system

Abstract

We provide the system. [Solution] Means of obtaining customer-related information, A means of analyzing acquired customer-related information to identify customer demand, A means for automatically generating visual media content based on identified demand, Means for distributing generated visual media content through social infrastructure, 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There are many proposed products and solutions for corporations, and it is difficult for salespersons to make efficient and customer-oriented proposals while constantly updated with new information. Also, while video marketing is effective, there is an issue that it requires high costs and time to create. Furthermore, on the customer side, there is a current situation where it is difficult to quickly obtain optimal information and proposals for their own company.

Means for Solving the Problems

[0005] This invention provides a system that acquires customer information, analyzes it, and identifies customer needs. Furthermore, it solves these problems by automatically generating video content based on the identified needs and distributing the generated videos to customers. This system uses machine learning models to precisely analyze customer needs and also reflects industry trends from external sources in the video content, thereby enabling more accurate proposals.

[0006] "Customer information" refers to data that includes attribute information about a company's customers, past transaction history, and notes from the person in charge.

[0007] "Analysis" is the process of using collected data to understand customer characteristics and needs, and organizing information according to a specific purpose.

[0008] "Needs" refer to the challenges a customer faces, the areas they want to improve, or the solutions they are seeking.

[0009] "Video content" refers to electronic visual media that includes audio narration, animation, and text information to appeal to viewers visually.

[0010] "Distribution" refers to the act of sending generated content to a specific recipient by electronic means.

[0011] A "machine learning model" is an algorithm or system that automatically learns patterns and characteristics based on collected data to perform predictions and analyses.

[0012] "Industry trends" refer to information that indicates recent developments, new technological trends, or market changes observed in a particular industry. [Brief explanation of the drawing]

[0013] [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] 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.

[0017] 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.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention is a system designed to streamline and improve the accuracy of product and service proposals for corporate clients. The system consists of multiple operating modules, each performing a specific function.

[0035] The core of the system is the customer information collection and analysis function. First, the server accesses the company's database and automatically retrieves customer-related information. This includes past transaction history and data on the customer's business needs, industry, and size.

[0036] Next, the server analyzes the acquired customer information and uses a machine learning model to identify the customer's potential needs and interests. The machine learning model used here compares the customer's past behavior patterns with current industry trends to predict future needs.

[0037] Next, the user (sales representative) uses the device to request the generation of a video proposal for a specific customer. This request includes specific proposal content and points to focus on. For example, they might request a "proposal regarding the latest security solutions."

[0038] Upon receiving this request, the server uses a generative AI model to automatically generate personalized video content based on the customer's specific needs and relevant information. The generated video visually incorporates sections designed to capture the customer's interest and clearly demonstrates the specific benefits of the solution.

[0039] The generated video content is delivered to the user via their device. Users can utilize this video in business negotiations and presentations, and also distribute it to customers via email. This email is integrated with the CRM system to ensure it reaches customers at the appropriate time.

[0040] This invention significantly improves sales efficiency and enhances the quality and relevance of information provided to customers. For example, when proposing a new cloud solution to Company A, the system considers Company A's industry trends and past challenges, and generates a video presenting the optimal solution. This maximizes the potential of sales activities and improves customer satisfaction.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server connects to the company's database and CRM system to collect comprehensive data about customers. This data includes information about the customer's industry, annual revenue, past transaction history, purchased products and services, and the customer's contact person.

[0044] Step 2:

[0045] The server retrieves the latest industry news and trends from external sources and industry databases. It utilizes external APIs and feeds to collect noteworthy topics and technological trends in the customer's industry.

[0046] Step 3:

[0047] The server analyzes collected customer information and industry trends. It utilizes machine learning models to predict customers' potential needs and problems they need solving. This process identifies customer interests and priorities.

[0048] Step 4:

[0049] The user enters a request from their terminal to create a proposal for a specific customer. They specify the details of the proposal (e.g., security solutions) and the points to focus on.

[0050] Step 5:

[0051] The server uses a generative AI model to generate customized video content based on requests. The generated videos include suggestions and product benefits optimized for the customer's characteristics.

[0052] Step 6:

[0053] The device displays the generated video content to the user. The user can review this video and make adjustments as needed.

[0054] Step 7:

[0055] Users utilize videos generated during sales meetings and presentations as a sales tool. They also prepare these videos for distribution via email and customer-facing online platforms.

[0056] Step 8:

[0057] The server schedules and manages video delivery to customers, integrating with the CRM system to send videos to customers via email at the appropriate time. This delivery automatically tracks customer responses and accumulates information that can be used for future proposals.

[0058] (Example 1)

[0059] 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."

[0060] Traditional sales support systems have had the problem of difficulty in accurately understanding customers' potential needs and providing appropriate information based on those needs. Furthermore, the personalization of the content provided was insufficient, limiting the effectiveness of proposals to customers. Therefore, improving the efficiency of sales activities and enhancing customer satisfaction are key challenges.

[0061] 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.

[0062] In this invention, the server includes means for acquiring customer information, means for identifying the customer's potential needs, and means for automatically generating video content using a generative artificial intelligence model. This enables the automatic generation and distribution of personalized content based on customer needs.

[0063] "Customer information" refers to data related to customers, such as transaction history, business details, business needs, industry, and size, involving corporations and individuals.

[0064] "Latent needs" are requirements or concerns that customers may have in the future but are not currently apparent.

[0065] A "generative artificial intelligence model" is a model based on machine learning or deep learning that is used to generate content tailored to customer needs based on large amounts of data.

[0066] "Personalized video content" refers to individually tailored video content that is specifically designed to meet the needs and interests of a particular customer.

[0067] An "information processing device" is a device that includes hardware and software for collecting, analyzing, processing, and outputting data.

[0068] "Industry trends" refer to current and anticipated changes and developments regarding products and services observed within a particular market or industry.

[0069] The system of this invention aims to efficiently propose products and services to corporate clients and to improve the accuracy of such proposals. This system is realized through a process of collecting and analyzing customer information and generating personalized video content based on that information.

[0070] The server accesses its own database to retrieve customer information. This uses a database management system, such as one for manipulating SQL or NoSQL databases. The collected information includes past transaction history, business needs, industry, and size data. This data is cached on the server and prepared for analysis.

[0071] Next, the server analyzes cached customer information using a machine learning model. Python is used as the specific programming language, and the learning model is executed using frameworks such as Scikit-learn and TENSORFLOW®. This model takes into account past behavioral patterns and industry trend information to identify customers' latent needs.

[0072] Users send requests from their devices to the server to generate video proposals for specific customers for use in sales activities. These requests include details such as the product type, proposal content, and key points to focus on. For example, a prompt might read, "Generate a video proposal for a cloud solution that takes into account recent industry trends and past challenges at Company A."

[0073] The server utilizes generative AI models to automatically generate personalized videos based on prompts received from the user. OpenAI's GPT model and DALL-E are used to construct the scenarios. Video editing software such as Adobe Premiere Pro and Final Cut Pro are used to generate the videos.

[0074] Ultimately, the generated video content is delivered to the user via their device. Users can utilize this video in business negotiations and presentations, and can also distribute it to customers via email. Distribution is coordinated with the CRM system to ensure the video reaches customers at the appropriate time.

[0075] In this way, this system improves sales efficiency and enhances the quality and suitability of proposals.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server connects to the company's database and retrieves customer information. The input here consists of commands, such as SQL queries, to extract the necessary customer data from the database. The server aggregates data such as the customer's past transaction history, business needs, industry, and size, and stores it in a cache as structured data. This prepares the dataset for analysis.

[0079] Step 2:

[0080] The server analyzes customer information using machine learning algorithms. The input data is customer information obtained in Step 1, and the output is insights that indicate the customer's potential needs. Predictive analysis is performed using the Python language and frameworks such as Scikit-learn and TensorFlow, taking into account past behavioral patterns and industry trends. This analysis identifies the customer's future needs.

[0081] Step 3:

[0082] The user uses their device to request the generation of video proposals for a specific customer. The input is a prompt message set by the user, containing information such as "specific product proposal details" and "technologies to focus on." The device sends this prompt message to the server. This prompt also reflects the customer analysis results.

[0083] Step 4:

[0084] The server automatically generates personalized video content based on user prompts using a generative AI model. The AI ​​model receives prompts and customer needs analysis as input and generates video scenarios and scripts as output. Tools used include the GPT model and DALL-E. Based on this script, a visually appealing video is created via video editing software.

[0085] Step 5:

[0086] The server converts the generated video into a digital format and sends it to the terminal. The output is a streamable video file that the user can receive and use in business negotiations and presentations. This also allows the user to email the video to customers at the appropriate time, maximizing its effectiveness through the CRM system.

[0087] (Application Example 1)

[0088] 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."

[0089] In today's B2B market, there is a demand for the rapid generation and timely delivery of effective visual media content tailored to individual customer needs. However, traditional methods struggle to accurately identify customers' latent needs and efficiently deliver video content that considers industry trends. Furthermore, distributing content across diverse platforms using different communication methods requires manual adjustments, resulting in inefficiency. Solving these problems will enable more accurate and rapid customer service.

[0090] 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.

[0091] In this invention, the server includes means for acquiring customer-related information, means for analyzing the acquired customer-related information and identifying customer demand, means for automatically generating visual media content based on the identified demand, and means for distributing the generated visual media content through social infrastructure. This makes it possible to efficiently generate personalized visual media content tailored to each customer and deliver it at the appropriate time.

[0092] "Customer-related information" refers to information about customers, such as their attributes, past behavioral patterns, and usage history.

[0093] "Demand" refers to the potential interests and needs of customers regarding products and services.

[0094] "Visual media content" refers to a collection of information that is conveyed visually, including videos and graphics.

[0095] "Social infrastructure" refers to a wide range of communication infrastructure, including the internet and mobile networks.

[0096] "Machine learning techniques" refer to algorithms and technologies that learn patterns and trends from data to make future predictions and classifications.

[0097] "Industry trends" refer to the latest trends and innovations in a particular industry or market.

[0098] This invention is a system designed to improve the efficiency of proposing products and services to corporate clients. The system primarily consists of a server and various terminals, and is responsible for acquiring and analyzing customer-related information, and generating and distributing visual media content.

[0099] The server retrieves customer-related information from a database and analyzes it using machine learning techniques. Specifically, it uses machine learning software such as TensorFlow to predict future demand based on past customer behavior patterns. Meanwhile, it automatically generates personalized visual media content based on specific demands by using generative AI models (e.g., OpenAI's GPT-4®). This allows for the rapid creation of visual media that captures customer interest.

[0100] The generated visual media content is delivered to the user via their device. Users utilize this content in business negotiations, presentations, or for distribution to social infrastructure via email. At this stage in particular, trends and past challenges in the customer's industry are considered, enabling customized proposals.

[0101] As a concrete example, when proposing a new health-oriented product to the food industry, this system can analyze the customer's past purchase history and local consumption trends to generate content containing the most appealing elements. This process is achieved when the server sends prompts such as "Customer Information: Food Industry, Past Issues: Low Interest in Health-Oriented Products, New Proposal: Healthy Snack Product" to the AI ​​model, which then receives a prompt message such as "Generate an advertising video that highlights the features of the new health-oriented snack product and how it differentiates itself from conventional products."

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The server retrieves customer-related information from the database. Inputs include customer ID and transaction history, and based on this, it extracts customer attributes and past purchase data. The output is a set of customer-related information that can be analyzed.

[0105] Step 2:

[0106] The server analyzes the acquired customer-related information using machine learning techniques such as TensorFlow. The input is the customer-related information acquired in step 1, and the data processing involves feature extraction and normalization. The output is predictive data regarding the customer's potential demand and interests.

