system

Abstract

An object of the system according to the embodiment is to grasp an interest or a mind of a specific person and to generate an appropriate handling method or a proposal story based on the interest or the mind.SOLUTION: A system includes a data collection unit, an analysis unit, and a proposal generation unit. The data collection unit collects data of company change news, SNS, seminar lectures, and SNS. The analysis unit analyzes the data collected by the data collection unit. The proposal generation unit generates a customer service method for consumers or a proposal story for corporations on the basis of the analysis result obtained by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the problem that it is difficult to grasp the interests and mindset of a specific person and generate appropriate responses and proposal stories based on that.

[0005] The system according to the embodiment aims to understand the interests and mindset of a specific person and generate appropriate ways of responding and suggested stories based on that. [Means for solving the problem]

[0006] The system according to the embodiment includes a data collection unit, an analysis unit, and a proposal generation unit. The data collection unit collects data such as company transfer news, social media, seminar lectures, and social media. The analysis unit analyzes the data collected by the data collection unit. The proposal generation unit generates a customer service method for consumers or a proposal story for corporations based on the analysis results obtained by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can grasp the interests and mindset of a specific person and generate appropriate responses and suggested stories based on that. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An AI system according to an embodiment of the present invention analyzes a variety of data related to a specific person and identifies that person's mindset and areas of interest. This system collects data such as company transfer news, social media, seminar lectures, and Yahoo! LINE data, and performs analysis using generative AI. Based on the analysis results, it provides support by coming up with ideas for customer service methods for consumers and proposal stories for corporations. This allows the AI ​​system to analyze a variety of data related to a specific person and identify that person's mindset and areas of interest, enabling more effective customer service and proposals.

[0029] The AI ​​system according to the embodiment includes a data collection unit, an analysis unit, and a proposal generation unit. The data collection unit collects data on company transfer news, social media, seminar lectures, and Yahoo! LINE. For example, the data collection unit collects transfer news from news sites using web scraping technology. The data collection unit can also acquire social media posting data using an API. The data collection unit can also record seminar lecture content and convert it into text data. For example, the data collection unit analyzes the HTML structure of a news site to extract transfer news. The data collection unit can acquire posting data from Twitter or Facebook using an API. The seminar lecture content is converted into text data using speech recognition technology. The analysis unit analyzes the collected data. For example, the analysis unit can analyze the text data using natural language processing technology to evaluate the level of interest in a specific topic. The analysis unit can also analyze data patterns using machine learning algorithms. The analysis unit can also perform sentiment analysis and extract patterns of emotional fluctuations from the data. For example, the analysis unit can extract keywords from the data and evaluate the level of interest using text mining technology. The system uses a machine learning algorithm to cluster data and analyze patterns. It uses a sentiment analysis algorithm to calculate positive, negative, or neutral sentiment scores from the data. The proposal generation unit generates customer service methods for consumers and proposal stories for corporations based on the analysis results. For example, if the proposal generation unit is interested in a particular brand or product based on the analysis results, it can propose a personalized customer service method based on that information. The proposal generation unit can also build proposal stories based on information if the proposal generation unit is interested in a company's industry trends and challenges. Furthermore, the proposal generation unit can use the sentiment estimation function to evaluate the effectiveness of proposals and improve future proposals. For example, the proposal generation unit can propose attentive customer service and the introduction of high-quality products to a customer who is interested in a particular brand. It can propose environmentally friendly products and services to a customer who is interested in a company's industry trends. The sentiment estimation function can also be used to evaluate the effectiveness of proposals and improve future proposals.As a result, the AI ​​system of the embodiment can analyze various data related to a specific person and identify that person's mindset and areas of interest, enabling more effective customer service and suggestions.

[0030] The analysis unit can analyze what topics a person is interested in from the content of their social media posts. For example, the analysis unit analyzes collected social media posts and calculates a positive, negative, or neutral emotion score. This allows the analysis unit to identify patterns of emotional fluctuations over a specific period of time and gain a detailed understanding of the person's psychological state. The analysis unit can also analyze the content of seminar lectures and monitor the speaker's emotional fluctuations in real time. For example, it can identify parts that the speaker emphasized or parts that excited emotion, and analyze the person's areas of interest and psychological state. The analysis unit can also analyze the content of Yahoo! LINE messages and extract patterns of emotional fluctuations. For example, it can analyze emotional fluctuations regarding specific topics and identify changes in the person's psychological state and interests. This allows the analysis unit to identify a person's interests from the content of their social media posts, enabling more personalized suggestions.

[0031] The analysis unit can identify a person's expertise or areas of interest from the content of the seminar lecture. The analysis unit, for example, analyzes a person's posting history on social media and identifies changes in the person's interests based on the content of posts over the past few years. For example, it analyzes how interest in a particular topic has changed over time. The analysis unit also collects past purchasing history and analyzes the types and frequency of products purchased. This identifies changes in the person's purchasing trends and interests. The analysis unit also analyzes seminar participation history and identifies changes in the person's expertise and areas of interest based on the themes and content of seminars attended in the past. This allows for more appropriate suggestions to be made by identifying a person's expertise and areas of interest from the content of seminar lectures.

[0032] If a customer has an interest in a particular brand or product, the proposal generation unit can propose a personalized customer service method based on that information. For example, the proposal generation unit analyzes the content of posts on social media in real time and calculates an emotion score using an emotion estimation function. As a result, the analysis results are dynamically updated based on emotional fluctuations. The proposal generation unit also analyzes the content of seminar lectures in real time and estimates the speaker's emotions. For example, it analyzes the speaker's tone of voice and facial expressions and updates the analysis results based on emotional fluctuations. The proposal generation unit also analyzes the content of Yahoo! LINE messages in real time and calculates an emotion score using an emotion estimation function. As a result, the analysis results are dynamically updated based on emotional fluctuations. As a result, if a customer has an interest in a particular brand or product, a personalized customer service method is proposed based on that information, improving customer satisfaction.

[0033] If the person is interested in industry trends or issues of the company to which the person belongs, the proposal generation unit can construct a proposal story based on that information. The proposal generation unit, for example, collects blog articles and analyzes their content to identify the interests and concerns of a specific person. For example, it analyzes the frequency and content of articles on a specific topic. The proposal generation unit also collects forum posts and analyzes the opinions and questions of the posters. This identifies what topics a specific person is interested in. The proposal generation unit also collects articles related to a specific person from news sites and analyzes their content. For example, it identifies news topics that a specific person is interested in. As a result, if the person is interested in industry trends or issues of a company, constructing a proposal story based on that information enables more effective proposals.

[0034] The data collection unit can periodically analyze the content of posts on SNS and identify new interests or concerns. For example, the data collection unit correlates and analyzes the content of posts on SNS with the content of lectures at seminars. For example, it identifies similarities between comments on SNS and comments at seminars and analyzes consistency of interests. The data collection unit also correlates and analyzes the content of Yahoo! LINE messages with purchase history. For example, it identifies the relationship between the message content and purchased products and analyzes purchasing motivations. The data collection unit also correlates and analyzes the content of transfer news with the content of posts on SNS. For example, it analyzes changes in the content of posts on SNS after a transfer and identifies the impact the transfer has on the person's interests. In this way, by periodically analyzing the content of posts on SNS and identifying new interests or concerns, it is possible to always make suggestions based on the latest information.

