System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting information of a seller company; means for extracting a candidate buyer from a database; means for generating a proposal based on the extracted information of the candidate buyer; and means for displaying the generated proposal on a user interface.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the current M&A process for small and medium-sized enterprises, it takes a great deal of time and effort for the selling company to find suitable potential buyers, and preparing proposals is also quite time-consuming. Furthermore, intermediary companies often provide buyer-centric support, which can sometimes result in the selling company being unable to sell under the terms they wish. A new system is needed to solve these problems, streamline the M&A process for small and medium-sized enterprises, and ensure fair and speedy transactions. [Means for solving the problem]

[0005] The present invention provides a system that inputs information about a seller company, extracts potential buyers from a database based on that information, and generates a proposal based on that information. Specifically, the proposed system includes the following means: a means for inputting information about the seller company, a means for extracting potential buyers from a database, a means for generating a proposal based on the information about the extracted potential buyers, and a means for displaying the generated proposal on a user interface. This system enables small and medium-sized enterprises to quickly and efficiently find potential buyers and conduct transactions on fair terms. Furthermore, by using a machine learning algorithm to extract potential buyers and optimize the proposal, even more accurate matching can be achieved.

[0006] The "means for inputting information about the seller company" refers to an interface that allows the seller company to input its basic information and business details into the system.

[0007] "Means for extracting potential buyers from the database" refers to algorithms and search functions for selecting appropriate potential buyers from the database based on information about the seller company.

[0008] The "means for generating a proposal based on the information of the extracted potential buyers" is a program for automatically generating a proposal to the seller company based on the information of the selected potential buyers.

[0009] The "means for displaying the generated proposal on the user interface" is a function for displaying the generated proposal on the screen of the terminal so that the user can check it.

[0010] A "generative artificial intelligence model" is a machine learning algorithm or statistical model used to make optimal matches between seller and buyer companies.

[0011] A "machine learning algorithm" is a program that learns specific patterns and relationships based on large data sets and makes predictions and classifications.

[0012] The "feedback system" is a function that receives evaluations and opinions from users and uses them to improve the performance of the system and the contents of the proposal. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

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

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

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

[0023] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0030] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] This invention provides an M&A business support system for small and medium-sized enterprises. This system automates a series of processes: inputting information about the seller company, extracting potential buyers from a database based on that information, generating a proposal based on the extracted information about the potential buyers, and displaying the generated proposal on a user interface.

[0035] The server functions as the central component of the system. It receives information about the selling company from the user (M&A specialist) and uses that information to extract suitable potential buyers from a database. The server utilizes a generative artificial intelligence model to extract potential buyers, thereby achieving highly accurate matching. It then generates a proposal based on the extracted information about the potential buyers and sends this proposal to the terminal.

[0036] The terminal serves as an interface for users to interact with the system. The terminal provides a form for users to enter basic information about the seller company and transmits the entered information to the server. The terminal also displays proposals received from the server to the users, allowing them to review the proposals and take necessary actions.

[0037] The user uses a terminal to input information about the seller company and sends the input information to the server. The server generates a proposal and displays it on the terminal, allowing the user to review it and select the most suitable potential buyer.

[0038] Consider the following scenario as a specific example. When AAA Corporation, a small or medium-sized enterprise, uses the system, the user enters AAA Corporation's company information (e.g., company name, "AAA Corporation," business description, "software development") into an input form on a terminal. This information is sent to the server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review it. This process enables AAA Corporation to quickly and efficiently find potential buyers and propose optimal terms to the selling company.

[0039] By implementing this invention, the M&A process for small and medium-sized enterprises will be significantly more efficient, making it easier for sellers to find buyers on the terms they desire. This system will resolve business succession issues for small and medium-sized enterprises and promote sustainable economic growth.

[0040] The processing flow will be explained below.

[0041] Step 1:

[0042] The terminal displays a form on the user interface for the seller company to enter basic information about the company (company name, business details, etc.).

[0043] Step 2:

[0044] The user enters the seller's company information into the input form on the terminal and clicks the "Submit" button on the form.

[0045] Step 3:

[0046] The terminal acquires the seller company information entered by the user, creates a request to send the information to the server, and sends it.

[0047] Step 4:

[0048] The server processes the seller company information received from the terminal and accesses a database to execute queries to extract suitable potential buyers.

[0049] Step 5:

[0050] The server uses machine learning algorithms to extract suitable potential buyers from the database, thereby identifying buyers that match the characteristics of the seller.

[0051] Step 6:

[0052] The server executes a program for generating a proposal based on the extracted information of potential buyers, and creates the proposal by embedding the information in a template.

[0053] Step 7:

[0054] The server transmits the generated proposal to the terminal.

[0055] Step 8:

[0056] The terminal displays the proposal received from the server on a user interface, allowing the user to check the proposal.

[0057] Step 9:

[0058] The user can review the proposals displayed through the terminal interface, provide feedback if necessary, and select the most suitable potential buyer.

[0059] Through this series of processing steps, the system of the present invention enables a seller to quickly and efficiently find potential buyers and proceed with the M&A process under optimal conditions.

[0060] Example 1

[0061] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0062] There is a lack of appropriate support systems for small and medium-sized enterprises to carry out M&A work quickly and efficiently. Furthermore, there is a need for high accuracy in matching sellers with potential buyers and in automatically generating proposals. This is expected to streamline the entire M&A process and improve the success rate.

[0063] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0064] In this invention, the server includes means for transmitting input information, means for searching a database based on the received information to extract candidates, means for generating proposals based on the information using a generative artificial intelligence model, and means for displaying the generated proposals on a user interface, thereby enabling highly accurate matching between seller companies and potential buyer companies and realizing the automatic generation and display of proposals quickly and efficiently.

[0065] The "means for transmitting input information" is a means by which a user inputs information about a seller company into a terminal and transmits it to a server.

[0066] "Means for searching a database based on received information and extracting candidates" refers to means for the server to search data in a database based on the information of the seller company received from the user and extract appropriate buyer candidates.

[0067] "Means for generating a proposal based on information using a generative artificial intelligence model" refers to means for automatically generating a proposal using a generative artificial intelligence model based on information about potential buyers extracted by the server.

[0068] The "means for displaying the generated proposal on a user interface" refers to a means for the server to transmit the generated proposal to the terminal, and for the terminal to display this proposal on a user interface.

[0069] The "generative artificial intelligence model that automatically matches seller information with buyer information and quickly creates proposals" is an artificial intelligence model that automatically matches information on seller companies and potential buyer companies and quickly generates proposals with high accuracy.

[0070] "Extraction of candidates from the database is performed using a machine learning algorithm" refers to the process in which the server searches the data in the database and extracts suitable potential buyers using a machine learning algorithm.

[0071] The present invention provides an M&A business support system for small and medium-sized enterprises, which automates a series of processes: inputting information about the selling company, extracting potential buyers from a database based on that information, generating a proposal based on the information about the extracted potential buyers, and displaying the generated proposal on a user interface.

[0072] Hardware and software used

[0073] server

[0074] The server is the central component of the system and uses cloud servers such as AWS (Amazon Web Services) and Google Cloud Platform. The database uses a relational database management system (RDBMS) such as MySQL or PostgreSQL. Machine learning frameworks such as TensorFlow and PyTorch are used as generative artificial intelligence models.

[0075] Terminal

[0076] The terminals are PCs, tablets, and smartphones that serve as interfaces for users to interact with the system. The user interface is built using front-end frameworks such as React, Vue.js, and Angular.

[0077] Program processing

[0078] The server performs a database search based on the seller company information received from the terminal and extracts suitable potential buyers. This process uses a generative artificial intelligence model to achieve highly accurate matching. A proposal is automatically generated based on the extracted information on the potential buyers and sent to the terminal.

[0079] The terminal provides a form for the user to input information about the seller company, transmits the input information to the server, and displays the proposal received from the server on a user interface, allowing the user to review the proposal and take necessary actions.

[0080] The user inputs the seller's information and sends it to the server. The server generates a proposal and displays it on the terminal, allowing the user to review it and select the most suitable potential buyer.

[0081] Specific examples

[0082] A specific example of how a small and medium-sized enterprise, AAA Co., Ltd., uses the system is given below.

[0083] The user enters the following information into the terminal's input form:

[0084] Company name: "AAA Co., Ltd."

[0085] Business: Software development

[0086] This information is sent to a server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review it. This process enables AAA Corporation to quickly and efficiently find potential buyers and propose optimal terms to the seller.

[0087] The above is an embodiment of the present invention.

[0088] Example of a prompt statement without JSON

[0089] The user enters the following information into the terminal's input form:

[0090] Company name: "AAA Co., Ltd."

[0091] Business: Software development

[0092] The server receives this information, performs a database search, and extracts suitable potential buyers using a generative AI model (e.g., using TensorFlow).The server then generates a proposal based on the extracted information about the potential buyers and sends the generated proposal to the terminal.The terminal displays the proposal on a user interface, and the user can confirm the proposal.

[0093] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0094] Step 1:

[0095] The user enters information about the seller company into an input form on the device, including specific information such as the company name and business details. The entered information is temporarily stored in the device's internal memory.

[0096] input:

[0097] Company name: "AAA Co., Ltd."

[0098] Business: Software development

[0099] output:

[0100] Company information entered into the terminal

[0101] Step 2:

[0102] The terminal sends the entered seller information to the server using the HTTPS protocol, and the data is encoded in JSON format, so the entered information is passed to the server securely.

[0103] input:

[0104] Company information entered into the terminal

[0105] output:

[0106] Company information in JSON format sent to the server

[0107] Step 3:

[0108] The server parses the received JSON data and extracts information about the seller. Based on this information, it performs a database search to extract potential buyers. This process uses a generative AI model to achieve highly accurate matching.

[0109] input:

[0110] Company information in JSON format sent to the server

[0111] output:

[0112] Extracted information on potential buyers

[0113] Step 4:

[0114] The server automatically generates a proposal based on the extracted information of potential buyers. This proposal includes details of the potential buyers and their proposals. The generative AI model is used to generate the optimal proposal.

[0115] input:

[0116] Extracted information on potential buyers

[0117] output:

[0118] Auto-generated proposal

[0119] Step 5:

[0120] The server sends the generated proposal in JSON format to the terminal. Because the proposal is sent as an HTTP response, there is little latency (delay) when the terminal receives it.

[0121] input:

[0122] Auto-generated proposal

[0123] output:

[0124] Proposal in JSON format sent to the device

[0125] Step 6:

[0126] The terminal parses the received proposal data and displays it in a user interface, using front-end frameworks such as React and Vue.js to display the proposal in a visually easy-to-understand format.

[0127] input:

[0128] Proposal in JSON format sent to the device

[0129] output:

[0130] Proposal displayed in the user interface

[0131] Step 7:

[0132] The user checks the proposal on the device screen, selects the most suitable buyer based on the information on potential buyers listed in the proposal, and decides on the next action (contact or adjustment of terms).

[0133] input:

[0134] Proposal displayed in the user interface

[0135] output:

[0136] Review results and next actions

[0137] (Application example 1)

[0138] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0139] Currently, there are systems that effectively support M&A activities for SMEs, but the M&A process for certain industrial sectors, particularly factory equipment, is not fully covered. This makes it difficult to quickly match M&A deals involving factory equipment and generate proposals, which in turn hinders efficient business succession and capital restructuring for SMEs.

[0140] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0141] In this invention, the server includes means for inputting information about the seller company, means for extracting potential buyers from a database, means for generating a proposal based on the extracted information about the potential buyers, means for displaying the generated proposal on a user interface, and means for inputting and matching information about factory equipment. This enables highly accurate matching in the M&A process for small and medium-sized enterprises that include factory equipment, making it possible to quickly and efficiently find suitable potential buyers and generate and provide proposals.

[0142] "Information about the seller's company" refers to basic information necessary to sell a company, such as the company's name, business operations, and financial status.

[0143] A "database" is an organized collection of data for collecting, storing, and retrieving information based on specified criteria.

[0144] A "potential buyer" is a company or individual that has the potential to acquire the seller company.

[0145] A "proposal" is a document that contains the information necessary to proceed with a contract between a selling company and a potential buyer.

[0146] A "user interface" refers to the input and display screens that allow a user to interact with a system.

[0147] "Factory equipment" is a general term for various devices, machines, robots, etc. used in factory production processes.

[0148] "Matching" involves comparing the seller's information with the conditions of potential buyers and finding the optimal combination based on matching elements.

[0149] A "generative artificial intelligence model" is an AI (artificial intelligence) algorithm that is trained to analyze patterns in data and make decisions or predictions.

[0150] A "machine learning algorithm" is a mathematical model that learns from data and makes predictions or classifications to perform a specific task.

[0151] "Extraction" means selecting information from a database or other source that meets specific criteria.

[0152] A "form" is an interface that allows a user to enter information, typically containing text boxes, drop-down menus, radio buttons, etc.

[0153] "Processing" refers to a series of steps or operations that input, transform, analyze, and output data.

[0154] This invention is a system for supporting the M&A process of small and medium-sized enterprises that purchase factory equipment. The system has various functions for inputting and matching information on seller companies, factory equipment, and potential buyers, and generating and displaying proposals.

[0155] The server functions as the central component of the entire system. It receives information about the seller company and factory equipment from the user, and extracts suitable potential buyers from the database based on that information. High-precision matching can be achieved using a generative artificial intelligence model. The server also generates proposals based on the extracted information about potential buyers and sends these proposals to the terminal.

[0156] The terminal functions as an interface for users to interact with the system. The terminal provides a form for users to enter basic information about the seller company and factory equipment, and transmits the entered information to the server. The terminal also displays proposals received from the server to users, allowing them to review the proposals and take necessary actions.

[0157] The user uses a terminal to enter information about the seller company and the factory equipment, and then sends the entered information to the server. The server receives the information, extracts suitable potential buyers from a database, generates a proposal, and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review the proposal. This process allows the user to quickly and efficiently find potential buyers and make the best proposal for the seller company and the factory equipment.

[0158] As a concrete example, when a user of a small or medium-sized enterprise uses the system, he or she enters company information and information about factory equipment into an input form on a terminal. For example, the user enters the company name "XYZ Corporation," the business description "software development," and the information about the "industrial robots" they use. This information is sent to the server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review the proposal, allowing the M&A process to proceed quickly and effectively.

[0159] Prompt Sentence Examples

[0160] Company name: XYZ Corporation, Business description: Software development, Factory equipment: Industrial robots

[0161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0162] Step 1: The user enters information about the seller company and factory equipment through the terminal.

[0163] The user enters information about the company name, business activities, and factory equipment into a form on the terminal. The input for this step is the data entered by the user, which is then retrieved by the terminal. The output is a dataset containing all the information entered.

[0164] Step 2: The device sends the input information to the server

[0165] The terminal sends the data entered by the user to the server. The input of this step is the dataset acquired in step 1, and it sends it to the server. The output is the data sent to the server.

[0166] Step 3: The server receives the data

[0167] The server receives the seller company and factory equipment information sent from the terminal. The input to this step is the data sent in step 2. The server receives this data and prepares it for processing. The output is the correctly received data.

[0168] Step 4: The server extracts suitable potential buyers from the database

[0169] The server uses the received data to process it to extract suitable potential buyers from the database, using machine learning algorithms and generative AI models. The input is the data received by the server and the contents of the database, and the output is a list of potential buyers.

[0170] Step 5: The server generates a proposal based on the extracted information about the potential buyer.

[0171] The server generates a proposal based on the extracted information of potential buyers. This process utilizes natural language generation technology. The input is a list of potential buyers, and the output is the generated proposal.

[0172] Step 6: The server sends the generated proposal to the device

[0173] The server sends the generated proposal to the terminal. The input is the generated proposal and performs a sending operation. The output is the proposal sent to the terminal.

[0174] Step 7: The device displays the proposal in its user interface.

[0175] The terminal displays the proposal received from the server on a user interface. The input is the received proposal and the output is the proposal displayed on the user interface, allowing the user to review the proposal and take action if necessary.

[0176] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0177] This invention provides an M&A business support system for small and medium-sized enterprises. This system automates a series of processes: inputting information about the selling company, extracting potential buyers from a database based on that information, generating a proposal based on the extracted information about the potential buyers, and displaying the generated proposal on a user interface. Furthermore, by incorporating an emotion engine that recognizes the user's emotions and customizes the content of the proposal based on that information, the system can provide more personalized proposals.

[0178] The server functions as the central component of the system. First, the server receives information about the seller company from the user and then uses that information to extract suitable potential buyers from a database. The server utilizes a generative artificial intelligence model to extract potential buyers, thereby achieving highly accurate matching. The server then generates a proposal based on the extracted information about the potential buyers and sends this proposal to the terminal.