[0107] Step 3:

[0108] The server generates and sends a specific prompt to the generative AI model. The input is the prediction data from step 2, which generates a specific prompt: "Customer information: Food industry, Past challenges: Low interest in health-oriented products, New proposal: Healthy snack products". The output is passed to the generative AI model as a prompt.

[0109] Step 4:

[0110] The generative AI model generates personalized visual media content based on prompt text. The input is the prompt text from step 3, and the data calculation involves content generation using natural language processing. The output is video content highlighting the features of a new health-conscious snack product.

[0111] Step 5:

[0112] The device provides the user with the generated visual media content. The input is the video content generated in step 4, which the user can then use in presentations or emails. The output is visually compelling content designed to support business decision-making.

[0113] Step 6:

[0114] Users utilize content generated via their devices to conduct sales activities with customers. The input is the video content from step 5, and specific actions include showing the content to customers and distributing it through various platforms. The output is the implementation of effective customer proposals and the generation of high customer interest.

[0115] 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.

[0116] This invention is a system that recognizes user emotions and personalizes and optimizes suggested content. The system consists of the following main modules:

[0117] First, the server retrieves basic customer information from the company's database and CRM system. This information includes past transaction history, customer attributes, and past product usage data. It also retrieves the latest industry trends and market developments from external sources. This allows for a comprehensive understanding of the customer's current situation.

[0118] The server analyzes this information using machine learning models to extract customers' latent needs. This makes it possible to generate customized video content for each customer, going beyond generic suggestions.

[0119] In addition, this system employs an emotion engine. The terminal acquires emotion data in real time from the user's facial expressions and voice. This emotion data is used to measure the user's level of engagement and response.

[0120] The server adjusts the generated video content based on analysis by the emotion engine. For example, if the user is excited, the video will be adjusted to provide more detailed and advanced technical information. Conversely, if the user is not excited, it will select concise and visually appealing content to capture their interest.

[0121] For example, when a user requires a security solution, the system generates a proposal that takes into account the company's past incident information and industry security risks. In this process, the number and details of success stories included in the proposal can be dynamically adjusted based on the user's emotional state.

[0122] Ultimately, the generated content is displayed on a terminal as a support tool for sales activities, or delivered to customers via email at the appropriate time. In this way, the present invention makes it possible to achieve advanced personalization utilizing emotional data and significantly improve the quality of customer interactions.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The server retrieves customer information from the company's database and CRM system. This information includes basic customer attributes, past transaction history, and product usage.

[0126] Step 2:

[0127] The server collects industry trends and the latest market developments via external APIs. This includes news articles and information on innovative technologies related to the customer's industry.

[0128] Step 3:

[0129] The server analyzes collected customer information and industry data using machine learning models to identify customers' potential needs and interests. This analysis provides the foundational data for making personalized recommendations to customers.

[0130] Step 4:

[0131] The user uses their device to enter a request to generate a suggestion video for a specific customer. The request includes the product to be suggested and the segment to focus on.

[0132] Step 5:

[0133] The server uses a generative AI model to automatically generate video content based on analysis results and user requests. This video incorporates appropriate suggestions, relevant product benefits, and visual elements.

[0134] Step 6:

[0135] The device provides the generated video to the user, who then reviews the video's content, and the device also collects emotional data in real time from the user's facial expressions and voice.

[0136] Step 7:

[0137] The server analyzes emotional data collected using an emotion engine and dynamically adjusts video content according to the user's emotional state. For example, if the user's reaction is positive, detailed technical information is added; if it is negative, simplified information is provided.

[0138] Step 8:

[0139] Users prepare to use the edited videos in business negotiations and other settings, and to distribute the video content to customers via email and online platforms.

[0140] Step 9:

[0141] The server manages the video distribution schedule and integrates with the CRM system to deliver videos to customers at the optimal time. After distribution, it collects customer viewing data and feedback to help improve future sales activities.

[0142] (Example 2)

[0143] 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".

[0144] Traditional customer service systems struggle to fully grasp overall needs and individual preferences simply by analyzing acquired customer information, making it difficult to provide customers with the most suitable content. Furthermore, the lack of interactive personalization utilizing emotional data makes it challenging to increase customer engagement.

[0145] 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.

[0146] In this invention, the server includes means for acquiring customer information, means for analyzing the acquired customer information to identify the customer's hidden needs, means for acquiring emotional data to measure user preferences, means for adjusting video content to reflect those preferences, and means for transmitting the generated and adjusted video content to the customer. This enables accurate understanding of the customer's hidden needs and the provision of personalized content utilizing emotional data.

[0147] "Customer information" refers to information used to understand customer behavior and characteristics, such as attribute information, transaction history, and past product usage.

[0148] "Analysis" is the process of extracting hidden requirements and patterns from acquired data and transforming them into meaningful information.

[0149] "Emotional data" refers to information that indicates a user's emotional state, obtained based on the user's facial expressions and voice.

[0150] "Video content" refers to dynamic visual and auditory works created to convey information to users.

[0151] "Adjusting" refers to the process of changing or optimizing content or its presentation to meet a specific goal.

[0152] "Communicating" means delivering generated or adapted content to customers using appropriate means.

[0153] "Trends" refer to information that describes the current state or future predictions in a particular field.

[0154] Embodiments of the present invention are systems that generate and provide personalized video content to customers by utilizing customer information and sentiment data. This system mainly includes a server and terminals.

[0155] The server first acquires customer information. This information is collected from the company's customer management system and databases and includes customer attributes, transaction history, and past product usage data. It also obtains industry trends and the latest market information from external sources to comprehensively understand the customer's situation. This information is analyzed using machine learning models such as TensorFlow and PyTorch, and the data is processed to extract hidden customer requests and potential needs.

[0156] In parallel, the device acquires user emotion data in real time. This utilizes hardware such as the camera and microphone, and employs OpenCV and speech analysis APIs to extract emotions from the user's facial expressions and voice. The acquired emotion data is used to measure user preferences and personalize content.

[0157] The server dynamically adjusts video content based on customer requests and sentiment data obtained from machine learning models. Specifically, it uses video editing software such as Adobe Premiere Pro to change the amount of information and visual effects of the content according to the user's level of excitement. It provides detailed information to excited users and concise and engaging content to less excited users.

[0158] Ultimately, the generated content is either displayed to the user through their device or delivered at the appropriate time via email or other means. For example, by using a prompt such as "Generate engaging content based on customer sentiment data" to the generation AI model, it becomes possible to generate specific content. This process can improve the quality of the customer experience.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] The server retrieves customer information. Inputs include customer attribute data from the customer management system, transaction history, and product usage. Using this data, the server generates a comprehensive customer profile. The output is a set of relevant customer information. This process provides a foundation for understanding customer needs.

[0162] Step 2:

[0163] The server analyzes the acquired customer information. The input is the output from step 1, and the data is analyzed using machine learning models such as TensorFlow and PyTorch. Data processing involves feature selection and data clustering to extract hidden patterns and latent customer needs. The output is the analysis results regarding the customer's hidden needs. This allows for the suggestion of customizable content for each customer.

[0164] Step 3:

[0165] The device acquires user emotion data. Input includes the user's facial expressions and voice, collected via the camera and microphone. This data is used to analyze emotions in real time using OpenCV and voice analysis APIs. Data processing outputs numerical information representing the user's emotional state and level of engagement. This step allows for an understanding of the user's current emotional state.

[0166] Step 4:

[0167] The server adjusts the video content based on the analysis results and sentiment data. Inputs include the analysis results from step 2 and the sentiment data from step 3. Video editing software such as Adobe Premiere Pro is used to adjust the visual effects and amount of information in the content. For example, if the user is excited, a video rich in technical information is generated. The output is optimal video content tailored to the user's emotions.

[0168] Step 5:

[0169] The device displays or delivers the adjusted video content. The input is the video content generated in step 4. For display, it uses the device screen or is sent directly to the user via email, etc. As output, visually appealing content is delivered to the user at the appropriate time. This makes it possible to further capture the user's interest.

[0170] (Application Example 2)

[0171] 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".

[0172] Conventional video content distribution systems offered suggestions based solely on customer preferences, failing to optimize content to consider the emotional state of individual customers. Therefore, customers had to actively search for and select content to match their mood and emotional state at any given time, resulting in limited quality of suggestions. This created a need for a system capable of acquiring customers' real-time emotional states and dynamically adjusting and optimizing content accordingly.

[0173] 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.

[0174] In this invention, the server includes means for acquiring customer information, means for analyzing the acquired customer information and identifying the customer's potential needs, means for acquiring emotional data in real time from the user's facial expressions and voice, means for analyzing the acquired emotional data and dynamically adjusting and optimizing video content, and means for delivering the optimized video content to the customer. This makes it possible to provide personalized video content that takes into account the customer's real-time emotional state.

[0175] "Customer information" refers to all data related to customers, including attribute information, transaction history, and product usage history.

[0176] "Latent needs" refer to demands or desires that are not explicitly stated but are likely to be needed by customers in the future.

[0177] "Methods for acquiring emotional data in real time from facial expressions and voice" refers to technologies and devices that analyze a user's facial movements and voice tone to instantly grasp their current emotional state.

[0178] "Methods for analyzing emotional data and dynamically adjusting and optimizing video content" refers to technologies that, based on acquired emotional information, modify the content and structure of video content in real time to make it most suitable for the viewer.

[0179] "Means of delivering video content to customers" refers to the technologies and protocols used to transmit edited video to customers' viewing devices via the internet.

[0180] In this invention, both the server and the terminal work together to build the system. The server retrieves customer information from the company's own database and customer relationship management system, and analyzes this information using a machine learning model to identify the customer's potential needs. Specifically, it utilizes machine learning frameworks such as TensorFlow to learn from past transaction history and customer attributes, and performs analysis to predict future needs.

[0181] Meanwhile, the device is equipped with a camera and microphone to capture the user's facial expressions and voice in real time. This data is analyzed using image processing libraries such as OpenCV and the Google Cloud Speech-to-Text API to determine the user's current emotional state. The analyzed emotional data is sent to a server, which then dynamically adjusts the video content.

[0182] The generated content is delivered from the server to the device and optimized in real time. Specifically, when the user is relaxed, content with a storyline or relaxing videos is selected.

[0183] In this way, the system can provide content that is most suitable to the user's mood and state at that time. Furthermore, by using generative AI models, video content can generate even more detailed and personalized suggestions.

[0184] A concrete example of its use is using this system on a smartphone during a commute. One could watch yoga videos to relax in the morning or music videos to boost energy. An example of a prompt message in this scenario would be, "Please suggest videos that match my current mood."

[0185] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0186] Step 1:

[0187] The server retrieves customer information from the company's database and customer relationship management system. Inputs include customer IDs and transaction history from the database, while outputs include customer attribute information and past purchase history, which form the basis for analysis.

[0188] Step 2:

[0189] The server analyzes acquired customer information using a machine learning model. The input includes customer attribute information and purchase history, and based on this, it performs data processing and calculations to predict potential needs. The output is a list of potential needs for each customer.

[0190] Step 3:

[0191] The device uses its built-in camera and microphone to acquire the user's facial expressions and voice data in real time. The input is real-time data of the user's face and voice, and the output is raw data for sentiment analysis.

[0192] Step 4:

[0193] The device analyzes emotions from facial and voice data acquired in real time using OpenCV and the Google Cloud Speech-to-Text API. The input is the raw data acquired beforehand, and data processing and calculations are performed on this data to determine the emotional state. The output is data indicating the user's current emotional state.

[0194] Step 5:

[0195] The server dynamically adjusts and optimizes video content based on analyzed emotional data and potential needs. The input consists of emotional state data and a list of potential needs, and the server performs data calculations for content adjustment and optimization. The output is a list of video content optimized for the user's current state.

[0196] Step 6:

[0197] The server delivers optimized video content to the device. The input is a list of video content, and the output is content viewable on the user's device. This allows the user to watch the most suitable content according to their mood at the time.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] [Second Embodiment]

[0202] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0203] 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.

