system

Abstract

We provide the system. [Solution] A method for extracting related companies from a database containing company information based on specific keywords, A means of utilizing generative artificial intelligence to analyze the financial data and capabilities of extracted companies, A means for generating a score indicating the suitability of each company for alliances, mergers, and acquisitions, A means of presenting the results to the user based on the aforementioned score, 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When a company considers alliances, mergers, or acquisitions, there is a problem that creating a long list for selecting candidate companies requires a huge amount of time and labor. In the current approach, it is necessary to manually collect and analyze company information, which may lead to a shortage of manpower and subjective judgment, and thus the efficiency and fairness of the selection may be impaired. In such a situation, there is a need for a method to quickly and accurately select candidate companies while utilizing limited resources.

Means for Solving the Problems

[0005] This invention extracts relevant companies from a database containing company information through keyword searches, and generates a score indicating the suitability of each company for alliances, mergers, or acquisitions by analyzing the financial data and capabilities of the extracted companies using generative artificial intelligence. Furthermore, by presenting this score to the user, it becomes possible to objectively and efficiently select suitable candidate companies. This system significantly reduces the man-hours required for conventional manual information gathering and analysis, and achieves decision support with record-breaking accuracy.

[0006] A "database containing company information" is a database that stores various types of information about a company and allows for searching and extraction of that information.

[0007] "Specific keywords" are important words or phrases, such as relevant industry names, technical terms, and geographical conditions, used to narrow down potential alliances, mergers, and acquisitions.

[0008] "Generative artificial intelligence" is an artificial intelligence technology that analyzes collected data and makes decisions under certain conditions, and is particularly useful for scoring the suitability of companies.

[0009] "Financial data and capabilities" refers to information used to evaluate a company's performance and potential, including its financial condition, operational capabilities, and technological characteristics.

[0010] A "score" is a numerical evaluation index that assesses the suitability of companies for alliances, mergers, or acquisitions, and serves as a criterion for selecting candidate companies.

[0011] A "user" is an entity that uses the system to select candidate companies in the process of alliances, mergers, and acquisitions. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of the data processing device and 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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0015] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0017] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memories (SSDs (Solid State Drives)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, a communication I / F (Interface) with a reference numeral is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

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

[0020] [First Embodiment]

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

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

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

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

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

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

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

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

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

[0033] This invention is a system for streamlining the selection of candidate companies when companies are considering alliances, mergers, or acquisitions. Specifically, it enables users to quickly and objectively select candidate companies through the use of a database containing company information and analysis by generative artificial intelligence.

[0034] The terminal has an interface that accepts user input. Users enter specific keywords into the terminal to narrow down potential alliance, merger, or acquisition candidates. These keywords may include desired industries, relevant technical terms, and geographical conditions.

[0035] The server uses keywords received from the terminal to search a database containing company information. This search results in a list of relevant companies. Company information includes company name, location, industry, as well as publicly available financial data and capabilities.

[0036] Next, the server uses generative artificial intelligence to analyze the extracted financial data and capabilities of the companies. As a result of this analysis, a score is generated indicating the suitability of each company for alliances, mergers, and acquisitions. The generated score reflects each company's strategic fit, growth potential, and financial health.

[0037] For example, if a user wishes to form an alliance with a North American company that possesses AI technology, they would enter keywords such as "AI technology" and "North America" ​​into their terminal. Based on this, the server searches its database for relevant companies, analyzes the financial data of the extracted companies, and generates an optimal score. As a result, companies with high scores are prioritized and listed, providing the user with the basic information needed to proceed to the next step.

[0038] This process allows users to efficiently select candidate companies and focus on subsequent negotiations and analysis. The system reduces the burden of manual information gathering, enabling faster and more accurate decision-making.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] Users enter keywords into their terminals to identify target companies for alliances, mergers, or acquisitions. These keywords can include industry names, technical terms, geographical locations, and more.

[0042] Step 2:

[0043] The terminal collects the entered keywords and sends them to the server.

[0044] Step 3:

[0045] The server uses the received keywords to search a database containing company information and then generates a list of companies that match the criteria.

[0046] Step 4:

[0047] The server then retrieves more detailed financial and capability information for each company from a database or external data source from the generated list of companies.

[0048] Step 5:

[0049] The server inputs the acquired data into generative artificial intelligence to perform analysis including each company's financial health, strategic fit, and growth potential.

[0050] Step 6:

[0051] The server assigns a score to each company based on the analysis results, and evaluates their suitability for alliances, mergers, and acquisitions.

[0052] Step 7:

[0053] The server returns the scoring results and an overview of each company to the terminal.

[0054] Step 8:

[0055] Users review the scoring results displayed on their device and decide which companies to proceed to the next selection process with.

[0056] (Example 1)

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

[0058] When companies engage in alliances, mergers, or acquisitions, quickly and efficiently identifying suitable candidates is challenging. The process of gathering and analyzing relevant information is time-consuming, labor-intensive, and often relies on subjective judgment. Therefore, a system is needed to select candidate companies based on objective and fair criteria.

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

[0060] In this invention, the server includes means for receiving specific input information, means for searching for information in an information aggregate based on the input information and extracting relevant information, and means for utilizing generative automated intelligence to analyze the numerical data and skill information of the extracted information. This enables the user to quickly and objectively evaluate the suitability of linking, retrieving, and integrating tasks and select the optimal candidate.

[0061] "Specific input information" refers to information provided by the user to the system, including industry names, technical terms, and regional conditions.

[0062] An "information aggregate" refers to a database or other means of collecting information used to store data about a company.

[0063] "Related information" refers to company-related data that the system presents to the user, extracted based on specific input information.

[0064] "Numerical data and skills information" refers to detailed information about a company's financial situation and capabilities, and serves as evaluation criteria in company selection.

[0065] "Generative automated intelligence" is a form of artificial intelligence technology that is equipped with algorithms that analyze diverse data and generate evaluation values.

[0066] "Suitability for mergers, acquisitions, and integrations" refers to evaluation criteria that demonstrate a company's suitability for alliances, mergers, and acquisitions with other companies.

[0067] The "evaluation value" is a numerical value calculated by generative automated intelligence, indicating the suitability of a particular company for alliances, mergers, or acquisitions.

[0068] This invention is for selecting appropriate candidates when considering corporate alliances, mergers, or acquisitions using an information processing device. Specifically, it involves the interaction of a server, a terminal, and a user.

[0069] First, the user provides specific input information through the terminal interface. This includes the name of the relevant industry sector, technical terms, and regional conditions. The user can do this through text input or voice input.

[0070] Next, the terminal sends this input information to the server. The server searches a database, which is a collection of information, and extracts company information related to the input information. This process utilizes a high-speed search algorithm and a database management system.

[0071] The server then uses generative automated intelligence to analyze the extracted numerical data and skills information of the companies. The generative automated intelligence assesses each company's financial health, growth potential, and strategic suitability, generating evaluation values ​​that indicate its suitability for merger-related or acquisition and integration work. This analysis utilizes software powered by machine learning algorithms.

[0072] Finally, the server sends the evaluation results to the terminal, which then presents them to the user. Based on the presented evaluation values, the user can then make the next decision.

[0073] For example, if a user wishes to form an alliance with a North American company possessing AI technology, they would enter prompts such as "AI technology" or "North America" ​​into their terminal. Based on this, the server would search its database to extract relevant companies, analyze them, and present the optimal evaluation score. This allows the user to efficiently select candidate companies.

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

[0075] Step 1:

[0076] The user provides specific input information through the terminal's interface. Specifically, they input industry names, technical terms, geographical conditions, etc., using the keyboard or voice input function. The input information is converted into digital data within the terminal and prepared for transmission to the server.

[0077] Input: Specific input information provided via keyboard or voice input.

[0078] Output: Digital information data for transmission to the server.

[0079] Step 2:

[0080] The terminal sends the input information received from the user to the server. A secure communication protocol is used for transmission via the internet connection. The server then formats the received data directly into a query for database retrieval.

[0081] Input: Digital information data from a terminal.

[0082] Output: Search queries that reached the server

[0083] Step 3:

[0084] The server searches the corporate information database, which is a collection of information, based on the received query. A high-speed search algorithm is used to extract relevant corporate information. The found information is organized in a list format and passed on to the next processing step.

[0085] Input: Search query on the server

[0086] Output: List of related company information

[0087] Step 4:

[0088] The server uses generative automated intelligence to analyze the numerical and skills data of extracted company information. In this process, machine learning algorithms evaluate each company's financial health and growth potential, and generate evaluation values ​​indicating their suitability for integration.

[0089] Input: List of extracted company information

[0090] Output: Evaluation values ​​for each company

[0091] Step 5:

[0092] The server ranks companies based on the generated evaluation scores and sends this ranking to the terminal. The ranked information is then organized in order of priority to support the user's decision-making.

