system

Abstract

We provide the system. [Solution] Information acquisition means for obtaining data from public information sources, Information analysis tools for organizing and analyzing acquired information, A combination generation means that generates a list of combinations of business entities based on the analysis results, A result display means that presents the generated list to the user, A means of collecting user opinions and reflecting them in optimizing the system, A relationship evaluation tool that assesses and recommends relationships between business entities based on similarity, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The problems faced by existing small and medium-sized enterprises are that it is difficult to find appropriate business partners within limited human resources and time. In traditional methods, information collection, evaluation of synergies between enterprises, and formation of realistic partnerships cannot be carried out efficiently, resulting in problems such as delays in the development of new products and services.

Means for Solving the Problems

[0005] This invention solves the above problems by providing a system that analyzes information collected from public data sources, generates matching lists between companies, and presents them to users. Specifically, information is acquired by a data collection means, analyzed by a data analysis means, and then a matching generation means is used to generate a list of company combinations. Furthermore, suggestions are made to the user by a results presentation means, and user reactions are collected by a feedback collection means to improve the system. In this way, small and medium-sized enterprises can efficiently find collaboration partners.

[0006] "Public data sources" refer to information providers that are widely available to the public and can be used without specific conditions.

[0007] "Data collection means" refers to mechanisms and devices for effectively and efficiently acquiring information from public data sources.

[0008] "Data analysis methods" refer to analytical techniques and programs used to organize acquired data and obtain information tailored to specific purposes.

[0009] "Matching generation means" refers to processes and tools for automatically creating combinations of companies based on analyzed information.

[0010] "Result presentation means" refers to a device or interface for effectively providing the generated list of company combinations to the user.

[0011] "Feedback collection methods" refer to mechanisms and methods for gathering user reactions and opinions and using them to improve and optimize the system.

[0012] "Synergy effect" refers to the effect of collaboration between companies that generates greater results and value than would be achieved by working independently.

[0013] "Evaluation methods" refer to methods and devices for analyzing the likelihood of success of synergy effects and combinations of companies, and for making appropriate recommendations.

[0014] "Means of explanation" refers to mechanisms and technologies used to clearly communicate the key points and benefits of information or proposals to users. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention provides a business matching system for small and medium-sized enterprises, and includes a system for collecting and analyzing information from diverse data sources and effectively matching companies with each other. This system primarily achieves its objectives through the interaction of three parties: a server, terminals, and users.

[0037] First, the server retrieves data from public data sources. This includes social media, industry reports, and publicly available company information. After collecting this information, the server preprocesses the data to remove unwanted characters and noise. This improves the quality of the data.

[0038] Next, the server analyzes the data using natural language processing and data mining techniques. In this analysis phase, the server identifies market trends and customer needs from the collected information and extracts potential matching candidates for companies and products.

[0039] Based on the analysis results, the server evaluates combinations of companies and products. It automatically lists combinations of companies with high synergy potential, increasing the likelihood of successful collaboration.

[0040] Next, the terminal receives a matching list generated from the server and presents it to the user. At this time, the AI ​​agent clearly explains the advantages and feasibility of each combination in the list, supporting the user in making an appropriate choice.

[0041] Users select the most suitable collaboration partner from the presented options and then send their opinions and feedback to the system. This user feedback is collected on the server and used to further improve and optimize the system.

[0042] As a concrete example, suppose a user company is considering expanding into a new field. By using the system, this company can find effective partners in a short period of time and gain the opportunity to maximize synergistic effects.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server collects necessary information from public data sources. This includes accessing social media APIs, downloading industry reports, and scraping from official company websites. The collected data is stored in storage.

[0046] Step 2:

[0047] The server preprocesses the collected data. Specifically, it removes noise from the data, standardizes case, and normalizes the text. It also imputes missing values ​​and removes duplicate data to prepare the data for analysis.

[0048] Step 3:

[0049] The server uses natural language processing (NLP) to analyze data. It extracts market trends through topic modeling and understands consumer opinions through sentiment analysis. This allows it to identify customer needs and market demands.

[0050] Step 4:

[0051] The server evaluates combinations of companies and products based on the analyzed data. To measure synergy effects, it uses algorithms to calculate similarity scores and predict the likelihood of successful collaboration.

[0052] Step 5:

[0053] Based on the evaluation results, the server lists combinations of companies and generates a matching list. This list is ranked based on synergy effects and feasibility.

[0054] Step 6:

[0055] The terminal presents the user with a matching list received from the server. An AI agent explains the advantages and key points of each suggestion on the list, supporting the user's decision-making.

[0056] Step 7:

[0057] Users select the most suitable collaboration partner from the presented matching list. After selection, users provide feedback to the system, reporting their reasons for selection and details of their preferences.

[0058] Step 8:

[0059] The server analyzes user feedback and uses it to improve the system's evaluation model and filtering algorithms. This will enable more accurate matching in subsequent attempts.

[0060] (Example 1)

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

[0062] In today's business environment, companies need to find partners and build collaborative relationships quickly and effectively. However, collecting appropriate information from the vast ocean of data and conducting accurate data analysis requires significant resources, making it particularly difficult for small and medium-sized enterprises (SMEs). Furthermore, the lack of objective indicators for evaluating inter-company combinations and mechanisms for clearly presenting the results hinders optimal decision-making.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes data collection means for acquiring data from information sources, data preprocessing means for preprocessing the acquired data and removing noise, and data analysis means for analyzing the data using natural language processing and data mining techniques. This enables companies to efficiently collect information and build appropriate and rapid collaborative relationships based on the analysis results.

[0065] "Information sources" refer to external databases and platforms accessible to businesses, including public data and open data.

[0066] "Data acquisition means" refers to the hardware and software functions used to obtain necessary data from information sources.

[0067] "Data preprocessing means" refers to processes and techniques for removing noise from acquired data and processing it into a format suitable for analysis.

[0068] "Natural language processing" refers to the methods and techniques for processing human language using computers, and is used for analyzing text data.

[0069] "Data mining techniques" refer to scientific and statistical methods for extracting useful information and patterns from large amounts of data.

[0070] "Data analysis tools" refer to functions that analyze data using natural language processing and data mining techniques to derive useful insights.

[0071] "Matching generation means" refers to a part of the algorithm or system used to evaluate and generate appropriate combinations of companies and products based on analysis results.

[0072] "Result presentation means" refers to a function that provides the generated matching list and evaluation results to the user in visual or text format.

[0073] "Feedback collection methods" refer to methods or processes for collecting opinions and evaluations from users and incorporating them into further system optimization.

[0074] "Evaluation methods" refer to criteria or algorithms used to assess the synergistic effects of a particular combination of companies.

[0075] This invention is configured as a system that acquires data from information sources and effectively supports business matching between small and medium-sized enterprises. This objective is achieved primarily through the interaction of three parties: a server, a terminal, and a user.

[0076] First, the server has data collection means to obtain the necessary data from information sources. Specifically, it collects data from social media APIs and public websites. During this process, a script using Python is executed periodically to automatically retrieve data. The server preprocesses the retrieved data using the pandas library to remove noise and transform it into an analyzable format.

[0077] Next, the server utilizes natural language processing technology, analyzing text data using the NLTK library. This allows for the extraction of important keywords and the understanding of market trends. Furthermore, the scikit-learn library is used as a data mining technique to extract matching candidates based on the characteristics of each company.

[0078] Based on the analysis results, the server uses a recommendation algorithm to evaluate appropriate combinations and constructs a list using a matching generation mechanism. This matching list includes combinations of companies that maximize synergy effects, thereby increasing the likelihood of successful collaboration.

[0079] The terminal receives a matching list from the server and presents it to the user visually and intuitively via an agent. The interface is designed to be easy for viewers to understand, clearly explaining the details and advantages of each candidate.

[0080] Users refer to the presented matching list and select the most suitable partner candidate. The selection results and feedback are sent to the server via the device and used by the system's feedback collection mechanism to improve the system in the future.

[0081] As a concrete example, consider a case where a small or medium-sized enterprise in the food industry is looking for a partner with packaging technology. By entering the prompt message "Please suggest potential partner candidates for a food company seeking new food packaging technology," this company can quickly and effectively find suitable candidates through the system. In this way, the system of the present invention enables each company to quickly find its ideal partner and maximize synergistic effects.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The server retrieves data from the information source. It takes an API key or the URL to be scraped as input, and the output is raw text data. Specifically, the server uses a Python script to automatically retrieve industry-related information from social media APIs and public databases.

[0085] Step 2:

[0086] The server preprocesses the acquired data. In this step, raw text data is given as input, and cleaned data is produced as output. Specifically, the server uses the pandas library to remove unwanted characters and noise from the data and impute missing values. This improves the quality of the analysis.

[0087] Step 3:

[0088] The server analyzes pre-processed data. Cleaned data is given as input, and the analysis results are obtained as output. Specifically, the server uses the NLTK library to perform natural language processing and extract keywords from the text. It also applies a machine learning model using the scikit-learn library to analyze market trends.

[0089] Step 4:

[0090] The server generates matching candidates based on the analysis results. The analysis results are given as input, and a list of company and product combinations is obtained as output. Specifically, it runs a recommendation algorithm and automatically lists company combinations that are expected to have synergistic effects. This helps users make quick decisions.

[0091] Step 5:

[0092] The terminal displays a matching list received from the server. It receives a list of company combinations as input and outputs a visually clear display that is easy for the user to understand. Specifically, the terminal uses a GUI to graphically display the advantages and potential of each company, supporting the user in selecting a partner.

[0093] Step 6:

[0094] The user selects an appropriate partner from the presented options and provides feedback. Based on the combination of companies presented as input, the system sends the selection results and feedback as output. Specifically, the user enters selections and comments on the terminal interface, which are collected on the server and used to improve the accuracy of matching in the future.

[0095] (Application Example 1)

[0096] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0097] Traditional business matching systems have faced challenges in quickly finding the optimal combination of companies, and manually searching for the right combination to maximize synergy is time-consuming and costly. Furthermore, they often fail to adequately present crucial information such as the key points and advantages of each combination, making decision-making difficult.

[0098] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0099] In this invention, the server includes information acquisition means, information analysis means, combination generation means, result display means, opinion collection means, and relationship evaluation means. This makes it possible to automatically generate the optimal combination between companies in a short period of time and provide users with a clear explanation of the key points and advantages.

[0100] "Information acquisition means" refers to a system for obtaining data from public information sources.

[0101] An "information analysis tool" is a system for organizing and analyzing acquired data.

[0102] The "combination generation means" is a mechanism that generates a list of optimal combinations of business entities based on the analysis results.

[0103] A "result display means" is a mechanism for presenting the generated list of combinations to the user.

[0104] A "means of gathering opinions" refers to a system for collecting opinions and feedback from users and using them to optimize the system.

[0105] A "relationship evaluation tool" is a system that evaluates the relationships between business entities based on similarity and recommends the optimal combination.

[0106] The system for implementing this invention achieves its objectives primarily through the interaction of three parties: a server, a terminal, and a user. The server collects various data from public information sources using information acquisition means. Next, it uses information analysis means to organize the collected data, remove noise, and then analyze the data. Based on this analysis, a relationship evaluation means evaluates similarity, and a combination generation means creates a list of optimal combinations of business entities.

[0107] The terminal uses a results display mechanism to present the user with a list of combinations sent from the server. Based on the presented information, the user decides on a partnership candidate and sends feedback to the system using a feedback collection mechanism. This feedback is used by the server to update the generated AI model and improve the system's accuracy.

[0108] For example, if a small or medium-sized e-commerce business is considering expanding into a different category, it can automatically find the best partner from manufacturers in a short period of time. Such companies can select the partner that best suits their needs through a recommendation list generated by the server. An example of a prompt to the generating AI model would be, "How can you provide optimal trade matching between manufacturers and distributors based on a rich data source?"

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server retrieves data from public information sources using information acquisition methods. In this process, the input is the URL or API of the public information source, and the output is the retrieved raw data. The data is stored on the server in JSON or XML format. Specifically, the data is downloaded via HTTP requests.

[0112] Step 2:

[0113] The server uses information analysis tools to process the acquired data and remove noise. The input is the raw data acquired in step 1, and the output is the cleaned and processed data. Specifically, unnecessary characters and spaces are removed, and the data is converted into a parseable format.

[0114] Step 3:

[0115] The server uses combination generation methods to evaluate similarity within the prepared data and create a list of optimal combinations of business entities. The input is the prepared data, and the output is a list containing pairs or groups of business entities with high similarity. Specifically, it vectorizes text data using TF-IDF and calculates cosine similarity.

[0116] Step 4:

[0117] The server sends the generated list of combinations to the terminal via a results display mechanism. The input is an optimized list of combinations, and the output is visualized data. Specifically, the list is converted into a user-friendly format (e.g., HTML or JSON).

[0118] Step 5:

[0119] The terminal displays a list of combinations received from the server to the user using a results display mechanism. The input is data received from the server, and the output is data displayed on the user interface. Specifically, the list is displayed visually through a GUI.