[0204] 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).

[0205] 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.

[0206] 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.

[0207] 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).

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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".

[0214] This invention is a system designed to streamline and improve the accuracy of product and service proposals for corporate clients. The system consists of multiple operating modules, each performing a specific function.

[0215] The core of the system is the customer information collection and analysis function. First, the server accesses the company's database and automatically retrieves customer-related information. This includes past transaction history and data on the customer's business needs, industry, and size.

[0216] Next, the server analyzes the acquired customer information and uses a machine learning model to identify the customer's potential needs and interests. The machine learning model used here compares the customer's past behavior patterns with current industry trends to predict future needs.

[0217] Next, the user (sales representative) uses the device to request the generation of a video proposal for a specific customer. This request includes specific proposal content and points to focus on. For example, they might request a "proposal regarding the latest security solutions."

[0218] Upon receiving this request, the server uses a generative AI model to automatically generate personalized video content based on the customer's specific needs and relevant information. The generated video visually incorporates sections designed to capture the customer's interest and clearly demonstrates the specific benefits of the solution.

[0219] The generated video content is delivered to the user via their device. Users can utilize this video in business negotiations and presentations, and also distribute it to customers via email. This email is integrated with the CRM system to ensure it reaches customers at the appropriate time.

[0220] This invention significantly improves sales efficiency and enhances the quality and relevance of information provided to customers. For example, when proposing a new cloud solution to Company A, the system considers Company A's industry trends and past challenges, and generates a video presenting the optimal solution. This maximizes the potential of sales activities and improves customer satisfaction.

[0221] The following describes the processing flow.

[0222] Step 1:

[0223] The server connects to the company's database and CRM system to collect comprehensive data about customers. This data includes information about the customer's industry, annual revenue, past transaction history, purchased products and services, and the customer's contact person.

[0224] Step 2:

[0225] The server retrieves the latest industry news and trends from external sources and industry databases. It utilizes external APIs and feeds to collect noteworthy topics and technological trends in the customer's industry.

[0226] Step 3:

[0227] The server analyzes collected customer information and industry trends. It utilizes machine learning models to predict customers' potential needs and problems they need solving. This process identifies customer interests and priorities.

[0228] Step 4:

[0229] The user enters a request from their terminal to create a proposal for a specific customer. They specify the details of the proposal (e.g., security solutions) and the points to focus on.

[0230] Step 5:

[0231] The server uses a generative AI model to generate customized video content based on requests. The generated videos include suggestions and product benefits optimized for the customer's characteristics.

[0232] Step 6:

[0233] The device displays the generated video content to the user. The user can review this video and make adjustments as needed.

[0234] Step 7:

[0235] Users utilize videos generated during sales meetings and presentations as a sales tool. They also prepare these videos for distribution via email and customer-facing online platforms.

[0236] Step 8:

[0237] The server schedules and manages video delivery to customers, integrating with the CRM system to send videos to customers via email at the appropriate time. This delivery automatically tracks customer responses and accumulates information that can be used for future proposals.

[0238] (Example 1)

[0239] 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".

[0240] Traditional sales support systems have had the problem of difficulty in accurately understanding customers' potential needs and providing appropriate information based on those needs. Furthermore, the personalization of the content provided was insufficient, limiting the effectiveness of proposals to customers. Therefore, improving the efficiency of sales activities and enhancing customer satisfaction are key challenges.

[0241] 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.

[0242] In this invention, the server includes means for acquiring customer information, means for identifying the customer's potential needs, and means for automatically generating video content using a generative artificial intelligence model. This enables the automatic generation and distribution of personalized content based on customer needs.

[0243] "Customer information" refers to data related to customers, such as transaction history, business details, business needs, industry, and size, involving corporations and individuals.

[0244] "Latent needs" are requirements or concerns that customers may have in the future but are not currently apparent.

[0245] A "generative artificial intelligence model" is a model based on machine learning or deep learning that is used to generate content tailored to customer needs based on large amounts of data.

[0246] "Personalized video content" refers to individually tailored video content that is specifically designed to meet the needs and interests of a particular customer.

[0247] An "information processing device" is a device that includes hardware and software for collecting, analyzing, processing, and outputting data.

[0248] "Industry trends" refer to current and anticipated changes and developments regarding products and services observed within a particular market or industry.

[0249] The system of this invention aims to efficiently propose products and services to corporate clients and to improve the accuracy of such proposals. This system is realized through a process of collecting and analyzing customer information and generating personalized video content based on that information.

[0250] The server accesses its own database to retrieve customer information. This uses a database management system, such as one for manipulating SQL or NoSQL databases. The collected information includes past transaction history, business needs, industry, and size data. This data is cached on the server and prepared for analysis.

[0251] Next, the server analyzes cached customer information using a machine learning model. Python is used as the specific programming language, and the learning model is executed using frameworks such as Scikit-learn and TensorFlow. This model takes into account past behavioral patterns and industry trend information to identify customers' latent needs.

[0252] Users send requests from their devices to the server to generate video proposals for specific customers for use in sales activities. These requests include details such as the product type, proposal content, and key points to focus on. For example, a prompt might read, "Generate a video proposal for a cloud solution that takes into account recent industry trends and past challenges at Company A."

[0253] The server uses generative AI models to automatically generate personalized videos based on prompts received from the user. OpenAI's GPT model and DALL-E are used to construct the scenarios. Video editing software such as Adobe Premiere Pro and Final Cut Pro are used to generate the videos.

[0254] Ultimately, the generated video content is delivered to the user via their device. Users can utilize this video in business negotiations and presentations, and can also distribute it to customers via email. Distribution is coordinated with the CRM system to ensure the video reaches customers at the appropriate time.

[0255] In this way, this system improves sales efficiency and enhances the quality and suitability of proposals.

[0256] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0257] Step 1:

[0258] The server connects to the company's database and retrieves customer information. The input here consists of commands, such as SQL queries, to extract the necessary customer data from the database. The server aggregates data such as the customer's past transaction history, business needs, industry, and size, and stores it in a cache as structured data. This prepares the dataset for analysis.

[0259] Step 2:

[0260] The server analyzes customer information using machine learning algorithms. The input data is customer information obtained in Step 1, and the output is insights that indicate the customer's potential needs. Predictive analysis is performed using the Python language and frameworks such as Scikit-learn and TensorFlow, taking into account past behavioral patterns and industry trends. This analysis identifies the customer's future needs.

[0261] Step 3:

[0262] The user uses their device to request the generation of video proposals for a specific customer. The input is a prompt message set by the user, containing information such as "specific product proposal details" and "technologies to focus on." The device sends this prompt message to the server. This prompt also reflects the customer analysis results.

[0263] Step 4:

[0264] The server automatically generates personalized video content based on user prompts using a generative AI model. The AI ​​model receives prompts and customer needs analysis as input and generates video scenarios and scripts as output. Tools used include the GPT model and DALL-E. Based on this script, a visually appealing video is created via video editing software.

[0265] Step 5:

[0266] The server converts the generated video into a digital format and sends it to the terminal. The output is a streamable video file that the user can receive and use in business negotiations and presentations. This also allows the user to email the video to customers at the appropriate time, maximizing its effectiveness through the CRM system.

[0267] (Application Example 1)

[0268] 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 glasses 214 will be referred to as the "terminal."

[0269] In today's B2B market, there is a demand for the rapid generation and timely delivery of effective visual media content tailored to individual customer needs. However, traditional methods struggle to accurately identify customers' latent needs and efficiently deliver video content that considers industry trends. Furthermore, distributing content across diverse platforms using different communication methods requires manual adjustments, resulting in inefficiency. Solving these problems will enable more accurate and rapid customer service.

[0270] 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.

[0271] In this invention, the server includes means for acquiring customer-related information, means for analyzing the acquired customer-related information and identifying customer demand, means for automatically generating visual media content based on the identified demand, and means for distributing the generated visual media content through social infrastructure. This makes it possible to efficiently generate personalized visual media content tailored to each customer and deliver it at the appropriate time.

[0272] "Customer-related information" refers to information about customers, such as their attributes, past behavioral patterns, and usage history.

[0273] "Demand" refers to the potential interests and needs of customers regarding products and services.

[0274] "Visual media content" refers to a collection of information that is conveyed visually, including videos and graphics.

[0275] "Social infrastructure" refers to a wide range of communication infrastructure, including the internet and mobile networks.

[0276] "Machine learning techniques" refer to algorithms and technologies that learn patterns and trends from data to make future predictions and classifications.

[0277] "Industry trends" refer to the latest trends and innovations in a particular industry or market.

[0278] This invention is a system designed to improve the efficiency of proposing products and services to corporate clients. The system primarily consists of a server and various terminals, and is responsible for acquiring and analyzing customer-related information, and generating and distributing visual media content.

[0279] The server retrieves customer-related information from a database and analyzes it using machine learning techniques. Specifically, it uses machine learning software such as TensorFlow to predict future demand based on past customer behavior patterns. Meanwhile, it automatically generates personalized visual media content based on specific demands by using generative AI models (e.g., OpenAI's GPT-4). This allows for the rapid creation of visual media that captures customer interest.

[0280] The generated visual media content is delivered to the user via their device. Users utilize this content in business negotiations, presentations, or for distribution to social infrastructure via email. At this stage in particular, trends and past challenges in the customer's industry are considered, enabling customized proposals.

[0281] As a specific example, when proposing new health-oriented products in the food industry, this system can analyze customers' past purchase histories and regional consumption trends to generate content that includes the most interesting elements. This process is realized by the server sending prompts such as "Customer Information: Food Industry, Past Issue: Low Interest in Health-Oriented Products, New Proposal: Healthy Snack Products" to the generative AI model and passing through a prompt sentence like "Please generate an advertising video that emphasizes the features of the new health-oriented snack products and the differentiating points from conventional products."

[0282] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0283] Step 1:

[0284] The server retrieves customer-related information from the database. The inputs are customer IDs and transaction histories, and based on these, customer attributes and past purchase data are extracted. The output is a set of customer-related information that can be analyzed.

[0285] Step 2:

[0286] The server analyzes the retrieved customer-related information using machine learning techniques such as TensorFlow. The input is the customer-related information obtained in Step 1, and data processing includes feature extraction and normalization. The output is predictive data regarding customers' potential needs and interests.

[0287] Step 3:

[0288] The server generates and sends a specific prompt sentence to the generative AI model. The input is the predictive data from Step 2, and a specific prompt like "Customer Information: Food Industry, Past Issue: Low Interest in Health-Oriented Products, New Proposal: Healthy Snack Products" is generated. The output is passed to the generative AI model as a prompt sentence.

[0289] Step 4:

[0290] The generative AI model generates personalized visual media content based on prompt text. The input is the prompt text from step 3, and the data calculation involves content generation using natural language processing. The output is video content highlighting the features of a new health-conscious snack product.

[0291] Step 5:

[0292] The device provides the user with the generated visual media content. The input is the video content generated in step 4, which the user can then use in presentations or emails. The output is visually compelling content designed to support business decision-making.

[0293] Step 6:

[0294] Users utilize content generated via their devices to conduct sales activities with customers. The input is the video content from step 5, and specific actions include showing the content to customers and distributing it through various platforms. The output is the implementation of effective customer proposals and the generation of high customer interest.

[0295] 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.

[0296] This invention is a system that recognizes user emotions and personalizes and optimizes suggested content. The system consists of the following main modules:

[0297] First, the server retrieves basic customer information from the company's database and CRM system. This information includes past transaction history, customer attributes, and past product usage data. It also retrieves the latest industry trends and market developments from external sources. This allows for a comprehensive understanding of the customer's current situation.

[0298] The server analyzes this information using machine learning models to extract customers' latent needs. This makes it possible to generate customized video content for each customer, going beyond generic suggestions.

