system

Abstract

We provide the system. [Solution] A means of registering information about each company's problems in a database, A means of registering product information in a database, A means for calculating the correlation between the aforementioned problem information and the aforementioned product information using a generative AI model that analyzes the aforementioned problem information and the aforementioned product information, Based on the aforementioned correlation, a means of notifying prospective companies of the proposal content, In response to the aforementioned notification, a means by which prospective companies can send a "Like", A system that includes means for providing the sales company with the contact information of the prospective company when it receives the aforementioned "Like".

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 performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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] Telemarketing is a method used by many companies when aiming to expand customers and improve business efficiency, but the current success rate is very low. The reasons include the psychological barrier of "unknown = reject" and the fact that the proposed content cannot be accepted. The present invention aims to achieve efficient and effective matching between potential companies and sales-side companies and significantly improve the success rate of telemarketing.

Means for Solving the Problems

[0005] The present invention is a system including the following means.

[0006] Means for registering the trouble information of each company in a database

[0007] A means of registering product information in a database.

[0008] A means for calculating the correlation between the aforementioned problem information and the aforementioned product information using a generative AI model that analyzes the aforementioned problem information and the aforementioned product information,

[0009] Based on the aforementioned correlation, a means of notifying prospective companies of the proposal content,

[0010] In response to the aforementioned notification, prospective companies can send a "Like",

[0011] The system includes means for providing the sales company with the contact information of the prospective company when it receives the aforementioned "Like!". The system also includes means for the generating AI model to use text mining techniques to extract keywords and context from the problem information and the product information, calculate correlations, and provide the prospective company with a dashboard to view the proposed content when it is notified of the proposed content.

[0012]

[0013] A "database" is a collection of information that can be systematically stored, managed, and retrieved.

[0014] A "company" is an organization that provides goods or services.

[0015] "Problem information" refers to detailed information about the problems and challenges that a company faces.

[0016] "Product information" refers to detailed information about the products or services offered by the sales company.

[0017] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze data and find patterns and relationships.

[0018] "Correlation" is an indicator that shows the degree of association between two different datasets.

[0019] The "proposal content" refers to the details of the solutions and services provided by the business-side enterprise to the prospective enterprise.

[0020] A "notification" is an act or message by which the system informs the user of specific information.

[0021] A "like" is positive feedback sent by a prospective enterprise to indicate interest or concern about the proposal content.

[0022] "Contact information" refers to detailed information such as phone numbers and email addresses for contacting the person in charge of the prospective enterprise.

[0023] "Text mining technology" is a technology that extracts meaning and patterns from text data using natural language processing.

[0024] A "dashboard" is an interface designed so that users can view important information at a glance.

Brief Description of Drawings

[0025] [Figure 1] It 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]This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0026] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0027] First, let's explain the terminology used in the following explanation.

[0028] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0029] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0030] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0031] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0032] 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."

[0033] [First Embodiment]

[0034] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0035] 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.

[0036] 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).

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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".

[0046] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system includes means for registering each company's problem information and product information in a database, calculating correlation using a generative AI model that analyzes them, notifying prospective companies of the proposal content, sending "likes," and providing contact information to sales companies.

[0047] The following explanation uses natural language and includes concrete examples of how the program works.

[0048] 1. Registering prospective companies

[0049] Users (prospective companies) create a free account through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the problems and challenges their company faces. This information is received by the server and stored in a database.

[0050] Specific example:

[0051] A user (prospective company B) enters their concerns into the platform, such as "We need a new marketing strategy, but we're unsure which direction to take," and registers their findings.

[0052] 2. Registration of sales companies

[0053] Users (sales companies) create paid accounts through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[0054] Specific example:

[0055] The user (sales company A) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[0056] 3. Matching process

[0057] The server periodically collects information on the concerns of prospective companies and the products / services of sales companies from the database. Using a generative AI model, it analyzes the prospective companies' concern data and extracts appropriate keywords and context. Furthermore, it analyzes the sales companies' product / service information to find common keywords and highly relevant information. Based on this correlation, it extracts pairs with high correlation.

[0058] Specific example:

[0059] The server analyzes prospective company B's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company A is suitable.

[0060] 4. Submitting the proposal

[0061] The server notifies prospective companies of successful matches. Prospective companies can view the proposal and, if interested, click the "Like" button to send positive feedback.

[0062] Specific example:

[0063] The server notifies prospective company B that "a proposal regarding the digital marketing strategy from sales company A has arrived." Prospective company B reviews the proposal and clicks the "Like" button.

[0064] 5. Matching successful

[0065] When the server receives a "like" from a prospective company, it sends a notification of successful matching to the sales company. At the same time, it provides the sales company with the prospective company's contact information. The sales company then uses the provided contact information to contact the prospective company with a specific proposal.

[0066] Specific example:

[0067] Prospective company B sends a "Like!" and the server notifies sales company A that "Prospective company B has agreed to the proposal." Sales company A obtains prospective company B's contact information and takes specific sales actions via phone or email.

[0068] This invention enables high-quality sales between prospective companies and sales companies. Because proposals tailored to the needs of both parties can be reviewed in advance, the success rate of telemarketing is significantly improved. This system, through highly accurate matching using a generative AI model, enables mutually beneficial sales activities.

[0069] The following describes the processing flow.

[0070] Step 1:

[0071] Users (prospective companies) open the dedicated website or application and access the free account creation page. Users enter basic information such as company name, contact person's name, email address, and password, and click the registration button.

[0072] Step 2:

[0073] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[0074] Step 3:

[0075] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter detailed information about the challenges and problems their company faces in the problem information form.

[0076] Step 4:

[0077] The server receives the entered problem information and saves it to the database. This registers the problem information of potential companies in the system.

[0078] Step 5:

[0079] The user (sales company) opens the dedicated website or application and accesses the paid account creation page. The user enters basic information such as company name, contact person's name, email address, and password, and clicks the registration button.

[0080] Step 6:

[0081] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[0082] Step 7:

[0083] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter details of the products or services they will be offering in the product information form.

[0084] Step 8:

[0085] The server receives the entered product information and saves it to a database for the generated AI model. This registers the sales company's product information in the system.

[0086] Step 9:

[0087] The server periodically collects information on the problems of prospective companies and the products and services of sales companies from the database. A generative AI model is used to analyze the data on the problems of prospective companies and the products and services of sales companies.

[0088] Step 10:

[0089] The server (generating AI model) uses text mining techniques to extract keywords and context from problem information and product information. Next, it calculates the correlation between problem information and product information and extracts pairs with high correlation.

[0090] Step 11:

[0091] The server notifies prospective companies of highly correlated pairs as proposals. Notifications are sent via email or as alerts in the dashboard.

[0092] Step 12:

[0093] Users (potential companies) receive notifications and review the proposals on their dashboard after logging in. If they are interested, users click the "Like" button.

[0094] Step 13:

[0095] The server receives the "Like!" input and saves that information to its database. At the same time, the server automatically sends a notification to the sales company that a match has been made.

[0096] Step 14:

[0097] The server provides sales companies with contact information for prospective companies. This allows sales companies to contact prospective companies directly and make specific proposals and follow up.

[0098] (Example 1)

[0099] 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."

[0100] In traditional sales activities, sales companies often expend considerable effort and time to find potential clients, leading to a high likelihood of wasted contact and failures. Furthermore, it was difficult to create sales proposals that accurately addressed the concerns and challenges of potential clients, making effective matching challenging. A system is needed to improve this situation and enable efficient and effective sales activities.

[0101] 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.

[0102] In this invention, the server includes means for registering information on each company's problems in a database, means for registering product information in the database, means for calculating the correlation between the problem information and the product information using a generative AI model that analyzes the problem information and the product information, means for notifying the target company of the proposed solution based on the correlation, means for the target company to send a "positive response" to the notification, and means for providing the target company's contact information to the sales company when the "positive response" is received. This enables highly accurate matching of the problems of prospective companies and the product information of sales companies, resulting in mutually beneficial sales activities.

[0103] A "database" is a system that permanently stores information and allows for efficient retrieval and management as needed.

[0104] "Problem information" refers to data about problems and challenges faced by companies, which is registered in the system.

[0105] "Product information" refers to detailed data about the products and services offered by the sales company, and is registered in the system.

[0106] A "generative AI model" refers to an algorithm that uses artificial intelligence to analyze data and generate predictions and recommendations.

[0107] "Correlation" refers to a criterion for evaluating the relationships and commonalities between two different datasets.

[0108] A "positive response" refers to an action taken by a prospective company to show a favorable reaction to the proposal, such as clicking "Like."

[0109] "Target companies" refers collectively to prospective companies and sales-related companies registered in the system.

[0110] A "selling company" refers to a company that offers goods or services to a prospective client company.

[0111] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system uses specific hardware and software to perform a series of processes, including data registration, analysis, notification, feedback reception, and contact information provision.

[0112] Hardware and software details

[0113] Server Environment

[0114] Hardware: High-performance server machines (e.g., dual-processor servers or Amazon Web Services as a cloud service)

[0115] software:

[0116] Operating System: Linux-based OS (e.g., Ubuntu Server)

[0117] Database management systems: MySQL, PostgreSQL

[0118] Web servers: Nginx, Apache

[0119] Programming frameworks: Flask and Django using Python

[0120] Generative AI model: OpenAI's GPT-3

[0121] Program processing flow

[0122] This system provides an interface for registering each company's problem information and product information in a database. This allows for centralized management of information on both prospective and sales companies.

[0123] Registration process

[0124] Registration of prospective companies

[0125] Users (potential companies) create a free account through a dedicated website or application and enter detailed information about the problems and challenges their company faces. The server receives this information and stores it in a database.

[0126] As a concrete example, a user (prospective company B) might enter and register a problem on the platform such as, "We need a new marketing strategy, but we're unsure which direction to take."

[0127] Registration of sales companies

[0128] Users (sales companies) create paid accounts and enter detailed information about the products and services they offer. The server receives this information and stores it in its database.

[0129] As a concrete example, a user (sales company A) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[0130] Matching process

[0131] The server uses a generative AI model to analyze prospective companies' problem information and sales companies' product information from the collected database. This model uses text mining techniques to extract keywords and context from the problem information and product information, and calculates their correlation.

[0132] As a concrete example, the server analyzes prospective company B's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company A is suitable. In this way, the optimal proposal is generated.

[0133] Notification and feedback on proposals

[0134] The generated proposal is notified to the prospective company by the server, and the prospective company reviews the proposal upon receiving this notification. If interested, the prospective company sends a "positive response" (e.g., "Like!"). This feedback is sent to the server, and the prospective company's contact information is provided to the sales company.

[0135] As a concrete example, the server notifies prospective company B that "a proposal regarding a digital marketing strategy from sales company A has arrived," and when prospective company B clicks "Like," sales company A obtains prospective company B's contact information.

[0136] Examples of prompt statements

[0137] Please explain the process of analyzing the service and product information provided by sales companies based on the concerns of prospective clients, and then generating the optimal sales proposal based on those results.

[0138] This system enables highly accurate matching between prospective companies and sales companies, allowing for effective sales activities. The use of a generative AI model provides an efficient sales process.

[0139] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0140] Step 1: Create an account for the prospective company

[0141] Input: The user (prospective company) enters the company name, contact person's name, email address, and password on a dedicated website or application.

[0142] Operation: The terminal collects this information and sends it to the server. The server validates the received information and, if there are no problems, saves it to the database.

[0143] Output: The prospective company's account information is registered in the database.

[0144] Step 2: Register information about the problems of potential companies.

[0145] Input: Users (prospective companies) log in to the platform and enter detailed information about their company's problems and challenges on the "Problem / Challenge Input" page.

[0146] Operation: The terminal sends the entered problem information to the server, and the server stores the information in a database.

[0147] Output: Information about the problems of prospective companies is saved in the database.

[0148] Specific operation: The user enters "We need a new marketing strategy, but we're unsure which direction to take" through the terminal and registers.

[0149] Step 3: Create an account for the sales company

[0150] Input: The user (sales company) enters the company name, contact person's name, email address, password, and payment information on the paid account creation page.

[0151] Operation: The device collects this information and sends it to the server. The server validates the received information, and if there are no problems, saves it to the database and sets up the paid account.

[0152] Output: The account information of the sales company is registered in the database.

[0153] Step 4: Register product information of the sales company.

[0154] Input: Users (sales companies) log in to the platform and enter details of the products or services they offer on the "Product Information Input" page.

[0155] Operation: The terminal sends the entered product information to the server, and the server stores the information in a database.

[0156] Output: Product information from the sales company is saved in the database.

[0157] Specific operation: The user enters and registers for the "Digital Marketing Strategy Building Support Service" via their device.

[0158] Step 5: Data Collection

[0159] Input: Information on the problems of prospective companies in the database and product information of sales companies.

[0160] Operation: The server periodically collects information on prospective and sales companies from the database.

[0161] Output: The collected problem information and product information are passed to the AI ​​model for generation.

[0162] Step 6: Data Analysis

[0163] Input: Information on the problems of prospective companies and product information of sales companies.

[0164] Operation: The server analyzes this information using a generative AI model (e.g., OpenAI's GPT-3). It extracts keywords and context using text mining techniques and calculates correlations.

[0165] Output: The results of the correlation analysis are generated.

[0166] Specific operation: The generating AI model extracts keywords such as "marketing strategy" and "direction" from the concerns of prospective company B, and extracts keywords such as "digital marketing" and "implementation support" from the product information of sales company A.

[0167] Step 7: Generating the proposal

[0168] Input: Results of correlation analysis by a generative AI model.

[0169] Operation: The server generates suggestions based on this and saves them to the database.

[0170] Output: The generated suggestions are saved to the database.

[0171] Step 8: Notification of Proposal

[0172] Input: Generated suggestion content.

[0173] Operation: The server notifies prospective companies of the proposal details. The notification is sent to the prospective company's terminal.

[0174] Output: A notification is sent to the prospective company.

[0175] Specific action: The server notifies prospective company B that "a proposal regarding the digital marketing strategy from sales company A has been received."

[0176] Step 9: Receive Feedback

[0177] Input: Feedback from prospective companies on the proposal (e.g., "Like!").

[0178] Operation: The terminal sends feedback from prospective companies to the server, and the server stores the feedback in a database.

[0179] Output: Feedback is saved to the database.

[0180] Specific operation: When prospective company B clicks "Like," the server receives feedback.

[0181] Step 10: Provide contact information

[0182] Input: Feedback ("Likes") from prospective companies and their contact information.

[0183] Operation: The server reviews the feedback and provides the prospective company's contact information to the sales company.

[0184] Output: Contact information is provided to the sales company.

[0185] Specific operation: The server notifies sales company A that "prospective company B has agreed to the proposal" and provides contact information.

[0186] (Application Example 1)

[0187] 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."

[0188] In the traditional marketing and advertising industry, it was difficult to effectively match the challenges faced by advertisers with the services offered by marketing companies. As a result, advertisers were unable to find the optimal advertising services, and marketing companies were unable to conduct effective sales activities. Furthermore, the process of quickly and efficiently proposing highly relevant advertising services, obtaining the advertiser's consent, and providing contact information was cumbersome.

[0189] 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.

[0190] In this invention, the server includes means for registering information on each company's problems in a database, means for registering product information in a database, means for calculating correlation using a generative AI model that analyzes the problem information and the product information, means for notifying the content of the proposal, means for prospective companies to send "likes", means for providing contact information, means for registering detailed information of advertising services provided by marketing companies, means for viewing the content of advertising services proposed based on the challenges faced by advertisers, and means for providing product information when the advertiser agrees to the proposed content. This enables effective matching between advertisers with problems and appropriate marketing companies, and allows for the rapid proposal of highly relevant advertising services and simplification of the communication process.

[0191] A "database" is a system for efficiently storing and managing information about a company's problems and products.

[0192] "Problem information" refers to information that includes the challenges and problems that companies face.

[0193] "Product information" refers to detailed information about the products and services offered by the sales company.

[0194] A "generative AI model" is an artificial intelligence technology that analyzes registered data and calculates its correlations.

[0195] "Correlation" refers to the degree of connection between information about problems and information about products, indicating a high degree of agreement.

[0196] "Means of notifying about the proposed content" refers to a function for informing prospective companies about appropriate product proposals.

[0197] "Like!" is a way for prospective companies to send positive feedback on a proposal.

[0198] "Contact information" refers to information provided by a prospective company that allows them to be contacted.

[0199] A "marketing company" is a company that provides advertising and promotional services.

[0200] "Detailed information about advertising services" refers to information that includes specific details about the advertising provided by a marketing company.

[0201] An "advertiser" is a company that wishes to promote its products or services.

[0202] "Challenges" refer to problems or requests that advertisers have that need to be resolved.

[0203] "Means for viewing the proposed advertising service details" refers to a function that allows advertisers to confirm the details of the advertising services provided.

[0204] "Means of providing product information" refers to a function that provides relevant information to advertisers if they agree to the proposal.

[0205] This invention is a system for achieving efficient and effective matching between advertisers and marketing companies. This system includes means for registering each company's problem information and product information in a database, calculating correlation using a generative AI model that analyzes them, notifying advertisers of proposed solutions, sending "likes," and providing contact information to marketing companies.

[0206] Hardware to use

[0207] server

[0208] Smartphone

[0209] Software to use

[0210] Database: MySQL

[0211] Application server: Node.js

[0212] Frontend: React Native

[0213] Generative AI model: OpenAI GPT-4

[0214] Data processing and calculations

[0215] The server receives data sent by the user and stores it in a database. Then, it uses a generative AI model (OpenAI GPT-4) to calculate the correlation between problem information and product information in the database.

[0216] in particular,

[0217] 1. The data collection server collects information from advertisers (companies facing problems) and marketing companies (advertising service providers) and stores it in a MySQL database.

[0218] Advertisers input information about their challenges through the application. For example, they might enter a problem such as, "We want to increase awareness of our new product, but our target market is unclear."

[0219] Marketing companies register details of the advertising services they offer in a database. For example, they might enter product information such as "social media marketing services."

[0220] 2. The data analysis server periodically analyzes the information in the database using a generative AI model (GPT-4), extracting keywords and context from problem information and product information, and calculating their correlation.

[0221] For example, the context of information such as "We need a new marketing strategy" and product information such as "Digital marketing strategy development support service" is analyzed to extract highly correlated pairs.

[0222] 3. The proposal sending server notifies advertisers who have entered problem information of proposals from marketing companies that have product information deemed to be highly correlated.

[0223] Advertisers can review their proposals through the application and, if interested, send positive feedback by clicking the "Like" button.

[0224] 4. Provision of Contact Information: When an advertiser sends a "Like," the server sends a notification of the successful match to the marketing company and provides the advertiser's contact information.

[0225] Marketing companies use the provided contact information to make detailed proposals and sell services to advertisers.

[0226] Specific example

[0227] Examples of prompts for generative AI models

[0228] "User-entered text: 'We need a new marketing strategy, but we're unsure which direction to take.'"

[0229] "Text for matching candidates: 'Digital Marketing Strategy Development Support Service'"

[0230] "Generates prompt messages for an AI model that calculates the correlation between the two and finds the optimal pair."

[0231] Sample prompt message

[0232] The prospective company's concern: "We need a new marketing strategy, but we're unsure which direction to take."

[0233] Sales company's product / service: "Support service for building digital marketing strategies"

[0234] Based on this information, please calculate the correlation between the two.

[0235] This enables efficient and effective matching between advertisers and marketing companies, facilitating the resolution of advertisers' challenges and the smooth progress of marketing companies' sales activities.

[0236] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0237] Step 1:

[0238] Data entry

[0239] Users (advertisers) input information about their company's challenges through a smartphone application. For example, they might input a challenge such as, "We want to increase awareness of our new product, but our target market is unclear." Users (marketing companies) input information about the advertising services they offer. For example, they might input product information such as, "Social Media Marketing Services."

[0240] Input and output

[0241] Input: Information on the advertiser's problems and information on the marketing company's products / services.

[0242] Output: Problem information and product information stored in the database

[0243] Specific actions

[0244] The information entered by the user is received by the server and stored in a MySQL database.

[0245] Step 2:

[0246] Data analysis

[0247] The server periodically uses a generative AI model (OpenAI GPT-4) to analyze problem information and product information in the database. The server extracts keywords and context related to the issues from the problem information and keywords and context related to the services provided from the product information.

[0248] Input and output

[0249] Input: Problem information and product information stored in the database

[0250] Output: Extracted keywords and analysis results

[0251] Specific actions

[0252] Generative AI models use text mining techniques to extract keywords and context, and discover highly correlated information.

[0253] Step 3:

[0254] Calculation of correlation

[0255] The server calculates the correlation between problem information and product information based on the analysis results of the generative AI model (GPT-4). It then generates an overall score to find appropriate matching candidates.

[0256] Input and output

[0257] Input: Analyzed keywords and analysis results

[0258] Output: Correlation score and matching candidates

[0259] Specific actions

[0260] The generative AI model generates prompt sentences, compares the information from both sides to calculate the correlation, and determines the optimal pair.

[0261] Step 4:

[0262] Notification of proposed content

[0263] The server notifies advertisers facing challenges with proposals from highly correlated marketing companies. Advertisers can then review the proposals through a smartphone application.