[0120] Step 6:

[0121] The user selects a candidate from the presented combinations and inputs feedback into the device using a feedback collection tool. The input consists of the user's selection and opinion, and the output is saved on the device as feedback data. Specifically, the user clicks on an option and enters a comment in a text box.

[0122] Step 7:

[0123] The terminal sends collected feedback to the server to help optimize the system. The input is user feedback data, and the output is structured data sent to the server. Specifically, the feedback is stored in a database and used as data to train the generated AI model in preparation for the next model update.

[0124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0125] This invention is a system that enables effective business matching for companies. In addition to collecting, analyzing, and generating matches from public data sources, it incorporates an emotion engine that recognizes and analyzes user emotions. This system aims to improve the user experience through collaboration among the server, terminal, and user.

[0126] First, the server collects rich information from public data sources. Data collection includes API calls, web scraping, and database access. The collected information is preprocessed to remove unnecessary noise and normalize the text before being ready for analysis.

[0127] Next, the server utilizes advanced natural language processing (NLP) and data analysis techniques to identify market trends and customer preferences. The analyzed data is then used to calculate potential matches between companies, taking synergy effects into consideration, and a list of optimal combinations is generated.

[0128] Furthermore, the server incorporates an emotion engine that recognizes the user's emotional state from their interactions and feedback. This emotion analysis is used to adjust the content and presentation method of the matching list presented to the user, contributing to increased user satisfaction.

[0129] The device receives a matching list generated by the server and presents it visually to the user. An AI agent explains the merits of each combination to the user, and the suggestions may be modified based on sentiment data.

[0130] For example, if the user is a company representative seeking new collaborations, the emotion engine captures the user's interests and satisfaction levels in real time, prioritizing the display of combinations that interest them. In this way, users can obtain the results they expect more quickly and accurately.

[0131] Ultimately, the user selects the partner they deem best and provides feedback on their choice to the system. The server analyzes this feedback and sentiment data to improve the system's overall algorithm and enhance matching accuracy in the future.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The server retrieves information from public data sources. This involves sending requests through social media APIs, accessing corporate databases, and utilizing website scraping techniques. The retrieved data is temporarily stored in storage.

[0135] Step 2:

[0136] The server preprocesses the collected data. Specifically, it removes noise, normalizes the data, and imputes missing values ​​to maintain data integrity. It also performs duplicate removal and categorization.

[0137] Step 3:

[0138] The server analyzes pre-processed data. Using natural language processing techniques, it extracts customer needs and market trends from text data. Furthermore, it uses data mining techniques to find patterns and identify potential business opportunities.

[0139] Step 4:

[0140] The server evaluates combinations of companies and products based on the analysis results and generates a matching list based on synergy effects and likelihood of success. This uses algorithms to analyze similarities and differences between companies and derive the most effective combinations.

[0141] Step 5:

[0142] The server activates the emotion engine and analyzes the user's emotional state from past choices and interaction data. This allows it to determine which combinations the user is favorably disposed towards and reflect this in the matching list.

[0143] Step 6:

[0144] The device presents the generated matching list to the user. At this point, the AI ​​agent explains the details of each suggestion and highlights suggestions that the user may be interested in based on the results of the emotion engine.

[0145] Step 7:

[0146] Users select a suitable collaboration partner from the presented proposals. They can make a satisfactory choice after considering the advantages and disadvantages.

[0147] Step 8:

[0148] Users enter and submit feedback to the system. This feedback includes reasons for their selection and any additional comments.

[0149] Step 9:

[0150] The server analyzes feedback and sentiment data received from users. This allows the system's algorithms and suggestions to be improved, leading to better matching accuracy in the future.

[0151] (Example 2)

[0152] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0153] In today's business environment, effective matching between companies is crucial. However, traditional systems struggle to respond quickly to market changes and diverse customer needs, and are particularly inadequate at providing flexible proposals that cater to user emotions. Therefore, there is a need for a system that provides potential partners that meet user expectations and improves the user experience.

[0154] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0155] In this invention, the server includes information gathering means, information analysis means, combination generation means, sentiment analysis means, result display means, and feedback collection means. This enables the generation of appropriate combinations of companies based on public information sources and flexible suggestions based on the user's sentiment. Furthermore, it is possible to improve the accuracy of the system by utilizing the collected feedback.

[0156] An "information gathering tool" is a mechanism that has the function of automatically acquiring necessary information from public information sources.

[0157] An "information analysis tool" is a mechanism for transforming acquired information into a useful form by preprocessing and analyzing it.

[0158] A "combination generation mechanism" is a system that identifies and proposes optimal interrelationships and partnership candidates from data based on analysis results.

[0159] An "emotion analysis tool" is a mechanism that recognizes the user's emotional state from their interactions and input data, and processes that information.

[0160] A "result display means" is a mechanism that has the function of visually presenting the generated combinations and suggestions to the user.

[0161] A "feedback collection mechanism" is a system for collecting user feedback and usage data and using it to improve the system.

[0162] "Synergy effect" is a term that refers to additional benefits obtained through partnerships between companies that would not be achievable individually.

[0163] An "explanatory mechanism" is a system designed to provide users with an easily understandable overview of the key points and benefits of the generated suggestions and combinations.

[0164] To implement this invention, a server plays a central role. The server collects information from public sources using information gathering means. This process includes specific scripts for making API calls and performing web scraping. The collected data is preprocessed and analyzed through information analysis means. Specifically, the Python NLTK library is used to perform data denoising and natural language processing.

[0165] Next, the server uses a combination generation mechanism to generate the optimal combination of business partners based on the analyzed data. At this stage, machine learning algorithms are used to identify candidates while considering the synergistic effects between companies.

[0166] Furthermore, the server incorporates emotion analysis capabilities to recognize emotional data from user feedback and interactions. For example, it analyzes input data obtained from the user's device to determine whether there are many positive emotional expressions.

[0167] The terminal visually displays information received from the server. The user interface is designed to be simple and intuitive, with an AI agent clearly guiding the user through the advantages of each combination. This agent enhances satisfaction by adjusting the presented suggestions based on the user's emotional state.

[0168] Users provide feedback by reviewing the presented suggestions and selecting the optimal combination of partners. This user feedback is collected on a server and used to improve the system's algorithms through feedback collection mechanisms, leading to increased accuracy in future iterations.

[0169] For example, if a user is a sales representative seeking new collaborations, the emotion engine captures the user's interests and satisfaction levels in real time, prioritizing and displaying the most suitable matchups. In this way, users can obtain their desired results more quickly and accurately.

[0170] Examples of prompt statements for a generative AI model are shown below.

[0171] "Please find new collaboration partners for my company, prioritizing companies that focus particularly on sustainable business practices."

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The server uses data gathering methods to obtain data from public sources. This process automatically collects the necessary information using data requests from APIs and web scraping. Inputs include specific URLs and API endpoints, and the output is obtained as a structured dataset.

[0175] Step 2:

[0176] The server uses information analysis tools to preprocess and analyze the collected data. Here, the Python Pandas library is used to denoise the data and normalize the text. It accepts raw data as input and generates a clean, analyzable dataset as output.

[0177] Step 3:

[0178] The server uses a combination generation mechanism to calculate appropriate business partner combinations from the analyzed data. Specifically, it applies similarity calculations and clustering algorithms to select the optimal combination candidates. The input is the analyzed data, and the output is a list of candidate partners.

[0179] Step 4:

[0180] The server uses sentiment analysis techniques to recognize emotions from user feedback and interaction data. It calculates an emotion score using natural language processing methods and identifies positive or negative emotions. It takes user feedback messages as input and outputs the results of the sentiment analysis.

[0181] Step 5:

[0182] The terminal receives a list of combinations generated by the server and presents it to the user via a results display device. An AI agent is activated and explains the advantages of the combinations on the user interface. The input is the list of combinations from the server, and the output is the information displayed on the user's screen.

[0183] Step 6:

[0184] The user reviews the presented combinations and provides feedback. This feedback is sent from the terminal to the server and stored in a database by the feedback collection mechanism. The input is user feedback data, and the output is data for improvement that is accumulated in the system.

[0185] (Application Example 2)

[0186] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0187] To achieve effective business matching between companies, it is crucial not only to optimize the combinations of companies but also to enhance user satisfaction. However, conventional systems have struggled to consider user emotions and interests when presenting company combinations, resulting in a limited user experience. Furthermore, methods for effectively incorporating feedback and continuously improving the system have not been established. As a result, there is a challenge in obtaining the flexible and accurate matching results that users expect.

[0188] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0189] In this invention, the server includes data collection means for acquiring information from public data sources, data analysis means for processing and analyzing the acquired information, matching generation means for generating a list of organizational combinations based on the analysis results, emotion analysis means for analyzing the user's emotions using an emotion analysis engine, adjustment means for adjusting the presentation of results based on the emotion analysis, and feedback collection means for collecting feedback from users and reflecting it in improving the system. This makes it possible to provide flexible matching results that reflect the user's emotional state, increase user satisfaction, and continuously improve the system.

[0190] "Data collection means" refers to devices and methods for collecting information from public data sources.

[0191] "Data analysis means" refers to devices and methods for processing and analyzing collected information.

[0192] A "matching generation means" is a device or method for generating a list of organizational combinations based on analysis results.

[0193] "Result presentation means" refers to a device or method for presenting the generated combination list to the user visually or audibly.

[0194] "Emotional analysis means" refers to devices or methods for analyzing a user's emotional state using an emotional analysis engine.

[0195] "Adjustment means" refers to devices or methods for optimally adjusting the results presented based on emotion analysis.

[0196] "Feedback collection methods" refer to devices or methods for collecting feedback from users and incorporating it into system improvements.

[0197] This invention is a system that enables effective business matching between companies, and is realized through the collaboration of three parties: a server, a terminal, and a user.

[0198] The server first collects information from public data sources. Specifically, it obtains market data and company information from the internet through API calls and web scraping. This collection process uses Python and the Beautiful Soup library.

[0199] Next, the server preprocesses the collected information and performs data analysis using natural language processing. Preprocessing involves removing noise and normalizing the text. In this step, natural language processing tools such as TENSORFLOW® are used to analyze company needs and market trends.

[0200] Furthermore, the server uses an emotion analysis engine to analyze emotions from user feedback and interactions. This allows for prioritization and adjustment of the generated matching list. The adjusted results are then presented to the user. This process makes it possible to prioritize and present combinations that the user is more likely to be interested in.

[0201] The device visually displays a matching list sent from the server to the user, and an AI assistant provides voice explanations of the merits of each suggestion. This allows the user to easily understand the characteristics of the suggested companies.

[0202] Users provide feedback on the presented combinations. This feedback is collected by the server and used, along with sentiment analysis results, to improve the algorithm. This makes it possible to improve the accuracy of matching in the future.

[0203] As a concrete example, suppose a user is looking for a partner for new security technology. The server collects and analyzes relevant industry data to generate a list of optimal partners. Based on user feedback, the suggestions are continuously improved, resulting in more accurate matches.

[0204] An example of a prompt for a generative AI model would be: "In a business matching app, company A is looking for a partner for new security technology. Please suggest natural language processing techniques to gather useful information from publicly available data and understand the company's needs. Also, please provide ideas on how to improve the next suggestion based on user feedback."

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The server retrieves information from public data sources. Input is APIs and website information on the internet, and output is raw data. Python and Beautiful Soup are used for data collection, extracting market data and company information in the security industry through API calls and web scraping.

[0208] Step 2:

[0209] The server preprocesses the acquired raw data. The input is the raw data obtained in step 1, and the output is de-noise-removed and normalized text data. Specifically, it performs operations such as removing unnecessary information using regular expressions and normalizing strings.

[0210] Step 3:

[0211] The server analyzes pre-processed data using natural language processing (NLP) techniques. The input is the normalized text data obtained in step 2, and the output is the analysis results reflecting company needs and market trends. Using NLP libraries such as TensorFlow, it extracts important keywords from the text data and identifies matching candidates that consider synergistic effects between companies.

[0212] Step 4:

[0213] The server analyzes the user's emotions using an emotion analysis engine. The input is user interaction and feedback data, and the output is the analyzed emotional state. An AI model is used to estimate emotions from the user's text and behavior logs, and the matching results are prioritized based on this.

[0214] Step 5:

[0215] The server generates a list of organizational combinations based on the analysis results and sentiment data. The input is the data obtained in steps 3 and 4, and the output is a matching list to be presented to the user. The system derives the optimal combination of companies and proposes new business opportunities.

[0216] Step 6:

[0217] The terminal visually presents the user with a matching list sent from the server, and an AI assistant explains the merits of each proposal. The input is the matching list from the server, and the output is to improve the user's understanding and stimulate their willingness to partner. A voice assistant is used to explain the proposals in an easy-to-understand manner.

[0218] Step 7:

[0219] Users provide feedback on the presented combinations. The input is the user's evaluation and comments, and the output is feedback data received and processed by the server. This feedback is analyzed by the server to improve future suggestions and is also used as training data for the AI ​​model.

