system

Abstract

We provide the system. [Solution] Means of collecting information, The means of analyzing the collected information, A means of training a generative model based on the analysis results, A means of generating proposed content using a generative model, Means of distributing proposed content, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Proposed products and solutions for corporations are diverse and new information is updated daily, so it takes a great deal of time and effort for sales staff to create appropriate proposal documents for each customer. Also, it is difficult for customers to efficiently obtain information and proposals that match their own issues. Furthermore, while it is understood that video marketing has a high appeal, creating videos requires a great deal of cost and time. In such a situation, there is a problem that it is difficult to realize efficient and effective sales proposals.

Means for Solving the Problems

[0005] This invention provides a system that includes means for collecting information, means for analyzing the collected information, means for training a generative model based on the analysis results, means for generating proposal content using the generative model, and means for distributing the generated proposal content. This makes it possible to create original video-format proposals tailored to customer needs quickly and at low cost, enabling efficient sales activities. Furthermore, by utilizing the customer's past inquiry history, more accurate proposals can be made, and customers can efficiently obtain useful information.

[0006] "Means for collecting information" refers to a device or method that has the function of automatically collecting necessary information from multiple information sources such as databases and the internet.

[0007] "Means for analyzing collected information" refers to devices or methods that have the function of processing and analyzing acquired data to reveal industry trends and customer needs.

[0008] "Means for training generative models" refers to devices or methods that have the function of training machine learning models based on collected and analyzed data and improving their accuracy.

[0009] "Means for generating proposed content using a generative model" refers to an apparatus or method that utilizes a trained generative model to create customized content tailored to customer needs.

[0010] "Means for distributing proposal content" refers to a device or method that has the function of sending generated proposal content to customers or sales representatives in an appropriate format.

[0011] "Customer's past inquiry history" refers to the content of previous inquiries and consultations made by the customer. This data is used in analysis to provide information that can be used as a reference for making more appropriate suggestions. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is a system for efficiently generating and distributing proposal content for corporate clients, and mainly includes a process of collecting and analyzing information and automatically generating customized proposal content using a generation model.

[0034] Program Processing Description

[0035] The server automatically collects sales activity information, product information, industry news, customer information, and other data from internal databases and external sources at pre-configured frequencies. This ensures that the latest information is always available.

[0036] The server integrates this collected data and performs AI-powered analysis. This analysis identifies customer trends and potential needs, and predicts overall industry trends.

[0037] Users (sales representatives) input specific customer names and solution categories into the system. This allows for proposals tailored to specific needs.

[0038] The server uses a generative model based on the input information and analysis results to generate a customized video proposal for the customer. This proposal includes product introductions and simulations that are likely to interest the customer.

[0039] The device sends the generated video proposal to the customer's email address. The email includes a summary of the proposal and is formatted so that the customer can play the proposal video on any device.

[0040] Specific example

[0041] When targeting a medium-sized enterprise, if the user provides instructions to propose a security solution, the server selects recommended products based on the company's past inquiry history and industry cybersecurity trends, and generates a video proposal. This video includes actual demonstration scenes and case studies to enhance its visual appeal. When the terminal sends this proposal video, it can generate an effective email template for the initial proposal, strengthening the impression made on the customer.

[0042] This system configuration enables more efficient sales activities and improved proposal accuracy, making meaningful business negotiations possible for both sales representatives and customers.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server collects information from internal databases and multiple external sources according to a set schedule. The collected information includes sales activity data, product information, and industry news. The collected information is stored in the database, where duplicates are removed and the formatting is standardized.

[0046] Step 2:

[0047] The server uses an AI analysis engine to analyze the collected information. This analysis includes predicting customer trends, identifying industry trends, and determining customer needs. The analysis results are saved as reference data for subsequent proposal generation processes.

[0048] Step 3:

[0049] The user logs into the system and enters a specific customer name and the area of ​​solution they wish to propose. The more specific these instructions are, the more accurate the customized proposal will be.

[0050] Step 4:

[0051] The server combines the information entered by the user with the analysis results from step 2 and creates suggested content using a generative model. Here, it automatically generates product introductions, use cases, and simulation videos tailored to customer characteristics.

[0052] Step 5:

[0053] The device encodes the generated suggestion content in the optimal format and sends it to the customer's email address. During sending, an email template encouraging video viewing is automatically generated and inserted.

[0054] Step 6:

[0055] Users utilize the submitted video proposals during business negotiations to explain the details of the proposal to customers. They play the videos through their devices, enhancing the visual approach in their presentations.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] There is a need to provide a means to efficiently and effectively generate and distribute proposal content for corporate clients. Traditional proposal processes often involve manual information gathering and analysis, which is time-consuming, and there is a desire for improved accuracy and speed in customizing and distributing proposal content.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes means for collecting information, means for integrating and analyzing the collected information, means for identifying trends and potential demands of others and predicting industry-wide trends, means for generating proposals using a generation AI model based on the analysis results and input information, and means for distributing the proposals. This enables the rapid generation and highly accurate customization of proposal content for corporate customers.

[0061] "Means of collecting information" refers to technologies for automatically retrieving relevant information from databases and external information sources.

[0062] "Means for integrating and analyzing collected information" refers to techniques for centralizing and formatting acquired data, and then extracting and evaluating information relevant to a specific purpose.

[0063] "A means of identifying trends and potential demands and predicting industry-wide developments" refers to a process of interpreting customer behavior patterns and market changes from data to foresee future needs.

[0064] "Methods for generating proposal content using generative AI models" refers to technologies that use generative models to construct concrete proposal documents based on information and analysis results.

[0065] "Means for distributing proposal content" refers to communication methods and systems for delivering generated proposal content to target recipients.

[0066] This invention is a system for efficiently generating and distributing proposal content for corporate clients. The details of the embodiment of this invention are described below.

[0067] First, the server periodically collects data from various sources. These sources include database systems and news websites, utilizing common commercial database software and web APIs. Specific examples include collecting sales activity information and product data from internal databases, and industry news from external sources.

[0068] Next, the server performs operations to integrate and analyze this collected data. For this purpose, it uses analytical tools such as Amazon Web Services (AWS®) SageMaker and Google®'s AI platform. This makes it possible to identify customer trends and potential needs and predict industry trends.

[0069] Users input information into the system by specifying a particular customer and the category of solution they will offer to that customer. This input is done through an interface such as Salesforce.

[0070] Based on this information, the server uses a generative AI model to create customized suggestion content. For example, it uses an OpenAI® generative model to generate personalized suggestions for each customer, which may include product introductions and simulation videos.

[0071] Finally, the device delivers the generated proposal content to the recipient. This delivery uses a common email service (e.g., Outlook, Gmail). The email includes a summary of the proposal and a link to play a video, which the customer can use to view the content.

[0072] As a concrete example, when proposing a security solution to a medium-sized company, the user instructs the system to do so. The server then generates a video based on the company's historical data and cybersecurity trends, and the terminal distributes that video. This process improves the accuracy of the proposal and the efficiency of sales activities.

[0073] An example of a prompt message is: "Generate a security solution proposal for a specific customer. Consider past inquiry history and industry trends, and include a visually impactful demo."

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server collects the necessary data from various information sources. First, it has access to internal databases and external information sources, and periodically performs processes to collect sales activity information, product information, industry news, etc. The input is raw data obtained from databases and APIs. The output is a structured dataset. At this stage, for example, database queries are executed and API calls are made.

[0077] Step 2:

[0078] The server integrates and analyzes the collected data. The input here is the raw data collected in Step 1. Specifically, it performs data cleaning, formatting standardization, and data normalization, and then prepares the input data for application to the analytical model. The output is an analyzable dataset. This dataset is used on the AI ​​platform to derive potential customer needs and industry trends.

[0079] Step 3:

[0080] The user enters a specific customer name and the category of the proposed solution. The input includes customer information and the category of the proposed solution obtained from the user. The server formats this information appropriately for the AI ​​model. The output is formalized data to initiate the AI ​​model's proposal generation process.

[0081] Step 4:

[0082] The server generates suggested content using a generative AI model. This process generates suggested content based on the analysis results from step 2 and the user input from step 3. Specifically, the AI ​​model automatically creates proposal documents and video content using prompt text. Customized proposal documents and video files are generated as output.

[0083] Step 5:

[0084] The terminal distributes the generated proposal content to recipients. The input is the proposal content created in step 4. Specifically, it sends the proposal content to the recipient's email address using the email system. The output is an email in a format playable on various devices used by the customer, enabling rapid information dissemination.

[0085] (Application Example 1)

[0086] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0087] While there is a need to efficiently generate and deliver proposal content optimized for the individual needs of corporate clients, conventional systems have the challenge of limited effectiveness because they do not adequately customize to the industry characteristics and interests of clients.

[0088] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0089] In this invention, the server includes means for collecting information, means for analyzing the collected information, means for training a generative model based on the analysis results, means for generating suggested content using the generative model, means for transmitting the generated suggested content using communication means, and means for proposing electronic trading solutions tailored to the customer's industry and interests. This makes it possible to effectively generate and deliver optimized suggestions for each customer.

[0090] "Means of collecting information" refers to the function of obtaining customer information and industry data through internal and external databases and APIs.

[0091] "Means of analyzing information" refers to the function of analyzing collected data using AI algorithms to identify customer needs and industry trends.

[0092] "Methods for training generative models" refer to functions that enable highly accurate predictions and suggestions by training generative AI models based on analysis results.

[0093] "Methods for generating proposal content using generative models" refers to a function that utilizes a trained generative AI model to create proposal materials tailored to individual customer needs.

[0094] "Means of transmission using communication means" refers to the function of distributing generated proposal content to customers via email or messaging services over the internet.

[0095] "Means of proposing electronic transaction solutions" refers to the function of building and proposing appropriate e-commerce solutions based on the customer's industry and areas of interest.

[0096] The system implementing this invention is for efficiently generating and distributing proposal content for corporate clients. The system mainly consists of a server, terminals, and users.

[0097] The server automatically collects information via a database or API. Specifically, it utilizes high-performance server equipment as hardware and executes data collection scripts using programming languages ​​such as Python as software. The collected information is diverse, including customer information, industry trends, and past inquiry history.

[0098] Next, the server analyzes the information using AI algorithms. It trains AI models using machine learning libraries such as TENSORFLOW® and Scikit-learn. This process makes it possible to understand individual customer needs and industry trends.

[0099] Based on the generated analysis data, the server utilizes a generative AI model to create suggested content. Using advanced natural language processing technologies such as OpenAI's GPT model, it provides customized suggestions tailored to customer needs. This suggested content can take the form of a combination of text, images, and videos.

[0100] Meanwhile, the terminal transmits this proposed content to the customer using communication methods. Specifically, it utilizes communication methods such as email and instant messaging applications to deliver the generated content as a video link. This allows the customer to view the proposed content on any device.

[0101] Finally, users utilize the suggested content provided by this system to conduct sales activities. Users can input specific customer names and solution categories into the server and instantly generate and send customized proposals.

[0102] As a concrete example, when proposing a multi-currency electronic transaction solution to an office supplies company, it is possible to generate videos that showcase the most effective products and services based on the customer's characteristics and market trends. Examples of prompts to support this workflow include the following:

[0103] Example of a prompt:

[0104] Proposal for electronic transaction solutions for corporate clients:

[0105] Customer industry: Office supplies

[0106] Features of interest: Multi-currency support, advanced security features

[0107] Past inquiries: Payment integration via API

[0108] Based on this, please generate a customized proposal.

[0109] This system configuration enables more efficient sales activities and more accurate proposals.

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server automatically collects data such as customer information, industry trends, and past inquiry history using internal databases and external APIs. The input for this data collection is API requests and database queries, and the output is a set of retrieved raw data. A Python script is used to run this process periodically.

[0113] Step 2:

[0114] The server analyzes the collected data. The input is raw data, and AI algorithms are used to analyze it. Specifically, Scikit-learn and TensorFlow are used to perform clustering and classification in order to identify trends and patterns hidden in the data. The output is the analysis results regarding customer purchasing trends and industry trends.

[0115] Step 3:

[0116] The server trains the generative AI model. It uses the analysis results obtained in step 2 as input and updates the model using a framework such as TensorFlow. This training process allows the model to make more accurate predictions. The output is a customer-specific suggestion content generation model.