[0264] Input and output

[0265] Input: Matched suggestion information

[0266] Output: Proposal notification to advertisers

[0267] Specific actions

[0268] The server notifies the advertiser of the proposal via push notification or email. The advertiser then reviews the proposal within the application.

[0269] Step 5:

[0270] Sending a "Like"

[0271] If the advertiser is interested in the proposed content, by clicking the "Like!" button, positive feedback on the proposal is sent.

[0272] Input and Output

[0273] Input: Advertiser's "Like!" feedback

[0274] Output: Notification of receiving "Like!"

[0275] Specific Operations

[0276] When the advertiser clicks the "Like!" button, the information is sent to the server and recorded.

[0277] Step 6:

[0278] Provision of Contact Information

[0279] After receiving "Like!" from the advertiser, the server sends a notification of successful matching to the marketing company and provides the advertiser's contact information.

[0280] Input and Output

[0281] Input: Information of receiving "Like!"

[0282] Output: Notification of providing contact information to the marketing company

[0283] Specific Operations

[0284] The server sends a notification of successful matching to the marketing company and provides the advertiser's contact information. The marketing company uses the provided contact information to make specific proposals or conduct sales to the advertiser.

[0285] Through the above steps, efficient matching and effective advertising proposals between the advertiser and the marketing company are realized.

[0286] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0287] The present invention is a system for realizing efficient and effective matching between a prospective company and a business-side company. This system includes means for registering the problems and product information of each company in a database, calculating the correlation using a generative AI model for analyzing them, means for notifying the prospective company of the proposed content, means for sending "likes", and means for providing contact information to the business-side company. Also, in the present invention, by combining an emotion engine for recognizing the user's emotion, the proposed content can be more effectively adapted.

[0288] Hereinafter, a specific example of the program processing will be described in natural language.

[0289] 1. Registration of prospective companies

[0290] The user (prospective company) creates a free account through a dedicated website or application. After creating the account, the user logs in to the platform and enters in detail the problems and issues faced by the company. These pieces of information are received by the server and stored in the database.

[0291] Specific example:

[0292] The user (prospective company B) enters and registers on the platform a problem such as "A new marketing strategy is needed, but I'm worried about which direction is good."

[0293] 2. Registration of business-side companies

[0294] Users (sales companies) create paid accounts through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[0295] Specific example:

[0296] The user (sales company A) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[0297] 3. Matching process

[0298] The server periodically collects information on the concerns of prospective companies and the products / services of sales companies from the database. Using a generative AI model, it analyzes the prospective companies' concern data and extracts appropriate keywords and context. Furthermore, it analyzes the sales companies' product / service information to find common keywords and highly relevant information. Based on this correlation, it extracts pairs with high correlation.

[0299] Specific example:

[0300] The server analyzes prospective company B's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company A is suitable.

[0301] 4. Submitting the proposal

[0302] The server notifies prospective companies of successful matches. Notifications are sent via email or as alerts in the dashboard. Furthermore, this proposal notification incorporates a sentiment engine that analyzes the prospective company's emotional state.

[0303] Specific example:

[0304] The server notifies the prospective enterprise B that "a proposal regarding the digital marketing strategy of enterprise A on the sales side has been received". In this notification, the emotion engine is activated to analyze the user's reaction in real time and generate emotion data.

[0305] 5. Emotion Analysis and Adaptation of Proposals

[0306] The user (prospective enterprise) receives the notification and checks the content of the proposal. The emotion engine analyzes the user's expression and text feedback to grasp the user's emotional state. Based on this, the server can adapt the content of the proposal according to the user's emotion.

[0307] Specific example:

[0308] When the emotion engine detects that the prospective enterprise B shows interest from its expression, the server strengthens the content of the proposal based on this data and resends more specific information and relevant additional proposals.

[0309] 6. Sending "Like"

[0310] If the user (prospective enterprise) is interested, it clicks the "Like" button. The emotion engine adds this action to the emotion data and evaluates the overall degree of the user's interest.

[0311] Specific example:

[0312] When the prospective enterprise B sends "Like", the emotion engine analyzes the reaction and saves it as data evaluating the user's high interest.

[0313] 7. Matching Success

[0314] The server receives the input of "Like" and saves the information in the database. At the same time, the server automatically sends a notification of matching success to the enterprise on the sales side. Also, it provides the contact information of the prospective enterprise to the enterprise on the sales side. Based on this, the enterprise on the sales side directly contacts the prospective enterprise.

[0315] Specific example:

[0316] Upon receiving a "Like!" from prospective company B, the server notifies sales company A that "Prospective company B has agreed to the proposal." Sales company A then obtains prospective company B's contact information and communicates specific improvement suggestions.

[0317] This invention enables high-quality sales between prospective companies and sales companies, and significantly improves the success rate of telemarketing because proposals tailored to the needs of both parties can be confirmed in advance. This system enables mutually beneficial sales activities through highly accurate matching and sentiment analysis using a generative AI model and emotion engine.

[0318] The following describes the processing flow.

[0319] Step 1:

[0320] Users (prospective companies) open the dedicated website or application and access the free account creation page. Users enter basic information such as company name, contact person's name, email address, and password, and click the registration button.

[0321] Step 2:

[0322] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[0323] Step 3:

[0324] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter detailed information about the challenges and problems their company faces in the problem information form.

[0325] Step 4:

[0326] The server receives the entered problem information and saves it to the database. This registers the problem information of potential companies in the system.

[0327] Step 5:

[0328] The user (sales company) opens the dedicated website or application and accesses the paid account creation page. The user enters basic information such as company name, contact person's name, email address, and password, and clicks the registration button.

[0329] Step 6:

[0330] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[0331] Step 7:

[0332] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter details of the products or services they will be offering in the product information form.

[0333] Step 8:

[0334] The server receives the entered product information and saves it to a database for the generated AI model. This registers the sales company's product information in the system.

[0335] Step 9:

[0336] The server periodically collects information on the problems of prospective companies and the products and services of sales companies from the database. A generative AI model is used to analyze the data on the problems of prospective companies and the products and services of sales companies.

[0337] Step 10:

[0338] The server (generating AI model) uses text mining techniques to extract keywords and context from problem information and product information. Next, it calculates the correlation between problem information and product information and extracts pairs with high correlation.

[0339] Step 11:

[0340] The server notifies prospective companies of highly correlated pairs as proposals. Notifications are sent via email or as alerts in the dashboard.

[0341] Step 12:

[0342] Users (potential companies) receive notifications and review the proposals on their dashboard after logging in.

[0343] Step 13:

[0344] The emotion engine analyzes user (potential company) responses in real time to understand the emotional state of the potential company.

[0345] Step 14:

[0346] The server adaptively modifies the proposal based on emotional information obtained from the emotion engine and re-notifies the prospective company.

[0347] Step 15:

[0348] Users (potential companies) review the revised proposal and click the "Like" button if they are interested.

[0349] Step 16:

[0350] The server receives the "Like!" input and saves that information to its database. At the same time, the server automatically sends a notification to the sales company that a match has been made.

[0351] Step 17:

[0352] The server provides sales companies with contact information for prospective companies. This allows sales companies to contact prospective companies directly and make specific proposals and follow up.

[0353] (Example 2)

[0354] 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".

[0355] This invention aims to improve sales results for both prospective companies and sales companies by efficiently and effectively matching them in sales activities. Conventional sales methods often involve simultaneous approaches to a large number of prospective companies and proposals that do not match the needs of the prospective companies, resulting in decreased sales effectiveness and wasted time and resources. Furthermore, because it is difficult to properly understand the emotions and reactions of prospective companies, the suitability of proposals is low, making it difficult to improve the closing rate.

[0356] 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.

[0357] In this invention, the server includes means for registering information on each company's problems in a database, means for registering product information in the database, means for calculating the correlation between the problem information and the product information using a generative AI model that analyzes the problem information and the product information, means for notifying prospective companies of the proposed content based on the correlation, means for analyzing the prospective company's emotional state using an emotion engine and adapting the proposed content, means for the prospective company to send a "like!" in response to the notification, and means for providing the prospective company's contact information to the sales company when the "like!" is received. This enables appropriate and effective matching of proposed content between prospective companies and sales companies, improving the efficiency of sales activities and the closing rate.

[0358] A "database" is a system for efficiently storing and managing data such as information about a company's problems and product information.

[0359] A "generative AI model" is an artificial intelligence model that extracts keywords and context from specified data and calculates correlations by analyzing the data.

[0360] An "emotion engine" is software or a system that analyzes a user's facial expressions and text feedback to understand the user's emotional state.

[0361] A "prospective company" is a company that has shown interest in a particular product or service and may potentially do business with the company in the future.

[0362] A "sales-oriented company" is a company that provides specific goods or services and intends to sell or provide them to prospective companies.

[0363] "Correlation" is an indicator that shows the relationship or degree of relevance between information about the concerns of prospective companies and product information of sales companies.

[0364] "Proposal details" refer to the detailed information and proposals for products and services that the sales company presents to solve the problems and challenges of the prospective client.

[0365] A "Like" is a type of positive feedback that a prospective company sends to show interest in or concern about a proposal.

[0366] "Contact information" refers to information necessary to contact a prospective company directly, such as the name of the contact person, email address, and phone number.

[0367] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system consists of a server, terminals, and users.

[0368] 1. Registering prospective companies

[0369] Users (prospective companies) create a free account using a dedicated website or application. They enter necessary information such as company name, contact person's name, and email address on the account creation screen. After creating the account, they log in to the platform and enter detailed information about the company's problems and challenges. This information is received by the server and stored in the database.

[0370] Specific example:

[0371] A user (prospective company A) enters their concerns into the platform, such as "We need a new marketing strategy, but we're unsure which direction to take," and registers their findings.

[0372] 2. Registration of sales companies

[0373] Users (sales companies) create paid accounts using a dedicated website or application. They enter necessary information such as company name, contact person's name, email address, and payment information on the account creation screen. After creating the account, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[0374] Specific example:

[0375] The user (sales company B) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[0376] 3. Matching process

[0377] The server collects information on the concerns of prospective companies and the products / services of sales companies from the database. Using a generative AI model, the server analyzes the prospective companies' concerns data and extracts appropriate keywords and context. Simultaneously, it analyzes the sales companies' product / service information to find common keywords and highly relevant information. Based on these analysis results, it extracts pairs with high correlation.

[0378] Specific example:

[0379] The server analyzes prospective company A's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company B is suitable.

[0380] 4. Submitting the proposal

[0381] The server notifies prospective companies of proposals that have been successfully matched by the generated AI model. Notifications are sent via email or as alerts in the dashboard. These notifications also incorporate an emotion engine that analyzes the prospective company's emotional state.

[0382] Specific example:

[0383] The server notifies prospective company A that "a proposal regarding the digital marketing strategy from sales company B has arrived." This notification utilizes an emotion engine, which analyzes the user's response in real time and generates emotion data.

[0384] 5. Sentiment Analysis and Adaptation of Proposals

[0385] The user (potential company) receives a notification and reviews the proposal. The emotion engine analyzes the user's facial expressions and text feedback to understand the user's emotional state. This allows the server to adapt the proposal according to the user's emotions.

[0386] Specific example:

[0387] If the emotion engine detects from prospective company A's facial expressions that they are interested, the server uses that data to enhance the proposal and resends more specific information and related additional suggestions.

[0388] 6. Send a "Like"

[0389] If a user (potential company) is interested, they click the "Like" button. The sentiment engine adds this action to the sentiment data and evaluates the overall level of user interest.

[0390] Specific example:

[0391] When prospective company A sends a "Like," the emotion engine analyzes that reaction and stores it as data that evaluates the user's level of interest.

[0392] 7. Matching successful

[0393] The server receives the "Like!" input and saves the information to its database. At the same time, the server automatically sends a notification of the successful match to the sales company. It also provides the sales company with the prospective company's contact information. The sales company then uses this information to contact the prospective company directly.

[0394] Specific example:

[0395] When the server receives a "Like!" from prospective company A, it notifies sales company B that "Prospective company A has agreed to the proposal." Sales company B obtains prospective company A's contact information and contacts them with specific improvement suggestions.

[0396] This enables high-quality sales interactions between prospective clients and sales companies, allowing for pre-approval of proposals that meet the needs of both parties, thereby improving the efficiency of sales activities and closing rates. By utilizing servers, generative AI models, and emotion engines, highly accurate matching and emotion analysis become possible, resulting in beneficial sales activities for both prospective clients and sales companies.

[0397] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0398] Step 1: Register prospective companies

[0399] Users (prospective companies) create a free account through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the problems and challenges their company faces. This information is received by the server and stored in a database.

[0400] Input: Basic information such as company name, contact person's name, and email address, as well as details of the problem or issue.

[0401] Output: Profiles and problem information of prospective companies registered in the database.

[0402] Specific actions:

[0403] When a user clicks the "Create Account" button, the entered data is sent to the server, and a record of the new prospective company is added to the database. Next, when the user logs in and clicks the "Register Problem Information" button, the entered problem information is sent to the server and saved to the database.

[0404] Step 2: Register the sales company

[0405] Users (sales companies) create paid accounts through a dedicated website or application. They create an account by entering their company name, contact person's name, email address, payment information, etc., on the account creation screen. After creation, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[0406] Input: Company name, contact person name, email address, payment information, and product / service details.

[0407] Output: Profiles and product information of sales companies registered in the database.

[0408] Specific actions:

[0409] When a user clicks the "Create Account" button, the entered data is sent to the server, and a new sales company record is added to the database. Next, when the user logs in and clicks the "Register Product Information" button, the entered product information is sent to the server and saved to the database.

[0410] Step 3: Matching Process

[0411] The server collects information on the concerns of prospective companies and product information from sales companies within a database. Using a generative AI model, the server analyzes the prospective companies' concern data and extracts appropriate keywords and context. Simultaneously, it analyzes the sales companies' product information to find common keywords and highly relevant information. Based on these analysis results, it extracts pairs with high correlation.

[0412] Input: Data on the concerns of prospective companies in the database and product data of sales companies.

[0413] Output: Correlation score and pairs of prospective and sales companies with high correlation.

[0414] Specific actions:

[0415] A scheduled server job executes SQL queries to retrieve data on potential clients' concerns and sales companies' product data from the database. A generative AI model receives this text data and performs keyword extraction and contextual analysis. The server then selects pairs with high correlation scores and saves them to the database.

[0416] Step 4: Submit your proposal

[0417] The server notifies prospective companies of successful matches. Notifications are sent via email or as alerts in the dashboard. These notifications also incorporate an emotion engine that analyzes the prospective company's emotional state.

[0418] Input: Matching results and contact information for prospective companies (email address, etc.)

[0419] Output: Proposal notifications and sentiment data for prospective companies

[0420] Specific actions:

[0421] The server generates a proposal notification when a match is made and sends an email to the prospective company using the SMTP protocol or sends a real-time alert via WebSocket. The sentiment engine analyzes the prospective company's reaction to the notification and generates sentiment data.

[0422] Step 5: Sentiment analysis and adaptation of proposals

[0423] The user (potential company) receives a notification and reviews the proposal. The emotion engine analyzes the user's facial expressions and text feedback to understand the user's emotional state. This allows the server to adapt the proposal to the user's emotions.

[0424] Input: Prospective company's reaction (facial expression, text feedback)

[0425] Output: Sentiment data and adapted suggestions

[0426] Specific actions:

[0427] The user clicks the notification link to view the suggestion details page. The sentiment engine analyzes the camera feed or feedback text and generates a sentiment score. The server receives the sentiment score, updates the suggestion based on it, and generates a new suggestion.

[0428] Step 6: Send a "Like!"

[0429] If a user (potential client) is interested in a proposal, they click the "Like" button. The sentiment engine adds this action to the sentiment data and evaluates the overall level of user interest.

[0430] Input: "Like" click data

[0431] Output: Updated sentiment data

[0432] Specific actions:

[0433] When a user clicks the "Like" button, that information is sent to the server. The emotion engine analyzes this reaction and updates the emotion data. The server saves the updated emotion data to the database.

[0434] Step 7: Matching successful

[0435] The server receives the "Like!" input and saves the information to its database. At the same time, the server automatically sends a notification of the successful match to the sales company. It also provides the sales company with the prospective company's contact information. The sales company then uses this information to contact the prospective company directly.

[0436] Input: "Like" data and contact information of prospective companies

[0437] Output: Notification of successful matching to the sales company and contact information of the prospective company.

[0438] Specific actions:

[0439] When the server receives a "Like" data, it adds it to the database as a new record. At the same time, it sends a matching notification to the sales company using the SMTP protocol. The server securely provides the sales company with the prospect's contact information, preparing the sales company to contact the prospect directly.

[0440] (Application Example 2)

[0441] 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".

[0442] Traditional methods of matching customers with sales staff in physical stores often resulted in products and services not meeting customer needs, making it difficult to improve satisfaction. Furthermore, the inefficient matching of staff and customers within the store led to a lack of personalized service and a diminished customer experience. Additionally, the lack of suggestions that considered the customer's emotional state meant there was no guarantee that suggestions would align with the customer's interests and needs.

[0443] 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.

[0444] In this invention, the server includes means for registering information about each organization's concerns in a database, means for registering product information in the database, means for calculating the correlation between the concern information and the product information using a generative AI model that analyzes the concern information and the product information, means for notifying prospective organizations of the proposed content based on the correlation, means for prospective organizations to send a "Like!" in response to the notification, means for providing the prospective organization's contact information to the providing organization when a "Like!" is received, means for analyzing the prospective organization's emotional state using an emotion engine and adjusting the proposed content, and means for resending the adjusted proposed content. This enables efficient matching of customers and sales staff in physical stores, and further improves customer satisfaction by providing more appropriate suggestions based on the customer's emotional state.

[0445] An "organization" refers to a group of people, such as a company or association, who come together for a specific purpose.

[0446] "Problem information" refers to data about problems and challenges faced by organizations and individuals.

[0447] "Product information" refers to detailed data about the products and services offered.

[0448] A "generative AI model" refers to a model that uses artificial intelligence technology to analyze text data and automatically generate relationships and specific information.

[0449] "Correlation" refers to an indicator that shows the degree of relationship or linkage between two or more data points.

[0450] A "prospective organization" refers to a company or group that may be interested in a particular service or product.

[0451] "Proposal details" refers to information that explains the benefits and advantages of the services or products offered to the prospective organization.

[0452] "Notification" refers to a message or alert used to inform a target person of specific information.

[0453] "Like!" refers to an action that indicates interest in or agreement with a proposal.

[0454] "Contact information" refers to information such as phone numbers and email addresses used to contact prospective organizations.

[0455] "Provider organizations" refer to companies or groups that provide goods or services.

[0456] An "emotion engine" refers to a technology that analyzes a user's emotions and changes the system's output and suggestions according to that emotional state.

[0457] "Adjusted suggestions" refers to suggestions that have been modified by the emotion engine based on the user's emotional state.

[0458] "Resending" refers to the act of sending information that has already been sent once.

[0459] This system is designed to enable efficient matching between customers and sales staff in physical stores. The specific implementation of the system is described below.

[0460] Hardware configuration

[0461] Server: Hosts a database that manages customer and sales staff information, a generative AI model, and an emotion engine.

[0462] Smartphone or smart glasses: Used by customers to access the system, input information, and receive data within the store.

[0463] Display device: Provides a screen for sales staff to review proposals and customer information.

[0464] Software Configuration

[0465] Database: Customer and sales staff information is stored in a database such as SQLite.

[0466] Generative AI Model: We use generative AI models such as OpenAI's GPT-3.5-turbo to analyze text data and generate suggested content.

[0467] Emotion Engine: Uses the emotion analysis model from the Transformers library to analyze the customer's emotional state.

[0468] Data processing and data calculation

[0469] 1. Data Registration

[0470] Customers input information about the products and services they are looking for in the store via their smartphones or smart glasses. This information is sent to a server and stored in a database. Similarly, sales staff register their areas of expertise and the services they can offer in the database.

[0471] 2. Calculation of correlation

[0472] The server periodically collects customer problem information and sales staff expertise information from a database. Using a generative AI model, it analyzes the text data from both sources and extracts appropriate keywords and context. Correlations are calculated using text analysis techniques such as TF-IDF and cosine similarity.

[0473] 3. Notification of proposed content

[0474] Based on calculated correlations, an AI model selects the most appropriate sales staff and generates recommendations for the customer. These recommendations are then communicated to the customer via smartphone or smart glasses.

[0475] 4. Emotion analysis

[0476] Customer reactions to the proposed content are analyzed by an emotion engine. The degree of interest and engagement is evaluated through the customer's facial expressions and text feedback. For example, if a customer provides feedback such as "This is interesting," the engine will judge their emotional state to be highly positive.

[0477] 5. Adjustment and re-notification of the proposed content.

[0478] Based on the results of the sentiment analysis, the proposed content is adapted. If the customer shows interest, the AI ​​model generates more specific information and additional suggestions, and notifies the customer again.

[0479] Specific example

[0480] When information is entered that customer A is looking for a smartphone, a generative AI model is used to calculate the correlation and match customer A with a sales staff member A who is knowledgeable about smartphones. The generative AI model then makes a suggestion such as "This is the latest smartphone," and the emotion engine analyzes customer A's response. If the response is positive, more detailed information and additional suggestions are sent again.