[0220] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0221] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0222] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0226] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0227] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0228] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0229] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0230] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0231] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0232] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0233] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0234] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0235] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0236] This invention provides a business matching system for small and medium-sized enterprises, and includes a system for collecting and analyzing information from diverse data sources and effectively matching companies with each other. This system primarily achieves its objectives through the interaction of three parties: a server, terminals, and users.

[0237] First, the server retrieves data from public data sources. This includes social media, industry reports, and publicly available company information. After collecting this information, the server preprocesses the data to remove unwanted characters and noise. This improves the quality of the data.

[0238] Next, the server analyzes the data using natural language processing and data mining techniques. In this analysis phase, the server identifies market trends and customer needs from the collected information and extracts potential matching candidates for companies and products.

[0239] Based on the analysis results, the server evaluates combinations of companies and products. It automatically lists combinations of companies with high synergy potential, increasing the likelihood of successful collaboration.

[0240] Next, the terminal receives a matching list generated from the server and presents it to the user. At this time, the AI ​​agent clearly explains the advantages and feasibility of each combination in the list, supporting the user in making an appropriate choice.

[0241] Users select the most suitable collaboration partner from the presented options and then send their opinions and feedback to the system. This user feedback is collected on the server and used to further improve and optimize the system.

[0242] As a concrete example, suppose a user company is considering expanding into a new field. By using the system, this company can find effective partners in a short period of time and gain the opportunity to maximize synergistic effects.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The server collects necessary information from public data sources. This includes accessing social media APIs, downloading industry reports, and scraping from official company websites. The collected data is stored in storage.

[0246] Step 2:

[0247] The server preprocesses the collected data. Specifically, it removes noise from the data, standardizes case, and normalizes the text. It also imputes missing values ​​and removes duplicate data to prepare the data for analysis.

[0248] Step 3:

[0249] The server uses natural language processing (NLP) to analyze data. It extracts market trends through topic modeling and understands consumer opinions through sentiment analysis. This allows it to identify customer needs and market demands.

[0250] Step 4:

[0251] The server evaluates combinations of companies and products based on the analyzed data. To measure synergy effects, it uses algorithms to calculate similarity scores and predict the likelihood of successful collaboration.

[0252] Step 5:

[0253] Based on the evaluation results, the server lists combinations of companies and generates a matching list. This list is ranked based on synergy effects and feasibility.

[0254] Step 6:

[0255] The terminal presents the user with a matching list received from the server. An AI agent explains the advantages and key points of each suggestion on the list, supporting the user's decision-making.

[0256] Step 7:

[0257] Users select the most suitable collaboration partner from the presented matching list. After selection, users provide feedback to the system, reporting their reasons for selection and details of their preferences.

[0258] Step 8:

[0259] The server analyzes user feedback and uses it to improve the system's evaluation model and filtering algorithms. This will enable more accurate matching in subsequent attempts.

[0260] (Example 1)

[0261] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0262] In today's business environment, companies need to find partners and build collaborative relationships quickly and effectively. However, collecting appropriate information from the vast ocean of data and conducting accurate data analysis requires significant resources, making it particularly difficult for small and medium-sized enterprises (SMEs). Furthermore, the lack of objective indicators for evaluating inter-company combinations and mechanisms for clearly presenting the results hinders optimal decision-making.

[0263] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0264] In this invention, the server includes data collection means for acquiring data from information sources, data preprocessing means for preprocessing the acquired data and removing noise, and data analysis means for analyzing the data using natural language processing and data mining techniques. This enables companies to efficiently collect information and build appropriate and rapid collaborative relationships based on the analysis results.

[0265] "Information sources" refer to external databases and platforms accessible to businesses, including public data and open data.

[0266] "Data acquisition means" refers to the hardware and software functions used to obtain necessary data from information sources.

[0267] "Data preprocessing means" refers to processes and techniques for removing noise from acquired data and processing it into a format suitable for analysis.

[0268] "Natural language processing" refers to the methods and techniques for processing human language using computers, and is used for analyzing text data.

[0269] "Data mining techniques" refer to scientific and statistical methods for extracting useful information and patterns from large amounts of data.

[0270] "Data analysis tools" refer to functions that analyze data using natural language processing and data mining techniques to derive useful insights.

[0271] "Matching generation means" refers to a part of the algorithm or system used to evaluate and generate appropriate combinations of companies and products based on analysis results.

[0272] "Result presentation means" refers to a function that provides the generated matching list and evaluation results to the user in visual or text format.

[0273] "Feedback collection methods" refer to methods or processes for collecting opinions and evaluations from users and incorporating them into further system optimization.

[0274] "Evaluation methods" refer to criteria or algorithms used to assess the synergistic effects of a particular combination of companies.

[0275] This invention is configured as a system that acquires data from information sources and effectively supports business matching between small and medium-sized enterprises. This objective is achieved primarily through the interaction of three parties: a server, a terminal, and a user.

[0276] First, the server has data collection means to obtain the necessary data from information sources. Specifically, it collects data from social media APIs and public websites. During this process, a script using Python is executed periodically to automatically retrieve data. The server preprocesses the retrieved data using the pandas library to remove noise and transform it into an analyzable format.

[0277] Next, the server utilizes natural language processing technology, analyzing text data using the NLTK library. This allows for the extraction of important keywords and the understanding of market trends. Furthermore, the scikit-learn library is used as a data mining technique to extract matching candidates based on the characteristics of each company.

[0278] Based on the analysis results, the server uses a recommendation algorithm to evaluate appropriate combinations and constructs a list using a matching generation mechanism. This matching list includes combinations of companies that maximize synergy effects, thereby increasing the likelihood of successful collaboration.

[0279] The terminal receives a matching list from the server and presents it to the user visually and intuitively via an agent. The interface is designed to be easy for viewers to understand, clearly explaining the details and advantages of each candidate.

[0280] Users refer to the presented matching list and select the most suitable partner candidate. The selection results and feedback are sent to the server via the device and used by the system's feedback collection mechanism to improve the system in the future.

[0281] As a specific example, consider the case where a small and medium-sized enterprise in the food industry is looking for a partner with packaging technology. By inputting the prompt sentence "Please propose partnership candidates for a food company seeking new food packaging technology" into the system, this enterprise can quickly and effectively find suitable candidates through the system. Thus, the system of the present invention enables each enterprise to quickly find an ideal partner and maximize the synergy effect.

[0282] The flow of the specific process in Example 1 will be described using FIG. 11.

[0283] Step 1:

[0284] The server acquires data from the information source. As input, an API key and the URL of the scraping target are provided, and raw text data is obtained as output. Specifically, the server uses a Python script to automatically acquire industry-related information from social media APIs and public databases.

[0285] Step 2:

[0286] The server preprocesses the acquired data. In this step, raw text data is provided as input, and cleaned data is obtained as output. Specifically, the server uses the pandas library to remove unnecessary characters and noise in the data and complete missing values. This improves the quality of the analysis.

[0287] Step 3:

[0288] The server analyzes the preprocessed data. Cleaned data is provided as input, and analysis results are obtained as output. Specifically, the server performs natural language processing using the NLTK library to extract keywords from the text. Also, it applies a machine learning model with the scikit-learn library to analyze market trends.

[0289] Step 4:

[0290] The server generates matching candidates based on the analysis results. The analysis results are given as input, and a list of company and product combinations is obtained as output. Specifically, it runs a recommendation algorithm and automatically lists company combinations that are expected to have synergistic effects. This helps users make quick decisions.

[0291] Step 5:

[0292] The terminal displays a matching list received from the server. It receives a list of company combinations as input and outputs a visually clear display that is easy for the user to understand. Specifically, the terminal uses a GUI to graphically display the advantages and potential of each company, supporting the user in selecting a partner.

[0293] Step 6:

[0294] The user selects an appropriate partner from the presented options and provides feedback. Based on the combination of companies presented as input, the system sends the selection results and feedback as output. Specifically, the user enters selections and comments on the terminal interface, which are collected on the server and used to improve the accuracy of matching in the future.

[0295] (Application Example 1)

[0296] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0297] Traditional business matching systems have faced challenges in quickly finding the optimal combination of companies, and manually searching for the right combination to maximize synergy is time-consuming and costly. Furthermore, they often fail to adequately present crucial information such as the key points and advantages of each combination, making decision-making difficult.

[0298] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0299] In this invention, the server includes information acquisition means, information analysis means, combination generation means, result display means, opinion collection means, and relationship evaluation means. This makes it possible to automatically generate the optimal combination between companies in a short period of time and provide users with a clear explanation of the key points and advantages.

[0300] "Information acquisition means" refers to a system for obtaining data from public information sources.

[0301] An "information analysis tool" is a system for organizing and analyzing acquired data.

[0302] The "combination generation means" is a mechanism that generates a list of optimal combinations of business entities based on the analysis results.

[0303] A "result display means" is a mechanism for presenting the generated list of combinations to the user.

[0304] A "means of gathering opinions" refers to a system for collecting opinions and feedback from users and using them to optimize the system.

[0305] A "relationship evaluation tool" is a system that evaluates the relationships between business entities based on similarity and recommends the optimal combination.

[0306] The system for implementing this invention mainly achieves its purpose through the interaction of three parties: the server, the terminal, and the user. The server uses information acquisition means to collect various data from public information sources. Next, by making full use of information analysis means, after organizing the collected data and removing noise, it analyzes the data. Based on this analysis, the relationship evaluation means for evaluating similarity creates a list of optimal combinations of business entities by the combination generation means.

[0307] The terminal uses result display means to present the combination list sent from the server to the user. The user determines partnership candidates based on the presented information and uses opinion collection means to send feedback to the system. This feedback is used by the server to update the generated AI model and improve the accuracy of the system.

[0308] As a specific example, when small and medium-sized e-commerce operators are considering expanding their businesses into different categories, they can automatically find the most suitable partners from manufacturers in a short period. Such enterprises can choose the most suitable cooperation partners for their own needs through the recommended list generated by the server. An example of a prompt sentence for the generated AI model is "Please teach me a method to provide optimal transaction matching between manufacturers and sellers based on rich data sources."

[0309] The flow of specific processing in Application Example 1 will be described using FIG. 12.

[0310] Step 1:

[0311] The server uses information acquisition means to obtain data from public information sources. At this time, the input is the URL or API of the public information source, and the output is the raw data obtained. The data is stored in the server in JSON or XML format. As a specific operation, the data is downloaded through an HTTP request.

[0312] Step 2:

[0313] The server uses information analysis tools to process the acquired data and remove noise. The input is the raw data acquired in step 1, and the output is the cleaned and processed data. Specifically, unnecessary characters and spaces are removed, and the data is converted into a parseable format.

[0314] Step 3:

[0315] The server uses combination generation methods to evaluate similarity within the prepared data and create a list of optimal combinations of business entities. The input is the prepared data, and the output is a list containing pairs or groups of business entities with high similarity. Specifically, it vectorizes text data using TF-IDF and calculates cosine similarity.

[0316] Step 4:

[0317] The server sends the generated list of combinations to the terminal via a results display mechanism. The input is an optimized list of combinations, and the output is visualized data. Specifically, the list is converted into a user-friendly format (e.g., HTML or JSON).

[0318] Step 5:

[0319] The terminal displays a list of combinations received from the server to the user using a results display mechanism. The input is data received from the server, and the output is data displayed on the user interface. Specifically, the list is displayed visually through a GUI.

[0320] Step 6:

[0321] The user selects a candidate from the presented combinations and inputs feedback into the device using a feedback collection tool. The input consists of the user's selection and opinion, and the output is saved on the device as feedback data. Specifically, the user clicks on an option and enters a comment in a text box.

[0322] Step 7:

[0323] The terminal sends collected feedback to the server to help optimize the system. The input is user feedback data, and the output is structured data sent to the server. Specifically, the feedback is stored in a database and used as data to train the generated AI model in preparation for the next model update.

[0324] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0325] This invention is a system that enables effective business matching for companies. In addition to collecting, analyzing, and generating matches from public data sources, it incorporates an emotion engine that recognizes and analyzes user emotions. This system aims to improve the user experience through collaboration among the server, terminal, and user.

[0326] First, the server collects rich information from public data sources. Data collection includes API calls, web scraping, and database access. The collected information is preprocessed to remove unnecessary noise and normalize the text before being ready for analysis.

[0327] Next, the server utilizes advanced natural language processing (NLP) and data analysis techniques to identify market trends and customer preferences. The analyzed data is then used to calculate potential matches between companies, taking synergy effects into consideration, and a list of optimal combinations is generated.

[0328] Furthermore, the server incorporates an emotion engine that recognizes the user's emotional state from their interactions and feedback. This emotion analysis is used to adjust the content and presentation method of the matching list presented to the user, contributing to increased user satisfaction.

[0329] The device receives a matching list generated by the server and presents it visually to the user. An AI agent explains the merits of each combination to the user, and the suggestions may be modified based on sentiment data.