[0179] The terminal functions as an interface for users to interact with the system. It provides a form for users to enter basic information about the seller company and sends the entered information to the server. The terminal also displays the proposal received from the server to the user, allowing the user to review the proposal and take any necessary actions. Furthermore, the terminal is equipped with an emotion engine that analyzes user emotions in real time and sends that information to the server to optimize the content of the proposal.

[0180] The user uses a terminal to enter information about the seller company and sends the entered information to the server. A proposal is generated from the server and displayed on the terminal, where the user can review it and select the most suitable potential buyer. The emotion engine analyzes the user's facial expressions and voice as they review the proposal to understand their emotional state. For example, if the user appears satisfied after viewing the proposal, the engine collects feedback and analyzes what aspects of the proposal the user finds appealing. This feedback information is used when generating the next proposal, improving the system to make more appropriate proposals.

[0181] Consider the following scenario as a specific example. When a small- to medium-sized enterprise (SME) called "BBB Co., Ltd." uses the system, the user enters basic information about "BBB Co., Ltd." (e.g., company name "BBB Co., Ltd.", business description "manufacturing") into an input form on a terminal. This information is sent to the server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on its user interface, while an emotion engine analyzes the user's facial expressions and voice to understand their emotional state. For example, if the user shows positive emotions, such as smiling, when reviewing the proposal, this emotion data is sent to the server and used as feedback to improve the quality of future proposals.

[0182] By implementing this invention, the M&A process for small and medium-sized enterprises will be significantly more efficient, making it easier for sellers to find buyers on their desired terms. Furthermore, by incorporating an emotion engine, more appropriate and personalized proposals based on the user's emotions will be provided. This system will solve business succession issues for small and medium-sized enterprises and promote sustainable economic growth.

[0183] The processing flow will be explained below.

[0184] Step 1:

[0185] The terminal displays a form on the user interface for entering basic information about the seller company, including fields for the company name, business details, contact information, etc.

[0186] Step 2:

[0187] The user enters the necessary information into the input form on the terminal and clicks the "Submit" button, which causes the data entered into the form to be acquired by the terminal.

[0188] Step 3:

[0189] The terminal packages the acquired seller information and creates a request to send to the server, using JSON format or similar.

[0190] Step 4:

[0191] The server receives the seller company information sent from the terminal and prepares for database access.

[0192] Step 5:

[0193] The server runs machine learning algorithms to extract the best-matched potential buyers from the database based on the seller's information, using predictive models and clustering algorithms.

[0194] Step 6:

[0195] The server analyzes the extracted information about the potential buyer and begins the process of embedding that information into a proposal template for the seller company.

[0196] Step 7:

[0197] The server then sends the generated proposal to the terminal, which includes details such as the buyer's name, business activities, and offer details.

[0198] Step 8:

[0199] The terminal displays the proposal received from the server on the user interface in an easy-to-read format so that the user can check the proposal.

[0200] Step 9:

[0201] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice, and based on the results of this analysis, determines the user's emotional state in real time.

[0202] Step 10:

[0203] The emotion engine sends the user's emotion data to the server. For example, if the user looks satisfied while looking at the proposal, the engine sends data containing that information.

[0204] Step 11:

[0205] The server analyzes the feedback on the proposal based on the received emotional data and uses it in the next proposal generation process, thereby optimizing the proposal content.

[0206] Step 12:

[0207] The user can review the proposals displayed through the terminal interface, provide feedback if necessary, and select the most suitable potential buyer.

[0208] Through this series of processing steps, the system of the present invention enables sellers to quickly and efficiently find potential buyers and advance the M&A process with personalized proposals based on emotional data.

[0209] Example 2

[0210] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0211] Conventional M&A support systems for small and medium-sized enterprises have problems such as low accuracy in effectively matching information on sellers and potential buyers, and a lack of personalization in the generation of proposals, resulting in low user satisfaction.Furthermore, feedback reflecting user sentiment is not incorporated into proposals, making it difficult to continuously improve the quality of proposals.

[0212] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0213] In this invention, the server includes means for inputting information about the seller company, means for extracting potential buyers from a database, means for generating a proposal based on the extracted information about the potential buyers, means for displaying the generated proposal on a user interface, and means for recognizing a user's emotions and customizing the contents of the proposal based on that information. This makes it possible to optimize the proposal contents based on the individual emotional state of the user and provide highly accurate matching and personalized proposals.

[0214] A "seller" is a company or organization seeking to sell a company or business.

[0215] A "potential buyer" is a company or organization that may purchase the company or business being sold.

[0216] A "database" is a collection of data organized to efficiently store, retrieve, edit, and delete information.

[0217] A "proposal" is a document prepared to facilitate a transaction between a selling company and a potential buyer, and primarily contains transaction terms and background information.

[0218] "User interface" refers to the screens and operating means through which the system and the user interact with each other.

[0219] "Means for recognizing emotions" refers to technology or devices that analyze a user's facial expressions and voice and identify their emotional state.

[0220] A "generative artificial intelligence model" is a program that uses machine learning algorithms to learn patterns from data and make decisions and predictions.

[0221] A "machine learning model" is a technology that learns rules and patterns from data and makes predictions and classifications for new data.

[0222] This invention provides a system for supporting M&A transactions for small and medium-sized enterprises. This system inputs information about the seller company, extracts potential buyers from a database based on that information, then generates a proposal based on the information about the potential buyers, and finally displays the generated proposal on a user interface. It can also recognize the user's emotions and customize the content of the proposal based on that information.

[0223] The server acts as the central component of this system. It receives information about sellers from users and processes it to extract suitable potential buyers from a database based on that information. To improve the accuracy of this matching, a generative artificial intelligence model is used. For example, machine learning libraries such as TensorFlow and PyTorch can be used.

[0224] The server then uses a template engine to generate a proposal based on the extracted information about the potential buyer. The generated proposal is output in PDF or HTML format and sent from the server to the device, typically using an HTTP response.

[0225] The terminal functions as an interface for users to interact with the system. The terminal prompts users to enter basic information about the seller company through an input form built with HTML / CSS, and then sends that information to the server. The terminal also displays the proposal received from the server to the user. The user can review the proposal and take any necessary actions.

[0226] The device is also equipped with an emotion engine that analyzes the user's facial expressions and voice to understand their emotional state. Using technologies such as OpenCV and NVIDIA DeepStream, the device can analyze the user's emotions in real time. This emotion data is sent from the device to a server, which then uses it to optimize the content of the next proposal.

[0227] Consider the following scenario as a concrete example. When a seller company, "Company A," uses the system, the user enters basic information about "Company A" (company name, business activities, location, and desired buyer conditions) into an input form on their terminal. This information is sent to the server, which then uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the potential buyers and sends it to the terminal. The terminal displays the proposal on a user interface, and the user confirms it. At the same time, an emotion engine analyzes the user's facial expressions and voice, and the emotional data is sent to the server. For example, if the user confirms the proposal and smiles with satisfaction, this positive emotional data is used as feedback the next time a proposal is generated.

[0228] An example prompt is:

[0229] Basic information of seller company "Company A":

[0230] Company name: Company A

[0231] Business content: Manufacturing industry

[0232] Location: Tokyo

[0233] Desired buyer conditions: Domestic companies considering business expansion

[0234] By inputting this prompt into the generative AI model, highly accurate matching and proposal generation become possible. In addition, the feedback function of the emotion engine allows for continuous improvement of the quality of the proposal content.

[0235] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0236] Step 1:

[0237] Input: The user enters basic information about the seller company (company name, business activities, location, desired buyer conditions, etc.) into the input form on the terminal.

[0238] Processing: The terminal displays an input form built with HTML / CSS and allows the user to enter the required information.

[0239] Output: The information entered by the user is sent by the terminal to the server.

[0240] Specific operation: The user enters the required information into the form and clicks the submit button. The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[0241] Step 2:

[0242] Input: The server receives the basic information of the seller company sent from the terminal.

[0243] Processing: The server parses the HTTP request and converts the received data into a format that can be processed.

[0244] Output: The parsed data is stored as a data object available in the server.

[0245] What happens: The server receives the HTTP request, parses the data using a JSON parser, and converts it into the appropriate database entry.

[0246] Step 3:

[0247] Input: Basic information about the seller company.

[0248] Processing: The server uses a generative artificial intelligence model to extract potential buyers from the database.

[0249] Output: Extracted potential buyer information.

[0250] How it works: The server uses machine learning libraries such as TensorFlow and PyTorch to run algorithms to identify the most suitable potential buyers for the selling company from the database.

[0251] Step 4:

[0252] Input: Extracted prospective buyer information.

[0253] Processing: The server uses a template engine to generate the proposal.

[0254] Output: The generated proposal (PDF or HTML format).

[0255] Specific operation: The server uses a template engine (e.g., Jinja2) to generate a proposal by inserting the extracted information of the potential buyer. The generated proposal is saved as a file.

[0256] Step 5:

[0257] Input: The generated proposal.

[0258] Processing: The server sends the generated proposal to the terminal.

[0259] Output: Proposal link or file viewable on your device.

[0260] Specific operation: The server sends the proposal file as an HTTP response and provides the device with a download link and a viewing page.

[0261] Step 6:

[0262] Input: Proposal link or file sent from the server.

[0263] Processing: The terminal displays the proposal on the user interface.

[0264] Output: The proposal that is displayed to the user.

[0265] Specific operation: The device analyzes the HTTP response and displays the received proposal link and file in the user interface. The user interacts with the response to confirm it.

[0266] Step 7:

[0267] Input: User's facial expressions and voice.

[0268] Processing: The terminal uses the emotion engine to analyze the user's emotions.

[0269] Output: Parsed emotion data.

[0270] Specific operation: Using the device's built-in camera and microphone, the system captures the user's facial expressions and voice in real time, and performs emotion analysis using technologies such as OpenCV and NVIDIA DeepStream.

[0271] Step 8:

[0272] Input: Parsed emotion data.

[0273] Processing: The device sends the emotion data to the server.

[0274] Output: Emotion data object available on the server side.

[0275] Specific operation: The device converts the analyzed emotion data into JSON format and sends it to the server as an HTTP request.

[0276] Step 9:

[0277] Input: Emotion data.

[0278] Processing: The server analyzes the received emotion data and stores it in a database to optimize the content of the next proposal.

[0279] Output: Feedback for optimized proposal generation.

[0280] Specific operation: The server receives the emotion data, analyzes it, stores it in a database, and reflects this feedback when generating the next proposal.

[0281] (Application example 2)

[0282] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0283] In conventional systems for matching sellers and buyers, the process from inputting seller information to identifying potential buyers and generating proposals takes a lot of time and effort. Furthermore, the proposals are uniform, resulting in low user satisfaction and making it difficult to conclude efficient sales contracts. While there is a particular demand for personalized proposals that take user sentiment into account, there is a lack of mechanisms to achieve this. This prevents sellers, such as small and medium-sized enterprises, from conducting quick and effective sales activities, often resulting in missed market opportunities.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0285] In this invention, the server includes means for inputting information about the seller company, means for extracting potential buyers from a database, means for generating a proposal based on the information about the extracted potential buyers, means for transmitting the proposal to a user terminal and displaying it on the display of the user terminal, means for analyzing the user's emotions in real time and customizing the contents of the proposal based on that information, and means for the emotion analysis means to analyze the user's facial expressions and voice and transmit emotional data to the server. This enables quick and effective matching between seller companies and buyer companies, and also makes it possible to provide personalized proposals based on the user's emotions.

[0286] "Means for inputting seller company information" refers to an interface or device that allows a seller company to input its own company information into the system.

[0287] "Means for extracting potential buyers from a database" refers to technology for selecting and extracting appropriate potential buyers from a database based on the input information of the seller company.

[0288] The "means for generating a proposal" is a system or algorithm for creating a proposal that is beneficial to both the seller company and the potential buyer based on the extracted information about the potential buyer.

[0289] The "means for displaying the proposal on the display of the user terminal" is a system for transmitting the generated proposal to the user terminal and displaying it on the display.

[0290] "Emotion analysis means" is a technology for analyzing a user's facial expressions and voice in real time to understand the user's emotional state.

[0291] "Means for the emotion analysis means to analyze the user's facial expressions and voice and send the emotion data to the server" is a technology for sending the data acquired by the emotion analysis means to the server and customizing the contents of the proposal.

[0292] The present invention relates to an emotion-aware store support system for improving the shopping experience in physical stores. This system integrates multiple hardware and software components to provide personalized suggestions based on customer emotions in real time. This specification describes the specific configuration and operation of the system.

[0293] System configuration

[0294] 1. Server

[0295] Role: Serves as the central component of the system, receiving, processing and storing data.

[0296] Technologies used: Machine learning algorithms, generative AI models

[0297] Specific process: Based on the seller's information, appropriate potential buyers are extracted from the database and a proposal is generated.

[0298] 2. User Device

[0299] Role: Receives input from the user and communicates with the server.

[0300] Hardware examples: smartphones, smart glasses

[0301] Specific process: The user inputs seller or product information through the terminal interface and sends this information to the server, and the proposal received from the server is displayed on the screen.

[0302] 3. Sentiment Analysis Engine

[0303] Role: Analyzes the user's facial expressions and voice in real time to obtain emotional data.

[0304] Technologies used: facial expression recognition algorithm, voice analysis technology

[0305] Specific processing: Understand the user's emotional state when reviewing the proposal and send that information to the server.

[0306] Detailed System Operation

[0307] 1. Enter and submit information

[0308] Users enter their personal information (preferences, desired conditions, etc.) using an input form displayed on the screen of their smartphone or smart glasses. The entered information is sent to the server in real time.

[0309] 2. Identifying potential buyers

[0310] The server extracts potential buyers from a database based on the received user information, using machine learning algorithms to achieve highly accurate matching.

[0311] 3. Proposal Generation and Viewing

[0312] The server generates a proposal based on the extracted candidate information and sends it to the user's terminal, where the proposal is displayed on the screen.

[0313] 4. Sentiment Analysis and Feedback

[0314] The emotion analysis engine analyzes the user's facial expressions and voice in real time and sends the emotional data to the server, which then uses this emotional feedback to customize the content of future proposals.

[0315] Specific examples

[0316] System usage examples

[0317] For example, if a customer uses the system in a fashion shop and enters "I want casual fashion, blue, size M," the server will send the following prompt to the generative AI model:

[0318] "I'm looking for casual fashion. The color is blue, and the size is medium. Please recommend some products."

[0319] Based on this information, the system will suggest suitable products and display them on the user's device. At the same time, by analyzing the user's facial expressions and voice, the system can understand the customer's level of satisfaction with the suggestions and use this information as feedback to improve the quality of the suggestions.

[0320] This system will significantly improve the customer experience in physical stores and enable more personalized shopping suggestions.

[0321] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0322] Step 1:

[0323] User enters information on device

[0324] Input: Information such as the style, color, and size desired by the user

[0325] How it works: Users enter their fashion preferences and desired conditions using an input form displayed on the screen of their smartphone or smart glasses. The input information is sent to the server in real time.

[0326] Output: The user's input information is sent to the server.

[0327] Step 2:

[0328] The server extracts potential buyers

[0329] Input: Fashion preferences and desired conditions submitted by the user

[0330] How it works: The server extracts potential buyers from a database based on the received user information. This process uses machine learning algorithms to achieve highly accurate matching.

[0331] Output: Extracted information about potential buyers

[0332] Step 3:

[0333] The server generates the proposal

[0334] Input: Extracted information about potential buyers

[0335] Specific operation: Based on the extracted information of potential buyers, the server uses a generative AI model to create an optimal proposal, which is a list of products and services that meet the user's requirements.

[0336] Output: Generated proposal

[0337] Step 4:

[0338] The server sends the proposal to the device.

[0339] Input: Generated proposal

[0340] Specific operation: The proposal is sent to the user's device and displayed on the user's device's display.

[0341] Output: The proposal is displayed on the user's device.

[0342] Step 5:

[0343] The user reviews the proposal and analyzes the sentiment data.

[0344] Input: Facial expressions and voice of the user reviewing the proposal

[0345] How it works: The emotion analysis engine analyzes the user's facial expressions and voice in real time and sends the results to the server. It uses the camera built into the smart glasses or the front camera of the smartphone for facial recognition, and the microphone for voice analysis.

[0346] Output: Parsed emotion data

[0347] Step 6:

[0348] The server improves the proposal based on the feedback.

[0349] Input: Parsed emotion data

[0350] Specific operation: The server analyzes the user's emotional data and reflects it in the next proposal generation. At this time, feedback information obtained from the emotional data is utilized.

