System

Abstract

An object of the system according to the embodiment is to efficiently collect requests and opinions from customers and utilize them for product development and proposal.SOLUTION: A system according to an embodiment includes a request collection unit, a product information collection unit, a product information storage unit, and an inquiry handling unit. The request collection unit collects requests and opinions using the generated AI. The commodity information collection part collects commodity information from a Web site. The commodity information storage part stores the collected commodity information. The inquiry handling unit automates sending of an answer or a sample to the inquiry.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 had the problem of not being able to efficiently collect customer requests and opinions and fully utilize them in product development and proposals.

[0005] The system according to the embodiment aims to efficiently collect requests and opinions from customers and use them in product development and proposals. [Means for solving the problem]

[0006] The system according to the embodiment includes a request collection unit, a product information collection unit, a product information storage unit, and an inquiry response unit. The request collection unit uses a generation AI to collect requests and opinions. The product information collection unit collects product information from websites. The product information storage unit stores the collected product information. The inquiry response unit automates responses to inquiries and the delivery of samples. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently collect requests and opinions from customers and use them in product development and proposals. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The product development and proposal system according to an embodiment of the present invention automates product development and proposal processes by utilizing generative AI, RAG, and LLM. This system uses generative AI to collect and learn from daily customer requests and opinions, thereby identifying customer needs and effectively utilizing them in product development. It can also collect product information from websites and use AI to suggest products desired by customers. Furthermore, when inquiries are received, this information can be used by product search and proposals by product representatives. RAG is used to accumulate product information, and LLM is used to automate inquiry responses and sample delivery. This allows the product development and proposal system to establish a system for instantly automating product proposals, sample provision, and contacting distributors based on customer inquiries, enabling instant proposals to meet existing customer needs.

[0029] A product development and proposal system according to an embodiment includes a request collection unit, a product information collection unit, a product information storage unit, and an inquiry response unit. The request collection unit collects requests and opinions using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to collect customer requests and opinions. The generation AI can also collect requests and opinions from voice and image data using a multimodal generation AI. The generation AI also uses natural language processing technology to analyze the content of the requests and opinions and understand what needs exist. For example, the generation AI uses a text generation AI to extract key points from the requests and opinions and use them in product development. The product information collection unit collects product information from websites. For example, the product information collection unit uses web scraping technology to collect information such as product features, prices, and stock status from websites. The product information collection unit can also acquire product information from websites using an API. For example, the product information collection unit acquires detailed product information using a specific API. The product information storage unit stores the collected product information. For example, the product information storage unit uses a database to efficiently manage collected product information. The product information storage unit also uses RAG to organize product information and quickly retrieve necessary information. For example, the product information storage unit uses RAG to store product lifecycle and trend information, enabling long-term proposals. The inquiry response unit automates responses to inquiries and the delivery of samples. For example, the inquiry response unit uses LLM to analyze the content of inquiries and generate appropriate responses. The inquiry response unit can also automate sample delivery procedures using LLM. For example, the inquiry response unit uses LLM to process sample delivery procedures and respond quickly. As a result, the product development and proposal system according to the embodiment automates and efficiently performs processes from collecting requests and opinions to storing product information and responding to inquiries. For example, the output unit displays the proposal results to customers via a web application or a mobile application. If feedback on paper is desired, the results can be printed using a printer.Email submission provides immediate feedback by sending results directly to you.

[0030] The request collection unit can extract more personalized needs by referring to the user's past purchase history and browsing history when collecting requests and opinions. The request collection unit, for example, can extract personalized needs by referring to the user's past purchase history when collecting requests and opinions. For example, the generation AI analyzes the user's past purchase history and prioritizes collecting related requests. The request collection unit can also extract personalized needs by referring to the user's past browsing history. For example, the generation AI analyzes the user's past browsing history and prioritizes collecting related requests. In this way, more personalized needs can be extracted by referring to the user's past purchase history and browsing history.

[0031] The request collection unit collects requests and opinions not only from text but also from voice and image data, making it possible to utilize multimodal information. The request collection unit, for example, collects requests and opinions not only from text but also from voice data. For example, the generation AI uses voice recognition technology to convert voice data into text, which is then analyzed by the generation AI. The request collection unit can also collect requests and opinions from image data. For example, the generation AI uses image recognition technology to analyze image data and extract requests and opinions. This makes it possible to collect requests and opinions not only from text but also from voice and image data, making it possible to utilize multimodal information.