[0481] Example of a prompt

[0482] "Please write down what you would suggest to a customer looking for a new smartphone."

[0483] In this way, efficient matching of customers and sales staff, as well as appropriate recommendations, can be achieved in physical stores.

[0484] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0485] Step 1:

[0486] Entering and registering customer information

[0487] The user (customer) uses a smartphone or smart glasses to input information about the products or services they are looking for in the store. This information includes specific details such as "I'm looking for a new smartphone." The entered information is sent to a server, which registers the received information in a database.

[0488] Input: Information entered by the customer via smartphone or smart glasses.

[0489] Output: Customer information registered in the database

[0490] Step 2:

[0491] Entering and registering sales staff information

[0492] Users (sales staff) use a smartphone or display device to input information about their areas of expertise and the services they can offer. This includes specific details such as "smartphone expert." The entered information is sent to a server, which registers it in a database.

[0493] Input: Information on areas of expertise and services offered entered by sales staff.

[0494] Output: Sales staff information registered in the database

[0495] Step 3:

[0496] Information gathering and analysis

[0497] The server periodically collects customer problem information and sales staff expertise information from the database. A generative AI model is used to analyze this text data and extract appropriate keywords and context. Text analysis techniques such as TF-IDF and cosine similarity are used for this analysis.

[0498] Input: Customer problem information and sales staff expertise information from the database.

[0499] Output: Analyzed keywords and contextual information

[0500] Step 4:

[0501] Calculation of correlation

[0502] The server uses a generative AI model to calculate the correlation between customer problem information and sales staff expertise information based on collected keywords and contextual information. It then extracts highly correlated pairs and performs matching.

[0503] Input: Analyzed keywords and contextual information

[0504] Output: Highly correlated customer-sales staff pairs

[0505] Step 5:

[0506] Proposal generation and notification

[0507] The server uses a generative AI model to generate suggestions based on the information of the matched customer and sales staff. The generated suggestions are then notified to the customer's smartphone or smart glasses.

[0508] Input: Pairs of customers and sales staff with a high correlation

[0509] Output: Proposal content notified to the customer

[0510] Step 6:

[0511] Emotion analysis

[0512] The user (customer) reviews the proposal and inputs their response via smartphone or smart glasses. The server uses an emotion engine to analyze the customer's text feedback and facial expression data to evaluate the customer's emotional state.

[0513] Input: Customer feedback and facial expression data

[0514] Output: Analyzed emotional state data

[0515] Step 7:

[0516] Adjustment and re-notification of the proposed content

[0517] The server adjusts the suggestions based on the sentiment analysis results. If the customer shows interest, the AI ​​model generates more specific information and additional suggestions, and notifies the customer again.

[0518] Input: Analyzed emotional state data

[0519] Output: Adjusted proposal and reminder message

[0520] The above outlines the processing steps for an efficient customer-sales staff matching system in physical stores. This makes it possible to improve the customer experience.

[0521] 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.

[0522] 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.

[0523] 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.

[0524] [Second Embodiment]

[0525] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0526] 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.

[0527] 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).

[0528] 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.

[0529] 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.

[0530] 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).

[0531] 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.

[0532] 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.

[0533] 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.

[0534] 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.

[0535] 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.

[0536] 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".

[0537] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system includes means for registering each company's problem information and product information in a database, calculating correlation using a generative AI model that analyzes them, notifying prospective companies of the proposal content, sending "likes," and providing contact information to sales companies.

[0538] The following explanation uses natural language and includes concrete examples of how the program works.

[0539] 1. Registering prospective companies

[0540] Users (prospective companies) create a free account through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the problems and challenges their company faces. This information is received by the server and stored in a database.

[0541] Specific example:

[0542] A user (prospective company B) enters their concerns into the platform, such as "We need a new marketing strategy, but we're unsure which direction to take," and registers their findings.

[0543] 2. Registration of sales companies

[0544] Users (sales companies) create paid accounts through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[0545] Specific example:

[0546] The user (sales company A) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[0547] 3. Matching process

[0548] The server periodically collects information on the concerns of prospective companies and the products / services of sales companies from the database. Using a generative AI model, it analyzes the prospective companies' concern data and extracts appropriate keywords and context. Furthermore, it analyzes the sales companies' product / service information to find common keywords and highly relevant information. Based on this correlation, it extracts pairs with high correlation.

[0549] Specific example:

[0550] The server analyzes prospective company B's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company A is suitable.

[0551] 4. Submitting the proposal

[0552] The server notifies prospective companies of successful matches. Prospective companies can view the proposal and, if interested, click the "Like" button to send positive feedback.

[0553] Specific example:

[0554] The server notifies prospective company B that "a proposal regarding the digital marketing strategy from sales company A has arrived." Prospective company B reviews the proposal and clicks the "Like" button.

[0555] 5. Matching successful

[0556] When the server receives a "like" from a prospective company, it sends a notification of successful matching to the sales company. At the same time, it provides the sales company with the prospective company's contact information. The sales company then uses the provided contact information to contact the prospective company with a specific proposal.

[0557] Specific example:

[0558] Prospective company B sends a "Like!" and the server notifies sales company A that "Prospective company B has agreed to the proposal." Sales company A obtains prospective company B's contact information and takes specific sales actions via phone or email.

[0559] This invention enables high-quality sales between prospective companies and sales companies. Because proposals tailored to the needs of both parties can be reviewed in advance, the success rate of telemarketing is significantly improved. This system, through highly accurate matching using a generative AI model, enables mutually beneficial sales activities.

[0560] The following describes the processing flow.

[0561] Step 1:

[0562] Users (prospective companies) open the dedicated website or application and access the free account creation page. Users enter basic information such as company name, contact person's name, email address, and password, and click the registration button.

[0563] Step 2:

[0564] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[0565] Step 3:

[0566] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter detailed information about the challenges and problems their company faces in the problem information form.

[0567] Step 4:

[0568] The server receives the entered problem information and saves it to the database. This registers the problem information of potential companies in the system.

[0569] Step 5:

[0570] The user (sales company) opens the dedicated website or application and accesses the paid account creation page. The user enters basic information such as company name, contact person's name, email address, and password, and clicks the registration button.

[0571] Step 6:

[0572] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[0573] Step 7:

[0574] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter details of the products or services they will be offering in the product information form.

[0575] Step 8:

[0576] The server receives the entered product information and saves it to a database for the generated AI model. This registers the sales company's product information in the system.

[0577] Step 9:

[0578] The server periodically collects information on the problems of prospective companies and the products and services of sales companies from the database. A generative AI model is used to analyze the data on the problems of prospective companies and the products and services of sales companies.

[0579] Step 10:

[0580] The server (generating AI model) uses text mining techniques to extract keywords and context from problem information and product information. Next, it calculates the correlation between problem information and product information and extracts pairs with high correlation.

[0581] Step 11:

[0582] The server notifies prospective companies of highly correlated pairs as proposals. Notifications are sent via email or as alerts in the dashboard.

[0583] Step 12:

[0584] Users (potential companies) receive notifications and review the proposals on their dashboard after logging in. If they are interested, users click the "Like" button.

[0585] Step 13:

[0586] The server receives the "Like!" input and saves that information to its database. At the same time, the server automatically sends a notification to the sales company that a match has been made.

[0587] Step 14:

[0588] The server provides sales companies with contact information for prospective companies. This allows sales companies to contact prospective companies directly and make specific proposals and follow up.

[0589] (Example 1)

[0590] 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".

[0591] In traditional sales activities, sales companies often expend considerable effort and time to find potential clients, leading to a high likelihood of wasted contact and failures. Furthermore, it was difficult to create sales proposals that accurately addressed the concerns and challenges of potential clients, making effective matching challenging. A system is needed to improve this situation and enable efficient and effective sales activities.

[0592] 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.

[0593] In this invention, the server includes means for registering information on each company's problems in a database, means for registering product information in the database, means for calculating the correlation between the problem information and the product information using a generative AI model that analyzes the problem information and the product information, means for notifying the target company of the proposed solution based on the correlation, means for the target company to send a "positive response" to the notification, and means for providing the target company's contact information to the sales company when the "positive response" is received. This enables highly accurate matching of the problems of prospective companies and the product information of sales companies, resulting in mutually beneficial sales activities.

[0594] A "database" is a system that permanently stores information and allows for efficient retrieval and management as needed.

[0595] "Problem information" refers to data about problems and challenges faced by companies, which is registered in the system.

[0596] "Product information" refers to detailed data about the products and services offered by the sales company, and is registered in the system.

[0597] A "generative AI model" refers to an algorithm that uses artificial intelligence to analyze data and generate predictions and recommendations.

[0598] "Correlation" refers to a criterion for evaluating the relationships and commonalities between two different datasets.

[0599] A "positive response" refers to an action taken by a prospective company to show a favorable reaction to the proposal, such as clicking "Like."

[0600] "Target companies" refers collectively to prospective companies and sales-related companies registered in the system.

[0601] A "selling company" refers to a company that offers goods or services to a prospective client company.

[0602] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system uses specific hardware and software to perform a series of processes, including data registration, analysis, notification, feedback reception, and contact information provision.

[0603] Hardware and software details

[0604] Server Environment

[0605] Hardware: High-performance server machines (e.g., dual-processor servers or Amazon Web Services as a cloud service)

[0606] software:

[0607] Operating System: Linux-based OS (e.g., Ubuntu Server)

[0608] Database management systems: MySQL, PostgreSQL

[0609] Web servers: Nginx, Apache

[0610] Programming frameworks: Flask and Django using Python

[0611] Generative AI model: OpenAI's GPT-3

[0612] Program processing flow

[0613] This system provides an interface for registering each company's problem information and product information in a database. This allows for centralized management of information on both prospective and sales companies.

[0614] Registration process

[0615] Registration of prospective companies

[0616] Users (potential companies) create a free account through a dedicated website or application and enter detailed information about the problems and challenges their company faces. The server receives this information and stores it in a database.

[0617] As a concrete example, a user (prospective company B) might enter and register a problem on the platform such as, "We need a new marketing strategy, but we're unsure which direction to take."

[0618] Registration of sales companies

[0619] Users (sales companies) create paid accounts and enter detailed information about the products and services they offer. The server receives this information and stores it in its database.

[0620] As a concrete example, a user (sales company A) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[0621] Matching process

[0622] The server uses a generative AI model to analyze prospective companies' problem information and sales companies' product information from the collected database. This model uses text mining techniques to extract keywords and context from the problem information and product information, and calculates their correlation.

[0623] As a concrete example, the server analyzes prospective company B's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company A is suitable. In this way, the optimal proposal is generated.

[0624] Notification and feedback on proposals

[0625] The generated proposal is notified to the prospective company by the server, and the prospective company reviews the proposal upon receiving this notification. If interested, the prospective company sends a "positive response" (e.g., "Like!"). This feedback is sent to the server, and the prospective company's contact information is provided to the sales company.

[0626] As a concrete example, the server notifies prospective company B that "a proposal regarding a digital marketing strategy from sales company A has arrived," and when prospective company B clicks "Like," sales company A obtains prospective company B's contact information.

[0627] Examples of prompt statements

[0628] Please explain the process of analyzing the service and product information provided by sales companies based on the concerns of prospective clients, and then generating the optimal sales proposal based on those results.

[0629] This system enables highly accurate matching between prospective companies and sales companies, allowing for effective sales activities. The use of a generative AI model provides an efficient sales process.

[0630] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0631] Step 1: Create an account for the prospective company

[0632] Input: The user (prospective company) enters the company name, contact person's name, email address, and password on a dedicated website or application.

[0633] Operation: The terminal collects this information and sends it to the server. The server validates the received information and, if there are no problems, saves it to the database.

[0634] Output: The prospective company's account information is registered in the database.

[0635] Step 2: Register information about the problems of potential companies.

[0636] Input: Users (prospective companies) log in to the platform and enter detailed information about their company's problems and challenges on the "Problem / Challenge Input" page.

[0637] Operation: The terminal sends the entered problem information to the server, and the server stores the information in a database.

[0638] Output: Information about the problems of prospective companies is saved in the database.

[0639] Specific operation: The user enters "We need a new marketing strategy, but we're unsure which direction to take" through the terminal and registers.

[0640] Step 3: Create an account for the sales company

[0641] Input: The user (sales company) enters the company name, contact person's name, email address, password, and payment information on the paid account creation page.

[0642] Operation: The device collects this information and sends it to the server. The server validates the received information, and if there are no problems, saves it to the database and sets up the paid account.

[0643] Output: The account information of the sales company is registered in the database.

[0644] Step 4: Register product information of the sales company.

[0645] Input: Users (sales companies) log in to the platform and enter details of the products or services they offer on the "Product Information Input" page.

[0646] Operation: The terminal sends the entered product information to the server, and the server stores the information in a database.

[0647] Output: Product information from the sales company is saved in the database.

[0648] Specific operation: The user enters and registers for the "Digital Marketing Strategy Building Support Service" via their device.

[0649] Step 5: Data Collection

[0650] Input: Information on the problems of prospective companies in the database and product information of sales companies.

[0651] Operation: The server periodically collects information on prospective and sales companies from the database.

[0652] Output: The collected problem information and product information are passed to the AI ​​model for generation.

[0653] Step 6: Data Analysis

[0654] Input: Information on the problems of prospective companies and product information of sales companies.

[0655] Operation: The server analyzes this information using a generative AI model (e.g., OpenAI's GPT-3). It extracts keywords and context using text mining techniques and calculates correlations.

[0656] Output: The results of the correlation analysis are generated.

[0657] Specific operation: The generating AI model extracts keywords such as "marketing strategy" and "direction" from the concerns of prospective company B, and extracts keywords such as "digital marketing" and "implementation support" from the product information of sales company A.

[0658] Step 7: Generating the proposal

[0659] Input: Results of correlation analysis by a generative AI model.

[0660] Operation: The server generates suggestions based on this and saves them to the database.

[0661] Output: The generated suggestions are saved to the database.

[0662] Step 8: Notification of Proposal

[0663] Input: Generated suggestion content.

[0664] Operation: The server notifies prospective companies of the proposal details. The notification is sent to the prospective company's terminal.

[0665] Output: A notification is sent to the prospective company.

[0666] Specific action: The server notifies prospective company B that "a proposal regarding the digital marketing strategy from sales company A has been received."

[0667] Step 9: Receive Feedback

[0668] Input: Feedback from prospective companies on the proposal (e.g., "Like!").

[0669] Operation: The terminal sends feedback from prospective companies to the server, and the server stores the feedback in a database.

[0670] Output: Feedback is saved to the database.

[0671] Specific operation: When prospective company B clicks "Like," the server receives feedback.

[0672] Step 10: Provide contact information

[0673] Input: Feedback ("Likes") from prospective companies and their contact information.

[0674] Operation: The server reviews the feedback and provides the prospective company's contact information to the sales company.

[0675] Output: Contact information is provided to the sales company.

[0676] Specific operation: The server notifies sales company A that "prospective company B has agreed to the proposal" and provides contact information.

[0677] (Application Example 1)

[0678] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0679] In the traditional marketing and advertising industry, it was difficult to effectively match the challenges faced by advertisers with the services offered by marketing companies. As a result, advertisers were unable to find the optimal advertising services, and marketing companies were unable to conduct effective sales activities. Furthermore, the process of quickly and efficiently proposing highly relevant advertising services, obtaining the advertiser's consent, and providing contact information was cumbersome.

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

[0681] In this invention, the server includes means for registering information on each company's problems in a database, means for registering product information in a database, means for calculating correlation using a generative AI model that analyzes the problem information and the product information, means for notifying the content of the proposal, means for prospective companies to send "likes", means for providing contact information, means for registering detailed information of advertising services provided by marketing companies, means for viewing the content of advertising services proposed based on the challenges faced by advertisers, and means for providing product information when the advertiser agrees to the proposed content. This enables effective matching between advertisers with problems and appropriate marketing companies, and allows for the rapid proposal of highly relevant advertising services and simplification of the communication process.

[0682] A "database" is a system for efficiently storing and managing information about a company's problems and products.

[0683] "Problem information" refers to information that includes the challenges and problems that companies face.

[0684] "Product information" refers to detailed information about the products and services offered by the sales company.

[0685] A "generative AI model" is an artificial intelligence technology that analyzes registered data and calculates its correlations.

[0686] "Correlation" refers to the degree of connection between information about problems and information about products, indicating a high degree of agreement.

[0687] "Means of notifying about the proposed content" refers to a function for informing prospective companies about appropriate product proposals.

[0688] "Like!" is a way for prospective companies to send positive feedback on a proposal.

[0689] "Contact information" refers to information provided by a prospective company that allows them to be contacted.

[0690] A "marketing company" is a company that provides advertising and promotional services.

[0691] "Detailed information about advertising services" refers to information that includes specific details about the advertising provided by a marketing company.

[0692] An "advertiser" is a company that wishes to promote its products or services.

[0693] "Challenges" refer to problems or requests that advertisers have that need to be resolved.

[0694] "Means for viewing the proposed advertising service details" refers to a function that allows advertisers to confirm the details of the advertising services provided.

[0695] "Means of providing product information" refers to a function that provides relevant information to advertisers if they agree to the proposal.

[0696] This invention is a system for achieving efficient and effective matching between advertisers and marketing companies. This system includes means for registering each company's problem information and product information in a database, calculating correlation using a generative AI model that analyzes them, notifying advertisers of proposed solutions, sending "likes," and providing contact information to marketing companies.

[0697] Hardware to use

[0698] server

[0699] Smartphone

[0700] Software to use

[0701] Database: MySQL

[0702] Application server: Node.js

[0703] Frontend: React Native

[0704] Generative AI model: OpenAI GPT-4

[0705] Data processing and calculations

[0706] The server receives data sent by the user and stores it in a database. Then, it uses a generative AI model (OpenAI GPT-4) to calculate the correlation between problem information and product information in the database.

[0707] in particular,

[0708] 1. The data collection server collects information from advertisers (companies facing problems) and marketing companies (advertising service providers) and stores it in a MySQL database.

[0709] Advertisers input information about their challenges through the application. For example, they might enter a problem such as, "We want to increase awareness of our new product, but our target market is unclear."

[0710] Marketing companies register details of the advertising services they offer in a database. For example, they might enter product information such as "social media marketing services."

[0711] 2. The data analysis server periodically analyzes the information in the database using a generative AI model (GPT-4), extracting keywords and context from problem information and product information, and calculating their correlation.

[0712] For example, the context of information such as "We need a new marketing strategy" and product information such as "Digital marketing strategy development support service" is analyzed to extract highly correlated pairs.

[0713] 3. The proposal sending server notifies advertisers who have entered problem information of proposals from marketing companies that have product information deemed to be highly correlated.

[0714] Advertisers can review their proposals through the application and, if interested, send positive feedback by clicking the "Like" button.

[0715] 4. Provision of Contact Information: When an advertiser sends a "Like," the server sends a notification of the successful match to the marketing company and provides the advertiser's contact information.

[0716] Marketing companies use the provided contact information to make detailed proposals and sell services to advertisers.

[0717] Specific example

[0718] Examples of prompts for generative AI models

[0719] "User-entered text: 'We need a new marketing strategy, but we're unsure which direction to take.'"

[0720] "Text for matching candidates: 'Digital Marketing Strategy Development Support Service'"

[0721] "Generates prompt messages for an AI model that calculates the correlation between the two and finds the optimal pair."

[0722] Sample prompt message

[0723] The prospective company's concern: "We need a new marketing strategy, but we're unsure which direction to take."

[0724] Sales company's product / service: "Support service for building digital marketing strategies"

[0725] Based on this information, please calculate the correlation between the two.

[0726] This enables efficient and effective matching between advertisers and marketing companies, facilitating the resolution of advertisers' challenges and the smooth progress of marketing companies' sales activities.

[0727] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0728] Step 1:

[0729] Data entry

[0730] Users (advertisers) input information about their company's challenges through a smartphone application. For example, they might input a challenge such as, "We want to increase awareness of our new product, but our target market is unclear." Users (marketing companies) input information about the advertising services they offer. For example, they might input product information such as, "Social Media Marketing Services."

[0731] Input and output

[0732] Input: Information on the advertiser's problems and information on the marketing company's products / services.

[0733] Output: Problem information and product information stored in the database

[0734] Specific actions

[0735] The information entered by the user is received by the server and stored in a MySQL database.

[0736] Step 2:

[0737] Data analysis

[0738] The server periodically uses a generative AI model (OpenAI GPT-4) to analyze problem information and product information in the database. The server extracts keywords and context related to the issues from the problem information and keywords and context related to the services provided from the product information.

[0739] Input and output

[0740] Input: Problem information and product information stored in the database

[0741] Output: Extracted keywords and analysis results

[0742] Specific actions

[0743] Generative AI models use text mining techniques to extract keywords and context, and discover highly correlated information.

[0744] Step 3:

[0745] Calculation of correlation

[0746] The server calculates the correlation between problem information and product information based on the analysis results of the generative AI model (GPT-4). It then generates an overall score to find appropriate matching candidates.

[0747] Input and output

[0748] Input: Analyzed keywords and analysis results

[0749] Output: Correlation score and matching candidates

[0750] Specific actions

[0751] The generative AI model generates prompt sentences, compares the information from both sides to calculate the correlation, and determines the optimal pair.