[0351] Output: Data base for improved proposals

[0352] Through the above processing steps, users can receive personalized suggestions in real time, enabling them to find the best products and services.

[0353] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0354] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0355] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0356] [Second embodiment]

[0357] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0358] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0359] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0360] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0361] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0362] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0363] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0364] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0365] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0366] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0367] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0368] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0369] This invention provides an M&A business support system for small and medium-sized enterprises. This system automates a series of processes: inputting information about the seller company, extracting potential buyers from a database based on that information, generating a proposal based on the extracted information about the potential buyers, and displaying the generated proposal on a user interface.

[0370] The server functions as the central component of the system. It receives information about the selling company from the user (M&A specialist) and uses that information to extract suitable potential buyers from a database. The server utilizes a generative artificial intelligence model to extract potential buyers, thereby achieving highly accurate matching. It then generates a proposal based on the extracted information about the potential buyers and sends this proposal to the terminal.

[0371] The terminal serves as an interface for users to interact with the system. The terminal provides a form for users to enter basic information about the seller company and transmits the entered information to the server. The terminal also displays proposals received from the server to the users, allowing them to review the proposals and take necessary actions.

[0372] The user uses a terminal to input information about the seller company and sends the input information to the server. The server generates a proposal and displays it on the terminal, allowing the user to review it and select the most suitable potential buyer.

[0373] Consider the following scenario as a specific example. When AAA Corporation, a small or medium-sized enterprise, uses the system, the user enters AAA Corporation's company information (e.g., company name, "AAA Corporation," business description, "software development") into an input form on a terminal. This information is sent to the server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review it. This process enables AAA Corporation to quickly and efficiently find potential buyers and propose optimal terms to the selling company.

[0374] By implementing this invention, the M&A process for small and medium-sized enterprises will be significantly more efficient, making it easier for sellers to find buyers on the terms they desire. This system will resolve business succession issues for small and medium-sized enterprises and promote sustainable economic growth.

[0375] The processing flow will be explained below.

[0376] Step 1:

[0377] The terminal displays a form on the user interface for the seller company to enter basic information about the company (company name, business details, etc.).

[0378] Step 2:

[0379] The user enters the seller's company information into the input form on the terminal and clicks the "Submit" button on the form.

[0380] Step 3:

[0381] The terminal acquires the seller company information entered by the user, creates a request to send the information to the server, and sends it.

[0382] Step 4:

[0383] The server processes the seller company information received from the terminal and accesses a database to execute queries to extract suitable potential buyers.

[0384] Step 5:

[0385] The server uses machine learning algorithms to extract suitable potential buyers from the database, thereby identifying buyers that match the characteristics of the seller.

[0386] Step 6:

[0387] The server executes a program for generating a proposal based on the extracted information of potential buyers, and creates the proposal by embedding the information in a template.

[0388] Step 7:

[0389] The server transmits the generated proposal to the terminal.

[0390] Step 8:

[0391] The terminal displays the proposal received from the server on a user interface, allowing the user to check the proposal.

[0392] Step 9:

[0393] The user can review the proposals displayed through the terminal interface, provide feedback if necessary, and select the most suitable potential buyer.

[0394] Through this series of processing steps, the system of the present invention enables a seller to quickly and efficiently find potential buyers and proceed with the M&A process under optimal conditions.

[0395] Example 1

[0396] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0397] There is a lack of appropriate support systems for small and medium-sized enterprises to carry out M&A work quickly and efficiently. Furthermore, there is a need for high accuracy in matching sellers with potential buyers and in automatically generating proposals. This is expected to streamline the entire M&A process and improve the success rate.

[0398] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0399] In this invention, the server includes means for transmitting input information, means for searching a database based on the received information to extract candidates, means for generating proposals based on the information using a generative artificial intelligence model, and means for displaying the generated proposals on a user interface, thereby enabling highly accurate matching between seller companies and potential buyer companies and realizing the automatic generation and display of proposals quickly and efficiently.

[0400] The "means for transmitting input information" is a means by which a user inputs information about a seller company into a terminal and transmits it to a server.

[0401] "Means for searching a database based on received information and extracting candidates" refers to means for the server to search data in a database based on the information of the seller company received from the user and extract appropriate buyer candidates.

[0402] "Means for generating a proposal based on information using a generative artificial intelligence model" refers to means for automatically generating a proposal using a generative artificial intelligence model based on information about potential buyers extracted by the server.

[0403] The "means for displaying the generated proposal on a user interface" refers to a means for the server to transmit the generated proposal to the terminal, and for the terminal to display this proposal on a user interface.

[0404] The "generative artificial intelligence model that automatically matches seller information with buyer information and quickly creates proposals" is an artificial intelligence model that automatically matches information on seller companies and potential buyer companies and quickly generates proposals with high accuracy.

[0405] "Extraction of candidates from the database is performed using a machine learning algorithm" refers to the process in which the server searches the data in the database and extracts suitable potential buyers using a machine learning algorithm.

[0406] The present invention provides an M&A business support system for small and medium-sized enterprises, which automates a series of processes: inputting information about the selling company, extracting potential buyers from a database based on that information, generating a proposal based on the information about the extracted potential buyers, and displaying the generated proposal on a user interface.

[0407] Hardware and software used

[0408] server

[0409] The server is the central component of the system and uses cloud servers such as AWS (Amazon Web Services) and Google Cloud Platform. The database uses a relational database management system (RDBMS) such as MySQL or PostgreSQL. Machine learning frameworks such as TensorFlow and PyTorch are used as generative artificial intelligence models.

[0410] Terminal

[0411] The terminals are PCs, tablets, and smartphones that serve as interfaces for users to interact with the system. The user interface is built using front-end frameworks such as React, Vue.js, and Angular.

[0412] Program processing

[0413] The server performs a database search based on the seller company information received from the terminal and extracts suitable potential buyers. This process uses a generative artificial intelligence model to achieve highly accurate matching. A proposal is automatically generated based on the extracted information on the potential buyers and sent to the terminal.

[0414] The terminal provides a form for the user to input information about the seller company, transmits the input information to the server, and displays the proposal received from the server on a user interface, allowing the user to review the proposal and take necessary actions.

[0415] The user inputs the seller's information and sends it to the server. The server generates a proposal and displays it on the terminal, allowing the user to review it and select the most suitable potential buyer.

[0416] Specific examples

[0417] A specific example of how a small and medium-sized enterprise, AAA Co., Ltd., uses the system is given below.

[0418] The user enters the following information into the terminal's input form:

[0419] Company name: "AAA Co., Ltd."

[0420] Business: Software development

[0421] This information is sent to a server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review it. This process enables AAA Corporation to quickly and efficiently find potential buyers and propose optimal terms to the seller.

[0422] The above is an embodiment of the present invention.

[0423] Example of a prompt statement without JSON

[0424] The user enters the following information into the terminal's input form:

[0425] Company name: "AAA Co., Ltd."

[0426] Business: Software development

[0427] The server receives this information, performs a database search, and extracts suitable potential buyers using a generative AI model (e.g., using TensorFlow).The server then generates a proposal based on the extracted information about the potential buyers and sends the generated proposal to the terminal.The terminal displays the proposal on a user interface, and the user can confirm the proposal.

[0428] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0429] Step 1:

[0430] The user enters information about the seller company into an input form on the device, including specific information such as the company name and business details. The entered information is temporarily stored in the device's internal memory.

[0431] input:

[0432] Company name: "AAA Co., Ltd."

[0433] Business: Software development

[0434] output:

[0435] Company information entered into the terminal

[0436] Step 2:

[0437] The terminal sends the entered seller information to the server using the HTTPS protocol, and the data is encoded in JSON format, so the entered information is passed to the server securely.

[0438] input:

[0439] Company information entered into the terminal

[0440] output:

[0441] Company information in JSON format sent to the server

[0442] Step 3:

[0443] The server parses the received JSON data and extracts information about the seller. Based on this information, it performs a database search to extract potential buyers. This process uses a generative AI model to achieve highly accurate matching.

[0444] input:

[0445] Company information in JSON format sent to the server

[0446] output:

[0447] Extracted information on potential buyers

[0448] Step 4:

[0449] The server automatically generates a proposal based on the extracted information of potential buyers. This proposal includes details of the potential buyers and their proposals. The generative AI model is used to generate the optimal proposal.

[0450] input:

[0451] Extracted information on potential buyers

[0452] output:

[0453] Auto-generated proposal

[0454] Step 5:

[0455] The server sends the generated proposal in JSON format to the terminal. Because the proposal is sent as an HTTP response, there is little latency (delay) when the terminal receives it.

[0456] input:

[0457] Auto-generated proposal

[0458] output:

[0459] Proposal in JSON format sent to the device

[0460] Step 6:

[0461] The terminal parses the received proposal data and displays it in a user interface, using front-end frameworks such as React and Vue.js to display the proposal in a visually easy-to-understand format.

[0462] input:

[0463] Proposal in JSON format sent to the device

[0464] output:

[0465] Proposal displayed in the user interface

[0466] Step 7:

[0467] The user checks the proposal on the device screen, selects the most suitable buyer based on the information on potential buyers listed in the proposal, and decides on the next action (contact or adjustment of terms).

[0468] input:

[0469] Proposal displayed in the user interface

[0470] output:

[0471] Review results and next actions

[0472] (Application example 1)

[0473] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0474] Currently, there are systems that effectively support M&A activities for SMEs, but the M&A process for certain industrial sectors, particularly factory equipment, is not fully covered. This makes it difficult to quickly match M&A deals involving factory equipment and generate proposals, which in turn hinders efficient business succession and capital restructuring for SMEs.

[0475] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0476] In this invention, the server includes means for inputting information about the seller company, means for extracting potential buyers from a database, means for generating a proposal based on the extracted information about the potential buyers, means for displaying the generated proposal on a user interface, and means for inputting and matching information about factory equipment. This enables highly accurate matching in the M&A process for small and medium-sized enterprises that include factory equipment, making it possible to quickly and efficiently find suitable potential buyers and generate and provide proposals.

[0477] "Information about the seller's company" refers to basic information necessary to sell a company, such as the company's name, business operations, and financial status.

[0478] A "database" is an organized collection of data for collecting, storing, and retrieving information based on specified criteria.

[0479] A "potential buyer" is a company or individual that has the potential to acquire the seller company.

[0480] A "proposal" is a document that contains the information necessary to proceed with a contract between a selling company and a potential buyer.

[0481] A "user interface" refers to the input and display screens that allow a user to interact with a system.

[0482] "Factory equipment" is a general term for various devices, machines, robots, etc. used in factory production processes.

[0483] "Matching" involves comparing the seller's information with the conditions of potential buyers and finding the optimal combination based on matching elements.

[0484] A "generative artificial intelligence model" is an AI (artificial intelligence) algorithm that is trained to analyze patterns in data and make decisions or predictions.

[0485] A "machine learning algorithm" is a mathematical model that learns from data and makes predictions or classifications to perform a specific task.

[0486] "Extraction" means selecting information from a database or other source that meets specific criteria.

[0487] A "form" is an interface that allows a user to enter information, typically containing text boxes, drop-down menus, radio buttons, etc.

[0488] "Processing" refers to a series of steps or operations that input, transform, analyze, and output data.

[0489] This invention is a system for supporting the M&A process of small and medium-sized enterprises that purchase factory equipment. The system has various functions for inputting and matching information on seller companies, factory equipment, and potential buyers, and generating and displaying proposals.

[0490] The server functions as the central component of the entire system. It receives information about the seller company and factory equipment from the user, and extracts suitable potential buyers from the database based on that information. High-precision matching can be achieved using a generative artificial intelligence model. The server also generates proposals based on the extracted information about potential buyers and sends these proposals to the terminal.

[0491] The terminal functions as an interface for users to interact with the system. The terminal provides a form for users to enter basic information about the seller company and factory equipment, and transmits the entered information to the server. The terminal also displays proposals received from the server to users, allowing them to review the proposals and take necessary actions.

[0492] The user uses a terminal to enter information about the seller company and the factory equipment, and then sends the entered information to the server. The server receives the information, extracts suitable potential buyers from a database, generates a proposal, and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review the proposal. This process allows the user to quickly and efficiently find potential buyers and make the best proposal for the seller company and the factory equipment.

[0493] As a concrete example, when a user of a small or medium-sized enterprise uses the system, he or she enters company information and information about factory equipment into an input form on a terminal. For example, the user enters the company name "XYZ Corporation," the business description "software development," and the information about the "industrial robots" they use. This information is sent to the server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review the proposal, allowing the M&A process to proceed quickly and effectively.

[0494] Prompt Sentence Examples

[0495] Company name: XYZ Corporation, Business description: Software development, Factory equipment: Industrial robots

[0496] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0497] Step 1: The user enters information about the seller company and factory equipment through the terminal.

[0498] The user enters information about the company name, business activities, and factory equipment into a form on the terminal. The input for this step is the data entered by the user, which is then retrieved by the terminal. The output is a dataset containing all the information entered.

[0499] Step 2: The device sends the input information to the server

[0500] The terminal sends the data entered by the user to the server. The input of this step is the dataset acquired in step 1, and it sends it to the server. The output is the data sent to the server.

[0501] Step 3: The server receives the data

[0502] The server receives the seller company and factory equipment information sent from the terminal. The input to this step is the data sent in step 2. The server receives this data and prepares it for processing. The output is the correctly received data.

[0503] Step 4: The server extracts suitable potential buyers from the database

[0504] The server uses the received data to process it to extract suitable potential buyers from the database, using machine learning algorithms and generative AI models. The input is the data received by the server and the contents of the database, and the output is a list of potential buyers.

[0505] Step 5: The server generates a proposal based on the extracted information about the potential buyer.

[0506] The server generates a proposal based on the extracted information of potential buyers. This process utilizes natural language generation technology. The input is a list of potential buyers, and the output is the generated proposal.

[0507] Step 6: The server sends the generated proposal to the device

[0508] The server sends the generated proposal to the terminal. The input is the generated proposal and performs a sending operation. The output is the proposal sent to the terminal.

[0509] Step 7: The device displays the proposal in its user interface.

[0510] The terminal displays the proposal received from the server on a user interface. The input is the received proposal and the output is the proposal displayed on the user interface, allowing the user to review the proposal and take action if necessary.

[0511] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0512] This invention provides an M&A business support system for small and medium-sized enterprises. This system automates a series of processes: inputting information about the selling company, extracting potential buyers from a database based on that information, generating a proposal based on the extracted information about the potential buyers, and displaying the generated proposal on a user interface. Furthermore, by incorporating an emotion engine that recognizes the user's emotions and customizes the content of the proposal based on that information, the system can provide more personalized proposals.

[0513] The server functions as the central component of the system. First, the server receives information about the seller company from the user and then uses that information to extract suitable potential buyers from a database. The server utilizes a generative artificial intelligence model to extract potential buyers, thereby achieving highly accurate matching. The server then generates a proposal based on the extracted information about the potential buyers and sends this proposal to the terminal.

[0514] The terminal functions as an interface for users to interact with the system. It provides a form for users to enter basic information about the seller company and sends the entered information to the server. The terminal also displays the proposal received from the server to the user, allowing the user to review the proposal and take any necessary actions. Furthermore, the terminal is equipped with an emotion engine that analyzes user emotions in real time and sends that information to the server to optimize the content of the proposal.

[0515] The user uses a terminal to enter information about the seller company and sends the entered information to the server. A proposal is generated from the server and displayed on the terminal, where the user can review it and select the most suitable potential buyer. The emotion engine analyzes the user's facial expressions and voice as they review the proposal to understand their emotional state. For example, if the user appears satisfied after viewing the proposal, the engine collects feedback and analyzes what aspects of the proposal the user finds appealing. This feedback information is used when generating the next proposal, improving the system to make more appropriate proposals.

[0516] Consider the following scenario as a specific example. When a small- to medium-sized enterprise (SME) called "BBB Co., Ltd." uses the system, the user enters basic information about "BBB Co., Ltd." (e.g., company name "BBB Co., Ltd.", business description "manufacturing") into an input form on a terminal. This information is sent to the server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on its user interface, while an emotion engine analyzes the user's facial expressions and voice to understand their emotional state. For example, if the user shows positive emotions, such as smiling, when reviewing the proposal, this emotion data is sent to the server and used as feedback to improve the quality of future proposals.

[0517] By implementing this invention, the M&A process for small and medium-sized enterprises will be significantly more efficient, making it easier for sellers to find buyers on their desired terms. Furthermore, by incorporating an emotion engine, more appropriate and personalized proposals based on the user's emotions will be provided. This system will solve business succession issues for small and medium-sized enterprises and promote sustainable economic growth.