[0117] Step 4:

[0118] The server generates suggestion content using an updated generative AI model. The input consists of customer information and solution categories specified by the user, and the generative model creates customized suggestion content based on this information. The output is suggestion content in visually appealing formats such as videos and slides.

[0119] Step 5:

[0120] The device sends the generated proposal content to the customer. The input consists of the generated proposal content and the customer's contact information. This information is used to deliver the proposal via email or instant messaging apps. The output is content in the form of links or files that the customer can access on any device.

[0121] Step 6:

[0122] Users utilize suggested content from the server to support their sales activities. The input is customized suggestions provided by the server, and the output is used for preparing sales negotiations and presentations to customers.

[0123] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0124] The present invention aims to achieve greater appeal and effectiveness in a system for generating and distributing proposal content for corporate clients by using an emotion engine to recognize the user's emotions in real time and dynamically customizing the proposal content based on those emotions.

[0125] Program Processing Description

[0126] The server first collects information from both internal and external sources and stores it in a database. This information includes past customer inquiry history, industry trend information, and product information. The information is regularly updated and formatted to be suitable for analysis.

[0127] The server analyzes the collected data and trains an AI model. This model learns which customers the proposed products and solutions are suitable for.

[0128] The user inputs the target customer's information and instructs the server to generate suggestions. This input includes the customer's name, product categories of interest, and past behavioral patterns.

[0129] The server uses a generative model to create suggested content based on user input and analysis results.

[0130] The server is connected to an emotion engine that recognizes user emotions, analyzing the user's voice and facial expressions in real time during online calls and presentations. This allows the content and presentation of the proposal to be modified according to the emotions the user displays during the proposal.

[0131] The device delivers the final generated suggestion content to customers via email or direct interaction. During delivery, the video is optimized based on sentiment analysis.

[0132] Specific example

[0133] Let's consider a scenario where a sales representative proposes new security software to Company A. The user (sales representative) inputs basic information about Company A and the purpose of the proposal into the server and activates the emotion engine. During the presentation, the server's emotion engine detects emotions from the sales representative's tone of voice and facial expressions. If the other party shows excitement or interest, the system automatically makes changes such as deepening the proposal content and adding a visual demo video. Through this process, customer interest and satisfaction can be increased.

[0134] This system will improve the quality of communication with customers and enhance the results of sales activities.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] The server automatically collects information from internal databases and external sources. This information includes past customer inquiry data, current market trends, and technical specifications for new products, and is stored in the database. The collected information is formatted and analyzed to a standardized format.

[0138] Step 2:

[0139] The server analyzes the accumulated data and trains a generative model. Using AI algorithms, it learns potential product and service suggestions that meet customer needs. The trained model is then used in the process of creating suggestion content.

[0140] Step 3:

[0141] The user enters information about the target customer into a format. This includes providing the customer's name, product categories of interest, and past transaction history, which helps establish the criteria for customized proposals.

[0142] Step 4:

[0143] The server combines user input with data learned by an AI model to generate suggested content. This content is designed in video format and may include presentation materials or demo videos.

[0144] Step 5:

[0145] During the proposal process, an emotion engine installed on the server activates, monitoring the user's voice and facial expressions in real time. The emotion engine analyzes the customer's reactions and evaluates their level of interest, dynamically adjusting the proposal accordingly.

[0146] Step 6:

[0147] The device delivers the generated proposal content to the customer. The proposal video is not only sent via email, but is also used as a presentation tool during face-to-face business meetings, providing optimal information based on the customer's emotional feedback.

[0148] (Example 2)

[0149] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0150] When generating proposal content for corporate clients, there is a challenge in effectively considering customer emotions to achieve higher appeal and conversion rates. Traditional systems are limited to generating static content that ignores emotions, and have failed to maximize customer interest and engagement.

[0151] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0152] In this invention, the server includes means for collecting information, means for analyzing the collected information, means for training a generative model based on the analysis results, means for generating suggested content using the generative model, means for distributing the suggested content, and means for recognizing the user's emotions in real time and dynamically adjusting the suggested content. This enables the generation and distribution of dynamic and effective suggested content that responds to changes in the customer's emotions.

[0153] "Means of collecting information" refers to a system for acquiring and accumulating data from internal and external information sources.

[0154] "Means of analysis" refers to the process of processing collected data to derive useful insights.

[0155] "Means for training generative models" refer to functions that use collected data to train AI models and improve their ability to recognize specific patterns and trends.

[0156] "Methods for generating suggestion content using generative models" refer to a system that utilizes a trained AI model to automatically create optimal suggestions for customers.

[0157] "Means for distributing proposed content" refers to functions for delivering generated proposed content to customers, using methods such as email or video conferencing.

[0158] "A means of recognizing user emotions in real time and dynamically adjusting suggested content" refers to a function that uses an emotion engine to analyze the user's emotional state in real time and change the suggested content accordingly.

[0159] This invention relates to a system for dynamically generating and delivering proposal content for corporate clients. Its primary objective is to maximize effectiveness by utilizing AI technology and emotion recognition technology to adjust proposal content according to the client's emotions.

[0160] The system's core is the server, where information is collected, analyzed, models are trained, and content is generated and distributed. Information collection includes functions to retrieve data from internal databases, external APIs, and internet resources. The information is diverse, encompassing customer inquiry history, industry trends, and related product information. Analysis involves data processing and cleansing using Python.

[0161] Next, the server uses AI frameworks such as TensorFlow and PyTorch to train generative models with the collected data. This creates models capable of predicting and generating personalized recommendations for each customer.

[0162] This trained generative AI model is used to generate suggested content. Based on user instructions and prompts, it constructs content and automatically creates presentation materials. Slide creation tools such as PowerPoint and Google Slides are also utilized in this process.

[0163] During the proposal delivery phase, the device sends the final content to the customer via email or direct presentation. This is where the emotion recognition engine plays a crucial role. It analyzes the user's emotions in real time and makes necessary adjustments during the presentation to capture the customer's interest and attention. Furthermore, optimizations such as enhancing visual content are performed as needed.

[0164] A concrete example would be a scenario where a sales representative, acting as a user, inputs information into a server and creates proposal content according to the instructions of a generative model in order to propose new security software. An example of a prompt might be, "Create a proposal for new security software for a specific company. This company has a strong interest in data security."

[0165] This will further strengthen communication between companies and customers, making it possible to significantly improve sales results.

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] The server collects data from internal and external sources. This input includes customer inquiry history, purchase history, and industry trend information. The server cleanses, removes duplicates, and standardizes the format of this data before storing it in an internal database. This process results in customer information data organized in a format suitable for analysis.

[0169] Step 2:

[0170] The server trains an AI model using the collected data. Cleansed customer data is used as input. The server uses frameworks such as TensorFlow and PyTorch to label past inquiry history and train the model to optimize it. The output is a generative AI model with improved prediction accuracy.

[0171] Step 3:

[0172] The user inputs customer information through the server interface and instructs the server to create suggestions. This input includes customer name, location, industry, product categories of interest, and past behavioral patterns. Based on this input, the server generates prompts. These prompts function as instructions for the AI ​​model, serving as guidelines for content generation.

[0173] Step 4:

[0174] The server uses the generated prompts and trained AI model to create suggested content. This process generates the necessary graphs, charts, and text information based on user input, constructing presentation materials. The output is a customized suggested document or presentation slides.

[0175] Step 5:

[0176] The server uses an emotion engine to recognize the user's emotions in real time. Input includes voice tone and facial expression data from the presentation. The server analyzes this data to determine the user's current emotional state. The output is a dynamic content adjustment action based on this analysis. If necessary, the suggestions are improved in real time to optimize user engagement.

[0177] Step 6:

[0178] The terminal delivers the final proposal content. The input is optimized proposal materials provided by the server. The terminal uses this to send emails to customers or to use the materials in direct business negotiations. The output is the presentation materials or proposal delivered to the customer, which are used for actual communication.

[0179] (Application Example 2)

[0180] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0181] In modern sales activities, understanding customer emotions in real time and proposing products and services accordingly is a challenging task. Traditional systems tend to rely heavily on analysis based on static customer data, failing to utilize customer emotional states. As a result, it was difficult to communicate with customers more effectively and maximize sales opportunities.

[0182] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0183] In this invention, the server includes means for collecting information, means for analyzing the collected information, means for training a generative model based on the analysis results, means for generating suggested content using the generative model, means for distributing the suggested content, means for analyzing emotional states, means for dynamically customizing the suggested content based on the analyzed emotional states, means for recognizing facial features, and means for processing audio data. This enables real-time recognition of customer emotions and the generation and distribution of appropriate suggested content accordingly.

[0184] "Means of collecting information" refers to functions for gathering customer data, market information, and so on.

[0185] "Means of analysis" refer to functions for processing collected information and identifying patterns and trends.

[0186] "Means for training generative models" refers to functions that use past data and analysis results to train AI models.

[0187] "Methods for generating suggested content using generative models" refers to a function that utilizes a trained AI model to create suggested content tailored to the user.

[0188] "Means for distributing proposed content" refers to functions for sending or presenting generated proposed content to users or customers.

[0189] "Means of analyzing emotional state" refers to a function that reads emotions from a customer's facial expressions and voice, and evaluates their current emotional state.

[0190] The "dynamic customization method" refers to a function that instantly optimizes suggested content based on sentiment data obtained in real time.

[0191] "Means of recognizing facial features" refers to a function that analyzes image data acquired through a camera to identify facial expressions and characteristics.

[0192] "Means for processing audio data" refers to a function that analyzes audio acquired through a microphone and extracts linguistic content and emotions.

[0193] This invention is a system for streamlining customer service in physical stores. Its main components consist of a server that processes information, terminals used by sales staff, and users who input data.

[0194] The server aggregates customer information and trains an AI model based on the collected data. Data collection is performed using two methods: image acquisition via camera and audio acquisition via microphone. The server uses OpenCV for facial recognition on the image data and Google Cloud Speech-to-Text for processing the audio data. This allows for real-time analysis of the customer's emotional state, and based on this analysis, a generative AI model (e.g., Hugging Face Transformer) is used to generate personalized suggestion content.

[0195] The device provides salespeople with generated suggestion content, supporting real-time customer service. The suggestion content is dynamically customized based on the customer's emotional state, improving sales efficiency.

[0196] Users interact with customers while operating their devices. By providing content that captures customers' interests and concerns, improved customer satisfaction can be expected.

[0197] As a concrete example, consider a scenario where a customer is browsing for items in a clothing store on a holiday. The salesperson uses a terminal to assist the customer, and the system suggests appropriate products and styling options. At this time, the system analyzes the customer's responses in real time and instantly optimizes the suggestions.

[0198] The generative AI model enables effective suggestions by using prompts such as, "When a customer shows excitement, generate the optimal combination of products to suggest based on the product categories and related information they are interested in."

[0199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0200] Step 1:

[0201] The server receives image and audio data transmitted from the smartphone's camera and microphone. The input consists of images showing the customer's facial expressions and audio of their conversation. This data is necessary as preprocessing for sentiment analysis.

[0202] Step 2:

[0203] The server uses the OpenCV library to recognize the facial features of the customer from the received image data and analyze their facial expressions. The input is facial image data, and the output is data indicating the customer's emotional state. This analysis quantitatively evaluates what emotions the customer is currently experiencing.

[0204] Step 3:

[0205] The server uses Google Cloud Speech-to-Text to convert audio data into text and analyzes the conversation content and customer tone from that text. The input is the customer's audio data, and the output is the emotional state derived from the customer's utterances and tone. This process allows for an understanding of the customer's interests and concerns.

[0206] Step 4:

[0207] The server integrates emotional state data obtained from facial expressions and voice, creating a dataset to input into the generative AI model. This prepares it to make suggestions that reflect emotions in real time.

[0208] Step 5:

[0209] The server uses generative AI models such as Hugging Face Transformer to generate optimal suggestion content based on prompt text. The input is integrated sentiment data and prompt text, and the output is dynamically customized suggestion content. This enables the suggestion of the most suitable products and services tailored to the customer's interests.

[0210] Step 6:

[0211] The terminal receives suggestion content sent from the server and displays it to the salesperson. The input is the suggestion content generated by the server, and the output is the selection displayed on the screen. This allows the salesperson to provide suggestions tailored to the customer's needs in real time.