[0032] The request collection unit can collect requests from different industries and fields to promote crossover innovation. For example, the generative AI could combine requests from the medical and technology fields to develop a new product. The request collection unit can also collect requests from different fields to promote crossover innovation. For example, the generative AI could combine requests from the consumer market and technology fields to develop a new product. This allows the collection of requests from different industries and fields to promote crossover innovation.

[0033] The generation AI analyzes not only product features, price, and availability, but also user reviews and ratings, allowing for more accurate suggestions. The generation AI, for example, not only analyzes product features, price, and availability, but also analyzes user reviews and ratings. For example, the generation AI uses text generation AI (e.g., LLM) to calculate an emotional score for user reviews and reflect this in product suggestions. The generation AI can also use multimodal generation AI to analyze user reviews and ratings from voice and image data. For example, the generation AI analyzes the tone and speed of voice data to calculate an emotional score. The generation AI also analyzes facial expressions in image data to calculate an emotional score. This allows for more accurate suggestions by analyzing not only product features, price, and availability, but also user reviews and ratings.

[0034] When collecting product information, the generation AI can simultaneously collect information on competitors and perform comparative analysis. For example, when collecting product information, the generation AI can simultaneously collect information on competitors and perform comparative analysis. For example, the generation AI can use text generation AI (e.g., LLM) to analyze the prices and features of competing products and reflect this in proposals. The generation AI can also use multimodal generation AI to collect information on competitors from voice and image data and perform comparative analysis. For example, the generation AI can analyze the tone and speed of voice data to extract the features of competing products. The generation AI can also analyze facial expressions in image data to extract the features of competing products. In this way, by simultaneously collecting information on competitors when collecting product information and performing comparative analysis, more accurate proposals can be made.

[0035] The generative AI can collect product information not only from text data but also from image and video data, making use of visual information. The generative AI can, for example, collect product information not only from text data but also from image data. For example, the generative AI can use image recognition technology to analyze product images and have the generative AI learn from them. The generative AI can also collect product information from video data. For example, the generative AI can use video recognition technology to analyze video data and extract product information. This allows the generative AI to collect product information not only from text data but also from image and video data, making use of visual information.

[0036] Generative AI can collect information on products from different industries and applications and discover new market needs. For example, generative AI can collect information on products from different industries and discover new market needs. For example, generative AI can collect product information that combines the technology field and the consumer market and discover new market needs. Generative AI can also collect information on products from different applications and discover new market needs. For example, generative AI can collect information on products from the medical and technology fields and discover new market needs. This makes it possible to collect information on products from different industries and applications and discover new market needs.

[0037] When accumulating product information, RAG simultaneously accumulates product lifecycle and trend information, enabling long-term proposals. For example, when accumulating product information, RAG simultaneously accumulates product lifecycle information. For example, RAG includes information such as the product's release date, improvement history, and discontinuation schedule. RAG can also simultaneously accumulate trend information. For example, RAG accumulates information on changes in fashion and consumer preferences. This allows product lifecycle and trend information to be simultaneously accumulated when accumulating product information, enabling long-term proposals.

[0038] RAG can reflect user feedback and ratings when accumulating product information, thereby providing more accurate information. For example, RAG can reflect user feedback and ratings when accumulating product information. For example, RAG can add user reviews and rating scores to product information. RAG can also update product information based on user feedback. For example, RAG can modify product information based on user comments and ratings. This allows user feedback and ratings to be reflected when accumulating product information, thereby providing more accurate information.

[0039] RAG accumulates product information not only from text data but also from image and video data, making it possible to utilize visual information. For example, RAG accumulates product information not only from text data but also from image data. For example, RAG uses image recognition technology to analyze product images and accumulate the information in the RAG. RAG can also accumulate product information from video data. For example, RAG uses video recognition technology to analyze video data and extract product information. This allows product information to be accumulated not only from text data but also from image and video data, making it possible to utilize visual information.

[0040] RAG can accumulate information on products from different industries and applications and discover new market needs. For example, RAG can accumulate information on products from different industries and discover new market needs. For example, RAG can accumulate product information that combines the technology field and the consumer market and discover new market needs. RAG can also accumulate information on products from different applications and discover new market needs. For example, RAG can accumulate information on products from the medical and technology fields and discover new market needs. This allows RAG to accumulate information on products from different industries and applications and discover new market needs.

[0041] When analyzing the content of an inquiry, LLM can refer to past inquiry history and user behavior history to generate a more personalized answer. For example, when analyzing the content of an inquiry, LLM can refer to past inquiry history and generate a personalized answer. For example, LLM uses text generation AI (e.g., LLM) to analyze past inquiry content and generate a relevant answer. LLM can also refer to user behavior history to generate a personalized answer. For example, LLM analyzes a user's website browsing history and purchase history to generate a relevant answer. This allows LLM to refer to past inquiry history and user behavior history when analyzing the content of an inquiry to generate a more personalized answer.