[0035] The proposal generation unit evaluates the actual effectiveness of the proposed customer service method or the proposal story, and can improve the next proposal based on the evaluation results. The proposal generation unit, for example, analyzes the content of posts on social media in real time and calculates an emotion score using an emotion estimation function. As a result, posts with high emotion scores are preferentially collected. The proposal generation unit also analyzes the content of seminar lectures in real time and estimates the emotions of the speakers. As a result, parts with high emotions are preferentially collected. The proposal generation unit also analyzes the content of Yahoo! LINE messages in real time and calculates an emotion score using an emotion estimation function. As a result, messages with high emotion scores are preferentially collected. As a result, the effectiveness of the proposals is evaluated and the next proposal is improved, enabling more effective proposals.

[0036] The data collection unit can collect data from a wider variety of sources, such as blog articles and forum posts. For example, the data collection unit collects blog articles and analyzes their content to identify the interests and concerns of a particular person. For example, it analyzes the frequency and content of articles on a particular topic. The data collection unit also collects the content of forum posts and analyzes the opinions and questions of the posters. This identifies what topics a particular person is interested in. The data collection unit also collects articles related to a particular person from news sites and analyzes their content. For example, it identifies news topics that a particular person is interested in. In this way, collecting data from a wider variety of sources improves the accuracy of the analysis.

[0037] The analysis unit analyzes the correlation between different data sources and complements the data to obtain more accurate analysis results. For example, the analysis unit correlates and analyzes the content of posts on social media with the content of seminar lectures. For example, it identifies similarities between comments on social media and comments at seminars and analyzes the consistency of interests. The analysis unit also correlates and analyzes the content of Yahoo! LINE messages with purchasing history. For example, it identifies the correlation between the message content and purchased products and analyzes purchasing motivations. The analysis unit also correlates and analyzes the content of transfer news with the content of posts on social media. For example, it analyzes changes in the content of posts on social media after a transfer and identifies the impact the transfer has on the person's interests. In this way, by analyzing the correlation between different data sources and complementing the data, more accurate analysis results can be obtained.

[0038] The analysis unit can perform a detailed analysis of the person's career path and work experience from the transfer news and the content of the SNS posts. The analysis unit, for example, analyzes the transfer news to identify the person's past work experience and career path. For example, it analyzes the changes in job content and position before and after the transfer. The analysis unit also analyzes the content of the SNS posts to identify the person's comments and experience related to their career. For example, it analyzes posts related to past projects and work content. The analysis unit also associates and analyzes the transfer news with the content of the SNS posts to identify the details of the career path. For example, it analyzes SNS posts related to the job content after the transfer. This enables more appropriate suggestions to be made by performing a detailed analysis of the person's career path and work experience from the transfer news and the content of the SNS posts.

[0039] The analysis unit can analyze the content of the seminar lecture and identify the person's expertise and skill set. The analysis unit, for example, analyzes the content of the seminar lecture and identifies the speaker's expertise and skill set. For example, it analyzes comments related to the topics and technologies covered in the lecture. The analysis unit also analyzes the seminar slide materials and presentation content to identify the person's expertise and skill set. For example, it analyzes the terminology and technical explanations used. The analysis unit also associates and analyzes the content of the seminar lecture with the content of posts on social media to identify the details of the expertise and skill set. For example, it analyzes social media posts related to the topics covered in the lecture. In this way, by analyzing the content of the seminar lecture and identifying the person's expertise and skill set, more appropriate suggestions can be made.

[0040] When analyzing the transfer news and the SNS data, the data collection unit can also collect data on colleagues and related parties to analyze the relationships between people. The data collection unit, for example, analyzes the transfer news and collects data on the person's colleagues and related parties. This identifies the relationships between people. For example, it analyzes the relationships with colleagues and superiors at the new workplace. The data collection unit also analyzes the content of posts on the SNS and collects posts from the person's colleagues and related parties. This identifies the relationships between people. For example, it analyzes posts related to interactions with colleagues and joint projects. The data collection unit also associates and analyzes the content of the transfer news and the SNS posts to identify the relationships between people. For example, it analyzes SNS interactions with colleagues at the new workplace. This allows for a more detailed analysis by also collecting data on colleagues and related parties when analyzing the transfer news and SNS data and analyzing the relationships between people.

[0041] When analyzing the content of the seminar lecture, the analysis unit can also collect reactions and feedback from other participants and perform a comprehensive evaluation. The analysis unit, for example, analyzes the content of the seminar lecture and collects reactions and feedback from other participants. This allows for a comprehensive evaluation of the lecture. For example, it analyzes the participants' comments and questions. The analysis unit also collects the results of a seminar questionnaire and analyzes the participants' evaluations of the lecture content. This allows for a comprehensive evaluation of the lecture. For example, it analyzes the free-form comment section of the questionnaire. The analysis unit also associates and analyzes the content of the seminar lecture with the participants' social media posts and performs a comprehensive evaluation. For example, it analyzes social media reactions to the lecture. This allows for a more accurate analysis by collecting reactions and feedback from other participants and performing a comprehensive evaluation when analyzing the content of the seminar lecture.

[0042] The proposal generation unit can analyze the person's purchasing history and preferences in detail from the analysis results and propose a personalized customer service method. The proposal generation unit, for example, analyzes the purchasing history to identify the types and frequency of products the person has purchased in the past. This allows the proposal to propose a personalized customer service method. For example, it may prioritize the introduction of specific brands or products. The proposal generation unit also analyzes the content of posts on social media to identify the person's preferences and interests. This allows the proposal to propose a personalized customer service method. For example, it may introduce products related to specific hobbies or interests. The proposal generation unit also analyzes the person's past customer service history to identify the type of service the person prefers. This allows the proposal to propose a personalized customer service method. For example, it may prioritize courteous service and quick responses. This allows the proposal to improve customer satisfaction by analyzing the purchasing history and preferences in detail and proposing a personalized customer service method.

[0043] When proposing methods for dealing with customers, the proposal generation unit can make proposals from a global perspective by referring to customer service methods in different industries and cultural spheres. The proposal generation unit, for example, collects customer service methods from different industries and selects the optimal method from among them. This makes proposals from a global perspective. For example, it refers to customer service methods in the hotel industry. The proposal generation unit also collects customer service methods from different cultural spheres and selects the optimal method from among them. This makes proposals from a global perspective. For example, it refers to Japan's "omotenashi" culture. The proposal generation unit also analyzes customer service methods from different industries and cultural spheres and identifies common success factors. This makes proposals from a global perspective. For example, it extracts common factors that increase customer satisfaction. This makes it possible to refer to customer service methods from different industries and cultural spheres and make proposals from a global perspective, thereby responding to a wider variety of customers.

[0044] When proposing a method of dealing with customers, the proposal generation unit can propose a multimodal customer service method that utilizes visual and auditory information. The proposal generation unit, for example, proposes a customer service method that utilizes visual information. For example, it proposes a customer service method that uses a visual presentation of a product. The proposal generation unit also proposes a customer service method that utilizes auditory information. For example, it proposes a customer service method that uses an audio guide or music. The proposal generation unit also proposes a multimodal customer service method that combines visual and auditory information. For example, it proposes a customer service method that combines a visual presentation and an audio guide. In this way, by proposing a multimodal customer service method that utilizes visual and auditory information, more effective customer service becomes possible.