[0212] Step 7:

[0213] Users operate the terminal to make proposals to customers and observe their reactions. Salespeople can use the information provided by the system to conduct sales while communicating appropriately.

[0214] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0215] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search)<url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0220] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0221] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0222] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0223] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0224] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0225] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0227] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0228] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0229] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0230] This invention is a system for efficiently generating and distributing proposal content for corporate clients, and mainly includes a process of collecting and analyzing information and automatically generating customized proposal content using a generation model.

[0231] Program Processing Description

[0232] The server automatically collects sales activity information, product information, industry news, customer information, and other data from internal databases and external sources at pre-configured frequencies. This ensures that the latest information is always available.

[0233] The server integrates this collected data and performs AI-powered analysis. This analysis identifies customer trends and potential needs, and predicts overall industry trends.

[0234] Users (sales representatives) input specific customer names and solution categories into the system. This allows for proposals tailored to specific needs.

[0235] The server uses a generative model based on the input information and analysis results to generate a customized video proposal for the customer. This proposal includes product introductions and simulations that are likely to interest the customer.

[0236] The device sends the generated video proposal to the customer's email address. The email includes a summary of the proposal and is formatted so that the customer can play the proposal video on any device.

[0237] Specific example

[0238] When targeting a medium-sized enterprise, if the user provides instructions to propose a security solution, the server selects recommended products based on the company's past inquiry history and industry cybersecurity trends, and generates a video proposal. This video includes actual demonstration scenes and case studies to enhance its visual appeal. When the terminal sends this proposal video, it can generate an effective email template for the initial proposal, strengthening the impression made on the customer.

[0239] This system configuration enables more efficient sales activities and improved proposal accuracy, making meaningful business negotiations possible for both sales representatives and customers.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The server collects information from internal databases and multiple external sources according to a set schedule. The collected information includes sales activity data, product information, and industry news. The collected information is stored in the database, where duplicates are removed and the formatting is standardized.

[0243] Step 2:

[0244] The server uses an AI analysis engine to analyze the collected information. This analysis includes predicting customer trends, identifying industry trends, and determining customer needs. The analysis results are saved as reference data for subsequent proposal generation processes.

[0245] Step 3:

[0246] The user logs into the system and enters a specific customer name and the area of ​​solution they wish to propose. The more specific these instructions are, the more accurate the customized proposal will be.

[0247] Step 4:

[0248] The server combines the information entered by the user with the analysis results from step 2 and creates suggested content using a generative model. Here, it automatically generates product introductions, use cases, and simulation videos tailored to customer characteristics.

[0249] Step 5:

[0250] The device encodes the generated suggestion content in the optimal format and sends it to the customer's email address. During sending, an email template encouraging video viewing is automatically generated and inserted.

[0251] Step 6:

[0252] Users utilize the submitted video proposals during business negotiations to explain the details of the proposal to customers. They play the videos through their devices, enhancing the visual approach in their presentations.

[0253] (Example 1)

[0254] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0255] There is a need to provide a means to efficiently and effectively generate and distribute proposal content for corporate clients. Traditional proposal processes often involve manual information gathering and analysis, which is time-consuming, and there is a desire for improved accuracy and speed in customizing and distributing proposal content.

[0256] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0257] In this invention, the server includes means for collecting information, means for integrating and analyzing the collected information, means for identifying trends and potential demands of others and predicting industry-wide trends, means for generating proposals using a generation AI model based on the analysis results and input information, and means for distributing the proposals. This enables the rapid generation and highly accurate customization of proposal content for corporate customers.

[0258] "Means of collecting information" refers to technologies for automatically retrieving relevant information from databases and external information sources.

[0259] "Means for integrating and analyzing collected information" refers to techniques for centralizing and formatting acquired data, and then extracting and evaluating information relevant to a specific purpose.

[0260] "A means of identifying trends and potential demands and predicting industry-wide developments" refers to a process of interpreting customer behavior patterns and market changes from data to foresee future needs.

[0261] "Methods for generating proposal content using generative AI models" refers to technologies that use generative models to construct concrete proposal documents based on information and analysis results.

[0262] "Means for distributing proposal content" refers to communication methods and systems for delivering generated proposal content to target recipients.

[0263] This invention is a system for efficiently generating and distributing proposal content for corporate clients. The details of the embodiment of this invention are described below.

[0264] First, the server periodically collects data from various sources. These sources include database systems and news websites, utilizing common commercial database software and web APIs. Specific examples include collecting sales activity information and product data from internal databases, and industry news from external sources.

[0265] Next, the server performs operations to integrate and analyze this collected data. For this purpose, it uses analytical tools such as Amazon Web Services (AWS) SageMaker and Google's AI platform. This makes it possible to identify customer trends and potential needs and predict industry trends.

[0266] Users input information into the system by specifying a particular customer and the category of solution they will offer to that customer. This input is done through an interface such as Salesforce.

[0267] Based on this information, the server uses a generative AI model to create customized suggestion content. For example, it uses an OpenAI generative model to generate personalized suggestions for each customer, which may include product introductions and simulation videos.

[0268] Finally, the device delivers the generated proposal content to the recipient. This delivery uses a common email service (e.g., Outlook, Gmail). The email includes a summary of the proposal and a link to play a video, which the customer can use to view the content.

[0269] As a concrete example, when proposing a security solution to a medium-sized company, the user instructs the system to do so. The server then generates a video based on the company's historical data and cybersecurity trends, and the terminal distributes that video. This process improves the accuracy of the proposal and the efficiency of sales activities.

[0270] An example of a prompt message is: "Generate a security solution proposal for a specific customer. Consider past inquiry history and industry trends, and include a visually impactful demo."

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The server collects the necessary data from various information sources. First, it has access to internal databases and external information sources, and periodically performs processes to collect sales activity information, product information, industry news, etc. The input is raw data obtained from databases and APIs. The output is a structured dataset. At this stage, for example, database queries are executed and API calls are made.

[0274] Step 2:

[0275] The server integrates and analyzes the collected data. The input here is the raw data collected in Step 1. Specifically, it performs data cleaning, formatting standardization, and data normalization, and then prepares the input data for application to the analytical model. The output is an analyzable dataset. This dataset is used on the AI ​​platform to derive potential customer needs and industry trends.

[0276] Step 3:

[0277] The user enters a specific customer name and the category of the proposed solution. The input includes customer information and the category of the proposed solution obtained from the user. The server formats this information appropriately for the AI ​​model. The output is formalized data to initiate the AI ​​model's proposal generation process.

[0278] Step 4:

[0279] The server generates suggested content using a generative AI model. This process generates suggested content based on the analysis results from step 2 and the user input from step 3. Specifically, the AI ​​model automatically creates proposal documents and video content using prompt text. Customized proposal documents and video files are generated as output.

[0280] Step 5:

[0281] The terminal distributes the generated proposal content to recipients. The input is the proposal content created in step 4. Specifically, it sends the proposal content to the recipient's email address using the email system. The output is an email in a format playable on various devices used by the customer, enabling rapid information dissemination.

[0282] (Application Example 1)

[0283] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0284] There is a demand for efficiently generating and delivering proposal content optimized for individual needs for corporate customers. However, in conventional systems, customization according to the industry characteristics and interests of customers is insufficient, so there is a problem that the effect of the proposal is limited.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0286] In this invention, the server includes means for collecting information, means for analyzing the collected information, means for training a generation model based on the analysis result, means for generating proposal content using the generation model, means for transmitting the generated proposal content using communication means, and means for proposing an e-commerce solution specialized for the customer's industry and interests. As a result, it becomes possible to effectively generate and deliver proposals optimized for each customer.

[0287] The "means for collecting information" is a function of acquiring customer information and industry data through databases and APIs inside and outside the company.

[0288] The "means for analyzing information" is a function of analyzing the collected data using an AI algorithm to identify customer needs and industry trends.

[0289] The "means for training a generation model" is a function of learning a generated AI model based on the analysis result, enabling highly accurate predictions and proposals.

[0290] The "means for generating proposal content using the generation model" is a function of using the trained generated AI model to create proposal materials according to individual customer needs.

[0291] "Means of transmission using communication means" refers to the function of distributing generated proposal content to customers via email or messaging services over the internet.

[0292] "Means of proposing electronic transaction solutions" refers to the function of building and proposing appropriate e-commerce solutions based on the customer's industry and areas of interest.

[0293] The system implementing this invention is for efficiently generating and distributing proposal content for corporate clients. The system mainly consists of a server, terminals, and users.

[0294] The server automatically collects information via a database or API. Specifically, it utilizes high-performance server equipment as hardware and executes data collection scripts using programming languages ​​such as Python as software. The collected information is diverse, including customer information, industry trends, and past inquiry history.

[0295] Next, the server analyzes the information using AI algorithms. It trains AI models using machine learning libraries such as TensorFlow and Scikit-learn. This process makes it possible to understand individual customer needs and industry trends.

[0296] Based on the generated analysis data, the server utilizes a generative AI model to create suggested content. Using advanced natural language processing technologies such as OpenAI's GPT model, it provides customized suggestions tailored to customer needs. This suggested content can take the form of a combination of text, images, and videos.

[0297] Meanwhile, the terminal transmits this proposed content to the customer using communication methods. Specifically, it utilizes communication methods such as email and instant messaging applications to deliver the generated content as a video link. This allows the customer to view the proposed content on any device.

[0298] Finally, the user utilizes the proposed content provided by this system to conduct sales activities. The user can input a specific customer name or solution category into the server and immediately generate and send a customized proposal.

[0299] As a specific example, when proposing a multi-currency electronic trading solution for an office supplies company, videos introducing the most effective products and services can be generated based on customer characteristics and market trends. Examples of prompt texts to support this workflow are as follows.

[0300] Example of prompt text:

[0301] Proposal for electronic trading solution for corporate customers:

[0302] Customer's industry: Office supplies

[0303] Features of interest: Multi-currency support, advanced security features

[0304] Previous inquiries: Settlement integration via API

[0305] Based on this, please generate a customized proposal.

[0306] With this system configuration, the efficiency of sales activities and accurate proposals are realized.

[0307] The flow of specific processing in Application Example 1 will be described using FIG. 12.

[0308] Step 1:

[0309] The server automatically collects data such as customer information, industry trends, and past inquiry history using internal databases and external APIs. The input for this data collection is API requests and database queries, and the output is a set of retrieved raw data. A Python script is used to run this process periodically.

[0310] Step 2:

[0311] The server analyzes the collected data. The input is raw data, and AI algorithms are used to analyze it. Specifically, Scikit-learn and TensorFlow are used to perform clustering and classification in order to identify trends and patterns hidden in the data. The output is the analysis results regarding customer purchasing trends and industry trends.

[0312] Step 3:

[0313] The server trains the generative AI model. It uses the analysis results obtained in step 2 as input and updates the model using a framework such as TensorFlow. This training process allows the model to make more accurate predictions. The output is a customer-specific suggestion content generation model.

[0314] Step 4:

[0315] The server generates suggestion content using an updated generative AI model. The input consists of customer information and solution categories specified by the user, and the generative model creates customized suggestion content based on this information. The output is suggestion content in visually appealing formats such as videos and slides.

[0316] Step 5:

[0317] The device sends the generated proposal content to the customer. The input consists of the generated proposal content and the customer's contact information. This information is used to deliver the proposal via email or instant messaging apps. The output is content in the form of links or files that the customer can access on any device.

[0318] Step 6:

[0319] Users utilize suggested content from the server to support their sales activities. The input is customized suggestions provided by the server, and the output is used for preparing sales negotiations and presentations to customers.

[0320] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0321] The present invention aims to achieve greater appeal and effectiveness in a system for generating and distributing proposal content for corporate clients by using an emotion engine to recognize the user's emotions in real time and dynamically customizing the proposal content based on those emotions.

[0322] Program Processing Description

[0323] The server first collects information from both internal and external sources and stores it in a database. This information includes past customer inquiry history, industry trend information, and product information. The information is regularly updated and formatted to be suitable for analysis.

[0324] The server analyzes the collected data and trains an AI model. This model learns which customers the proposed products and solutions are suitable for.

[0325] The user inputs the target customer's information and instructs the server to generate suggestions. This input includes the customer's name, product categories of interest, and past behavioral patterns.

[0326] The server uses a generative model to create suggested content based on user input and analysis results.