[0330] For example, if the user is a company representative seeking new collaborations, the emotion engine captures the user's interests and satisfaction levels in real time, prioritizing the display of combinations that interest them. In this way, users can obtain the results they expect more quickly and accurately.

[0331] Ultimately, the user selects the partner they deem best and provides feedback on their choice to the system. The server analyzes this feedback and sentiment data to improve the system's overall algorithm and enhance matching accuracy in the future.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] The server retrieves information from public data sources. This involves sending requests through social media APIs, accessing corporate databases, and utilizing website scraping techniques. The retrieved data is temporarily stored in storage.

[0335] Step 2:

[0336] The server preprocesses the collected data. Specifically, it removes noise, normalizes the data, and imputes missing values ​​to maintain data integrity. It also performs duplicate removal and categorization.

[0337] Step 3:

[0338] The server analyzes pre-processed data. Using natural language processing techniques, it extracts customer needs and market trends from text data. Furthermore, it uses data mining techniques to find patterns and identify potential business opportunities.

[0339] Step 4:

[0340] The server evaluates combinations of companies and products based on the analysis results and generates a matching list based on synergy effects and likelihood of success. This uses algorithms to analyze similarities and differences between companies and derive the most effective combinations.

[0341] Step 5:

[0342] The server activates the emotion engine and analyzes the user's emotional state from past choices and interaction data. This allows it to determine which combinations the user is favorably disposed towards and reflect this in the matching list.

[0343] Step 6:

[0344] The device presents the generated matching list to the user. At this point, the AI ​​agent explains the details of each suggestion and highlights suggestions that the user may be interested in based on the results of the emotion engine.

[0345] Step 7:

[0346] Users select a suitable collaboration partner from the presented proposals. They can make a satisfactory choice after considering the advantages and disadvantages.

[0347] Step 8:

[0348] Users enter and submit feedback to the system. This feedback includes reasons for their selection and any additional comments.

[0349] Step 9:

[0350] The server analyzes feedback and sentiment data received from users. This allows the system's algorithms and suggestions to be improved, leading to better matching accuracy in the future.

[0351] (Example 2)

[0352] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0353] In today's business environment, effective matching between companies is crucial. However, traditional systems struggle to respond quickly to market changes and diverse customer needs, and are particularly inadequate at providing flexible proposals that cater to user emotions. Therefore, there is a need for a system that provides potential partners that meet user expectations and improves the user experience.

[0354] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0355] In this invention, the server includes information gathering means, information analysis means, combination generation means, sentiment analysis means, result display means, and feedback collection means. This enables the generation of appropriate combinations of companies based on public information sources and flexible suggestions based on the user's sentiment. Furthermore, it is possible to improve the accuracy of the system by utilizing the collected feedback.

[0356] An "information gathering tool" is a mechanism that has the function of automatically acquiring necessary information from public information sources.

[0357] An "information analysis tool" is a mechanism for transforming acquired information into a useful form by preprocessing and analyzing it.

[0358] A "combination generation mechanism" is a system that identifies and proposes optimal interrelationships and partnership candidates from data based on analysis results.

[0359] An "emotion analysis tool" is a mechanism that recognizes the user's emotional state from their interactions and input data, and processes that information.

[0360] A "result display means" is a mechanism that has the function of visually presenting the generated combinations and suggestions to the user.

[0361] A "feedback collection mechanism" is a system for collecting user feedback and usage data and using it to improve the system.

[0362] "Synergy effect" is a term that refers to additional benefits obtained through partnerships between companies that would not be achievable individually.

[0363] An "explanatory mechanism" is a system designed to provide users with an easily understandable overview of the key points and benefits of the generated suggestions and combinations.

[0364] To implement this invention, a server plays a central role. The server collects information from public sources using information gathering means. This process includes specific scripts for making API calls and performing web scraping. The collected data is preprocessed and analyzed through information analysis means. Specifically, the Python NLTK library is used to perform data denoising and natural language processing.

[0365] Next, the server uses a combination generation mechanism to generate the optimal combination of business partners based on the analyzed data. At this stage, machine learning algorithms are used to identify candidates while considering the synergistic effects between companies.

[0366] Furthermore, the server incorporates emotion analysis capabilities to recognize emotional data from user feedback and interactions. For example, it analyzes input data obtained from the user's device to determine whether there are many positive emotional expressions.

[0367] The terminal visually displays information received from the server. The user interface is designed to be simple and intuitive, with an AI agent clearly guiding the user through the advantages of each combination. This agent enhances satisfaction by adjusting the presented suggestions based on the user's emotional state.

[0368] Users provide feedback by reviewing the presented suggestions and selecting the optimal combination of partners. This user feedback is collected on a server and used to improve the system's algorithms through feedback collection mechanisms, leading to increased accuracy in future iterations.

[0369] For example, if a user is a sales representative seeking new collaborations, the emotion engine captures the user's interests and satisfaction levels in real time, prioritizing and displaying the most suitable matchups. In this way, users can obtain their desired results more quickly and accurately.

[0370] Examples of prompt statements for a generative AI model are shown below.

[0371] "Please find new collaboration partners for my company, prioritizing companies that focus particularly on sustainable business practices."

[0372] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0373] Step 1:

[0374] The server uses data gathering methods to obtain data from public sources. This process automatically collects the necessary information using data requests from APIs and web scraping. Inputs include specific URLs and API endpoints, and the output is obtained as a structured dataset.

[0375] Step 2:

[0376] The server uses information analysis tools to preprocess and analyze the collected data. Here, the Python Pandas library is used to denoise the data and normalize the text. It accepts raw data as input and generates a clean, analyzable dataset as output.

[0377] Step 3:

[0378] The server uses a combination generation mechanism to calculate appropriate business partner combinations from the analyzed data. Specifically, it applies similarity calculations and clustering algorithms to select the optimal combination candidates. The input is the analyzed data, and the output is a list of candidate partners.

[0379] Step 4:

[0380] The server uses sentiment analysis techniques to recognize emotions from user feedback and interaction data. It calculates an emotion score using natural language processing methods and identifies positive or negative emotions. It takes user feedback messages as input and outputs the results of the sentiment analysis.

[0381] Step 5:

[0382] The terminal receives a list of combinations generated by the server and presents it to the user via a results display device. An AI agent is activated and explains the advantages of the combinations on the user interface. The input is the list of combinations from the server, and the output is the information displayed on the user's screen.

[0383] Step 6:

[0384] The user reviews the presented combinations and provides feedback. This feedback is sent from the terminal to the server and stored in a database by the feedback collection mechanism. The input is user feedback data, and the output is data for improvement that is accumulated in the system.

[0385] (Application Example 2)

[0386] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0387] To achieve effective business matching between companies, it is crucial not only to optimize the combinations of companies but also to enhance user satisfaction. However, conventional systems have struggled to consider user emotions and interests when presenting company combinations, resulting in a limited user experience. Furthermore, methods for effectively incorporating feedback and continuously improving the system have not been established. As a result, there is a challenge in obtaining the flexible and accurate matching results that users expect.

[0388] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0389] In this invention, the server includes data collection means for acquiring information from public data sources, data analysis means for processing and analyzing the acquired information, matching generation means for generating a list of organizational combinations based on the analysis results, emotion analysis means for analyzing the user's emotions using an emotion analysis engine, adjustment means for adjusting the presentation of results based on the emotion analysis, and feedback collection means for collecting feedback from users and reflecting it in improving the system. This makes it possible to provide flexible matching results that reflect the user's emotional state, increase user satisfaction, and continuously improve the system.

[0390] "Data collection means" refers to devices and methods for collecting information from public data sources.

[0391] "Data analysis means" refers to devices and methods for processing and analyzing collected information.

[0392] A "matching generation means" is a device or method for generating a list of organizational combinations based on analysis results.

[0393] "Result presentation means" refers to a device or method for presenting the generated combination list to the user visually or audibly.

[0394] "Emotional analysis means" refers to devices or methods for analyzing a user's emotional state using an emotional analysis engine.

[0395] "Adjustment means" refers to devices or methods for optimally adjusting the results presented based on emotion analysis.

[0396] "Feedback collection methods" refer to devices or methods for collecting feedback from users and incorporating it into system improvements.

[0397] This invention is a system that enables effective business matching between companies, and is realized through the collaboration of three parties: a server, a terminal, and a user.

[0398] The server first collects information from public data sources. Specifically, it obtains market data and company information from the internet through API calls and web scraping. This collection process uses Python and the Beautiful Soup library.

[0399] Next, the server preprocesses the collected information and performs data analysis using natural language processing. Preprocessing involves removing noise and normalizing the text. In this step, natural language processing tools such as TensorFlow are used to analyze the company's needs and market trends.

[0400] Furthermore, the server uses an emotion analysis engine to analyze emotions from user feedback and interactions. This allows for prioritization and adjustment of the generated matching list. The adjusted results are then presented to the user. This process makes it possible to prioritize and present combinations that the user is more likely to be interested in.

[0401] The device visually displays a matching list sent from the server to the user, and an AI assistant provides voice explanations of the merits of each suggestion. This allows the user to easily understand the characteristics of the suggested companies.

[0402] Users provide feedback on the presented combinations. This feedback is collected by the server and used, along with sentiment analysis results, to improve the algorithm. This makes it possible to improve the accuracy of matching in the future.

[0403] As a concrete example, suppose a user is looking for a partner for new security technology. The server collects and analyzes relevant industry data to generate a list of optimal partners. Based on user feedback, the suggestions are continuously improved, resulting in more accurate matches.

[0404] An example of a prompt for a generative AI model would be: "In a business matching app, company A is looking for a partner for new security technology. Please suggest natural language processing techniques to gather useful information from publicly available data and understand the company's needs. Also, please provide ideas on how to improve the next suggestion based on user feedback."

[0405] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0406] Step 1:

[0407] The server retrieves information from public data sources. Input is APIs and website information on the internet, and output is raw data. Python and Beautiful Soup are used for data collection, extracting market data and company information in the security industry through API calls and web scraping.

[0408] Step 2:

[0409] The server preprocesses the acquired raw data. The input is the raw data obtained in step 1, and the output is de-noise-removed and normalized text data. Specifically, it performs operations such as removing unnecessary information using regular expressions and normalizing strings.

[0410] Step 3:

[0411] The server analyzes pre-processed data using natural language processing (NLP) techniques. The input is the normalized text data obtained in step 2, and the output is the analysis results reflecting company needs and market trends. Using NLP libraries such as TensorFlow, it extracts important keywords from the text data and identifies matching candidates that consider synergistic effects between companies.

[0412] Step 4:

[0413] The server analyzes the user's emotions using an emotion analysis engine. The input is user interaction and feedback data, and the output is the analyzed emotional state. An AI model is used to estimate emotions from the user's text and behavior logs, and the matching results are prioritized based on this.

[0414] Step 5:

[0415] The server generates a list of organizational combinations based on the analysis results and sentiment data. The input is the data obtained in steps 3 and 4, and the output is a matching list to be presented to the user. The system derives the optimal combination of companies and proposes new business opportunities.

[0416] Step 6:

[0417] The terminal visually presents the user with a matching list sent from the server, and an AI assistant explains the merits of each proposal. The input is the matching list from the server, and the output is to improve the user's understanding and stimulate their willingness to partner. A voice assistant is used to explain the proposals in an easy-to-understand manner.

[0418] Step 7:

[0419] Users provide feedback on the presented combinations. The input is the user's evaluation and comments, and the output is feedback data received and processed by the server. This feedback is analyzed by the server to improve future suggestions and is also used as training data for the AI ​​model.

[0420] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0421] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0422] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0423] [Third Embodiment]

[0424] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0425] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0426] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0427] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0428] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0429] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0430] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0431] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0432] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0433] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0434] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0435] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0436] This invention provides a business matching system for small and medium-sized enterprises, and includes a system for collecting and analyzing information from diverse data sources and effectively matching companies with each other. This system primarily achieves its objectives through the interaction of three parties: a server, terminals, and users.

[0437] First, the server retrieves data from public data sources. This includes social media, industry reports, and publicly available company information. After collecting this information, the server preprocesses the data to remove unwanted characters and noise. This improves the quality of the data.

[0438] Next, the server analyzes the data using natural language processing and data mining techniques. In this analysis phase, the server identifies market trends and customer needs from the collected information and extracts potential matching candidates for companies and products.

[0439] Based on the analysis results, the server evaluates combinations of companies and products. It automatically lists combinations of companies with high synergy potential, increasing the likelihood of successful collaboration.

[0440] Next, the terminal receives a matching list generated from the server and presents it to the user. At this time, the AI ​​agent clearly explains the advantages and feasibility of each combination in the list, supporting the user in making an appropriate choice.

[0441] Users select the most suitable collaboration partner from the presented options and then send their opinions and feedback to the system. This user feedback is collected on the server and used to further improve and optimize the system.

[0442] As a concrete example, suppose a user company is considering expanding into a new field. By using the system, this company can find effective partners in a short period of time and gain the opportunity to maximize synergistic effects.

[0443] The following describes the processing flow.