[0299] In addition, this system employs an emotion engine. The terminal acquires emotion data in real time from the user's facial expressions and voice. This emotion data is used to measure the user's level of engagement and response.

[0300] The server adjusts the generated video content based on analysis by the emotion engine. For example, if the user is excited, the video will be adjusted to provide more detailed and advanced technical information. Conversely, if the user is not excited, it will select concise and visually appealing content to capture their interest.

[0301] For example, when a user requires a security solution, the system generates a proposal that takes into account the company's past incident information and industry security risks. In this process, the number and details of success stories included in the proposal can be dynamically adjusted based on the user's emotional state.

[0302] Ultimately, the generated content is displayed on a terminal as a support tool for sales activities, or delivered to customers via email at the appropriate time. In this way, the present invention makes it possible to achieve advanced personalization utilizing emotional data and significantly improve the quality of customer interactions.

[0303] The following describes the processing flow.

[0304] Step 1:

[0305] The server retrieves customer information from its own database and CRM system. This information includes basic customer attributes, past transaction history, product usage status, etc.

[0306] Step 2:

[0307] The server collects industry trends and the latest market movements via external APIs. This includes news articles related to the customer's industry and information on innovative technologies.

[0308] Step 3:

[0309] The server analyzes the collected customer information and industry data using a machine learning model to identify the potential needs and interests of customers. The results of this analysis serve as the basic data for making personalized proposals to customers.

[0310] Step 4:

[0311] The user uses a terminal to input a request to generate a proposal video for a specific customer. The request includes the product to be proposed and the segment to be focused on.

[0312] Step 5:

[0313] The server utilizes a generative AI model to automatically generate video content based on the analysis results and the user's request. This video incorporates appropriate proposal content, relevant product merits, and visual elements.

[0314] Step 6:

[0315] The terminal provides the generated video to the user, and the user checks the content of the video. Additionally, the terminal collects emotion data in real-time from the user's expression and voice.

[0316] Step 7:

[0317] The server analyzes emotional data collected using an emotion engine and dynamically adjusts video content according to the user's emotional state. For example, if the user's reaction is positive, detailed technical information is added; if it is negative, simplified information is provided.

[0318] Step 8:

[0319] Users prepare to use the edited videos in business negotiations and other settings, and to distribute the video content to customers via email and online platforms.

[0320] Step 9:

[0321] The server manages the video distribution schedule and integrates with the CRM system to deliver videos to customers at the optimal time. After distribution, it collects customer viewing data and feedback to help improve future sales activities.

[0322] (Example 2)

[0323] 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".

[0324] Traditional customer service systems struggle to fully grasp overall needs and individual preferences simply by analyzing acquired customer information, making it difficult to provide customers with the most suitable content. Furthermore, the lack of interactive personalization utilizing emotional data makes it challenging to increase customer engagement.

[0325] 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.

[0326] In this invention, the server includes means for acquiring customer information, means for analyzing the acquired customer information to identify the customer's hidden needs, means for acquiring emotional data to measure user preferences, means for adjusting video content to reflect those preferences, and means for transmitting the generated and adjusted video content to the customer. This enables accurate understanding of the customer's hidden needs and the provision of personalized content utilizing emotional data.

[0327] "Customer information" refers to information used to understand customer behavior and characteristics, such as attribute information, transaction history, and past product usage.

[0328] "Analysis" is the process of extracting hidden requirements and patterns from acquired data and transforming them into meaningful information.

[0329] "Emotional data" refers to information that indicates a user's emotional state, obtained based on the user's facial expressions and voice.

[0330] "Video content" refers to dynamic visual and auditory works created to convey information to users.

[0331] "Adjusting" refers to the process of changing or optimizing content or its presentation to meet a specific goal.

[0332] "Communicating" means delivering generated or adapted content to customers using appropriate means.

[0333] "Trends" refer to information that describes the current state or future predictions in a particular field.

[0334] Embodiments of the present invention are systems that generate and provide personalized video content to customers by utilizing customer information and sentiment data. This system mainly includes a server and terminals.

[0335] The server first acquires customer information. This information is collected from the company's customer management system and databases and includes customer attributes, transaction history, and past product usage data. It also obtains industry trends and the latest market information from external sources to comprehensively understand the customer's situation. This information is analyzed using machine learning models such as TensorFlow and PyTorch, and the data is processed to extract hidden customer requests and potential needs.

[0336] In parallel, the device acquires user emotion data in real time. This utilizes hardware such as the camera and microphone, and employs OpenCV and speech analysis APIs to extract emotions from the user's facial expressions and voice. The acquired emotion data is used to measure user preferences and personalize content.

[0337] The server dynamically adjusts video content based on customer requests and sentiment data obtained from machine learning models. Specifically, it uses video editing software such as Adobe Premiere Pro to change the amount of information and visual effects of the content according to the user's level of excitement. It provides detailed information to excited users and concise and engaging content to less excited users.

[0338] Ultimately, the generated content is either displayed to the user through their device or delivered at the appropriate time via email or other means. For example, by using a prompt such as "Generate engaging content based on customer sentiment data" to the generation AI model, it becomes possible to generate specific content. This process can improve the quality of the customer experience.

[0339] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0340] Step 1:

[0341] The server retrieves customer information. Inputs include customer attribute data from the customer management system, transaction history, and product usage. Using this data, the server generates a comprehensive customer profile. The output is a set of relevant customer information. This process provides a foundation for understanding customer needs.

[0342] Step 2:

[0343] The server analyzes the acquired customer information. The input is the output from step 1, and the data is analyzed using machine learning models such as TensorFlow and PyTorch. Data processing involves feature selection and data clustering to extract hidden patterns and latent customer needs. The output is the analysis results regarding the customer's hidden needs. This allows for the suggestion of customizable content for each customer.

[0344] Step 3:

[0345] The device acquires user emotion data. Input includes the user's facial expressions and voice, collected via the camera and microphone. This data is used to analyze emotions in real time using OpenCV and voice analysis APIs. Data processing outputs numerical information representing the user's emotional state and level of engagement. This step allows for an understanding of the user's current emotional state.

[0346] Step 4:

[0347] The server adjusts the video content based on the analysis results and sentiment data. Inputs include the analysis results from step 2 and the sentiment data from step 3. Video editing software such as Adobe Premiere Pro is used to adjust the visual effects and amount of information in the content. For example, if the user is excited, a video rich in technical information is generated. The output is optimal video content tailored to the user's emotions.

[0348] Step 5:

[0349] The device displays or delivers the adjusted video content. The input is the video content generated in step 4. For display, it uses the device screen or is sent directly to the user via email, etc. As output, visually appealing content is delivered to the user at the appropriate time. This makes it possible to further capture the user's interest.

[0350] (Application Example 2)

[0351] 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."

[0352] Conventional video content distribution systems offered suggestions based solely on customer preferences, failing to optimize content to consider the emotional state of individual customers. Therefore, customers had to actively search for and select content to match their mood and emotional state at any given time, resulting in limited quality of suggestions. This created a need for a system capable of acquiring customers' real-time emotional states and dynamically adjusting and optimizing content accordingly.

[0353] 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.

[0354] In this invention, the server includes means for acquiring customer information, means for analyzing the acquired customer information and identifying the customer's potential needs, means for acquiring emotional data in real time from the user's facial expressions and voice, means for analyzing the acquired emotional data and dynamically adjusting and optimizing video content, and means for delivering the optimized video content to the customer. This makes it possible to provide personalized video content that takes into account the customer's real-time emotional state.

[0355] "Customer information" refers to all data related to customers, including attribute information, transaction history, and product usage history.

[0356] "Latent needs" refer to demands or desires that are not explicitly stated but are likely to be needed by customers in the future.

[0357] "Methods for acquiring emotional data in real time from facial expressions and voice" refers to technologies and devices that analyze a user's facial movements and voice tone to instantly grasp their current emotional state.

[0358] "Methods for analyzing emotional data and dynamically adjusting and optimizing video content" refers to technologies that, based on acquired emotional information, modify the content and structure of video content in real time to make it most suitable for the viewer.

[0359] "Means of delivering video content to customers" refers to the technologies and protocols used to transmit edited video to customers' viewing devices via the internet.

[0360] In this invention, both the server and the terminal work together to build the system. The server retrieves customer information from the company's own database and customer relationship management system, and analyzes this information using a machine learning model to identify the customer's potential needs. Specifically, it utilizes machine learning frameworks such as TensorFlow to learn from past transaction history and customer attributes, and performs analysis to predict future needs.

[0361] Meanwhile, the device is equipped with a camera and microphone to capture the user's facial expressions and voice in real time. This data is analyzed using image processing libraries such as OpenCV and the Google Cloud Speech-to-Text API to determine the user's current emotional state. The analyzed emotional data is sent to a server, which then dynamically adjusts the video content.

[0362] The generated content is delivered from the server to the device and optimized in real time. Specifically, when the user is relaxed, content with a storyline or relaxing videos is selected.

[0363] In this way, the system can provide content that is most suitable to the user's mood and state at that time. Furthermore, by using generative AI models, video content can generate even more detailed and personalized suggestions.

[0364] A concrete example of its use is using this system on a smartphone during a commute. One could watch yoga videos to relax in the morning or music videos to boost energy. An example of a prompt message in this scenario would be, "Please suggest videos that match my current mood."

[0365] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0366] Step 1:

[0367] The server retrieves customer information from the company's database and customer relationship management system. Inputs include customer IDs and transaction history from the database, while outputs include customer attribute information and past purchase history, which form the basis for analysis.

[0368] Step 2:

[0369] The server analyzes acquired customer information using a machine learning model. The input includes customer attribute information and purchase history, and based on this, it performs data processing and calculations to predict potential needs. The output is a list of potential needs for each customer.

[0370] Step 3:

[0371] The device uses its built-in camera and microphone to acquire the user's facial expressions and voice data in real time. The input is real-time data of the user's face and voice, and the output is raw data for sentiment analysis.

[0372] Step 4:

[0373] The device analyzes emotions from facial and voice data acquired in real time using OpenCV and the Google Cloud Speech-to-Text API. The input is the raw data acquired beforehand, and data processing and calculations are performed on this data to determine the emotional state. The output is data indicating the user's current emotional state.

[0374] Step 5:

[0375] The server dynamically adjusts and optimizes video content based on analyzed emotional data and potential needs. The input consists of emotional state data and a list of potential needs, and the server performs data calculations for content adjustment and optimization. The output is a list of video content optimized for the user's current state.

[0376] Step 6:

[0377] The server delivers optimized video content to the device. The input is a list of video content, and the output is content viewable on the user's device. This allows the user to watch the most suitable content according to their mood at the time.

[0378] 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.

[0379] 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.

[0380] 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.

[0381] [Third Embodiment]

[0382] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0383] 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.

[0384] 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).

[0385] 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.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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.

[0391] 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.

[0392] 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.

[0393] 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".

[0394] This invention is a system designed to streamline and improve the accuracy of product and service proposals for corporate clients. The system consists of multiple operating modules, each performing a specific function.

[0395] The core of the system is the customer information collection and analysis function. First, the server accesses the company's database and automatically retrieves customer-related information. This includes past transaction history and data on the customer's business needs, industry, and size.

[0396] Next, the server analyzes the acquired customer information and uses a machine learning model to identify the customer's potential needs and interests. The machine learning model used here compares the customer's past behavior patterns with current industry trends to predict future needs.

[0397] Next, the user (sales representative) uses the device to request the generation of a video proposal for a specific customer. This request includes specific proposal content and points to focus on. For example, they might request a "proposal regarding the latest security solutions."

[0398] Upon receiving this request, the server uses a generative AI model to automatically generate personalized video content based on the customer's specific needs and relevant information. The generated video visually incorporates sections designed to capture the customer's interest and clearly demonstrates the specific benefits of the solution.