[0327] The server is connected to an emotion engine that recognizes user emotions, analyzing the user's voice and facial expressions in real time during online calls and presentations. This allows the content and presentation of the proposal to be modified according to the emotions the user displays during the proposal.

[0328] The device delivers the final generated suggestion content to customers via email or direct interaction. During delivery, the video is optimized based on sentiment analysis.

[0329] Specific example

[0330] Let's consider a scenario where a sales representative proposes new security software to Company A. The user (sales representative) inputs basic information about Company A and the purpose of the proposal into the server and activates the emotion engine. During the presentation, the server's emotion engine detects emotions from the sales representative's tone of voice and facial expressions. If the other party shows excitement or interest, the system automatically makes changes such as deepening the proposal content and adding a visual demo video. Through this process, customer interest and satisfaction can be increased.

[0331] This system will improve the quality of communication with customers and enhance the results of sales activities.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] The server automatically collects information from internal databases and external sources. This information includes past customer inquiry data, current market trends, and technical specifications for new products, and is stored in the database. The collected information is formatted and analyzed to a standardized format.

[0335] Step 2:

[0336] The server analyzes the accumulated data and trains a generative model. Using AI algorithms, it learns potential product and service suggestions that meet customer needs. The trained model is then used in the process of creating suggestion content.

[0337] Step 3:

[0338] The user enters information about the target customer into a format. This includes providing the customer's name, product categories of interest, and past transaction history, which helps establish the criteria for customized proposals.

[0339] Step 4:

[0340] The server combines user input with data learned by an AI model to generate suggested content. This content is designed in video format and may include presentation materials or demo videos.

[0341] Step 5:

[0342] During the proposal process, an emotion engine installed on the server activates, monitoring the user's voice and facial expressions in real time. The emotion engine analyzes the customer's reactions and evaluates their level of interest, dynamically adjusting the proposal accordingly.

[0343] Step 6:

[0344] The device delivers the generated proposal content to the customer. The proposal video is not only sent via email, but is also used as a presentation tool during face-to-face business meetings, providing optimal information based on the customer's emotional feedback.

[0345] (Example 2)

[0346] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0347] When generating proposal content for corporate clients, there is a challenge in effectively considering customer emotions to achieve higher appeal and conversion rates. Traditional systems are limited to generating static content that ignores emotions, and have failed to maximize customer interest and engagement.

[0348] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0349] In this invention, the server includes means for collecting information, means for analyzing the collected information, means for training a generative model based on the analysis results, means for generating suggested content using the generative model, means for distributing the suggested content, and means for recognizing the user's emotions in real time and dynamically adjusting the suggested content. This enables the generation and distribution of dynamic and effective suggested content that responds to changes in the customer's emotions.

[0350] "Means of collecting information" refers to a system for acquiring and accumulating data from internal and external information sources.

[0351] "Means of analysis" refers to the process of processing collected data to derive useful insights.

[0352] "Means for training generative models" refer to functions that use collected data to train AI models and improve their ability to recognize specific patterns and trends.

[0353] "Methods for generating suggestion content using generative models" refer to a system that utilizes a trained AI model to automatically create optimal suggestions for customers.

[0354] "Means for distributing proposed content" refers to functions for delivering generated proposed content to customers, using methods such as email or video conferencing.

[0355] "A means of recognizing user emotions in real time and dynamically adjusting suggested content" refers to a function that uses an emotion engine to analyze the user's emotional state in real time and change the suggested content accordingly.

[0356] This invention relates to a system for dynamically generating and delivering proposal content for corporate clients. Its primary objective is to maximize effectiveness by utilizing AI technology and emotion recognition technology to adjust proposal content according to the client's emotions.

[0357] The system's core is the server, where information is collected, analyzed, models are trained, and content is generated and distributed. Information collection includes functions to retrieve data from internal databases, external APIs, and internet resources. The information is diverse, encompassing customer inquiry history, industry trends, and related product information. Analysis involves data processing and cleansing using Python.

[0358] Next, the server uses AI frameworks such as TensorFlow and PyTorch to train generative models with the collected data. This creates models capable of predicting and generating personalized recommendations for each customer.

[0359] This trained generative AI model is used to generate suggested content. Based on user instructions and prompts, it constructs content and automatically creates presentation materials. Slide creation tools such as PowerPoint and Google Slides are also utilized in this process.

[0360] During the proposal delivery phase, the device sends the final content to the customer via email or direct presentation. This is where the emotion recognition engine plays a crucial role. It analyzes the user's emotions in real time and makes necessary adjustments during the presentation to capture the customer's interest and attention. Furthermore, optimizations such as enhancing visual content are performed as needed.

[0361] A concrete example would be a scenario where a sales representative, acting as a user, inputs information into a server and creates proposal content according to the instructions of a generative model in order to propose new security software. An example of a prompt might be, "Create a proposal for new security software for a specific company. This company has a strong interest in data security."

[0362] This will further strengthen communication between companies and customers, making it possible to significantly improve sales results.

[0363] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0364] Step 1:

[0365] The server collects data from internal and external sources. This input includes customer inquiry history, purchase history, and industry trend information. The server cleanses, removes duplicates, and standardizes the format of this data before storing it in an internal database. This process results in customer information data organized in a format suitable for analysis.

[0366] Step 2:

[0367] The server trains an AI model using the collected data. Cleansed customer data is used as input. The server uses frameworks such as TensorFlow and PyTorch to label past inquiry history and train the model to optimize it. The output is a generative AI model with improved prediction accuracy.

[0368] Step 3:

[0369] The user inputs customer information through the server interface and instructs the server to create suggestions. This input includes customer name, location, industry, product categories of interest, and past behavioral patterns. Based on this input, the server generates prompts. These prompts function as instructions for the AI ​​model, serving as guidelines for content generation.

[0370] Step 4:

[0371] The server uses the generated prompts and trained AI model to create suggested content. This process generates the necessary graphs, charts, and text information based on user input, constructing presentation materials. The output is a customized suggested document or presentation slides.

[0372] Step 5:

[0373] The server uses an emotion engine to recognize the user's emotions in real time. Input includes voice tone and facial expression data from the presentation. The server analyzes this data to determine the user's current emotional state. The output is a dynamic content adjustment action based on this analysis. If necessary, the suggestions are improved in real time to optimize user engagement.

[0374] Step 6:

[0375] The terminal delivers the final proposal content. The input is optimized proposal materials provided by the server. The terminal uses this to send emails to customers or to use the materials in direct business negotiations. The output is the presentation materials or proposal delivered to the customer, which are used for actual communication.

[0376] (Application Example 2)

[0377] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0378] In modern sales activities, understanding customer emotions in real time and proposing products and services accordingly is a challenging task. Traditional systems tend to rely heavily on analysis based on static customer data, failing to utilize customer emotional states. As a result, it was difficult to communicate with customers more effectively and maximize sales opportunities.

[0379] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0380] In this invention, the server includes means for collecting information, means for analyzing the collected information, means for training a generative model based on the analysis results, means for generating suggested content using the generative model, means for distributing the suggested content, means for analyzing emotional states, means for dynamically customizing the suggested content based on the analyzed emotional states, means for recognizing facial features, and means for processing audio data. This enables real-time recognition of customer emotions and the generation and distribution of appropriate suggested content accordingly.

[0381] "Means of collecting information" refers to functions for gathering customer data, market information, and so on.

[0382] "Means of analysis" refer to functions for processing collected information and identifying patterns and trends.

[0383] "Means for training generative models" refers to functions that use past data and analysis results to train AI models.

[0384] "Methods for generating suggested content using generative models" refers to a function that utilizes a trained AI model to create suggested content tailored to the user.

[0385] "Means for distributing proposed content" refers to functions for sending or presenting generated proposed content to users or customers.

[0386] "Means of analyzing emotional state" refers to a function that reads emotions from a customer's facial expressions and voice, and evaluates their current emotional state.

[0387] The "dynamic customization method" refers to a function that instantly optimizes suggested content based on sentiment data obtained in real time.

[0388] "Means of recognizing facial features" refers to a function that analyzes image data acquired through a camera to identify facial expressions and characteristics.

[0389] "Means for processing audio data" refers to a function that analyzes audio acquired through a microphone and extracts linguistic content and emotions.

[0390] This invention is a system for streamlining customer service in physical stores. Its main components consist of a server that processes information, terminals used by sales staff, and users who input data.

[0391] The server aggregates customer information and trains an AI model based on the collected data. Data collection is performed using two methods: image acquisition via camera and audio acquisition via microphone. The server uses OpenCV for facial recognition on the image data and Google Cloud Speech-to-Text for processing the audio data. This allows for real-time analysis of the customer's emotional state, and based on this analysis, a generative AI model (e.g., Hugging Face Transformer) is used to generate personalized suggestion content.

[0392] The device provides salespeople with generated suggestion content, supporting real-time customer service. The suggestion content is dynamically customized based on the customer's emotional state, improving sales efficiency.

[0393] Users interact with customers while operating their devices. By providing content that captures customers' interests and concerns, improved customer satisfaction can be expected.

[0394] As a concrete example, consider a scenario where a customer is browsing for items in a clothing store on a holiday. The salesperson uses a terminal to assist the customer, and the system suggests appropriate products and styling options. At this time, the system analyzes the customer's responses in real time and instantly optimizes the suggestions.

[0395] The generative AI model enables effective suggestions by using prompts such as, "When a customer shows excitement, generate the optimal combination of products to suggest based on the product categories and related information they are interested in."

[0396] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0397] Step 1:

[0398] The server receives image and audio data transmitted from the smartphone's camera and microphone. The input consists of images showing the customer's facial expressions and audio of their conversation. This data is necessary as preprocessing for sentiment analysis.

[0399] Step 2:

[0400] The server uses the OpenCV library to recognize the facial features of the customer from the received image data and analyze their facial expressions. The input is facial image data, and the output is data indicating the customer's emotional state. This analysis quantitatively evaluates what emotions the customer is currently experiencing.

[0401] Step 3:

[0402] The server uses Google Cloud Speech-to-Text to convert audio data into text and analyzes the conversation content and customer tone from that text. The input is the customer's audio data, and the output is the emotional state derived from the customer's utterances and tone. This process allows for an understanding of the customer's interests and concerns.

[0403] Step 4:

[0404] The server integrates emotional state data obtained from facial expressions and voice, creating a dataset to input into the generative AI model. This prepares it to make suggestions that reflect emotions in real time.

[0405] Step 5:

[0406] The server uses generative AI models such as Hugging Face Transformer to generate optimal suggestion content based on prompt text. The input is integrated sentiment data and prompt text, and the output is dynamically customized suggestion content. This enables the suggestion of the most suitable products and services tailored to the customer's interests.

[0407] Step 6:

[0408] The terminal receives suggestion content sent from the server and displays it to the salesperson. The input is the suggestion content generated by the server, and the output is the selection displayed on the screen. This allows the salesperson to provide suggestions tailored to the customer's needs in real time.

[0409] Step 7:

[0410] Users operate the terminal to make proposals to customers and observe their reactions. Salespeople can use the information provided by the system to conduct sales while communicating appropriately.

[0411] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0412] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0413] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0414] [Third Embodiment]

[0415] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0416] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0417] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0418] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0419] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0420] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0421] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0422] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0423] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0424] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0425] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0426] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0427] This invention is a system for efficiently generating and distributing proposal content for corporate clients, and mainly includes a process of collecting and analyzing information and automatically generating customized proposal content using a generation model.

[0428] Program Processing Description

[0429] The server automatically collects sales activity information, product information, industry news, customer information, and other data from internal databases and external sources at pre-configured frequencies. This ensures that the latest information is always available.

[0430] The server integrates this collected data and performs AI-powered analysis. This analysis identifies customer trends and potential needs, and predicts overall industry trends.

[0431] Users (sales representatives) input specific customer names and solution categories into the system. This allows for proposals tailored to specific needs.

[0432] The server uses a generative model based on the input information and analysis results to generate a customized video proposal for the customer. This proposal includes product introductions and simulations that are likely to interest the customer.

[0433] The device sends the generated video proposal to the customer's email address. The email includes a summary of the proposal and is formatted so that the customer can play the proposal video on any device.