[0093] Input: Evaluation value for each company

[0094] Output: Ranked company information

[0095] Step 6:

[0096] The terminal displays ranked company information received from the server on its screen. The user reviews this information and makes decisions for the next step based on the evaluation scores. Specifically, they can request additional data or view detailed information about the selected companies.

[0097] Input: Ranked company information

[0098] Output: Specific company information displayed to the user

[0099] (Application Example 1)

[0100] 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."

[0101] Traditional company selection processes have presented challenges in efficiently selecting potential alliance, merger, and acquisition candidates. Furthermore, the time-consuming and labor-intensive information gathering and analysis required for selection often led to delays in decision-making. Additionally, a lack of objective criteria and tools for evaluating each company's suitability prevented users from quickly comparing and evaluating options. There is a need for solutions to these challenges, enabling more efficient and accurate company selection.

[0102] 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.

[0103] In this invention, the server includes means for extracting relevant companies from a database containing company information based on specific keywords; means for utilizing generative data processing technology to analyze the financial data and capabilities of the extracted companies; means for calculating the strength indicating the suitability of each company for collaboration or organizational restructuring; means for visually presenting the results to the user based on the strength; and an intuitive information display device for displaying candidates that meet the criteria based on user input. This enables the user to quickly grasp the details of candidate companies and make the optimal selection.

[0104] A "database containing corporate information" is a digital collection of information about various companies, including company name, location, industry, and publicly available financial data and capabilities.

[0105] "Methods for extracting relevant companies based on specific keywords" refers to algorithms or processes for selecting companies from a database that match the conditions specified by the user.

[0106] "Methods that utilize generative data processing technology" refer to techniques that use generative artificial intelligence and advanced data analysis technologies to process extracted company information and obtain meaningful analytical results.

[0107] "Means for calculating the strength of suitability for collaboration or organizational restructuring" refers to a method for quantitatively evaluating how suitable companies are for collaboration or integration and displaying it as a score or index.

[0108] "Means of visually presenting results to users" refers to interfaces and tools that visualize analysis results in an easy-to-understand way for users and display information in various forms.

[0109] An "intuitive information display device" refers to a display device or software designed to allow users to easily understand and operate information.

[0110] This invention includes a system for efficiently selecting and evaluating the suitability of companies. This system realizes the invention through the following main processes.

[0111] The system's core server utilizes a database of stored company information to extract relevant companies that match specific keywords based on user input data. Specific database searches include query processing using SQL and full-text searches using Apache® Lucene. Users access the system using smartphones or desktop terminals and input their desired criteria (e.g., "AI technology," "North America").

[0112] The server analyzes the extracted financial data and capabilities of companies using generative data processing technologies, such as TENSORFLOW® and PyTorch. This technology is crucial for evaluating a company's financial condition and strategic fit in the market. The analysis of the generated data yields a strength score indicating the suitability of each company's collaborations and organizational restructuring.

[0113] Users receive results in a visually easy-to-understand format, such as dashboards or graphs, to check their intensity. Data visualization libraries like D3.js are used to achieve this. In addition, frameworks such as React and Angular are used in the user interface to provide an intuitive information display system, enhancing usability.

[0114] For example, if a user wants to find the best partner in a particular technology field as part of their preparations for participating in an industrial trade show, they can use the system to quickly list companies that meet their criteria and narrow down promising candidates by comparing the strengths of each company.

[0115] An example of a prompt message is, "List companies that meet the following criteria and generate scores for financial health and growth potential: AI technology, North America." This helps users make appropriate decisions quickly and efficiently.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The server receives user input data sent from the terminal. This input data includes conditions and keywords selected by the user (e.g., "AI technology," "North America"). The server uses this data to query a database containing company information and extract companies that match the conditions. A list of related companies is generated as output.

[0119] Step 2:

[0120] The server uses a generative AI model to analyze the extracted list of companies. Financial data and capability information for each company are used as input. The server processes and calculates the strength of each company's suitability for collaboration or restructuring using machine learning algorithms. This information is necessary for subsequent processing.

[0121] Step 3:

[0122] The server prepares data to visually present the results to the user based on the generated intensity. Using a data visualization library, it processes the data into graphs and dashboards for visualization. The output is a visual representation of the intensity in a user-friendly format.

[0123] Step 4:

[0124] The terminal receives visualization data sent from the server and displays it on the user interface. Users can intuitively view and compare information through operations on the terminal. The output provides detailed information on companies individually selected by the user, which can then be used for subsequent decision-making.

[0125] Step 5:

[0126] Based on the information presented, the user retrieves further details about companies that match their selected criteria and generates additional prompts as needed. This allows them to instruct the system to take the next action, enabling further information gathering and analysis.

[0127] 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.

[0128] This invention is a system for companies to select appropriate candidate companies when forming alliances, mergers, or acquisitions, and further provides more personalized information by combining it with an emotion engine that recognizes user emotions.

[0129] The terminal has an interface that accepts specific keywords from the user. The user enters keywords such as industry names, technical terms, and geographical conditions based on their preferences. The terminal then sends this information to the server.

[0130] The server uses the received keywords to search a database containing company information and generates a list of relevant companies that match the criteria. The server then retrieves financial and capability information for the listed companies from the database and external data sources.

[0131] Furthermore, the server uses generative artificial intelligence to analyze the acquired data and generate a score that quantifies the suitability of each company for alliances, mergers, and acquisitions. This scoring allows users to efficiently select companies based on scientifically supported information.

[0132] A key feature of this invention is the integration of an emotion engine to analyze the user's emotions during input and when reviewing scoring results. This emotion analysis allows the server to dynamically adjust the format and method of information presented according to the user's emotions. For example, if the user has negative emotions, the engine simplifies the list display and provides only important highlights. Conversely, if positive emotions are detected, more detailed analysis results and recommendations are presented more explicitly.

[0133] For example, if a user wishes to partner with a technology company in an emerging market, they would enter keywords such as "technology" and "emerging market" into their device. The server would then extract relevant companies from its database and perform scoring based on these keywords. The emotion engine would analyze the user's response, and the resulting information would flexibly change to match the user's intentions and desires, thus supporting optimal decision-making.

[0134] This system is a comprehensive tool designed to improve user convenience while also enhancing the accuracy and efficiency of candidate company selection.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] Users enter keywords related to their desired conditions for alliances, mergers, or acquisitions with companies into the terminal. This allows them to set criteria to narrow down potential companies that meet their objectives.

[0138] Step 2:

[0139] The terminal sends the received keywords to the server as structured data. This information acts as a trigger for database searches.

[0140] Step 3:

[0141] The server searches multiple databases containing company information based on the received keywords and extracts relevant companies that match the criteria. This process takes into account factors such as the company's industry, location, and technology.

[0142] Step 4:

[0143] The server collects detailed financial and capability information for the selected companies from databases and external sources. This clarifies the economic and technological background of each company.

[0144] Step 5:

[0145] The server inputs the collected data into generative artificial intelligence to analyze companies' financial health, growth potential, and strategic fit. As a result, it generates a score indicating the suitability of each company.

[0146] Step 6:

[0147] The server sends the scoring results to the sentiment engine, which infers the user's emotions based on the user's past response data and real-time feedback. This information is then used to dynamically adjust how the information is displayed.

[0148] Step 7:

[0149] The device presents the user with a customized scoring result based on the analysis of the emotion engine. The content is adjusted as needed, providing detailed information for positive emotions and a summary for negative emotions.

[0150] Step 8:

[0151] Based on the information displayed on their device, users select companies that are potential candidates for alliances, mergers, or acquisitions. Throughout this process, the sentiment engine continuously observes the user's reactions and modifies the information presented as needed.

[0152] (Example 2)

[0153] 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".

[0154] When companies engage in alliances, mergers, or acquisitions, selecting the right candidates from a vast amount of information is extremely difficult. Furthermore, user subjectivity and emotions can influence the selection process, leading to inefficient decision-making. There is a need to solve this problem and provide users with the optimal choice.

[0155] 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.

[0156] In this invention, the server includes means for extracting relevant organizations from a data bank containing corporate information, means for utilizing a generative intelligence model to analyze the financial information and capabilities of the extracted organizations, and means for dynamically adjusting the information using sentiment analysis. This makes it possible to select candidate companies based on scientific evidence while adjusting the display method according to the user's emotions.

[0157] "Company information" refers to all information about a company, including its name, address, industry, business activities, financial information, business partners, and other related matters.

[0158] A "data bank" is a collection of information that is systematically organized and stored in a format that allows for searching and analysis.

[0159] "Relevant organizations" refers to companies and organizations extracted based on specified conditions or keywords.

[0160] "Means of extraction" refers to methods and techniques for retrieving data that meets specific conditions from a data bank.

[0161] A "generative intelligence model" is a type of artificial intelligence trained to automatically make predictions and classifications based on input data.