[0399] The generated video content is delivered to the user via their device. Users can utilize this video in business negotiations and presentations, and also distribute it to customers via email. This email is integrated with the CRM system to ensure it reaches customers at the appropriate time.

[0400] This invention significantly improves sales efficiency and enhances the quality and relevance of information provided to customers. For example, when proposing a new cloud solution to Company A, the system considers Company A's industry trends and past challenges, and generates a video presenting the optimal solution. This maximizes the potential of sales activities and improves customer satisfaction.

[0401] The following describes the processing flow.

[0402] Step 1:

[0403] The server connects to the company's database and CRM system to collect comprehensive data about customers. This data includes information about the customer's industry, annual revenue, past transaction history, purchased products and services, and the customer's contact person.

[0404] Step 2:

[0405] The server retrieves the latest industry news and trends from external sources and industry databases. It utilizes external APIs and feeds to collect noteworthy topics and technological trends in the customer's industry.

[0406] Step 3:

[0407] The server analyzes collected customer information and industry trends. It utilizes machine learning models to predict customers' potential needs and problems they need solving. This process identifies customer interests and priorities.

[0408] Step 4:

[0409] The user enters a request from their terminal to create a proposal for a specific customer. They specify the details of the proposal (e.g., security solutions) and the points to focus on.

[0410] Step 5:

[0411] The server uses a generative AI model to generate customized video content based on requests. The generated videos include suggestions and product benefits optimized for the customer's characteristics.

[0412] Step 6:

[0413] The device displays the generated video content to the user. The user can review this video and make adjustments as needed.

[0414] Step 7:

[0415] Users utilize videos generated during sales meetings and presentations as a sales tool. They also prepare these videos for distribution via email and customer-facing online platforms.

[0416] Step 8:

[0417] The server schedules and manages video delivery to customers, integrating with the CRM system to send videos to customers via email at the appropriate time. This delivery automatically tracks customer responses and accumulates information that can be used for future proposals.

[0418] (Example 1)

[0419] 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."

[0420] Traditional sales support systems have had the problem of difficulty in accurately understanding customers' potential needs and providing appropriate information based on those needs. Furthermore, the personalization of the content provided was insufficient, limiting the effectiveness of proposals to customers. Therefore, improving the efficiency of sales activities and enhancing customer satisfaction are key challenges.

[0421] 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.

[0422] In this invention, the server includes means for acquiring customer information, means for identifying the customer's potential needs, and means for automatically generating video content using a generative artificial intelligence model. This enables the automatic generation and distribution of personalized content based on customer needs.

[0423] "Customer information" refers to data related to customers, such as transaction history, business details, business needs, industry, and size, involving corporations and individuals.

[0424] "Latent needs" are requirements or concerns that customers may have in the future but are not currently apparent.

[0425] A "generative artificial intelligence model" is a model based on machine learning or deep learning that is used to generate content tailored to customer needs based on large amounts of data.

[0426] "Personalized video content" refers to individually tailored video content that is specifically designed to meet the needs and interests of a particular customer.

[0427] An "information processing device" is a device that includes hardware and software for collecting, analyzing, processing, and outputting data.

[0428] "Industry trends" refer to current and anticipated changes and developments regarding products and services observed within a particular market or industry.

[0429] The system of this invention aims to efficiently propose products and services to corporate clients and to improve the accuracy of such proposals. This system is realized through a process of collecting and analyzing customer information and generating personalized video content based on that information.

[0430] The server accesses its own database to retrieve customer information. This uses a database management system, such as one for manipulating SQL or NoSQL databases. The collected information includes past transaction history, business needs, industry, and size data. This data is cached on the server and prepared for analysis.

[0431] Next, the server analyzes cached customer information using a machine learning model. Python is used as the specific programming language, and the learning model is executed using frameworks such as Scikit-learn and TensorFlow. This model takes into account past behavioral patterns and industry trend information to identify customers' latent needs.

[0432] Users send requests from their devices to the server to generate video proposals for specific customers for use in sales activities. These requests include details such as the product type, proposal content, and key points to focus on. For example, a prompt might read, "Generate a video proposal for a cloud solution that takes into account recent industry trends and past challenges at Company A."

[0433] The server uses generative AI models to automatically generate personalized videos based on prompts received from the user. OpenAI's GPT model and DALL-E are used to construct the scenarios. Video editing software such as Adobe Premiere Pro and Final Cut Pro are used to generate the videos.

[0434] Ultimately, the generated video content is delivered to the user via their device. Users can utilize this video in business negotiations and presentations, and can also distribute it to customers via email. Distribution is coordinated with the CRM system to ensure the video reaches customers at the appropriate time.

[0435] In this way, this system improves sales efficiency and enhances the quality and suitability of proposals.

[0436] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0437] Step 1:

[0438] The server connects to the company's database and retrieves customer information. The input here consists of commands, such as SQL queries, to extract the necessary customer data from the database. The server aggregates data such as the customer's past transaction history, business needs, industry, and size, and stores it in a cache as structured data. This prepares the dataset for analysis.

[0439] Step 2:

[0440] The server analyzes customer information using machine learning algorithms. The input data is customer information obtained in Step 1, and the output is insights that indicate the customer's potential needs. Predictive analysis is performed using the Python language and frameworks such as Scikit-learn and TensorFlow, taking into account past behavioral patterns and industry trends. This analysis identifies the customer's future needs.

[0441] Step 3:

[0442] The user uses their device to request the generation of video proposals for a specific customer. The input is a prompt message set by the user, containing information such as "specific product proposal details" and "technologies to focus on." The device sends this prompt message to the server. This prompt also reflects the customer analysis results.

[0443] Step 4:

[0444] The server automatically generates personalized video content based on user prompts using a generative AI model. The AI ​​model receives prompts and customer needs analysis as input and generates video scenarios and scripts as output. Tools used include the GPT model and DALL-E. Based on this script, a visually appealing video is created via video editing software.

[0445] Step 5:

[0446] The server converts the generated video into a digital format and sends it to the terminal. The output is a streamable video file that the user can receive and use in business negotiations and presentations. This also allows the user to email the video to customers at the appropriate time, maximizing its effectiveness through the CRM system.

[0447] (Application Example 1)

[0448] 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."

[0449] In today's B2B market, there is a demand for the rapid generation and timely delivery of effective visual media content tailored to individual customer needs. However, traditional methods struggle to accurately identify customers' latent needs and efficiently deliver video content that considers industry trends. Furthermore, distributing content across diverse platforms using different communication methods requires manual adjustments, resulting in inefficiency. Solving these problems will enable more accurate and rapid customer service.

[0450] 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.

[0451] In this invention, the server includes means for acquiring customer-related information, means for analyzing the acquired customer-related information and identifying customer demand, means for automatically generating visual media content based on the identified demand, and means for distributing the generated visual media content through social infrastructure. This makes it possible to efficiently generate personalized visual media content tailored to each customer and deliver it at the appropriate time.

[0452] "Customer-related information" refers to information about customers, such as their attributes, past behavioral patterns, and usage history.

[0453] "Demand" refers to the potential interests and needs of customers regarding products and services.

[0454] "Visual media content" refers to a collection of information that is conveyed visually, including videos and graphics.

[0455] "Social infrastructure" refers to a wide range of communication infrastructure, including the internet and mobile networks.

[0456] "Machine learning techniques" refer to algorithms and technologies that learn patterns and trends from data to make future predictions and classifications.

[0457] "Industry trends" refer to the latest trends and innovations in a particular industry or market.

[0458] This invention is a system designed to improve the efficiency of proposing products and services to corporate clients. The system primarily consists of a server and various terminals, and is responsible for acquiring and analyzing customer-related information, and generating and distributing visual media content.

[0459] The server retrieves customer-related information from a database and analyzes it using machine learning techniques. Specifically, it uses machine learning software such as TensorFlow to predict future demand based on past customer behavior patterns. Meanwhile, it automatically generates personalized visual media content based on specific demands by using generative AI models (e.g., OpenAI's GPT-4). This allows for the rapid creation of visual media that captures customer interest.

[0460] The generated visual media content is delivered to the user via their device. Users utilize this content in business negotiations, presentations, or for distribution to social infrastructure via email. At this stage in particular, trends and past challenges in the customer's industry are considered, enabling customized proposals.

[0461] As a concrete example, when proposing a new health-oriented product to the food industry, this system can analyze the customer's past purchase history and local consumption trends to generate content containing the most appealing elements. This process is achieved when the server sends prompts such as "Customer Information: Food Industry, Past Issues: Low Interest in Health-Oriented Products, New Proposal: Healthy Snack Product" to the AI ​​model, which then receives a prompt message such as "Generate an advertising video that highlights the features of the new health-oriented snack product and how it differentiates itself from conventional products."

[0462] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0463] Step 1:

[0464] The server retrieves customer-related information from the database. Inputs include customer ID and transaction history, and based on this, it extracts customer attributes and past purchase data. The output is a set of customer-related information that can be analyzed.

[0465] Step 2:

[0466] The server analyzes the acquired customer-related information using machine learning techniques such as TensorFlow. The input is the customer-related information acquired in step 1, and the data processing involves feature extraction and normalization. The output is predictive data regarding the customer's potential demand and interests.

[0467] Step 3:

[0468] The server generates and sends a specific prompt to the generative AI model. The input is the prediction data from step 2, which generates a specific prompt: "Customer information: Food industry, Past challenges: Low interest in health-oriented products, New proposal: Healthy snack products". The output is passed to the generative AI model as a prompt.

[0469] Step 4:

[0470] The generative AI model generates personalized visual media content based on prompt text. The input is the prompt text from step 3, and the data calculation involves content generation using natural language processing. The output is video content highlighting the features of a new health-conscious snack product.

[0471] Step 5:

[0472] The device provides the user with the generated visual media content. The input is the video content generated in step 4, which the user can then use in presentations or emails. The output is visually compelling content designed to support business decision-making.

[0473] Step 6:

[0474] Users utilize content generated via their devices to conduct sales activities with customers. The input is the video content from step 5, and specific actions include showing the content to customers and distributing it through various platforms. The output is the implementation of effective customer proposals and the generation of high customer interest.

[0475] 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.

[0476] This invention is a system that recognizes user emotions and personalizes and optimizes suggested content. The system consists of the following main modules:

[0477] First, the server retrieves basic customer information from the company's database and CRM system. This information includes past transaction history, customer attributes, and past product usage data. It also retrieves the latest industry trends and market developments from external sources. This allows for a comprehensive understanding of the customer's current situation.

[0478] The server analyzes this information using machine learning models to extract customers' latent needs. This makes it possible to generate customized video content for each customer, going beyond generic suggestions.

[0479] In addition, this system employs an emotion engine. The terminal acquires emotion data in real time from the user's facial expressions and voice. This emotion data is used to measure the user's level of engagement and response.

[0480] The server adjusts the generated video content based on analysis by the emotion engine. For example, if the user is excited, the video will be adjusted to provide more detailed and advanced technical information. Conversely, if the user is not excited, it will select concise and visually appealing content to capture their interest.

[0481] For example, when a user requires a security solution, the system generates a proposal that takes into account the company's past incident information and industry security risks. In this process, the number and details of success stories included in the proposal can be dynamically adjusted based on the user's emotional state.

[0482] Ultimately, the generated content is displayed on a terminal as a support tool for sales activities, or delivered to customers via email at the appropriate time. In this way, the present invention makes it possible to achieve advanced personalization utilizing emotional data and significantly improve the quality of customer interactions.

[0483] The following describes the processing flow.

[0484] Step 1:

[0485] The server retrieves customer information from the company's database and CRM system. This information includes basic customer attributes, past transaction history, and product usage.

[0486] Step 2:

[0487] The server collects industry trends and the latest market developments via external APIs. This includes news articles and information on innovative technologies related to the customer's industry.