[0434] Specific example

[0435] When targeting a medium-sized enterprise, if the user provides instructions to propose a security solution, the server selects recommended products based on the company's past inquiry history and industry cybersecurity trends, and generates a video proposal. This video includes actual demonstration scenes and case studies to enhance its visual appeal. When the terminal sends this proposal video, it can generate an effective email template for the initial proposal, strengthening the impression made on the customer.

[0436] This system configuration enables more efficient sales activities and improved proposal accuracy, making meaningful business negotiations possible for both sales representatives and customers.

[0437] The following describes the processing flow.

[0438] Step 1:

[0439] The server collects information from internal databases and multiple external sources according to a set schedule. The collected information includes sales activity data, product information, and industry news. The collected information is stored in the database, where duplicates are removed and the formatting is standardized.

[0440] Step 2:

[0441] The server uses an AI analysis engine to analyze the collected information. This analysis includes predicting customer trends, identifying industry trends, and determining customer needs. The analysis results are saved as reference data for subsequent proposal generation processes.

[0442] Step 3:

[0443] The user logs into the system and enters a specific customer name and the area of ​​solution they wish to propose. The more specific these instructions are, the more accurate the customized proposal will be.

[0444] Step 4:

[0445] The server combines the information entered by the user with the analysis results from step 2 and creates suggested content using a generative model. Here, it automatically generates product introductions, use cases, and simulation videos tailored to customer characteristics.

[0446] Step 5:

[0447] The device encodes the generated suggestion content in the optimal format and sends it to the customer's email address. During sending, an email template encouraging video viewing is automatically generated and inserted.

[0448] Step 6:

[0449] Users utilize the submitted video proposals during business negotiations to explain the details of the proposal to customers. They play the videos through their devices, enhancing the visual approach in their presentations.

[0450] (Example 1)

[0451] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0452] There is a need to provide a means to efficiently and effectively generate and distribute proposal content for corporate clients. Traditional proposal processes often involve manual information gathering and analysis, which is time-consuming, and there is a desire for improved accuracy and speed in customizing and distributing proposal content.

[0453] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0454] In this invention, the server includes means for collecting information, means for integrating and analyzing the collected information, means for identifying trends and potential demands of others and predicting industry-wide trends, means for generating proposals using a generation AI model based on the analysis results and input information, and means for distributing the proposals. This enables the rapid generation and highly accurate customization of proposal content for corporate customers.

[0455] "Means of collecting information" refers to technologies for automatically retrieving relevant information from databases and external information sources.

[0456] "Means for integrating and analyzing collected information" refers to techniques for centralizing and formatting acquired data, and then extracting and evaluating information relevant to a specific purpose.

[0457] "A means of identifying trends and potential demands and predicting industry-wide developments" refers to a process of interpreting customer behavior patterns and market changes from data to foresee future needs.

[0458] "Methods for generating proposal content using generative AI models" refers to technologies that use generative models to construct concrete proposal documents based on information and analysis results.

[0459] "Means for distributing proposal content" refers to communication methods and systems for delivering generated proposal content to target recipients.

[0460] This invention is a system for efficiently generating and distributing proposal content for corporate clients. The details of the embodiment of this invention are described below.

[0461] First, the server periodically collects data from various sources. These sources include database systems and news websites, utilizing common commercial database software and web APIs. Specific examples include collecting sales activity information and product data from internal databases, and industry news from external sources.

[0462] Next, the server performs operations to integrate and analyze this collected data. For this purpose, it uses analytical tools such as Amazon Web Services (AWS) SageMaker and Google's AI platform. This makes it possible to identify customer trends and potential needs and predict industry trends.

[0463] Users input information into the system by specifying a particular customer and the category of solution they will offer to that customer. This input is done through an interface such as Salesforce.

[0464] Based on this information, the server uses a generative AI model to create customized suggestion content. For example, it uses an OpenAI generative model to generate personalized suggestions for each customer, which may include product introductions and simulation videos.

[0465] Finally, the device delivers the generated proposal content to the recipient. This delivery uses a common email service (e.g., Outlook, Gmail). The email includes a summary of the proposal and a link to play a video, which the customer can use to view the content.

[0466] As a concrete example, when proposing a security solution to a medium-sized company, the user instructs the system to do so. The server then generates a video based on the company's historical data and cybersecurity trends, and the terminal distributes that video. This process improves the accuracy of the proposal and the efficiency of sales activities.

[0467] An example of a prompt message is: "Generate a security solution proposal for a specific customer. Consider past inquiry history and industry trends, and include a visually impactful demo."

[0468] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0469] Step 1:

[0470] The server collects the necessary data from various information sources. First, it has access to internal databases and external information sources, and periodically performs processes to collect sales activity information, product information, industry news, etc. The input is raw data obtained from databases and APIs. The output is a structured dataset. At this stage, for example, database queries are executed and API calls are made.

[0471] Step 2:

[0472] The server integrates and analyzes the collected data. The input here is the raw data collected in Step 1. Specifically, it performs data cleaning, formatting standardization, and data normalization, and then prepares the input data for application to the analytical model. The output is an analyzable dataset. This dataset is used on the AI ​​platform to derive potential customer needs and industry trends.

[0473] Step 3:

[0474] The user enters a specific customer name and the category of the proposed solution. The input includes customer information and the category of the proposed solution obtained from the user. The server formats this information appropriately for the AI ​​model. The output is formalized data to initiate the AI ​​model's proposal generation process.

[0475] Step 4:

[0476] The server generates suggested content using a generative AI model. This process generates suggested content based on the analysis results from step 2 and the user input from step 3. Specifically, the AI ​​model automatically creates proposal documents and video content using prompt text. Customized proposal documents and video files are generated as output.

[0477] Step 5:

[0478] The terminal distributes the generated proposal content to recipients. The input is the proposal content created in step 4. Specifically, it sends the proposal content to the recipient's email address using the email system. The output is an email in a format playable on various devices used by the customer, enabling rapid information dissemination.

[0479] (Application Example 1)

[0480] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0481] While there is a need to efficiently generate and deliver proposal content optimized for the individual needs of corporate clients, conventional systems have the challenge of limited effectiveness because they do not adequately customize to the industry characteristics and interests of clients.

[0482] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0483] In this invention, the server includes means for collecting information, means for analyzing the collected information, means for training a generative model based on the analysis results, means for generating suggested content using the generative model, means for transmitting the generated suggested content using communication means, and means for proposing electronic trading solutions tailored to the customer's industry and interests. This makes it possible to effectively generate and deliver optimized suggestions for each customer.

[0484] "Means of collecting information" refers to the function of obtaining customer information and industry data through internal and external databases and APIs.

[0485] "Means of analyzing information" refers to the function of analyzing collected data using AI algorithms to identify customer needs and industry trends.

[0486] "Methods for training generative models" refer to functions that enable highly accurate predictions and suggestions by training generative AI models based on analysis results.

[0487] "Methods for generating proposal content using generative models" refers to a function that utilizes a trained generative AI model to create proposal materials tailored to individual customer needs.

[0488] "Means of transmission using communication means" refers to the function of distributing generated proposal content to customers via email or messaging services over the internet.

[0489] "Means of proposing electronic transaction solutions" refers to the function of building and proposing appropriate e-commerce solutions based on the customer's industry and areas of interest.

[0490] The system implementing this invention is for efficiently generating and distributing proposal content for corporate clients. The system mainly consists of a server, terminals, and users.

[0491] The server automatically collects information via a database or API. Specifically, it utilizes high-performance server equipment as hardware and executes data collection scripts using programming languages ​​such as Python as software. The collected information is diverse, including customer information, industry trends, and past inquiry history.

[0492] Next, the server analyzes the information using AI algorithms. It trains AI models using machine learning libraries such as TensorFlow and Scikit-learn. This process makes it possible to understand individual customer needs and industry trends.

[0493] Based on the generated analysis data, the server utilizes a generative AI model to create suggested content. Using advanced natural language processing technologies such as OpenAI's GPT model, it provides customized suggestions tailored to customer needs. This suggested content can take the form of a combination of text, images, and videos.

[0494] Meanwhile, the terminal transmits this proposed content to the customer using communication methods. Specifically, it utilizes communication methods such as email and instant messaging applications to deliver the generated content as a video link. This allows the customer to view the proposed content on any device.

[0495] Finally, users utilize the suggested content provided by this system to conduct sales activities. Users can input specific customer names and solution categories into the server and instantly generate and send customized proposals.

[0496] As a concrete example, when proposing a multi-currency electronic transaction solution to an office supplies company, it is possible to generate videos that showcase the most effective products and services based on the customer's characteristics and market trends. Examples of prompts to support this workflow include the following:

[0497] Example of a prompt:

[0498] Proposal for electronic transaction solutions for corporate clients:

[0499] Customer industry: Office supplies

[0500] Features of interest: Multi-currency support, advanced security features

[0501] Past inquiries: Payment integration via API

[0502] Based on this, please generate a customized proposal.

[0503] This system configuration enables more efficient sales activities and more accurate proposals.

[0504] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0505] Step 1:

[0506] The server automatically collects data such as customer information, industry trends, and past inquiry history using internal databases and external APIs. The input for this data collection is API requests and database queries, and the output is a set of retrieved raw data. A Python script is used to run this process periodically.

[0507] Step 2:

[0508] The server analyzes the collected data. The input is raw data, and AI algorithms are used to analyze it. Specifically, Scikit-learn and TensorFlow are used to perform clustering and classification in order to identify trends and patterns hidden in the data. The output is the analysis results regarding customer purchasing trends and industry trends.

[0509] Step 3:

[0510] The server trains the generative AI model. It uses the analysis results obtained in step 2 as input and updates the model using a framework such as TensorFlow. This training process allows the model to make more accurate predictions. The output is a customer-specific suggestion content generation model.

[0511] Step 4:

[0512] The server generates suggestion content using an updated generative AI model. The input consists of customer information and solution categories specified by the user, and the generative model creates customized suggestion content based on this information. The output is suggestion content in visually appealing formats such as videos and slides.

[0513] Step 5:

[0514] The device sends the generated proposal content to the customer. The input consists of the generated proposal content and the customer's contact information. This information is used to deliver the proposal via email or instant messaging apps. The output is content in the form of links or files that the customer can access on any device.

[0515] Step 6:

[0516] Users utilize suggested content from the server to support their sales activities. The input is customized suggestions provided by the server, and the output is used for preparing sales negotiations and presentations to customers.

[0517] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0518] The present invention aims to achieve greater appeal and effectiveness in a system for generating and distributing proposal content for corporate clients by using an emotion engine to recognize the user's emotions in real time and dynamically customizing the proposal content based on those emotions.

[0519] Program Processing Description

[0520] The server first collects information from both internal and external sources and stores it in a database. This information includes past customer inquiry history, industry trend information, and product information. The information is regularly updated and formatted to be suitable for analysis.

[0521] The server analyzes the collected data and trains an AI model. This model learns which customers the proposed products and solutions are suitable for.

[0522] The user inputs the target customer's information and instructs the server to generate suggestions. This input includes the customer's name, product categories of interest, and past behavioral patterns.

[0523] The server uses a generative model to create suggested content based on user input and analysis results.

[0524] The server is connected to an emotion engine that recognizes user emotions, analyzing the user's voice and facial expressions in real time during online calls and presentations. This allows the content and presentation of the proposal to be modified according to the emotions the user displays during the proposal.

[0525] The device delivers the final generated suggestion content to customers via email or direct interaction. During delivery, the video is optimized based on sentiment analysis.

[0526] Specific example

[0527] Let's consider a scenario where a sales representative proposes new security software to Company A. The user (sales representative) inputs basic information about Company A and the purpose of the proposal into the server and activates the emotion engine. During the presentation, the server's emotion engine detects emotions from the sales representative's tone of voice and facial expressions. If the other party shows excitement or interest, the system automatically makes changes such as deepening the proposal content and adding a visual demo video. Through this process, customer interest and satisfaction can be increased.

[0528] This system will improve the quality of communication with customers and enhance the results of sales activities.

[0529] The following describes the processing flow.

[0530] Step 1:

[0531] The server automatically collects information from internal databases and external sources. This information includes past customer inquiry data, current market trends, and technical specifications for new products, and is stored in the database. The collected information is formatted and analyzed to a standardized format.

[0532] Step 2:

[0533] The server analyzes the accumulated data and trains a generative model. Using AI algorithms, it learns potential product and service suggestions that meet customer needs. The trained model is then used in the process of creating suggestion content.