[0752] Step 4:

[0753] Notification of proposed content

[0754] The server notifies advertisers facing challenges with proposals from highly correlated marketing companies. Advertisers can then review the proposals through a smartphone application.

[0755] Input and output

[0756] Input: Matched suggestion information

[0757] Output: Proposal notification to advertisers

[0758] Specific actions

[0759] The server notifies the advertiser of the proposal via push notification or email. The advertiser then reviews the proposal within the application.

[0760] Step 5:

[0761] Sending a "Like"

[0762] If an advertiser is interested in a proposal, they can send positive feedback by clicking the "Like" button.

[0763] Input and output

[0764] Input: Advertiser's "Like" feedback

[0765] Output: Notification of receiving a "Like"

[0766] Specific actions

[0767] When an advertiser clicks the "Like" button, that information is sent to the server and recorded.

[0768] Step 6:

[0769] Providing contact information

[0770] After receiving a "like" from an advertiser, the server sends a notification of the successful match to the marketing company and provides the advertiser's contact information.

[0771] Input and output

[0772] Input: Information on received "Likes"

[0773] Output: Notification of providing contact information to marketing companies

[0774] Specific actions

[0775] The server sends a notification to the marketing company that a match has been made and provides the advertiser's contact information. The marketing company then uses the provided contact information to make specific proposals and sales pitches to the advertiser.

[0776] The above steps enable efficient matching and effective advertising proposals between advertisers and marketing companies.

[0777] 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.

[0778] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system includes means for registering each company's problem information and product information in a database, calculating correlation using a generative AI model that analyzes them, notifying prospective companies of the proposed content, sending "likes," and providing contact information to sales companies. Furthermore, in this invention, by combining it with an emotion engine that recognizes user emotions, the proposed content can be adapted even more effectively.

[0779] The following explanation uses natural language and includes concrete examples of how the program works.

[0780] 1. Registering prospective companies

[0781] Users (prospective companies) create a free account through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the problems and challenges their company faces. This information is received by the server and stored in a database.

[0782] Specific example:

[0783] A user (prospective company B) enters their concerns into the platform, such as "We need a new marketing strategy, but we're unsure which direction to take," and registers their findings.

[0784] 2. Registration of sales companies

[0785] Users (sales companies) create paid accounts through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[0786] Specific example:

[0787] The user (sales company A) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[0788] 3. Matching process

[0789] The server periodically collects information on the concerns of prospective companies and the products / services of sales companies from the database. Using a generative AI model, it analyzes the prospective companies' concern data and extracts appropriate keywords and context. Furthermore, it analyzes the sales companies' product / service information to find common keywords and highly relevant information. Based on this correlation, it extracts pairs with high correlation.

[0790] Specific example:

[0791] The server analyzes prospective company B's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company A is suitable.

[0792] 4. Submitting the proposal

[0793] The server notifies prospective companies of successful matches. Notifications are sent via email or as alerts in the dashboard. Furthermore, this proposal notification incorporates a sentiment engine that analyzes the prospective company's emotional state.

[0794] Specific example:

[0795] The server notifies prospective company B that "a proposal regarding the digital marketing strategy from sales company A has arrived." This notification utilizes an emotion engine, which analyzes the user's response in real time and generates emotion data.

[0796] 5. Sentiment Analysis and Adaptation of Proposals

[0797] The user (potential company) receives a notification and reviews the proposal. The emotion engine analyzes the user's facial expressions and text feedback to understand the user's emotional state. This allows the server to adapt the proposal according to the user's emotions.

[0798] Specific example:

[0799] If the emotion engine detects that prospective company B is showing interest based on their facial expressions, the server uses that data to enhance the proposal and resends more specific information and related additional suggestions.

[0800] 6. Send a "Like"

[0801] If a user (potential company) is interested, they click the "Like" button. The sentiment engine adds this action to the sentiment data and evaluates the overall level of user interest.

[0802] Specific example:

[0803] When prospective company B sends a "Like," the emotion engine analyzes that reaction and stores it as data that evaluates the user's level of interest.

[0804] 7. Matching successful

[0805] The server receives the "Like!" input and saves the information to its database. At the same time, the server automatically sends a notification of the successful match to the sales company. It also provides the sales company with the prospective company's contact information. The sales company then uses this information to contact the prospective company directly.

[0806] Specific example:

[0807] Upon receiving a "Like!" from prospective company B, the server notifies sales company A that "Prospective company B has agreed to the proposal." Sales company A then obtains prospective company B's contact information and communicates specific improvement suggestions.

[0808] This invention enables high-quality sales between prospective companies and sales companies, and significantly improves the success rate of telemarketing because proposals tailored to the needs of both parties can be confirmed in advance. This system enables mutually beneficial sales activities through highly accurate matching and sentiment analysis using a generative AI model and emotion engine.

[0809] The following describes the processing flow.

[0810] Step 1:

[0811] Users (prospective companies) open the dedicated website or application and access the free account creation page. Users enter basic information such as company name, contact person's name, email address, and password, and click the registration button.

[0812] Step 2:

[0813] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[0814] Step 3:

[0815] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter detailed information about the challenges and problems their company faces in the problem information form.

[0816] Step 4:

[0817] The server receives the entered problem information and saves it to the database. This registers the problem information of potential companies in the system.

[0818] Step 5:

[0819] The user (sales company) opens the dedicated website or application and accesses the paid account creation page. The user enters basic information such as company name, contact person's name, email address, and password, and clicks the registration button.

[0820] Step 6:

[0821] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[0822] Step 7:

[0823] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter details of the products or services they will be offering in the product information form.

[0824] Step 8:

[0825] The server receives the entered product information and saves it to a database for the generated AI model. This registers the sales company's product information in the system.

[0826] Step 9:

[0827] The server periodically collects information on the problems of prospective companies and the products and services of sales companies from the database. A generative AI model is used to analyze the data on the problems of prospective companies and the products and services of sales companies.

[0828] Step 10:

[0829] The server (generating AI model) uses text mining techniques to extract keywords and context from problem information and product information. Next, it calculates the correlation between problem information and product information and extracts pairs with high correlation.

[0830] Step 11:

[0831] The server notifies prospective companies of highly correlated pairs as proposals. Notifications are sent via email or as alerts in the dashboard.

[0832] Step 12:

[0833] Users (potential companies) receive notifications and review the proposals on their dashboard after logging in.

[0834] Step 13:

[0835] The emotion engine analyzes user (potential company) responses in real time to understand the emotional state of the potential company.

[0836] Step 14:

[0837] The server adaptively modifies the proposal based on emotional information obtained from the emotion engine and re-notifies the prospective company.

[0838] Step 15:

[0839] Users (potential companies) review the revised proposal and click the "Like" button if they are interested.

[0840] Step 16:

[0841] The server receives the "Like!" input and saves that information to its database. At the same time, the server automatically sends a notification to the sales company that a match has been made.

[0842] Step 17:

[0843] The server provides sales companies with contact information for prospective companies. This allows sales companies to contact prospective companies directly and make specific proposals and follow up.

[0844] (Example 2)

[0845] 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".

[0846] This invention aims to improve sales results for both prospective companies and sales companies by efficiently and effectively matching them in sales activities. Conventional sales methods often involve simultaneous approaches to a large number of prospective companies and proposals that do not match the needs of the prospective companies, resulting in decreased sales effectiveness and wasted time and resources. Furthermore, because it is difficult to properly understand the emotions and reactions of prospective companies, the suitability of proposals is low, making it difficult to improve the closing rate.

[0847] 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.

[0848] In this invention, the server includes means for registering information on each company's problems in a database, means for registering product information in the database, means for calculating the correlation between the problem information and the product information using a generative AI model that analyzes the problem information and the product information, means for notifying prospective companies of the proposed content based on the correlation, means for analyzing the prospective company's emotional state using an emotion engine and adapting the proposed content, means for the prospective company to send a "like!" in response to the notification, and means for providing the prospective company's contact information to the sales company when the "like!" is received. This enables appropriate and effective matching of proposed content between prospective companies and sales companies, improving the efficiency of sales activities and the closing rate.

[0849] A "database" is a system for efficiently storing and managing data such as information about a company's problems and product information.

[0850] A "generative AI model" is an artificial intelligence model that extracts keywords and context from specified data and calculates correlations by analyzing the data.

[0851] An "emotion engine" is software or a system that analyzes a user's facial expressions and text feedback to understand the user's emotional state.

[0852] A "prospective company" is a company that has shown interest in a particular product or service and may potentially do business with the company in the future.

[0853] A "sales-oriented company" is a company that provides specific goods or services and intends to sell or provide them to prospective companies.

[0854] "Correlation" is an indicator that shows the relationship or degree of relevance between information about the concerns of prospective companies and product information of sales companies.

[0855] "Proposal details" refer to the detailed information and proposals for products and services that the sales company presents to solve the problems and challenges of the prospective client.

[0856] A "Like" is a type of positive feedback that a prospective company sends to show interest in or concern about a proposal.

[0857] "Contact information" refers to information necessary to contact a prospective company directly, such as the name of the contact person, email address, and phone number.

[0858] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system consists of a server, terminals, and users.

[0859] 1. Registering prospective companies

[0860] Users (prospective companies) create a free account using a dedicated website or application. They enter necessary information such as company name, contact person's name, and email address on the account creation screen. After creating the account, they log in to the platform and enter detailed information about the company's problems and challenges. This information is received by the server and stored in the database.

[0861] Specific example:

[0862] A user (prospective company A) enters their concerns into the platform, such as "We need a new marketing strategy, but we're unsure which direction to take," and registers their findings.

[0863] 2. Registration of sales companies

[0864] Users (sales companies) create paid accounts using a dedicated website or application. They enter necessary information such as company name, contact person's name, email address, and payment information on the account creation screen. After creating the account, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[0865] Specific example:

[0866] The user (sales company B) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[0867] 3. Matching process

[0868] The server collects information on the concerns of prospective companies and the products / services of sales companies from the database. Using a generative AI model, the server analyzes the prospective companies' concerns data and extracts appropriate keywords and context. Simultaneously, it analyzes the sales companies' product / service information to find common keywords and highly relevant information. Based on these analysis results, it extracts pairs with high correlation.

[0869] Specific example:

[0870] The server analyzes prospective company A's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company B is suitable.

[0871] 4. Submitting the proposal

[0872] The server notifies prospective companies of proposals that have been successfully matched by the generated AI model. Notifications are sent via email or as alerts in the dashboard. These notifications also incorporate an emotion engine that analyzes the prospective company's emotional state.

[0873] Specific example:

[0874] The server notifies prospective company A that "a proposal regarding the digital marketing strategy from sales company B has arrived." This notification utilizes an emotion engine, which analyzes the user's response in real time and generates emotion data.

[0875] 5. Sentiment Analysis and Adaptation of Proposals

[0876] The user (potential company) receives a notification and reviews the proposal. The emotion engine analyzes the user's facial expressions and text feedback to understand the user's emotional state. This allows the server to adapt the proposal according to the user's emotions.

[0877] Specific example:

[0878] If the emotion engine detects from prospective company A's facial expressions that they are interested, the server uses that data to enhance the proposal and resends more specific information and related additional suggestions.

[0879] 6. Send a "Like"

[0880] If a user (potential company) is interested, they click the "Like" button. The sentiment engine adds this action to the sentiment data and evaluates the overall level of user interest.

[0881] Specific example:

[0882] When prospective company A sends a "Like," the emotion engine analyzes that reaction and stores it as data that evaluates the user's level of interest.

[0883] 7. Matching successful

[0884] The server receives the "Like!" input and saves the information to its database. At the same time, the server automatically sends a notification of the successful match to the sales company. It also provides the sales company with the prospective company's contact information. The sales company then uses this information to contact the prospective company directly.

[0885] Specific example:

[0886] When the server receives a "Like!" from prospective company A, it notifies sales company B that "Prospective company A has agreed to the proposal." Sales company B obtains prospective company A's contact information and contacts them with specific improvement suggestions.

[0887] This enables high-quality sales interactions between prospective clients and sales companies, allowing for pre-approval of proposals that meet the needs of both parties, thereby improving the efficiency of sales activities and closing rates. By utilizing servers, generative AI models, and emotion engines, highly accurate matching and emotion analysis become possible, resulting in beneficial sales activities for both prospective clients and sales companies.

[0888] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0889] Step 1: Register prospective companies

[0890] Users (prospective companies) create a free account through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the problems and challenges their company faces. This information is received by the server and stored in a database.

[0891] Input: Basic information such as company name, contact person's name, and email address, as well as details of the problem or issue.

[0892] Output: Profiles and problem information of prospective companies registered in the database.

[0893] Specific actions:

[0894] When a user clicks the "Create Account" button, the entered data is sent to the server, and a record of the new prospective company is added to the database. Next, when the user logs in and clicks the "Register Problem Information" button, the entered problem information is sent to the server and saved to the database.

[0895] Step 2: Register the sales company

[0896] Users (sales companies) create paid accounts through a dedicated website or application. They create an account by entering their company name, contact person's name, email address, payment information, etc., on the account creation screen. After creation, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[0897] Input: Company name, contact person name, email address, payment information, and product / service details.

[0898] Output: Profiles and product information of sales companies registered in the database.

[0899] Specific actions:

[0900] When a user clicks the "Create Account" button, the entered data is sent to the server, and a new sales company record is added to the database. Next, when the user logs in and clicks the "Register Product Information" button, the entered product information is sent to the server and saved to the database.

[0901] Step 3: Matching Process

[0902] The server collects information on the concerns of prospective companies and product information from sales companies within a database. Using a generative AI model, the server analyzes the prospective companies' concern data and extracts appropriate keywords and context. Simultaneously, it analyzes the sales companies' product information to find common keywords and highly relevant information. Based on these analysis results, it extracts pairs with high correlation.

[0903] Input: Data on the concerns of prospective companies in the database and product data of sales companies.

[0904] Output: Correlation score and pairs of prospective and sales companies with high correlation.

[0905] Specific actions:

[0906] A scheduled server job executes SQL queries to retrieve data on potential clients' concerns and sales companies' product data from the database. A generative AI model receives this text data and performs keyword extraction and contextual analysis. The server then selects pairs with high correlation scores and saves them to the database.

[0907] Step 4: Submit your proposal

[0908] The server notifies prospective companies of successful matches. Notifications are sent via email or as alerts in the dashboard. These notifications also incorporate an emotion engine that analyzes the prospective company's emotional state.

[0909] Input: Matching results and contact information for prospective companies (email address, etc.)

[0910] Output: Proposal notifications and sentiment data for prospective companies

[0911] Specific actions:

[0912] The server generates a proposal notification when a match is made and sends an email to the prospective company using the SMTP protocol or sends a real-time alert via WebSocket. The sentiment engine analyzes the prospective company's reaction to the notification and generates sentiment data.

[0913] Step 5: Sentiment analysis and adaptation of proposals

[0914] The user (potential company) receives a notification and reviews the proposal. The emotion engine analyzes the user's facial expressions and text feedback to understand the user's emotional state. This allows the server to adapt the proposal to the user's emotions.

[0915] Input: Prospective company's reaction (facial expression, text feedback)

[0916] Output: Sentiment data and adapted suggestions

[0917] Specific actions:

[0918] The user clicks the notification link to view the suggestion details page. The sentiment engine analyzes the camera feed or feedback text and generates a sentiment score. The server receives the sentiment score, updates the suggestion based on it, and generates a new suggestion.

[0919] Step 6: Send a "Like!"

[0920] If a user (potential client) is interested in a proposal, they click the "Like" button. The sentiment engine adds this action to the sentiment data and evaluates the overall level of user interest.

[0921] Input: "Like" click data

[0922] Output: Updated sentiment data

[0923] Specific actions:

[0924] When a user clicks the "Like" button, that information is sent to the server. The emotion engine analyzes this reaction and updates the emotion data. The server saves the updated emotion data to the database.

[0925] Step 7: Matching successful

[0926] The server receives the "Like!" input and saves the information to its database. At the same time, the server automatically sends a notification of the successful match to the sales company. It also provides the sales company with the prospective company's contact information. The sales company then uses this information to contact the prospective company directly.

[0927] Input: "Like" data and contact information of prospective companies

[0928] Output: Notification of successful matching to the sales company and contact information of the prospective company.

[0929] Specific actions:

[0930] When the server receives a "Like" data, it adds it to the database as a new record. At the same time, it sends a matching notification to the sales company using the SMTP protocol. The server securely provides the sales company with the prospect's contact information, preparing the sales company to contact the prospect directly.

[0931] (Application Example 2)

[0932] 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."

[0933] Traditional methods of matching customers with sales staff in physical stores often resulted in products and services not meeting customer needs, making it difficult to improve satisfaction. Furthermore, the inefficient matching of staff and customers within the store led to a lack of personalized service and a diminished customer experience. Additionally, the lack of suggestions that considered the customer's emotional state meant there was no guarantee that suggestions would align with the customer's interests and needs.

[0934] 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.

[0935] In this invention, the server includes means for registering information about each organization's concerns in a database, means for registering product information in the database, means for calculating the correlation between the concern information and the product information using a generative AI model that analyzes the concern information and the product information, means for notifying prospective organizations of the proposed content based on the correlation, means for prospective organizations to send a "Like!" in response to the notification, means for providing the prospective organization's contact information to the providing organization when a "Like!" is received, means for analyzing the prospective organization's emotional state using an emotion engine and adjusting the proposed content, and means for resending the adjusted proposed content. This enables efficient matching of customers and sales staff in physical stores, and further improves customer satisfaction by providing more appropriate suggestions based on the customer's emotional state.

[0936] An "organization" refers to a group of people, such as a company or association, who come together for a specific purpose.

[0937] "Problem information" refers to data about problems and challenges faced by organizations and individuals.

[0938] "Product information" refers to detailed data about the products and services offered.

[0939] A "generative AI model" refers to a model that uses artificial intelligence technology to analyze text data and automatically generate relationships and specific information.

[0940] "Correlation" refers to an indicator that shows the degree of relationship or linkage between two or more data points.

[0941] A "prospective organization" refers to a company or group that may be interested in a particular service or product.

[0942] "Proposal details" refers to information that explains the benefits and advantages of the services or products offered to the prospective organization.

[0943] "Notification" refers to a message or alert used to inform a target person of specific information.

[0944] "Like!" refers to an action that indicates interest in or agreement with a proposal.

[0945] "Contact information" refers to information such as phone numbers and email addresses used to contact prospective organizations.

[0946] "Provider organizations" refer to companies or groups that provide goods or services.

[0947] An "emotion engine" refers to a technology that analyzes a user's emotions and changes the system's output and suggestions according to that emotional state.

[0948] "Adjusted suggestions" refers to suggestions that have been modified by the emotion engine based on the user's emotional state.

[0949] "Resending" refers to the act of sending information that has already been sent once.

[0950] This system is designed to enable efficient matching between customers and sales staff in physical stores. The specific implementation of the system is described below.

[0951] Hardware configuration

[0952] Server: Hosts a database that manages customer and sales staff information, a generative AI model, and an emotion engine.

[0953] Smartphone or smart glasses: Used by customers to access the system, input information, and receive data within the store.

[0954] Display device: Provides a screen for sales staff to review proposals and customer information.

[0955] Software Configuration

[0956] Database: Customer and sales staff information is stored in a database such as SQLite.

[0957] Generative AI Model: We use generative AI models such as OpenAI's GPT-3.5-turbo to analyze text data and generate suggested content.

[0958] Emotion Engine: Uses the emotion analysis model from the Transformers library to analyze the customer's emotional state.

[0959] Data processing and data calculation

[0960] 1. Data Registration

[0961] Customers input information about the products and services they are looking for in the store via their smartphones or smart glasses. This information is sent to a server and stored in a database. Similarly, sales staff register their areas of expertise and the services they can offer in the database.

[0962] 2. Calculation of correlation

[0963] The server periodically collects customer problem information and sales staff expertise information from a database. Using a generative AI model, it analyzes the text data from both sources and extracts appropriate keywords and context. Correlations are calculated using text analysis techniques such as TF-IDF and cosine similarity.

[0964] 3. Notification of proposed content

[0965] Based on calculated correlations, an AI model selects the most appropriate sales staff and generates recommendations for the customer. These recommendations are then communicated to the customer via smartphone or smart glasses.

[0966] 4. Emotion analysis

[0967] Customer reactions to the proposed content are analyzed by an emotion engine. The degree of interest and engagement is evaluated through the customer's facial expressions and text feedback. For example, if a customer provides feedback such as "This is interesting," the engine will judge their emotional state to be highly positive.

[0968] 5. Adjustment and re-notification of the proposed content.

[0969] Based on the results of the sentiment analysis, the proposed content is adapted. If the customer shows interest, the AI ​​model generates more specific information and additional suggestions, and notifies the customer again.

[0970] Specific example

[0971] When information is entered that customer A is looking for a smartphone, a generative AI model is used to calculate the correlation and match customer A with a sales staff member A who is knowledgeable about smartphones. The generative AI model then makes a suggestion such as "This is the latest smartphone," and the emotion engine analyzes customer A's response. If the response is positive, more detailed information and additional suggestions are sent again.

[0972] Example of a prompt

[0973] "Please write down what you would suggest to a customer looking for a new smartphone."