[0162] "Emotion analysis" is a technology that estimates a user's emotions from their facial expressions, voice, and input content, and adjusts the system's operation based on those emotions.

[0163] "Means of dynamic adjustment" refers to methods for flexibly changing the way information is presented or its content in response to changes in circumstances or conditions.

[0164] A description of embodiments for carrying out this invention will be given.

[0165] The server first builds a database containing company information. This database includes detailed information about companies, such as their financial information, industry, business activities, and geographical location. This allows the server to efficiently search and extract relevant organizations based on specific keywords. The server performs data retrieval using database query languages ​​such as SQL.

[0166] Next, the server utilizes generative intelligence models to analyze the extracted financial information and capabilities of the companies. These are implemented using programming languages ​​such as Python and machine learning frameworks like TensorFlow and PyTorch. This generative intelligence model quantifies the suitability of companies for alliances and mergers / acquisitions, generating a score. The generated score is based on scientific evidence and serves as an important indicator in company selection.

[0167] Furthermore, the server implements emotion analysis technology to estimate the user's emotions as they view information through the interface. It uses the device's built-in camera and microphone to capture the user's facial expressions and voice tone, and performs emotion analysis based on this data. This analysis utilizes libraries such as Python's OpenCV and Emotion SDK. Based on the analysis results, the server dynamically adjusts the information displayed to reflect the user's emotions. For example, if the user is showing positive emotions, it presents detailed results from the generative AI model's analysis.

[0168] As a concrete example, consider a scenario where a user is seeking partnerships with technology companies in emerging markets. In this case, the user enters keywords such as "emerging markets" and "technology" into their device. The server extracts relevant companies from a database based on these keywords and generates evaluation scores using a generative intelligence model.

[0169] An example of a prompt message used by the server is, "Analyze the candidates for the best technology companies in emerging markets," which is input to the generative AI model. This prompt allows the generative AI model to perform appropriate information analysis and ultimately provide the information the user is looking for.

[0170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0171] Step 1:

[0172] The user enters keywords indicating their desired conditions using a terminal. This interface allows users to enter industry names, technical terms, geographical conditions, and more. The entered keywords are sent to the server as search criteria for the data.

[0173] Step 2:

[0174] Upon receiving keywords sent from the terminal, the server searches a database containing company information. The server manipulates the database using SQL queries to extract companies that match the criteria. This process generates a list of companies matching the keywords, which is then used in the next processing step.

[0175] Step 3:

[0176] The server collects detailed financial and capability information for each company based on the extracted list. Here, in addition to information within the data bank, the latest data is obtained using external APIs. All collected data is prepared for analysis by generative intelligence models.

[0177] Step 4:

[0178] The server uses a generative intelligence model to analyze the collected corporate data. Specifically, it uses Python and machine learning frameworks (e.g., TensorFlow, PyTorch) to convert the suitability of each company for alliances, mergers, and acquisitions into a numerical score. This score serves as reference information for users when making decisions.

[0179] Step 5:

[0180] The server receives data in real time from the device's camera and microphone to analyze the user's emotions. Using libraries such as Python's OpenCV and Emotion SDK, it analyzes the user's facial expressions and tone of voice to estimate their emotions.

[0181] Step 6:

[0182] Based on the sentiment analysis results, the server dynamically adjusts the information presented to the user. If positive emotions are detected, detailed analysis results are presented; if negative emotions are detected, concise information focusing on key points is presented.

[0183] Step 7:

[0184] Finally, the server sends the generated score and analysis results to the terminal, where the user can view the information on the interface. This information forms the basis for the user to efficiently and effectively select a company.

[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] Selecting the right partner is crucial in the process of considering collaboration and integration between companies, but making such selections based on vast amounts of company information and complex criteria is not easy. Therefore, there is a need for efficient and scientifically-based selection methods. Furthermore, there is a demand for user-friendly systems that flexibly adapt information presentation based on the user's emotional state.

[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 means for extracting relevant organizations from an information set including corporate attributes based on specific identifiers; means for utilizing generative intelligence to analyze the resource data and capabilities of the extracted organizations; means for generating evaluation values ​​indicating the suitability of each organization for collaboration, integration, and absorption; and means for dynamically adjusting the information presentation method based on the evaluation values ​​and the user's emotional state. This enables efficient selection of appropriate collaboration candidates and the presentation of appropriate information in accordance with the user's emotions.

[0190] "Company attributes" is a general term for information that indicates the characteristics and features of a company, and includes information such as industry, location, size, technological capabilities, and financial status.

[0191] An "information collection" refers to a database or recording medium in which diverse information is aggregated and systematized.

[0192] An "identifier" is a string of characters or symbols used to identify an object, and is used as a search condition in a database.

[0193] An "organization" is a group or structure formed by people coming together for a specific purpose.

[0194] "Resource data" refers to data that a company possesses, including financial information, human resources, and technological resources.

[0195] "Capability" refers to the ability and efficiency with which an organization or individual can perform a specific task or mission.

[0196] "Generative intelligence" is a form of artificial intelligence that learns from large amounts of data and performs inference and prediction.

[0197] "Collaboration" refers to different organizations or individuals working together on a project.

[0198] "Integration" refers to the process of bringing together multiple elements or organizations into a single, unified entity.

[0199] "Absorption" refers to the process where one organization incorporates another organization and makes it a part of itself.

[0200] "Aptitude" refers to qualities or abilities that are suitable for a particular purpose or condition.

[0201] An "evaluation value" is a numerical or level representation of the value or performance of something, based on specific criteria.

[0202] "Emotional state" refers to the emotions and psychological conditions an individual is experiencing at a given time.

[0203] "Information presentation method" refers to the methods and means of how information is presented and provided to users.

[0204] Users can initiate a search based on company attributes by entering specific identifiers, such as industry names or regional conditions, through an application installed on their mobile device. The device sends this information to a server. The server extracts relevant organizations from the information set, including company attributes, and then analyzes the resource data and capabilities of the extracted organizations using generative intelligence. This calculates an evaluation value indicating the suitability of each relevant organization for collaboration, integration, or acquisition.

[0205] Furthermore, the server uses an emotion engine to analyze the user's emotional state and dynamically adjusts how information is presented based on the evaluation score and the user's emotions. This adjustment of information presentation is supported by a generative AI model. For example, if the user's emotions are positive, the results are presented in a way that includes detailed information and additional suggestions. Conversely, if the emotions are negative, the results are presented in a concise format that summarizes the key points.

[0206] This system is based on communication between a cloud server and a smartphone, and utilizes machine learning models (Python, TensorFlow / PyTorch) and sentiment analysis APIs (e.g., Google Cloud Natural Language API). This approach allows users to receive the most relevant information and suggestions without being bothered by unnecessary information.

[0207] As a concrete example, consider a case where a company is looking for a partner for an electronic payment system in the Asian market. When a user enters "electronic payment" and "Asian market" into the app, the device communicates with a server to search for and analyze relevant company candidates. Finally, information is presented to the user based on the analysis results and the user's sentiment.

[0208] Examples of prompts for generative AI models:

[0209] "We would like to select a new business partner. Please incorporate a results display method based on user sentiment data."

[0210] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0211] Step 1:

[0212] The user enters a specific identifier into the application on their mobile device. This identifier may include the industry name or regional conditions. This input data is generated by the device and sent to the server.

[0213] Step 2:

[0214] The server searches the information set based on identifiers received from the user and extracts relevant organizations. During data processing, a database query is generated, and data matching the company attributes is selected. The output is a list of relevant organizations.

[0215] Step 3:

[0216] The server analyzes the extracted organizational resource data and capabilities using generative intelligence. Here, machine learning models are applied as data calculations to determine the suitability of each organization. The output is the evaluation score for each organization.

[0217] Step 4:

[0218] The server uses an emotion engine to analyze the user's emotional state. It takes emotional data obtained from the user's terminal as input, analyzes it, and outputs the user's emotional state.

[0219] Step 5:

[0220] The server dynamically adjusts the information presentation method based on the evaluation value and the user's emotional state. It evaluates the input evaluation value and emotional state, applies logic to change the format of information delivery, and selects the optimal information display format.

[0221] Step 6:

[0222] The server sends information in a formatted manner to the user's terminal and presents the results. The user's terminal receives the output from the server and displays the information to the user in an appropriately visualized format.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] [Second Embodiment]

[0227] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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".

[0239] This invention is a system for streamlining the selection of candidate companies when companies are considering alliances, mergers, or acquisitions. Specifically, it enables users to quickly and objectively select candidate companies through the use of a database containing company information and analysis by generative artificial intelligence.

[0240] The terminal has an interface that accepts user input. Users enter specific keywords into the terminal to narrow down potential alliance, merger, or acquisition candidates. These keywords may include desired industries, relevant technical terms, and geographical conditions.

[0241] The server uses keywords received from the terminal to search a database containing company information. This search results in a list of relevant companies. Company information includes company name, location, industry, as well as publicly available financial data and capabilities.