[0042] LLM can analyze inquiry content not only from text data, but also from voice and image data, making it possible to utilize multimodal information. For example, LLM can analyze inquiry content not only from text data, but also from voice data. For example, LLM uses voice recognition technology to convert voice data into text and then analyzes it using LLM. LLM can also analyze inquiry content from image data. For example, LLM uses image recognition technology to analyze image data and extract inquiry content. This makes it possible to analyze inquiry content not only from text data, but also from voice and image data, making it possible to utilize multimodal information.

[0043] LLMs can analyze inquiries from different industries and applications to promote crossover innovation. For example, an LLM can combine inquiries from the medical and technology fields to propose new products. LLMs can also analyze inquiries from different applications to promote crossover innovation. For example, an LLM can combine inquiries from the consumer market and technology fields to propose new products. This allows them to analyze inquiries from different industries and applications to promote crossover innovation.

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

[0045] When collecting user requests and opinions, the request collection unit can use the user's geographical location information to understand regional needs. For example, the generation AI analyzes the user's IP address and GPS data to classify requests by region. The request collection unit can also prioritize collecting requests related to seasons and events in each region. For example, the generation AI can extract requests related to seasonal products and events in a specific region and use this information in product development. This allows the unit to understand regional needs and make more personalized product suggestions.

[0046] When collecting user requests and opinions, the request collection unit can utilize information from the user's social media account to understand more detailed needs. For example, the generation AI analyzes the user's social media posts and extracts requests and opinions. The request collection unit can also collect requests from the user's followers and friends to understand related needs. For example, the generation AI analyzes the user's social network and extracts common needs. This allows the information from social media to be utilized to understand more detailed needs.

[0047] When collecting user requests and opinions, the request collection unit can use the user's health data to understand health-related needs. For example, the generation AI analyzes data from the user's fitness tracker or health app to extract health-related requests. The request collection unit can also make product suggestions based on the user's health condition. For example, the generation AI can suggest health foods or fitness equipment based on the user's health data. In this way, the user's health data can be used to understand health-related needs.

[0048] When collecting user requests and opinions, the request collection unit can use the user's lifestyle data to understand needs based on the user's lifestyle. For example, the generation AI analyzes data from the user's smart home devices and wearable devices to extract requests related to the user's lifestyle. The request collection unit can also make product suggestions based on the user's lifestyle. For example, the generation AI can suggest smart home devices and fitness equipment based on the user's lifestyle data. This makes it possible to use the user's lifestyle data to understand needs based on the user's lifestyle.

[0049] When collecting user requests and opinions, the request collection unit can analyze the user's hobbies and interests and make product suggestions based on those hobbies and interests. For example, the generation AI analyzes the user's social media posts and browsing history to extract requests related to those hobbies and interests. The request collection unit can also make product suggestions based on the user's hobbies and interests. For example, the generation AI suggests related products and services based on the user's hobbies and interests. This makes it possible to analyze the user's hobbies and interests and make product suggestions based on those hobbies and interests.

[0050] When collecting user requests and opinions, the request collection unit can analyze the user's purchase history and browsing history and prioritize collecting related requests. For example, the generation AI analyzes the user's past purchase history and extracts related requests. The request collection unit can also analyze the user's browsing history and prioritize collecting related requests. For example, the generation AI extracts related requests based on the user's browsing history. This makes it possible to analyze the user's purchase history and browsing history and prioritize collecting related requests.

[0051] The processing flow of the first embodiment will be briefly explained below.

[0052] Step 1: The request collection unit uses generation AI to collect requests and opinions. For example, it uses text generation AI (e.g., LLM) to collect customer requests and opinions. It can also use multimodal generation AI to collect requests and opinions from voice and image data. It then uses natural language processing technology to analyze the content of the requests and opinions and understand what needs exist. Step 2: The product information collection unit collects product information from the website. For example, it uses web scraping technology to collect information such as product features, prices, and stock status from the website. It can also use an API to obtain product information from the website. For example, it uses a specific API to obtain detailed product information. Step 3: The product information storage unit stores the collected product information. For example, a database can be used to efficiently manage the collected product information. In addition, RAG can be used to organize the product information and quickly retrieve the necessary information. For example, product life cycle and trend information can be stored, enabling long-term proposals. Step 4: The inquiry response department automates the process of responding to inquiries and sending samples. For example, it uses LLM to analyze the content of inquiries and generate appropriate responses. It can also use LLM to automate sample shipping procedures. For example, it can process sample shipping procedures and respond quickly.