[0974] In this way, efficient matching of customers and sales staff, as well as appropriate recommendations, can be achieved in physical stores.

[0975] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0976] Step 1:

[0977] Entering and registering customer information

[0978] The user (customer) uses a smartphone or smart glasses to input information about the products or services they are looking for in the store. This information includes specific details such as "I'm looking for a new smartphone." The entered information is sent to a server, which registers the received information in a database.

[0979] Input: Information entered by the customer via smartphone or smart glasses.

[0980] Output: Customer information registered in the database

[0981] Step 2:

[0982] Entering and registering sales staff information

[0983] Users (sales staff) use a smartphone or display device to input information about their areas of expertise and the services they can offer. This includes specific details such as "smartphone expert." The entered information is sent to a server, which registers it in a database.

[0984] Input: Information on areas of expertise and services offered entered by sales staff.

[0985] Output: Sales staff information registered in the database

[0986] Step 3:

[0987] Information gathering and analysis

[0988] The server periodically collects customer problem information and sales staff expertise information from the database. A generative AI model is used to analyze this text data and extract appropriate keywords and context. Text analysis techniques such as TF-IDF and cosine similarity are used for this analysis.

[0989] Input: Customer problem information and sales staff expertise information from the database.

[0990] Output: Analyzed keywords and contextual information

[0991] Step 4:

[0992] Calculation of correlation

[0993] The server uses a generative AI model to calculate the correlation between customer problem information and sales staff expertise information based on collected keywords and contextual information. It then extracts highly correlated pairs and performs matching.

[0994] Input: Analyzed keywords and contextual information

[0995] Output: Highly correlated customer-sales staff pairs

[0996] Step 5:

[0997] Proposal generation and notification

[0998] The server uses a generative AI model to generate suggestions based on the information of the matched customer and sales staff. The generated suggestions are then notified to the customer's smartphone or smart glasses.

[0999] Input: Pairs of customers and sales staff with a high correlation

[1000] Output: Proposal content notified to the customer

[1001] Step 6:

[1002] Emotion analysis

[1003] The user (customer) reviews the proposal and inputs their response via smartphone or smart glasses. The server uses an emotion engine to analyze the customer's text feedback and facial expression data to evaluate the customer's emotional state.

[1004] Input: Customer feedback and facial expression data

[1005] Output: Analyzed emotional state data

[1006] Step 7:

[1007] Adjustment and re-notification of the proposed content

[1008] The server adjusts the suggestions based on the sentiment analysis results. If the customer shows interest, the AI ​​model generates more specific information and additional suggestions, and notifies the customer again.

[1009] Input: Analyzed emotional state data

[1010] Output: Adjusted proposal and reminder message

[1011] The above outlines the processing steps for an efficient customer-sales staff matching system in physical stores. This makes it possible to improve the customer experience.

[1012] 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.

[1013] 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.

[1014] 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.

[1015] [Third Embodiment]

[1016] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1017] 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.

[1018] 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).

[1019] 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.

[1020] 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.

[1021] 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).

[1022] 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.

[1023] 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.

[1024] 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.

[1025] 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.

[1026] 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.

[1027] 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".

[1028] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system includes means for registering each company's problem information and product information in a database, calculating correlation using a generative AI model that analyzes them, notifying prospective companies of the proposal content, sending "likes," and providing contact information to sales companies.

[1029] The following explanation uses natural language and includes concrete examples of how the program works.

[1030] 1. Registering prospective companies

[1031] Users (prospective companies) create a free account through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the problems and challenges their company faces. This information is received by the server and stored in a database.

[1032] Specific example:

[1033] A user (prospective company B) enters their concerns into the platform, such as "We need a new marketing strategy, but we're unsure which direction to take," and registers their findings.

[1034] 2. Registration of sales companies

[1035] Users (sales companies) create paid accounts through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[1036] Specific example:

[1037] The user (sales company A) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[1038] 3. Matching process

[1039] The server periodically collects information on the concerns of prospective companies and the products / services of sales companies from the database. Using a generative AI model, it analyzes the prospective companies' concern data and extracts appropriate keywords and context. Furthermore, it analyzes the sales companies' product / service information to find common keywords and highly relevant information. Based on this correlation, it extracts pairs with high correlation.

[1040] Specific example:

[1041] The server analyzes prospective company B's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company A is suitable.

[1042] 4. Submitting the proposal

[1043] The server notifies prospective companies of successful matches. Prospective companies can view the proposal and, if interested, click the "Like" button to send positive feedback.

[1044] Specific example:

[1045] The server notifies prospective company B that "a proposal regarding the digital marketing strategy from sales company A has arrived." Prospective company B reviews the proposal and clicks the "Like" button.

[1046] 5. Matching successful

[1047] When the server receives a "like" from a prospective company, it sends a notification of successful matching to the sales company. At the same time, it provides the sales company with the prospective company's contact information. The sales company then uses the provided contact information to contact the prospective company with a specific proposal.

[1048] Specific example:

[1049] Prospective company B sends a "Like!" and the server notifies sales company A that "Prospective company B has agreed to the proposal." Sales company A obtains prospective company B's contact information and takes specific sales actions via phone or email.

[1050] This invention enables high-quality sales between prospective companies and sales companies. Because proposals tailored to the needs of both parties can be reviewed in advance, the success rate of telemarketing is significantly improved. This system, through highly accurate matching using a generative AI model, enables mutually beneficial sales activities.

[1051] The following describes the processing flow.

[1052] Step 1:

[1053] Users (prospective companies) open the dedicated website or application and access the free account creation page. Users enter basic information such as company name, contact person's name, email address, and password, and click the registration button.

[1054] Step 2:

[1055] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[1056] Step 3:

[1057] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter detailed information about the challenges and problems their company faces in the problem information form.

[1058] Step 4:

[1059] The server receives the entered problem information and saves it to the database. This registers the problem information of potential companies in the system.

[1060] Step 5:

[1061] The user (sales company) opens the dedicated website or application and accesses the paid account creation page. The user enters basic information such as company name, contact person's name, email address, and password, and clicks the registration button.

[1062] Step 6:

[1063] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[1064] Step 7:

[1065] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter details of the products or services they will be offering in the product information form.

[1066] Step 8:

[1067] The server receives the entered product information and saves it to a database for the generated AI model. This registers the sales company's product information in the system.

[1068] Step 9:

[1069] The server periodically collects information on the problems of prospective companies and the products and services of sales companies from the database. A generative AI model is used to analyze the data on the problems of prospective companies and the products and services of sales companies.

[1070] Step 10:

[1071] The server (generating AI model) uses text mining techniques to extract keywords and context from problem information and product information. Next, it calculates the correlation between problem information and product information and extracts pairs with high correlation.

[1072] Step 11:

[1073] The server notifies prospective companies of highly correlated pairs as proposals. Notifications are sent via email or as alerts in the dashboard.

[1074] Step 12:

[1075] Users (potential companies) receive notifications and review the proposals on their dashboard after logging in. If they are interested, users click the "Like" button.

[1076] Step 13:

[1077] The server receives the "Like!" input and saves that information to its database. At the same time, the server automatically sends a notification to the sales company that a match has been made.

[1078] Step 14:

[1079] The server provides sales companies with contact information for prospective companies. This allows sales companies to contact prospective companies directly and make specific proposals and follow up.

[1080] (Example 1)

[1081] 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."

[1082] In traditional sales activities, sales companies often expend considerable effort and time to find potential clients, leading to a high likelihood of wasted contact and failures. Furthermore, it was difficult to create sales proposals that accurately addressed the concerns and challenges of potential clients, making effective matching challenging. A system is needed to improve this situation and enable efficient and effective sales activities.

[1083] 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.

[1084] In this invention, the server includes means for registering information on each company's problems in a database, means for registering product information in the database, means for calculating the correlation between the problem information and the product information using a generative AI model that analyzes the problem information and the product information, means for notifying the target company of the proposed solution based on the correlation, means for the target company to send a "positive response" to the notification, and means for providing the target company's contact information to the sales company when the "positive response" is received. This enables highly accurate matching of the problems of prospective companies and the product information of sales companies, resulting in mutually beneficial sales activities.

[1085] A "database" is a system that permanently stores information and allows for efficient retrieval and management as needed.

[1086] "Problem information" refers to data about problems and challenges faced by companies, which is registered in the system.

[1087] "Product information" refers to detailed data about the products and services offered by the sales company, and is registered in the system.

[1088] A "generative AI model" refers to an algorithm that uses artificial intelligence to analyze data and generate predictions and recommendations.

[1089] "Correlation" refers to a criterion for evaluating the relationships and commonalities between two different datasets.

[1090] A "positive response" refers to an action taken by a prospective company to show a favorable reaction to the proposal, such as clicking "Like."

[1091] "Target companies" refers collectively to prospective companies and sales-related companies registered in the system.

[1092] A "selling company" refers to a company that offers goods or services to a prospective client company.

[1093] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system uses specific hardware and software to perform a series of processes, including data registration, analysis, notification, feedback reception, and contact information provision.

[1094] Hardware and software details

[1095] Server Environment

[1096] Hardware: High-performance server machines (e.g., dual-processor servers or Amazon Web Services as a cloud service)

[1097] software:

[1098] Operating System: Linux-based OS (e.g., Ubuntu Server)

[1099] Database management systems: MySQL, PostgreSQL

[1100] Web servers: Nginx, Apache

[1101] Programming frameworks: Flask and Django using Python

[1102] Generative AI model: OpenAI's GPT-3

[1103] Program processing flow

[1104] This system provides an interface for registering each company's problem information and product information in a database. This allows for centralized management of information on both prospective and sales companies.

[1105] Registration process

[1106] Registration of prospective companies

[1107] Users (potential companies) create a free account through a dedicated website or application and enter detailed information about the problems and challenges their company faces. The server receives this information and stores it in a database.

[1108] As a concrete example, a user (prospective company B) might enter and register a problem on the platform such as, "We need a new marketing strategy, but we're unsure which direction to take."

[1109] Registration of sales companies

[1110] Users (sales companies) create paid accounts and enter detailed information about the products and services they offer. The server receives this information and stores it in its database.

[1111] As a concrete example, a user (sales company A) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[1112] Matching process

[1113] The server uses a generative AI model to analyze prospective companies' problem information and sales companies' product information from the collected database. This model uses text mining techniques to extract keywords and context from the problem information and product information, and calculates their correlation.

[1114] As a concrete example, the server analyzes prospective company B's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company A is suitable. In this way, the optimal proposal is generated.

[1115] Notification and feedback on proposals

[1116] The generated proposal is notified to the prospective company by the server, and the prospective company reviews the proposal upon receiving this notification. If interested, the prospective company sends a "positive response" (e.g., "Like!"). This feedback is sent to the server, and the prospective company's contact information is provided to the sales company.

[1117] As a concrete example, the server notifies prospective company B that "a proposal regarding a digital marketing strategy from sales company A has arrived," and when prospective company B clicks "Like," sales company A obtains prospective company B's contact information.

[1118] Examples of prompt statements

[1119] Please explain the process of analyzing the service and product information provided by sales companies based on the concerns of prospective clients, and then generating the optimal sales proposal based on those results.

[1120] This system enables highly accurate matching between prospective companies and sales companies, allowing for effective sales activities. The use of a generative AI model provides an efficient sales process.

[1121] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1122] Step 1: Create an account for the prospective company

[1123] Input: The user (prospective company) enters the company name, contact person's name, email address, and password on a dedicated website or application.

[1124] Operation: The terminal collects this information and sends it to the server. The server validates the received information and, if there are no problems, saves it to the database.

[1125] Output: The prospective company's account information is registered in the database.

[1126] Step 2: Register information about the problems of potential companies.

[1127] Input: Users (prospective companies) log in to the platform and enter detailed information about their company's problems and challenges on the "Problem / Challenge Input" page.

[1128] Operation: The terminal sends the entered problem information to the server, and the server stores the information in a database.

[1129] Output: Information about the problems of prospective companies is saved in the database.

[1130] Specific operation: The user enters "We need a new marketing strategy, but we're unsure which direction to take" through the terminal and registers.

[1131] Step 3: Create an account for the sales company

[1132] Input: The user (sales company) enters the company name, contact person's name, email address, password, and payment information on the paid account creation page.

[1133] Operation: The device collects this information and sends it to the server. The server validates the received information, and if there are no problems, saves it to the database and sets up the paid account.

[1134] Output: The account information of the sales company is registered in the database.

[1135] Step 4: Register product information of the sales company.

[1136] Input: Users (sales companies) log in to the platform and enter details of the products or services they offer on the "Product Information Input" page.

[1137] Operation: The terminal sends the entered product information to the server, and the server stores the information in a database.

[1138] Output: Product information from the sales company is saved in the database.

[1139] Specific operation: The user enters and registers for the "Digital Marketing Strategy Building Support Service" via their device.

[1140] Step 5: Data Collection

[1141] Input: Information on the problems of prospective companies in the database and product information of sales companies.

[1142] Operation: The server periodically collects information on prospective and sales companies from the database.

[1143] Output: The collected problem information and product information are passed to the AI ​​model for generation.

[1144] Step 6: Data Analysis

[1145] Input: Information on the problems of prospective companies and product information of sales companies.

[1146] Operation: The server analyzes this information using a generative AI model (e.g., OpenAI's GPT-3). It extracts keywords and context using text mining techniques and calculates correlations.

[1147] Output: The results of the correlation analysis are generated.

[1148] Specific operation: The generating AI model extracts keywords such as "marketing strategy" and "direction" from the concerns of prospective company B, and extracts keywords such as "digital marketing" and "implementation support" from the product information of sales company A.

[1149] Step 7: Generating the proposal

[1150] Input: Results of correlation analysis by a generative AI model.

[1151] Operation: The server generates suggestions based on this and saves them to the database.

[1152] Output: The generated suggestions are saved to the database.

[1153] Step 8: Notification of Proposal

[1154] Input: Generated suggestion content.

[1155] Operation: The server notifies prospective companies of the proposal details. The notification is sent to the prospective company's terminal.

[1156] Output: A notification is sent to the prospective company.

[1157] Specific action: The server notifies prospective company B that "a proposal regarding the digital marketing strategy from sales company A has been received."

[1158] Step 9: Receive Feedback

[1159] Input: Feedback from prospective companies on the proposal (e.g., "Like!").

[1160] Operation: The terminal sends feedback from prospective companies to the server, and the server stores the feedback in a database.

[1161] Output: Feedback is saved to the database.

[1162] Specific operation: When prospective company B clicks "Like," the server receives feedback.

[1163] Step 10: Provide contact information

[1164] Input: Feedback ("Likes") from prospective companies and their contact information.

[1165] Operation: The server reviews the feedback and provides the prospective company's contact information to the sales company.

[1166] Output: Contact information is provided to the sales company.

[1167] Specific operation: The server notifies sales company A that "prospective company B has agreed to the proposal" and provides contact information.

[1168] (Application Example 1)

[1169] 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."

[1170] In the traditional marketing and advertising industry, it was difficult to effectively match the challenges faced by advertisers with the services offered by marketing companies. As a result, advertisers were unable to find the optimal advertising services, and marketing companies were unable to conduct effective sales activities. Furthermore, the process of quickly and efficiently proposing highly relevant advertising services, obtaining the advertiser's consent, and providing contact information was cumbersome.

[1171] 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.

[1172] In this invention, the server includes means for registering information on each company's problems in a database, means for registering product information in a database, means for calculating correlation using a generative AI model that analyzes the problem information and the product information, means for notifying the content of the proposal, means for prospective companies to send "likes", means for providing contact information, means for registering detailed information of advertising services provided by marketing companies, means for viewing the content of advertising services proposed based on the challenges faced by advertisers, and means for providing product information when the advertiser agrees to the proposed content. This enables effective matching between advertisers with problems and appropriate marketing companies, and allows for the rapid proposal of highly relevant advertising services and simplification of the communication process.

[1173] A "database" is a system for efficiently storing and managing information about a company's problems and products.

[1174] "Problem information" refers to information that includes the challenges and problems that companies face.

[1175] "Product information" refers to detailed information about the products and services offered by the sales company.

[1176] A "generative AI model" is an artificial intelligence technology that analyzes registered data and calculates its correlations.

[1177] "Correlation" refers to the degree of connection between information about problems and information about products, indicating a high degree of agreement.

[1178] "Means of notifying about the proposed content" refers to a function for informing prospective companies about appropriate product proposals.

[1179] "Like!" is a way for prospective companies to send positive feedback on a proposal.

[1180] "Contact information" refers to information provided by a prospective company that allows them to be contacted.

[1181] A "marketing company" is a company that provides advertising and promotional services.

[1182] "Detailed information about advertising services" refers to information that includes specific details about the advertising provided by a marketing company.

[1183] An "advertiser" is a company that wishes to promote its products or services.

[1184] "Challenges" refer to problems or requests that advertisers have that need to be resolved.

[1185] "Means for viewing the proposed advertising service details" refers to a function that allows advertisers to confirm the details of the advertising services provided.

[1186] "Means of providing product information" refers to a function that provides relevant information to advertisers if they agree to the proposal.

[1187] This invention is a system for achieving efficient and effective matching between advertisers and marketing companies. This system includes means for registering each company's problem information and product information in a database, calculating correlation using a generative AI model that analyzes them, notifying advertisers of proposed solutions, sending "likes," and providing contact information to marketing companies.

[1188] Hardware to use

[1189] server

[1190] Smartphone

[1191] Software to use

[1192] Database: MySQL

[1193] Application server: Node.js

[1194] Frontend: React Native

[1195] Generative AI model: OpenAI GPT-4

[1196] Data processing and calculations

[1197] The server receives data sent by the user and stores it in a database. Then, it uses a generative AI model (OpenAI GPT-4) to calculate the correlation between problem information and product information in the database.

[1198] in particular,

[1199] 1. The data collection server collects information from advertisers (companies facing problems) and marketing companies (advertising service providers) and stores it in a MySQL database.

[1200] Advertisers input information about their challenges through the application. For example, they might enter a problem such as, "We want to increase awareness of our new product, but our target market is unclear."

[1201] Marketing companies register details of the advertising services they offer in a database. For example, they might enter product information such as "social media marketing services."

[1202] 2. The data analysis server periodically analyzes the information in the database using a generative AI model (GPT-4), extracting keywords and context from problem information and product information, and calculating their correlation.

[1203] For example, the context of information such as "We need a new marketing strategy" and product information such as "Digital marketing strategy development support service" is analyzed to extract highly correlated pairs.

[1204] 3. The proposal sending server notifies advertisers who have entered problem information of proposals from marketing companies that have product information deemed to be highly correlated.

[1205] Advertisers can review their proposals through the application and, if interested, send positive feedback by clicking the "Like" button.

[1206] 4. Provision of Contact Information: When an advertiser sends a "Like," the server sends a notification of the successful match to the marketing company and provides the advertiser's contact information.

[1207] Marketing companies use the provided contact information to make detailed proposals and sell services to advertisers.

[1208] Specific example

[1209] Examples of prompts for generative AI models

[1210] "User-entered text: 'We need a new marketing strategy, but we're unsure which direction to take.'"

[1211] "Text for matching candidates: 'Digital Marketing Strategy Development Support Service'"

[1212] "Generates prompt messages for an AI model that calculates the correlation between the two and finds the optimal pair."

[1213] Sample prompt message

[1214] The prospective company's concern: "We need a new marketing strategy, but we're unsure which direction to take."

[1215] Sales company's product / service: "Support service for building digital marketing strategies"

[1216] Based on this information, please calculate the correlation between the two.

[1217] This enables efficient and effective matching between advertisers and marketing companies, facilitating the resolution of advertisers' challenges and the smooth progress of marketing companies' sales activities.

[1218] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1219] Step 1:

[1220] Data entry

[1221] Users (advertisers) input information about their company's challenges through a smartphone application. For example, they might input a challenge such as, "We want to increase awareness of our new product, but our target market is unclear." Users (marketing companies) input information about the advertising services they offer. For example, they might input product information such as, "Social Media Marketing Services."

[1222] Input and output

[1223] Input: Information on the advertiser's problems and information on the marketing company's products / services.

[1224] Output: Problem information and product information stored in the database

[1225] Specific actions

[1226] The information entered by the user is received by the server and stored in a MySQL database.

[1227] Step 2:

[1228] Data analysis

[1229] The server periodically uses a generative AI model (OpenAI GPT-4) to analyze problem information and product information in the database. The server extracts keywords and context related to the issues from the problem information and keywords and context related to the services provided from the product information.

[1230] Input and output

[1231] Input: Problem information and product information stored in the database

[1232] Output: Extracted keywords and analysis results

[1233] Specific actions

[1234] Generative AI models use text mining techniques to extract keywords and context, and discover highly correlated information.

[1235] Step 3:

[1236] Calculation of correlation

[1237] The server calculates the correlation between problem information and product information based on the analysis results of the generative AI model (GPT-4). It then generates an overall score to find appropriate matching candidates.

[1238] Input and output

[1239] Input: Analyzed keywords and analysis results

[1240] Output: Correlation score and matching candidates

[1241] Specific actions

[1242] The generative AI model generates prompt sentences, compares the information from both sides to calculate the correlation, and determines the optimal pair.