[0444] Step 1:

[0445] The server collects necessary information from public data sources. This includes accessing social media APIs, downloading industry reports, and scraping from official company websites. The collected data is stored in storage.

[0446] Step 2:

[0447] The server preprocesses the collected data. Specifically, it removes noise from the data, standardizes case, and normalizes the text. It also imputes missing values ​​and removes duplicate data to prepare the data for analysis.

[0448] Step 3:

[0449] The server uses natural language processing (NLP) to analyze data. It extracts market trends through topic modeling and understands consumer opinions through sentiment analysis. This allows it to identify customer needs and market demands.

[0450] Step 4:

[0451] The server evaluates combinations of companies and products based on the analyzed data. To measure synergy effects, it uses algorithms to calculate similarity scores and predict the likelihood of successful collaboration.

[0452] Step 5:

[0453] Based on the evaluation results, the server lists combinations of companies and generates a matching list. This list is ranked based on synergy effects and feasibility.

[0454] Step 6:

[0455] The terminal presents the user with a matching list received from the server. An AI agent explains the advantages and key points of each suggestion on the list, supporting the user's decision-making.

[0456] Step 7:

[0457] Users select the most suitable collaboration partner from the presented matching list. After selection, users provide feedback to the system, reporting their reasons for selection and details of their preferences.

[0458] Step 8:

[0459] The server analyzes user feedback and uses it to improve the system's evaluation model and filtering algorithms. This will enable more accurate matching in subsequent attempts.

[0460] (Example 1)

[0461] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0462] In today's business environment, companies need to find partners and build collaborative relationships quickly and effectively. However, collecting appropriate information from the vast ocean of data and conducting accurate data analysis requires significant resources, making it particularly difficult for small and medium-sized enterprises (SMEs). Furthermore, the lack of objective indicators for evaluating inter-company combinations and mechanisms for clearly presenting the results hinders optimal decision-making.

[0463] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0464] In this invention, the server includes data collection means for acquiring data from information sources, data preprocessing means for preprocessing the acquired data and removing noise, and data analysis means for analyzing the data using natural language processing and data mining techniques. This enables companies to efficiently collect information and build appropriate and rapid collaborative relationships based on the analysis results.

[0465] "Information sources" refer to external databases and platforms accessible to businesses, including public data and open data.

[0466] "Data acquisition means" refers to the hardware and software functions used to obtain necessary data from information sources.

[0467] "Data preprocessing means" refers to processes and techniques for removing noise from acquired data and processing it into a format suitable for analysis.

[0468] "Natural language processing" refers to the methods and techniques for processing human language using computers, and is used for analyzing text data.

[0469] "Data mining techniques" refer to scientific and statistical methods for extracting useful information and patterns from large amounts of data.

[0470] "Data analysis tools" refer to functions that analyze data using natural language processing and data mining techniques to derive useful insights.

[0471] "Matching generation means" refers to a part of the algorithm or system used to evaluate and generate appropriate combinations of companies and products based on analysis results.

[0472] "Result presentation means" refers to a function that provides the generated matching list and evaluation results to the user in visual or text format.

[0473] "Feedback collection methods" refer to methods or processes for collecting opinions and evaluations from users and incorporating them into further system optimization.

[0474] "Evaluation methods" refer to criteria or algorithms used to assess the synergistic effects of a particular combination of companies.

[0475] This invention is configured as a system that acquires data from information sources and effectively supports business matching between small and medium-sized enterprises. This objective is achieved primarily through the interaction of three parties: a server, a terminal, and a user.

[0476] First, the server has data collection means to obtain the necessary data from information sources. Specifically, it collects data from social media APIs and public websites. During this process, a script using Python is executed periodically to automatically retrieve data. The server preprocesses the retrieved data using the pandas library to remove noise and transform it into an analyzable format.

[0477] Next, the server utilizes natural language processing technology, analyzing text data using the NLTK library. This allows for the extraction of important keywords and the understanding of market trends. Furthermore, the scikit-learn library is used as a data mining technique to extract matching candidates based on the characteristics of each company.

[0478] Based on the analysis results, the server uses a recommendation algorithm to evaluate appropriate combinations and constructs a list using a matching generation mechanism. This matching list includes combinations of companies that maximize synergy effects, thereby increasing the likelihood of successful collaboration.

[0479] The terminal receives a matching list from the server and presents it to the user visually and intuitively via an agent. The interface is designed to be easy for viewers to understand, clearly explaining the details and advantages of each candidate.

[0480] Users refer to the presented matching list and select the most suitable partner candidate. The selection results and feedback are sent to the server via the device and used by the system's feedback collection mechanism to improve the system in the future.

[0481] As a concrete example, consider a case where a small or medium-sized enterprise in the food industry is looking for a partner with packaging technology. By entering the prompt message "Please suggest potential partner candidates for a food company seeking new food packaging technology," this company can quickly and effectively find suitable candidates through the system. In this way, the system of the present invention enables each company to quickly find its ideal partner and maximize synergistic effects.

[0482] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0483] Step 1:

[0484] The server retrieves data from the information source. It takes an API key or the URL to be scraped as input, and the output is raw text data. Specifically, the server uses a Python script to automatically retrieve industry-related information from social media APIs and public databases.

[0485] Step 2:

[0486] The server preprocesses the acquired data. In this step, raw text data is given as input, and cleaned data is produced as output. Specifically, the server uses the pandas library to remove unwanted characters and noise from the data and impute missing values. This improves the quality of the analysis.

[0487] Step 3:

[0488] The server analyzes pre-processed data. Cleaned data is given as input, and the analysis results are obtained as output. Specifically, the server uses the NLTK library to perform natural language processing and extract keywords from the text. It also applies a machine learning model using the scikit-learn library to analyze market trends.

[0489] Step 4:

[0490] The server generates matching candidates based on the analysis results. The analysis results are given as input, and a list of company and product combinations is obtained as output. Specifically, it runs a recommendation algorithm and automatically lists company combinations that are expected to have synergistic effects. This helps users make quick decisions.

[0491] Step 5:

[0492] The terminal displays a matching list received from the server. It receives a list of company combinations as input and outputs a visually clear display that is easy for the user to understand. Specifically, the terminal uses a GUI to graphically display the advantages and potential of each company, supporting the user in selecting a partner.

[0493] Step 6:

[0494] The user selects an appropriate partner from the presented options and provides feedback. Based on the combination of companies presented as input, the system sends the selection results and feedback as output. Specifically, the user enters selections and comments on the terminal interface, which are collected on the server and used to improve the accuracy of matching in the future.

[0495] (Application Example 1)

[0496] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0497] Traditional business matching systems have faced challenges in quickly finding the optimal combination of companies, and manually searching for the right combination to maximize synergy is time-consuming and costly. Furthermore, they often fail to adequately present crucial information such as the key points and advantages of each combination, making decision-making difficult.

[0498] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0499] In this invention, the server includes information acquisition means, information analysis means, combination generation means, result display means, opinion collection means, and relationship evaluation means. This makes it possible to automatically generate the optimal combination between companies in a short period of time and provide users with a clear explanation of the key points and advantages.

[0500] "Information acquisition means" refers to a system for obtaining data from public information sources.

[0501] An "information analysis tool" is a system for organizing and analyzing acquired data.

[0502] The "combination generation means" is a mechanism that generates a list of optimal combinations of business entities based on the analysis results.

[0503] A "result display means" is a mechanism for presenting the generated list of combinations to the user.

[0504] A "means of gathering opinions" refers to a system for collecting opinions and feedback from users and using them to optimize the system.

[0505] A "relationship evaluation tool" is a system that evaluates the relationships between business entities based on similarity and recommends the optimal combination.

[0506] The system for implementing this invention achieves its objectives primarily through the interaction of three parties: a server, a terminal, and a user. The server collects various data from public information sources using information acquisition means. Next, it uses information analysis means to organize the collected data, remove noise, and then analyze the data. Based on this analysis, a relationship evaluation means evaluates similarity, and a combination generation means creates a list of optimal combinations of business entities.

[0507] The terminal uses a results display mechanism to present the user with a list of combinations sent from the server. Based on the presented information, the user decides on a partnership candidate and sends feedback to the system using a feedback collection mechanism. This feedback is used by the server to update the generated AI model and improve the system's accuracy.

[0508] For example, if a small or medium-sized e-commerce business is considering expanding into a different category, it can automatically find the best partner from manufacturers in a short period of time. Such companies can select the partner that best suits their needs through a recommendation list generated by the server. An example of a prompt to the generating AI model would be, "How can you provide optimal trade matching between manufacturers and distributors based on a rich data source?"

[0509] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0510] Step 1:

[0511] The server retrieves data from public information sources using information acquisition methods. In this process, the input is the URL or API of the public information source, and the output is the retrieved raw data. The data is stored on the server in JSON or XML format. Specifically, the data is downloaded via HTTP requests.

[0512] Step 2:

[0513] The server uses information analysis tools to process the acquired data and remove noise. The input is the raw data acquired in step 1, and the output is the cleaned and processed data. Specifically, unnecessary characters and spaces are removed, and the data is converted into a parseable format.

[0514] Step 3:

[0515] The server uses combination generation methods to evaluate similarity within the prepared data and create a list of optimal combinations of business entities. The input is the prepared data, and the output is a list containing pairs or groups of business entities with high similarity. Specifically, it vectorizes text data using TF-IDF and calculates cosine similarity.

[0516] Step 4:

[0517] The server sends the generated list of combinations to the terminal via a results display mechanism. The input is an optimized list of combinations, and the output is visualized data. Specifically, the list is converted into a user-friendly format (e.g., HTML or JSON).

[0518] Step 5:

[0519] The terminal displays a list of combinations received from the server to the user using a results display mechanism. The input is data received from the server, and the output is data displayed on the user interface. Specifically, the list is displayed visually through a GUI.

[0520] Step 6:

[0521] The user selects a candidate from the presented combinations and inputs feedback into the device using a feedback collection tool. The input consists of the user's selection and opinion, and the output is saved on the device as feedback data. Specifically, the user clicks on an option and enters a comment in a text box.

[0522] Step 7:

[0523] The terminal sends collected feedback to the server to help optimize the system. The input is user feedback data, and the output is structured data sent to the server. Specifically, the feedback is stored in a database and used as data to train the generated AI model in preparation for the next model update.

[0524] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0525] This invention is a system that enables effective business matching for companies. In addition to collecting, analyzing, and generating matches from public data sources, it incorporates an emotion engine that recognizes and analyzes user emotions. This system aims to improve the user experience through collaboration among the server, terminal, and user.

[0526] First, the server collects rich information from public data sources. Data collection includes API calls, web scraping, and database access. The collected information is preprocessed to remove unnecessary noise and normalize the text before being ready for analysis.

[0527] Next, the server utilizes advanced natural language processing (NLP) and data analysis techniques to identify market trends and customer preferences. The analyzed data is then used to calculate potential matches between companies, taking synergy effects into consideration, and a list of optimal combinations is generated.

[0528] Furthermore, the server incorporates an emotion engine that recognizes the user's emotional state from their interactions and feedback. This emotion analysis is used to adjust the content and presentation method of the matching list presented to the user, contributing to increased user satisfaction.

[0529] The device receives a matching list generated by the server and presents it visually to the user. An AI agent explains the merits of each combination to the user, and the suggestions may be modified based on sentiment data.

[0530] For example, if the user is a company representative seeking new collaborations, the emotion engine captures the user's interests and satisfaction levels in real time, prioritizing the display of combinations that interest them. In this way, users can obtain the results they expect more quickly and accurately.

[0531] Ultimately, the user selects the partner they deem best and provides feedback on their choice to the system. The server analyzes this feedback and sentiment data to improve the system's overall algorithm and enhance matching accuracy in the future.

[0532] The following describes the processing flow.

[0533] Step 1:

[0534] The server retrieves information from public data sources. This involves sending requests through social media APIs, accessing corporate databases, and utilizing website scraping techniques. The retrieved data is temporarily stored in storage.

[0535] Step 2:

[0536] The server preprocesses the collected data. Specifically, it removes noise, normalizes the data, and imputes missing values ​​to maintain data integrity. It also performs duplicate removal and categorization.

[0537] Step 3:

[0538] The server analyzes pre-processed data. Using natural language processing techniques, it extracts customer needs and market trends from text data. Furthermore, it uses data mining techniques to find patterns and identify potential business opportunities.

[0539] Step 4:

[0540] The server evaluates combinations of companies and products based on the analysis results and generates a matching list based on synergy effects and likelihood of success. This uses algorithms to analyze similarities and differences between companies and derive the most effective combinations.

[0541] Step 5:

[0542] The server activates the emotion engine and analyzes the user's emotional state from past choices and interaction data. This allows it to determine which combinations the user is favorably disposed towards and reflect this in the matching list.

[0543] Step 6:

[0544] The device presents the generated matching list to the user. At this point, the AI ​​agent explains the details of each suggestion and highlights suggestions that the user may be interested in based on the results of the emotion engine.