[0045] When creating a proposal story for a corporation based on the analysis results, the proposal generation unit can perform a detailed analysis of the corporation's industry trends or challenges and create an optimal proposal story. The proposal generation unit, for example, analyzes industry trends and identifies the challenges the corporation is facing. This allows the creation of an optimal proposal story. For example, a proposal that reflects the latest industry trends and competitive situation is made. The proposal generation unit also analyzes the corporation's past performance and projects and identifies success factors and challenges. This allows the creation of an optimal proposal story. For example, a proposal based on past success stories is made. The proposal generation unit also collects opinions and reports from industry experts and reflects them in the analysis results. This allows the creation of an optimal proposal story. For example, a proposal that incorporates the opinions of experts is made. This allows for a detailed analysis of industry trends and challenges to create an optimal proposal story, enabling more effective proposals.

[0046] When creating a proposal story, the proposal generation unit can refer to past proposal history and success cases to identify effective stories. The proposal generation unit, for example, analyzes past proposal history to identify the factors behind successful proposals. This allows for creating effective proposal stories. For example, a proposal based on past success cases is made. The proposal generation unit also collects success cases and analyzes their commonalities and success factors. This allows for creating effective proposal stories. For example, a proposal that incorporates the commonalities of the success cases is made. The proposal generation unit also associates and analyzes past proposal history and success cases to identify effective proposal stories. This allows for creating effective proposal stories. For example, a proposal that reflects the factors behind the success cases is made. This allows for more effective proposals by referring to past proposal history and success cases to identify effective stories.

[0047] When creating a proposal story, the proposal generation unit can refer to success stories from different industries and applications and make proposals from a new perspective. The proposal generation unit, for example, collects success stories from different industries and analyzes their commonalities and success factors. This allows for proposals to be made from a new perspective. For example, a proposal that incorporates success stories from different industries is made. The proposal generation unit also collects success stories from different applications and analyzes their commonalities and success factors. This allows for proposals to be made from a new perspective. For example, a proposal that incorporates success stories from different applications is made. The proposal generation unit also associates and analyzes success stories from different industries and applications and makes proposals from a new perspective. This allows for proposals to be made from a new perspective. For example, a proposal that combines success stories from different industries and applications is made. This allows for more effective proposals by referring to success stories from different industries and applications and making proposals from a new perspective.

[0048] When creating a proposal story, the proposal generation unit can propose a multimedia story that utilizes visuals and audio. For example, the proposal generation unit incorporates visual elements into the proposal story to make a proposal that is easy to understand visually. For example, a proposal that uses graphs and diagrams is made. The proposal generation unit also incorporates audio elements into the proposal story to make a proposal that is easy to understand auditorily. For example, a proposal that uses audio guides and narration is made. The proposal generation unit also creates a multimedia proposal story that combines visuals and audio. For example, a proposal that combines a visual presentation and audio guide is made. This makes it possible to make more effective proposals by proposing a multimedia story that utilizes visuals and audio.

[0049] The proposal generation unit can automatically generate planning proposals specialized for different markets or regions. The proposal generation unit, for example, uses a generation AI to build a system that automatically generates planning proposals specialized for different markets or regions. For example, it makes proposals according to market needs and regional characteristics. The proposal generation unit also collects data from different markets, and the generation AI proposes market-specific plans based on that data. For example, it makes proposals suitable for emerging markets and mature markets. The proposal generation unit also takes into account the culture and economic situation of each region, and the generation AI automatically generates regionally specialized plans. For example, it makes proposals tailored to regional events and trends. This enables more effective proposals by automatically generating planning proposals specialized for different markets and regions.

[0050] The proposal generation unit can automatically generate visual prototypes of proposed plans to make them easier to understand visually. The proposal generation unit, for example, uses generative AI to develop a system that automatically generates visual prototypes of proposed plans. For example, it visually displays product designs and service flows. The proposal generation unit also automatically generates visual prototypes to enable users to intuitively understand the content of the plan. For example, it provides 3D models and interactive demos. The proposal generation unit also builds a system that generates visual prototypes of proposed plans in real time and improves them based on user feedback. For example, it collects user opinions based on the prototype. This enables more effective proposals by automatically generating visual prototypes that are easier to understand visually.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The data collection unit, for example, analyzes the HTML structure of a news site and extracts personnel transfer news. It uses an API to obtain posted data from Twitter and Facebook. It converts seminar lecture content into text data using speech recognition technology. The analysis unit analyzes the collected data. For example, the analysis unit may analyze text data using natural language processing technology to evaluate interest in a specific topic. The analysis unit may also analyze data patterns using machine learning algorithms. Furthermore, the analysis unit may perform sentiment analysis and extract emotional fluctuation patterns from the data. Based on the analysis results, the proposal generation unit generates customer service methods for consumers and proposal stories for corporations. For example, if the proposal generation unit determines that a customer is interested in a particular brand or product based on the analysis results, it may propose a personalized customer service method based on that information. Furthermore, if the proposal generation unit determines that a customer is interested in a company's industry trends and challenges, it may also construct a proposal story based on that information. Furthermore, the proposal generation unit may use an emotion estimation function to evaluate the effectiveness of proposals and improve future proposals. As a result, the AI ​​system of the embodiment can analyze various data related to a specific person and identify that person's mindset and areas of interest, enabling more effective customer service and suggestions.

[0053] The analysis unit, for example, analyzes a person's social media posting history and identifies changes in that person's interests based on the content of posts over the past few years. For example, it analyzes how interest in a particular topic has changed over time. The analysis unit also collects past purchase history and analyzes the types and frequency of products purchased. This identifies changes in the person's purchasing trends and interests. The analysis unit also analyzes seminar participation history and identifies changes in the person's expertise and areas of interest based on the themes and content of seminars attended in the past. This allows for more appropriate suggestions to be made by identifying a person's expertise and areas of interest from the content of seminar lectures.

[0054] The proposal generation unit, for example, collects blog articles and analyzes their content to identify the interests and concerns of a specific person. For example, it analyzes the frequency and content of articles on a specific theme. The proposal generation unit also collects forum posts and analyzes the opinions and questions of the posters. This identifies what topics a specific person is interested in. The proposal generation unit also collects articles related to a specific person from news sites and analyzes their content. For example, it identifies news topics that a specific person is interested in. This makes it possible to make more effective proposals if the person is interested in industry trends and challenges within a company by building a proposal story based on that information.

[0055] The data collection unit, for example, correlates and analyzes the content of social media posts with the content of seminar lectures. For example, it identifies similarities between comments on social media and comments at seminars and analyzes consistency of interests. The data collection unit also correlates and analyzes the content of Yahoo! LINE messages with purchase history. For example, it identifies the relationship between the message content and purchased products and analyzes purchasing motivations. The data collection unit also correlates and analyzes the content of transfer news with the content of social media posts. For example, it analyzes changes in the content of social media posts after a transfer and identifies the impact the transfer has on the person's interests. This allows the content of social media posts to be analyzed regularly and new interests and concerns to be identified, making it possible to always make proposals based on the latest information.

[0056] The data collection unit, for example, collects blog articles and analyzes their content to identify the interests and concerns of a specific person. For example, it analyzes the frequency and content of articles on a specific topic. The data collection unit also collects the content of forum posts and analyzes the opinions and questions of the posters. This identifies what topics a specific person is interested in. The data collection unit also collects articles related to a specific person from news sites and analyzes their content. For example, it identifies news topics that a specific person is interested in. This allows data to be collected from a wider variety of information sources, improving the accuracy of the analysis.

