales talk is being conducted, the generation AI will analyze customer reactions in real time and suggest adjustments to the talk. For example, if a customer has a positive reaction, it will dig deeper into that topic. This makes it possible to analyze customer reactions in real time while a sales talk is being conducted and suggest adjustments to the talk.

[0092] The sales talk generation unit can share feedback information with other sales representatives and build a platform for improving overall sales skills. For example, feedback information can be shared with other sales representatives to build a platform for improving overall sales skills. For example, success stories and areas for improvement can be shared. In addition, a platform can be developed based on the feedback information from which other sales representatives can learn. For example, cases in which specific talk patterns or phrases were effective can be shared. In addition, feedback information can be shared with other sales representatives to build a platform for improving overall sales skills. For example, success stories and areas for improvement can be shared. In this way, a platform can be built for sharing feedback information and improving overall sales skills.

[0093] The sales talk generation unit can use the emotion estimation function to analyze the customer's emotions from the feedback information and reflect them in the next talk. For example, a system can be built that uses the emotion estimation function to analyze the customer's emotions from the feedback information and reflect them in the next talk. For example, a talk that elicits positive emotions can be incorporated into the next talk. A system can also be developed that analyzes the customer's emotions based on the feedback information and reflects the results in the next talk. For example, a talk that avoids negative emotions can be incorporated into the next talk. The emotion estimation function can also be used to analyze the customer's emotions from the feedback information and reflect them in the next talk. For example, a topic that is likely to interest the customer can be incorporated into the next talk. This makes it possible to analyze the customer's emotions from the feedback information and reflect them in the next talk.

[0094] The sales talk generation unit can automatically insert the customer's name and specific information into the generated talk, providing personalized talk. For example, we will build a system that automatically inserts the customer's name and specific information into the generated sales talk. For example, we will include a personalized greeting such as "Hello, Mr. / Ms. XX." The generation AI will also provide personalized talk based on the customer's specific information. For example, we will generate talk based on the customer's past purchase history. We will also develop a system that automatically inserts the customer's name and specific information into the generated talk, providing personalized talk. For example, we will include topics related to the customer's interests in the talk. This will allow us to insert the customer's name and specific information and provide personalized talk.

[0095] The sales talk generation unit uses a generation AI to analyze customer reactions in real time while a sales talk is being conducted and suggest adjustments to the talk. For example, we will build a system in which a generation AI analyzes customer reactions in real time while a sales talk is being conducted and suggests adjustments to the talk. For example, it may highlight topics that interest the customer. We will also develop a system that analyzes customer reactions in real time and suggests adjustments to the talk based on the results. For example, if a customer has a negative reaction, it will change the topic. Furthermore, while a sales talk is being conducted, the generation AI will analyze customer reactions in real time and suggest adjustments to the talk. For example, if a customer has a positive reaction, it will dig deeper into that topic. This makes it possible to analyze customer reactions in real time while a sales talk is being conducted and suggest adjustments to the talk.

[0096] The sales talk generation unit can share feedback information with other sales representatives and build a platform for improving overall sales skills. For example, feedback information can be shared with other sales representatives to build a platform for improving overall sales skills. For example, success stories and areas for improvement can be shared. In addition, a platform can be developed based on the feedback information from which other sales representatives can learn. For example, cases in which specific talk patterns or phrases were effective can be shared. In addition, feedback information can be shared with other sales representatives to build a platform for improving overall sales skills. For example, success stories and areas for improvement can be shared. In this way, a platform can be built for sharing feedback information and improving overall sales skills.

[0097] The sales talk generation unit can use the emotion estimation function to analyze the customer's emotions from the feedback information and reflect them in the next talk. For example, a system can be built that uses the emotion estimation function to analyze the customer's emotions from the feedback information and reflect them in the next talk. For example, a talk that elicits positive emotions can be incorporated into the next talk. A system can also be developed that analyzes the customer's emotions based on the feedback information and reflects the results in the next talk. For example, a talk that avoids negative emotions can be incorporated into the next talk. The emotion estimation function can also be used to analyze the customer's emotions from the feedback information and reflect them in the next talk. For example, a topic that is likely to interest the customer can be incorporated into the next talk. This makes it possible to analyze the customer's emotions from the feedback information and reflect them in the next talk.

[0098] The sales talk generation unit can automatically insert the customer's name and specific information into the generated talk, providing personalized talk. For example, we will build a system that automatically inserts the customer's name and specific information into the generated sales talk. For example, we will include a personalized greeting such as "Hello, Mr. / Ms. XX." The generation AI will also provide personalized talk based on the customer's specific information. For example, we will generate talk based on the customer's past purchase history. We will also develop a system that automatically inserts the customer's name and specific information into the generated talk, providing personalized talk. For example, we will include topics related to the customer's interests in the talk. This will allow us to insert the customer's name and specific information and provide personalized talk.

[0099] The sales talk generation unit uses a generation AI to analyze customer reactions in real time while a sales talk is being conducted and suggest adjustments to the talk. For example, we will build a system in which a generation AI analyzes customer reactions in real time while a sales talk is being conducted and suggests adjustments to the talk. For example, it may highlight topics that interest the customer. We will also develop a system that analyzes customer reactions in real time and suggests adjustments to the talk based on the results. For example, if a customer has a negative reaction, it will change the topic. Furthermore, while a sales talk is being conducted, the generation AI will analyze customer reactions in real time and suggest adjustments to the talk. For example, if a customer has a positive reaction, it will dig deeper into that topic. This makes it possible to analyze customer reactions in real time while a sales talk is being conducted and suggest adjustments to the talk.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The customer information input unit inputs customer information. For example, basic customer information (such as name, age, gender, and occupation), past purchase history, and interests are input. For example, if a customer is interested in sports, that information is input. Step 2: The product information input section inputs product information. For example, the features, price, and advantages of the product to be sold are input. The purpose of the sales (introduction of a new product, upselling of an existing product, etc.) can also be input. For example, if the purpose is to introduce a new product, information emphasizing the features and advantages of the product is input. Step 3: The sales pitch generation unit generates a sales pitch based on the information entered by the customer information input unit and the product information input unit. For example, the generation AI generates a sales pitch by selecting appropriate topics, questions, humor, anecdotes, etc. according to the customer's personality, interests, and situation. For example, if the customer likes to travel, including a question such as "Where was your most recent trip?" can increase affinity with the customer. Step 4: The editing department edits the sales talk generated by the sales talk generator. For example, they can add additional information to the generated talk or modify specific parts. This allows salespeople to create talks that suit their own style.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0114] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0115] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0116] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0117] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0118] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] The data processing system 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.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0128] 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.

[0129] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0130] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0136] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0146] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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."

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0168] 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]

[0169] 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 information input unit for inputting customer information; a product information input unit for inputting product information; a sales talk generation unit that generates a sales talk based on the information input by the customer information input unit and the product information input unit; an editing unit that edits the sales talk generated by the sales talk generation unit; A system characterized by:

2. The customer information input unit Public information is collected from customers' social media accounts, and the generation AI analyzes the information to identify the customers' latest interests.

2. The system of claim 1.

3. The customer information input unit Analyze customers' past purchase history, browsing history, and cart information to understand their interests in more detail 2. The system of claim 1.

4. The customer information input unit Analyze the customer's emotions during past purchases and select topics that will elicit positive emotions 2. The system of claim 1.

5. The customer information input unit Enables voice input, allowing salespeople to enter information verbally 2. The system of claim 1.

Images