[0242] Next, the server uses generative artificial intelligence to analyze the extracted financial data and capabilities of the companies. As a result of this analysis, a score is generated indicating the suitability of each company for alliances, mergers, and acquisitions. The generated score reflects each company's strategic fit, growth potential, and financial health.

[0243] For example, if a user wishes to form an alliance with a North American company that possesses AI technology, they would enter keywords such as "AI technology" and "North America" ​​into their terminal. Based on this, the server searches its database for relevant companies, analyzes the financial data of the extracted companies, and generates an optimal score. As a result, companies with high scores are prioritized and listed, providing the user with the basic information needed to proceed to the next step.

[0244] This process allows users to efficiently select candidate companies and focus on subsequent negotiations and analysis. The system reduces the burden of manual information gathering, enabling faster and more accurate decision-making.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] Users enter keywords into their terminals to identify target companies for alliances, mergers, or acquisitions. These keywords can include industry names, technical terms, geographical locations, and more.

[0248] Step 2:

[0249] The terminal collects the entered keywords and sends them to the server.

[0250] Step 3:

[0251] The server uses the received keywords to search a database containing company information and then generates a list of companies that match the criteria.

[0252] Step 4:

[0253] The server then retrieves more detailed financial and capability information for each company from a database or external data source from the generated list of companies.

[0254] Step 5:

[0255] The server inputs the acquired data into generative artificial intelligence to perform analysis including each company's financial health, strategic fit, and growth potential.

[0256] Step 6:

[0257] The server assigns a score to each company based on the analysis results, and evaluates their suitability for alliances, mergers, and acquisitions.

[0258] Step 7:

[0259] The server returns the scoring results and an overview of each company to the terminal.

[0260] Step 8:

[0261] Users review the scoring results displayed on their device and decide which companies to proceed to the next selection process with.

[0262] (Example 1)

[0263] 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."

[0264] When companies engage in alliances, mergers, or acquisitions, quickly and efficiently identifying suitable candidates is challenging. The process of gathering and analyzing relevant information is time-consuming, labor-intensive, and often relies on subjective judgment. Therefore, a system is needed to select candidate companies based on objective and fair criteria.

[0265] 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.

[0266] In this invention, the server includes means for receiving specific input information, means for searching for information in an information aggregate based on the input information and extracting relevant information, and means for utilizing generative automated intelligence to analyze the numerical data and skill information of the extracted information. This enables the user to quickly and objectively evaluate the suitability of linking, retrieving, and integrating tasks and select the optimal candidate.

[0267] "Specific input information" refers to information provided by the user to the system, including industry names, technical terms, and regional conditions.

[0268] An "information aggregate" refers to a database or other means of collecting information used to store data about a company.

[0269] "Related information" refers to company-related data that the system presents to the user, extracted based on specific input information.

[0270] "Numerical data and skills information" refers to detailed information about a company's financial situation and capabilities, and serves as evaluation criteria in company selection.

[0271] "Generative automated intelligence" is a form of artificial intelligence technology that is equipped with algorithms that analyze diverse data and generate evaluation values.

[0272] "Suitability for mergers, acquisitions, and integrations" refers to evaluation criteria that demonstrate a company's suitability for alliances, mergers, and acquisitions with other companies.

[0273] The "evaluation value" is a numerical value calculated by generative automated intelligence, indicating the suitability of a particular company for alliances, mergers, or acquisitions.

[0274] This invention is for selecting appropriate candidates when considering corporate alliances, mergers, or acquisitions using an information processing device. Specifically, it involves the interaction of a server, a terminal, and a user.

[0275] First, the user provides specific input information through the terminal interface. This includes the name of the relevant industry sector, technical terms, and regional conditions. The user can do this through text input or voice input.

[0276] Next, the terminal sends this input information to the server. The server searches a database, which is a collection of information, and extracts company information related to the input information. This process utilizes a high-speed search algorithm and a database management system.

[0277] The server then uses generative automated intelligence to analyze the extracted numerical data and skills information of the companies. The generative automated intelligence assesses each company's financial health, growth potential, and strategic suitability, generating evaluation values ​​that indicate its suitability for merger-related or acquisition and integration work. This analysis utilizes software powered by machine learning algorithms.

[0278] Finally, the server sends the evaluation results to the terminal, which then presents them to the user. Based on the presented evaluation values, the user can then make the next decision.

[0279] As a specific example, when a user hopes to form an alliance with a North American company possessing AI technology, the user inputs prompt texts such as "AI technology" and "North America" into the terminal. Based on this, the server searches the database, extracts relevant companies, analyzes them, and presents an optimal evaluation value. As a result, the user can efficiently select candidate companies.

[0280] The flow of the specific process in Example 1 will be described using FIG. 11.

[0281] Step 1:

[0282] The user provides specific input information via the terminal interface. Specifically, using a keyboard or voice input function, the user inputs the industrial field name, skill terms, geographical conditions, etc. The input information is converted into digital data within the terminal and prepared for transmission to the server.

[0283] Input: Specific input information provided by keyboard or voice input

[0284] Output: Information data in digital format for transmission to the server

[0285] Step 2:

[0286] The terminal transmits the input information received from the user to the server. For the transmission, a secure communication protocol via an Internet connection is used. The server formats the received data directly into a query for database search.

[0287] Input: Information data in digital format from the terminal

[0288] Output: Query for search reaching the server

[0289] Step 3:

[0290] The server searches the corporate information database, which is a collection of information, based on the received query. A high-speed search algorithm is used to extract relevant corporate information. The found information is organized in a list format and passed on to the next processing step.

[0291] Input: Search query on the server

[0292] Output: List of related company information

[0293] Step 4:

[0294] The server uses generative automated intelligence to analyze the numerical and skills data of extracted company information. In this process, machine learning algorithms evaluate each company's financial health and growth potential, and generate evaluation values ​​indicating their suitability for integration.

[0295] Input: List of extracted company information

[0296] Output: Evaluation values ​​for each company

[0297] Step 5:

[0298] The server ranks companies based on the generated evaluation scores and sends this ranking to the terminal. The ranked information is then organized in order of priority to support the user's decision-making.

[0299] Input: Evaluation value for each company

[0300] Output: Ranked company information

[0301] Step 6:

[0302] The terminal displays ranked company information received from the server on its screen. The user reviews this information and makes decisions for the next step based on the evaluation scores. Specifically, they can request additional data or view detailed information about the selected companies.

[0303] Input: Ranked enterprise information

[0304] Output: Specific enterprise information displayed to the user

[0305] (Application Example 1)

[0306] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0307] In the conventional enterprise selection process, there was a problem that it was difficult to efficiently select enterprises that are candidates for alliances, mergers, and acquisitions. In addition, the information collection and analysis required for selection took time and effort, and decision-making was often delayed. Furthermore, since there were insufficient criteria and tools for objectively evaluating the suitability of each enterprise, users could not quickly compare and consider. Means for solving these problems and performing enterprise selection more efficiently and accurately are required.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0309] In this invention, the server includes means for extracting related enterprises from a database containing enterprise information based on specific keywords, means for utilizing generative data processing technology to analyze the financial data and capabilities of the extracted enterprises, means for calculating the strength indicating the suitability of cooperation or organizational reorganization of each enterprise, means for visually presenting the results to the user based on the strength, and an intuitive information display device for displaying candidates that meet the conditions based on the user's input. As a result, the user can grasp the details of candidate enterprises in a short time and make an optimal selection.

[0310] The "database containing enterprise information" is a digitally stored material that accumulates information on various enterprises, including company names, locations, industries, and publicly available financial data and capabilities.

[0311] "Methods for extracting relevant companies based on specific keywords" refers to algorithms or processes for selecting companies from a database that match the conditions specified by the user.

[0312] "Methods that utilize generative data processing technology" refer to techniques that use generative artificial intelligence and advanced data analysis technologies to process extracted company information and obtain meaningful analytical results.

[0313] "Means for calculating the strength of suitability for collaboration or organizational restructuring" refers to a method for quantitatively evaluating how suitable companies are for collaboration or integration and displaying it as a score or index.

[0314] "Means of visually presenting results to users" refers to interfaces and tools that visualize analysis results in an easy-to-understand way for users and display information in various forms.

[0315] An "intuitive information display device" refers to a display device or software designed to allow users to easily understand and operate information.

[0316] This invention includes a system for efficiently selecting and evaluating the suitability of companies. This system realizes the invention through the following main processes.

[0317] The system's core server utilizes a database of stored company information to extract relevant companies that match specific keywords based on user input data. Specific database searches include SQL query processing and full-text searches using Apache Lucene. Users access the system using smartphones or desktop terminals and input their desired criteria (e.g., "AI technology," "North America").