[1243] Step 4:

[1244] Notification of proposed content

[1245] The server notifies advertisers facing challenges with proposals from highly correlated marketing companies. Advertisers can then review the proposals through a smartphone application.

[1246] Input and output

[1247] Input: Matched suggestion information

[1248] Output: Proposal notification to advertisers

[1249] Specific actions

[1250] The server notifies the advertiser of the proposal via push notification or email. The advertiser then reviews the proposal within the application.

[1251] Step 5:

[1252] Sending a "Like"

[1253] If an advertiser is interested in a proposal, they can send positive feedback by clicking the "Like" button.

[1254] Input and output

[1255] Input: Advertiser's "Like" feedback

[1256] Output: Notification of receiving a "Like"

[1257] Specific actions

[1258] When an advertiser clicks the "Like" button, that information is sent to the server and recorded.

[1259] Step 6:

[1260] Providing contact information

[1261] After receiving a "like" from an advertiser, the server sends a notification of the successful match to the marketing company and provides the advertiser's contact information.

[1262] Input and output

[1263] Input: Information on received "Likes"

[1264] Output: Notification of providing contact information to marketing companies

[1265] Specific actions

[1266] The server sends a notification to the marketing company that a match has been made and provides the advertiser's contact information. The marketing company then uses the provided contact information to make specific proposals and sales pitches to the advertiser.

[1267] The above steps enable efficient matching and effective advertising proposals between advertisers and marketing companies.

[1268] 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.

[1269] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system includes means for registering each company's problem information and product information in a database, calculating correlation using a generative AI model that analyzes them, notifying prospective companies of the proposed content, sending "likes," and providing contact information to sales companies. Furthermore, in this invention, by combining it with an emotion engine that recognizes user emotions, the proposed content can be adapted even more effectively.

[1270] The following explanation uses natural language and includes concrete examples of how the program works.

[1271] 1. Registering prospective companies

[1272] Users (prospective companies) create a free account through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the problems and challenges their company faces. This information is received by the server and stored in a database.

[1273] Specific example:

[1274] A user (prospective company B) enters their concerns into the platform, such as "We need a new marketing strategy, but we're unsure which direction to take," and registers their findings.

[1275] 2. Registration of sales companies

[1276] Users (sales companies) create paid accounts through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[1277] Specific example:

[1278] The user (sales company A) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[1279] 3. Matching process

[1280] The server periodically collects information on the concerns of prospective companies and the products / services of sales companies from the database. Using a generative AI model, it analyzes the prospective companies' concern data and extracts appropriate keywords and context. Furthermore, it analyzes the sales companies' product / service information to find common keywords and highly relevant information. Based on this correlation, it extracts pairs with high correlation.

[1281] Specific example:

[1282] The server analyzes prospective company B's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company A is suitable.

[1283] 4. Submitting the proposal

[1284] The server notifies prospective companies of successful matches. Notifications are sent via email or as alerts in the dashboard. Furthermore, this proposal notification incorporates a sentiment engine that analyzes the prospective company's emotional state.

[1285] Specific example:

[1286] The server notifies prospective company B that "a proposal regarding the digital marketing strategy from sales company A has arrived." This notification utilizes an emotion engine, which analyzes the user's response in real time and generates emotion data.

[1287] 5. Sentiment Analysis and Adaptation of Proposals

[1288] The user (potential company) receives a notification and reviews the proposal. The emotion engine analyzes the user's facial expressions and text feedback to understand the user's emotional state. This allows the server to adapt the proposal according to the user's emotions.

[1289] Specific example:

[1290] If the emotion engine detects that prospective company B is showing interest based on their facial expressions, the server uses that data to enhance the proposal and resends more specific information and related additional suggestions.

[1291] 6. Send a "Like"

[1292] If a user (potential company) is interested, they click the "Like" button. The sentiment engine adds this action to the sentiment data and evaluates the overall level of user interest.

[1293] Specific example:

[1294] When prospective company B sends a "Like," the emotion engine analyzes that reaction and stores it as data that evaluates the user's level of interest.

[1295] 7. Matching successful

[1296] The server receives the "Like!" input and saves the information to its database. At the same time, the server automatically sends a notification of the successful match to the sales company. It also provides the sales company with the prospective company's contact information. The sales company then uses this information to contact the prospective company directly.

[1297] Specific example:

[1298] Upon receiving a "Like!" from prospective company B, the server notifies sales company A that "Prospective company B has agreed to the proposal." Sales company A then obtains prospective company B's contact information and communicates specific improvement suggestions.

[1299] This invention enables high-quality sales between prospective companies and sales companies, and significantly improves the success rate of telemarketing because proposals tailored to the needs of both parties can be confirmed in advance. This system enables mutually beneficial sales activities through highly accurate matching and sentiment analysis using a generative AI model and emotion engine.

[1300] The following describes the processing flow.

[1301] Step 1:

[1302] Users (prospective companies) open the dedicated website or application and access the free account creation page. Users enter basic information such as company name, contact person's name, email address, and password, and click the registration button.

[1303] Step 2:

[1304] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[1305] Step 3:

[1306] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter detailed information about the challenges and problems their company faces in the problem information form.

[1307] Step 4:

[1308] The server receives the entered problem information and saves it to the database. This registers the problem information of potential companies in the system.

[1309] Step 5:

[1310] The user (sales company) opens the dedicated website or application and accesses the paid account creation page. The user enters basic information such as company name, contact person's name, email address, and password, and clicks the registration button.

[1311] Step 6:

[1312] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[1313] Step 7:

[1314] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter details of the products or services they will be offering in the product information form.

[1315] Step 8:

[1316] The server receives the entered product information and saves it to a database for the generated AI model. This registers the sales company's product information in the system.

[1317] Step 9:

[1318] The server periodically collects information on the problems of prospective companies and the products and services of sales companies from the database. A generative AI model is used to analyze the data on the problems of prospective companies and the products and services of sales companies.

[1319] Step 10:

[1320] The server (generating AI model) uses text mining techniques to extract keywords and context from problem information and product information. Next, it calculates the correlation between problem information and product information and extracts pairs with high correlation.

[1321] Step 11:

[1322] The server notifies prospective companies of highly correlated pairs as proposals. Notifications are sent via email or as alerts in the dashboard.

[1323] Step 12:

[1324] Users (potential companies) receive notifications and review the proposals on their dashboard after logging in.

[1325] Step 13:

[1326] The emotion engine analyzes user (potential company) responses in real time to understand the emotional state of the potential company.

[1327] Step 14:

[1328] The server adaptively modifies the proposal based on emotional information obtained from the emotion engine and re-notifies the prospective company.

[1329] Step 15:

[1330] Users (potential companies) review the revised proposal and click the "Like" button if they are interested.

[1331] Step 16:

[1332] The server receives the "Like!" input and saves that information to its database. At the same time, the server automatically sends a notification to the sales company that a match has been made.

[1333] Step 17:

[1334] The server provides sales companies with contact information for prospective companies. This allows sales companies to contact prospective companies directly and make specific proposals and follow up.

[1335] (Example 2)

[1336] 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."

[1337] This invention aims to improve sales results for both prospective companies and sales companies by efficiently and effectively matching them in sales activities. Conventional sales methods often involve simultaneous approaches to a large number of prospective companies and proposals that do not match the needs of the prospective companies, resulting in decreased sales effectiveness and wasted time and resources. Furthermore, because it is difficult to properly understand the emotions and reactions of prospective companies, the suitability of proposals is low, making it difficult to improve the closing rate.

[1338] 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.

[1339] In this invention, the server includes means for registering information on each company's problems in a database, means for registering product information in the database, means for calculating the correlation between the problem information and the product information using a generative AI model that analyzes the problem information and the product information, means for notifying prospective companies of the proposed content based on the correlation, means for analyzing the prospective company's emotional state using an emotion engine and adapting the proposed content, means for the prospective company to send a "like!" in response to the notification, and means for providing the prospective company's contact information to the sales company when the "like!" is received. This enables appropriate and effective matching of proposed content between prospective companies and sales companies, improving the efficiency of sales activities and the closing rate.

[1340] A "database" is a system for efficiently storing and managing data such as information about a company's problems and product information.

[1341] A "generative AI model" is an artificial intelligence model that extracts keywords and context from specified data and calculates correlations by analyzing the data.

[1342] An "emotion engine" is software or a system that analyzes a user's facial expressions and text feedback to understand the user's emotional state.

[1343] A "prospective company" is a company that has shown interest in a particular product or service and may potentially do business with the company in the future.

[1344] A "sales-oriented company" is a company that provides specific goods or services and intends to sell or provide them to prospective companies.

[1345] "Correlation" is an indicator that shows the relationship or degree of relevance between information about the concerns of prospective companies and product information of sales companies.

[1346] "Proposal details" refer to the detailed information and proposals for products and services that the sales company presents to solve the problems and challenges of the prospective client.

[1347] A "Like" is a type of positive feedback that a prospective company sends to show interest in or concern about a proposal.

[1348] "Contact information" refers to information necessary to contact a prospective company directly, such as the name of the contact person, email address, and phone number.

[1349] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system consists of a server, terminals, and users.

[1350] 1. Registering prospective companies

[1351] Users (prospective companies) create a free account using a dedicated website or application. They enter necessary information such as company name, contact person's name, and email address on the account creation screen. After creating the account, they log in to the platform and enter detailed information about the company's problems and challenges. This information is received by the server and stored in the database.

[1352] Specific example:

[1353] A user (prospective company A) enters their concerns into the platform, such as "We need a new marketing strategy, but we're unsure which direction to take," and registers their findings.

[1354] 2. Registration of sales companies

[1355] Users (sales companies) create paid accounts using a dedicated website or application. They enter necessary information such as company name, contact person's name, email address, and payment information on the account creation screen. After creating the account, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[1356] Specific example:

[1357] The user (sales company B) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[1358] 3. Matching process

[1359] The server collects information on the concerns of prospective companies and the products / services of sales companies from the database. Using a generative AI model, the server analyzes the prospective companies' concerns data and extracts appropriate keywords and context. Simultaneously, it analyzes the sales companies' product / service information to find common keywords and highly relevant information. Based on these analysis results, it extracts pairs with high correlation.

[1360] Specific example:

[1361] The server analyzes prospective company A's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company B is suitable.

[1362] 4. Submitting the proposal

[1363] The server notifies prospective companies of proposals that have been successfully matched by the generated AI model. Notifications are sent via email or as alerts in the dashboard. These notifications also incorporate an emotion engine that analyzes the prospective company's emotional state.

[1364] Specific example:

[1365] The server notifies prospective company A that "a proposal regarding the digital marketing strategy from sales company B has arrived." This notification utilizes an emotion engine, which analyzes the user's response in real time and generates emotion data.

[1366] 5. Sentiment Analysis and Adaptation of Proposals

[1367] The user (potential company) receives a notification and reviews the proposal. The emotion engine analyzes the user's facial expressions and text feedback to understand the user's emotional state. This allows the server to adapt the proposal according to the user's emotions.

[1368] Specific example:

[1369] If the emotion engine detects from prospective company A's facial expressions that they are interested, the server uses that data to enhance the proposal and resends more specific information and related additional suggestions.

[1370] 6. Send a "Like"

[1371] If a user (potential company) is interested, they click the "Like" button. The sentiment engine adds this action to the sentiment data and evaluates the overall level of user interest.

[1372] Specific example:

[1373] When prospective company A sends a "Like," the emotion engine analyzes that reaction and stores it as data that evaluates the user's level of interest.

[1374] 7. Matching successful

[1375] The server receives the "Like!" input and saves the information to its database. At the same time, the server automatically sends a notification of the successful match to the sales company. It also provides the sales company with the prospective company's contact information. The sales company then uses this information to contact the prospective company directly.

[1376] Specific example:

[1377] When the server receives a "Like!" from prospective company A, it notifies sales company B that "Prospective company A has agreed to the proposal." Sales company B obtains prospective company A's contact information and contacts them with specific improvement suggestions.

[1378] This enables high-quality sales interactions between prospective clients and sales companies, allowing for pre-approval of proposals that meet the needs of both parties, thereby improving the efficiency of sales activities and closing rates. By utilizing servers, generative AI models, and emotion engines, highly accurate matching and emotion analysis become possible, resulting in beneficial sales activities for both prospective clients and sales companies.

[1379] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1380] Step 1: Register prospective companies

[1381] Users (prospective companies) create a free account through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the problems and challenges their company faces. This information is received by the server and stored in a database.

[1382] Input: Basic information such as company name, contact person's name, and email address, as well as details of the problem or issue.

[1383] Output: Profiles and problem information of prospective companies registered in the database.

[1384] Specific actions:

[1385] When a user clicks the "Create Account" button, the entered data is sent to the server, and a record of the new prospective company is added to the database. Next, when the user logs in and clicks the "Register Problem Information" button, the entered problem information is sent to the server and saved to the database.

[1386] Step 2: Register the sales company

[1387] Users (sales companies) create paid accounts through a dedicated website or application. They create an account by entering their company name, contact person's name, email address, payment information, etc., on the account creation screen. After creation, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[1388] Input: Company name, contact person name, email address, payment information, and product / service details.

[1389] Output: Profiles and product information of sales companies registered in the database.

[1390] Specific actions:

[1391] When a user clicks the "Create Account" button, the entered data is sent to the server, and a new sales company record is added to the database. Next, when the user logs in and clicks the "Register Product Information" button, the entered product information is sent to the server and saved to the database.

[1392] Step 3: Matching Process

[1393] The server collects information on the concerns of prospective companies and product information from sales companies within a database. Using a generative AI model, the server analyzes the prospective companies' concern data and extracts appropriate keywords and context. Simultaneously, it analyzes the sales companies' product information to find common keywords and highly relevant information. Based on these analysis results, it extracts pairs with high correlation.

[1394] Input: Data on the concerns of prospective companies in the database and product data of sales companies.

[1395] Output: Correlation score and pairs of prospective and sales companies with high correlation.

[1396] Specific actions:

[1397] A scheduled server job executes SQL queries to retrieve data on potential clients' concerns and sales companies' product data from the database. A generative AI model receives this text data and performs keyword extraction and contextual analysis. The server then selects pairs with high correlation scores and saves them to the database.

[1398] Step 4: Submit your proposal

[1399] The server notifies prospective companies of successful matches. Notifications are sent via email or as alerts in the dashboard. These notifications also incorporate an emotion engine that analyzes the prospective company's emotional state.

[1400] Input: Matching results and contact information for prospective companies (email address, etc.)

[1401] Output: Proposal notifications and sentiment data for prospective companies

[1402] Specific actions:

[1403] The server generates a proposal notification when a match is made and sends an email to the prospective company using the SMTP protocol or sends a real-time alert via WebSocket. The sentiment engine analyzes the prospective company's reaction to the notification and generates sentiment data.

[1404] Step 5: Sentiment analysis and adaptation of proposals

[1405] The user (potential company) receives a notification and reviews the proposal. The emotion engine analyzes the user's facial expressions and text feedback to understand the user's emotional state. This allows the server to adapt the proposal to the user's emotions.

[1406] Input: Prospective company's reaction (facial expression, text feedback)

[1407] Output: Sentiment data and adapted suggestions

[1408] Specific actions:

[1409] The user clicks the notification link to view the suggestion details page. The sentiment engine analyzes the camera feed or feedback text and generates a sentiment score. The server receives the sentiment score, updates the suggestion based on it, and generates a new suggestion.

[1410] Step 6: Send a "Like!"

[1411] If a user (potential client) is interested in a proposal, they click the "Like" button. The sentiment engine adds this action to the sentiment data and evaluates the overall level of user interest.

[1412] Input: "Like" click data

[1413] Output: Updated sentiment data

[1414] Specific actions:

[1415] When a user clicks the "Like" button, that information is sent to the server. The emotion engine analyzes this reaction and updates the emotion data. The server saves the updated emotion data to the database.

[1416] Step 7: Matching successful

[1417] The server receives the "Like!" input and saves the information to its database. At the same time, the server automatically sends a notification of the successful match to the sales company. It also provides the sales company with the prospective company's contact information. The sales company then uses this information to contact the prospective company directly.

[1418] Input: "Like" data and contact information of prospective companies

[1419] Output: Notification of successful matching to the sales company and contact information of the prospective company.

[1420] Specific actions:

[1421] When the server receives a "Like" data, it adds it to the database as a new record. At the same time, it sends a matching notification to the sales company using the SMTP protocol. The server securely provides the sales company with the prospect's contact information, preparing the sales company to contact the prospect directly.

[1422] (Application Example 2)

[1423] 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."

[1424] Traditional methods of matching customers with sales staff in physical stores often resulted in products and services not meeting customer needs, making it difficult to improve satisfaction. Furthermore, the inefficient matching of staff and customers within the store led to a lack of personalized service and a diminished customer experience. Additionally, the lack of suggestions that considered the customer's emotional state meant there was no guarantee that suggestions would align with the customer's interests and needs.

[1425] 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.

[1426] In this invention, the server includes means for registering information about each organization's concerns in a database, means for registering product information in the database, means for calculating the correlation between the concern information and the product information using a generative AI model that analyzes the concern information and the product information, means for notifying prospective organizations of the proposed content based on the correlation, means for prospective organizations to send a "Like!" in response to the notification, means for providing the prospective organization's contact information to the providing organization when a "Like!" is received, means for analyzing the prospective organization's emotional state using an emotion engine and adjusting the proposed content, and means for resending the adjusted proposed content. This enables efficient matching of customers and sales staff in physical stores, and further improves customer satisfaction by providing more appropriate suggestions based on the customer's emotional state.

[1427] An "organization" refers to a group of people, such as a company or association, who come together for a specific purpose.

[1428] "Problem information" refers to data about problems and challenges faced by organizations and individuals.

[1429] "Product information" refers to detailed data about the products and services offered.

[1430] A "generative AI model" refers to a model that uses artificial intelligence technology to analyze text data and automatically generate relationships and specific information.

[1431] "Correlation" refers to an indicator that shows the degree of relationship or linkage between two or more data points.

[1432] A "prospective organization" refers to a company or group that may be interested in a particular service or product.

[1433] "Proposal details" refers to information that explains the benefits and advantages of the services or products offered to the prospective organization.

[1434] "Notification" refers to a message or alert used to inform a target person of specific information.

[1435] "Like!" refers to an action that indicates interest in or agreement with a proposal.

[1436] "Contact information" refers to information such as phone numbers and email addresses used to contact prospective organizations.

[1437] "Provider organizations" refer to companies or groups that provide goods or services.

[1438] An "emotion engine" refers to a technology that analyzes a user's emotions and changes the system's output and suggestions according to that emotional state.

[1439] "Adjusted suggestions" refers to suggestions that have been modified by the emotion engine based on the user's emotional state.

[1440] "Resending" refers to the act of sending information that has already been sent once.

[1441] This system is designed to enable efficient matching between customers and sales staff in physical stores. The specific implementation of the system is described below.

[1442] Hardware configuration

[1443] Server: Hosts a database that manages customer and sales staff information, a generative AI model, and an emotion engine.

[1444] Smartphone or smart glasses: Used by customers to access the system, input information, and receive data within the store.

[1445] Display device: Provides a screen for sales staff to review proposals and customer information.

[1446] Software Configuration

[1447] Database: Customer and sales staff information is stored in a database such as SQLite.

[1448] Generative AI Model: We use generative AI models such as OpenAI's GPT-3.5-turbo to analyze text data and generate suggested content.

[1449] Emotion Engine: Uses the emotion analysis model from the Transformers library to analyze the customer's emotional state.

[1450] Data processing and data calculation

[1451] 1. Data Registration

[1452] Customers input information about the products and services they are looking for in the store via their smartphones or smart glasses. This information is sent to a server and stored in a database. Similarly, sales staff register their areas of expertise and the services they can offer in the database.

[1453] 2. Calculation of correlation

[1454] The server periodically collects customer problem information and sales staff expertise information from a database. Using a generative AI model, it analyzes the text data from both sources and extracts appropriate keywords and context. Correlations are calculated using text analysis techniques such as TF-IDF and cosine similarity.

[1455] 3. Notification of proposed content

[1456] Based on calculated correlations, an AI model selects the most appropriate sales staff and generates recommendations for the customer. These recommendations are then communicated to the customer via smartphone or smart glasses.

[1457] 4. Emotion analysis

[1458] Customer reactions to the proposed content are analyzed by an emotion engine. The degree of interest and engagement is evaluated through the customer's facial expressions and text feedback. For example, if a customer provides feedback such as "This is interesting," the engine will judge their emotional state to be highly positive.

[1459] 5. Adjustment and re-notification of the proposed content.

[1460] Based on the results of the sentiment analysis, the proposed content is adapted. If the customer shows interest, the AI ​​model generates more specific information and additional suggestions, and notifies the customer again.

[1461] Specific example

[1462] When information is entered that customer A is looking for a smartphone, a generative AI model is used to calculate the correlation and match customer A with a sales staff member A who is knowledgeable about smartphones. The generative AI model then makes a suggestion such as "This is the latest smartphone," and the emotion engine analyzes customer A's response. If the response is positive, more detailed information and additional suggestions are sent again.

[1463] Example of a prompt

[1464] "Please write down what you would suggest to a customer looking for a new smartphone."

[1465] In this way, efficient matching of customers and sales staff, as well as appropriate recommendations, can be achieved in physical stores.