[0488] Step 3:

[0489] The server analyzes collected customer information and industry data using machine learning models to identify customers' potential needs and interests. This analysis provides the foundational data for making personalized recommendations to customers.

[0490] Step 4:

[0491] The user uses their device to enter a request to generate a suggestion video for a specific customer. The request includes the product to be suggested and the segment to focus on.

[0492] Step 5:

[0493] The server uses a generative AI model to automatically generate video content based on analysis results and user requests. This video incorporates appropriate suggestions, relevant product benefits, and visual elements.

[0494] Step 6:

[0495] The device provides the generated video to the user, who then reviews the video's content, and the device also collects emotional data in real time from the user's facial expressions and voice.

[0496] Step 7:

[0497] The server analyzes emotional data collected using an emotion engine and dynamically adjusts video content according to the user's emotional state. For example, if the user's reaction is positive, detailed technical information is added; if it is negative, simplified information is provided.

[0498] Step 8:

[0499] Users prepare to use the edited videos in business negotiations and other settings, and to distribute the video content to customers via email and online platforms.

[0500] Step 9:

[0501] The server manages the video distribution schedule and integrates with the CRM system to deliver videos to customers at the optimal time. After distribution, it collects customer viewing data and feedback to help improve future sales activities.

[0502] (Example 2)

[0503] 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."

[0504] Traditional customer service systems struggle to fully grasp overall needs and individual preferences simply by analyzing acquired customer information, making it difficult to provide customers with the most suitable content. Furthermore, the lack of interactive personalization utilizing emotional data makes it challenging to increase customer engagement.

[0505] 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.

[0506] In this invention, the server includes means for acquiring customer information, means for analyzing the acquired customer information to identify the customer's hidden needs, means for acquiring emotional data to measure user preferences, means for adjusting video content to reflect those preferences, and means for transmitting the generated and adjusted video content to the customer. This enables accurate understanding of the customer's hidden needs and the provision of personalized content utilizing emotional data.

[0507] "Customer information" refers to information used to understand customer behavior and characteristics, such as attribute information, transaction history, and past product usage.

[0508] "Analysis" is the process of extracting hidden requirements and patterns from acquired data and transforming them into meaningful information.

[0509] "Emotional data" refers to information that indicates a user's emotional state, obtained based on the user's facial expressions and voice.

[0510] "Video content" refers to dynamic visual and auditory works created to convey information to users.

[0511] "Adjusting" refers to the process of changing or optimizing content or its presentation to meet a specific goal.

[0512] "Communicating" means delivering generated or adapted content to customers using appropriate means.

[0513] "Trends" refer to information that describes the current state or future predictions in a particular field.

[0514] Embodiments of the present invention are systems that generate and provide personalized video content to customers by utilizing customer information and sentiment data. This system mainly includes a server and terminals.

[0515] The server first acquires customer information. This information is collected from the company's customer management system and databases and includes customer attributes, transaction history, and past product usage data. It also obtains industry trends and the latest market information from external sources to comprehensively understand the customer's situation. This information is analyzed using machine learning models such as TensorFlow and PyTorch, and the data is processed to extract hidden customer requests and potential needs.

[0516] In parallel, the device acquires user emotion data in real time. This utilizes hardware such as the camera and microphone, and employs OpenCV and speech analysis APIs to extract emotions from the user's facial expressions and voice. The acquired emotion data is used to measure user preferences and personalize content.

[0517] The server dynamically adjusts video content based on customer requests and sentiment data obtained from machine learning models. Specifically, it uses video editing software such as Adobe Premiere Pro to change the amount of information and visual effects of the content according to the user's level of excitement. It provides detailed information to excited users and concise and engaging content to less excited users.

[0518] Ultimately, the generated content is either displayed to the user through their device or delivered at the appropriate time via email or other means. For example, by using a prompt such as "Generate engaging content based on customer sentiment data" to the generation AI model, it becomes possible to generate specific content. This process can improve the quality of the customer experience.

[0519] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0520] Step 1:

[0521] The server retrieves customer information. Inputs include customer attribute data from the customer management system, transaction history, and product usage. Using this data, the server generates a comprehensive customer profile. The output is a set of relevant customer information. This process provides a foundation for understanding customer needs.

[0522] Step 2:

[0523] The server analyzes the acquired customer information. The input is the output from step 1, and the data is analyzed using machine learning models such as TensorFlow and PyTorch. Data processing involves feature selection and data clustering to extract hidden patterns and latent customer needs. The output is the analysis results regarding the customer's hidden needs. This allows for the suggestion of customizable content for each customer.

[0524] Step 3:

[0525] The device acquires user emotion data. Input includes the user's facial expressions and voice, collected via the camera and microphone. This data is used to analyze emotions in real time using OpenCV and voice analysis APIs. Data processing outputs numerical information representing the user's emotional state and level of engagement. This step allows for an understanding of the user's current emotional state.

[0526] Step 4:

[0527] The server adjusts the video content based on the analysis results and sentiment data. Inputs include the analysis results from step 2 and the sentiment data from step 3. Video editing software such as Adobe Premiere Pro is used to adjust the visual effects and amount of information in the content. For example, if the user is excited, a video rich in technical information is generated. The output is optimal video content tailored to the user's emotions.

[0528] Step 5:

[0529] The device displays or delivers the adjusted video content. The input is the video content generated in step 4. For display, it uses the device screen or is sent directly to the user via email, etc. As output, visually appealing content is delivered to the user at the appropriate time. This makes it possible to further capture the user's interest.

[0530] (Application Example 2)

[0531] 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."

[0532] Conventional video content distribution systems offered suggestions based solely on customer preferences, failing to optimize content to consider the emotional state of individual customers. Therefore, customers had to actively search for and select content to match their mood and emotional state at any given time, resulting in limited quality of suggestions. This created a need for a system capable of acquiring customers' real-time emotional states and dynamically adjusting and optimizing content accordingly.

[0533] 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.

[0534] In this invention, the server includes means for acquiring customer information, means for analyzing the acquired customer information and identifying the customer's potential needs, means for acquiring emotional data in real time from the user's facial expressions and voice, means for analyzing the acquired emotional data and dynamically adjusting and optimizing video content, and means for delivering the optimized video content to the customer. This makes it possible to provide personalized video content that takes into account the customer's real-time emotional state.

[0535] "Customer information" refers to all data related to customers, including attribute information, transaction history, and product usage history.

[0536] "Latent needs" refer to demands or desires that are not explicitly stated but are likely to be needed by customers in the future.

[0537] "Methods for acquiring emotional data in real time from facial expressions and voice" refers to technologies and devices that analyze a user's facial movements and voice tone to instantly grasp their current emotional state.

[0538] "Methods for analyzing emotional data and dynamically adjusting and optimizing video content" refers to technologies that, based on acquired emotional information, modify the content and structure of video content in real time to make it most suitable for the viewer.

[0539] "Means of delivering video content to customers" refers to the technologies and protocols used to transmit edited video to customers' viewing devices via the internet.

[0540] In this invention, both the server and the terminal work together to build the system. The server retrieves customer information from the company's own database and customer relationship management system, and analyzes this information using a machine learning model to identify the customer's potential needs. Specifically, it utilizes machine learning frameworks such as TensorFlow to learn from past transaction history and customer attributes, and performs analysis to predict future needs.

[0541] Meanwhile, the device is equipped with a camera and microphone to capture the user's facial expressions and voice in real time. This data is analyzed using image processing libraries such as OpenCV and the Google Cloud Speech-to-Text API to determine the user's current emotional state. The analyzed emotional data is sent to a server, which then dynamically adjusts the video content.

[0542] The generated content is delivered from the server to the device and optimized in real time. Specifically, when the user is relaxed, content with a storyline or relaxing videos is selected.

[0543] In this way, the system can provide content that is most suitable to the user's mood and state at that time. Furthermore, by using generative AI models, video content can generate even more detailed and personalized suggestions.

[0544] A concrete example of its use is using this system on a smartphone during a commute. One could watch yoga videos to relax in the morning or music videos to boost energy. An example of a prompt message in this scenario would be, "Please suggest videos that match my current mood."

[0545] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0546] Step 1:

[0547] The server retrieves customer information from the company's database and customer relationship management system. Inputs include customer IDs and transaction history from the database, while outputs include customer attribute information and past purchase history, which form the basis for analysis.

[0548] Step 2:

[0549] The server analyzes acquired customer information using a machine learning model. The input includes customer attribute information and purchase history, and based on this, it performs data processing and calculations to predict potential needs. The output is a list of potential needs for each customer.

[0550] Step 3:

[0551] The device uses its built-in camera and microphone to acquire the user's facial expressions and voice data in real time. The input is real-time data of the user's face and voice, and the output is raw data for sentiment analysis.

[0552] Step 4:

[0553] The device analyzes emotions from facial and voice data acquired in real time using OpenCV and the Google Cloud Speech-to-Text API. The input is the raw data acquired beforehand, and data processing and calculations are performed on this data to determine the emotional state. The output is data indicating the user's current emotional state.

[0554] Step 5:

[0555] The server dynamically adjusts and optimizes video content based on analyzed emotional data and potential needs. The input consists of emotional state data and a list of potential needs, and the server performs data calculations for content adjustment and optimization. The output is a list of video content optimized for the user's current state.

[0556] Step 6:

[0557] The server delivers optimized video content to the device. The input is a list of video content, and the output is content viewable on the user's device. This allows the user to watch the most suitable content according to their mood at the time.

[0558] 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.

[0559] 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.

[0560] 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.

[0561] [Fourth Embodiment]

[0562] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0563] 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.

[0564] 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).

[0565] 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.

[0566] 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.

[0567] 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).

[0568] 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.

[0569] 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.

[0570] 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.

[0571] 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.

[0572] 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.

[0573] 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.

[0574] 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".

[0575] This invention is a system designed to streamline and improve the accuracy of product and service proposals for corporate clients. The system consists of multiple operating modules, each performing a specific function.

[0576] The core of the system is the customer information collection and analysis function. First, the server accesses the company's database and automatically retrieves customer-related information. This includes past transaction history and data on the customer's business needs, industry, and size.

[0577] Next, the server analyzes the acquired customer information and uses a machine learning model to identify the customer's potential needs and interests. The machine learning model used here compares the customer's past behavior patterns with current industry trends to predict future needs.

[0578] Next, the user (sales representative) uses the device to request the generation of a video proposal for a specific customer. This request includes specific proposal content and points to focus on. For example, they might request a "proposal regarding the latest security solutions."

[0579] Upon receiving this request, the server uses a generative AI model to automatically generate personalized video content based on the customer's specific needs and relevant information. The generated video visually incorporates sections designed to capture the customer's interest and clearly demonstrates the specific benefits of the solution.

[0580] The generated video content is delivered to the user via their device. Users can utilize this video in business negotiations and presentations, and also distribute it to customers via email. This email is integrated with the CRM system to ensure it reaches customers at the appropriate time.

[0581] This invention significantly improves sales efficiency and enhances the quality and relevance of information provided to customers. For example, when proposing a new cloud solution to Company A, the system considers Company A's industry trends and past challenges, and generates a video presenting the optimal solution. This maximizes the potential of sales activities and improves customer satisfaction.

[0582] The following describes the processing flow.

[0583] Step 1:

[0584] The server connects to the company's database and CRM system to collect comprehensive data about customers. This data includes information about the customer's industry, annual revenue, past transaction history, purchased products and services, and the customer's contact person.

[0585] Step 2:

[0586] The server retrieves the latest industry news and trends from external sources and industry databases. It utilizes external APIs and feeds to collect noteworthy topics and technological trends in the customer's industry.

[0587] Step 3:

[0588] The server analyzes collected customer information and industry trends. It utilizes machine learning models to predict customers' potential needs and problems they need solving. This process identifies customer interests and priorities.