[0057] The analysis unit, for example, correlates and analyzes the content of social media posts with the content of seminar lectures. For example, it identifies similarities between comments on social media and comments at seminars and analyzes consistency of interests. The analysis unit also correlates and analyzes the content of Yahoo! LINE messages with purchasing history. For example, it identifies the relationship between message content and purchased products and analyzes purchasing motivations. The analysis unit also correlates and analyzes transfer news with the content of social media posts. For example, it analyzes changes in the content of social media posts after a transfer and identifies the impact the transfer has on the person's interests. This makes it possible to analyze the correlation between different data sources and mutually complement the data, thereby obtaining more accurate analysis results.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The data collection department collects data on company transfer news, social media, seminar lectures, and Yahoo! LINE. For example, the data collection department uses web scraping technology to collect transfer news from news sites. The data collection department can also use APIs to obtain social media post data. Furthermore, the data collection department can record the content of seminar lectures and convert it into text data. For example, the data collection department analyzes the HTML structure of news sites to extract transfer news. It uses APIs to obtain post data from Twitter and Facebook. The content of seminar lectures is converted into text data using voice recognition technology. Step 2: The analysis unit analyzes the collected data. For example, the analysis unit may use natural language processing technology to analyze text data and evaluate the level of interest in a particular topic. The analysis unit may also use machine learning algorithms to analyze data patterns. The analysis unit may also perform sentiment analysis and extract patterns of emotional fluctuations from the data. For example, the analysis unit may use text mining technology to extract keywords from the data and evaluate the level of interest. A machine learning algorithm may be used to cluster the data and analyze patterns. A sentiment analysis algorithm may be used to calculate positive, negative, or neutral sentiment scores from the data. Step 3: The proposal generation unit generates customer service methods for consumers and proposal stories for corporations based on the analysis results. For example, if the customer is interested in a particular brand or product based on the analysis results, the proposal generation unit can propose a personalized customer service method based on that information. In addition, if the customer is interested in the company's industry trends and issues, the proposal generation unit can also build a proposal story based on that information. Furthermore, the proposal generation unit can use the emotion estimation function to evaluate the effectiveness of the proposal and improve the next proposal. For example, the proposal generation unit can propose attentive customer service and the introduction of high-quality products to a customer who is interested in a particular brand. It can propose environmentally friendly products and services to a customer who is interested in the company's industry trends. It can use the emotion estimation function to evaluate the effectiveness of the proposal and improve the next proposal.

[0060] (Example 2) An AI system according to an embodiment of the present invention analyzes a variety of data related to a specific person and identifies that person's mindset and areas of interest. This system collects data such as company transfer news, social media, seminar lectures, and Yahoo! LINE data, and performs analysis using generative AI. Based on the analysis results, it provides support by coming up with ideas for customer service methods for consumers and proposal stories for corporations. This allows the AI ​​system to analyze a variety of data related to a specific person and identify that person's mindset and areas of interest, enabling more effective customer service and proposals.

[0061] The AI ​​system according to the embodiment includes a data collection unit, an analysis unit, and a proposal generation unit. The data collection unit collects data on company transfer news, social media, seminar lectures, and Yahoo! LINE. For example, the data collection unit collects transfer news from news sites using web scraping technology. The data collection unit can also acquire social media posting data using an API. The data collection unit can also record seminar lecture content and convert it into text data. For example, the data collection unit analyzes the HTML structure of a news site to extract transfer news. The data collection unit can acquire posting data from Twitter or Facebook using an API. The seminar lecture content is converted into text data using speech recognition technology. The analysis unit analyzes the collected data. For example, the analysis unit can analyze the text data using natural language processing technology to evaluate the level of interest in a specific topic. The analysis unit can also analyze data patterns using machine learning algorithms. The analysis unit can also perform sentiment analysis and extract patterns of emotional fluctuations from the data. For example, the analysis unit can extract keywords from the data and evaluate the level of interest using text mining technology. The system uses a machine learning algorithm to cluster data and analyze patterns. It uses a sentiment analysis algorithm to calculate positive, negative, or neutral sentiment scores from the data. The proposal generation unit generates customer service methods for consumers and proposal stories for corporations based on the analysis results. For example, if the proposal generation unit is interested in a particular brand or product based on the analysis results, it can propose a personalized customer service method based on that information. The proposal generation unit can also build proposal stories based on information if the proposal generation unit is interested in a company's industry trends and challenges. Furthermore, the proposal generation unit can use the sentiment estimation function to evaluate the effectiveness of proposals and improve future proposals. For example, the proposal generation unit can propose attentive customer service and the introduction of high-quality products to a customer who is interested in a particular brand. It can propose environmentally friendly products and services to a customer who is interested in a company's industry trends. The sentiment estimation function can also be used to evaluate the effectiveness of proposals and improve future proposals.As a result, the AI ​​system of the embodiment can analyze various data related to a specific person and identify that person's mindset and areas of interest, enabling more effective customer service and suggestions.

[0062] The analysis unit can analyze what topics a person is interested in from the content of their social media posts. For example, the analysis unit analyzes collected social media posts and calculates a positive, negative, or neutral emotion score. This allows the analysis unit to identify patterns of emotional fluctuations over a specific period of time and gain a detailed understanding of the person's psychological state. The analysis unit can also analyze the content of seminar lectures and monitor the speaker's emotional fluctuations in real time. For example, it can identify parts that the speaker emphasized or parts that excited emotion, and analyze the person's areas of interest and psychological state. The analysis unit can also analyze the content of Yahoo! LINE messages and extract patterns of emotional fluctuations. For example, it can analyze emotional fluctuations regarding specific topics and identify changes in the person's psychological state and interests. This allows the analysis unit to identify a person's interests from the content of their social media posts, enabling more personalized suggestions.

[0063] The analysis unit can identify a person's expertise or areas of interest from the content of the seminar lecture. The analysis unit, for example, analyzes a person's posting history on social media and identifies changes in the person's interests based on the content of posts over the past few years. For example, it analyzes how interest in a particular topic has changed over time. The analysis unit also collects past purchasing history and analyzes the types and frequency of products purchased. This identifies changes in the person's purchasing trends and interests. The analysis unit also analyzes seminar participation history and identifies changes in the person's expertise and areas of interest based on the themes and content of seminars attended in the past. This allows for more appropriate suggestions to be made by identifying a person's expertise and areas of interest from the content of seminar lectures.

[0064] If a customer has an interest in a particular brand or product, the proposal generation unit can propose a personalized customer service method based on that information. For example, the proposal generation unit analyzes the content of posts on social media in real time and calculates an emotion score using an emotion estimation function. As a result, the analysis results are dynamically updated based on emotional fluctuations. The proposal generation unit also analyzes the content of seminar lectures in real time and estimates the speaker's emotions. For example, it analyzes the speaker's tone of voice and facial expressions and updates the analysis results based on emotional fluctuations. The proposal generation unit also analyzes the content of Yahoo! LINE messages in real time and calculates an emotion score using an emotion estimation function. As a result, the analysis results are dynamically updated based on emotional fluctuations. As a result, if a customer has an interest in a particular brand or product, a personalized customer service method is proposed based on that information, improving customer satisfaction.