[1466] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1467] Step 1:

[1468] Entering and registering customer information

[1469] The user (customer) uses a smartphone or smart glasses to input information about the products or services they are looking for in the store. This information includes specific details such as "I'm looking for a new smartphone." The entered information is sent to a server, which registers the received information in a database.

[1470] Input: Information entered by the customer via smartphone or smart glasses.

[1471] Output: Customer information registered in the database

[1472] Step 2:

[1473] Entering and registering sales staff information

[1474] Users (sales staff) use a smartphone or display device to input information about their areas of expertise and the services they can offer. This includes specific details such as "smartphone expert." The entered information is sent to a server, which registers it in a database.

[1475] Input: Information on areas of expertise and services offered entered by sales staff.

[1476] Output: Sales staff information registered in the database

[1477] Step 3:

[1478] Information gathering and analysis

[1479] The server periodically collects customer problem information and sales staff expertise information from the database. A generative AI model is used to analyze this text data and extract appropriate keywords and context. Text analysis techniques such as TF-IDF and cosine similarity are used for this analysis.

[1480] Input: Customer problem information and sales staff expertise information from the database.

[1481] Output: Analyzed keywords and contextual information

[1482] Step 4:

[1483] Calculation of correlation

[1484] The server uses a generative AI model to calculate the correlation between customer problem information and sales staff expertise information based on collected keywords and contextual information. It then extracts highly correlated pairs and performs matching.

[1485] Input: Analyzed keywords and contextual information

[1486] Output: Highly correlated customer-sales staff pairs

[1487] Step 5:

[1488] Proposal generation and notification

[1489] The server uses a generative AI model to generate suggestions based on the information of the matched customer and sales staff. The generated suggestions are then notified to the customer's smartphone or smart glasses.

[1490] Input: Pairs of customers and sales staff with a high correlation

[1491] Output: Proposal content notified to the customer

[1492] Step 6:

[1493] Emotion analysis

[1494] The user (customer) reviews the proposal and inputs their response via smartphone or smart glasses. The server uses an emotion engine to analyze the customer's text feedback and facial expression data to evaluate the customer's emotional state.

[1495] Input: Customer feedback and facial expression data

[1496] Output: Analyzed emotional state data

[1497] Step 7:

[1498] Adjustment and re-notification of the proposed content

[1499] The server adjusts the suggestions based on the sentiment analysis results. If the customer shows interest, the AI ​​model generates more specific information and additional suggestions, and notifies the customer again.

[1500] Input: Analyzed emotional state data

[1501] Output: Adjusted proposal and reminder message

[1502] The above outlines the processing steps for an efficient customer-sales staff matching system in physical stores. This makes it possible to improve the customer experience.

[1503] 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.

[1504] 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.

[1505] 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.

[1506] [Fourth Embodiment]

[1507] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1508] 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.

[1509] 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).

[1510] 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.

[1511] 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.

[1512] 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).

[1513] 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.

[1514] 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.

[1515] 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.

[1516] 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.

[1517] 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.

[1518] 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.

[1519] 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".

[1520] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system includes means for registering each company's problem information and product information in a database, calculating correlation using a generative AI model that analyzes them, notifying prospective companies of the proposal content, sending "likes," and providing contact information to sales companies.

[1521] The following explanation uses natural language and includes concrete examples of how the program works.

[1522] 1. Registering prospective companies

[1523] Users (prospective companies) create a free account through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the problems and challenges their company faces. This information is received by the server and stored in a database.

[1524] Specific example:

[1525] A user (prospective company B) enters their concerns into the platform, such as "We need a new marketing strategy, but we're unsure which direction to take," and registers their findings.

[1526] 2. Registration of sales companies

[1527] Users (sales companies) create paid accounts through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[1528] Specific example:

[1529] The user (sales company A) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[1530] 3. Matching process

[1531] The server periodically collects information on the concerns of prospective companies and the products / services of sales companies from the database. Using a generative AI model, it analyzes the prospective companies' concern data and extracts appropriate keywords and context. Furthermore, it analyzes the sales companies' product / service information to find common keywords and highly relevant information. Based on this correlation, it extracts pairs with high correlation.

[1532] Specific example:

[1533] The server analyzes prospective company B's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company A is suitable.

[1534] 4. Submitting the proposal

[1535] The server notifies prospective companies of successful matches. Prospective companies can view the proposal and, if interested, click the "Like" button to send positive feedback.

[1536] Specific example:

[1537] The server notifies prospective company B that "a proposal regarding the digital marketing strategy from sales company A has arrived." Prospective company B reviews the proposal and clicks the "Like" button.

[1538] 5. Matching successful

[1539] When the server receives a "like" from a prospective company, it sends a notification of successful matching to the sales company. At the same time, it provides the sales company with the prospective company's contact information. The sales company then uses the provided contact information to contact the prospective company with a specific proposal.

[1540] Specific example:

[1541] Prospective company B sends a "Like!" and the server notifies sales company A that "Prospective company B has agreed to the proposal." Sales company A obtains prospective company B's contact information and takes specific sales actions via phone or email.

[1542] This invention enables high-quality sales between prospective companies and sales companies. Because proposals tailored to the needs of both parties can be reviewed in advance, the success rate of telemarketing is significantly improved. This system, through highly accurate matching using a generative AI model, enables mutually beneficial sales activities.

[1543] The following describes the processing flow.

[1544] Step 1:

[1545] Users (prospective companies) open the dedicated website or application and access the free account creation page. Users enter basic information such as company name, contact person's name, email address, and password, and click the registration button.

[1546] Step 2:

[1547] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[1548] Step 3:

[1549] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter detailed information about the challenges and problems their company faces in the problem information form.

[1550] Step 4:

[1551] The server receives the entered problem information and saves it to the database. This registers the problem information of potential companies in the system.

[1552] Step 5:

[1553] The user (sales company) opens the dedicated website or application and accesses the paid account creation page. The user enters basic information such as company name, contact person's name, email address, and password, and clicks the registration button.

[1554] Step 6:

[1555] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[1556] Step 7:

[1557] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter details of the products or services they will be offering in the product information form.

[1558] Step 8:

[1559] The server receives the entered product information and saves it to a database for the generated AI model. This registers the sales company's product information in the system.

[1560] Step 9:

[1561] The server periodically collects information on the problems of prospective companies and the products and services of sales companies from the database. A generative AI model is used to analyze the data on the problems of prospective companies and the products and services of sales companies.

[1562] Step 10:

[1563] The server (generating AI model) uses text mining techniques to extract keywords and context from problem information and product information. Next, it calculates the correlation between problem information and product information and extracts pairs with high correlation.

[1564] Step 11:

[1565] The server notifies prospective companies of highly correlated pairs as proposals. Notifications are sent via email or as alerts in the dashboard.

[1566] Step 12:

[1567] Users (potential companies) receive notifications and review the proposals on their dashboard after logging in. If they are interested, users click the "Like" button.

[1568] Step 13:

[1569] The server receives the "Like!" input and saves that information to its database. At the same time, the server automatically sends a notification to the sales company that a match has been made.

[1570] Step 14:

[1571] The server provides sales companies with contact information for prospective companies. This allows sales companies to contact prospective companies directly and make specific proposals and follow up.

[1572] (Example 1)

[1573] 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".

[1574] In traditional sales activities, sales companies often expend considerable effort and time to find potential clients, leading to a high likelihood of wasted contact and failures. Furthermore, it was difficult to create sales proposals that accurately addressed the concerns and challenges of potential clients, making effective matching challenging. A system is needed to improve this situation and enable efficient and effective sales activities.

[1575] 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.

[1576] In this invention, the server includes means for registering information on each company's problems in a database, means for registering product information in the database, means for calculating the correlation between the problem information and the product information using a generative AI model that analyzes the problem information and the product information, means for notifying the target company of the proposed solution based on the correlation, means for the target company to send a "positive response" to the notification, and means for providing the target company's contact information to the sales company when the "positive response" is received. This enables highly accurate matching of the problems of prospective companies and the product information of sales companies, resulting in mutually beneficial sales activities.

[1577] A "database" is a system that permanently stores information and allows for efficient retrieval and management as needed.

[1578] "Problem information" refers to data about problems and challenges faced by companies, which is registered in the system.

[1579] "Product information" refers to detailed data about the products and services offered by the sales company, and is registered in the system.

[1580] A "generative AI model" refers to an algorithm that uses artificial intelligence to analyze data and generate predictions and recommendations.

[1581] "Correlation" refers to a criterion for evaluating the relationships and commonalities between two different datasets.

[1582] A "positive response" refers to an action taken by a prospective company to show a favorable reaction to the proposal, such as clicking "Like."

[1583] "Target companies" refers collectively to prospective companies and sales-related companies registered in the system.

[1584] A "selling company" refers to a company that offers goods or services to a prospective client company.

[1585] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system uses specific hardware and software to perform a series of processes, including data registration, analysis, notification, feedback reception, and contact information provision.

[1586] Hardware and software details

[1587] Server Environment

[1588] Hardware: High-performance server machines (e.g., dual-processor servers or Amazon Web Services as a cloud service)

[1589] software:

[1590] Operating System: Linux-based OS (e.g., Ubuntu Server)

[1591] Database management systems: MySQL, PostgreSQL

[1592] Web servers: Nginx, Apache

[1593] Programming frameworks: Flask and Django using Python

[1594] Generative AI model: OpenAI's GPT-3

[1595] Program processing flow

[1596] This system provides an interface for registering each company's problem information and product information in a database. This allows for centralized management of information on both prospective and sales companies.

[1597] Registration process

[1598] Registration of prospective companies

[1599] Users (potential companies) create a free account through a dedicated website or application and enter detailed information about the problems and challenges their company faces. The server receives this information and stores it in a database.

[1600] As a concrete example, a user (prospective company B) might enter and register a problem on the platform such as, "We need a new marketing strategy, but we're unsure which direction to take."

[1601] Registration of sales companies

[1602] Users (sales companies) create paid accounts and enter detailed information about the products and services they offer. The server receives this information and stores it in its database.

[1603] As a concrete example, a user (sales company A) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[1604] Matching process

[1605] The server uses a generative AI model to analyze prospective companies' problem information and sales companies' product information from the collected database. This model uses text mining techniques to extract keywords and context from the problem information and product information, and calculates their correlation.

[1606] As a concrete example, the server analyzes prospective company B's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company A is suitable. In this way, the optimal proposal is generated.

[1607] Notification and feedback on proposals

[1608] The generated proposal is notified to the prospective company by the server, and the prospective company reviews the proposal upon receiving this notification. If interested, the prospective company sends a "positive response" (e.g., "Like!"). This feedback is sent to the server, and the prospective company's contact information is provided to the sales company.

[1609] As a concrete example, the server notifies prospective company B that "a proposal regarding a digital marketing strategy from sales company A has arrived," and when prospective company B clicks "Like," sales company A obtains prospective company B's contact information.

[1610] Examples of prompt statements

[1611] Please explain the process of analyzing the service and product information provided by sales companies based on the concerns of prospective clients, and then generating the optimal sales proposal based on those results.

[1612] This system enables highly accurate matching between prospective companies and sales companies, allowing for effective sales activities. The use of a generative AI model provides an efficient sales process.

[1613] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1614] Step 1: Create an account for the prospective company

[1615] Input: The user (prospective company) enters the company name, contact person's name, email address, and password on a dedicated website or application.

[1616] Operation: The terminal collects this information and sends it to the server. The server validates the received information and, if there are no problems, saves it to the database.

[1617] Output: The prospective company's account information is registered in the database.

[1618] Step 2: Register information about the problems of potential companies.

[1619] Input: Users (prospective companies) log in to the platform and enter detailed information about their company's problems and challenges on the "Problem / Challenge Input" page.

[1620] Operation: The terminal sends the entered problem information to the server, and the server stores the information in a database.

[1621] Output: Information about the problems of prospective companies is saved in the database.

[1622] Specific operation: The user enters "We need a new marketing strategy, but we're unsure which direction to take" through the terminal and registers.

[1623] Step 3: Create an account for the sales company

[1624] Input: The user (sales company) enters the company name, contact person's name, email address, password, and payment information on the paid account creation page.

[1625] Operation: The device collects this information and sends it to the server. The server validates the received information, and if there are no problems, saves it to the database and sets up the paid account.

[1626] Output: The account information of the sales company is registered in the database.

[1627] Step 4: Register product information of the sales company.

[1628] Input: Users (sales companies) log in to the platform and enter details of the products or services they offer on the "Product Information Input" page.

[1629] Operation: The terminal sends the entered product information to the server, and the server stores the information in a database.

[1630] Output: Product information from the sales company is saved in the database.

[1631] Specific operation: The user enters and registers for the "Digital Marketing Strategy Building Support Service" via their device.

[1632] Step 5: Data Collection

[1633] Input: Information on the problems of prospective companies in the database and product information of sales companies.

[1634] Operation: The server periodically collects information on prospective and sales companies from the database.

[1635] Output: The collected problem information and product information are passed to the AI ​​model for generation.

[1636] Step 6: Data Analysis

[1637] Input: Information on the problems of prospective companies and product information of sales companies.

[1638] Operation: The server analyzes this information using a generative AI model (e.g., OpenAI's GPT-3). It extracts keywords and context using text mining techniques and calculates correlations.

[1639] Output: The results of the correlation analysis are generated.

[1640] Specific operation: The generating AI model extracts keywords such as "marketing strategy" and "direction" from the concerns of prospective company B, and extracts keywords such as "digital marketing" and "implementation support" from the product information of sales company A.

[1641] Step 7: Generating the proposal

[1642] Input: Results of correlation analysis by a generative AI model.

[1643] Operation: The server generates suggestions based on this and saves them to the database.

[1644] Output: The generated suggestions are saved to the database.

[1645] Step 8: Notification of Proposal

[1646] Input: Generated suggestion content.

[1647] Operation: The server notifies prospective companies of the proposal details. The notification is sent to the prospective company's terminal.

[1648] Output: A notification is sent to the prospective company.

[1649] Specific action: The server notifies prospective company B that "a proposal regarding the digital marketing strategy from sales company A has been received."

[1650] Step 9: Receive Feedback

[1651] Input: Feedback from prospective companies on the proposal (e.g., "Like!").

[1652] Operation: The terminal sends feedback from prospective companies to the server, and the server stores the feedback in a database.

[1653] Output: Feedback is saved to the database.

[1654] Specific operation: When prospective company B clicks "Like," the server receives feedback.

[1655] Step 10: Provide contact information

[1656] Input: Feedback ("Likes") from prospective companies and their contact information.

[1657] Operation: The server reviews the feedback and provides the prospective company's contact information to the sales company.

[1658] Output: Contact information is provided to the sales company.

[1659] Specific operation: The server notifies sales company A that "prospective company B has agreed to the proposal" and provides contact information.

[1660] (Application Example 1)

[1661] 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".

[1662] In the traditional marketing and advertising industry, it was difficult to effectively match the challenges faced by advertisers with the services offered by marketing companies. As a result, advertisers were unable to find the optimal advertising services, and marketing companies were unable to conduct effective sales activities. Furthermore, the process of quickly and efficiently proposing highly relevant advertising services, obtaining the advertiser's consent, and providing contact information was cumbersome.

[1663] 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.

[1664] In this invention, the server includes means for registering information on each company's problems in a database, means for registering product information in a database, means for calculating correlation using a generative AI model that analyzes the problem information and the product information, means for notifying the content of the proposal, means for prospective companies to send "likes", means for providing contact information, means for registering detailed information of advertising services provided by marketing companies, means for viewing the content of advertising services proposed based on the challenges faced by advertisers, and means for providing product information when the advertiser agrees to the proposed content. This enables effective matching between advertisers with problems and appropriate marketing companies, and allows for the rapid proposal of highly relevant advertising services and simplification of the communication process.

[1665] A "database" is a system for efficiently storing and managing information about a company's problems and products.

[1666] "Problem information" refers to information that includes the challenges and problems that companies face.

[1667] "Product information" refers to detailed information about the products and services offered by the sales company.

[1668] A "generative AI model" is an artificial intelligence technology that analyzes registered data and calculates its correlations.

[1669] "Correlation" refers to the degree of connection between information about problems and information about products, indicating a high degree of agreement.

[1670] "Means of notifying about the proposed content" refers to a function for informing prospective companies about appropriate product proposals.

[1671] "Like!" is a way for prospective companies to send positive feedback on a proposal.

[1672] "Contact information" refers to information provided by a prospective company that allows them to be contacted.

[1673] A "marketing company" is a company that provides advertising and promotional services.

[1674] "Detailed information about advertising services" refers to information that includes specific details about the advertising provided by a marketing company.

[1675] An "advertiser" is a company that wishes to promote its products or services.

[1676] "Challenges" refer to problems or requests that advertisers have that need to be resolved.

[1677] "Means for viewing the proposed advertising service details" refers to a function that allows advertisers to confirm the details of the advertising services provided.

[1678] "Means of providing product information" refers to a function that provides relevant information to advertisers if they agree to the proposal.

[1679] This invention is a system for achieving efficient and effective matching between advertisers and marketing companies. This system includes means for registering each company's problem information and product information in a database, calculating correlation using a generative AI model that analyzes them, notifying advertisers of proposed solutions, sending "likes," and providing contact information to marketing companies.

[1680] Hardware to use

[1681] server

[1682] Smartphone

[1683] Software to use

[1684] Database: MySQL

[1685] Application server: Node.js

[1686] Frontend: React Native

[1687] Generative AI model: OpenAI GPT-4

[1688] Data processing and calculations

[1689] The server receives data sent by the user and stores it in a database. Then, it uses a generative AI model (OpenAI GPT-4) to calculate the correlation between problem information and product information in the database.

[1690] in particular,

[1691] 1. The data collection server collects information from advertisers (companies facing problems) and marketing companies (advertising service providers) and stores it in a MySQL database.

[1692] Advertisers input information about their challenges through the application. For example, they might enter a problem such as, "We want to increase awareness of our new product, but our target market is unclear."

[1693] Marketing companies register details of the advertising services they offer in a database. For example, they might enter product information such as "social media marketing services."

[1694] 2. The data analysis server periodically analyzes the information in the database using a generative AI model (GPT-4), extracting keywords and context from problem information and product information, and calculating their correlation.

[1695] For example, the context of information such as "We need a new marketing strategy" and product information such as "Digital marketing strategy development support service" is analyzed to extract highly correlated pairs.

[1696] 3. The proposal sending server notifies advertisers who have entered problem information of proposals from marketing companies that have product information deemed to be highly correlated.

[1697] Advertisers can review their proposals through the application and, if interested, send positive feedback by clicking the "Like" button.

[1698] 4. Provision of Contact Information: When an advertiser sends a "Like," the server sends a notification of the successful match to the marketing company and provides the advertiser's contact information.

[1699] Marketing companies use the provided contact information to make detailed proposals and sell services to advertisers.

[1700] Specific example

[1701] Examples of prompts for generative AI models

[1702] "User-entered text: 'We need a new marketing strategy, but we're unsure which direction to take.'"

[1703] "Text for matching candidates: 'Digital Marketing Strategy Development Support Service'"

[1704] "Generates prompt messages for an AI model that calculates the correlation between the two and finds the optimal pair."

[1705] Sample prompt message

[1706] The prospective company's concern: "We need a new marketing strategy, but we're unsure which direction to take."

[1707] Sales company's product / service: "Support service for building digital marketing strategies"

[1708] Based on this information, please calculate the correlation between the two.

[1709] This enables efficient and effective matching between advertisers and marketing companies, facilitating the resolution of advertisers' challenges and the smooth progress of marketing companies' sales activities.

[1710] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1711] Step 1:

[1712] Data entry

[1713] Users (advertisers) input information about their company's challenges through a smartphone application. For example, they might input a challenge such as, "We want to increase awareness of our new product, but our target market is unclear." Users (marketing companies) input information about the advertising services they offer. For example, they might input product information such as, "Social Media Marketing Services."

[1714] Input and output

[1715] Input: Information on the advertiser's problems and information on the marketing company's products / services.

[1716] Output: Problem information and product information stored in the database

[1717] Specific actions

[1718] The information entered by the user is received by the server and stored in a MySQL database.

[1719] Step 2:

[1720] Data analysis

[1721] The server periodically uses a generative AI model (OpenAI GPT-4) to analyze problem information and product information in the database. The server extracts keywords and context related to the issues from the problem information and keywords and context related to the services provided from the product information.

[1722] Input and output

[1723] Input: Problem information and product information stored in the database

[1724] Output: Extracted keywords and analysis results

[1725] Specific actions

[1726] Generative AI models use text mining techniques to extract keywords and context, and discover highly correlated information.

[1727] Step 3:

[1728] Calculation of correlation

[1729] The server calculates the correlation between problem information and product information based on the analysis results of the generative AI model (GPT-4). It then generates an overall score to find appropriate matching candidates.

[1730] Input and output

[1731] Input: Analyzed keywords and analysis results

[1732] Output: Correlation score and matching candidates

[1733] Specific actions

[1734] The generative AI model generates prompt sentences, compares the information from both sides to calculate the correlation, and determines the optimal pair.

[1735] Step 4:

[1736] Notification of proposed content

[1737] The server notifies advertisers facing challenges with proposals from highly correlated marketing companies. Advertisers can then review the proposals through a smartphone application.