[0534] Step 3:

[0535] The user enters information about the target customer into a format. This includes providing the customer's name, product categories of interest, and past transaction history, which helps establish the criteria for customized proposals.

[0536] Step 4:

[0537] The server combines user input with data learned by an AI model to generate suggested content. This content is designed in video format and may include presentation materials or demo videos.

[0538] Step 5:

[0539] During the proposal process, an emotion engine installed on the server activates, monitoring the user's voice and facial expressions in real time. The emotion engine analyzes the customer's reactions and evaluates their level of interest, dynamically adjusting the proposal accordingly.

[0540] Step 6:

[0541] The device delivers the generated proposal content to the customer. The proposal video is not only sent via email, but is also used as a presentation tool during face-to-face business meetings, providing optimal information based on the customer's emotional feedback.

[0542] (Example 2)

[0543] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0544] When generating proposal content for corporate clients, there is a challenge in effectively considering customer emotions to achieve higher appeal and conversion rates. Traditional systems are limited to generating static content that ignores emotions, and have failed to maximize customer interest and engagement.

[0545] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0546] In this invention, the server includes means for collecting information, means for analyzing the collected information, means for training a generative model based on the analysis results, means for generating suggested content using the generative model, means for distributing the suggested content, and means for recognizing the user's emotions in real time and dynamically adjusting the suggested content. This enables the generation and distribution of dynamic and effective suggested content that responds to changes in the customer's emotions.

[0547] "Means of collecting information" refers to a system for acquiring and accumulating data from internal and external information sources.

[0548] "Means of analysis" refers to the process of processing collected data to derive useful insights.

[0549] "Means for training generative models" refer to functions that use collected data to train AI models and improve their ability to recognize specific patterns and trends.

[0550] "Methods for generating suggestion content using generative models" refer to a system that utilizes a trained AI model to automatically create optimal suggestions for customers.

[0551] "Means for distributing proposed content" refers to functions for delivering generated proposed content to customers, using methods such as email or video conferencing.

[0552] "A means of recognizing user emotions in real time and dynamically adjusting suggested content" refers to a function that uses an emotion engine to analyze the user's emotional state in real time and change the suggested content accordingly.

[0553] This invention relates to a system for dynamically generating and delivering proposal content for corporate clients. Its primary objective is to maximize effectiveness by utilizing AI technology and emotion recognition technology to adjust proposal content according to the client's emotions.

[0554] The system's core is the server, where information is collected, analyzed, models are trained, and content is generated and distributed. Information collection includes functions to retrieve data from internal databases, external APIs, and internet resources. The information is diverse, encompassing customer inquiry history, industry trends, and related product information. Analysis involves data processing and cleansing using Python.

[0555] Next, the server uses AI frameworks such as TensorFlow and PyTorch to train generative models with the collected data. This creates models capable of predicting and generating personalized recommendations for each customer.

[0556] This trained generative AI model is used to generate suggested content. Based on user instructions and prompts, it constructs content and automatically creates presentation materials. Slide creation tools such as PowerPoint and Google Slides are also utilized in this process.

[0557] During the proposal delivery phase, the device sends the final content to the customer via email or direct presentation. This is where the emotion recognition engine plays a crucial role. It analyzes the user's emotions in real time and makes necessary adjustments during the presentation to capture the customer's interest and attention. Furthermore, optimizations such as enhancing visual content are performed as needed.

[0558] A concrete example would be a scenario where a sales representative, acting as a user, inputs information into a server and creates proposal content according to the instructions of a generative model in order to propose new security software. An example of a prompt might be, "Create a proposal for new security software for a specific company. This company has a strong interest in data security."

[0559] This will further strengthen communication between companies and customers, making it possible to significantly improve sales results.

[0560] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0561] Step 1:

[0562] The server collects data from internal and external sources. This input includes customer inquiry history, purchase history, and industry trend information. The server cleanses, removes duplicates, and standardizes the format of this data before storing it in an internal database. This process results in customer information data organized in a format suitable for analysis.

[0563] Step 2:

[0564] The server trains an AI model using the collected data. Cleansed customer data is used as input. The server uses frameworks such as TensorFlow and PyTorch to label past inquiry history and train the model to optimize it. The output is a generative AI model with improved prediction accuracy.

[0565] Step 3:

[0566] The user inputs customer information through the server interface and instructs the server to create suggestions. This input includes customer name, location, industry, product categories of interest, and past behavioral patterns. Based on this input, the server generates prompts. These prompts function as instructions for the AI ​​model, serving as guidelines for content generation.

[0567] Step 4:

[0568] The server uses the generated prompts and trained AI model to create suggested content. This process generates the necessary graphs, charts, and text information based on user input, constructing presentation materials. The output is a customized suggested document or presentation slides.

[0569] Step 5:

[0570] The server uses an emotion engine to recognize the user's emotions in real time. Input includes voice tone and facial expression data from the presentation. The server analyzes this data to determine the user's current emotional state. The output is a dynamic content adjustment action based on this analysis. If necessary, the suggestions are improved in real time to optimize user engagement.

[0571] Step 6:

[0572] The terminal delivers the final proposal content. The input is optimized proposal materials provided by the server. The terminal uses this to send emails to customers or to use the materials in direct business negotiations. The output is the presentation materials or proposal delivered to the customer, which are used for actual communication.

[0573] (Application Example 2)

[0574] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0575] In modern sales activities, understanding customer emotions in real time and proposing products and services accordingly is a challenging task. Traditional systems tend to rely heavily on analysis based on static customer data, failing to utilize customer emotional states. As a result, it was difficult to communicate with customers more effectively and maximize sales opportunities.

[0576] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0577] In this invention, the server includes means for collecting information, means for analyzing the collected information, means for training a generative model based on the analysis results, means for generating suggested content using the generative model, means for distributing the suggested content, means for analyzing emotional states, means for dynamically customizing the suggested content based on the analyzed emotional states, means for recognizing facial features, and means for processing audio data. This enables real-time recognition of customer emotions and the generation and distribution of appropriate suggested content accordingly.

[0578] "Means of collecting information" refers to functions for gathering customer data, market information, and so on.

[0579] "Means of analysis" refer to functions for processing collected information and identifying patterns and trends.

[0580] "Means for training generative models" refers to functions that use past data and analysis results to train AI models.

[0581] "Methods for generating suggested content using generative models" refers to a function that utilizes a trained AI model to create suggested content tailored to the user.

[0582] "Means for distributing proposed content" refers to functions for sending or presenting generated proposed content to users or customers.

[0583] "Means of analyzing emotional state" refers to a function that reads emotions from a customer's facial expressions and voice, and evaluates their current emotional state.

[0584] The "dynamic customization method" refers to a function that instantly optimizes suggested content based on sentiment data obtained in real time.

[0585] "Means of recognizing facial features" refers to a function that analyzes image data acquired through a camera to identify facial expressions and characteristics.

[0586] "Means for processing audio data" refers to a function that analyzes audio acquired through a microphone and extracts linguistic content and emotions.

[0587] This invention is a system for streamlining customer service in physical stores. Its main components consist of a server that processes information, terminals used by sales staff, and users who input data.

[0588] The server aggregates customer information and trains an AI model based on the collected data. Data collection is performed using two methods: image acquisition via camera and audio acquisition via microphone. The server uses OpenCV for facial recognition on the image data and Google Cloud Speech-to-Text for processing the audio data. This allows for real-time analysis of the customer's emotional state, and based on this analysis, a generative AI model (e.g., Hugging Face Transformer) is used to generate personalized suggestion content.

[0589] The device provides salespeople with generated suggestion content, supporting real-time customer service. The suggestion content is dynamically customized based on the customer's emotional state, improving sales efficiency.

[0590] Users interact with customers while operating their devices. By providing content that captures customers' interests and concerns, improved customer satisfaction can be expected.

[0591] As a concrete example, consider a scenario where a customer is browsing for items in a clothing store on a holiday. The salesperson uses a terminal to assist the customer, and the system suggests appropriate products and styling options. At this time, the system analyzes the customer's responses in real time and instantly optimizes the suggestions.

[0592] The generative AI model enables effective suggestions by using prompts such as, "When a customer shows excitement, generate the optimal combination of products to suggest based on the product categories and related information they are interested in."

[0593] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0594] Step 1:

[0595] The server receives image and audio data transmitted from the smartphone's camera and microphone. The input consists of images showing the customer's facial expressions and audio of their conversation. This data is necessary as preprocessing for sentiment analysis.

[0596] Step 2:

[0597] The server uses the OpenCV library to recognize the facial features of the customer from the received image data and analyze their facial expressions. The input is facial image data, and the output is data indicating the customer's emotional state. This analysis quantitatively evaluates what emotions the customer is currently experiencing.

[0598] Step 3:

[0599] The server uses Google Cloud Speech-to-Text to convert audio data into text and analyzes the conversation content and customer tone from that text. The input is the customer's audio data, and the output is the emotional state derived from the customer's utterances and tone. This process allows for an understanding of the customer's interests and concerns.

[0600] Step 4:

[0601] The server integrates emotional state data obtained from facial expressions and voice, creating a dataset to input into the generative AI model. This prepares it to make suggestions that reflect emotions in real time.

[0602] Step 5:

[0603] The server uses generative AI models such as Hugging Face Transformer to generate optimal suggestion content based on prompt text. The input is integrated sentiment data and prompt text, and the output is dynamically customized suggestion content. This enables the suggestion of the most suitable products and services tailored to the customer's interests.

[0604] Step 6:

[0605] The terminal receives suggestion content sent from the server and displays it to the salesperson. The input is the suggestion content generated by the server, and the output is the selection displayed on the screen. This allows the salesperson to provide suggestions tailored to the customer's needs in real time.

[0606] Step 7:

[0607] Users operate the terminal to make proposals to customers and observe their reactions. Salespeople can use the information provided by the system to conduct sales while communicating appropriately.

[0608] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0609] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0610] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0611] [Fourth Embodiment]

[0612] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0613] As shown in Figure 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.

[0614] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0615] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0616] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0617] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0618] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0619] The controlled 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0620] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0621] The specific processing program 56 is an example of a "program" relating to the technology of this 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 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.

[0622] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0623] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0624] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0625] This invention is a system for efficiently generating and distributing proposal content for corporate clients, and mainly includes a process of collecting and analyzing information and automatically generating customized proposal content using a generation model.

[0626] Program Processing Description

[0627] The server automatically collects sales activity information, product information, industry news, customer information, and other data from internal databases and external sources at pre-configured frequencies. This ensures that the latest information is always available.

[0628] The server integrates this collected data and performs AI-powered analysis. This analysis identifies customer trends and potential needs, and predicts overall industry trends.

[0629] Users (sales representatives) input specific customer names and solution categories into the system. This allows for proposals tailored to specific needs.

[0630] The server uses a generative model based on the input information and analysis results to generate a customized video proposal for the customer. This proposal includes product introductions and simulations that are likely to interest the customer.

[0631] The device sends the generated video proposal to the customer's email address. The email includes a summary of the proposal and is formatted so that the customer can play the proposal video on any device.

[0632] Specific example

[0633] When targeting a medium-sized enterprise, if the user provides instructions to propose a security solution, the server selects recommended products based on the company's past inquiry history and industry cybersecurity trends, and generates a video proposal. This video includes actual demonstration scenes and case studies to enhance its visual appeal. When the terminal sends this proposal video, it can generate an effective email template for the initial proposal, strengthening the impression made on the customer.

[0634] This system configuration enables more efficient sales activities and improved proposal accuracy, making meaningful business negotiations possible for both sales representatives and customers.

[0635] The following describes the processing flow.

[0636] Step 1:

[0637] The server collects information from internal databases and multiple external sources according to a set schedule. The collected information includes sales activity data, product information, and industry news. The collected information is stored in the database, where duplicates are removed and the formatting is standardized.

[0638] Step 2:

[0639] The server uses an AI analysis engine to analyze the collected information. This analysis includes predicting customer trends, identifying industry trends, and determining customer needs. The analysis results are saved as reference data for subsequent proposal generation processes.

[0640] Step 3:

[0641] The user logs into the system and enters a specific customer name and the area of ​​solution they wish to propose. The more specific these instructions are, the more accurate the customized proposal will be.