[0053] (Example 2) The product development and proposal system according to an embodiment of the present invention automates product development and proposal processes by utilizing generative AI, RAG, and LLM. This system uses generative AI to collect and learn from daily customer requests and opinions, thereby identifying customer needs and effectively utilizing them in product development. It can also collect product information from websites and use AI to suggest products desired by customers. Furthermore, when inquiries are received, this information can be used by product search and proposals by product representatives. RAG is used to accumulate product information, and LLM is used to automate inquiry responses and sample delivery. This allows the product development and proposal system to establish a system for instantly automating product proposals, sample provision, and contacting distributors based on customer inquiries, enabling instant proposals to meet existing customer needs.

[0054] A product development and proposal system according to an embodiment includes a request collection unit, a product information collection unit, a product information storage unit, and an inquiry response unit. The request collection unit collects requests and opinions using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to collect customer requests and opinions. The generation AI can also collect requests and opinions from voice and image data using a multimodal generation AI. The generation AI also uses natural language processing technology to analyze the content of the requests and opinions and understand what needs exist. For example, the generation AI uses a text generation AI to extract key points from the requests and opinions and use them in product development. The product information collection unit collects product information from websites. For example, the product information collection unit uses web scraping technology to collect information such as product features, prices, and stock status from websites. The product information collection unit can also acquire product information from websites using an API. For example, the product information collection unit acquires detailed product information using a specific API. The product information storage unit stores the collected product information. For example, the product information storage unit uses a database to efficiently manage collected product information. The product information storage unit also uses RAG to organize product information and quickly retrieve necessary information. For example, the product information storage unit uses RAG to store product lifecycle and trend information, enabling long-term proposals. The inquiry response unit automates responses to inquiries and the delivery of samples. For example, the inquiry response unit uses LLM to analyze the content of inquiries and generate appropriate responses. The inquiry response unit can also automate sample delivery procedures using LLM. For example, the inquiry response unit uses LLM to process sample delivery procedures and respond quickly. As a result, the product development and proposal system according to the embodiment automates and efficiently performs processes from collecting requests and opinions to storing product information and responding to inquiries. For example, the output unit displays the proposal results to customers via a web application or a mobile application. If feedback on paper is desired, the results can be printed using a printer.Email submission provides immediate feedback by sending results directly to you.

[0055] The request collection unit performs sentiment analysis of requests and opinions, and can prioritize learning of requests with positive sentiment. The request collection unit, for example, uses a generation AI to analyze text data of requests and opinions and perform sentiment analysis. For example, the generation AI uses a text generation AI (e.g., LLM) to calculate a sentiment score for the request or opinion. The generation AI can also perform sentiment analysis from audio and image data using a multimodal generation AI. For example, the generation AI analyzes the tone and speed of audio data to calculate a sentiment score. The generation AI also analyzes facial expressions in image data to calculate a sentiment score. This allows requests with positive sentiment to be prioritized for learning, thereby promoting the development of products that provide high customer satisfaction.

[0056] The request collection unit can extract more personalized needs by referring to the user's past purchase history and browsing history when collecting requests and opinions. The request collection unit, for example, can extract personalized needs by referring to the user's past purchase history when collecting requests and opinions. For example, the generation AI analyzes the user's past purchase history and prioritizes collecting related requests. The request collection unit can also extract personalized needs by referring to the user's past browsing history. For example, the generation AI analyzes the user's past browsing history and prioritizes collecting related requests. In this way, more personalized needs can be extracted by referring to the user's past purchase history and browsing history.

[0057] The request collection unit can estimate the user's emotions in real time using the emotion estimation function and set the priority of requests based on the emotions. The request collection unit can, for example, estimate the user's emotions in real time using the emotion estimation function and set the priority of requests. For example, the generation AI can use a text generation AI (e.g., LLM) to calculate the user's emotion score and prioritize requests with strong positive emotions. The generation AI can also use a multimodal generation AI to estimate emotions from voice and image data. For example, the generation AI can analyze the tone and speed of voice data to calculate an emotion score. The generation AI can also analyze facial expressions in image data to calculate an emotion score. This makes it possible to estimate the user's emotions in real time and set the priority of requests based on emotions.

[0058] The request collection unit collects requests and opinions not only from text but also from voice and image data, making it possible to utilize multimodal information. The request collection unit, for example, collects requests and opinions not only from text but also from voice data. For example, the generation AI uses voice recognition technology to convert voice data into text, which is then analyzed by the generation AI. The request collection unit can also collect requests and opinions from image data. For example, the generation AI uses image recognition technology to analyze image data and extract requests and opinions. This makes it possible to collect requests and opinions not only from text but also from voice and image data, making it possible to utilize multimodal information.