[0518] The processing flow will be explained below.

[0519] Step 1:

[0520] The terminal displays a form on the user interface for entering basic information about the seller company, including fields for the company name, business details, contact information, etc.

[0521] Step 2:

[0522] The user enters the necessary information into the input form on the terminal and clicks the "Submit" button, which causes the data entered into the form to be acquired by the terminal.

[0523] Step 3:

[0524] The terminal packages the acquired seller information and creates a request to send to the server, using JSON format or similar.

[0525] Step 4:

[0526] The server receives the seller company information sent from the terminal and prepares for database access.

[0527] Step 5:

[0528] The server runs machine learning algorithms to extract the best-matched potential buyers from the database based on the seller's information, using predictive models and clustering algorithms.

[0529] Step 6:

[0530] The server analyzes the extracted information about the potential buyer and begins the process of embedding that information into a proposal template for the seller company.

[0531] Step 7:

[0532] The server then sends the generated proposal to the terminal, which includes details such as the buyer's name, business activities, and offer details.

[0533] Step 8:

[0534] The terminal displays the proposal received from the server on the user interface in an easy-to-read format so that the user can check the proposal.

[0535] Step 9:

[0536] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice, and based on the results of this analysis, determines the user's emotional state in real time.

[0537] Step 10:

[0538] The emotion engine sends the user's emotion data to the server. For example, if the user looks satisfied while looking at the proposal, the engine sends data containing that information.

[0539] Step 11:

[0540] The server analyzes the feedback on the proposal based on the received emotional data and uses it in the next proposal generation process, thereby optimizing the proposal content.

[0541] Step 12:

[0542] The user can review the proposals displayed through the terminal interface, provide feedback if necessary, and select the most suitable potential buyer.

[0543] Through this series of processing steps, the system of the present invention enables sellers to quickly and efficiently find potential buyers and advance the M&A process with personalized proposals based on emotional data.

[0544] Example 2

[0545] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0546] Conventional M&A support systems for small and medium-sized enterprises have problems such as low accuracy in effectively matching information on sellers and potential buyers, and a lack of personalization in the generation of proposals, resulting in low user satisfaction.Furthermore, feedback reflecting user sentiment is not incorporated into proposals, making it difficult to continuously improve the quality of proposals.

[0547] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0548] In this invention, the server includes means for inputting information about the seller company, means for extracting potential buyers from a database, means for generating a proposal based on the extracted information about the potential buyers, means for displaying the generated proposal on a user interface, and means for recognizing a user's emotions and customizing the contents of the proposal based on that information. This makes it possible to optimize the proposal contents based on the individual emotional state of the user and provide highly accurate matching and personalized proposals.

[0549] A "seller" is a company or organization seeking to sell a company or business.

[0550] A "potential buyer" is a company or organization that may purchase the company or business being sold.

[0551] A "database" is a collection of data organized to efficiently store, retrieve, edit, and delete information.

[0552] A "proposal" is a document prepared to facilitate a transaction between a selling company and a potential buyer, and primarily contains transaction terms and background information.

[0553] "User interface" refers to the screens and operating means through which the system and the user interact with each other.

[0554] "Means for recognizing emotions" refers to technology or devices that analyze a user's facial expressions and voice and identify their emotional state.

[0555] A "generative artificial intelligence model" is a program that uses machine learning algorithms to learn patterns from data and make decisions and predictions.

[0556] A "machine learning model" is a technology that learns rules and patterns from data and makes predictions and classifications for new data.

[0557] This invention provides a system for supporting M&A transactions for small and medium-sized enterprises. This system inputs information about the seller company, extracts potential buyers from a database based on that information, then generates a proposal based on the information about the potential buyers, and finally displays the generated proposal on a user interface. It can also recognize the user's emotions and customize the content of the proposal based on that information.

[0558] The server acts as the central component of this system. It receives information about sellers from users and processes it to extract suitable potential buyers from a database based on that information. To improve the accuracy of this matching, a generative artificial intelligence model is used. For example, machine learning libraries such as TensorFlow and PyTorch can be used.

[0559] The server then uses a template engine to generate a proposal based on the extracted information about the potential buyer. The generated proposal is output in PDF or HTML format and sent from the server to the device, typically using an HTTP response.

[0560] The terminal functions as an interface for users to interact with the system. The terminal prompts users to enter basic information about the seller company through an input form built with HTML / CSS, and then sends that information to the server. The terminal also displays the proposal received from the server to the user. The user can review the proposal and take any necessary actions.

[0561] The device is also equipped with an emotion engine that analyzes the user's facial expressions and voice to understand their emotional state. Using technologies such as OpenCV and NVIDIA DeepStream, the device can analyze the user's emotions in real time. This emotion data is sent from the device to a server, which then uses it to optimize the content of the next proposal.

[0562] Consider the following scenario as a concrete example. When a seller company, "Company A," uses the system, the user enters basic information about "Company A" (company name, business activities, location, and desired buyer conditions) into an input form on their terminal. This information is sent to the server, which then uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the potential buyers and sends it to the terminal. The terminal displays the proposal on a user interface, and the user confirms it. At the same time, an emotion engine analyzes the user's facial expressions and voice, and the emotional data is sent to the server. For example, if the user confirms the proposal and smiles with satisfaction, this positive emotional data is used as feedback the next time a proposal is generated.

[0563] An example prompt is:

[0564] Basic information of seller company "Company A":

[0565] Company name: Company A

[0566] Business content: Manufacturing industry

[0567] Location: Tokyo

[0568] Desired buyer conditions: Domestic companies considering business expansion

[0569] By inputting this prompt into the generative AI model, highly accurate matching and proposal generation become possible. In addition, the feedback function of the emotion engine allows for continuous improvement of the quality of the proposal content.

[0570] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0571] Step 1:

[0572] Input: The user enters basic information about the seller company (company name, business activities, location, desired buyer conditions, etc.) into the input form on the terminal.

[0573] Processing: The terminal displays an input form built with HTML / CSS and allows the user to enter the required information.

[0574] Output: The information entered by the user is sent by the terminal to the server.

[0575] Specific operation: The user enters the required information into the form and clicks the submit button. The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[0576] Step 2:

[0577] Input: The server receives the basic information of the seller company sent from the terminal.

[0578] Processing: The server parses the HTTP request and converts the received data into a format that can be processed.

[0579] Output: The parsed data is stored as a data object available in the server.

[0580] What happens: The server receives the HTTP request, parses the data using a JSON parser, and converts it into the appropriate database entry.

[0581] Step 3:

[0582] Input: Basic information about the seller company.

[0583] Processing: The server uses a generative artificial intelligence model to extract potential buyers from the database.

[0584] Output: Extracted potential buyer information.

[0585] How it works: The server uses machine learning libraries such as TensorFlow and PyTorch to run algorithms to identify the most suitable potential buyers for the selling company from the database.

[0586] Step 4:

[0587] Input: Extracted prospective buyer information.

[0588] Processing: The server uses a template engine to generate the proposal.

[0589] Output: The generated proposal (PDF or HTML format).

[0590] Specific operation: The server uses a template engine (e.g., Jinja2) to generate a proposal by inserting the extracted information of the potential buyer. The generated proposal is saved as a file.

[0591] Step 5:

[0592] Input: The generated proposal.

[0593] Processing: The server sends the generated proposal to the terminal.

[0594] Output: Proposal link or file viewable on your device.

[0595] Specific operation: The server sends the proposal file as an HTTP response and provides the device with a download link and a viewing page.

[0596] Step 6:

[0597] Input: Proposal link or file sent from the server.

[0598] Processing: The terminal displays the proposal on the user interface.

[0599] Output: The proposal that is displayed to the user.

[0600] Specific operation: The device analyzes the HTTP response and displays the received proposal link and file in the user interface. The user interacts with the response to confirm it.

[0601] Step 7:

[0602] Input: User's facial expressions and voice.

[0603] Processing: The terminal uses the emotion engine to analyze the user's emotions.

[0604] Output: Parsed emotion data.

[0605] Specific operation: Using the device's built-in camera and microphone, the system captures the user's facial expressions and voice in real time, and performs emotion analysis using technologies such as OpenCV and NVIDIA DeepStream.

[0606] Step 8:

[0607] Input: Parsed emotion data.

[0608] Processing: The device sends the emotion data to the server.

[0609] Output: Emotion data object available on the server side.

[0610] Specific operation: The device converts the analyzed emotion data into JSON format and sends it to the server as an HTTP request.

[0611] Step 9:

[0612] Input: Emotion data.

[0613] Processing: The server analyzes the received emotion data and stores it in a database to optimize the content of the next proposal.

[0614] Output: Feedback for optimized proposal generation.

[0615] Specific operation: The server receives the emotion data, analyzes it, stores it in a database, and reflects this feedback when generating the next proposal.

[0616] (Application example 2)

[0617] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0618] In conventional systems for matching sellers and buyers, the process from inputting seller information to identifying potential buyers and generating proposals takes a lot of time and effort. Furthermore, the proposals are uniform, resulting in low user satisfaction and making it difficult to conclude efficient sales contracts. While there is a particular demand for personalized proposals that take user sentiment into account, there is a lack of mechanisms to achieve this. This prevents sellers, such as small and medium-sized enterprises, from conducting quick and effective sales activities, often resulting in missed market opportunities.

[0619] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0620] In this invention, the server includes means for inputting information about the seller company, means for extracting potential buyers from a database, means for generating a proposal based on the information about the extracted potential buyers, means for transmitting the proposal to a user terminal and displaying it on the display of the user terminal, means for analyzing the user's emotions in real time and customizing the contents of the proposal based on that information, and means for the emotion analysis means to analyze the user's facial expressions and voice and transmit emotional data to the server. This enables quick and effective matching between seller companies and buyer companies, and also makes it possible to provide personalized proposals based on the user's emotions.

[0621] "Means for inputting seller company information" refers to an interface or device that allows a seller company to input its own company information into the system.

[0622] "Means for extracting potential buyers from a database" refers to technology for selecting and extracting appropriate potential buyers from a database based on the input information of the seller company.

[0623] The "means for generating a proposal" is a system or algorithm for creating a proposal that is beneficial to both the seller company and the potential buyer based on the extracted information about the potential buyer.

[0624] The "means for displaying the proposal on the display of the user terminal" is a system for transmitting the generated proposal to the user terminal and displaying it on the display.

[0625] "Emotion analysis means" is a technology for analyzing a user's facial expressions and voice in real time to understand the user's emotional state.

[0626] "Means for the emotion analysis means to analyze the user's facial expressions and voice and send the emotion data to the server" is a technology for sending the data acquired by the emotion analysis means to the server and customizing the contents of the proposal.

[0627] The present invention relates to an emotion-aware store support system for improving the shopping experience in physical stores. This system integrates multiple hardware and software components to provide personalized suggestions based on customer emotions in real time. This specification describes the specific configuration and operation of the system.

[0628] System configuration

[0629] 1. Server

[0630] Role: Serves as the central component of the system, receiving, processing and storing data.

[0631] Technologies used: Machine learning algorithms, generative AI models

[0632] Specific process: Based on the seller's information, appropriate potential buyers are extracted from the database and a proposal is generated.

[0633] 2. User Device

[0634] Role: Receives input from the user and communicates with the server.

[0635] Hardware examples: smartphones, smart glasses

[0636] Specific process: The user inputs seller or product information through the terminal interface and sends this information to the server, and the proposal received from the server is displayed on the screen.

[0637] 3. Sentiment Analysis Engine

[0638] Role: Analyzes the user's facial expressions and voice in real time to obtain emotional data.

[0639] Technologies used: facial expression recognition algorithm, voice analysis technology

[0640] Specific processing: Understand the user's emotional state when reviewing the proposal and send that information to the server.

[0641] Detailed System Operation

[0642] 1. Enter and submit information

[0643] Users enter their personal information (preferences, desired conditions, etc.) using an input form displayed on the screen of their smartphone or smart glasses. The entered information is sent to the server in real time.

[0644] 2. Identifying potential buyers

[0645] The server extracts potential buyers from a database based on the received user information, using machine learning algorithms to achieve highly accurate matching.

[0646] 3. Proposal Generation and Viewing

[0647] The server generates a proposal based on the extracted candidate information and sends it to the user's terminal, where the proposal is displayed on the screen.

[0648] 4. Sentiment Analysis and Feedback

[0649] The emotion analysis engine analyzes the user's facial expressions and voice in real time and sends the emotional data to the server, which then uses this emotional feedback to customize the content of future proposals.

[0650] Specific examples

[0651] System usage examples

[0652] For example, if a customer uses the system in a fashion shop and enters "I want casual fashion, blue, size M," the server will send the following prompt to the generative AI model:

[0653] "I'm looking for casual fashion. The color is blue, and the size is medium. Please recommend some products."

[0654] Based on this information, the system will suggest suitable products and display them on the user's device. At the same time, by analyzing the user's facial expressions and voice, the system can understand the customer's level of satisfaction with the suggestions and use this information as feedback to improve the quality of the suggestions.

[0655] This system will significantly improve the customer experience in physical stores and enable more personalized shopping suggestions.

[0656] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0657] Step 1:

[0658] User enters information on device

[0659] Input: Information such as the style, color, and size desired by the user

[0660] How it works: Users enter their fashion preferences and desired conditions using an input form displayed on the screen of their smartphone or smart glasses. The input information is sent to the server in real time.

[0661] Output: The user's input information is sent to the server.

[0662] Step 2:

[0663] The server extracts potential buyers

[0664] Input: Fashion preferences and desired conditions submitted by the user

[0665] How it works: The server extracts potential buyers from a database based on the received user information. This process uses machine learning algorithms to achieve highly accurate matching.

[0666] Output: Extracted information about potential buyers

[0667] Step 3:

[0668] The server generates the proposal

[0669] Input: Extracted information about potential buyers

[0670] Specific operation: Based on the extracted information of potential buyers, the server uses a generative AI model to create an optimal proposal, which is a list of products and services that meet the user's requirements.

[0671] Output: Generated proposal

[0672] Step 4:

[0673] The server sends the proposal to the device.

[0674] Input: Generated proposal

[0675] Specific operation: The proposal is sent to the user's device and displayed on the user's device's display.

[0676] Output: The proposal is displayed on the user's device.

[0677] Step 5:

[0678] The user reviews the proposal and analyzes the sentiment data.

[0679] Input: Facial expressions and voice of the user reviewing the proposal

[0680] How it works: The emotion analysis engine analyzes the user's facial expressions and voice in real time and sends the results to the server. It uses the camera built into the smart glasses or the front camera of the smartphone for facial recognition, and the microphone for voice analysis.

[0681] Output: Parsed emotion data

[0682] Step 6:

[0683] The server improves the proposal based on the feedback.

[0684] Input: Parsed emotion data

[0685] Specific operation: The server analyzes the user's emotional data and reflects it in the next proposal generation. At this time, feedback information obtained from the emotional data is utilized.

[0686] Output: Data base for improved proposals

[0687] Through the above processing steps, users can receive personalized suggestions in real time, enabling them to find the best products and services.

[0688] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0689] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0690] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0691] [Third embodiment]

[0692] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0693] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0694] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0695] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0696] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0697] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0698] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0699] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0700] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0701] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0702] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0703] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0704] This invention provides an M&A business support system for small and medium-sized enterprises. This system automates a series of processes: inputting information about the seller company, extracting potential buyers from a database based on that information, generating a proposal based on the extracted information about the potential buyers, and displaying the generated proposal on a user interface.

[0705] The server functions as the central component of the system. It receives information about the selling company from the user (M&A specialist) and uses that information to extract suitable potential buyers from a database. The server utilizes a generative artificial intelligence model to extract potential buyers, thereby achieving highly accurate matching. It then generates a proposal based on the extracted information about the potential buyers and sends this proposal to the terminal.

[0706] The terminal serves as an interface for users to interact with the system. The terminal provides a form for users to enter basic information about the seller company and transmits the entered information to the server. The terminal also displays proposals received from the server to the users, allowing them to review the proposals and take necessary actions.

[0707] The user uses a terminal to input information about the seller company and sends the input information to the server. The server generates a proposal and displays it on the terminal, allowing the user to review it and select the most suitable potential buyer.

[0708] Consider the following scenario as a specific example. When AAA Corporation, a small or medium-sized enterprise, uses the system, the user enters AAA Corporation's company information (e.g., company name, "AAA Corporation," business description, "software development") into an input form on a terminal. This information is sent to the server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review it. This process enables AAA Corporation to quickly and efficiently find potential buyers and propose optimal terms to the selling company.