[0642] Step 4:

[0643] The server combines the information entered by the user with the analysis results from step 2 and creates suggested content using a generative model. Here, it automatically generates product introductions, use cases, and simulation videos tailored to customer characteristics.

[0644] Step 5:

[0645] The device encodes the generated suggestion content in the optimal format and sends it to the customer's email address. During sending, an email template encouraging video viewing is automatically generated and inserted.

[0646] Step 6:

[0647] Users utilize the submitted video proposals during business negotiations to explain the details of the proposal to customers. They play the videos through their devices, enhancing the visual approach in their presentations.

[0648] (Example 1)

[0649] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0650] There is a need to provide a means to efficiently and effectively generate and distribute proposal content for corporate clients. Traditional proposal processes often involve manual information gathering and analysis, which is time-consuming, and there is a desire for improved accuracy and speed in customizing and distributing proposal content.

[0651] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0652] In this invention, the server includes means for collecting information, means for integrating and analyzing the collected information, means for identifying trends and potential demands of others and predicting industry-wide trends, means for generating proposals using a generation AI model based on the analysis results and input information, and means for distributing the proposals. This enables the rapid generation and highly accurate customization of proposal content for corporate customers.

[0653] "Means of collecting information" refers to technologies for automatically retrieving relevant information from databases and external information sources.

[0654] "Means for integrating and analyzing collected information" refers to techniques for centralizing and formatting acquired data, and then extracting and evaluating information relevant to a specific purpose.

[0655] "A means of identifying trends and potential demands and predicting industry-wide developments" refers to a process of interpreting customer behavior patterns and market changes from data to foresee future needs.

[0656] "Methods for generating proposal content using generative AI models" refers to technologies that use generative models to construct concrete proposal documents based on information and analysis results.

[0657] "Means for distributing proposal content" refers to communication methods and systems for delivering generated proposal content to target recipients.

[0658] This invention is a system for efficiently generating and distributing proposal content for corporate clients. The details of the embodiment of this invention are described below.

[0659] First, the server periodically collects data from various sources. These sources include database systems and news websites, utilizing common commercial database software and web APIs. Specific examples include collecting sales activity information and product data from internal databases, and industry news from external sources.

[0660] Next, the server performs operations to integrate and analyze this collected data. For this purpose, it uses analytical tools such as Amazon Web Services (AWS) SageMaker and Google's AI platform. This makes it possible to identify customer trends and potential needs and predict industry trends.

[0661] Users input information into the system by specifying a particular customer and the category of solution they will offer to that customer. This input is done through an interface such as Salesforce.

[0662] Based on this information, the server uses a generative AI model to create customized suggestion content. For example, it uses an OpenAI generative model to generate personalized suggestions for each customer, which may include product introductions and simulation videos.

[0663] Finally, the device delivers the generated proposal content to the recipient. This delivery uses a common email service (e.g., Outlook, Gmail). The email includes a summary of the proposal and a link to play a video, which the customer can use to view the content.

[0664] As a concrete example, when proposing a security solution to a medium-sized company, the user instructs the system to do so. The server then generates a video based on the company's historical data and cybersecurity trends, and the terminal distributes that video. This process improves the accuracy of the proposal and the efficiency of sales activities.

[0665] An example of a prompt message is: "Generate a security solution proposal for a specific customer. Consider past inquiry history and industry trends, and include a visually impactful demo."

[0666] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0667] Step 1:

[0668] The server collects the necessary data from various information sources. First, it has access to internal databases and external information sources, and periodically performs processes to collect sales activity information, product information, industry news, etc. The input is raw data obtained from databases and APIs. The output is a structured dataset. At this stage, for example, database queries are executed and API calls are made.

[0669] Step 2:

[0670] The server integrates and analyzes the collected data. The input here is the raw data collected in Step 1. Specifically, it performs data cleaning, formatting standardization, and data normalization, and then prepares the input data for application to the analytical model. The output is an analyzable dataset. This dataset is used on the AI ​​platform to derive potential customer needs and industry trends.

[0671] Step 3:

[0672] The user enters a specific customer name and the category of the proposed solution. The input includes customer information and the category of the proposed solution obtained from the user. The server formats this information appropriately for the AI ​​model. The output is formalized data to initiate the AI ​​model's proposal generation process.

[0673] Step 4:

[0674] The server generates suggested content using a generative AI model. This process generates suggested content based on the analysis results from step 2 and the user input from step 3. Specifically, the AI ​​model automatically creates proposal documents and video content using prompt text. Customized proposal documents and video files are generated as output.

[0675] Step 5:

[0676] The terminal distributes the generated proposal content to recipients. The input is the proposal content created in step 4. Specifically, it sends the proposal content to the recipient's email address using the email system. The output is an email in a format playable on various devices used by the customer, enabling rapid information dissemination.

[0677] (Application Example 1)

[0678] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0679] While there is a need to efficiently generate and deliver proposal content optimized for the individual needs of corporate clients, conventional systems have the challenge of limited effectiveness because they do not adequately customize to the industry characteristics and interests of clients.

[0680] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0681] In this invention, the server includes means for collecting information, means for analyzing the collected information, means for training a generative model based on the analysis results, means for generating suggested content using the generative model, means for transmitting the generated suggested content using communication means, and means for proposing electronic trading solutions tailored to the customer's industry and interests. This makes it possible to effectively generate and deliver optimized suggestions for each customer.

[0682] "Means of collecting information" refers to the function of obtaining customer information and industry data through internal and external databases and APIs.

[0683] "Means of analyzing information" refers to the function of analyzing collected data using AI algorithms to identify customer needs and industry trends.

[0684] "Methods for training generative models" refer to functions that enable highly accurate predictions and suggestions by training generative AI models based on analysis results.

[0685] "Methods for generating proposal content using generative models" refers to a function that utilizes a trained generative AI model to create proposal materials tailored to individual customer needs.

[0686] "Means of transmission using communication means" refers to the function of distributing generated proposal content to customers via email or messaging services over the internet.

[0687] "Means of proposing electronic transaction solutions" refers to the function of building and proposing appropriate e-commerce solutions based on the customer's industry and areas of interest.

[0688] The system implementing this invention is for efficiently generating and distributing proposal content for corporate clients. The system mainly consists of a server, terminals, and users.

[0689] The server automatically collects information via a database or API. Specifically, it utilizes high-performance server equipment as hardware and executes data collection scripts using programming languages ​​such as Python as software. The collected information is diverse, including customer information, industry trends, and past inquiry history.

[0690] Next, the server analyzes the information using AI algorithms. It trains AI models using machine learning libraries such as TensorFlow and Scikit-learn. This process makes it possible to understand individual customer needs and industry trends.

[0691] Based on the generated analysis data, the server utilizes a generative AI model to create suggested content. Using advanced natural language processing technologies such as OpenAI's GPT model, it provides customized suggestions tailored to customer needs. This suggested content can take the form of a combination of text, images, and videos.

[0692] Meanwhile, the terminal transmits this proposed content to the customer using communication methods. Specifically, it utilizes communication methods such as email and instant messaging applications to deliver the generated content as a video link. This allows the customer to view the proposed content on any device.

[0693] Finally, users utilize the suggested content provided by this system to conduct sales activities. Users can input specific customer names and solution categories into the server and instantly generate and send customized proposals.

[0694] As a concrete example, when proposing a multi-currency electronic transaction solution to an office supplies company, it is possible to generate videos that showcase the most effective products and services based on the customer's characteristics and market trends. Examples of prompts to support this workflow include the following:

[0695] Example of a prompt:

[0696] Proposal for electronic transaction solutions for corporate clients:

[0697] Customer industry: Office supplies

[0698] Features of interest: Multi-currency support, advanced security features

[0699] Past inquiries: Payment integration via API

[0700] Based on this, please generate a customized proposal.

[0701] This system configuration enables more efficient sales activities and more accurate proposals.

[0702] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0703] Step 1:

[0704] The server automatically collects data such as customer information, industry trends, and past inquiry history using internal databases and external APIs. The input for this data collection is API requests and database queries, and the output is a set of retrieved raw data. A Python script is used to run this process periodically.

[0705] Step 2:

[0706] The server analyzes the collected data. The input is raw data, and AI algorithms are used to analyze it. Specifically, Scikit-learn and TensorFlow are used to perform clustering and classification in order to identify trends and patterns hidden in the data. The output is the analysis results regarding customer purchasing trends and industry trends.

[0707] Step 3:

[0708] The server trains the generative AI model. It uses the analysis results obtained in step 2 as input and updates the model using a framework such as TensorFlow. This training process allows the model to make more accurate predictions. The output is a customer-specific suggestion content generation model.

[0709] Step 4:

[0710] The server generates suggestion content using an updated generative AI model. The input consists of customer information and solution categories specified by the user, and the generative model creates customized suggestion content based on this information. The output is suggestion content in visually appealing formats such as videos and slides.

[0711] Step 5:

[0712] The device sends the generated proposal content to the customer. The input consists of the generated proposal content and the customer's contact information. This information is used to deliver the proposal via email or instant messaging apps. The output is content in the form of links or files that the customer can access on any device.

[0713] Step 6:

[0714] Users utilize suggested content from the server to support their sales activities. The input is customized suggestions provided by the server, and the output is used for preparing sales negotiations and presentations to customers.

[0715] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0716] The present invention aims to achieve greater appeal and effectiveness in a system for generating and distributing proposal content for corporate clients by using an emotion engine to recognize the user's emotions in real time and dynamically customizing the proposal content based on those emotions.

[0717] Program Processing Description

[0718] The server first collects information from both internal and external sources and stores it in a database. This information includes past customer inquiry history, industry trend information, and product information. The information is regularly updated and formatted to be suitable for analysis.

[0719] The server analyzes the collected data and trains an AI model. This model learns which customers the proposed products and solutions are suitable for.

[0720] The user inputs the target customer's information and instructs the server to generate suggestions. This input includes the customer's name, product categories of interest, and past behavioral patterns.

[0721] The server uses a generative model to create suggested content based on user input and analysis results.

[0722] The server is connected to an emotion engine that recognizes user emotions, analyzing the user's voice and facial expressions in real time during online calls and presentations. This allows the content and presentation of the proposal to be modified according to the emotions the user displays during the proposal.

[0723] The device delivers the final generated suggestion content to customers via email or direct interaction. During delivery, the video is optimized based on sentiment analysis.

[0724] Specific example

[0725] Let's consider a scenario where a sales representative proposes new security software to Company A. The user (sales representative) inputs basic information about Company A and the purpose of the proposal into the server and activates the emotion engine. During the presentation, the server's emotion engine detects emotions from the sales representative's tone of voice and facial expressions. If the other party shows excitement or interest, the system automatically makes changes such as deepening the proposal content and adding a visual demo video. Through this process, customer interest and satisfaction can be increased.

[0726] This system will improve the quality of communication with customers and enhance the results of sales activities.

[0727] The following describes the processing flow.

[0728] Step 1:

[0729] The server automatically collects information from internal databases and external sources. This information includes past customer inquiry data, current market trends, and technical specifications for new products, and is stored in the database. The collected information is formatted and analyzed to a standardized format.

[0730] Step 2:

[0731] The server analyzes the accumulated data and trains a generative model. Using AI algorithms, it learns potential product and service suggestions that meet customer needs. The trained model is then used in the process of creating suggestion content.

[0732] Step 3:

[0733] The user enters information about the target customer into a format. This includes providing the customer's name, product categories of interest, and past transaction history, which helps establish the criteria for customized proposals.

[0734] Step 4:

[0735] The server combines user input with data learned by an AI model to generate suggested content. This content is designed in video format and may include presentation materials or demo videos.

[0736] Step 5:

[0737] During the proposal process, an emotion engine installed on the server activates, monitoring the user's voice and facial expressions in real time. The emotion engine analyzes the customer's reactions and evaluates their level of interest, dynamically adjusting the proposal accordingly.

[0738] Step 6:

[0739] The device delivers the generated proposal content to the customer. The proposal video is not only sent via email, but is also used as a presentation tool during face-to-face business meetings, providing optimal information based on the customer's emotional feedback.

[0740] (Example 2)

[0741] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0742] When generating proposal content for corporate clients, there is a challenge in effectively considering customer emotions to achieve higher appeal and conversion rates. Traditional systems are limited to generating static content that ignores emotions, and have failed to maximize customer interest and engagement.