[0589] Step 4:

[0590] The user enters a request from their terminal to create a proposal for a specific customer. They specify the details of the proposal (e.g., security solutions) and the points to focus on.

[0591] Step 5:

[0592] The server uses a generative AI model to generate customized video content based on requests. The generated videos include suggestions and product benefits optimized for the customer's characteristics.

[0593] Step 6:

[0594] The device displays the generated video content to the user. The user can review this video and make adjustments as needed.

[0595] Step 7:

[0596] Users utilize videos generated during sales meetings and presentations as a sales tool. They also prepare these videos for distribution via email and customer-facing online platforms.

[0597] Step 8:

[0598] The server schedules and manages video delivery to customers, integrating with the CRM system to send videos to customers via email at the appropriate time. This delivery automatically tracks customer responses and accumulates information that can be used for future proposals.

[0599] (Example 1)

[0600] 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".

[0601] Traditional sales support systems have had the problem of difficulty in accurately understanding customers' potential needs and providing appropriate information based on those needs. Furthermore, the personalization of the content provided was insufficient, limiting the effectiveness of proposals to customers. Therefore, improving the efficiency of sales activities and enhancing customer satisfaction are key challenges.

[0602] 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.

[0603] In this invention, the server includes means for acquiring customer information, means for identifying the customer's potential needs, and means for automatically generating video content using a generative artificial intelligence model. This enables the automatic generation and distribution of personalized content based on customer needs.

[0604] "Customer information" refers to data related to customers, such as transaction history, business details, business needs, industry, and size, involving corporations and individuals.

[0605] "Latent needs" are requirements or concerns that customers may have in the future but are not currently apparent.

[0606] A "generative artificial intelligence model" is a model based on machine learning or deep learning that is used to generate content tailored to customer needs based on large amounts of data.

[0607] "Personalized video content" refers to individually tailored video content that is specifically designed to meet the needs and interests of a particular customer.

[0608] An "information processing device" is a device that includes hardware and software for collecting, analyzing, processing, and outputting data.

[0609] "Industry trends" refer to current and anticipated changes and developments regarding products and services observed within a particular market or industry.

[0610] The system of this invention aims to efficiently propose products and services to corporate clients and to improve the accuracy of such proposals. This system is realized through a process of collecting and analyzing customer information and generating personalized video content based on that information.

[0611] The server accesses its own database to retrieve customer information. This uses a database management system, such as one for manipulating SQL or NoSQL databases. The collected information includes past transaction history, business needs, industry, and size data. This data is cached on the server and prepared for analysis.

[0612] Next, the server analyzes cached customer information using a machine learning model. Python is used as the specific programming language, and the learning model is executed using frameworks such as Scikit-learn and TensorFlow. This model takes into account past behavioral patterns and industry trend information to identify customers' latent needs.

[0613] Users send requests from their devices to the server to generate video proposals for specific customers for use in sales activities. These requests include details such as the product type, proposal content, and key points to focus on. For example, a prompt might read, "Generate a video proposal for a cloud solution that takes into account recent industry trends and past challenges at Company A."

[0614] The server uses generative AI models to automatically generate personalized videos based on prompts received from the user. OpenAI's GPT model and DALL-E are used to construct the scenarios. Video editing software such as Adobe Premiere Pro and Final Cut Pro are used to generate the videos.

[0615] Ultimately, the generated video content is delivered to the user via their device. Users can utilize this video in business negotiations and presentations, and can also distribute it to customers via email. Distribution is coordinated with the CRM system to ensure the video reaches customers at the appropriate time.

[0616] In this way, this system improves sales efficiency and enhances the quality and suitability of proposals.

[0617] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0618] Step 1:

[0619] The server connects to the company's database and retrieves customer information. The input here consists of commands, such as SQL queries, to extract the necessary customer data from the database. The server aggregates data such as the customer's past transaction history, business needs, industry, and size, and stores it in a cache as structured data. This prepares the dataset for analysis.

[0620] Step 2:

[0621] The server analyzes customer information using machine learning algorithms. The input data is customer information obtained in Step 1, and the output is insights that indicate the customer's potential needs. Predictive analysis is performed using the Python language and frameworks such as Scikit-learn and TensorFlow, taking into account past behavioral patterns and industry trends. This analysis identifies the customer's future needs.

[0622] Step 3:

[0623] The user uses their device to request the generation of video proposals for a specific customer. The input is a prompt message set by the user, containing information such as "specific product proposal details" and "technologies to focus on." The device sends this prompt message to the server. This prompt also reflects the customer analysis results.

[0624] Step 4:

[0625] The server automatically generates personalized video content based on user prompts using a generative AI model. The AI ​​model receives prompts and customer needs analysis as input and generates video scenarios and scripts as output. Tools used include the GPT model and DALL-E. Based on this script, a visually appealing video is created via video editing software.

[0626] Step 5:

[0627] The server converts the generated video into a digital format and sends it to the terminal. The output is a streamable video file that the user can receive and use in business negotiations and presentations. This also allows the user to email the video to customers at the appropriate time, maximizing its effectiveness through the CRM system.

[0628] (Application Example 1)

[0629] 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".

[0630] In today's B2B market, there is a demand for the rapid generation and timely delivery of effective visual media content tailored to individual customer needs. However, traditional methods struggle to accurately identify customers' latent needs and efficiently deliver video content that considers industry trends. Furthermore, distributing content across diverse platforms using different communication methods requires manual adjustments, resulting in inefficiency. Solving these problems will enable more accurate and rapid customer service.

[0631] 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.

[0632] In this invention, the server includes means for acquiring customer-related information, means for analyzing the acquired customer-related information and identifying customer demand, means for automatically generating visual media content based on the identified demand, and means for distributing the generated visual media content through social infrastructure. This makes it possible to efficiently generate personalized visual media content tailored to each customer and deliver it at the appropriate time.

[0633] "Customer-related information" refers to information about customers, such as their attributes, past behavioral patterns, and usage history.

[0634] "Demand" refers to the potential interests and needs of customers regarding products and services.

[0635] "Visual media content" refers to a collection of information that is conveyed visually, including videos and graphics.

[0636] "Social infrastructure" refers to a wide range of communication infrastructure, including the internet and mobile networks.

[0637] "Machine learning techniques" refer to algorithms and technologies that learn patterns and trends from data to make future predictions and classifications.

[0638] "Industry trends" refer to the latest trends and innovations in a particular industry or market.

[0639] This invention is a system designed to improve the efficiency of proposing products and services to corporate clients. The system primarily consists of a server and various terminals, and is responsible for acquiring and analyzing customer-related information, and generating and distributing visual media content.

[0640] The server retrieves customer-related information from a database and analyzes it using machine learning techniques. Specifically, it uses machine learning software such as TensorFlow to predict future demand based on past customer behavior patterns. Meanwhile, it automatically generates personalized visual media content based on specific demands by using generative AI models (e.g., OpenAI's GPT-4). This allows for the rapid creation of visual media that captures customer interest.

[0641] The generated visual media content is delivered to the user via their device. Users utilize this content in business negotiations, presentations, or for distribution to social infrastructure via email. At this stage in particular, trends and past challenges in the customer's industry are considered, enabling customized proposals.

[0642] As a concrete example, when proposing a new health-oriented product to the food industry, this system can analyze the customer's past purchase history and local consumption trends to generate content containing the most appealing elements. This process is achieved when the server sends prompts such as "Customer Information: Food Industry, Past Issues: Low Interest in Health-Oriented Products, New Proposal: Healthy Snack Product" to the AI ​​model, which then receives a prompt message such as "Generate an advertising video that highlights the features of the new health-oriented snack product and how it differentiates itself from conventional products."

[0643] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0644] Step 1:

[0645] The server retrieves customer-related information from the database. Inputs include customer ID and transaction history, and based on this, it extracts customer attributes and past purchase data. The output is a set of customer-related information that can be analyzed.

[0646] Step 2:

[0647] The server analyzes the acquired customer-related information using machine learning techniques such as TensorFlow. The input is the customer-related information acquired in step 1, and the data processing involves feature extraction and normalization. The output is predictive data regarding the customer's potential demand and interests.

[0648] Step 3:

[0649] The server generates and sends a specific prompt to the generative AI model. The input is the prediction data from step 2, which generates a specific prompt: "Customer information: Food industry, Past challenges: Low interest in health-oriented products, New proposal: Healthy snack products". The output is passed to the generative AI model as a prompt.

[0650] Step 4:

[0651] The generative AI model generates personalized visual media content based on prompt text. The input is the prompt text from step 3, and the data calculation involves content generation using natural language processing. The output is video content highlighting the features of a new health-conscious snack product.

[0652] Step 5:

[0653] The device provides the user with the generated visual media content. The input is the video content generated in step 4, which the user can then use in presentations or emails. The output is visually compelling content designed to support business decision-making.

[0654] Step 6:

[0655] Users utilize content generated via their devices to conduct sales activities with customers. The input is the video content from step 5, and specific actions include showing the content to customers and distributing it through various platforms. The output is the implementation of effective customer proposals and the generation of high customer interest.

[0656] 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.

[0657] This invention is a system that recognizes user emotions and personalizes and optimizes suggested content. The system consists of the following main modules:

[0658] First, the server retrieves basic customer information from the company's database and CRM system. This information includes past transaction history, customer attributes, and past product usage data. It also retrieves the latest industry trends and market developments from external sources. This allows for a comprehensive understanding of the customer's current situation.

[0659] The server analyzes this information using machine learning models to extract customers' latent needs. This makes it possible to generate customized video content for each customer, going beyond generic suggestions.

[0660] In addition, this system employs an emotion engine. The terminal acquires emotion data in real time from the user's facial expressions and voice. This emotion data is used to measure the user's level of engagement and response.

[0661] The server adjusts the generated video content based on analysis by the emotion engine. For example, if the user is excited, the video will be adjusted to provide more detailed and advanced technical information. Conversely, if the user is not excited, it will select concise and visually appealing content to capture their interest.

[0662] For example, when a user requires a security solution, the system generates a proposal that takes into account the company's past incident information and industry security risks. In this process, the number and details of success stories included in the proposal can be dynamically adjusted based on the user's emotional state.

[0663] Ultimately, the generated content is displayed on a terminal as a support tool for sales activities, or delivered to customers via email at the appropriate time. In this way, the present invention makes it possible to achieve advanced personalization utilizing emotional data and significantly improve the quality of customer interactions.

[0664] The following describes the processing flow.

[0665] Step 1:

[0666] The server retrieves customer information from the company's database and CRM system. This information includes basic customer attributes, past transaction history, and product usage.

[0667] Step 2:

[0668] The server collects industry trends and the latest market developments via external APIs. This includes news articles and information on innovative technologies related to the customer's industry.

[0669] Step 3:

[0670] The server analyzes collected customer information and industry data using machine learning models to identify customers' potential needs and interests. This analysis provides the foundational data for making personalized recommendations to customers.

[0671] Step 4:

[0672] The user uses their device to enter a request to generate a suggestion video for a specific customer. The request includes the product to be suggested and the segment to focus on.

[0673] Step 5:

[0674] The server uses a generative AI model to automatically generate video content based on analysis results and user requests. This video incorporates appropriate suggestions, relevant product benefits, and visual elements.

[0675] Step 6:

[0676] The device provides the generated video to the user, who then reviews the video's content, and the device also collects emotional data in real time from the user's facial expressions and voice.

[0677] Step 7:

[0678] The server analyzes emotional data collected using an emotion engine and dynamically adjusts video content according to the user's emotional state. For example, if the user's reaction is positive, detailed technical information is added; if it is negative, simplified information is provided.

[0679] Step 8:

[0680] Users prepare to use the edited videos in business negotiations and other settings, and to distribute the video content to customers via email and online platforms.