[0059] The request collection unit can collect requests from different industries and fields to promote crossover innovation. For example, the generative AI could combine requests from the medical and technology fields to develop a new product. The request collection unit can also collect requests from different fields to promote crossover innovation. For example, the generative AI could combine requests from the consumer market and technology fields to develop a new product. This allows the collection of requests from different industries and fields to promote crossover innovation.

[0060] The request collection unit uses the emotion estimation function to estimate the emotion a user is feeling when entering a request in real time, and can make suggestions that elicit positive emotions. The request collection unit, for example, uses the emotion estimation function to estimate the emotion a user is feeling when entering a request in real time. For example, the generation AI uses a text generation AI (e.g., LLM) to calculate the user's emotion score and make positive suggestions. The generation AI can also use multimodal generation AI to estimate emotions from voice and image data. For example, the generation AI analyzes the tone and speed of voice data to calculate an emotion score. The generation AI also analyzes facial expressions in image data to calculate an emotion score. This makes it possible to estimate the emotion a user is feeling when entering a request in real time, and make suggestions that elicit positive emotions.

[0061] The generation AI analyzes not only product features, price, and availability, but also user reviews and ratings, allowing for more accurate suggestions. The generation AI, for example, not only analyzes product features, price, and availability, but also analyzes user reviews and ratings. For example, the generation AI uses text generation AI (e.g., LLM) to calculate an emotional score for user reviews and reflect this in product suggestions. The generation AI can also use multimodal generation AI to analyze user reviews and ratings from voice and image data. For example, the generation AI analyzes the tone and speed of voice data to calculate an emotional score. The generation AI also analyzes facial expressions in image data to calculate an emotional score. This allows for more accurate suggestions by analyzing not only product features, price, and availability, but also user reviews and ratings.

[0062] When collecting product information, the generation AI can simultaneously collect information on competitors and perform comparative analysis. For example, when collecting product information, the generation AI can simultaneously collect information on competitors and perform comparative analysis. For example, the generation AI can use text generation AI (e.g., LLM) to analyze the prices and features of competing products and reflect this in proposals. The generation AI can also use multimodal generation AI to collect information on competitors from voice and image data and perform comparative analysis. For example, the generation AI can analyze the tone and speed of voice data to extract the features of competing products. The generation AI can also analyze facial expressions in image data to extract the features of competing products. In this way, by simultaneously collecting information on competitors when collecting product information and performing comparative analysis, more accurate proposals can be made.

[0063] The generation AI can use the emotion estimation function to make product suggestions based on the user's emotions, and prioritize products that elicit positive emotions. The generation AI, for example, uses the emotion estimation function to make product suggestions based on the user's emotions. For example, the generation AI can use a text generation AI (e.g., LLM) to calculate a user's emotion score and prioritize products that elicit positive emotions. The generation AI can also use multimodal generation AI to estimate emotions from voice and image data. For example, the generation AI can analyze the tone and speed of voice data to calculate an emotion score. The generation AI can also analyze facial expressions in image data to calculate an emotion score. This allows the generation AI to make product suggestions based on the user's emotions, and prioritize products that elicit positive emotions.

[0064] The generative AI can collect product information not only from text data but also from image and video data, making use of visual information. The generative AI can, for example, collect product information not only from text data but also from image data. For example, the generative AI can use image recognition technology to analyze product images and have the generative AI learn from them. The generative AI can also collect product information from video data. For example, the generative AI can use video recognition technology to analyze video data and extract product information. This allows the generative AI to collect product information not only from text data but also from image and video data, making use of visual information.

[0065] Generative AI can collect information on products from different industries and applications and discover new market needs. For example, generative AI can collect information on products from different industries and discover new market needs. For example, generative AI can collect product information that combines the technology field and the consumer market and discover new market needs. Generative AI can also collect information on products from different applications and discover new market needs. For example, generative AI can collect information on products from the medical and technology fields and discover new market needs. This makes it possible to collect information on products from different industries and applications and discover new market needs.

[0066] The generation AI can use the emotion estimation function to monitor the emotions of users when they browse products in real time and suggest the most suitable products. The generation AI, for example, uses the emotion estimation function to monitor the emotions of users when they browse products in real time. For example, the generation AI can use a text generation AI (e.g., LLM) to calculate the user's emotion score and suggest the most suitable products. The generation AI can also use multimodal generation AI to estimate emotions from voice and image data. For example, the generation AI can analyze the tone and speed of voice data to calculate an emotion score. The generation AI can also analyze facial expressions in image data to calculate an emotion score. This makes it possible to monitor the emotions of users when they browse products in real time and suggest the most suitable products.