[0545] Step 7:

[0546] Users select a suitable collaboration partner from the presented proposals. They can make a satisfactory choice after considering the advantages and disadvantages.

[0547] Step 8:

[0548] Users enter and submit feedback to the system. This feedback includes reasons for their selection and any additional comments.

[0549] Step 9:

[0550] The server analyzes feedback and sentiment data received from users. This allows the system's algorithms and suggestions to be improved, leading to better matching accuracy in the future.

[0551] (Example 2)

[0552] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0553] In today's business environment, effective matching between companies is crucial. However, traditional systems struggle to respond quickly to market changes and diverse customer needs, and are particularly inadequate at providing flexible proposals that cater to user emotions. Therefore, there is a need for a system that provides potential partners that meet user expectations and improves the user experience.

[0554] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0555] In this invention, the server includes information gathering means, information analysis means, combination generation means, sentiment analysis means, result display means, and feedback collection means. This enables the generation of appropriate combinations of companies based on public information sources and flexible suggestions based on the user's sentiment. Furthermore, it is possible to improve the accuracy of the system by utilizing the collected feedback.

[0556] An "information gathering tool" is a mechanism that has the function of automatically acquiring necessary information from public information sources.

[0557] An "information analysis tool" is a mechanism for transforming acquired information into a useful form by preprocessing and analyzing it.

[0558] A "combination generation mechanism" is a system that identifies and proposes optimal interrelationships and partnership candidates from data based on analysis results.

[0559] An "emotion analysis tool" is a mechanism that recognizes the user's emotional state from their interactions and input data, and processes that information.

[0560] A "result display means" is a mechanism that has the function of visually presenting the generated combinations and suggestions to the user.

[0561] A "feedback collection mechanism" is a system for collecting user feedback and usage data and using it to improve the system.

[0562] "Synergy effect" is a term that refers to additional benefits obtained through partnerships between companies that would not be achievable individually.

[0563] An "explanatory mechanism" is a system designed to provide users with an easily understandable overview of the key points and benefits of the generated suggestions and combinations.

[0564] To implement this invention, a server plays a central role. The server collects information from public sources using information gathering means. This process includes specific scripts for making API calls and performing web scraping. The collected data is preprocessed and analyzed through information analysis means. Specifically, the Python NLTK library is used to perform data denoising and natural language processing.

[0565] Next, the server uses a combination generation mechanism to generate the optimal combination of business partners based on the analyzed data. At this stage, machine learning algorithms are used to identify candidates while considering the synergistic effects between companies.

[0566] Furthermore, the server incorporates emotion analysis capabilities to recognize emotional data from user feedback and interactions. For example, it analyzes input data obtained from the user's device to determine whether there are many positive emotional expressions.

[0567] The terminal visually displays information received from the server. The user interface is designed to be simple and intuitive, with an AI agent clearly guiding the user through the advantages of each combination. This agent enhances satisfaction by adjusting the presented suggestions based on the user's emotional state.

[0568] Users provide feedback by reviewing the presented suggestions and selecting the optimal combination of partners. This user feedback is collected on a server and used to improve the system's algorithms through feedback collection mechanisms, leading to increased accuracy in future iterations.

[0569] For example, if a user is a sales representative seeking new collaborations, the emotion engine captures the user's interests and satisfaction levels in real time, prioritizing and displaying the most suitable matchups. In this way, users can obtain their desired results more quickly and accurately.

[0570] Examples of prompt statements for a generative AI model are shown below.

[0571] "Please find new collaboration partners for my company, prioritizing companies that focus particularly on sustainable business practices."

[0572] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0573] Step 1:

[0574] The server uses data gathering methods to obtain data from public sources. This process automatically collects the necessary information using data requests from APIs and web scraping. Inputs include specific URLs and API endpoints, and the output is obtained as a structured dataset.

[0575] Step 2:

[0576] The server uses information analysis tools to preprocess and analyze the collected data. Here, the Python Pandas library is used to denoise the data and normalize the text. It accepts raw data as input and generates a clean, analyzable dataset as output.

[0577] Step 3:

[0578] The server uses a combination generation mechanism to calculate appropriate business partner combinations from the analyzed data. Specifically, it applies similarity calculations and clustering algorithms to select the optimal combination candidates. The input is the analyzed data, and the output is a list of candidate partners.

[0579] Step 4:

[0580] The server uses sentiment analysis techniques to recognize emotions from user feedback and interaction data. It calculates an emotion score using natural language processing methods and identifies positive or negative emotions. It takes user feedback messages as input and outputs the results of the sentiment analysis.

[0581] Step 5:

[0582] The terminal receives a list of combinations generated by the server and presents it to the user via a results display device. An AI agent is activated and explains the advantages of the combinations on the user interface. The input is the list of combinations from the server, and the output is the information displayed on the user's screen.

[0583] Step 6:

[0584] The user reviews the presented combinations and provides feedback. This feedback is sent from the terminal to the server and stored in a database by the feedback collection mechanism. The input is user feedback data, and the output is data for improvement that is accumulated in the system.

[0585] (Application Example 2)

[0586] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0587] To achieve effective business matching between companies, it is crucial not only to optimize the combinations of companies but also to enhance user satisfaction. However, conventional systems have struggled to consider user emotions and interests when presenting company combinations, resulting in a limited user experience. Furthermore, methods for effectively incorporating feedback and continuously improving the system have not been established. As a result, there is a challenge in obtaining the flexible and accurate matching results that users expect.

[0588] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0589] In this invention, the server includes data collection means for acquiring information from public data sources, data analysis means for processing and analyzing the acquired information, matching generation means for generating a list of organizational combinations based on the analysis results, emotion analysis means for analyzing the user's emotions using an emotion analysis engine, adjustment means for adjusting the presentation of results based on the emotion analysis, and feedback collection means for collecting feedback from users and reflecting it in improving the system. This makes it possible to provide flexible matching results that reflect the user's emotional state, increase user satisfaction, and continuously improve the system.

[0590] "Data collection means" refers to devices and methods for collecting information from public data sources.

[0591] "Data analysis means" refers to devices and methods for processing and analyzing collected information.

[0592] A "matching generation means" is a device or method for generating a list of organizational combinations based on analysis results.

[0593] "Result presentation means" refers to a device or method for presenting the generated combination list to the user visually or audibly.

[0594] "Emotional analysis means" refers to devices or methods for analyzing a user's emotional state using an emotional analysis engine.

[0595] "Adjustment means" refers to devices or methods for optimally adjusting the results presented based on emotion analysis.

[0596] "Feedback collection methods" refer to devices or methods for collecting feedback from users and incorporating it into system improvements.

[0597] This invention is a system that enables effective business matching between companies, and is realized through the collaboration of three parties: a server, a terminal, and a user.

[0598] The server first collects information from public data sources. Specifically, it obtains market data and company information from the internet through API calls and web scraping. This collection process uses Python and the Beautiful Soup library.

[0599] Next, the server preprocesses the collected information and performs data analysis using natural language processing. Preprocessing involves removing noise and normalizing the text. In this step, natural language processing tools such as TensorFlow are used to analyze the company's needs and market trends.

[0600] Furthermore, the server uses an emotion analysis engine to analyze emotions from user feedback and interactions. This allows for prioritization and adjustment of the generated matching list. The adjusted results are then presented to the user. This process makes it possible to prioritize and present combinations that the user is more likely to be interested in.

[0601] The device visually displays a matching list sent from the server to the user, and an AI assistant provides voice explanations of the merits of each suggestion. This allows the user to easily understand the characteristics of the suggested companies.

[0602] Users provide feedback on the presented combinations. This feedback is collected by the server and used, along with sentiment analysis results, to improve the algorithm. This makes it possible to improve the accuracy of matching in the future.

[0603] As a concrete example, suppose a user is looking for a partner for new security technology. The server collects and analyzes relevant industry data to generate a list of optimal partners. Based on user feedback, the suggestions are continuously improved, resulting in more accurate matches.

[0604] An example of a prompt for a generative AI model would be: "In a business matching app, company A is looking for a partner for new security technology. Please suggest natural language processing techniques to gather useful information from publicly available data and understand the company's needs. Also, please provide ideas on how to improve the next suggestion based on user feedback."

[0605] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0606] Step 1:

[0607] The server retrieves information from public data sources. Input is APIs and website information on the internet, and output is raw data. Python and Beautiful Soup are used for data collection, extracting market data and company information in the security industry through API calls and web scraping.

[0608] Step 2:

[0609] The server preprocesses the acquired raw data. The input is the raw data obtained in step 1, and the output is de-noise-removed and normalized text data. Specifically, it performs operations such as removing unnecessary information using regular expressions and normalizing strings.

[0610] Step 3:

[0611] The server analyzes pre-processed data using natural language processing (NLP) techniques. The input is the normalized text data obtained in step 2, and the output is the analysis results reflecting company needs and market trends. Using NLP libraries such as TensorFlow, it extracts important keywords from the text data and identifies matching candidates that consider synergistic effects between companies.

[0612] Step 4:

[0613] The server analyzes the user's emotions using an emotion analysis engine. The input is user interaction and feedback data, and the output is the analyzed emotional state. An AI model is used to estimate emotions from the user's text and behavior logs, and the matching results are prioritized based on this.

[0614] Step 5:

[0615] The server generates a list of organizational combinations based on the analysis results and sentiment data. The input is the data obtained in steps 3 and 4, and the output is a matching list to be presented to the user. The system derives the optimal combination of companies and proposes new business opportunities.

[0616] Step 6:

[0617] The terminal visually presents the user with a matching list sent from the server, and an AI assistant explains the merits of each proposal. The input is the matching list from the server, and the output is to improve the user's understanding and stimulate their willingness to partner. A voice assistant is used to explain the proposals in an easy-to-understand manner.

[0618] Step 7:

[0619] Users provide feedback on the presented combinations. The input is the user's evaluation and comments, and the output is feedback data received and processed by the server. This feedback is analyzed by the server to improve future suggestions and is also used as training data for the AI ​​model.

[0620] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0621] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0622] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0623] [Fourth Embodiment]

[0624] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0625] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0626] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0627] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0628] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0629] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0630] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0631] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0632] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0633] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0634] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0635] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0636] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0637] This invention provides a business matching system for small and medium-sized enterprises, and includes a system for collecting and analyzing information from diverse data sources and effectively matching companies with each other. This system primarily achieves its objectives through the interaction of three parties: a server, terminals, and users.

[0638] First, the server retrieves data from public data sources. This includes social media, industry reports, and publicly available company information. After collecting this information, the server preprocesses the data to remove unwanted characters and noise. This improves the quality of the data.

[0639] Next, the server analyzes the data using natural language processing and data mining techniques. In this analysis phase, the server identifies market trends and customer needs from the collected information and extracts potential matching candidates for companies and products.

[0640] Based on the analysis results, the server evaluates combinations of companies and products. It automatically lists combinations of companies with high synergy potential, increasing the likelihood of successful collaboration.

[0641] Next, the terminal receives a matching list generated from the server and presents it to the user. At this time, the AI ​​agent clearly explains the advantages and feasibility of each combination in the list, supporting the user in making an appropriate choice.

[0642] Users select the most suitable collaboration partner from the presented options and then send their opinions and feedback to the system. This user feedback is collected on the server and used to further improve and optimize the system.

[0643] As a concrete example, suppose a user company is considering expanding into a new field. By using the system, this company can find effective partners in a short period of time and gain the opportunity to maximize synergistic effects.

[0644] The following describes the processing flow.

[0645] Step 1:

[0646] The server collects necessary information from public data sources. This includes accessing social media APIs, downloading industry reports, and scraping from official company websites. The collected data is stored in storage.

[0647] Step 2:

[0648] The server preprocesses the collected data. Specifically, it removes noise from the data, standardizes case, and normalizes the text. It also imputes missing values ​​and removes duplicate data to prepare the data for analysis.

[0649] Step 3:

[0650] The server uses natural language processing (NLP) to analyze data. It extracts market trends through topic modeling and understands consumer opinions through sentiment analysis. This allows it to identify customer needs and market demands.

[0651] Step 4:

[0652] The server evaluates combinations of companies and products based on the analyzed data. To measure synergy effects, it uses algorithms to calculate similarity scores and predict the likelihood of successful collaboration.

[0653] Step 5:

[0654] Based on the evaluation results, the server lists combinations of companies and generates a matching list. This list is ranked based on synergy effects and feasibility.

[0655] Step 6:

[0656] The terminal presents the user with a matching list received from the server. An AI agent explains the advantages and key points of each suggestion on the list, supporting the user's decision-making.

[0657] Step 7:

[0658] Users select the most suitable collaboration partner from the presented matching list. After selection, users provide feedback to the system, reporting their reasons for selection and details of their preferences.

[0659] Step 8:

[0660] The server analyzes user feedback and uses it to improve the system's evaluation model and filtering algorithms. This will enable more accurate matching in subsequent attempts.