[0681] Step 9:

[0682] The server manages the video distribution schedule and integrates with the CRM system to deliver videos to customers at the optimal time. After distribution, it collects customer viewing data and feedback to help improve future sales activities.

[0683] (Example 2)

[0684] 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".

[0685] Traditional customer service systems struggle to fully grasp overall needs and individual preferences simply by analyzing acquired customer information, making it difficult to provide customers with the most suitable content. Furthermore, the lack of interactive personalization utilizing emotional data makes it challenging to increase customer engagement.

[0686] 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.

[0687] In this invention, the server includes means for acquiring customer information, means for analyzing the acquired customer information to identify the customer's hidden needs, means for acquiring emotional data to measure user preferences, means for adjusting video content to reflect those preferences, and means for transmitting the generated and adjusted video content to the customer. This enables accurate understanding of the customer's hidden needs and the provision of personalized content utilizing emotional data.

[0688] "Customer information" refers to information used to understand customer behavior and characteristics, such as attribute information, transaction history, and past product usage.

[0689] "Analysis" is the process of extracting hidden requirements and patterns from acquired data and transforming them into meaningful information.

[0690] "Emotional data" refers to information that indicates a user's emotional state, obtained based on the user's facial expressions and voice.

[0691] "Video content" refers to dynamic visual and auditory works created to convey information to users.

[0692] "Adjusting" refers to the process of changing or optimizing content or its presentation to meet a specific goal.

[0693] "Communicating" means delivering generated or adapted content to customers using appropriate means.

[0694] "Trends" refer to information that describes the current state or future predictions in a particular field.

[0695] Embodiments of the present invention are systems that generate and provide personalized video content to customers by utilizing customer information and sentiment data. This system mainly includes a server and terminals.

[0696] The server first acquires customer information. This information is collected from the company's customer management system and databases and includes customer attributes, transaction history, and past product usage data. It also obtains industry trends and the latest market information from external sources to comprehensively understand the customer's situation. This information is analyzed using machine learning models such as TensorFlow and PyTorch, and the data is processed to extract hidden customer requests and potential needs.

[0697] In parallel, the device acquires user emotion data in real time. This utilizes hardware such as the camera and microphone, and employs OpenCV and speech analysis APIs to extract emotions from the user's facial expressions and voice. The acquired emotion data is used to measure user preferences and personalize content.

[0698] The server dynamically adjusts video content based on customer requests and sentiment data obtained from machine learning models. Specifically, it uses video editing software such as Adobe Premiere Pro to change the amount of information and visual effects of the content according to the user's level of excitement. It provides detailed information to excited users and concise and engaging content to less excited users.

[0699] Ultimately, the generated content is either displayed to the user through their device or delivered at the appropriate time via email or other means. For example, by using a prompt such as "Generate engaging content based on customer sentiment data" to the generation AI model, it becomes possible to generate specific content. This process can improve the quality of the customer experience.

[0700] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0701] Step 1:

[0702] The server retrieves customer information. Inputs include customer attribute data from the customer management system, transaction history, and product usage. Using this data, the server generates a comprehensive customer profile. The output is a set of relevant customer information. This process provides a foundation for understanding customer needs.

[0703] Step 2:

[0704] The server analyzes the acquired customer information. The input is the output from step 1, and the data is analyzed using machine learning models such as TensorFlow and PyTorch. Data processing involves feature selection and data clustering to extract hidden patterns and latent customer needs. The output is the analysis results regarding the customer's hidden needs. This allows for the suggestion of customizable content for each customer.

[0705] Step 3:

[0706] The device acquires user emotion data. Input includes the user's facial expressions and voice, collected via the camera and microphone. This data is used to analyze emotions in real time using OpenCV and voice analysis APIs. Data processing outputs numerical information representing the user's emotional state and level of engagement. This step allows for an understanding of the user's current emotional state.

[0707] Step 4:

[0708] The server adjusts the video content based on the analysis results and sentiment data. Inputs include the analysis results from step 2 and the sentiment data from step 3. Video editing software such as Adobe Premiere Pro is used to adjust the visual effects and amount of information in the content. For example, if the user is excited, a video rich in technical information is generated. The output is optimal video content tailored to the user's emotions.

[0709] Step 5:

[0710] The device displays or delivers the adjusted video content. The input is the video content generated in step 4. For display, it uses the device screen or is sent directly to the user via email, etc. As output, visually appealing content is delivered to the user at the appropriate time. This makes it possible to further capture the user's interest.

[0711] (Application Example 2)

[0712] 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".

[0713] Conventional video content distribution systems offered suggestions based solely on customer preferences, failing to optimize content to consider the emotional state of individual customers. Therefore, customers had to actively search for and select content to match their mood and emotional state at any given time, resulting in limited quality of suggestions. This created a need for a system capable of acquiring customers' real-time emotional states and dynamically adjusting and optimizing content accordingly.

[0714] 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.

[0715] In this invention, the server includes means for acquiring customer information, means for analyzing the acquired customer information and identifying the customer's potential needs, means for acquiring emotional data in real time from the user's facial expressions and voice, means for analyzing the acquired emotional data and dynamically adjusting and optimizing video content, and means for delivering the optimized video content to the customer. This makes it possible to provide personalized video content that takes into account the customer's real-time emotional state.

[0716] "Customer information" refers to all data related to customers, including attribute information, transaction history, and product usage history.

[0717] "Latent needs" refer to demands or desires that are not explicitly stated but are likely to be needed by customers in the future.

[0718] "Methods for acquiring emotional data in real time from facial expressions and voice" refers to technologies and devices that analyze a user's facial movements and voice tone to instantly grasp their current emotional state.

[0719] "Methods for analyzing emotional data and dynamically adjusting and optimizing video content" refers to technologies that, based on acquired emotional information, modify the content and structure of video content in real time to make it most suitable for the viewer.

[0720] "Means of delivering video content to customers" refers to the technologies and protocols used to transmit edited video to customers' viewing devices via the internet.

[0721] In this invention, both the server and the terminal work together to build the system. The server retrieves customer information from the company's own database and customer relationship management system, and analyzes this information using a machine learning model to identify the customer's potential needs. Specifically, it utilizes machine learning frameworks such as TensorFlow to learn from past transaction history and customer attributes, and performs analysis to predict future needs.

[0722] Meanwhile, the device is equipped with a camera and microphone to capture the user's facial expressions and voice in real time. This data is analyzed using image processing libraries such as OpenCV and the Google Cloud Speech-to-Text API to determine the user's current emotional state. The analyzed emotional data is sent to a server, which then dynamically adjusts the video content.

[0723] The generated content is delivered from the server to the device and optimized in real time. Specifically, when the user is relaxed, content with a storyline or relaxing videos is selected.

[0724] In this way, the system can provide content that is most suitable to the user's mood and state at that time. Furthermore, by using generative AI models, video content can generate even more detailed and personalized suggestions.

[0725] A concrete example of its use is using this system on a smartphone during a commute. One could watch yoga videos to relax in the morning or music videos to boost energy. An example of a prompt message in this scenario would be, "Please suggest videos that match my current mood."

[0726] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0727] Step 1:

[0728] The server retrieves customer information from the company's database and customer relationship management system. Inputs include customer IDs and transaction history from the database, while outputs include customer attribute information and past purchase history, which form the basis for analysis.

[0729] Step 2:

[0730] The server analyzes acquired customer information using a machine learning model. The input includes customer attribute information and purchase history, and based on this, it performs data processing and calculations to predict potential needs. The output is a list of potential needs for each customer.

[0731] Step 3:

[0732] The device uses its built-in camera and microphone to acquire the user's facial expressions and voice data in real time. The input is real-time data of the user's face and voice, and the output is raw data for sentiment analysis.

[0733] Step 4:

[0734] The device analyzes emotions from facial and voice data acquired in real time using OpenCV and the Google Cloud Speech-to-Text API. The input is the raw data acquired beforehand, and data processing and calculations are performed on this data to determine the emotional state. The output is data indicating the user's current emotional state.

[0735] Step 5:

[0736] The server dynamically adjusts and optimizes video content based on analyzed emotional data and potential needs. The input consists of emotional state data and a list of potential needs, and the server performs data calculations for content adjustment and optimization. The output is a list of video content optimized for the user's current state.

[0737] Step 6:

[0738] The server delivers optimized video content to the device. The input is a list of video content, and the output is content viewable on the user's device. This allows the user to watch the most suitable content according to their mood at the time.

[0739] 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.

[0740] 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.

[0741] In the above embodiment, an example was given in which the 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.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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."

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] The following is further disclosed regarding the embodiments described above.

[0761] (Claim 1)

[0762] Means of obtaining customer information,

[0763] A means of analyzing acquired customer information to identify customer needs,

[0764] A means of automatically generating video content based on identified needs,

[0765] A means of distributing the generated video content to customers,

[0766] A system that includes this.

[0767] (Claim 2)

[0768] The system according to claim 1, which uses a machine learning model to analyze customer information.

[0769] (Claim 3)

[0770] The system according to claim 1, which obtains industry trends from external sources and reflects them in video content.

[0771] "Example 1"

[0772] (Claim 1)

[0773] Means of obtaining customer information,

[0774] A means of analyzing acquired customer information to identify customers' potential needs,

[0775] A means for automatically generating personalized video content using an artificial intelligence model based on identified needs,

[0776] A means of distributing generated video content to customers via the user's information processing device,

[0777] A system that includes this.

[0778] (Claim 2)

[0779] The system according to claim 1, which uses a machine learning model to analyze customer information and predicts needs based on past behavioral patterns and external information.

[0780] (Claim 3)

[0781] The system according to claim 1, which acquires external information, including industry trends, and reflects it in video content.

[0782] "Application Example 1"

[0783] (Claim 1)

[0784] Means of obtaining customer-related information,

[0785] A means of analyzing acquired customer-related information to identify customer demand,

[0786] A means for automatically generating visual media content based on identified demand,

[0787] Means for distributing generated visual media content through social infrastructure,

[0788] A system that includes this.

[0789] (Claim 2)

[0790] The system according to claim 1, which uses machine learning techniques to analyze customer-related information.

[0791] (Claim 3)

[0792] The system according to claim 1, which obtains industry trends from external information sources and reflects them in visual media content.

[0793] "Example 2 of combining an emotion engine"

[0794] (Claim 1)

[0795] Means of obtaining customer information,

[0796] A means of analyzing acquired customer information to identify hidden customer needs,

[0797] A means of acquiring sentiment data to measure user preferences,

[0798] A means of adjusting video content to reflect preferences,

[0799] A means of delivering generated and adjusted video content to customers,

[0800] A system that includes this.

[0801] (Claim 2)

[0802] The system according to claim 1, which dynamically converts video content based on acquired emotion data.

[0803] (Claim 3)

[0804] The system according to claim 1, which obtains trends from external information sources and applies them to video content.

[0805] "Application example 2 when combining with an emotional engine"

[0806] (Claim 1)

[0807] Means of obtaining customer information,

[0808] A means of analyzing acquired customer information to identify customers' potential needs,

[0809] Based on identified needs, a means of acquiring emotional data in real time from the user's facial expressions and voice,

[0810] A means of analyzing acquired emotional data and dynamically adjusting and optimizing video content,

[0811] A means of delivering optimized video content to customers,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, which uses a machine learning model to analyze customer information and sentiment data.

[0815] (Claim 3)

[0816] The system according to claim 1, which obtains market trends from external sources and reflects them in video content based on sentiment data. [Explanation of symbols]

[0817] 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 obtaining customer-related information, A means of analyzing acquired customer-related information to identify customer demand, A means for automatically generating visual media content based on identified demand, Means for distributing generated visual media content through social infrastructure, A system that includes this.

2. The system according to claim 1, which uses a machine learning method for analyzing customer-related information.

3. The system according to claim 1, which obtains industry trends from external information sources and reflects them in visual media content.

Images