[1738] Input and output

[1739] Input: Matched suggestion information

[1740] Output: Proposal notification to advertisers

[1741] Specific actions

[1742] The server notifies the advertiser of the proposal via push notification or email. The advertiser then reviews the proposal within the application.

[1743] Step 5:

[1744] Sending a "Like"

[1745] If an advertiser is interested in a proposal, they can send positive feedback by clicking the "Like" button.

[1746] Input and output

[1747] Input: Advertiser's "Like" feedback

[1748] Output: Notification of receiving a "Like"

[1749] Specific actions

[1750] When an advertiser clicks the "Like" button, that information is sent to the server and recorded.

[1751] Step 6:

[1752] Providing contact information

[1753] After receiving a "like" from an advertiser, the server sends a notification of the successful match to the marketing company and provides the advertiser's contact information.

[1754] Input and output

[1755] Input: Information on received "Likes"

[1756] Output: Notification of providing contact information to marketing companies

[1757] Specific actions

[1758] The server sends a notification to the marketing company that a match has been made and provides the advertiser's contact information. The marketing company then uses the provided contact information to make specific proposals and sales pitches to the advertiser.

[1759] The above steps enable efficient matching and effective advertising proposals between advertisers and marketing companies.

[1760] 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.

[1761] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system includes means for registering each company's problem information and product information in a database, calculating correlation using a generative AI model that analyzes them, notifying prospective companies of the proposed content, sending "likes," and providing contact information to sales companies. Furthermore, in this invention, by combining it with an emotion engine that recognizes user emotions, the proposed content can be adapted even more effectively.

[1762] The following explanation uses natural language and includes concrete examples of how the program works.

[1763] 1. Registering prospective companies

[1764] Users (prospective companies) create a free account through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the problems and challenges their company faces. This information is received by the server and stored in a database.

[1765] Specific example:

[1766] A user (prospective company B) enters their concerns into the platform, such as "We need a new marketing strategy, but we're unsure which direction to take," and registers their findings.

[1767] 2. Registration of sales companies

[1768] Users (sales companies) create paid accounts through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[1769] Specific example:

[1770] The user (sales company A) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[1771] 3. Matching process

[1772] The server periodically collects information on the concerns of prospective companies and the products / services of sales companies from the database. Using a generative AI model, it analyzes the prospective companies' concern data and extracts appropriate keywords and context. Furthermore, it analyzes the sales companies' product / service information to find common keywords and highly relevant information. Based on this correlation, it extracts pairs with high correlation.

[1773] Specific example:

[1774] The server analyzes prospective company B's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company A is suitable.

[1775] 4. Submitting the proposal

[1776] The server notifies prospective companies of successful matches. Notifications are sent via email or as alerts in the dashboard. Furthermore, this proposal notification incorporates a sentiment engine that analyzes the prospective company's emotional state.

[1777] Specific example:

[1778] The server notifies prospective company B that "a proposal regarding the digital marketing strategy from sales company A has arrived." This notification utilizes an emotion engine, which analyzes the user's response in real time and generates emotion data.

[1779] 5. Sentiment Analysis and Adaptation of Proposals

[1780] The user (potential company) receives a notification and reviews the proposal. The emotion engine analyzes the user's facial expressions and text feedback to understand the user's emotional state. This allows the server to adapt the proposal according to the user's emotions.

[1781] Specific example:

[1782] If the emotion engine detects that prospective company B is showing interest based on their facial expressions, the server uses that data to enhance the proposal and resends more specific information and related additional suggestions.

[1783] 6. Send a "Like"

[1784] If a user (potential company) is interested, they click the "Like" button. The sentiment engine adds this action to the sentiment data and evaluates the overall level of user interest.

[1785] Specific example:

[1786] When prospective company B sends a "Like," the emotion engine analyzes that reaction and stores it as data that evaluates the user's level of interest.

[1787] 7. Matching successful

[1788] The server receives the "Like!" input and saves the information to its database. At the same time, the server automatically sends a notification of the successful match to the sales company. It also provides the sales company with the prospective company's contact information. The sales company then uses this information to contact the prospective company directly.

[1789] Specific example:

[1790] Upon receiving a "Like!" from prospective company B, the server notifies sales company A that "Prospective company B has agreed to the proposal." Sales company A then obtains prospective company B's contact information and communicates specific improvement suggestions.

[1791] This invention enables high-quality sales between prospective companies and sales companies, and significantly improves the success rate of telemarketing because proposals tailored to the needs of both parties can be confirmed in advance. This system enables mutually beneficial sales activities through highly accurate matching and sentiment analysis using a generative AI model and emotion engine.

[1792] The following describes the processing flow.

[1793] Step 1:

[1794] Users (prospective companies) open the dedicated website or application and access the free account creation page. Users enter basic information such as company name, contact person's name, email address, and password, and click the registration button.

[1795] Step 2:

[1796] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[1797] Step 3:

[1798] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter detailed information about the challenges and problems their company faces in the problem information form.

[1799] Step 4:

[1800] The server receives the entered problem information and saves it to the database. This registers the problem information of potential companies in the system.

[1801] Step 5:

[1802] The user (sales company) opens the dedicated website or application and accesses the paid account creation page. The user enters basic information such as company name, contact person's name, email address, and password, and clicks the registration button.

[1803] Step 6:

[1804] The server receives the information entered by the user and registers the new account in the user database. After registration is complete, the server sends a registration confirmation email to the user.

[1805] Step 7:

[1806] Users activate their account by clicking the link included in the registration confirmation email and log in to the platform. After logging in, users go to their My Page and enter details of the products or services they will be offering in the product information form.

[1807] Step 8:

[1808] The server receives the entered product information and saves it to a database for the generated AI model. This registers the sales company's product information in the system.

[1809] Step 9:

[1810] The server periodically collects information on the problems of prospective companies and the products and services of sales companies from the database. A generative AI model is used to analyze the data on the problems of prospective companies and the products and services of sales companies.

[1811] Step 10:

[1812] The server (generating AI model) uses text mining techniques to extract keywords and context from problem information and product information. Next, it calculates the correlation between problem information and product information and extracts pairs with high correlation.

[1813] Step 11:

[1814] The server notifies prospective companies of highly correlated pairs as proposals. Notifications are sent via email or as alerts in the dashboard.

[1815] Step 12:

[1816] Users (potential companies) receive notifications and review the proposals on their dashboard after logging in.

[1817] Step 13:

[1818] The emotion engine analyzes user (potential company) responses in real time to understand the emotional state of the potential company.

[1819] Step 14:

[1820] The server adaptively modifies the proposal based on emotional information obtained from the emotion engine and re-notifies the prospective company.

[1821] Step 15:

[1822] Users (potential companies) review the revised proposal and click the "Like" button if they are interested.

[1823] Step 16:

[1824] The server receives the "Like!" input and saves that information to its database. At the same time, the server automatically sends a notification to the sales company that a match has been made.

[1825] Step 17:

[1826] The server provides sales companies with contact information for prospective companies. This allows sales companies to contact prospective companies directly and make specific proposals and follow up.

[1827] (Example 2)

[1828] 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".

[1829] This invention aims to improve sales results for both prospective companies and sales companies by efficiently and effectively matching them in sales activities. Conventional sales methods often involve simultaneous approaches to a large number of prospective companies and proposals that do not match the needs of the prospective companies, resulting in decreased sales effectiveness and wasted time and resources. Furthermore, because it is difficult to properly understand the emotions and reactions of prospective companies, the suitability of proposals is low, making it difficult to improve the closing rate.

[1830] 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.

[1831] In this invention, the server includes means for registering information on each company's problems in a database, means for registering product information in the database, means for calculating the correlation between the problem information and the product information using a generative AI model that analyzes the problem information and the product information, means for notifying prospective companies of the proposed content based on the correlation, means for analyzing the prospective company's emotional state using an emotion engine and adapting the proposed content, means for the prospective company to send a "like!" in response to the notification, and means for providing the prospective company's contact information to the sales company when the "like!" is received. This enables appropriate and effective matching of proposed content between prospective companies and sales companies, improving the efficiency of sales activities and the closing rate.

[1832] A "database" is a system for efficiently storing and managing data such as information about a company's problems and product information.

[1833] A "generative AI model" is an artificial intelligence model that extracts keywords and context from specified data and calculates correlations by analyzing the data.

[1834] An "emotion engine" is software or a system that analyzes a user's facial expressions and text feedback to understand the user's emotional state.

[1835] A "prospective company" is a company that has shown interest in a particular product or service and may potentially do business with the company in the future.

[1836] A "sales-oriented company" is a company that provides specific goods or services and intends to sell or provide them to prospective companies.

[1837] "Correlation" is an indicator that shows the relationship or degree of relevance between information about the concerns of prospective companies and product information of sales companies.

[1838] "Proposal details" refer to the detailed information and proposals for products and services that the sales company presents to solve the problems and challenges of the prospective client.

[1839] A "Like" is a type of positive feedback that a prospective company sends to show interest in or concern about a proposal.

[1840] "Contact information" refers to information necessary to contact a prospective company directly, such as the name of the contact person, email address, and phone number.

[1841] This invention is a system for achieving efficient and effective matching between prospective companies and sales companies. This system consists of a server, terminals, and users.

[1842] 1. Registering prospective companies

[1843] Users (prospective companies) create a free account using a dedicated website or application. They enter necessary information such as company name, contact person's name, and email address on the account creation screen. After creating the account, they log in to the platform and enter detailed information about the company's problems and challenges. This information is received by the server and stored in the database.

[1844] Specific example:

[1845] A user (prospective company A) enters their concerns into the platform, such as "We need a new marketing strategy, but we're unsure which direction to take," and registers their findings.

[1846] 2. Registration of sales companies

[1847] Users (sales companies) create paid accounts using a dedicated website or application. They enter necessary information such as company name, contact person's name, email address, and payment information on the account creation screen. After creating the account, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[1848] Specific example:

[1849] The user (sales company B) enters "Digital Marketing Strategy Development Support Service" as their product and registers it on the platform.

[1850] 3. Matching process

[1851] The server collects information on the concerns of prospective companies and the products / services of sales companies from the database. Using a generative AI model, the server analyzes the prospective companies' concerns data and extracts appropriate keywords and context. Simultaneously, it analyzes the sales companies' product / service information to find common keywords and highly relevant information. Based on these analysis results, it extracts pairs with high correlation.

[1852] Specific example:

[1853] The server analyzes prospective company A's "marketing strategy concerns" and determines that the "digital marketing strategy development support service" offered by sales company B is suitable.

[1854] 4. Submitting the proposal

[1855] The server notifies prospective companies of proposals that have been successfully matched by the generated AI model. Notifications are sent via email or as alerts in the dashboard. These notifications also incorporate an emotion engine that analyzes the prospective company's emotional state.

[1856] Specific example:

[1857] The server notifies prospective company A that "a proposal regarding the digital marketing strategy from sales company B has arrived." This notification utilizes an emotion engine, which analyzes the user's response in real time and generates emotion data.

[1858] 5. Sentiment Analysis and Adaptation of Proposals

[1859] The user (potential company) receives a notification and reviews the proposal. The emotion engine analyzes the user's facial expressions and text feedback to understand the user's emotional state. This allows the server to adapt the proposal according to the user's emotions.

[1860] Specific example:

[1861] If the emotion engine detects from prospective company A's facial expressions that they are interested, the server uses that data to enhance the proposal and resends more specific information and related additional suggestions.

[1862] 6. Send a "Like"

[1863] If a user (potential company) is interested, they click the "Like" button. The sentiment engine adds this action to the sentiment data and evaluates the overall level of user interest.

[1864] Specific example:

[1865] When prospective company A sends a "Like," the emotion engine analyzes that reaction and stores it as data that evaluates the user's level of interest.

[1866] 7. Matching successful

[1867] The server receives the "Like!" input and saves the information to its database. At the same time, the server automatically sends a notification of the successful match to the sales company. It also provides the sales company with the prospective company's contact information. The sales company then uses this information to contact the prospective company directly.

[1868] Specific example:

[1869] When the server receives a "Like!" from prospective company A, it notifies sales company B that "Prospective company A has agreed to the proposal." Sales company B obtains prospective company A's contact information and contacts them with specific improvement suggestions.

[1870] This enables high-quality sales interactions between prospective clients and sales companies, allowing for pre-approval of proposals that meet the needs of both parties, thereby improving the efficiency of sales activities and closing rates. By utilizing servers, generative AI models, and emotion engines, highly accurate matching and emotion analysis become possible, resulting in beneficial sales activities for both prospective clients and sales companies.

[1871] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1872] Step 1: Register prospective companies

[1873] Users (prospective companies) create a free account through a dedicated website or application. After creating an account, they log in to the platform and enter detailed information about the problems and challenges their company faces. This information is received by the server and stored in a database.

[1874] Input: Basic information such as company name, contact person's name, and email address, as well as details of the problem or issue.

[1875] Output: Profiles and problem information of prospective companies registered in the database.

[1876] Specific actions:

[1877] When a user clicks the "Create Account" button, the entered data is sent to the server, and a record of the new prospective company is added to the database. Next, when the user logs in and clicks the "Register Problem Information" button, the entered problem information is sent to the server and saved to the database.

[1878] Step 2: Register the sales company

[1879] Users (sales companies) create paid accounts through a dedicated website or application. They create an account by entering their company name, contact person's name, email address, payment information, etc., on the account creation screen. After creation, they log in to the platform and enter detailed information about the products and services they offer. This information is also received by the server and stored in the database.

[1880] Input: Company name, contact person name, email address, payment information, and product / service details.

[1881] Output: Profiles and product information of sales companies registered in the database.

[1882] Specific actions:

[1883] When a user clicks the "Create Account" button, the entered data is sent to the server, and a new sales company record is added to the database. Next, when the user logs in and clicks the "Register Product Information" button, the entered product information is sent to the server and saved to the database.

[1884] Step 3: Matching Process

[1885] The server collects information on the concerns of prospective companies and product information from sales companies within a database. Using a generative AI model, the server analyzes the prospective companies' concern data and extracts appropriate keywords and context. Simultaneously, it analyzes the sales companies' product information to find common keywords and highly relevant information. Based on these analysis results, it extracts pairs with high correlation.

[1886] Input: Data on the concerns of prospective companies in the database and product data of sales companies.

[1887] Output: Correlation score and pairs of prospective and sales companies with high correlation.

[1888] Specific actions:

[1889] A scheduled server job executes SQL queries to retrieve data on potential clients' concerns and sales companies' product data from the database. A generative AI model receives this text data and performs keyword extraction and contextual analysis. The server then selects pairs with high correlation scores and saves them to the database.

[1890] Step 4: Submit your proposal

[1891] The server notifies prospective companies of successful matches. Notifications are sent via email or as alerts in the dashboard. These notifications also incorporate an emotion engine that analyzes the prospective company's emotional state.

[1892] Input: Matching results and contact information for prospective companies (email address, etc.)

[1893] Output: Proposal notifications and sentiment data for prospective companies

[1894] Specific actions:

[1895] The server generates a proposal notification when a match is made and sends an email to the prospective company using the SMTP protocol or sends a real-time alert via WebSocket. The sentiment engine analyzes the prospective company's reaction to the notification and generates sentiment data.

[1896] Step 5: Sentiment analysis and adaptation of proposals

[1897] The user (potential company) receives a notification and reviews the proposal. The emotion engine analyzes the user's facial expressions and text feedback to understand the user's emotional state. This allows the server to adapt the proposal to the user's emotions.

[1898] Input: Prospective company's reaction (facial expression, text feedback)

[1899] Output: Sentiment data and adapted suggestions

[1900] Specific actions:

[1901] The user clicks the notification link to view the suggestion details page. The sentiment engine analyzes the camera feed or feedback text and generates a sentiment score. The server receives the sentiment score, updates the suggestion based on it, and generates a new suggestion.

[1902] Step 6: Send a "Like!"

[1903] If a user (potential client) is interested in a proposal, they click the "Like" button. The sentiment engine adds this action to the sentiment data and evaluates the overall level of user interest.

[1904] Input: "Like" click data

[1905] Output: Updated sentiment data

[1906] Specific actions:

[1907] When a user clicks the "Like" button, that information is sent to the server. The emotion engine analyzes this reaction and updates the emotion data. The server saves the updated emotion data to the database.

[1908] Step 7: Matching successful

[1909] The server receives the "Like!" input and saves the information to its database. At the same time, the server automatically sends a notification of the successful match to the sales company. It also provides the sales company with the prospective company's contact information. The sales company then uses this information to contact the prospective company directly.

[1910] Input: "Like" data and contact information of prospective companies

[1911] Output: Notification of successful matching to the sales company and contact information of the prospective company.

[1912] Specific actions:

[1913] When the server receives a "Like" data, it adds it to the database as a new record. At the same time, it sends a matching notification to the sales company using the SMTP protocol. The server securely provides the sales company with the prospect's contact information, preparing the sales company to contact the prospect directly.

[1914] (Application Example 2)

[1915] 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".

[1916] Traditional methods of matching customers with sales staff in physical stores often resulted in products and services not meeting customer needs, making it difficult to improve satisfaction. Furthermore, the inefficient matching of staff and customers within the store led to a lack of personalized service and a diminished customer experience. Additionally, the lack of suggestions that considered the customer's emotional state meant there was no guarantee that suggestions would align with the customer's interests and needs.

[1917] 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.

[1918] In this invention, the server includes means for registering information about each organization's concerns in a database, means for registering product information in the database, means for calculating the correlation between the concern information and the product information using a generative AI model that analyzes the concern information and the product information, means for notifying prospective organizations of the proposed content based on the correlation, means for prospective organizations to send a "Like!" in response to the notification, means for providing the prospective organization's contact information to the providing organization when a "Like!" is received, means for analyzing the prospective organization's emotional state using an emotion engine and adjusting the proposed content, and means for resending the adjusted proposed content. This enables efficient matching of customers and sales staff in physical stores, and further improves customer satisfaction by providing more appropriate suggestions based on the customer's emotional state.

[1919] An "organization" refers to a group of people, such as a company or association, who come together for a specific purpose.

[1920] "Problem information" refers to data about problems and challenges faced by organizations and individuals.

[1921] "Product information" refers to detailed data about the products and services offered.

[1922] A "generative AI model" refers to a model that uses artificial intelligence technology to analyze text data and automatically generate relationships and specific information.

[1923] "Correlation" refers to an indicator that shows the degree of relationship or linkage between two or more data points.

[1924] A "prospective organization" refers to a company or group that may be interested in a particular service or product.

[1925] "Proposal details" refers to information that explains the benefits and advantages of the services or products offered to the prospective organization.

[1926] "Notification" refers to a message or alert used to inform a target person of specific information.

[1927] "Like!" refers to an action that indicates interest in or agreement with a proposal.

[1928] "Contact information" refers to information such as phone numbers and email addresses used to contact prospective organizations.

[1929] "Provider organizations" refer to companies or groups that provide goods or services.

[1930] An "emotion engine" refers to a technology that analyzes a user's emotions and changes the system's output and suggestions according to that emotional state.

[1931] "Adjusted suggestions" refers to suggestions that have been modified by the emotion engine based on the user's emotional state.

[1932] "Resending" refers to the act of sending information that has already been sent once.

[1933] This system is designed to enable efficient matching between customers and sales staff in physical stores. The specific implementation of the system is described below.

[1934] Hardware configuration

[1935] Server: Hosts a database that manages customer and sales staff information, a generative AI model, and an emotion engine.

[1936] Smartphone or smart glasses: Used by customers to access the system, input information, and receive data within the store.

[1937] Display device: Provides a screen for sales staff to review proposals and customer information.

[1938] Software Configuration

[1939] Database: Customer and sales staff information is stored in a database such as SQLite.

[1940] Generative AI Model: We use generative AI models such as OpenAI's GPT-3.5-turbo to analyze text data and generate suggested content.

[1941] Emotion Engine: Uses the emotion analysis model from the Transformers library to analyze the customer's emotional state.

[1942] Data processing and data calculation

[1943] 1. Data Registration

[1944] Customers input information about the products and services they are looking for in the store via their smartphones or smart glasses. This information is sent to a server and stored in a database. Similarly, sales staff register their areas of expertise and the services they can offer in the database.

[1945] 2. Calculation of correlation

[1946] The server periodically collects customer problem information and sales staff expertise information from a database. Using a generative AI model, it analyzes the text data from both sources and extracts appropriate keywords and context. Correlations are calculated using text analysis techniques such as TF-IDF and cosine similar...

Claims

1. A means of registering information about each company's problems in a database, A means of registering product information in a database, A means for calculating the correlation between the aforementioned problem information and the aforementioned product information using a generative AI model that analyzes the aforementioned problem information and the aforementioned product information, Based on the aforementioned correlation, a means of notifying prospective companies of the proposal content, A means by which prospective companies can send a "Like!" in response to the aforementioned notification, A system that includes means for providing the sales company with the contact information of the prospective company when it receives the aforementioned "Like".

2. The system according to claim 1, wherein the generating AI model uses text mining technology to extract keywords and context from the problem information and the product information, and calculates their correlation.

3. The system according to claim 1, further comprising means for providing a dashboard for prospective companies to view the proposed content when they are notified of the proposed content.

Images