[0065] If the person is interested in industry trends or issues of the company to which the person belongs, the proposal generation unit can construct a proposal story based on that information. The proposal generation unit, for example, collects blog articles and analyzes their content to identify the interests and concerns of a specific person. For example, it analyzes the frequency and content of articles on a specific topic. The proposal generation unit also collects forum posts and analyzes the opinions and questions of the posters. This identifies what topics a specific person is interested in. The proposal generation unit also collects articles related to a specific person from news sites and analyzes their content. For example, it identifies news topics that a specific person is interested in. As a result, if the person is interested in industry trends or issues of a company, constructing a proposal story based on that information enables more effective proposals.

[0066] The data collection unit can periodically analyze the content of posts on SNS and identify new interests or concerns. For example, the data collection unit correlates and analyzes the content of posts on SNS with the content of lectures at seminars. For example, it identifies similarities between comments on SNS and comments at seminars and analyzes consistency of interests. The data collection unit also correlates and analyzes the content of Yahoo! LINE messages with purchase history. For example, it identifies the relationship between the message content and purchased products and analyzes purchasing motivations. The data collection unit also correlates and analyzes the content of transfer news with the content of posts on SNS. For example, it analyzes changes in the content of posts on SNS after a transfer and identifies the impact the transfer has on the person's interests. In this way, by periodically analyzing the content of posts on SNS and identifying new interests or concerns, it is possible to always make suggestions based on the latest information.

[0067] The proposal generation unit evaluates the actual effectiveness of the proposed customer service method or the proposal story, and can improve the next proposal based on the evaluation results. The proposal generation unit, for example, analyzes the content of posts on social media in real time and calculates an emotion score using an emotion estimation function. As a result, posts with high emotion scores are preferentially collected. The proposal generation unit also analyzes the content of seminar lectures in real time and estimates the emotions of the speakers. As a result, parts with high emotions are preferentially collected. The proposal generation unit also analyzes the content of Yahoo! LINE messages in real time and calculates an emotion score using an emotion estimation function. As a result, messages with high emotion scores are preferentially collected. As a result, the effectiveness of the proposals is evaluated and the next proposal is improved, enabling more effective proposals.

[0068] The analysis unit performs sentiment analysis on the data and analyzes patterns of emotional fluctuations, thereby enabling a more detailed identification of a person's psychological state. For example, the analysis unit analyzes collected social media postings and calculates a positive, negative, or neutral emotion score. This identifies patterns of emotional fluctuations over a specific period of time and provides a detailed understanding of the person's psychological state. The analysis unit also analyzes the content of seminar lectures and monitors the speaker's emotional fluctuations in real time. For example, it identifies the parts the speaker emphasized and the parts where the speaker's emotions were high, and analyzes the person's areas of interest and psychological state. The analysis unit also analyzes the content of Yahoo! LINE messages and extracts patterns of emotional fluctuations. For example, it analyzes emotional fluctuations on specific topics and identifies changes in the person's psychological state and interests. By analyzing patterns of emotional fluctuations, a more detailed identification of the person's psychological state can be achieved.

[0069] The analysis unit can use the emotion estimation function to estimate the person's emotion from the data and dynamically update the analysis results based on emotional fluctuations. The analysis unit, for example, analyzes the content of posts on SNS in real time and calculates an emotion score using the emotion estimation function. As a result, the analysis results are dynamically updated based on emotional fluctuations. The analysis unit also analyzes the content of a seminar lecture in real time and estimates the speaker's emotion. For example, it analyzes the speaker's tone of voice and facial expression and updates the analysis results based on emotional fluctuations. The analysis unit also analyzes the content of Yahoo! LINE messages in real time and calculates an emotion score using the emotion estimation function. As a result, the analysis results are dynamically updated based on emotional fluctuations. As a result, more accurate analysis is possible by dynamically updating the analysis results based on emotional fluctuations using the emotion estimation function.

[0070] The data collection unit can collect data from a wider variety of sources, such as blog articles and forum posts. For example, the data collection unit collects blog articles and analyzes their content to identify the interests and concerns of a particular person. For example, it analyzes the frequency and content of articles on a particular topic. The data collection unit also collects the content of forum posts and analyzes the opinions and questions of the posters. This identifies what topics a particular person is interested in. The data collection unit also collects articles related to a particular person from news sites and analyzes their content. For example, it identifies news topics that a particular person is interested in. In this way, collecting data from a wider variety of sources improves the accuracy of the analysis.

[0071] The analysis unit analyzes the correlation between different data sources and complements the data to obtain more accurate analysis results. For example, the analysis unit correlates and analyzes the content of posts on social media with the content of seminar lectures. For example, it identifies similarities between comments on social media and comments at seminars and analyzes the consistency of interests. The analysis unit also correlates and analyzes the content of Yahoo! LINE messages with purchasing history. For example, it identifies the correlation between the message content and purchased products and analyzes purchasing motivations. The analysis unit also correlates and analyzes the content of transfer news with the content of posts on social media. For example, it analyzes changes in the content of posts on social media after a transfer and identifies the impact the transfer has on the person's interests. In this way, by analyzing the correlation between different data sources and complementing the data, more accurate analysis results can be obtained.

[0072] The analysis unit can use the emotion estimation function to estimate emotions in real time during data collection and set priorities for data collection based on emotions. The analysis unit, for example, analyzes the content of posts on SNS in real time and calculates an emotion score using the emotion estimation function. As a result, posts with high emotion scores are preferentially collected. The analysis unit also analyzes the content of seminar lectures in real time and estimates the emotions of the speakers. As a result, parts with high emotions are preferentially collected. The analysis unit also analyzes the content of Yahoo! LINE messages in real time and calculates an emotion score using the emotion estimation function. As a result, messages with high emotion scores are preferentially collected. As a result, more effective data collection is possible by using the emotion estimation function to estimate emotions in real time and setting priorities for data collection based on emotions.

[0073] The analysis unit can perform a detailed analysis of the person's career path and work experience from the transfer news and the content of the SNS posts. The analysis unit, for example, analyzes the transfer news to identify the person's past work experience and career path. For example, it analyzes the changes in job content and position before and after the transfer. The analysis unit also analyzes the content of the SNS posts to identify the person's comments and experience related to their career. For example, it analyzes posts related to past projects and work content. The analysis unit also associates and analyzes the transfer news with the content of the SNS posts to identify the details of the career path. For example, it analyzes SNS posts related to the job content after the transfer. This enables more appropriate suggestions to be made by performing a detailed analysis of the person's career path and work experience from the transfer news and the content of the SNS posts.

[0074] The analysis unit can analyze the content of the seminar lecture and identify the person's expertise and skill set. The analysis unit, for example, analyzes the content of the seminar lecture and identifies the speaker's expertise and skill set. For example, it analyzes comments related to the topics and technologies covered in the lecture. The analysis unit also analyzes the seminar slide materials and presentation content to identify the person's expertise and skill set. For example, it analyzes the terminology and technical explanations used. The analysis unit also associates and analyzes the content of the seminar lecture with the content of posts on social media to identify the details of the expertise and skill set. For example, it analyzes social media posts related to the topics covered in the lecture. In this way, by analyzing the content of the seminar lecture and identifying the person's expertise and skill set, more appropriate suggestions can be made.