[0318] The server analyzes the extracted financial data and capabilities of companies using generative data processing technologies, such as TensorFlow and PyTorch. This technology is crucial for evaluating a company's financial situation and strategic fit in the market. The analysis of the generated data yields a strength score indicating the suitability of each company's collaborations and organizational restructuring.

[0319] Users receive results in a visually easy-to-understand format, such as dashboards or graphs, to check their intensity. Data visualization libraries like D3.js are used to achieve this. In addition, frameworks such as React and Angular are used in the user interface to provide an intuitive information display system, enhancing usability.

[0320] For example, if a user wants to find the best partner in a particular technology field as part of their preparations for participating in an industrial trade show, they can use the system to quickly list companies that meet their criteria and narrow down promising candidates by comparing the strengths of each company.

[0321] An example of a prompt message is, "List companies that meet the following criteria and generate scores for financial health and growth potential: AI technology, North America." This helps users make appropriate decisions quickly and efficiently.

[0322] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0323] Step 1:

[0324] The server receives user input data sent from the terminal. This input data includes conditions and keywords selected by the user (e.g., "AI technology," "North America"). The server uses this data to query a database containing company information and extract companies that match the conditions. A list of related companies is generated as output.

[0325] Step 2:

[0326] The server uses a generative AI model to analyze the extracted list of companies. Financial data and capability information for each company are used as input. The server processes and calculates the strength of each company's suitability for collaboration or restructuring using machine learning algorithms. This information is necessary for subsequent processing.

[0327] Step 3:

[0328] The server prepares data to visually present the results to the user based on the generated intensity. Using a data visualization library, it processes the data into graphs and dashboards for visualization. The output is a visual representation of the intensity in a user-friendly format.

[0329] Step 4:

[0330] The terminal receives visualization data sent from the server and displays it on the user interface. Users can intuitively view and compare information through operations on the terminal. The output provides detailed information on companies individually selected by the user, which can then be used for subsequent decision-making.

[0331] Step 5:

[0332] Based on the information presented, the user retrieves further details about companies that match their selected criteria and generates additional prompts as needed. This allows them to instruct the system to take the next action, enabling further information gathering and analysis.

[0333] 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.

[0334] This invention is a system for companies to select appropriate candidate companies when forming alliances, mergers, or acquisitions, and further provides more personalized information by combining it with an emotion engine that recognizes user emotions.

[0335] The terminal has an interface that accepts specific keywords from the user. The user enters keywords such as industry names, technical terms, and geographical conditions based on their preferences. The terminal then sends this information to the server.

[0336] The server uses the received keywords to search a database containing company information and generates a list of relevant companies that match the criteria. The server then retrieves financial and capability information for the listed companies from the database and external data sources.

[0337] Furthermore, the server uses generative artificial intelligence to analyze the acquired data and generate a score that quantifies the suitability of each company for alliances, mergers, and acquisitions. This scoring allows users to efficiently select companies based on scientifically supported information.

[0338] A key feature of this invention is the integration of an emotion engine to analyze the user's emotions during input and when reviewing scoring results. This emotion analysis allows the server to dynamically adjust the format and method of information presented according to the user's emotions. For example, if the user has negative emotions, the engine simplifies the list display and provides only important highlights. Conversely, if positive emotions are detected, more detailed analysis results and recommendations are presented more explicitly.

[0339] For example, if a user wishes to partner with a technology company in an emerging market, they would enter keywords such as "technology" and "emerging market" into their device. The server would then extract relevant companies from its database and perform scoring based on these keywords. The emotion engine would analyze the user's response, and the resulting information would flexibly change to match the user's intentions and desires, thus supporting optimal decision-making.

[0340] This system is a comprehensive tool designed to improve user convenience while also enhancing the accuracy and efficiency of candidate company selection.

[0341] The following describes the processing flow.

[0342] Step 1:

[0343] Users enter keywords related to their desired conditions for alliances, mergers, or acquisitions with companies into the terminal. This allows them to set criteria to narrow down potential companies that meet their objectives.

[0344] Step 2:

[0345] The terminal sends the received keywords to the server as structured data. This information acts as a trigger for database searches.

[0346] Step 3:

[0347] The server searches multiple databases containing company information based on the received keywords and extracts relevant companies that match the criteria. This process takes into account factors such as the company's industry, location, and technology.

[0348] Step 4:

[0349] The server collects detailed financial and capability information for the selected companies from databases and external sources. This clarifies the economic and technological background of each company.

[0350] Step 5:

[0351] The server inputs the collected data into generative artificial intelligence to analyze companies' financial health, growth potential, and strategic fit. As a result, it generates a score indicating the suitability of each company.

[0352] Step 6:

[0353] The server sends the scoring results to the sentiment engine, which infers the user's emotions based on the user's past response data and real-time feedback. This information is then used to dynamically adjust how the information is displayed.

[0354] Step 7:

[0355] The device presents the user with a customized scoring result based on the analysis of the emotion engine. The content is adjusted as needed, providing detailed information for positive emotions and a summary for negative emotions.

[0356] Step 8:

[0357] Based on the information displayed on their device, users select companies that are potential candidates for alliances, mergers, or acquisitions. Throughout this process, the sentiment engine continuously observes the user's reactions and modifies the information presented as needed.

[0358] (Example 2)

[0359] 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".

[0360] When companies engage in alliances, mergers, or acquisitions, selecting the right candidates from a vast amount of information is extremely difficult. Furthermore, user subjectivity and emotions can influence the selection process, leading to inefficient decision-making. There is a need to solve this problem and provide users with the optimal choice.

[0361] 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.

[0362] In this invention, the server includes means for extracting relevant organizations from a data bank containing corporate information, means for utilizing a generative intelligence model to analyze the financial information and capabilities of the extracted organizations, and means for dynamically adjusting the information using sentiment analysis. This makes it possible to select candidate companies based on scientific evidence while adjusting the display method according to the user's emotions.

[0363] "Company information" refers to all information about a company, including its name, address, industry, business activities, financial information, business partners, and other related matters.

[0364] A "data bank" is a collection of information that is systematically organized and stored in a format that allows for searching and analysis.

[0365] "Relevant organizations" refers to companies and organizations extracted based on specified conditions or keywords.

[0366] "Means of extraction" refers to methods and techniques for retrieving data that meets specific conditions from a data bank.

[0367] A "generative intelligence model" is a type of artificial intelligence trained to automatically make predictions and classifications based on input data.

[0368] "Emotion analysis" is a technology that estimates a user's emotions from their facial expressions, voice, and input content, and adjusts the system's operation based on those emotions.

[0369] "Means of dynamic adjustment" refers to methods for flexibly changing the way information is presented or its content in response to changes in circumstances or conditions.

[0370] A description of embodiments for carrying out this invention will be given.

[0371] The server first builds a database containing company information. This database includes detailed information about companies, such as their financial information, industry, business activities, and geographical location. This allows the server to efficiently search and extract relevant organizations based on specific keywords. The server performs data retrieval using database query languages ​​such as SQL.

[0372] Next, the server utilizes generative intelligence models to analyze the extracted financial information and capabilities of the companies. These are implemented using programming languages ​​such as Python and machine learning frameworks like TensorFlow and PyTorch. This generative intelligence model quantifies the suitability of companies for alliances and mergers / acquisitions, generating a score. The generated score is based on scientific evidence and serves as an important indicator in company selection.

[0373] Furthermore, the server implements emotion analysis technology to estimate the user's emotions as they view information through the interface. It uses the device's built-in camera and microphone to capture the user's facial expressions and voice tone, and performs emotion analysis based on this data. This analysis utilizes libraries such as Python's OpenCV and Emotion SDK. Based on the analysis results, the server dynamically adjusts the information displayed to reflect the user's emotions. For example, if the user is showing positive emotions, it presents detailed results from the generative AI model's analysis.

[0374] As a concrete example, consider a scenario where a user is seeking partnerships with technology companies in emerging markets. In this case, the user enters keywords such as "emerging markets" and "technology" into their device. The server extracts relevant companies from a database based on these keywords and generates evaluation scores using a generative intelligence model.

[0375] An example of a prompt message used by the server is, "Analyze the candidates for the best technology companies in emerging markets," which is input to the generative AI model. This prompt allows the generative AI model to perform appropriate information analysis and ultimately provide the information the user is looking for.

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The user enters keywords indicating their desired conditions using a terminal. This interface allows users to enter industry names, technical terms, geographical conditions, and more. The entered keywords are sent to the server as search criteria for the data.

[0379] Step 2:

[0380] Upon receiving keywords sent from the terminal, the server searches a database containing company information. The server manipulates the database using SQL queries to extract companies that match the criteria. This process generates a list of companies matching the keywords, which is then used in the next processing step.

[0381] Step 3:

[0382] The server collects detailed financial and capability information for each company based on the extracted list. Here, in addition to information within the data bank, the latest data is obtained using external APIs. All collected data is prepared for analysis by generative intelligence models.