[0067] When accumulating product information, RAG simultaneously accumulates product lifecycle and trend information, enabling long-term proposals. For example, when accumulating product information, RAG simultaneously accumulates product lifecycle information. For example, RAG includes information such as the product's release date, improvement history, and discontinuation schedule. RAG can also simultaneously accumulate trend information. For example, RAG accumulates information on changes in fashion and consumer preferences. This allows product lifecycle and trend information to be simultaneously accumulated when accumulating product information, enabling long-term proposals.

[0068] RAG can reflect user feedback and ratings when accumulating product information, thereby providing more accurate information. For example, RAG can reflect user feedback and ratings when accumulating product information. For example, RAG can add user reviews and rating scores to product information. RAG can also update product information based on user feedback. For example, RAG can modify product information based on user comments and ratings. This allows user feedback and ratings to be reflected when accumulating product information, thereby providing more accurate information.

[0069] RAG uses its emotion estimation function to accumulate product information based on the user's emotions, and can prioritize information that elicits positive emotions. For example, RAG uses its emotion estimation function to accumulate product information based on the user's emotions. For example, RAG uses a text generation AI (e.g., LLM) to calculate a user's emotion score and prioritize accumulation of product information that elicits positive emotions. RAG can also use multimodal generation AI to estimate emotions from voice and image data. For example, RAG analyzes the tone and speed of voice data to calculate an emotion score. RAG also analyzes facial expressions in image data to calculate an emotion score. This allows RAG to accumulate product information based on the user's emotions, and prioritize accumulation of information that elicits positive emotions.

[0070] RAG accumulates product information not only from text data but also from image and video data, making it possible to utilize visual information. For example, RAG accumulates product information not only from text data but also from image data. For example, RAG uses image recognition technology to analyze product images and accumulate the information in the RAG. RAG can also accumulate product information from video data. For example, RAG uses video recognition technology to analyze video data and extract product information. This allows product information to be accumulated not only from text data but also from image and video data, making it possible to utilize visual information.

[0071] RAG can accumulate information on products from different industries and applications and discover new market needs. For example, RAG can accumulate information on products from different industries and discover new market needs. For example, RAG can accumulate product information that combines the technology field and the consumer market and discover new market needs. RAG can also accumulate information on products from different applications and discover new market needs. For example, RAG can accumulate information on products from the medical and technology fields and discover new market needs. This allows RAG to accumulate information on products from different industries and applications and discover new market needs.

[0072] RAG uses its emotion estimation function to monitor users' emotions in real time as they browse product information and provide optimal information. For example, RAG uses its emotion estimation function to monitor users' emotions in real time as they browse product information. For example, RAG uses text generation AI (e.g., LLM) to calculate a user's emotion score and provide optimal information. RAG can also use multimodal generation AI to estimate emotions from voice and image data. For example, RAG analyzes the tone and speed of voice data to calculate an emotion score. RAG also analyzes facial expressions in image data to calculate an emotion score. This allows RAG to monitor users' emotions in real time as they browse product information and provide optimal information.

[0073] LLM can perform sentiment analysis of the inquiry content and prioritize generating answers with positive sentiment. For example, LLM can perform sentiment analysis of the inquiry content and prioritize generating answers with positive sentiment. For example, LLM can use text generation AI (e.g., LLM) to calculate a sentiment score for the inquiry content and generate an answer with positive sentiment. LLM can also perform sentiment analysis from voice and image data using multimodal generation AI. For example, LLM can analyze the tone and speed of voice data to calculate a sentiment score. LLM can also analyze facial expressions in image data to calculate a sentiment score. This allows for sentiment analysis of the inquiry content and prioritize generating answers with positive sentiment.

[0074] When analyzing the content of an inquiry, LLM can refer to past inquiry history and user behavior history to generate a more personalized answer. For example, when analyzing the content of an inquiry, LLM can refer to past inquiry history and generate a personalized answer. For example, LLM uses text generation AI (e.g., LLM) to analyze past inquiry content and generate a relevant answer. LLM can also refer to user behavior history to generate a personalized answer. For example, LLM analyzes a user's website browsing history and purchase history to generate a relevant answer. This allows LLM to refer to past inquiry history and user behavior history when analyzing the content of an inquiry to generate a more personalized answer.