[0075] The analysis unit can use the emotion estimation function to estimate a person's emotion from the SNS post and lecture content, and provide an analysis result based on the emotion. The analysis unit, for example, analyzes the SNS post content in real time and calculates an emotion score using the emotion estimation function. This provides an analysis result based on the emotion. The analysis unit also analyzes the content of a seminar lecture in real time and estimates the speaker's emotion. This provides an analysis result based on the emotion. The analysis unit also analyzes the content of a Yahoo! LINE message in real time and calculates an emotion score using the emotion estimation function. This provides an analysis result based on the emotion. This enables more accurate analysis by providing an analysis result based on the emotion using the emotion estimation function.

[0076] When analyzing the transfer news and the SNS data, the data collection unit can also collect data on colleagues and related parties to analyze the relationships between people. The data collection unit, for example, analyzes the transfer news and collects data on the person's colleagues and related parties. This identifies the relationships between people. For example, it analyzes the relationships with colleagues and superiors at the new workplace. The data collection unit also analyzes the content of posts on the SNS and collects posts from the person's colleagues and related parties. This identifies the relationships between people. For example, it analyzes posts related to interactions with colleagues and joint projects. The data collection unit also associates and analyzes the content of the transfer news and the SNS posts to identify the relationships between people. For example, it analyzes SNS interactions with colleagues at the new workplace. This allows for a more detailed analysis by also collecting data on colleagues and related parties when analyzing the transfer news and SNS data and analyzing the relationships between people.

[0077] When analyzing the content of the seminar lecture, the analysis unit can also collect reactions and feedback from other participants and perform a comprehensive evaluation. The analysis unit, for example, analyzes the content of the seminar lecture and collects reactions and feedback from other participants. This allows for a comprehensive evaluation of the lecture. For example, it analyzes the participants' comments and questions. The analysis unit also collects the results of a seminar questionnaire and analyzes the participants' evaluations of the lecture content. This allows for a comprehensive evaluation of the lecture. For example, it analyzes the free-form comment section of the questionnaire. The analysis unit also associates and analyzes the content of the seminar lecture with the participants' social media posts and performs a comprehensive evaluation. For example, it analyzes social media reactions to the lecture. This allows for a more accurate analysis by collecting reactions and feedback from other participants and performing a comprehensive evaluation when analyzing the content of the seminar lecture.

[0078] The analysis unit can use the emotion estimation function to estimate emotions in real time when collecting the personnel transfer news and the SNS data, and perform emotion-based data analysis. The analysis unit, for example, analyzes personnel transfer news in real time and calculates an emotion score using the emotion estimation function. This performs emotion-based data analysis. The analysis unit also analyzes the content of posts on the SNS in real time and calculates an emotion score using the emotion estimation function. This performs emotion-based data analysis. The analysis unit also analyzes the content of messages on Yahoo! LINE in real time and calculates an emotion score using the emotion estimation function. This performs emotion-based data analysis. This enables more accurate analysis by using the emotion estimation function to estimate emotions in real time and perform emotion-based data analysis.

[0079] The proposal generation unit can analyze the person's purchasing history and preferences in detail from the analysis results and propose a personalized customer service method. The proposal generation unit, for example, analyzes the purchasing history to identify the types and frequency of products the person has purchased in the past. This allows the proposal to propose a personalized customer service method. For example, it may prioritize the introduction of specific brands or products. The proposal generation unit also analyzes the content of posts on social media to identify the person's preferences and interests. This allows the proposal to propose a personalized customer service method. For example, it may introduce products related to specific hobbies or interests. The proposal generation unit also analyzes the person's past customer service history to identify the type of service the person prefers. This allows the proposal to propose a personalized customer service method. For example, it may prioritize courteous service and quick responses. This allows the proposal to improve customer satisfaction by analyzing the purchasing history and preferences in detail and proposing a personalized customer service method.

[0080] The proposal generation unit can use the emotion estimation function to estimate real-time emotions during customer service and propose a response method based on the emotions. For example, the proposal generation unit performs emotion estimation in real time during customer service and calculates a customer emotion score. This allows the proposal to propose a response method based on the emotions. For example, if the customer is dissatisfied, a quick response is proposed. The proposal generation unit also analyzes the customer's facial expressions and tone of voice to estimate emotions in real time. This allows the proposal to propose a response method based on the emotions. For example, if the customer is happy, a more positive response is proposed. The proposal generation unit also identifies the optimal response method by comparing it with past customer service history based on the emotion estimation data. This allows the proposal to propose a response method based on the emotions. For example, it prioritizes response methods that have been successful in the past. This allows more effective customer service by using the emotion estimation function to estimate emotions in real time and proposing a response method based on the emotions.

[0081] When proposing methods for dealing with customers, the proposal generation unit can make proposals from a global perspective by referring to customer service methods in different industries and cultural spheres. The proposal generation unit, for example, collects customer service methods from different industries and selects the optimal method from among them. This makes proposals from a global perspective. For example, it refers to customer service methods in the hotel industry. The proposal generation unit also collects customer service methods from different cultural spheres and selects the optimal method from among them. This makes proposals from a global perspective. For example, it refers to Japan's "omotenashi" culture. The proposal generation unit also analyzes customer service methods from different industries and cultural spheres and identifies common success factors. This makes proposals from a global perspective. For example, it extracts common factors that increase customer satisfaction. This makes it possible to refer to customer service methods from different industries and cultural spheres and make proposals from a global perspective, thereby responding to a wider variety of customers.

[0082] When proposing a method of dealing with customers, the proposal generation unit can propose a multimodal customer service method that utilizes visual and auditory information. The proposal generation unit, for example, proposes a customer service method that utilizes visual information. For example, it proposes a customer service method that uses a visual presentation of a product. The proposal generation unit also proposes a customer service method that utilizes auditory information. For example, it proposes a customer service method that uses an audio guide or music. The proposal generation unit also proposes a multimodal customer service method that combines visual and auditory information. For example, it proposes a customer service method that combines a visual presentation and an audio guide. In this way, by proposing a multimodal customer service method that utilizes visual and auditory information, more effective customer service becomes possible.

[0083] The proposal generation unit can use the emotion estimation function to monitor emotions during customer service in real time and dynamically update a response method based on the emotions. For example, the proposal generation unit performs emotion estimation in real time during customer service and calculates a customer emotion score. This dynamically updates a response method based on the emotions. For example, the response method is adjusted when the customer's emotions change. The proposal generation unit also analyzes the customer's facial expressions and tone of voice to estimate emotions in real time. This dynamically updates a response method based on emotions. For example, the response method is changed when the customer's emotions change from positive to negative. The proposal generation unit also compares the emotion estimation data with past customer service history to identify an optimal response method. This dynamically updates a response method based on emotions. For example, a response method that was successful in the past is applied in real time. This enables more effective customer service by monitoring emotions in real time using the emotion estimation function and dynamically updating a response method based on emotions.

[0084] When creating a proposal story for a corporation based on the analysis results, the proposal generation unit can perform a detailed analysis of the corporation's industry trends or challenges and create an optimal proposal story. The proposal generation unit, for example, analyzes industry trends and identifies the challenges the corporation is facing. This allows the creation of an optimal proposal story. For example, a proposal that reflects the latest industry trends and competitive situation is made. The proposal generation unit also analyzes the corporation's past performance and projects and identifies success factors and challenges. This allows the creation of an optimal proposal story. For example, a proposal based on past success stories is made. The proposal generation unit also collects opinions and reports from industry experts and reflects them in the analysis results. This allows the creation of an optimal proposal story. For example, a proposal that incorporates the opinions of experts is made. This allows for a detailed analysis of industry trends and challenges to create an optimal proposal story, enabling more effective proposals.