[0383] Step 4:

[0384] The server uses a generative intelligence model to analyze the collected corporate data. Specifically, it uses Python and machine learning frameworks (e.g., TensorFlow, PyTorch) to convert the suitability of each company for alliances, mergers, and acquisitions into a numerical score. This score serves as reference information for users when making decisions.

[0385] Step 5:

[0386] The server receives data in real time from the device's camera and microphone to analyze the user's emotions. Using libraries such as Python's OpenCV and Emotion SDK, it analyzes the user's facial expressions and tone of voice to estimate their emotions.

[0387] Step 6:

[0388] Based on the sentiment analysis results, the server dynamically adjusts the information presented to the user. If positive emotions are detected, detailed analysis results are presented; if negative emotions are detected, concise information focusing on key points is presented.

[0389] Step 7:

[0390] Finally, the server sends the generated score and analysis results to the terminal, where the user can view the information on the interface. This information forms the basis for the user to efficiently and effectively select a company.

[0391] (Application Example 2)

[0392] 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."

[0393] Selecting the right partner is crucial in the process of considering collaboration and integration between companies, but making such selections based on vast amounts of company information and complex criteria is not easy. Therefore, there is a need for efficient and scientifically-based selection methods. Furthermore, there is a demand for user-friendly systems that flexibly adapt information presentation based on the user's emotional state.

[0394] 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.

[0395] In this invention, the server includes means for extracting relevant organizations from an information set including corporate attributes based on specific identifiers; means for utilizing generative intelligence to analyze the resource data and capabilities of the extracted organizations; means for generating evaluation values ​​indicating the suitability of each organization for collaboration, integration, and absorption; and means for dynamically adjusting the information presentation method based on the evaluation values ​​and the user's emotional state. This enables efficient selection of appropriate collaboration candidates and the presentation of appropriate information in accordance with the user's emotions.

[0396] "Company attributes" is a general term for information that indicates the characteristics and features of a company, and includes information such as industry, location, size, technological capabilities, and financial status.

[0397] An "information collection" refers to a database or recording medium in which diverse information is aggregated and systematized.

[0398] An "identifier" is a string of characters or symbols used to identify an object, and is used as a search condition in a database.

[0399] An "organization" is a group or structure formed by people coming together for a specific purpose.

[0400] "Resource data" refers to data that a company possesses, including financial information, human resources, and technological resources.

[0401] "Capability" refers to the ability and efficiency with which an organization or individual can perform a specific task or mission.

[0402] "Generative intelligence" is a form of artificial intelligence that learns from large amounts of data and performs inference and prediction.

[0403] "Collaboration" refers to different organizations or individuals working together on a project.

[0404] "Integration" refers to the process of bringing together multiple elements or organizations into a single, unified entity.

[0405] "Absorption" refers to the process where one organization incorporates another organization and makes it a part of itself.

[0406] "Aptitude" refers to qualities or abilities that are suitable for a particular purpose or condition.

[0407] An "evaluation value" is a numerical or level representation of the value or performance of something, based on specific criteria.

[0408] "Emotional state" refers to the emotions and psychological conditions an individual is experiencing at a given time.

[0409] "Information presentation method" refers to the methods and means of how information is presented and provided to users.

[0410] Users can initiate a search based on company attributes by entering specific identifiers, such as industry names or regional conditions, through an application installed on their mobile device. The device sends this information to a server. The server extracts relevant organizations from the information set, including company attributes, and then analyzes the resource data and capabilities of the extracted organizations using generative intelligence. This calculates an evaluation value indicating the suitability of each relevant organization for collaboration, integration, or acquisition.

[0411] Furthermore, the server uses an emotion engine to analyze the user's emotional state and dynamically adjusts how information is presented based on the evaluation score and the user's emotions. This adjustment of information presentation is supported by a generative AI model. For example, if the user's emotions are positive, the results are presented in a way that includes detailed information and additional suggestions. Conversely, if the emotions are negative, the results are presented in a concise format that summarizes the key points.

[0412] This system is based on communication between a cloud server and a smartphone, and utilizes machine learning models (Python, TensorFlow / PyTorch) and sentiment analysis APIs (e.g., Google Cloud Natural Language API). This approach allows users to receive the most relevant information and suggestions without being bothered by unnecessary information.

[0413] As a concrete example, consider a case where a company is looking for a partner for an electronic payment system in the Asian market. When a user enters "electronic payment" and "Asian market" into the app, the device communicates with a server to search for and analyze relevant company candidates. Finally, information is presented to the user based on the analysis results and the user's sentiment.

[0414] Examples of prompts for generative AI models:

[0415] "We would like to select a new business partner. Please incorporate a results display method based on user sentiment data."

[0416] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0417] Step 1:

[0418] The user enters a specific identifier into the application on their mobile device. This identifier may include the industry name or regional conditions. This input data is generated by the device and sent to the server.

[0419] Step 2:

[0420] The server searches the information set based on identifiers received from the user and extracts relevant organizations. During data processing, a database query is generated, and data matching the company attributes is selected. The output is a list of relevant organizations.

[0421] Step 3:

[0422] The server analyzes the extracted organizational resource data and capabilities using generative intelligence. Here, machine learning models are applied as data calculations to determine the suitability of each organization. The output is the evaluation score for each organization.

[0423] Step 4:

[0424] The server uses an emotion engine to analyze the user's emotional state. It takes emotional data obtained from the user's terminal as input, analyzes it, and outputs the user's emotional state.

[0425] Step 5:

[0426] The server dynamically adjusts the information presentation method based on the evaluation value and the user's emotional state. It evaluates the input evaluation value and emotional state, applies logic to change the format of information delivery, and selects the optimal information display format.

[0427] Step 6:

[0428] The server sends information in a formatted manner to the user's terminal and presents the results. The user's terminal receives the output from the server and displays the information to the user in an appropriately visualized format.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] [Third Embodiment]

[0433] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0434] 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.

[0435] 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).

[0436] 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.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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".

[0445] This invention is a system for streamlining the selection of candidate companies when companies are considering alliances, mergers, or acquisitions. Specifically, it enables users to quickly and objectively select candidate companies through the use of a database containing company information and analysis by generative artificial intelligence.

[0446] The terminal has an interface that accepts user input. Users enter specific keywords into the terminal to narrow down potential alliance, merger, or acquisition candidates. These keywords may include desired industries, relevant technical terms, and geographical conditions.

[0447] The server uses keywords received from the terminal to search a database containing company information. This search results in a list of relevant companies. Company information includes company name, location, industry, as well as publicly available financial data and capabilities.

[0448] Next, the server uses generative artificial intelligence to analyze the extracted financial data and capabilities of the companies. As a result of this analysis, a score is generated indicating the suitability of each company for alliances, mergers, and acquisitions. The generated score reflects each company's strategic fit, growth potential, and financial health.

[0449] For example, if a user wishes to form an alliance with a North American company that possesses AI technology, they would enter keywords such as "AI technology" and "North America" ​​into their terminal. Based on this, the server searches its database for relevant companies, analyzes the financial data of the extracted companies, and generates an optimal score. As a result, companies with high scores are prioritized and listed, providing the user with the basic information needed to proceed to the next step.

[0450] This process allows users to efficiently select candidate companies and focus on subsequent negotiations and analysis. The system reduces the burden of manual information gathering, enabling faster and more accurate decision-making.

[0451] The following describes the processing flow.

[0452] Step 1:

[0453] Users enter keywords into their terminals to identify target companies for alliances, mergers, or acquisitions. These keywords can include industry names, technical terms, geographical locations, and more.

[0454] Step 2:

[0455] The terminal collects the entered keywords and sends them to the server.

[0456] Step 3:

[0457] The server uses the received keywords to search a database containing company information and then generates a list of companies that match the criteria.

[0458] Step 4:

[0459] The server then retrieves more detailed financial and capability information for each company from a database or external data source from the generated list of companies.

[0460] Step 5:

[0461] The server inputs the acquired data into generative artificial intelligence to perform analysis including each company's financial health, strategic fit, and growth potential.

[0462] Step 6:

[0463] The server assigns a score to each company based on the analysis results, and evaluates their suitability for alliances, mergers, and acquisitions.

[0464] Step 7:

[0465] The server returns the scoring results and an overview of each company to the terminal.

[0466] Step 8:

[0467] Users review the scoring results displayed on their device and decide which companies to proceed to the next selection process with.

[0468] (Example 1)

[0469] 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."

[0470] When companies engage in alliances, mergers, or acquisitions, quickly and efficiently identifying suitable candidates is challenging. The process of gathering and analyzing relevant information is time-consuming, labor-intensive, and often relies on subjective judgment. Therefore, a system is needed to select candidate companies based on objective and fair criteria.

[0471] 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.