[0709] By implementing this invention, the M&A process for small and medium-sized enterprises will be significantly more efficient, making it easier for sellers to find buyers on the terms they desire. This system will resolve business succession issues for small and medium-sized enterprises and promote sustainable economic growth.

[0710] The processing flow will be explained below.

[0711] Step 1:

[0712] The terminal displays a form on the user interface for the seller company to enter basic information about the company (company name, business details, etc.).

[0713] Step 2:

[0714] The user enters the seller's company information into the input form on the terminal and clicks the "Submit" button on the form.

[0715] Step 3:

[0716] The terminal acquires the seller company information entered by the user, creates a request to send the information to the server, and sends it.

[0717] Step 4:

[0718] The server processes the seller company information received from the terminal and accesses a database to execute queries to extract suitable potential buyers.

[0719] Step 5:

[0720] The server uses machine learning algorithms to extract suitable potential buyers from the database, thereby identifying buyers that match the characteristics of the seller.

[0721] Step 6:

[0722] The server executes a program for generating a proposal based on the extracted information of potential buyers, and creates the proposal by embedding the information in a template.

[0723] Step 7:

[0724] The server transmits the generated proposal to the terminal.

[0725] Step 8:

[0726] The terminal displays the proposal received from the server on a user interface, allowing the user to check the proposal.

[0727] Step 9:

[0728] The user can review the proposals displayed through the terminal interface, provide feedback if necessary, and select the most suitable potential buyer.

[0729] Through this series of processing steps, the system of the present invention enables a seller to quickly and efficiently find potential buyers and proceed with the M&A process under optimal conditions.

[0730] Example 1

[0731] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0732] There is a lack of appropriate support systems for small and medium-sized enterprises to carry out M&A work quickly and efficiently. Furthermore, there is a need for high accuracy in matching sellers with potential buyers and in automatically generating proposals. This is expected to streamline the entire M&A process and improve the success rate.

[0733] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0734] In this invention, the server includes means for transmitting input information, means for searching a database based on the received information to extract candidates, means for generating proposals based on the information using a generative artificial intelligence model, and means for displaying the generated proposals on a user interface, thereby enabling highly accurate matching between seller companies and potential buyer companies and realizing the automatic generation and display of proposals quickly and efficiently.

[0735] The "means for transmitting input information" is a means by which a user inputs information about a seller company into a terminal and transmits it to a server.

[0736] "Means for searching a database based on received information and extracting candidates" refers to means for the server to search data in a database based on the information of the seller company received from the user and extract appropriate buyer candidates.

[0737] "Means for generating a proposal based on information using a generative artificial intelligence model" refers to means for automatically generating a proposal using a generative artificial intelligence model based on information about potential buyers extracted by the server.

[0738] The "means for displaying the generated proposal on a user interface" refers to a means for the server to transmit the generated proposal to the terminal, and for the terminal to display this proposal on a user interface.

[0739] The "generative artificial intelligence model that automatically matches seller information with buyer information and quickly creates proposals" is an artificial intelligence model that automatically matches information on seller companies and potential buyer companies and quickly generates proposals with high accuracy.

[0740] "Extraction of candidates from the database is performed using a machine learning algorithm" refers to the process in which the server searches the data in the database and extracts suitable potential buyers using a machine learning algorithm.

[0741] The present invention provides an M&A business support system for small and medium-sized enterprises, which automates a series of processes: inputting information about the selling company, extracting potential buyers from a database based on that information, generating a proposal based on the information about the extracted potential buyers, and displaying the generated proposal on a user interface.

[0742] Hardware and software used

[0743] server

[0744] The server is the central component of the system and uses cloud servers such as AWS (Amazon Web Services) and Google Cloud Platform. The database uses a relational database management system (RDBMS) such as MySQL or PostgreSQL. Machine learning frameworks such as TensorFlow and PyTorch are used as generative artificial intelligence models.

[0745] Terminal

[0746] The terminals are PCs, tablets, and smartphones that serve as interfaces for users to interact with the system. The user interface is built using front-end frameworks such as React, Vue.js, and Angular.

[0747] Program processing

[0748] The server performs a database search based on the seller company information received from the terminal and extracts suitable potential buyers. This process uses a generative artificial intelligence model to achieve highly accurate matching. A proposal is automatically generated based on the extracted information on the potential buyers and sent to the terminal.

[0749] The terminal provides a form for the user to input information about the seller company, transmits the input information to the server, and displays the proposal received from the server on a user interface, allowing the user to review the proposal and take necessary actions.

[0750] The user inputs the seller's information and sends it to the server. The server generates a proposal and displays it on the terminal, allowing the user to review it and select the most suitable potential buyer.

[0751] Specific examples

[0752] A specific example of how a small and medium-sized enterprise, AAA Co., Ltd., uses the system is given below.

[0753] The user enters the following information into the terminal's input form:

[0754] Company name: "AAA Co., Ltd."

[0755] Business: Software development

[0756] This information is sent to a server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review it. This process enables AAA Corporation to quickly and efficiently find potential buyers and propose optimal terms to the seller.

[0757] The above is an embodiment of the present invention.

[0758] Example of a prompt statement without JSON

[0759] The user enters the following information into the terminal's input form:

[0760] Company name: "AAA Co., Ltd."

[0761] Business: Software development

[0762] The server receives this information, performs a database search, and extracts suitable potential buyers using a generative AI model (e.g., using TensorFlow).The server then generates a proposal based on the extracted information about the potential buyers and sends the generated proposal to the terminal.The terminal displays the proposal on a user interface, and the user can confirm the proposal.

[0763] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0764] Step 1:

[0765] The user enters information about the seller company into an input form on the device, including specific information such as the company name and business details. The entered information is temporarily stored in the device's internal memory.

[0766] input:

[0767] Company name: "AAA Co., Ltd."

[0768] Business: Software development

[0769] output:

[0770] Company information entered into the terminal

[0771] Step 2:

[0772] The terminal sends the entered seller information to the server using the HTTPS protocol, and the data is encoded in JSON format, so the entered information is passed to the server securely.

[0773] input:

[0774] Company information entered into the terminal

[0775] output:

[0776] Company information in JSON format sent to the server

[0777] Step 3:

[0778] The server parses the received JSON data and extracts information about the seller. Based on this information, it performs a database search to extract potential buyers. This process uses a generative AI model to achieve highly accurate matching.

[0779] input:

[0780] Company information in JSON format sent to the server

[0781] output:

[0782] Extracted information on potential buyers

[0783] Step 4:

[0784] The server automatically generates a proposal based on the extracted information of potential buyers. This proposal includes details of the potential buyers and their proposals. The generative AI model is used to generate the optimal proposal.

[0785] input:

[0786] Extracted information on potential buyers

[0787] output:

[0788] Auto-generated proposal

[0789] Step 5:

[0790] The server sends the generated proposal in JSON format to the terminal. Because the proposal is sent as an HTTP response, there is little latency (delay) when the terminal receives it.

[0791] input:

[0792] Auto-generated proposal

[0793] output:

[0794] Proposal in JSON format sent to the device

[0795] Step 6:

[0796] The terminal parses the received proposal data and displays it in a user interface, using front-end frameworks such as React and Vue.js to display the proposal in a visually easy-to-understand format.

[0797] input:

[0798] Proposal in JSON format sent to the device

[0799] output:

[0800] Proposal displayed in the user interface

[0801] Step 7:

[0802] The user checks the proposal on the device screen, selects the most suitable buyer based on the information on potential buyers listed in the proposal, and decides on the next action (contact or adjustment of terms).

[0803] input:

[0804] Proposal displayed in the user interface

[0805] output:

[0806] Review results and next actions

[0807] (Application example 1)

[0808] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0809] Currently, there are systems that effectively support M&A activities for SMEs, but the M&A process for certain industrial sectors, particularly factory equipment, is not fully covered. This makes it difficult to quickly match M&A deals involving factory equipment and generate proposals, which in turn hinders efficient business succession and capital restructuring for SMEs.

[0810] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0811] In this invention, the server includes means for inputting information about the seller company, means for extracting potential buyers from a database, means for generating a proposal based on the extracted information about the potential buyers, means for displaying the generated proposal on a user interface, and means for inputting and matching information about factory equipment. This enables highly accurate matching in the M&A process for small and medium-sized enterprises that include factory equipment, making it possible to quickly and efficiently find suitable potential buyers and generate and provide proposals.

[0812] "Information about the seller's company" refers to basic information necessary to sell a company, such as the company's name, business operations, and financial status.

[0813] A "database" is an organized collection of data for collecting, storing, and retrieving information based on specified criteria.

[0814] A "potential buyer" is a company or individual that has the potential to acquire the seller company.

[0815] A "proposal" is a document that contains the information necessary to proceed with a contract between a selling company and a potential buyer.

[0816] A "user interface" refers to the input and display screens that allow a user to interact with a system.

[0817] "Factory equipment" is a general term for various devices, machines, robots, etc. used in factory production processes.

[0818] "Matching" involves comparing the seller's information with the conditions of potential buyers and finding the optimal combination based on matching elements.

[0819] A "generative artificial intelligence model" is an AI (artificial intelligence) algorithm that is trained to analyze patterns in data and make decisions or predictions.

[0820] A "machine learning algorithm" is a mathematical model that learns from data and makes predictions or classifications to perform a specific task.

[0821] "Extraction" means selecting information from a database or other source that meets specific criteria.

[0822] A "form" is an interface that allows a user to enter information, typically containing text boxes, drop-down menus, radio buttons, etc.

[0823] "Processing" refers to a series of steps or operations that input, transform, analyze, and output data.

[0824] This invention is a system for supporting the M&A process of small and medium-sized enterprises that purchase factory equipment. The system has various functions for inputting and matching information on seller companies, factory equipment, and potential buyers, and generating and displaying proposals.

[0825] The server functions as the central component of the entire system. It receives information about the seller company and factory equipment from the user, and extracts suitable potential buyers from the database based on that information. High-precision matching can be achieved using a generative artificial intelligence model. The server also generates proposals based on the extracted information about potential buyers and sends these proposals to the terminal.

[0826] The terminal functions as an interface for users to interact with the system. The terminal provides a form for users to enter basic information about the seller company and factory equipment, and transmits the entered information to the server. The terminal also displays proposals received from the server to users, allowing them to review the proposals and take necessary actions.

[0827] The user uses a terminal to enter information about the seller company and the factory equipment, and then sends the entered information to the server. The server receives the information, extracts suitable potential buyers from a database, generates a proposal, and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review the proposal. This process allows the user to quickly and efficiently find potential buyers and make the best proposal for the seller company and the factory equipment.

[0828] As a concrete example, when a user of a small or medium-sized enterprise uses the system, he or she enters company information and information about factory equipment into an input form on a terminal. For example, the user enters the company name "XYZ Corporation," the business description "software development," and the information about the "industrial robots" they use. This information is sent to the server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review the proposal, allowing the M&A process to proceed quickly and effectively.

[0829] Prompt Sentence Examples

[0830] Company name: XYZ Corporation, Business description: Software development, Factory equipment: Industrial robots

[0831] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0832] Step 1: The user enters information about the seller company and factory equipment through the terminal.

[0833] The user enters information about the company name, business activities, and factory equipment into a form on the terminal. The input for this step is the data entered by the user, which is then retrieved by the terminal. The output is a dataset containing all the information entered.

[0834] Step 2: The device sends the input information to the server

[0835] The terminal sends the data entered by the user to the server. The input of this step is the dataset acquired in step 1, and it sends it to the server. The output is the data sent to the server.

[0836] Step 3: The server receives the data

[0837] The server receives the seller company and factory equipment information sent from the terminal. The input to this step is the data sent in step 2. The server receives this data and prepares it for processing. The output is the correctly received data.

[0838] Step 4: The server extracts suitable potential buyers from the database

[0839] The server uses the received data to process it to extract suitable potential buyers from the database, using machine learning algorithms and generative AI models. The input is the data received by the server and the contents of the database, and the output is a list of potential buyers.

[0840] Step 5: The server generates a proposal based on the extracted information about the potential buyer.

[0841] The server generates a proposal based on the extracted information of potential buyers. This process utilizes natural language generation technology. The input is a list of potential buyers, and the output is the generated proposal.

[0842] Step 6: The server sends the generated proposal to the device

[0843] The server sends the generated proposal to the terminal. The input is the generated proposal and performs a sending operation. The output is the proposal sent to the terminal.

[0844] Step 7: The device displays the proposal in its user interface.

[0845] The terminal displays the proposal received from the server on a user interface. The input is the received proposal and the output is the proposal displayed on the user interface, allowing the user to review the proposal and take action if necessary.

[0846] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0847] This invention provides an M&A business support system for small and medium-sized enterprises. This system automates a series of processes: inputting information about the selling company, extracting potential buyers from a database based on that information, generating a proposal based on the extracted information about the potential buyers, and displaying the generated proposal on a user interface. Furthermore, by incorporating an emotion engine that recognizes the user's emotions and customizes the content of the proposal based on that information, the system can provide more personalized proposals.

[0848] The server functions as the central component of the system. First, the server receives information about the seller company from the user and then uses that information to extract suitable potential buyers from a database. The server utilizes a generative artificial intelligence model to extract potential buyers, thereby achieving highly accurate matching. The server then generates a proposal based on the extracted information about the potential buyers and sends this proposal to the terminal.

[0849] The terminal functions as an interface for users to interact with the system. It provides a form for users to enter basic information about the seller company and sends the entered information to the server. The terminal also displays the proposal received from the server to the user, allowing the user to review the proposal and take any necessary actions. Furthermore, the terminal is equipped with an emotion engine that analyzes user emotions in real time and sends that information to the server to optimize the content of the proposal.

[0850] The user uses a terminal to enter information about the seller company and sends the entered information to the server. A proposal is generated from the server and displayed on the terminal, where the user can review it and select the most suitable potential buyer. The emotion engine analyzes the user's facial expressions and voice as they review the proposal to understand their emotional state. For example, if the user appears satisfied after viewing the proposal, the engine collects feedback and analyzes what aspects of the proposal the user finds appealing. This feedback information is used when generating the next proposal, improving the system to make more appropriate proposals.

[0851] Consider the following scenario as a specific example. When a small- to medium-sized enterprise (SME) called "BBB Co., Ltd." uses the system, the user enters basic information about "BBB Co., Ltd." (e.g., company name "BBB Co., Ltd.", business description "manufacturing") into an input form on a terminal. This information is sent to the server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on its user interface, while an emotion engine analyzes the user's facial expressions and voice to understand their emotional state. For example, if the user shows positive emotions, such as smiling, when reviewing the proposal, this emotion data is sent to the server and used as feedback to improve the quality of future proposals.

[0852] By implementing this invention, the M&A process for small and medium-sized enterprises will be significantly more efficient, making it easier for sellers to find buyers on their desired terms. Furthermore, by incorporating an emotion engine, more appropriate and personalized proposals based on the user's emotions will be provided. This system will solve business succession issues for small and medium-sized enterprises and promote sustainable economic growth.

[0853] The processing flow will be explained below.

[0854] Step 1:

[0855] The terminal displays a form on the user interface for entering basic information about the seller company, including fields for the company name, business details, contact information, etc.

[0856] Step 2:

[0857] The user enters the necessary information into the input form on the terminal and clicks the "Submit" button, which causes the data entered into the form to be acquired by the terminal.

[0858] Step 3:

[0859] The terminal packages the acquired seller information and creates a request to send to the server, using JSON format or similar.

[0860] Step 4:

[0861] The server receives the seller company information sent from the terminal and prepares for database access.

[0862] Step 5:

[0863] The server runs machine learning algorithms to extract the best-matched potential buyers from the database based on the seller's information, using predictive models and clustering algorithms.

[0864] Step 6:

[0865] The server analyzes the extracted information about the potential buyer and begins the process of embedding that information into a proposal template for the seller company.

[0866] Step 7:

[0867] The server then sends the generated proposal to the terminal, which includes details such as the buyer's name, business activities, and offer details.

[0868] Step 8:

[0869] The terminal displays the proposal received from the server on the user interface in an easy-to-read format so that the user can check the proposal.

[0870] Step 9:

[0871] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice, and based on the results of this analysis, determines the user's emotional state in real time.

[0872] Step 10:

[0873] The emotion engine sends the user's emotion data to the server. For example, if the user looks satisfied while looking at the proposal, the engine sends data containing that information.

[0874] Step 11:

[0875] The server analyzes the feedback on the proposal based on the received emotional data and uses it in the next proposal generation process, thereby optimizing the proposal content.

[0876] Step 12:

[0877] The user can review the proposals displayed through the terminal interface, provide feedback if necessary, and select the most suitable potential buyer.