[0085] When creating a proposal story, the proposal generation unit can refer to past proposal history and success cases to identify effective stories. The proposal generation unit, for example, analyzes past proposal history to identify the factors behind successful proposals. This allows for creating effective proposal stories. For example, a proposal based on past success cases is made. The proposal generation unit also collects success cases and analyzes their commonalities and success factors. This allows for creating effective proposal stories. For example, a proposal that incorporates the commonalities of the success cases is made. The proposal generation unit also associates and analyzes past proposal history and success cases to identify effective proposal stories. This allows for creating effective proposal stories. For example, a proposal that reflects the factors behind the success cases is made. This allows for more effective proposals by referring to past proposal history and success cases to identify effective stories.

[0086] The proposal generation unit can use the emotion estimation function to evaluate the emotional impact of a proposed story and create a story based on emotions. For example, when creating a proposed story, the proposal generation unit uses the emotion estimation function to calculate an emotion score. This evaluates the emotional impact and creates a story based on emotions. For example, elements that elicit positive emotions are incorporated. The proposal generation unit also performs emotion estimation for each element of the proposed story and evaluates the emotional impact. This creates a story based on emotions. For example, elements with high emotion scores are emphasized. The proposal generation unit also evaluates the emotional impact by comparing with past proposed stories based on the emotion estimation data. This creates a story based on emotions. For example, emotional elements similar to past success stories are incorporated. This enables more effective proposals by using the emotion estimation function to evaluate the emotional impact and create a story based on emotions.

[0087] When creating a proposal story, the proposal generation unit can refer to success stories from different industries and applications and make proposals from a new perspective. The proposal generation unit, for example, collects success stories from different industries and analyzes their commonalities and success factors. This allows for proposals to be made from a new perspective. For example, a proposal that incorporates success stories from different industries is made. The proposal generation unit also collects success stories from different applications and analyzes their commonalities and success factors. This allows for proposals to be made from a new perspective. For example, a proposal that incorporates success stories from different applications is made. The proposal generation unit also associates and analyzes success stories from different industries and applications and makes proposals from a new perspective. This allows for proposals to be made from a new perspective. For example, a proposal that combines success stories from different industries and applications is made. This allows for more effective proposals by referring to success stories from different industries and applications and making proposals from a new perspective.

[0088] When creating a proposal story, the proposal generation unit can propose a multimedia story that utilizes visuals and audio. For example, the proposal generation unit incorporates visual elements into the proposal story to make a proposal that is easy to understand visually. For example, a proposal that uses graphs and diagrams is made. The proposal generation unit also incorporates audio elements into the proposal story to make a proposal that is easy to understand auditorily. For example, a proposal that uses audio guides and narration is made. The proposal generation unit also creates a multimedia proposal story that combines visuals and audio. For example, a proposal that combines a visual presentation and audio guide is made. This makes it possible to make more effective proposals by proposing a multimedia story that utilizes visuals and audio.

[0089] The proposal generation unit can automatically generate planning proposals specialized for different markets or regions. The proposal generation unit, for example, uses a generation AI to build a system that automatically generates planning proposals specialized for different markets or regions. For example, it makes proposals according to market needs and regional characteristics. The proposal generation unit also collects data from different markets, and the generation AI proposes market-specific plans based on that data. For example, it makes proposals suitable for emerging markets and mature markets. The proposal generation unit also takes into account the culture and economic situation of each region, and the generation AI automatically generates regionally specialized plans. For example, it makes proposals tailored to regional events and trends. This enables more effective proposals by automatically generating planning proposals specialized for different markets and regions.

[0090] The proposal generation unit can automatically generate visual prototypes of proposed plans to make them easier to understand visually. The proposal generation unit, for example, uses generative AI to develop a system that automatically generates visual prototypes of proposed plans. For example, it visually displays product designs and service flows. The proposal generation unit also automatically generates visual prototypes to enable users to intuitively understand the content of the plan. For example, it provides 3D models and interactive demos. The proposal generation unit also builds a system that generates visual prototypes of proposed plans in real time and improves them based on user feedback. For example, it collects user opinions based on the prototype. This enables more effective proposals by automatically generating visual prototypes that are easier to understand visually.

[0091] The proposal generation unit uses the emotion estimation function to monitor the user's emotional response to new project proposals and continuously improve the quality of the proposals. The proposal generation unit, for example, uses the emotion estimation function to develop a system that monitors the user's emotional response to new project proposals in real time. For example, the proposal generation unit analyzes the user's facial expressions and voice and calculates an emotion score. The proposal generation unit also builds a system that continuously improves the quality of proposals based on the user's emotional response data. For example, it prioritizes the adoption of proposals with a high number of positive emotional responses. The proposal generation unit also collects emotion estimation data in real time and develops a system that dynamically adjusts the quality of proposals. For example, it modifies the content of the proposal according to changes in the user's emotions. As a result, by using the emotion estimation function to monitor the user's emotional response to new project proposals and continuously improving the quality of proposals, more effective proposals become possible.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The data collection unit, for example, analyzes the HTML structure of a news site and extracts personnel transfer news. It uses an API to obtain posted data from Twitter and Facebook. It converts seminar lecture content into text data using speech recognition technology. The analysis unit analyzes the collected data. For example, the analysis unit may analyze text data using natural language processing technology to evaluate interest in a specific topic. The analysis unit may also analyze data patterns using machine learning algorithms. Furthermore, the analysis unit may perform sentiment analysis and extract emotional fluctuation patterns from the data. Based on the analysis results, the proposal generation unit generates customer service methods for consumers and proposal stories for corporations. For example, if the proposal generation unit determines that a customer is interested in a particular brand or product based on the analysis results, it may propose a personalized customer service method based on that information. Furthermore, if the proposal generation unit determines that a customer is interested in a company's industry trends and challenges, it may also construct a proposal story based on that information. Furthermore, the proposal generation unit may use an emotion estimation function to evaluate the effectiveness of proposals and improve future proposals. As a result, the AI ​​system of the embodiment can analyze various data related to a specific person and identify that person's mindset and areas of interest, enabling more effective customer service and suggestions.

[0094] The analysis unit, for example, analyzes the collected content of social media posts and calculates a positive, negative, or neutral emotion score. This allows for identifying patterns of emotional fluctuations over a specific period of time and for a detailed understanding of the person's psychological state. The analysis unit also analyzes the content of seminar lectures and monitors the speaker's emotional fluctuations in real time. For example, it identifies the parts the speaker emphasized and the parts that made them emotionally charged, and analyzes the person's areas of interest and psychological state. The analysis unit also analyzes the content of Yahoo! LINE messages and extracts patterns of emotional fluctuation. For example, it analyzes emotional fluctuations on specific topics and identifies the changes in the person's psychological state and interests. This allows for identifying a person's interests from the content of social media posts, making it possible to make more personalized suggestions.

[0095] The analysis unit, for example, analyzes a person's social media posting history and identifies changes in that person's interests based on the content of posts over the past few years. For example, it analyzes how interest in a particular topic has changed over time. The analysis unit also collects past purchase history and analyzes the types and frequency of products purchased. This identifies changes in the person's purchasing trends and interests. The analysis unit also analyzes seminar participation history and identifies changes in the person's expertise and areas of interest based on the themes and content of seminars attended in the past. This allows for more appropriate suggestions to be made by identifying a person's expertise and areas of interest from the content of seminar lectures.