[0472] In this invention, the server includes means for receiving specific input information, means for searching for information in an information aggregate based on the input information and extracting relevant information, and means for utilizing generative automated intelligence to analyze the numerical data and skill information of the extracted information. This enables the user to quickly and objectively evaluate the suitability of linking, retrieving, and integrating tasks and select the optimal candidate.

[0473] "Specific input information" refers to information provided by the user to the system, including industry names, technical terms, and regional conditions.

[0474] An "information aggregate" refers to a database or other means of collecting information used to store data about a company.

[0475] "Related information" refers to company-related data that the system presents to the user, extracted based on specific input information.

[0476] "Numerical data and skills information" refers to detailed information about a company's financial situation and capabilities, and serves as evaluation criteria in company selection.

[0477] "Generative automated intelligence" is a form of artificial intelligence technology that is equipped with algorithms that analyze diverse data and generate evaluation values.

[0478] "Suitability for mergers, acquisitions, and integrations" refers to evaluation criteria that demonstrate a company's suitability for alliances, mergers, and acquisitions with other companies.

[0479] The "evaluation value" is a numerical value calculated by generative automated intelligence, indicating the suitability of a particular company for alliances, mergers, or acquisitions.

[0480] This invention is for selecting appropriate candidates when considering corporate alliances, mergers, or acquisitions using an information processing device. Specifically, it involves the interaction of a server, a terminal, and a user.

[0481] First, the user provides specific input information through the terminal interface. This includes the name of the relevant industry sector, technical terms, and regional conditions. The user can do this through text input or voice input.

[0482] Next, the terminal sends this input information to the server. The server searches a database, which is a collection of information, and extracts company information related to the input information. This process utilizes a high-speed search algorithm and a database management system.

[0483] The server then uses generative automated intelligence to analyze the extracted numerical data and skills information of the companies. The generative automated intelligence assesses each company's financial health, growth potential, and strategic suitability, generating evaluation values ​​that indicate its suitability for merger-related or acquisition and integration work. This analysis utilizes software powered by machine learning algorithms.

[0484] Finally, the server sends the evaluation results to the terminal, which then presents them to the user. Based on the presented evaluation values, the user can then make the next decision.

[0485] For example, if a user wishes to form an alliance with a North American company possessing AI technology, they would enter prompts such as "AI technology" or "North America" ​​into their terminal. Based on this, the server would search its database to extract relevant companies, analyze them, and present the optimal evaluation score. This allows the user to efficiently select candidate companies.

[0486] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0487] Step 1:

[0488] The user provides specific input information through the terminal's interface. Specifically, they input industry names, technical terms, geographical conditions, etc., using the keyboard or voice input function. The input information is converted into digital data within the terminal and prepared for transmission to the server.

[0489] Input: Specific input information provided via keyboard or voice input.

[0490] Output: Digital information data for transmission to the server.

[0491] Step 2:

[0492] The terminal sends the input information received from the user to the server. A secure communication protocol is used for transmission via the internet connection. The server then formats the received data directly into a query for database retrieval.

[0493] Input: Digital information data from a terminal.

[0494] Output: Search queries that reached the server

[0495] Step 3:

[0496] The server searches the corporate information database, which is a collection of information, based on the received query. A high-speed search algorithm is used to extract relevant corporate information. The found information is organized in a list format and passed on to the next processing step.

[0497] Input: Search query on the server

[0498] Output: List of related company information

[0499] Step 4:

[0500] The server uses generative automated intelligence to analyze the numerical and skills data of extracted company information. In this process, machine learning algorithms evaluate each company's financial health and growth potential, and generate evaluation values ​​indicating their suitability for integration.

[0501] Input: List of extracted company information

[0502] Output: Evaluation values ​​for each company

[0503] Step 5:

[0504] The server ranks companies based on the generated evaluation scores and sends this ranking to the terminal. The ranked information is then organized in order of priority to support the user's decision-making.

[0505] Input: Evaluation value for each company

[0506] Output: Ranked company information

[0507] Step 6:

[0508] The terminal displays ranked company information received from the server on its screen. The user reviews this information and makes decisions for the next step based on the evaluation scores. Specifically, they can request additional data or view detailed information about the selected companies.

[0509] Input: Ranked company information

[0510] Output: Specific company information displayed to the user

[0511] (Application Example 1)

[0512] 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."

[0513] Traditional company selection processes have presented challenges in efficiently selecting potential alliance, merger, and acquisition candidates. Furthermore, the time-consuming and labor-intensive information gathering and analysis required for selection often led to delays in decision-making. Additionally, a lack of objective criteria and tools for evaluating each company's suitability prevented users from quickly comparing and evaluating options. There is a need for solutions to these challenges, enabling more efficient and accurate company selection.

[0514] 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.

[0515] In this invention, the server includes means for extracting relevant companies from a database containing company information based on specific keywords; means for utilizing generative data processing technology to analyze the financial data and capabilities of the extracted companies; means for calculating the strength indicating the suitability of each company for collaboration or organizational restructuring; means for visually presenting the results to the user based on the strength; and an intuitive information display device for displaying candidates that meet the criteria based on user input. This enables the user to quickly grasp the details of candidate companies and make the optimal selection.

[0516] A "database containing corporate information" is a digital collection of information about various companies, including company name, location, industry, and publicly available financial data and capabilities.

[0517] "Methods for extracting relevant companies based on specific keywords" refers to algorithms or processes for selecting companies from a database that match the conditions specified by the user.

[0518] "Methods that utilize generative data processing technology" refer to techniques that use generative artificial intelligence and advanced data analysis technologies to process extracted company information and obtain meaningful analytical results.

[0519] "Means for calculating the strength of suitability for collaboration or organizational restructuring" refers to a method for quantitatively evaluating how suitable companies are for collaboration or integration and displaying it as a score or index.

[0520] "Means of visually presenting results to users" refers to interfaces and tools that visualize analysis results in an easy-to-understand way for users and display information in various forms.

[0521] An "intuitive information display device" refers to a display device or software designed to allow users to easily understand and operate information.

[0522] This invention includes a system for efficiently selecting and evaluating the suitability of companies. This system realizes the invention through the following main processes.

[0523] The system's core server utilizes a database of stored company information to extract relevant companies that match specific keywords based on user input data. Specific database searches include SQL query processing and full-text searches using Apache Lucene. Users access the system using smartphones or desktop terminals and input their desired criteria (e.g., "AI technology," "North America").

[0524] The server analyzes the extracted financial data and capabilities of companies using generative data processing technologies, such as TensorFlow and PyTorch. This technology is crucial for evaluating a company's financial situation and strategic fit in the market. The analysis of the generated data yields a strength score indicating the suitability of each company's collaborations and organizational restructuring.

[0525] Users receive results in a visually easy-to-understand format, such as dashboards or graphs, to check their intensity. Data visualization libraries like D3.js are used to achieve this. In addition, frameworks such as React and Angular are used in the user interface to provide an intuitive information display system, enhancing usability.

[0526] For example, if a user wants to find the best partner in a particular technology field as part of their preparations for participating in an industrial trade show, they can use the system to quickly list companies that meet their criteria and narrow down promising candidates by comparing the strengths of each company.

[0527] An example of a prompt message is, "List companies that meet the following criteria and generate scores for financial health and growth potential: AI technology, North America." This helps users make appropriate decisions quickly and efficiently.

[0528] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0529] Step 1:

[0530] The server receives user input data sent from the terminal. This input data includes conditions and keywords selected by the user (e.g., "AI technology," "North America"). The server uses this data to query a database containing company information and extract companies that match the conditions. A list of related companies is generated as output.

[0531] Step 2:

[0532] The server uses a generative AI model to analyze the extracted list of companies. Financial data and capability information for each company are used as input. The server processes and calculates the strength of each company's suitability for collaboration or restructuring using machine learning algorithms. This information is necessary for subsequent processing.

[0533] Step 3:

[0534] The server prepares data to visually present the results to the user based on the generated intensity. Using a data visualization library, it processes the data into graphs and dashboards for visualization. The output is a visual representation of the intensity in a user-friendly format.

[0535] Step 4:

[0536] The terminal receives visualization data sent from the server and displays it on the user interface. Users can intuitively view and compare information through operations on the terminal. The output provides detailed information on companies individually selected by the user, which can then be used for subsequent decision-making.

[0537] Step 5:

[0538] Based on the information presented, the user retrieves further details about companies that match their selected criteria and generates additional prompts as needed. This allows them to instruct the system to take the next action, enabling further information gathering and analysis.

[0539] 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.

[0540] This invention is a system for companies to select appropriate candidate companies when forming alliances, mergers, or acquisitions, and further provides more personalized information by combining it with an emotion engine that recognizes user emotions.

[0541] The terminal has an interface that accepts specific keywords from the user. The user enters keywords such as industry names, technical terms, and geographical conditions based on their preferences. The terminal then sends this information to the server.