[0743] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0744] In this invention, the server includes means for collecting information, means for analyzing the collected information, means for training a generative model based on the analysis results, means for generating suggested content using the generative model, means for distributing the suggested content, and means for recognizing the user's emotions in real time and dynamically adjusting the suggested content. This enables the generation and distribution of dynamic and effective suggested content that responds to changes in the customer's emotions.

[0745] "Means of collecting information" refers to a system for acquiring and accumulating data from internal and external information sources.

[0746] "Means of analysis" refers to the process of processing collected data to derive useful insights.

[0747] "Means for training generative models" refer to functions that use collected data to train AI models and improve their ability to recognize specific patterns and trends.

[0748] "Methods for generating suggestion content using generative models" refer to a system that utilizes a trained AI model to automatically create optimal suggestions for customers.

[0749] "Means for distributing proposed content" refers to functions for delivering generated proposed content to customers, using methods such as email or video conferencing.

[0750] "A means of recognizing user emotions in real time and dynamically adjusting suggested content" refers to a function that uses an emotion engine to analyze the user's emotional state in real time and change the suggested content accordingly.

[0751] This invention relates to a system for dynamically generating and delivering proposal content for corporate clients. Its primary objective is to maximize effectiveness by utilizing AI technology and emotion recognition technology to adjust proposal content according to the client's emotions.

[0752] The system's core is the server, where information is collected, analyzed, models are trained, and content is generated and distributed. Information collection includes functions to retrieve data from internal databases, external APIs, and internet resources. The information is diverse, encompassing customer inquiry history, industry trends, and related product information. Analysis involves data processing and cleansing using Python.

[0753] Next, the server uses AI frameworks such as TensorFlow and PyTorch to train generative models with the collected data. This creates models capable of predicting and generating personalized recommendations for each customer.

[0754] This trained generative AI model is used to generate suggested content. Based on user instructions and prompts, it constructs content and automatically creates presentation materials. Slide creation tools such as PowerPoint and Google Slides are also utilized in this process.

[0755] During the proposal delivery phase, the device sends the final content to the customer via email or direct presentation. This is where the emotion recognition engine plays a crucial role. It analyzes the user's emotions in real time and makes necessary adjustments during the presentation to capture the customer's interest and attention. Furthermore, optimizations such as enhancing visual content are performed as needed.

[0756] A concrete example would be a scenario where a sales representative, acting as a user, inputs information into a server and creates proposal content according to the instructions of a generative model in order to propose new security software. An example of a prompt might be, "Create a proposal for new security software for a specific company. This company has a strong interest in data security."

[0757] This will further strengthen communication between companies and customers, making it possible to significantly improve sales results.

[0758] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0759] Step 1:

[0760] The server collects data from internal and external sources. This input includes customer inquiry history, purchase history, and industry trend information. The server cleanses, removes duplicates, and standardizes the format of this data before storing it in an internal database. This process results in customer information data organized in a format suitable for analysis.

[0761] Step 2:

[0762] The server trains an AI model using the collected data. Cleansed customer data is used as input. The server uses frameworks such as TensorFlow and PyTorch to label past inquiry history and train the model to optimize it. The output is a generative AI model with improved prediction accuracy.

[0763] Step 3:

[0764] The user inputs customer information through the server interface and instructs the server to create suggestions. This input includes customer name, location, industry, product categories of interest, and past behavioral patterns. Based on this input, the server generates prompts. These prompts function as instructions for the AI ​​model, serving as guidelines for content generation.

[0765] Step 4:

[0766] The server uses the generated prompts and trained AI model to create suggested content. This process generates the necessary graphs, charts, and text information based on user input, constructing presentation materials. The output is a customized suggested document or presentation slides.

[0767] Step 5:

[0768] The server uses an emotion engine to recognize the user's emotions in real time. Input includes voice tone and facial expression data from the presentation. The server analyzes this data to determine the user's current emotional state. The output is a dynamic content adjustment action based on this analysis. If necessary, the suggestions are improved in real time to optimize user engagement.

[0769] Step 6:

[0770] The terminal delivers the final proposal content. The input is optimized proposal materials provided by the server. The terminal uses this to send emails to customers or to use the materials in direct business negotiations. The output is the presentation materials or proposal delivered to the customer, which are used for actual communication.

[0771] (Application Example 2)

[0772] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0773] In modern sales activities, understanding customer emotions in real time and proposing products and services accordingly is a challenging task. Traditional systems tend to rely heavily on analysis based on static customer data, failing to utilize customer emotional states. As a result, it was difficult to communicate with customers more effectively and maximize sales opportunities.

[0774] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0775] In this invention, the server includes means for collecting information, means for analyzing the collected information, means for training a generative model based on the analysis results, means for generating suggested content using the generative model, means for distributing the suggested content, means for analyzing emotional states, means for dynamically customizing the suggested content based on the analyzed emotional states, means for recognizing facial features, and means for processing audio data. This enables real-time recognition of customer emotions and the generation and distribution of appropriate suggested content accordingly.

[0776] "Means of collecting information" refers to functions for gathering customer data, market information, and so on.

[0777] "Means of analysis" refer to functions for processing collected information and identifying patterns and trends.

[0778] "Means for training generative models" refers to functions that use past data and analysis results to train AI models.

[0779] "Methods for generating suggested content using generative models" refers to a function that utilizes a trained AI model to create suggested content tailored to the user.

[0780] "Means for distributing proposed content" refers to functions for sending or presenting generated proposed content to users or customers.

[0781] "Means of analyzing emotional state" refers to a function that reads emotions from a customer's facial expressions and voice, and evaluates their current emotional state.

[0782] The "dynamic customization method" refers to a function that instantly optimizes suggested content based on sentiment data obtained in real time.

[0783] "Means of recognizing facial features" refers to a function that analyzes image data acquired through a camera to identify facial expressions and characteristics.

[0784] "Means for processing audio data" refers to a function that analyzes audio acquired through a microphone and extracts linguistic content and emotions.

[0785] This invention is a system for streamlining customer service in physical stores. Its main components consist of a server that processes information, terminals used by sales staff, and users who input data.

[0786] The server aggregates customer information and trains an AI model based on the collected data. Data collection is performed using two methods: image acquisition via camera and audio acquisition via microphone. The server uses OpenCV for facial recognition on the image data and Google Cloud Speech-to-Text for processing the audio data. This allows for real-time analysis of the customer's emotional state, and based on this analysis, a generative AI model (e.g., Hugging Face Transformer) is used to generate personalized suggestion content.

[0787] The device provides salespeople with generated suggestion content, supporting real-time customer service. The suggestion content is dynamically customized based on the customer's emotional state, improving sales efficiency.

[0788] Users interact with customers while operating their devices. By providing content that captures customers' interests and concerns, improved customer satisfaction can be expected.

[0789] As a concrete example, consider a scenario where a customer is browsing for items in a clothing store on a holiday. The salesperson uses a terminal to assist the customer, and the system suggests appropriate products and styling options. At this time, the system analyzes the customer's responses in real time and instantly optimizes the suggestions.

[0790] The generative AI model enables effective suggestions by using prompts such as, "When a customer shows excitement, generate the optimal combination of products to suggest based on the product categories and related information they are interested in."

[0791] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0792] Step 1:

[0793] The server receives image and audio data transmitted from the smartphone's camera and microphone. The input consists of images showing the customer's facial expressions and audio of their conversation. This data is necessary as preprocessing for sentiment analysis.

[0794] Step 2:

[0795] The server uses the OpenCV library to recognize the facial features of the customer from the received image data and analyze their facial expressions. The input is facial image data, and the output is data indicating the customer's emotional state. This analysis quantitatively evaluates what emotions the customer is currently experiencing.

[0796] Step 3:

[0797] The server uses Google Cloud Speech-to-Text to convert audio data into text and analyzes the conversation content and customer tone from that text. The input is the customer's audio data, and the output is the emotional state derived from the customer's utterances and tone. This process allows for an understanding of the customer's interests and concerns.

[0798] Step 4:

[0799] The server integrates emotional state data obtained from facial expressions and voice, creating a dataset to input into the generative AI model. This prepares it to make suggestions that reflect emotions in real time.

[0800] Step 5:

[0801] The server uses generative AI models such as Hugging Face Transformer to generate optimal suggestion content based on prompt text. The input is integrated sentiment data and prompt text, and the output is dynamically customized suggestion content. This enables the suggestion of the most suitable products and services tailored to the customer's interests.

[0802] Step 6:

[0803] The terminal receives suggestion content sent from the server and displays it to the salesperson. The input is the suggestion content generated by the server, and the output is the selection displayed on the screen. This allows the salesperson to provide suggestions tailored to the customer's needs in real time.

[0804] Step 7:

[0805] Users operate the terminal to make proposals to customers and observe their reactions. Salespeople can use the information provided by the system to conduct sales while communicating appropriately.

[0806] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0807] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0808] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0809] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0810] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0811] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0812] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0813] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0814] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0815] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0816] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0817] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0818] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0819] 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.

[0820] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0821] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0822] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0823] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0824] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0825] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0826] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0827] The following is further disclosed regarding the embodiments described above.

[0828] (Claim 1)

[0829] Means of collecting information,

[0830] The means of analyzing the collected information,

[0831] A means of training a generative model based on the analysis results,

[0832] A means of generating proposed content using a generative model,

[0833] Means of distributing proposed content,

[0834] A system that includes this.

[0835] (Claim 2)

[0836] The system according to claim 1, wherein the proposed content is in video format.

[0837] (Claim 3)

[0838] The system according to claim 1, further comprising means for customizing suggested content using a customer's past inquiry history.

[0839] "Example 1"

[0840] (Claim 1)

[0841] Means of collecting information,

[0842] A means of integrating and analyzing the collected information,

[0843] A means of identifying the trends and potential demands of others and predicting the overall trends in the industry,

[0844] A means for generating proposed content using a generated AI model based on analysis results and input information,

[0845] The means of distributing the proposal,

[0846] A system that includes this.

[0847] (Claim 2)

[0848] The proposed content is in video format and includes visual elements; the system according to claim 1.

[0849] (Claim 3)

[0850] The system according to claim 1, further comprising means for customizing the content of proposals using the past inquiry history of other parties.

[0851] "Application Example 1"

[0852] (Claim 1)

[0853] Means of collecting information,

[0854] The means of analyzing the collected information,

[0855] A means of training a generative model based on the analysis results,

[0856] A means of generating proposed content using a generative model,

[0857] A means for transmitting the generated proposed content using a communication means,

[0858] A means of proposing electronic transaction solutions tailored to the customer's industry and interests,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, wherein the proposed content is in video format.

[0862] (Claim 3)

[0863] The system according to claim 1, further comprising means for customizing suggested content using a customer's past inquiry history.

[0864] "Example 2 of combining an emotion engine"

[0865] (Claim 1)

[0866] Means of collecting information,

[0867] The means of analyzing the collected information,

[0868] A means of training a generative model based on the analysis results,

[0869] A means of generating proposed content using a generative model,

[0870] Means of distributing proposed content,

[0871] A means of recognizing user emotions in real time and dynamically adjusting the suggested content,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, wherein the proposed content is in video format and includes means for optimizing the video content based on emotion recognition.

[0875] (Claim 3)

[0876] The system according to claim 1, further comprising means for customizing suggested content using the customer's past inquiry history and behavioral patterns.

[0877] "Application example 2 when combining with an emotional engine"

[0878] (Claim 1)

[0879] Means of collecting information,

[0880] The means of analyzing the collected information,

[0881] A means of training a generative model based on the analysis results,

[0882] A means of generating proposed content using a generative model,

[0883] Means of distributing proposed content,

[0884] Methods for analyzing emotional states,

[0885] A means of dynamically customizing suggested content based on analyzed emotional states,

[0886] Means of recognizing facial features,

[0887] Means for processing audio data,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, wherein the proposed content is visual content.

[0891] (Claim 3)

[0892] The system according to claim 1, further comprising means for customizing suggested content using past behavioral history. [Explanation of Symbols]

[0893] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting information, The means of analyzing the collected information, A means of training a generative model based on the analysis results, A means of generating proposed content using a generative model, Means of distributing proposed content, A system that includes this.

2. The system according to claim 1, wherein the proposed content is in video format.

3. The system according to claim 1, further comprising means for customizing suggested content using the customer's past inquiry history.

Images