[0075] LLM can use an emotion estimation function to generate answers based on the user's emotions and provide answers that elicit positive emotions. LLM can, for example, use the emotion estimation function to generate answers based on the user's emotions. For example, LLM can use a text generation AI (e.g., LLM) to calculate a user's emotion score and generate answers that elicit positive emotions. LLM can also use multimodal generation AI to perform emotion estimation from voice and image data. For example, LLM can analyze the tone and speed of voice data to calculate an emotion score. LLM can also analyze facial expressions in image data to calculate an emotion score. This allows LLM to generate answers based on the user's emotions and provide answers that elicit positive emotions.

[0076] LLM can analyze inquiry content not only from text data, but also from voice and image data, making it possible to utilize multimodal information. For example, LLM can analyze inquiry content not only from text data, but also from voice data. For example, LLM uses voice recognition technology to convert voice data into text and then analyzes it using LLM. LLM can also analyze inquiry content from image data. For example, LLM uses image recognition technology to analyze image data and extract inquiry content. This makes it possible to analyze inquiry content not only from text data, but also from voice and image data, making it possible to utilize multimodal information.

[0077] LLMs can analyze inquiries from different industries and applications to promote crossover innovation. For example, an LLM can combine inquiries from the medical and technology fields to propose new products. LLMs can also analyze inquiries from different applications to promote crossover innovation. For example, an LLM can combine inquiries from the consumer market and technology fields to propose new products. This allows them to analyze inquiries from different industries and applications to promote crossover innovation.

[0078] LLM can use an emotion estimation function to monitor the emotions of users when they make inquiries in real time and provide the optimal answer. LLM, for example, uses an emotion estimation function to monitor the emotions of users when they make inquiries in real time. For example, LLM uses a text generation AI (e.g., LLM) to calculate the user's emotion score and provide the optimal answer. LLM can also use multimodal generation AI to estimate emotions from voice and image data. For example, LLM analyzes the tone and speed of voice data to calculate an emotion score. LLM also analyzes facial expressions in image data to calculate an emotion score. This allows LLM to monitor the emotions of users when they make inquiries in real time and provide the optimal answer.

[0079] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0080] When collecting user requests and opinions, the request collection unit can use the user's geographical location information to understand regional needs. For example, the generation AI analyzes the user's IP address and GPS data to classify requests by region. The request collection unit can also prioritize collecting requests related to seasons and events in each region. For example, the generation AI can extract requests related to seasonal products and events in a specific region and use this information in product development. This allows the unit to understand regional needs and make more personalized product suggestions.

[0081] When collecting user requests and opinions, the request collection unit can utilize information from the user's social media account to understand more detailed needs. For example, the generation AI analyzes the user's social media posts and extracts requests and opinions. The request collection unit can also collect requests from the user's followers and friends to understand related needs. For example, the generation AI analyzes the user's social network and extracts common needs. This allows the information from social media to be utilized to understand more detailed needs.

[0082] When collecting user requests and opinions, the request collection unit can use the user's health data to understand health-related needs. For example, the generation AI analyzes data from the user's fitness tracker or health app to extract health-related requests. The request collection unit can also make product suggestions based on the user's health condition. For example, the generation AI can suggest health foods or fitness equipment based on the user's health data. In this way, the user's health data can be used to understand health-related needs.

[0083] When collecting user requests and opinions, the request collection unit can estimate the user's purchasing intent and prioritize requests with a high purchasing intent. For example, the generation AI analyzes the user's past purchase history and browsing history to score purchasing intent. The request collection unit can also propose special offers and discounts to users with a high purchasing intent. For example, the generation AI can provide limited-edition product suggestions and discount coupons to users with a high purchasing intent. This makes it possible to estimate the user's purchasing intent and prioritize requests with a high purchasing intent.

[0084] When collecting user requests and opinions, the request collection unit can use the user's lifestyle data to understand needs based on the user's lifestyle. For example, the generation AI analyzes data from the user's smart home devices and wearable devices to extract requests related to the user's lifestyle. The request collection unit can also make product suggestions based on the user's lifestyle. For example, the generation AI can suggest smart home devices and fitness equipment based on the user's lifestyle data. This makes it possible to use the user's lifestyle data to understand needs based on the user's lifestyle.

[0085] When collecting user requests and opinions, the request collection unit can estimate the user's emotions and provide special responses to requests with negative emotions. For example, the generation AI can use text generation AI (e.g., LLM) to detect requests with negative emotions and provide special responses. The generation AI can also estimate negative emotions from voice and image data using multimodal generation AI. For example, the generation AI can analyze the tone and speed of voice data to detect negative emotions. The generation AI can also analyze facial expressions in image data to detect negative emotions. This allows special responses to be provided to requests with negative emotions.