[0661] (Example 1)

[0662] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0663] In today's business environment, companies need to find partners and build collaborative relationships quickly and effectively. However, collecting appropriate information from the vast ocean of data and conducting accurate data analysis requires significant resources, making it particularly difficult for small and medium-sized enterprises (SMEs). Furthermore, the lack of objective indicators for evaluating inter-company combinations and mechanisms for clearly presenting the results hinders optimal decision-making.

[0664] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0665] In this invention, the server includes data collection means for acquiring data from information sources, data preprocessing means for preprocessing the acquired data and removing noise, and data analysis means for analyzing the data using natural language processing and data mining techniques. This enables companies to efficiently collect information and build appropriate and rapid collaborative relationships based on the analysis results.

[0666] "Information sources" refer to external databases and platforms accessible to businesses, including public data and open data.

[0667] "Data acquisition means" refers to the hardware and software functions used to obtain necessary data from information sources.

[0668] "Data preprocessing means" refers to processes and techniques for removing noise from acquired data and processing it into a format suitable for analysis.

[0669] "Natural language processing" refers to the methods and techniques for processing human language using computers, and is used for analyzing text data.

[0670] "Data mining techniques" refer to scientific and statistical methods for extracting useful information and patterns from large amounts of data.

[0671] "Data analysis tools" refer to functions that analyze data using natural language processing and data mining techniques to derive useful insights.

[0672] "Matching generation means" refers to a part of the algorithm or system used to evaluate and generate appropriate combinations of companies and products based on analysis results.

[0673] "Result presentation means" refers to a function that provides the generated matching list and evaluation results to the user in visual or text format.

[0674] "Feedback collection methods" refer to methods or processes for collecting opinions and evaluations from users and incorporating them into further system optimization.

[0675] "Evaluation methods" refer to criteria or algorithms used to assess the synergistic effects of a particular combination of companies.

[0676] This invention is configured as a system that acquires data from information sources and effectively supports business matching between small and medium-sized enterprises. This objective is achieved primarily through the interaction of three parties: a server, a terminal, and a user.

[0677] First, the server has data collection means to obtain the necessary data from information sources. Specifically, it collects data from social media APIs and public websites. During this process, a script using Python is executed periodically to automatically retrieve data. The server preprocesses the retrieved data using the pandas library to remove noise and transform it into an analyzable format.

[0678] Next, the server utilizes natural language processing technology, analyzing text data using the NLTK library. This allows for the extraction of important keywords and the understanding of market trends. Furthermore, the scikit-learn library is used as a data mining technique to extract matching candidates based on the characteristics of each company.

[0679] Based on the analysis results, the server uses a recommendation algorithm to evaluate appropriate combinations and constructs a list using a matching generation mechanism. This matching list includes combinations of companies that maximize synergy effects, thereby increasing the likelihood of successful collaboration.

[0680] The terminal receives a matching list from the server and presents it to the user visually and intuitively via an agent. The interface is designed to be easy for viewers to understand, clearly explaining the details and advantages of each candidate.

[0681] Users refer to the presented matching list and select the most suitable partner candidate. The selection results and feedback are sent to the server via the device and used by the system's feedback collection mechanism to improve the system in the future.

[0682] As a concrete example, consider a case where a small or medium-sized enterprise in the food industry is looking for a partner with packaging technology. By entering the prompt message "Please suggest potential partner candidates for a food company seeking new food packaging technology," this company can quickly and effectively find suitable candidates through the system. In this way, the system of the present invention enables each company to quickly find its ideal partner and maximize synergistic effects.

[0683] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0684] Step 1:

[0685] The server retrieves data from the information source. It takes an API key or the URL to be scraped as input, and the output is raw text data. Specifically, the server uses a Python script to automatically retrieve industry-related information from social media APIs and public databases.

[0686] Step 2:

[0687] The server preprocesses the acquired data. In this step, raw text data is given as input, and cleaned data is produced as output. Specifically, the server uses the pandas library to remove unwanted characters and noise from the data and impute missing values. This improves the quality of the analysis.

[0688] Step 3:

[0689] The server analyzes pre-processed data. Cleaned data is given as input, and the analysis results are obtained as output. Specifically, the server uses the NLTK library to perform natural language processing and extract keywords from the text. It also applies a machine learning model using the scikit-learn library to analyze market trends.

[0690] Step 4:

[0691] The server generates matching candidates based on the analysis results. The analysis results are given as input, and a list of company and product combinations is obtained as output. Specifically, it runs a recommendation algorithm and automatically lists company combinations that are expected to have synergistic effects. This helps users make quick decisions.

[0692] Step 5:

[0693] The terminal displays a matching list received from the server. It receives a list of company combinations as input and outputs a visually clear display that is easy for the user to understand. Specifically, the terminal uses a GUI to graphically display the advantages and potential of each company, supporting the user in selecting a partner.

[0694] Step 6:

[0695] The user selects an appropriate partner from the presented options and provides feedback. Based on the combination of companies presented as input, the system sends the selection results and feedback as output. Specifically, the user enters selections and comments on the terminal interface, which are collected on the server and used to improve the accuracy of matching in the future.

[0696] (Application Example 1)

[0697] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] Traditional business matching systems have faced challenges in quickly finding the optimal combination of companies, and manually searching for the right combination to maximize synergy is time-consuming and costly. Furthermore, they often fail to adequately present crucial information such as the key points and advantages of each combination, making decision-making difficult.

[0699] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0700] In this invention, the server includes information acquisition means, information analysis means, combination generation means, result display means, opinion collection means, and relationship evaluation means. This makes it possible to automatically generate the optimal combination between companies in a short period of time and provide users with a clear explanation of the key points and advantages.

[0701] "Information acquisition means" refers to a system for obtaining data from public information sources.

[0702] An "information analysis tool" is a system for organizing and analyzing acquired data.

[0703] The "combination generation means" is a mechanism that generates a list of optimal combinations of business entities based on the analysis results.

[0704] A "result display means" is a mechanism for presenting the generated list of combinations to the user.

[0705] A "means of gathering opinions" refers to a system for collecting opinions and feedback from users and using them to optimize the system.

[0706] A "relationship evaluation tool" is a system that evaluates the relationships between business entities based on similarity and recommends the optimal combination.

[0707] The system for implementing this invention achieves its objectives primarily through the interaction of three parties: a server, a terminal, and a user. The server collects various data from public information sources using information acquisition means. Next, it uses information analysis means to organize the collected data, remove noise, and then analyze the data. Based on this analysis, a relationship evaluation means evaluates similarity, and a combination generation means creates a list of optimal combinations of business entities.

[0708] The terminal uses a results display mechanism to present the user with a list of combinations sent from the server. Based on the presented information, the user decides on a partnership candidate and sends feedback to the system using a feedback collection mechanism. This feedback is used by the server to update the generated AI model and improve the system's accuracy.

[0709] For example, if a small or medium-sized e-commerce business is considering expanding into a different category, it can automatically find the best partner from manufacturers in a short period of time. Such companies can select the partner that best suits their needs through a recommendation list generated by the server. An example of a prompt to the generating AI model would be, "How can you provide optimal trade matching between manufacturers and distributors based on a rich data source?"

[0710] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0711] Step 1:

[0712] The server retrieves data from public information sources using information acquisition methods. In this process, the input is the URL or API of the public information source, and the output is the retrieved raw data. The data is stored on the server in JSON or XML format. Specifically, the data is downloaded via HTTP requests.

[0713] Step 2:

[0714] The server uses information analysis tools to process the acquired data and remove noise. The input is the raw data acquired in step 1, and the output is the cleaned and processed data. Specifically, unnecessary characters and spaces are removed, and the data is converted into a parseable format.

[0715] Step 3:

[0716] The server uses combination generation methods to evaluate similarity within the prepared data and create a list of optimal combinations of business entities. The input is the prepared data, and the output is a list containing pairs or groups of business entities with high similarity. Specifically, it vectorizes text data using TF-IDF and calculates cosine similarity.

[0717] Step 4:

[0718] The server sends the generated list of combinations to the terminal via a results display mechanism. The input is an optimized list of combinations, and the output is visualized data. Specifically, the list is converted into a user-friendly format (e.g., HTML or JSON).

[0719] Step 5:

[0720] The terminal displays a list of combinations received from the server to the user using a results display mechanism. The input is data received from the server, and the output is data displayed on the user interface. Specifically, the list is displayed visually through a GUI.

[0721] Step 6:

[0722] The user selects a candidate from the presented combinations and inputs feedback into the device using a feedback collection tool. The input consists of the user's selection and opinion, and the output is saved on the device as feedback data. Specifically, the user clicks on an option and enters a comment in a text box.

[0723] Step 7:

[0724] The terminal sends collected feedback to the server to help optimize the system. The input is user feedback data, and the output is structured data sent to the server. Specifically, the feedback is stored in a database and used as data to train the generated AI model in preparation for the next model update.

[0725] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0726] This invention is a system that enables effective business matching for companies. In addition to collecting, analyzing, and generating matches from public data sources, it incorporates an emotion engine that recognizes and analyzes user emotions. This system aims to improve the user experience through collaboration among the server, terminal, and user.

[0727] First, the server collects rich information from public data sources. Data collection includes API calls, web scraping, and database access. The collected information is preprocessed to remove unnecessary noise and normalize the text before being ready for analysis.

[0728] Next, the server utilizes advanced natural language processing (NLP) and data analysis techniques to identify market trends and customer preferences. The analyzed data is then used to calculate potential matches between companies, taking synergy effects into consideration, and a list of optimal combinations is generated.

[0729] Furthermore, the server incorporates an emotion engine that recognizes the user's emotional state from their interactions and feedback. This emotion analysis is used to adjust the content and presentation method of the matching list presented to the user, contributing to increased user satisfaction.

[0730] The device receives a matching list generated by the server and presents it visually to the user. An AI agent explains the merits of each combination to the user, and the suggestions may be modified based on sentiment data.

[0731] For example, if the user is a company representative seeking new collaborations, the emotion engine captures the user's interests and satisfaction levels in real time, prioritizing the display of combinations that interest them. In this way, users can obtain the results they expect more quickly and accurately.

[0732] Ultimately, the user selects the partner they deem best and provides feedback on their choice to the system. The server analyzes this feedback and sentiment data to improve the system's overall algorithm and enhance matching accuracy in the future.

[0733] The following describes the processing flow.

[0734] Step 1:

[0735] The server retrieves information from public data sources. This involves sending requests through social media APIs, accessing corporate databases, and utilizing website scraping techniques. The retrieved data is temporarily stored in storage.

[0736] Step 2:

[0737] The server preprocesses the collected data. Specifically, it removes noise, normalizes the data, and imputes missing values ​​to maintain data integrity. It also performs duplicate removal and categorization.

[0738] Step 3:

[0739] The server analyzes pre-processed data. Using natural language processing techniques, it extracts customer needs and market trends from text data. Furthermore, it uses data mining techniques to find patterns and identify potential business opportunities.

[0740] Step 4:

[0741] The server evaluates combinations of companies and products based on the analysis results and generates a matching list based on synergy effects and likelihood of success. This uses algorithms to analyze similarities and differences between companies and derive the most effective combinations.

[0742] Step 5:

[0743] The server activates the emotion engine and analyzes the user's emotional state from past choices and interaction data. This allows it to determine which combinations the user is favorably disposed towards and reflect this in the matching list.

[0744] Step 6:

[0745] The device presents the generated matching list to the user. At this point, the AI ​​agent explains the details of each suggestion and highlights suggestions that the user may be interested in based on the results of the emotion engine.

[0746] Step 7:

[0747] Users select a suitable collaboration partner from the presented proposals. They can make a satisfactory choice after considering the advantages and disadvantages.

[0748] Step 8:

[0749] Users enter and submit feedback to the system. This feedback includes reasons for their selection and any additional comments.

[0750] Step 9:

[0751] The server analyzes feedback and sentiment data received from users. This allows the system's algorithms and suggestions to be improved, leading to better matching accuracy in the future.

[0752] (Example 2)

[0753] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0754] In today's business environment, effective matching between companies is crucial. However, traditional systems struggle to respond quickly to market changes and diverse customer needs, and are particularly inadequate at providing flexible proposals that cater to user emotions. Therefore, there is a need for a system that provides potential partners that meet user expectations and improves the user experience.

[0755] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0756] In this invention, the server includes information gathering means, information analysis means, combination generation means, sentiment analysis means, result display means, and feedback collection means. This enables the generation of appropriate combinations of companies based on public information sources and flexible suggestions based on the user's sentiment. Furthermore, it is possible to improve the accuracy of the system by utilizing the collected feedback.

[0757] An "information gathering tool" is a mechanism that has the function of automatically acquiring necessary information from public information sources.

[0758] An "information analysis tool" is a mechanism for transforming acquired information into a useful form by preprocessing and analyzing it.

[0759] A "combination generation mechanism" is a system that identifies and proposes optimal interrelationships and partnership candidates from data based on analysis results.

[0760] An "emotion analysis tool" is a mechanism that recognizes the user's emotional state from their interactions and input data, and processes that information.