[0878] Through this series of processing steps, the system of the present invention enables sellers to quickly and efficiently find potential buyers and advance the M&A process with personalized proposals based on emotional data.

[0879] Example 2

[0880] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0881] Conventional M&A support systems for small and medium-sized enterprises have problems such as low accuracy in effectively matching information on sellers and potential buyers, and a lack of personalization in the generation of proposals, resulting in low user satisfaction.Furthermore, feedback reflecting user sentiment is not incorporated into proposals, making it difficult to continuously improve the quality of proposals.

[0882] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0883] In this invention, the server includes means for inputting information about the seller company, means for extracting potential buyers from a database, means for generating a proposal based on the extracted information about the potential buyers, means for displaying the generated proposal on a user interface, and means for recognizing a user's emotions and customizing the contents of the proposal based on that information. This makes it possible to optimize the proposal contents based on the individual emotional state of the user and provide highly accurate matching and personalized proposals.

[0884] A "seller" is a company or organization seeking to sell a company or business.

[0885] A "potential buyer" is a company or organization that may purchase the company or business being sold.

[0886] A "database" is a collection of data organized to efficiently store, retrieve, edit, and delete information.

[0887] A "proposal" is a document prepared to facilitate a transaction between a selling company and a potential buyer, and primarily contains transaction terms and background information.

[0888] "User interface" refers to the screens and operating means through which the system and the user interact with each other.

[0889] "Means for recognizing emotions" refers to technology or devices that analyze a user's facial expressions and voice and identify their emotional state.

[0890] A "generative artificial intelligence model" is a program that uses machine learning algorithms to learn patterns from data and make decisions and predictions.

[0891] A "machine learning model" is a technology that learns rules and patterns from data and makes predictions and classifications for new data.

[0892] This invention provides a system for supporting M&A transactions for small and medium-sized enterprises. This system inputs information about the seller company, extracts potential buyers from a database based on that information, then generates a proposal based on the information about the potential buyers, and finally displays the generated proposal on a user interface. It can also recognize the user's emotions and customize the content of the proposal based on that information.

[0893] The server acts as the central component of this system. It receives information about sellers from users and processes it to extract suitable potential buyers from a database based on that information. To improve the accuracy of this matching, a generative artificial intelligence model is used. For example, machine learning libraries such as TensorFlow and PyTorch can be used.

[0894] The server then uses a template engine to generate a proposal based on the extracted information about the potential buyer. The generated proposal is output in PDF or HTML format and sent from the server to the device, typically using an HTTP response.

[0895] The terminal functions as an interface for users to interact with the system. The terminal prompts users to enter basic information about the seller company through an input form built with HTML / CSS, and then sends that information to the server. The terminal also displays the proposal received from the server to the user. The user can review the proposal and take any necessary actions.

[0896] The device is also equipped with an emotion engine that analyzes the user's facial expressions and voice to understand their emotional state. Using technologies such as OpenCV and NVIDIA DeepStream, the device can analyze the user's emotions in real time. This emotion data is sent from the device to a server, which then uses it to optimize the content of the next proposal.

[0897] Consider the following scenario as a concrete example. When a seller company, "Company A," uses the system, the user enters basic information about "Company A" (company name, business activities, location, and desired buyer conditions) into an input form on their terminal. This information is sent to the server, which then uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the potential buyers and sends it to the terminal. The terminal displays the proposal on a user interface, and the user confirms it. At the same time, an emotion engine analyzes the user's facial expressions and voice, and the emotional data is sent to the server. For example, if the user confirms the proposal and smiles with satisfaction, this positive emotional data is used as feedback the next time a proposal is generated.

[0898] An example prompt is:

[0899] Basic information of seller company "Company A":

[0900] Company name: Company A

[0901] Business content: Manufacturing industry

[0902] Location: Tokyo

[0903] Desired buyer conditions: Domestic companies considering business expansion

[0904] By inputting this prompt into the generative AI model, highly accurate matching and proposal generation become possible. In addition, the feedback function of the emotion engine allows for continuous improvement of the quality of the proposal content.

[0905] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0906] Step 1:

[0907] Input: The user enters basic information about the seller company (company name, business activities, location, desired buyer conditions, etc.) into the input form on the terminal.

[0908] Processing: The terminal displays an input form built with HTML / CSS and allows the user to enter the required information.

[0909] Output: The information entered by the user is sent by the terminal to the server.

[0910] Specific operation: The user enters the required information into the form and clicks the submit button. The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[0911] Step 2:

[0912] Input: The server receives the basic information of the seller company sent from the terminal.

[0913] Processing: The server parses the HTTP request and converts the received data into a format that can be processed.

[0914] Output: The parsed data is stored as a data object available in the server.

[0915] What happens: The server receives the HTTP request, parses the data using a JSON parser, and converts it into the appropriate database entry.

[0916] Step 3:

[0917] Input: Basic information about the seller company.

[0918] Processing: The server uses a generative artificial intelligence model to extract potential buyers from the database.

[0919] Output: Extracted potential buyer information.

[0920] How it works: The server uses machine learning libraries such as TensorFlow and PyTorch to run algorithms to identify the most suitable potential buyers for the selling company from the database.

[0921] Step 4:

[0922] Input: Extracted prospective buyer information.

[0923] Processing: The server uses a template engine to generate the proposal.

[0924] Output: The generated proposal (PDF or HTML format).

[0925] Specific operation: The server uses a template engine (e.g., Jinja2) to generate a proposal by inserting the extracted information of the potential buyer. The generated proposal is saved as a file.

[0926] Step 5:

[0927] Input: The generated proposal.

[0928] Processing: The server sends the generated proposal to the terminal.

[0929] Output: Proposal link or file viewable on your device.

[0930] Specific operation: The server sends the proposal file as an HTTP response and provides the device with a download link and a viewing page.

[0931] Step 6:

[0932] Input: Proposal link or file sent from the server.

[0933] Processing: The terminal displays the proposal on the user interface.

[0934] Output: The proposal that is displayed to the user.

[0935] Specific operation: The device analyzes the HTTP response and displays the received proposal link and file in the user interface. The user interacts with the response to confirm it.

[0936] Step 7:

[0937] Input: User's facial expressions and voice.

[0938] Processing: The terminal uses the emotion engine to analyze the user's emotions.

[0939] Output: Parsed emotion data.

[0940] Specific operation: Using the device's built-in camera and microphone, the system captures the user's facial expressions and voice in real time, and performs emotion analysis using technologies such as OpenCV and NVIDIA DeepStream.

[0941] Step 8:

[0942] Input: Parsed emotion data.

[0943] Processing: The device sends the emotion data to the server.

[0944] Output: Emotion data object available on the server side.

[0945] Specific operation: The device converts the analyzed emotion data into JSON format and sends it to the server as an HTTP request.

[0946] Step 9:

[0947] Input: Emotion data.

[0948] Processing: The server analyzes the received emotion data and stores it in a database to optimize the content of the next proposal.

[0949] Output: Feedback for optimized proposal generation.

[0950] Specific operation: The server receives the emotion data, analyzes it, stores it in a database, and reflects this feedback when generating the next proposal.

[0951] (Application example 2)

[0952] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0953] In conventional systems for matching sellers and buyers, the process from inputting seller information to identifying potential buyers and generating proposals takes a lot of time and effort. Furthermore, the proposals are uniform, resulting in low user satisfaction and making it difficult to conclude efficient sales contracts. While there is a particular demand for personalized proposals that take user sentiment into account, there is a lack of mechanisms to achieve this. This prevents sellers, such as small and medium-sized enterprises, from conducting quick and effective sales activities, often resulting in missed market opportunities.

[0954] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0955] In this invention, the server includes means for inputting information about the seller company, means for extracting potential buyers from a database, means for generating a proposal based on the information about the extracted potential buyers, means for transmitting the proposal to a user terminal and displaying it on the display of the user terminal, means for analyzing the user's emotions in real time and customizing the contents of the proposal based on that information, and means for the emotion analysis means to analyze the user's facial expressions and voice and transmit emotional data to the server. This enables quick and effective matching between seller companies and buyer companies, and also makes it possible to provide personalized proposals based on the user's emotions.

[0956] "Means for inputting seller company information" refers to an interface or device that allows a seller company to input its own company information into the system.

[0957] "Means for extracting potential buyers from a database" refers to technology for selecting and extracting appropriate potential buyers from a database based on the input information of the seller company.

[0958] The "means for generating a proposal" is a system or algorithm for creating a proposal that is beneficial to both the seller company and the potential buyer based on the extracted information about the potential buyer.

[0959] The "means for displaying the proposal on the display of the user terminal" is a system for transmitting the generated proposal to the user terminal and displaying it on the display.

[0960] "Emotion analysis means" is a technology for analyzing a user's facial expressions and voice in real time to understand the user's emotional state.

[0961] "Means for the emotion analysis means to analyze the user's facial expressions and voice and send the emotion data to the server" is a technology for sending the data acquired by the emotion analysis means to the server and customizing the contents of the proposal.

[0962] The present invention relates to an emotion-aware store support system for improving the shopping experience in physical stores. This system integrates multiple hardware and software components to provide personalized suggestions based on customer emotions in real time. This specification describes the specific configuration and operation of the system.

[0963] System configuration

[0964] 1. Server

[0965] Role: Serves as the central component of the system, receiving, processing and storing data.

[0966] Technologies used: Machine learning algorithms, generative AI models

[0967] Specific process: Based on the seller's information, appropriate potential buyers are extracted from the database and a proposal is generated.

[0968] 2. User Device

[0969] Role: Receives input from the user and communicates with the server.

[0970] Hardware examples: smartphones, smart glasses

[0971] Specific process: The user inputs seller or product information through the terminal interface and sends this information to the server, and the proposal received from the server is displayed on the screen.

[0972] 3. Sentiment Analysis Engine

[0973] Role: Analyzes the user's facial expressions and voice in real time to obtain emotional data.

[0974] Technologies used: facial expression recognition algorithm, voice analysis technology

[0975] Specific processing: Understand the user's emotional state when reviewing the proposal and send that information to the server.

[0976] Detailed System Operation

[0977] 1. Enter and submit information

[0978] Users enter their personal information (preferences, desired conditions, etc.) using an input form displayed on the screen of their smartphone or smart glasses. The entered information is sent to the server in real time.

[0979] 2. Identifying potential buyers

[0980] The server extracts potential buyers from a database based on the received user information, using machine learning algorithms to achieve highly accurate matching.

[0981] 3. Proposal Generation and Viewing

[0982] The server generates a proposal based on the extracted candidate information and sends it to the user's terminal, where the proposal is displayed on the screen.

[0983] 4. Sentiment Analysis and Feedback

[0984] The emotion analysis engine analyzes the user's facial expressions and voice in real time and sends the emotional data to the server, which then uses this emotional feedback to customize the content of future proposals.

[0985] Specific examples

[0986] System usage examples

[0987] For example, if a customer uses the system in a fashion shop and enters "I want casual fashion, blue, size M," the server will send the following prompt to the generative AI model:

[0988] "I'm looking for casual fashion. The color is blue, and the size is medium. Please recommend some products."

[0989] Based on this information, the system will suggest suitable products and display them on the user's device. At the same time, by analyzing the user's facial expressions and voice, the system can understand the customer's level of satisfaction with the suggestions and use this information as feedback to improve the quality of the suggestions.

[0990] This system will significantly improve the customer experience in physical stores and enable more personalized shopping suggestions.

[0991] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0992] Step 1:

[0993] User enters information on device

[0994] Input: Information such as the style, color, and size desired by the user

[0995] How it works: Users enter their fashion preferences and desired conditions using an input form displayed on the screen of their smartphone or smart glasses. The input information is sent to the server in real time.

[0996] Output: The user's input information is sent to the server.

[0997] Step 2:

[0998] The server extracts potential buyers

[0999] Input: Fashion preferences and desired conditions submitted by the user

[1000] How it works: The server extracts potential buyers from a database based on the received user information. This process uses machine learning algorithms to achieve highly accurate matching.

[1001] Output: Extracted information about potential buyers

[1002] Step 3:

[1003] The server generates the proposal

[1004] Input: Extracted information about potential buyers

[1005] Specific operation: Based on the extracted information of potential buyers, the server uses a generative AI model to create an optimal proposal, which is a list of products and services that meet the user's requirements.

[1006] Output: Generated proposal

[1007] Step 4:

[1008] The server sends the proposal to the device.

[1009] Input: Generated proposal

[1010] Specific operation: The proposal is sent to the user's device and displayed on the user's device's display.

[1011] Output: The proposal is displayed on the user's device.

[1012] Step 5:

[1013] The user reviews the proposal and analyzes the sentiment data.

[1014] Input: Facial expressions and voice of the user reviewing the proposal

[1015] How it works: The emotion analysis engine analyzes the user's facial expressions and voice in real time and sends the results to the server. It uses the camera built into the smart glasses or the front camera of the smartphone for facial recognition, and the microphone for voice analysis.

[1016] Output: Parsed emotion data

[1017] Step 6:

[1018] The server improves the proposal based on the feedback.

[1019] Input: Parsed emotion data

[1020] Specific operation: The server analyzes the user's emotional data and reflects it in the next proposal generation. At this time, feedback information obtained from the emotional data is utilized.

[1021] Output: Data base for improved proposals

[1022] Through the above processing steps, users can receive personalized suggestions in real time, enabling them to find the best products and services.

[1023] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1024] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1025] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1026] [Fourth embodiment]

[1027] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1028] 7, a 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.

[1029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1030] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1031] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1032] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1034] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1035] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1036] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1038] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1040] This invention provides an M&A business support system for small and medium-sized enterprises. This system automates a series of processes: inputting information about the seller company, extracting potential buyers from a database based on that information, generating a proposal based on the extracted information about the potential buyers, and displaying the generated proposal on a user interface.

[1041] The server functions as the central component of the system. It receives information about the selling company from the user (M&A specialist) and uses that information to extract suitable potential buyers from a database. The server utilizes a generative artificial intelligence model to extract potential buyers, thereby achieving highly accurate matching. It then generates a proposal based on the extracted information about the potential buyers and sends this proposal to the terminal.

[1042] The terminal serves as an interface for users to interact with the system. The terminal provides a form for users to enter basic information about the seller company and transmits the entered information to the server. The terminal also displays proposals received from the server to the users, allowing them to review the proposals and take necessary actions.

[1043] The user uses a terminal to input information about the seller company and sends the input information to the server. The server generates a proposal and displays it on the terminal, allowing the user to review it and select the most suitable potential buyer.

[1044] Consider the following scenario as a specific example. When AAA Corporation, a small or medium-sized enterprise, uses the system, the user enters AAA Corporation's company information (e.g., company name, "AAA Corporation," business description, "software development") into an input form on a terminal. This information is sent to the server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review it. This process enables AAA Corporation to quickly and efficiently find potential buyers and propose optimal terms to the selling company.

[1045] By implementing this invention, the M&A process for small and medium-sized enterprises will be significantly more efficient, making it easier for sellers to find buyers on the terms they desire. This system will resolve business succession issues for small and medium-sized enterprises and promote sustainable economic growth.

[1046] The processing flow will be explained below.

[1047] Step 1:

[1048] The terminal displays a form on the user interface for the seller company to enter basic information about the company (company name, business details, etc.).

[1049] Step 2:

[1050] The user enters the seller's company information into the input form on the terminal and clicks the "Submit" button on the form.

[1051] Step 3:

[1052] The terminal acquires the seller company information entered by the user, creates a request to send the information to the server, and sends it.

[1053] Step 4:

[1054] The server processes the seller company information received from the terminal and accesses a database to execute queries to extract suitable potential buyers.

[1055] Step 5:

[1056] The server uses machine learning algorithms to extract suitable potential buyers from the database, thereby identifying buyers that match the characteristics of the seller.

[1057] Step 6:

[1058] The server executes a program for generating a proposal based on the extracted information of potential buyers, and creates the proposal by embedding the information in a template.

[1059] Step 7:

[1060] The server transmits the generated proposal to the terminal.

[1061] Step 8:

[1062] The terminal displays the proposal received from the server on a user interface, allowing the user to check the proposal.

[1063] Step 9:

[1064] The user can review the proposals displayed through the terminal interface, provide feedback if necessary, and select the most suitable potential buyer.

[1065] Through this series of processing steps, the system of the present invention enables a seller to quickly and efficiently find potential buyers and proceed with the M&A process under optimal conditions.

[1066] Example 1

[1067] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1068] There is a lack of appropriate support systems for small and medium-sized enterprises to carry out M&A work quickly and efficiently. Furthermore, there is a need for high accuracy in matching sellers with potential buyers and in automatically generating proposals. This is expected to streamline the entire M&A process and improve the success rate.