[0096] The proposal generation unit, for example, analyzes the content of posts on social media in real time and calculates an emotion score using an emotion estimation function. As a result, the analysis results are dynamically updated based on emotional fluctuations. The proposal generation unit also analyzes the content of seminar lectures in real time and estimates the speaker's emotions. For example, it analyzes the speaker's tone of voice and facial expressions and updates the analysis results based on emotional fluctuations. The proposal generation unit also analyzes the content of Yahoo! LINE messages in real time and calculates an emotion score using an emotion estimation function. As a result, the analysis results are dynamically updated based on emotional fluctuations. As a result, if a customer is interested in a particular brand or product, personalized customer service methods are proposed based on that information, improving customer satisfaction.

[0097] The proposal generation unit, for example, collects blog articles and analyzes their content to identify the interests and concerns of a specific person. For example, it analyzes the frequency and content of articles on a specific theme. The proposal generation unit also collects forum posts and analyzes the opinions and questions of the posters. This identifies what topics a specific person is interested in. The proposal generation unit also collects articles related to a specific person from news sites and analyzes their content. For example, it identifies news topics that a specific person is interested in. This makes it possible to make more effective proposals if the person is interested in industry trends and challenges within a company by building a proposal story based on that information.

[0098] The data collection unit, for example, correlates and analyzes the content of social media posts with the content of seminar lectures. For example, it identifies similarities between comments on social media and comments at seminars and analyzes consistency of interests. The data collection unit also correlates and analyzes the content of Yahoo! LINE messages with purchase history. For example, it identifies the relationship between the message content and purchased products and analyzes purchasing motivations. The data collection unit also correlates and analyzes the content of transfer news with the content of social media posts. For example, it analyzes changes in the content of social media posts after a transfer and identifies the impact the transfer has on the person's interests. This allows the content of social media posts to be analyzed regularly and new interests and concerns to be identified, making it possible to always make proposals based on the latest information.

[0099] The proposal generation unit, for example, analyzes the content of posts on social media in real time and calculates an emotion score using an emotion estimation function. As a result, posts with high emotion scores are preferentially collected. The proposal generation unit also analyzes the content of seminar lectures in real time and estimates the emotions of the speakers. As a result, parts with high emotions are preferentially collected. The proposal generation unit also analyzes the content of Yahoo! LINE messages in real time and calculates an emotion score using an emotion estimation function. As a result, messages with high emotion scores are preferentially collected. As a result, the effectiveness of proposals can be evaluated and the next proposal can be improved, enabling more effective proposals.

[0100] The analysis unit, for example, analyzes the collected content of social media posts and calculates a positive, negative, or neutral emotion score. This allows for identifying patterns of emotional fluctuations over a specific period of time and for a detailed understanding of the person's psychological state. The analysis unit also analyzes the content of seminar lectures and monitors the speaker's emotional fluctuations in real time. For example, it identifies the parts the speaker emphasized and the parts where emotions were high, and analyzes the person's areas of interest and psychological state. The analysis unit also analyzes the content of Yahoo! LINE messages and extracts patterns of emotional fluctuation. For example, it analyzes emotional fluctuations on specific topics and identifies the changes in the person's psychological state and interests. By analyzing patterns of emotional fluctuations, the person's psychological state can be identified in more detail.

[0101] The data collection unit, for example, collects blog articles and analyzes their content to identify the interests and concerns of a specific person. For example, it analyzes the frequency and content of articles on a specific topic. The data collection unit also collects the content of forum posts and analyzes the opinions and questions of the posters. This identifies what topics a specific person is interested in. The data collection unit also collects articles related to a specific person from news sites and analyzes their content. For example, it identifies news topics that a specific person is interested in. This allows data to be collected from a wider variety of information sources, improving the accuracy of the analysis.

[0102] The analysis unit, for example, correlates and analyzes the content of social media posts with the content of seminar lectures. For example, it identifies similarities between comments on social media and comments at seminars and analyzes consistency of interests. The analysis unit also correlates and analyzes the content of Yahoo! LINE messages with purchasing history. For example, it identifies the relationship between message content and purchased products and analyzes purchasing motivations. The analysis unit also correlates and analyzes transfer news with the content of social media posts. For example, it analyzes changes in the content of social media posts after a transfer and identifies the impact the transfer has on the person's interests. This makes it possible to analyze the correlation between different data sources and mutually complement the data, thereby obtaining more accurate analysis results.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The data collection department collects data on company transfer news, social media, seminar lectures, and Yahoo! LINE. For example, the data collection department uses web scraping technology to collect transfer news from news sites. The data collection department can also use APIs to obtain social media post data. Furthermore, the data collection department can record the content of seminar lectures and convert it into text data. For example, the data collection department analyzes the HTML structure of news sites to extract transfer news. It uses APIs to obtain post data from Twitter and Facebook. The content of seminar lectures is converted into text data using voice recognition technology. Step 2: The analysis unit analyzes the collected data. For example, the analysis unit may use natural language processing technology to analyze text data and evaluate the level of interest in a particular topic. The analysis unit may also use machine learning algorithms to analyze data patterns. The analysis unit may also perform sentiment analysis and extract patterns of emotional fluctuations from the data. For example, the analysis unit may use text mining technology to extract keywords from the data and evaluate the level of interest. A machine learning algorithm may be used to cluster the data and analyze patterns. A sentiment analysis algorithm may be used to calculate positive, negative, or neutral sentiment scores from the data. Step 3: The proposal generation unit generates customer service methods for consumers and proposal stories for corporations based on the analysis results. For example, if the customer is interested in a particular brand or product based on the analysis results, the proposal generation unit can propose a personalized customer service method based on that information. In addition, if the customer is interested in the company's industry trends and issues, the proposal generation unit can also build a proposal story based on that information. Furthermore, the proposal generation unit can use the emotion estimation function to evaluate the effectiveness of the proposal and improve the next proposal. For example, the proposal generation unit can propose attentive customer service and the introduction of high-quality products to a customer who is interested in a particular brand. It can propose environmentally friendly products and services to a customer who is interested in the company's industry trends. It can use the emotion estimation function to evaluate the effectiveness of the proposal and improve the next proposal.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0109] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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).

[0114] 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.

[0115] 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.

[0116] 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.

[0117] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0118] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 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.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, 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.

[0126] 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.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] 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).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] 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.

[0131] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0133] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0134] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] The data processing system 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.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0149] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 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.

[0151] 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.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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).

[0158] 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.

[0159] 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."

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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]

[0172] 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 data collection department that collects company transfer news, social media, seminar lectures, and social media data. an analysis unit that analyzes the data collected by the data collection unit; and a proposal generation unit that generates a method of serving consumers or a proposal story for corporations based on the analysis results obtained by the analysis unit. A system characterized by:

2. The analysis unit Analyzing what topics a person is interested in based on the content of their posts on the SNS 2. The system of claim 1.

3. The analysis unit Identify the person's area of ​​expertise or interest from the content of the seminar presentation 2. The system of claim 1.

4. The proposal generation unit If you have an interest in a particular brand or product, we can use that information to provide you with personalized customer service.

2. The system of claim 1.

5. The proposal generation unit If the person is interested in industry trends or challenges facing the company they work for, use that information to build a proposal story.

2. The system of claim 1.

6. The data collection unit Periodically analyze the content of posts on the SNS to identify new interests or concerns 2. The system of claim 1.

Images