[0086] When collecting user requests and opinions, the request collection unit can analyze the user's hobbies and interests and make product suggestions based on those hobbies and interests. For example, the generation AI analyzes the user's social media posts and browsing history to extract requests related to those hobbies and interests. The request collection unit can also make product suggestions based on the user's hobbies and interests. For example, the generation AI suggests related products and services based on the user's hobbies and interests. This makes it possible to analyze the user's hobbies and interests and make product suggestions based on those hobbies and interests.

[0087] When collecting user requests and opinions, the request collection unit can estimate the user's emotions and provide feedback based on the emotions. For example, the generation AI uses a text generation AI (e.g., LLM) to calculate a user's emotion score and generate emotion-based feedback. The generation AI can also use a multimodal generation AI to estimate emotions from voice and image data. For example, the generation AI analyzes the tone and speed of voice data to calculate an emotion score. The generation AI also analyzes facial expressions in image data to calculate an emotion score. This makes it possible to estimate the user's emotions and provide emotion-based feedback.

[0088] When collecting user requests and opinions, the request collection unit can analyze the user's purchase history and browsing history and prioritize collecting related requests. For example, the generation AI analyzes the user's past purchase history and extracts related requests. The request collection unit can also analyze the user's browsing history and prioritize collecting related requests. For example, the generation AI extracts related requests based on the user's browsing history. This makes it possible to analyze the user's purchase history and browsing history and prioritize collecting related requests.

[0089] When collecting user requests and opinions, the request collection unit can estimate the user's emotions and prioritize requests based on their emotions. For example, the generation AI uses a text generation AI (e.g., LLM) to calculate a user's emotion score and prioritize requests with strong positive emotions. The generation AI can also use a multimodal generation AI to estimate emotions from voice and image data. For example, the generation AI analyzes the tone and speed of voice data to calculate an emotion score. The generation AI also analyzes facial expressions in image data to calculate an emotion score. This makes it possible to estimate the user's emotions and prioritize requests based on their emotions.

[0090] The processing flow of the second embodiment will be briefly explained below.

[0091] Step 1: The request collection unit uses generation AI to collect requests and opinions. For example, it uses text generation AI (e.g., LLM) to collect customer requests and opinions. It can also use multimodal generation AI to collect requests and opinions from voice and image data. It then uses natural language processing technology to analyze the content of the requests and opinions and understand what needs exist. Step 2: The product information collection unit collects product information from the website. For example, it uses web scraping technology to collect information such as product features, prices, and stock status from the website. It can also use an API to obtain product information from the website. For example, it uses a specific API to obtain detailed product information. Step 3: The product information storage unit stores the collected product information. For example, a database can be used to efficiently manage the collected product information. In addition, RAG can be used to organize the product information and quickly retrieve the necessary information. For example, product life cycle and trend information can be stored, enabling long-term proposals. Step 4: The inquiry response department automates the process of responding to inquiries and sending samples. For example, it uses LLM to analyze the content of inquiries and generate appropriate responses. It can also use LLM to automate sample shipping procedures. For example, it can process sample shipping procedures and respond quickly.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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).

[0101] 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.

[0102] 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.

[0103] 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.

[0104] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0105] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0120] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0136] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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."

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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]

[0159] 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 request collection section that uses generative AI to collect requests and opinions, a product information collection unit that collects product information from websites; a product information storage unit that stores collected product information; An inquiry response unit that automates responses to inquiries and the delivery of samples. A system characterized by:

2. The request collection unit Collecting the requests and opinions from not only text but also audio and image data, utilizing multimodal information.

2. The system of claim 1.

3. The generated AI is Analyze product features, prices, and availability, as well as user reviews and ratings, to make more accurate recommendations 2. The system of claim 1.

4. The RAG is When accumulating the product information, product life cycle and trend information is also accumulated at the same time, enabling long-term proposals.

2. The system of claim 1.

5. The LLM: Sentiment analysis of the inquiry content is performed, and answers with positive sentiment are preferentially generated.

2. The system of claim 1.

6. The request collection unit Conduct sentiment analysis of the requests and opinions, and prioritize learning requests with positive sentiment.

2. The system of claim 1.

7. The generated AI is Using emotion estimation functionality, product recommendations are made based on the user's emotions, with priority given to products that evoke positive emotions.

2. The system of claim 1.

8. The RAG is Using an emotion estimation function, the product information is accumulated based on the user's emotions, and information that elicits positive emotions is preferentially accumulated.

2. The system of claim 1.

Images