[1069] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1070] In this invention, the server includes means for transmitting input information, means for searching a database based on the received information to extract candidates, means for generating proposals based on the information using a generative artificial intelligence model, and means for displaying the generated proposals on a user interface, thereby enabling highly accurate matching between seller companies and potential buyer companies and realizing the automatic generation and display of proposals quickly and efficiently.

[1071] The "means for transmitting input information" is a means by which a user inputs information about a seller company into a terminal and transmits it to a server.

[1072] "Means for searching a database based on received information and extracting candidates" refers to means for the server to search data in a database based on the information of the seller company received from the user and extract appropriate buyer candidates.

[1073] "Means for generating a proposal based on information using a generative artificial intelligence model" refers to means for automatically generating a proposal using a generative artificial intelligence model based on information about potential buyers extracted by the server.

[1074] The "means for displaying the generated proposal on a user interface" refers to a means for the server to transmit the generated proposal to the terminal, and for the terminal to display this proposal on a user interface.

[1075] The "generative artificial intelligence model that automatically matches seller information with buyer information and quickly creates proposals" is an artificial intelligence model that automatically matches information on seller companies and potential buyer companies and quickly generates proposals with high accuracy.

[1076] "Extraction of candidates from the database is performed using a machine learning algorithm" refers to the process in which the server searches the data in the database and extracts suitable potential buyers using a machine learning algorithm.

[1077] The present invention provides an M&A business support system for small and medium-sized enterprises, which automates a series of processes: inputting information about the selling company, extracting potential buyers from a database based on that information, generating a proposal based on the information about the extracted potential buyers, and displaying the generated proposal on a user interface.

[1078] Hardware and software used

[1079] server

[1080] The server is the central component of the system and uses cloud servers such as AWS (Amazon Web Services) and Google Cloud Platform. The database uses a relational database management system (RDBMS) such as MySQL or PostgreSQL. Machine learning frameworks such as TensorFlow and PyTorch are used as generative artificial intelligence models.

[1081] Terminal

[1082] The terminals are PCs, tablets, and smartphones that serve as interfaces for users to interact with the system. The user interface is built using front-end frameworks such as React, Vue.js, and Angular.

[1083] Program processing

[1084] The server performs a database search based on the seller company information received from the terminal and extracts suitable potential buyers. This process uses a generative artificial intelligence model to achieve highly accurate matching. A proposal is automatically generated based on the extracted information on the potential buyers and sent to the terminal.

[1085] The terminal provides a form for the user to input information about the seller company, transmits the input information to the server, and displays the proposal received from the server on a user interface, allowing the user to review the proposal and take necessary actions.

[1086] The user inputs the seller's information and sends it to the server. The server generates a proposal and displays it on the terminal, allowing the user to review it and select the most suitable potential buyer.

[1087] Specific examples

[1088] A specific example of how a small and medium-sized enterprise, AAA Co., Ltd., uses the system is given below.

[1089] The user enters the following information into the terminal's input form:

[1090] Company name: "AAA Co., Ltd."

[1091] Business: Software development

[1092] This information is sent to a server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review it. This process enables AAA Corporation to quickly and efficiently find potential buyers and propose optimal terms to the seller.

[1093] The above is an embodiment of the present invention.

[1094] Example of a prompt statement without JSON

[1095] The user enters the following information into the terminal's input form:

[1096] Company name: "AAA Co., Ltd."

[1097] Business: Software development

[1098] The server receives this information, performs a database search, and extracts suitable potential buyers using a generative AI model (e.g., using TensorFlow).The server then generates a proposal based on the extracted information about the potential buyers and sends the generated proposal to the terminal.The terminal displays the proposal on a user interface, and the user can confirm the proposal.

[1099] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1100] Step 1:

[1101] The user enters information about the seller company into an input form on the device, including specific information such as the company name and business details. The entered information is temporarily stored in the device's internal memory.

[1102] input:

[1103] Company name: "AAA Co., Ltd."

[1104] Business: Software development

[1105] output:

[1106] Company information entered into the terminal

[1107] Step 2:

[1108] The terminal sends the entered seller information to the server using the HTTPS protocol, and the data is encoded in JSON format, so the entered information is passed to the server securely.

[1109] input:

[1110] Company information entered into the terminal

[1111] output:

[1112] Company information in JSON format sent to the server

[1113] Step 3:

[1114] The server parses the received JSON data and extracts information about the seller. Based on this information, it performs a database search to extract potential buyers. This process uses a generative AI model to achieve highly accurate matching.

[1115] input:

[1116] Company information in JSON format sent to the server

[1117] output:

[1118] Extracted information on potential buyers

[1119] Step 4:

[1120] The server automatically generates a proposal based on the extracted information of potential buyers. This proposal includes details of the potential buyers and their proposals. The generative AI model is used to generate the optimal proposal.

[1121] input:

[1122] Extracted information on potential buyers

[1123] output:

[1124] Auto-generated proposal

[1125] Step 5:

[1126] The server sends the generated proposal in JSON format to the terminal. Because the proposal is sent as an HTTP response, there is little latency (delay) when the terminal receives it.

[1127] input:

[1128] Auto-generated proposal

[1129] output:

[1130] Proposal in JSON format sent to the device

[1131] Step 6:

[1132] The terminal parses the received proposal data and displays it in a user interface, using front-end frameworks such as React and Vue.js to display the proposal in a visually easy-to-understand format.

[1133] input:

[1134] Proposal in JSON format sent to the device

[1135] output:

[1136] Proposal displayed in the user interface

[1137] Step 7:

[1138] The user checks the proposal on the device screen, selects the most suitable buyer based on the information on potential buyers listed in the proposal, and decides on the next action (contact or adjustment of terms).

[1139] input:

[1140] Proposal displayed in the user interface

[1141] output:

[1142] Review results and next actions

[1143] (Application example 1)

[1144] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1145] Currently, there are systems that effectively support M&A activities for SMEs, but the M&A process for certain industrial sectors, particularly factory equipment, is not fully covered. This makes it difficult to quickly match M&A deals involving factory equipment and generate proposals, which in turn hinders efficient business succession and capital restructuring for SMEs.

[1146] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1147] In this invention, the server includes means for inputting information about the seller company, means for extracting potential buyers from a database, means for generating a proposal based on the extracted information about the potential buyers, means for displaying the generated proposal on a user interface, and means for inputting and matching information about factory equipment. This enables highly accurate matching in the M&A process for small and medium-sized enterprises that include factory equipment, making it possible to quickly and efficiently find suitable potential buyers and generate and provide proposals.

[1148] "Information about the seller's company" refers to basic information necessary to sell a company, such as the company's name, business operations, and financial status.

[1149] A "database" is an organized collection of data for collecting, storing, and retrieving information based on specified criteria.

[1150] A "potential buyer" is a company or individual that has the potential to acquire the seller company.

[1151] A "proposal" is a document that contains the information necessary to proceed with a contract between a selling company and a potential buyer.

[1152] A "user interface" refers to the input and display screens that allow a user to interact with a system.

[1153] "Factory equipment" is a general term for various devices, machines, robots, etc. used in factory production processes.

[1154] "Matching" involves comparing the seller's information with the conditions of potential buyers and finding the optimal combination based on matching elements.

[1155] A "generative artificial intelligence model" is an AI (artificial intelligence) algorithm that is trained to analyze patterns in data and make decisions or predictions.

[1156] A "machine learning algorithm" is a mathematical model that learns from data and makes predictions or classifications to perform a specific task.

[1157] "Extraction" means selecting information from a database or other source that meets specific criteria.

[1158] A "form" is an interface that allows a user to enter information, typically containing text boxes, drop-down menus, radio buttons, etc.

[1159] "Processing" refers to a series of steps or operations that input, transform, analyze, and output data.

[1160] This invention is a system for supporting the M&A process of small and medium-sized enterprises that purchase factory equipment. The system has various functions for inputting and matching information on seller companies, factory equipment, and potential buyers, and generating and displaying proposals.

[1161] The server functions as the central component of the entire system. It receives information about the seller company and factory equipment from the user, and extracts suitable potential buyers from the database based on that information. High-precision matching can be achieved using a generative artificial intelligence model. The server also generates proposals based on the extracted information about potential buyers and sends these proposals to the terminal.

[1162] The terminal functions as an interface for users to interact with the system. The terminal provides a form for users to enter basic information about the seller company and factory equipment, and transmits the entered information to the server. The terminal also displays proposals received from the server to users, allowing them to review the proposals and take necessary actions.

[1163] The user uses a terminal to enter information about the seller company and the factory equipment, and then sends the entered information to the server. The server receives the information, extracts suitable potential buyers from a database, generates a proposal, and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review the proposal. This process allows the user to quickly and efficiently find potential buyers and make the best proposal for the seller company and the factory equipment.

[1164] As a concrete example, when a user of a small or medium-sized enterprise uses the system, he or she enters company information and information about factory equipment into an input form on a terminal. For example, the user enters the company name "XYZ Corporation," the business description "software development," and the information about the "industrial robots" they use. This information is sent to the server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on a user interface, and the user can review the proposal, allowing the M&A process to proceed quickly and effectively.

[1165] Prompt Sentence Examples

[1166] Company name: XYZ Corporation, Business description: Software development, Factory equipment: Industrial robots

[1167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1168] Step 1: The user enters information about the seller company and factory equipment through the terminal.

[1169] The user enters information about the company name, business activities, and factory equipment into a form on the terminal. The input for this step is the data entered by the user, which is then retrieved by the terminal. The output is a dataset containing all the information entered.

[1170] Step 2: The device sends the input information to the server

[1171] The terminal sends the data entered by the user to the server. The input of this step is the dataset acquired in step 1, and it sends it to the server. The output is the data sent to the server.

[1172] Step 3: The server receives the data

[1173] The server receives the seller company and factory equipment information sent from the terminal. The input to this step is the data sent in step 2. The server receives this data and prepares it for processing. The output is the correctly received data.

[1174] Step 4: The server extracts suitable potential buyers from the database

[1175] The server uses the received data to process it to extract suitable potential buyers from the database, using machine learning algorithms and generative AI models. The input is the data received by the server and the contents of the database, and the output is a list of potential buyers.

[1176] Step 5: The server generates a proposal based on the extracted information about the potential buyer.

[1177] The server generates a proposal based on the extracted information of potential buyers. This process utilizes natural language generation technology. The input is a list of potential buyers, and the output is the generated proposal.

[1178] Step 6: The server sends the generated proposal to the device

[1179] The server sends the generated proposal to the terminal. The input is the generated proposal and performs a sending operation. The output is the proposal sent to the terminal.

[1180] Step 7: The device displays the proposal in its user interface.

[1181] The terminal displays the proposal received from the server on a user interface. The input is the received proposal and the output is the proposal displayed on the user interface, allowing the user to review the proposal and take action if necessary.

[1182] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1183] This invention provides an M&A business support system for small and medium-sized enterprises. This system automates a series of processes: inputting information about the selling company, extracting potential buyers from a database based on that information, generating a proposal based on the extracted information about the potential buyers, and displaying the generated proposal on a user interface. Furthermore, by incorporating an emotion engine that recognizes the user's emotions and customizes the content of the proposal based on that information, the system can provide more personalized proposals.

[1184] The server functions as the central component of the system. First, the server receives information about the seller company from the user and then uses that information to extract suitable potential buyers from a database. The server utilizes a generative artificial intelligence model to extract potential buyers, thereby achieving highly accurate matching. The server then generates a proposal based on the extracted information about the potential buyers and sends this proposal to the terminal.

[1185] The terminal functions as an interface for users to interact with the system. It provides a form for users to enter basic information about the seller company and sends the entered information to the server. The terminal also displays the proposal received from the server to the user, allowing the user to review the proposal and take any necessary actions. Furthermore, the terminal is equipped with an emotion engine that analyzes user emotions in real time and sends that information to the server to optimize the content of the proposal.

[1186] The user uses a terminal to enter information about the seller company and sends the entered information to the server. A proposal is generated from the server and displayed on the terminal, where the user can review it and select the most suitable potential buyer. The emotion engine analyzes the user's facial expressions and voice as they review the proposal to understand their emotional state. For example, if the user appears satisfied after viewing the proposal, the engine collects feedback and analyzes what aspects of the proposal the user finds appealing. This feedback information is used when generating the next proposal, improving the system to make more appropriate proposals.

[1187] Consider the following scenario as a specific example. When a small- to medium-sized enterprise (SME) called "BBB Co., Ltd." uses the system, the user enters basic information about "BBB Co., Ltd." (e.g., company name "BBB Co., Ltd.", business description "manufacturing") into an input form on a terminal. This information is sent to the server, which uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the extracted information about the potential buyers and sends it to the terminal. The terminal displays the generated proposal on its user interface, while an emotion engine analyzes the user's facial expressions and voice to understand their emotional state. For example, if the user shows positive emotions, such as smiling, when reviewing the proposal, this emotion data is sent to the server and used as feedback to improve the quality of future proposals.

[1188] By implementing this invention, the M&A process for small and medium-sized enterprises will be significantly more efficient, making it easier for sellers to find buyers on their desired terms. Furthermore, by incorporating an emotion engine, more appropriate and personalized proposals based on the user's emotions will be provided. This system will solve business succession issues for small and medium-sized enterprises and promote sustainable economic growth.

[1189] The processing flow will be explained below.

[1190] Step 1:

[1191] The terminal displays a form on the user interface for entering basic information about the seller company, including fields for the company name, business details, contact information, etc.

[1192] Step 2:

[1193] The user enters the necessary information into the input form on the terminal and clicks the "Submit" button, which causes the data entered into the form to be acquired by the terminal.

[1194] Step 3:

[1195] The terminal packages the acquired seller information and creates a request to send to the server, using JSON format or similar.

[1196] Step 4:

[1197] The server receives the seller company information sent from the terminal and prepares for database access.

[1198] Step 5:

[1199] The server runs machine learning algorithms to extract the best-matched potential buyers from the database based on the seller's information, using predictive models and clustering algorithms.

[1200] Step 6:

[1201] The server analyzes the extracted information about the potential buyer and begins the process of embedding that information into a proposal template for the seller company.

[1202] Step 7:

[1203] The server then sends the generated proposal to the terminal, which includes details such as the buyer's name, business activities, and offer details.

[1204] Step 8:

[1205] The terminal displays the proposal received from the server on the user interface in an easy-to-read format so that the user can check the proposal.

[1206] Step 9:

[1207] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and voice, and based on the results of this analysis, determines the user's emotional state in real time.

[1208] Step 10:

[1209] The emotion engine sends the user's emotion data to the server. For example, if the user looks satisfied while looking at the proposal, the engine sends data containing that information.

[1210] Step 11:

[1211] The server analyzes the feedback on the proposal based on the received emotional data and uses it in the next proposal generation process, thereby optimizing the proposal content.

[1212] Step 12:

[1213] The user can review the proposals displayed through the terminal interface, provide feedback if necessary, and select the most suitable potential buyer.

[1214] Through this series of processing steps, the system of the present invention enables sellers to quickly and efficiently find potential buyers and advance the M&A process with personalized proposals based on emotional data.

[1215] Example 2

[1216] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1217] Conventional M&A support systems for small and medium-sized enterprises have problems such as low accuracy in effectively matching information on sellers and potential buyers, and a lack of personalization in the generation of proposals, resulting in low user satisfaction.Furthermore, feedback reflecting user sentiment is not incorporated into proposals, making it difficult to continuously improve the quality of proposals.

[1218] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1219] In this invention, the server includes means for inputting information about the seller company, means for extracting potential buyers from a database, means for generating a proposal based on the extracted information about the potential buyers, means for displaying the generated proposal on a user interface, and means for recognizing a user's emotions and customizing the contents of the proposal based on that information. This makes it possible to optimize the proposal contents based on the individual emotional state of the user and provide highly accurate matching and personalized proposals.

[1220] A "seller" is a company or organization seeking to sell a company or business.

[1221] A "potential buyer" is a company or organization that may purchase the company or business being sold.

[1222] A "database" is a collection of data organized to efficiently store, retrieve, edit, and delete information.

[1223] A "proposal" is a document prepared to facilitate a transaction between a selling company and a potential buyer, and primarily contains transaction terms and background information.

[1224] "User interface" refers to the screens and operating means through which the system and the user interact with each other.

[1225] "Means for recognizing emotions" refers to technology or devices that analyze a user's facial expressions and voice and identify their emotional state.

[1226] A "generative artificial intelligence model" is a program that uses machine learning algorithms to learn patterns from data and make decisions and predictions.