[0761] A "result display means" is a mechanism that has the function of visually presenting the generated combinations and suggestions to the user.

[0762] A "feedback collection mechanism" is a system for collecting user feedback and usage data and using it to improve the system.

[0763] "Synergy effect" is a term that refers to additional benefits obtained through partnerships between companies that would not be achievable individually.

[0764] An "explanatory mechanism" is a system designed to provide users with an easily understandable overview of the key points and benefits of the generated suggestions and combinations.

[0765] To implement this invention, a server plays a central role. The server collects information from public sources using information gathering means. This process includes specific scripts for making API calls and performing web scraping. The collected data is preprocessed and analyzed through information analysis means. Specifically, the Python NLTK library is used to perform data denoising and natural language processing.

[0766] Next, the server uses a combination generation mechanism to generate the optimal combination of business partners based on the analyzed data. At this stage, machine learning algorithms are used to identify candidates while considering the synergistic effects between companies.

[0767] Furthermore, the server incorporates emotion analysis capabilities to recognize emotional data from user feedback and interactions. For example, it analyzes input data obtained from the user's device to determine whether there are many positive emotional expressions.

[0768] The terminal visually displays information received from the server. The user interface is designed to be simple and intuitive, with an AI agent clearly guiding the user through the advantages of each combination. This agent enhances satisfaction by adjusting the presented suggestions based on the user's emotional state.

[0769] Users provide feedback by reviewing the presented suggestions and selecting the optimal combination of partners. This user feedback is collected on a server and used to improve the system's algorithms through feedback collection mechanisms, leading to increased accuracy in future iterations.

[0770] For example, if a user is a sales representative seeking new collaborations, the emotion engine captures the user's interests and satisfaction levels in real time, prioritizing and displaying the most suitable matchups. In this way, users can obtain their desired results more quickly and accurately.

[0771] Examples of prompt statements for a generative AI model are shown below.

[0772] "Please find new collaboration partners for my company, prioritizing companies that focus particularly on sustainable business practices."

[0773] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0774] Step 1:

[0775] The server uses data gathering methods to obtain data from public sources. This process automatically collects the necessary information using data requests from APIs and web scraping. Inputs include specific URLs and API endpoints, and the output is obtained as a structured dataset.

[0776] Step 2:

[0777] The server uses information analysis tools to preprocess and analyze the collected data. Here, the Python Pandas library is used to denoise the data and normalize the text. It accepts raw data as input and generates a clean, analyzable dataset as output.

[0778] Step 3:

[0779] The server uses a combination generation mechanism to calculate appropriate business partner combinations from the analyzed data. Specifically, it applies similarity calculations and clustering algorithms to select the optimal combination candidates. The input is the analyzed data, and the output is a list of candidate partners.

[0780] Step 4:

[0781] The server uses sentiment analysis techniques to recognize emotions from user feedback and interaction data. It calculates an emotion score using natural language processing methods and identifies positive or negative emotions. It takes user feedback messages as input and outputs the results of the sentiment analysis.

[0782] Step 5:

[0783] The terminal receives a list of combinations generated by the server and presents it to the user via a results display device. An AI agent is activated and explains the advantages of the combinations on the user interface. The input is the list of combinations from the server, and the output is the information displayed on the user's screen.

[0784] Step 6:

[0785] The user reviews the presented combinations and provides feedback. This feedback is sent from the terminal to the server and stored in a database by the feedback collection mechanism. The input is user feedback data, and the output is data for improvement that is accumulated in the system.

[0786] (Application Example 2)

[0787] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0788] To achieve effective business matching between companies, it is crucial not only to optimize the combinations of companies but also to enhance user satisfaction. However, conventional systems have struggled to consider user emotions and interests when presenting company combinations, resulting in a limited user experience. Furthermore, methods for effectively incorporating feedback and continuously improving the system have not been established. As a result, there is a challenge in obtaining the flexible and accurate matching results that users expect.

[0789] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0790] In this invention, the server includes data collection means for acquiring information from public data sources, data analysis means for processing and analyzing the acquired information, matching generation means for generating a list of organizational combinations based on the analysis results, emotion analysis means for analyzing the user's emotions using an emotion analysis engine, adjustment means for adjusting the presentation of results based on the emotion analysis, and feedback collection means for collecting feedback from users and reflecting it in improving the system. This makes it possible to provide flexible matching results that reflect the user's emotional state, increase user satisfaction, and continuously improve the system.

[0791] "Data collection means" refers to devices and methods for collecting information from public data sources.

[0792] "Data analysis means" refers to devices and methods for processing and analyzing collected information.

[0793] A "matching generation means" is a device or method for generating a list of organizational combinations based on analysis results.

[0794] "Result presentation means" refers to a device or method for presenting the generated combination list to the user visually or audibly.

[0795] "Emotional analysis means" refers to devices or methods for analyzing a user's emotional state using an emotional analysis engine.

[0796] "Adjustment means" refers to devices or methods for optimally adjusting the results presented based on emotion analysis.

[0797] "Feedback collection methods" refer to devices or methods for collecting feedback from users and incorporating it into system improvements.

[0798] This invention is a system that enables effective business matching between companies, and is realized through the collaboration of three parties: a server, a terminal, and a user.

[0799] The server first collects information from public data sources. Specifically, it obtains market data and company information from the internet through API calls and web scraping. This collection process uses Python and the Beautiful Soup library.

[0800] Next, the server preprocesses the collected information and performs data analysis using natural language processing. Preprocessing involves removing noise and normalizing the text. In this step, natural language processing tools such as TensorFlow are used to analyze the company's needs and market trends.

[0801] Furthermore, the server uses an emotion analysis engine to analyze emotions from user feedback and interactions. This allows for prioritization and adjustment of the generated matching list. The adjusted results are then presented to the user. This process makes it possible to prioritize and present combinations that the user is more likely to be interested in.

[0802] The device visually displays a matching list sent from the server to the user, and an AI assistant provides voice explanations of the merits of each suggestion. This allows the user to easily understand the characteristics of the suggested companies.

[0803] Users provide feedback on the presented combinations. This feedback is collected by the server and used, along with sentiment analysis results, to improve the algorithm. This makes it possible to improve the accuracy of matching in the future.

[0804] As a concrete example, suppose a user is looking for a partner for new security technology. The server collects and analyzes relevant industry data to generate a list of optimal partners. Based on user feedback, the suggestions are continuously improved, resulting in more accurate matches.

[0805] An example of a prompt for a generative AI model would be: "In a business matching app, company A is looking for a partner for new security technology. Please suggest natural language processing techniques to gather useful information from publicly available data and understand the company's needs. Also, please provide ideas on how to improve the next suggestion based on user feedback."

[0806] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0807] Step 1:

[0808] The server retrieves information from public data sources. Input is APIs and website information on the internet, and output is raw data. Python and Beautiful Soup are used for data collection, extracting market data and company information in the security industry through API calls and web scraping.

[0809] Step 2:

[0810] The server preprocesses the acquired raw data. The input is the raw data obtained in step 1, and the output is de-noise-removed and normalized text data. Specifically, it performs operations such as removing unnecessary information using regular expressions and normalizing strings.

[0811] Step 3:

[0812] The server analyzes pre-processed data using natural language processing (NLP) techniques. The input is the normalized text data obtained in step 2, and the output is the analysis results reflecting company needs and market trends. Using NLP libraries such as TensorFlow, it extracts important keywords from the text data and identifies matching candidates that consider synergistic effects between companies.

[0813] Step 4:

[0814] The server analyzes the user's emotions using an emotion analysis engine. The input is user interaction and feedback data, and the output is the analyzed emotional state. An AI model is used to estimate emotions from the user's text and behavior logs, and the matching results are prioritized based on this.

[0815] Step 5:

[0816] The server generates a list of organizational combinations based on the analysis results and sentiment data. The input is the data obtained in steps 3 and 4, and the output is a matching list to be presented to the user. The system derives the optimal combination of companies and proposes new business opportunities.

[0817] Step 6:

[0818] The terminal visually presents the user with a matching list sent from the server, and an AI assistant explains the merits of each proposal. The input is the matching list from the server, and the output is to improve the user's understanding and stimulate their willingness to partner. A voice assistant is used to explain the proposals in an easy-to-understand manner.

[0819] Step 7:

[0820] Users provide feedback on the presented combinations. The input is the user's evaluation and comments, and the output is feedback data received and processed by the server. This feedback is analyzed by the server to improve future suggestions and is also used as training data for the AI ​​model.

[0821] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0822] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0823] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0824] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0825] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0826] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0827] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0828] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0829] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0830] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0831] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0832] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0833] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0834] 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.

[0835] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0836] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0837] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0838] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0839] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0840] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0841] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0842] The following is further disclosed regarding the embodiments described above.

[0843] (Claim 1)

[0844] Data collection methods for obtaining information from public data sources,

[0845] A data analysis means for processing and analyzing acquired information,

[0846] A matching generation means that generates a list of company combinations based on the analysis results,

[0847] A result presentation means that presents the generated list to the user,

[0848] A feedback collection method that collects user feedback and reflects it in system improvements,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, further comprising an evaluation means for evaluating the synergistic effects of the proposed combination of companies.

[0852] (Claim 3)

[0853] The system according to claim 1, further comprising explanatory means for providing a user with the key points and benefits of the generated list.

[0854] "Example 1"

[0855] (Claim 1)

[0856] A data collection method for obtaining data from information sources,

[0857] A data preprocessing means for preprocessing acquired data and removing noise,

[0858] A data analysis method that analyzes data using natural language processing and data mining techniques,

[0859] A matching generation means that evaluates and lists combinations of organizations based on the analysis results,

[0860] A result presentation means that details the generated list using an agent and presents it to the user via a terminal,

[0861] A feedback collection method that collects user responses and reflects them in optimizing the system,

[0862] A system that includes this.

[0863] (Claim 2)

[0864] The system according to claim 1, further comprising an evaluation means for automatically evaluating the synergistic effects of proposed combinations of organizations.

[0865] (Claim 3)

[0866] The system according to claim 1, further comprising explanatory means for providing users with the key points and benefits of the generated list.

[0867] "Application Example 1"

[0868] (Claim 1)

[0869] Information acquisition means for obtaining data from public information sources,

[0870] Information analysis tools for organizing and analyzing acquired information,

[0871] A combination generation means that generates a list of combinations of business entities based on the analysis results,

[0872] A result display means that presents the generated list to the user,

[0873] A means of collecting user opinions and reflecting them in optimizing the system,

[0874] A relationship evaluation tool that assesses and recommends relationships between business entities based on similarity,

[0875] A system that includes this.

[0876] (Claim 2)

[0877] The system according to claim 1, further comprising a means for measuring the synergistic effect of the proposed combination of business entities.

[0878] (Claim 3)

[0879] The system according to claim 1, further comprising means for providing users with information about the key points and advantages of the generated list.

[0880] "Example 2 of combining an emotion engine"

[0881] (Claim 1)

[0882] Information gathering methods that obtain information from public sources,

[0883] Information analysis means for preprocessing and analyzing acquired information,

[0884] A combination generation means that generates a list of target combinations based on the analysis results,

[0885] A means of emotional analysis that recognizes and analyzes the emotional state of a user,

[0886] A results display means that presents the generated list to the user based on sentiment data,

[0887] A feedback collection method that collects user feedback and reflects it in system improvements,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, further comprising an evaluation means for evaluating the synergistic effects of the proposed combination.

[0891] (Claim 3)

[0892] The system according to claim 1, further comprising explanatory means for presenting to the user the key points and benefits of the generated list.

[0893] "Application example 2 when combining with an emotional engine"

[0894] (Claim 1)

[0895] Data collection methods for obtaining information from public data sources,

[0896] A data analysis means for processing and analyzing acquired information,

[0897] A matching generation means that generates a list of organizational combinations based on the analysis results,

[0898] A result presentation means that presents the generated list to the user,

[0899] An emotion analysis method that analyzes a user's emotions using an emotion analysis engine,

[0900] An adjustment mechanism that adjusts the presentation of results based on emotion analysis,

[0901] A feedback collection method that gathers feedback from users and reflects it in system improvements,

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, further comprising an evaluation means for evaluating the synergistic effects of the proposed combination of organizations.

[0905] (Claim 3)

[0906] The system according to claim 1, further comprising explanatory means for providing users with the key points and benefits of the generated list and adjusting the suggested content based on sentiment analysis. [Explanation of symbols]

[0907] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Information acquisition means for obtaining data from public information sources, Information analysis tools for organizing and analyzing acquired information, A combination generation means that generates a list of combinations of business entities based on the analysis results, A result display means that presents the generated list to the user, A means of collecting user opinions and reflecting them in optimizing the system, A relationship evaluation tool that assesses and recommends relationships between business entities based on similarity, A system that includes this.

2. The system according to claim 1, further comprising a means for measuring the synergistic effect of the proposed combination of business entities.

3. The system according to claim 1, further comprising an information provision means for providing users with the key points and advantages of the generated list.

Images