[1227] A "machine learning model" is a technology that learns rules and patterns from data and makes predictions and classifications for new data.

[1228] This invention provides a system for supporting M&A transactions for small and medium-sized enterprises. This system inputs information about the seller company, extracts potential buyers from a database based on that information, then generates a proposal based on the information about the potential buyers, and finally displays the generated proposal on a user interface. It can also recognize the user's emotions and customize the content of the proposal based on that information.

[1229] The server acts as the central component of this system. It receives information about sellers from users and processes it to extract suitable potential buyers from a database based on that information. To improve the accuracy of this matching, a generative artificial intelligence model is used. For example, machine learning libraries such as TensorFlow and PyTorch can be used.

[1230] The server then uses a template engine to generate a proposal based on the extracted information about the potential buyer. The generated proposal is output in PDF or HTML format and sent from the server to the device, typically using an HTTP response.

[1231] The terminal functions as an interface for users to interact with the system. The terminal prompts users to enter basic information about the seller company through an input form built with HTML / CSS, and then sends that information to the server. The terminal also displays the proposal received from the server to the user. The user can review the proposal and take any necessary actions.

[1232] The device is also equipped with an emotion engine that analyzes the user's facial expressions and voice to understand their emotional state. Using technologies such as OpenCV and NVIDIA DeepStream, the device can analyze the user's emotions in real time. This emotion data is sent from the device to a server, which then uses it to optimize the content of the next proposal.

[1233] Consider the following scenario as a concrete example. When a seller company, "Company A," uses the system, the user enters basic information about "Company A" (company name, business activities, location, and desired buyer conditions) into an input form on their terminal. This information is sent to the server, which then uses a machine learning algorithm to extract suitable potential buyers from a database. The server then generates a proposal based on the potential buyers and sends it to the terminal. The terminal displays the proposal on a user interface, and the user confirms it. At the same time, an emotion engine analyzes the user's facial expressions and voice, and the emotional data is sent to the server. For example, if the user confirms the proposal and smiles with satisfaction, this positive emotional data is used as feedback the next time a proposal is generated.

[1234] An example prompt is:

[1235] Basic information of seller company "Company A":

[1236] Company name: Company A

[1237] Business content: Manufacturing industry

[1238] Location: Tokyo

[1239] Desired buyer conditions: Domestic companies considering business expansion

[1240] By inputting this prompt into the generative AI model, highly accurate matching and proposal generation become possible. In addition, the feedback function of the emotion engine allows for continuous improvement of the quality of the proposal content.

[1241] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1242] Step 1:

[1243] Input: The user enters basic information about the seller company (company name, business activities, location, desired buyer conditions, etc.) into the input form on the terminal.

[1244] Processing: The terminal displays an input form built with HTML / CSS and allows the user to enter the required information.

[1245] Output: The information entered by the user is sent by the terminal to the server.

[1246] Specific operation: The user enters the required information into the form and clicks the submit button. The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[1247] Step 2:

[1248] Input: The server receives the basic information of the seller company sent from the terminal.

[1249] Processing: The server parses the HTTP request and converts the received data into a format that can be processed.

[1250] Output: The parsed data is stored as a data object available in the server.

[1251] What happens: The server receives the HTTP request, parses the data using a JSON parser, and converts it into the appropriate database entry.

[1252] Step 3:

[1253] Input: Basic information about the seller company.

[1254] Processing: The server uses a generative artificial intelligence model to extract potential buyers from the database.

[1255] Output: Extracted potential buyer information.

[1256] How it works: The server uses machine learning libraries such as TensorFlow and PyTorch to run algorithms to identify the most suitable potential buyers for the selling company from the database.

[1257] Step 4:

[1258] Input: Extracted prospective buyer information.

[1259] Processing: The server uses a template engine to generate the proposal.

[1260] Output: The generated proposal (PDF or HTML format).

[1261] Specific operation: The server uses a template engine (e.g., Jinja2) to generate a proposal by inserting the extracted information of the potential buyer. The generated proposal is saved as a file.

[1262] Step 5:

[1263] Input: The generated proposal.

[1264] Processing: The server sends the generated proposal to the terminal.

[1265] Output: Proposal link or file viewable on your device.

[1266] Specific operation: The server sends the proposal file as an HTTP response and provides the device with a download link and a viewing page.

[1267] Step 6:

[1268] Input: Proposal link or file sent from the server.

[1269] Processing: The terminal displays the proposal on the user interface.

[1270] Output: The proposal that is displayed to the user.

[1271] Specific operation: The device analyzes the HTTP response and displays the received proposal link and file in the user interface. The user interacts with the response to confirm it.

[1272] Step 7:

[1273] Input: User's facial expressions and voice.

[1274] Processing: The terminal uses the emotion engine to analyze the user's emotions.

[1275] Output: Parsed emotion data.

[1276] Specific operation: Using the device's built-in camera and microphone, the system captures the user's facial expressions and voice in real time, and performs emotion analysis using technologies such as OpenCV and NVIDIA DeepStream.

[1277] Step 8:

[1278] Input: Parsed emotion data.

[1279] Processing: The device sends the emotion data to the server.

[1280] Output: Emotion data object available on the server side.

[1281] Specific operation: The device converts the analyzed emotion data into JSON format and sends it to the server as an HTTP request.

[1282] Step 9:

[1283] Input: Emotion data.

[1284] Processing: The server analyzes the received emotion data and stores it in a database to optimize the content of the next proposal.

[1285] Output: Feedback for optimized proposal generation.

[1286] Specific operation: The server receives the emotion data, analyzes it, stores it in a database, and reflects this feedback when generating the next proposal.

[1287] (Application example 2)

[1288] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1289] In conventional systems for matching sellers and buyers, the process from inputting seller information to identifying potential buyers and generating proposals takes a lot of time and effort. Furthermore, the proposals are uniform, resulting in low user satisfaction and making it difficult to conclude efficient sales contracts. While there is a particular demand for personalized proposals that take user sentiment into account, there is a lack of mechanisms to achieve this. This prevents sellers, such as small and medium-sized enterprises, from conducting quick and effective sales activities, often resulting in missed market opportunities.

[1290] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1291] In this invention, the server includes means for inputting information about the seller company, means for extracting potential buyers from a database, means for generating a proposal based on the information about the extracted potential buyers, means for transmitting the proposal to a user terminal and displaying it on the display of the user terminal, means for analyzing the user's emotions in real time and customizing the contents of the proposal based on that information, and means for the emotion analysis means to analyze the user's facial expressions and voice and transmit emotional data to the server. This enables quick and effective matching between seller companies and buyer companies, and also makes it possible to provide personalized proposals based on the user's emotions.

[1292] "Means for inputting seller company information" refers to an interface or device that allows a seller company to input its own company information into the system.

[1293] "Means for extracting potential buyers from a database" refers to technology for selecting and extracting appropriate potential buyers from a database based on the input information of the seller company.

[1294] The "means for generating a proposal" is a system or algorithm for creating a proposal that is beneficial to both the seller company and the potential buyer based on the extracted information about the potential buyer.

[1295] The "means for displaying the proposal on the display of the user terminal" is a system for transmitting the generated proposal to the user terminal and displaying it on the display.

[1296] "Emotion analysis means" is a technology for analyzing a user's facial expressions and voice in real time to understand the user's emotional state.

[1297] "Means for the emotion analysis means to analyze the user's facial expressions and voice and send the emotion data to the server" is a technology for sending the data acquired by the emotion analysis means to the server and customizing the contents of the proposal.

[1298] The present invention relates to an emotion-aware store support system for improving the shopping experience in physical stores. This system integrates multiple hardware and software components to provide personalized suggestions based on customer emotions in real time. This specification describes the specific configuration and operation of the system.

[1299] System configuration

[1300] 1. Server

[1301] Role: Serves as the central component of the system, receiving, processing and storing data.

[1302] Technologies used: Machine learning algorithms, generative AI models

[1303] Specific process: Based on the seller's information, appropriate potential buyers are extracted from the database and a proposal is generated.

[1304] 2. User Device

[1305] Role: Receives input from the user and communicates with the server.

[1306] Hardware examples: smartphones, smart glasses

[1307] Specific process: The user inputs seller or product information through the terminal interface and sends this information to the server, and the proposal received from the server is displayed on the screen.

[1308] 3. Sentiment Analysis Engine

[1309] Role: Analyzes the user's facial expressions and voice in real time to obtain emotional data.

[1310] Technologies used: facial expression recognition algorithm, voice analysis technology

[1311] Specific processing: Understand the user's emotional state when reviewing the proposal and send that information to the server.

[1312] Detailed System Operation

[1313] 1. Enter and submit information

[1314] Users enter their personal information (preferences, desired conditions, etc.) using an input form displayed on the screen of their smartphone or smart glasses. The entered information is sent to the server in real time.

[1315] 2. Identifying potential buyers

[1316] The server extracts potential buyers from a database based on the received user information, using machine learning algorithms to achieve highly accurate matching.

[1317] 3. Proposal Generation and Viewing

[1318] The server generates a proposal based on the extracted candidate information and sends it to the user's terminal, where the proposal is displayed on the screen.

[1319] 4. Sentiment Analysis and Feedback

[1320] The emotion analysis engine analyzes the user's facial expressions and voice in real time and sends the emotional data to the server, which then uses this emotional feedback to customize the content of future proposals.

[1321] Specific examples

[1322] System usage examples

[1323] For example, if a customer uses the system in a fashion shop and enters "I want casual fashion, blue, size M," the server will send the following prompt to the generative AI model:

[1324] "I'm looking for casual fashion. The color is blue, and the size is medium. Please recommend some products."

[1325] Based on this information, the system will suggest suitable products and display them on the user's device. At the same time, by analyzing the user's facial expressions and voice, the system can understand the customer's level of satisfaction with the suggestions and use this information as feedback to improve the quality of the suggestions.

[1326] This system will significantly improve the customer experience in physical stores and enable more personalized shopping suggestions.

[1327] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1328] Step 1:

[1329] User enters information on device

[1330] Input: Information such as the style, color, and size desired by the user

[1331] How it works: Users enter their fashion preferences and desired conditions using an input form displayed on the screen of their smartphone or smart glasses. The input information is sent to the server in real time.

[1332] Output: The user's input information is sent to the server.

[1333] Step 2:

[1334] The server extracts potential buyers

[1335] Input: Fashion preferences and desired conditions submitted by the user

[1336] How it works: The server extracts potential buyers from a database based on the received user information. This process uses machine learning algorithms to achieve highly accurate matching.

[1337] Output: Extracted information about potential buyers

[1338] Step 3:

[1339] The server generates the proposal

[1340] Input: Extracted information about potential buyers

[1341] Specific operation: Based on the extracted information of potential buyers, the server uses a generative AI model to create an optimal proposal, which is a list of products and services that meet the user's requirements.

[1342] Output: Generated proposal

[1343] Step 4:

[1344] The server sends the proposal to the device.

[1345] Input: Generated proposal

[1346] Specific operation: The proposal is sent to the user's device and displayed on the user's device's display.

[1347] Output: The proposal is displayed on the user's device.

[1348] Step 5:

[1349] The user reviews the proposal and analyzes the sentiment data.

[1350] Input: Facial expressions and voice of the user reviewing the proposal

[1351] How it works: The emotion analysis engine analyzes the user's facial expressions and voice in real time and sends the results to the server. It uses the camera built into the smart glasses or the front camera of the smartphone for facial recognition, and the microphone for voice analysis.

[1352] Output: Parsed emotion data

[1353] Step 6:

[1354] The server improves the proposal based on the feedback.

[1355] Input: Parsed emotion data

[1356] Specific operation: The server analyzes the user's emotional data and reflects it in the next proposal generation. At this time, feedback information obtained from the emotional data is utilized.

[1357] Output: Data base for improved proposals

[1358] Through the above processing steps, users can receive personalized suggestions in real time, enabling them to find the best products and services.

[1359] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1360] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1361] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1362] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1363] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1364] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1365] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1366] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1367] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1368] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1369] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1370] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1371] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1372] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1373] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1374] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1375] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1376] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1377] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1378] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1379] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1380] The following is further disclosed regarding the above embodiment.

[1381] (Claim 1)

[1382] A means for inputting information about the seller company;

[1383] a means for extracting potential buyers from the database;

[1384] a means for generating a proposal based on the extracted information of the potential buyer;

[1385] means for displaying the generated proposal on a user interface;

[1386] A system including:

[1387] (Claim 2)

[1388] 10. The system of claim 1, including a generative artificial intelligence model for automatically matching information on seller companies with information on buyer companies and quickly creating proposals.

[1389] (Claim 3)

[1390] 10. The system of claim 1, wherein the extraction of potential buyers from the database is performed using a machine learning algorithm.

[1391] (Claim 4)

[1392] 10. The system of claim 1, further comprising a feedback system for receiving user feedback on the generated proposal and optimizing the content of the proposal.

[1393] (Claim 5)

[1394] 2. The system according to claim 1, wherein the terminal includes means for receiving information about the seller company from the user and transmitting it to the server.

[1395] "Example 1"

[1396] (Claim 1)

[1397] means for transmitting the input information;

[1398] A means for searching a database based on the received information to extract candidates;

[1399] means for generating suggestions based on the information using a generative artificial intelligence model;

[1400] means for displaying the generated suggestions in a user interface;

[1401] A system including:

[1402] (Claim 2)

[1403] 10. The system of claim 1, including a generative artificial intelligence model for automatically matching seller information with buyer information and rapidly generating proposals.

[1404] (Claim 3)

[1405] 10. The system of claim 1, wherein the extraction of candidates from the database is performed using a machine learning algorithm.

[1406] "Application Example 1"

[1407] (Claim 1)

[1408] A means for inputting information about the seller company;

[1409] a means for extracting potential buyers from the database;

[1410] a means for generating a proposal based on the extracted information of the potential buyer;

[1411] means for displaying the generated proposal on a user interface;

[1412] a means for inputting and matching factory equipment information;

[1413] A system including:

[1414] (Claim 2)

[1415] 2. The system of claim 1, including a generative artificial intelligence model for automatically matching information on seller companies with information on buyer companies and factory equipment, and for quickly creating proposals.

[1416] (Claim 3)

[1417] 2. The system of claim 1, wherein the extraction of potential buyers from the database is performed using a machine learning algorithm, and further includes a process for evaluating the suitability of factory equipment.

[1418] "Example 2: Combining Emotion Engines"

[1419] (Claim 1)

[1420] A means for inputting information about the seller company;

[1421] a means for extracting potential buyers from the database;

[1422] a means for generating a proposal based on the extracted information of the potential buyer;

[1423] means for displaying the generated proposal on a user interface;

[1424] A means of recognizing user emotions and customizing the content of proposals based on that information;

[1425] A system including:

[1426] (Claim 2)

[1427] The system of claim 1, including a generative artificial intelligence model that automatically matches information about seller companies with information about potential buyers using a machine learning model and quickly creates proposals.

[1428] (Claim 3)

[1429] 10. The system of claim 1, further comprising means for collecting emotion data sent by a user and utilizing the collected emotion data to optimize the content of the proposal.

[1430] "Application example 2 when combining emotion engines"

[1431] (Claim 1)

[1432] A means for inputting information about the seller company;

[1433] a means for extracting potential buyers from the database;

[1434] a means for generating a proposal based on the extracted information of the potential buyer;

[1435] means for transmitting the proposal to a user terminal and displaying it on a display of the user terminal;

[1436] A sentiment analysis means for analyzing user sentiment in real time and customizing the content of the proposal based on that sentiment information;

[1437] An emotion analysis means analyzes the facial expressions and voice of the user and transmits emotion data to a server;

[1438] A system including:

[1439] (Claim 2)

[1440] 10. The system of claim 1, including a generative artificial intelligence model for automatically matching information on seller companies with information on buyer companies and quickly creating proposals.

[1441] (Claim 3)

[1442] 10. The system of claim 1, wherein the extraction of potential buyers from the database is performed using a machine learning algorithm. [Explanation of symbols]

[1443] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for inputting information about the seller company; a means for extracting potential buyers from the database; A means for generating a proposal based on the extracted information of the potential buyers; means for displaying the generated proposal on a user interface; A system including:

2. 10. The system of claim 1, further comprising a generative artificial intelligence model for automatically matching information on seller companies with information on buyer companies and for quickly creating proposals.

3. The system of claim 1 , wherein the extraction of potential buyers from the database is performed using a machine learning algorithm.

4. 10. The system of claim 1, further comprising a feedback system for receiving user feedback on the generated proposal and optimizing the content of the proposal.

5. 2. The system according to claim 1, wherein the terminal includes means for receiving information about the seller company from the user and transmitting the information to the server.

Images