[0542] The server uses the received keywords to search a database containing company information and generates a list of relevant companies that match the criteria. The server then retrieves financial and capability information for the listed companies from the database and external data sources.

[0543] Furthermore, the server uses generative artificial intelligence to analyze the acquired data and generate a score that quantifies the suitability of each company for alliances, mergers, and acquisitions. This scoring allows users to efficiently select companies based on scientifically supported information.

[0544] A key feature of this invention is the integration of an emotion engine to analyze the user's emotions during input and when reviewing scoring results. This emotion analysis allows the server to dynamically adjust the format and method of information presented according to the user's emotions. For example, if the user has negative emotions, the engine simplifies the list display and provides only important highlights. Conversely, if positive emotions are detected, more detailed analysis results and recommendations are presented more explicitly.

[0545] For example, if a user wishes to partner with a technology company in an emerging market, they would enter keywords such as "technology" and "emerging market" into their device. The server would then extract relevant companies from its database and perform scoring based on these keywords. The emotion engine would analyze the user's response, and the resulting information would flexibly change to match the user's intentions and desires, thus supporting optimal decision-making.

[0546] This system is a comprehensive tool designed to improve user convenience while also enhancing the accuracy and efficiency of candidate company selection.

[0547] The following describes the processing flow.

[0548] Step 1:

[0549] Users enter keywords related to their desired conditions for alliances, mergers, or acquisitions with companies into the terminal. This allows them to set criteria to narrow down potential companies that meet their objectives.

[0550] Step 2:

[0551] The terminal sends the received keywords to the server as structured data. This information acts as a trigger for database searches.

[0552] Step 3:

[0553] The server searches multiple databases containing company information based on the received keywords and extracts relevant companies that match the criteria. This process takes into account factors such as the company's industry, location, and technology.

[0554] Step 4:

[0555] The server collects detailed financial and capability information for the selected companies from databases and external sources. This clarifies the economic and technological background of each company.

[0556] Step 5:

[0557] The server inputs the collected data into generative artificial intelligence to analyze companies' financial health, growth potential, and strategic fit. As a result, it generates a score indicating the suitability of each company.

[0558] Step 6:

[0559] The server sends the scoring results to the sentiment engine, which infers the user's emotions based on the user's past response data and real-time feedback. This information is then used to dynamically adjust how the information is displayed.

[0560] Step 7:

[0561] The device presents the user with a customized scoring result based on the analysis of the emotion engine. The content is adjusted as needed, providing detailed information for positive emotions and a summary for negative emotions.

[0562] Step 8:

[0563] Based on the information displayed on their device, users select companies that are potential candidates for alliances, mergers, or acquisitions. Throughout this process, the sentiment engine continuously observes the user's reactions and modifies the information presented as needed.

[0564] (Example 2)

[0565] 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."

[0566] When companies engage in alliances, mergers, or acquisitions, selecting the right candidates from a vast amount of information is extremely difficult. Furthermore, user subjectivity and emotions can influence the selection process, leading to inefficient decision-making. There is a need to solve this problem and provide users with the optimal choice.

[0567] 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.

[0568] In this invention, the server includes means for extracting relevant organizations from a data bank containing corporate information, means for utilizing a generative intelligence model to analyze the financial information and capabilities of the extracted organizations, and means for dynamically adjusting the information using sentiment analysis. This makes it possible to select candidate companies based on scientific evidence while adjusting the display method according to the user's emotions.

[0569] "Company information" refers to all information about a company, including its name, address, industry, business activities, financial information, business partners, and other related matters.

[0570] A "data bank" is a collection of information that is systematically organized and stored in a format that allows for searching and analysis.

[0571] "Relevant organizations" refers to companies and organizations extracted based on specified conditions or keywords.

[0572] "Means of extraction" refers to methods and techniques for retrieving data that meets specific conditions from a data bank.

[0573] A "generative intelligence model" is a type of artificial intelligence trained to automatically make predictions and classifications based on input data.

[0574] "Emotion analysis" is a technology that estimates a user's emotions from their facial expressions, voice, and input content, and adjusts the system's operation based on those emotions.

[0575] "Means of dynamic adjustment" refers to methods for flexibly changing the way information is presented or its content in response to changes in circumstances or conditions.

[0576] A description of embodiments for carrying out this invention will be given.

[0577] The server first builds a database containing company information. This database includes detailed information about companies, such as their financial information, industry, business activities, and geographical location. This allows the server to efficiently search and extract relevant organizations based on specific keywords. The server performs data retrieval using database query languages ​​such as SQL.

[0578] Next, the server utilizes generative intelligence models to analyze the extracted financial information and capabilities of the companies. These are implemented using programming languages ​​such as Python and machine learning frameworks like TensorFlow and PyTorch. This generative intelligence model quantifies the suitability of companies for alliances and mergers / acquisitions, generating a score. The generated score is based on scientific evidence and serves as an important indicator in company selection.

[0579] Furthermore, the server implements emotion analysis technology to estimate the user's emotions as they view information through the interface. It uses the device's built-in camera and microphone to capture the user's facial expressions and voice tone, and performs emotion analysis based on this data. This analysis utilizes libraries such as Python's OpenCV and Emotion SDK. Based on the analysis results, the server dynamically adjusts the information displayed to reflect the user's emotions. For example, if the user is showing positive emotions, it presents detailed results from the generative AI model's analysis.

[0580] As a concrete example, consider a scenario where a user is seeking partnerships with technology companies in emerging markets. In this case, the user enters keywords such as "emerging markets" and "technology" into their device. The server extracts relevant companies from a database based on these keywords and generates evaluation scores using a generative intelligence model.

[0581] An example of a prompt message used by the server is, "Analyze the candidates for the best technology companies in emerging markets," which is input to the generative AI model. This prompt allows the generative AI model to perform appropriate information analysis and ultimately provide the information the user is looking for.

[0582] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0583] Step 1:

[0584] The user enters keywords indicating their desired conditions using a terminal. This interface allows users to enter industry names, technical terms, geographical conditions, and more. The entered keywords are sent to the server as search criteria for the data.

[0585] Step 2:

[0586] Upon receiving keywords sent from the terminal, the server searches a database containing company information. The server manipulates the database using SQL queries to extract companies that match the criteria. This process generates a list of companies matching the keywords, which is then used in the next processing step.

[0587] Step 3:

[0588] The server collects detailed financial and capability information for each company based on the extracted list. Here, in addition to information within the data bank, the latest data is obtained using external APIs. All collected data is prepared for analysis by generative intelligence models.

[0589] Step 4:

[0590] The server uses a generative intelligence model to analyze the collected corporate data. Specifically, it uses Python and machine learning frameworks (e.g., TensorFlow, PyTorch) to convert the suitability of each company for alliances, mergers, and acquisitions into a numerical score. This score serves as reference information for users when making decisions.

[0591] Step 5:

[0592] The server receives data in real time from the device's camera and microphone to analyze the user's emotions. Using libraries such as Python's OpenCV and Emotion SDK, it analyzes the user's facial expressions and tone of voice to estimate their emotions.

[0593] Step 6:

[0594] Based on the sentiment analysis results, the server dynamically adjusts the information presented to the user. If positive emotions are detected, detailed analysis results are presented; if negative emotions are detected, concise information focusing on key points is presented.

[0595] Step 7:

[0596] Finally, the server sends the generated score and analysis results to the terminal, where the user can view the information on the interface. This information forms the basis for the user to efficiently and effectively select a company.

[0597] (Application Example 2)

[0598] 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."

[0599] Selecting the right partner is crucial in the process of considering collaboration and integration between companies, but making such selections based on vast amounts of company information and complex criteria is not easy. Therefore, there is a need for efficient and scientifically-based selection methods. Furthermore, there is a demand for user-friendly systems that flexibly adapt information presentation based on the user's emotional state.

[0600] 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.

[0601] In this invention, the server includes means for extracting relevant organizations from an information set including corporate attributes based on specific identifiers; means for utilizing generative intelligence to analyze the resource data and capabilities of the extracted organizations; means for generating evaluation values ​​indicating the suitability of each organization for collaboration, integration, and absorption; and means for dynamically adjusting the information presentation method based on the evaluation values ​​and the user's emotional state. This enables efficient selection of appropriate collaboration candidates and the presentation of appropriate information in accordance with the user's emotions.

[0602] "Company attributes" is a general term for information that indicates the characteristics and features of a company, and includes information such as industry, location, size, technological capabilities, and financial status.

[0603] An "information collection" refers to a database or recording medium in which diverse information is aggregated and systematized.

[0604] An "identifier" is a string of characters or symbols used to identify an object, and is used as a search condition in a database.

[0605] An "organization" is a group or structure formed by people coming together for a specific purpose.

[0606] "Resource data" refers to data that a company possesses, including financial information, human resources, and technological resources.

[0607] "Capability" refers to the ability and efficiency with which an organization or individual can perform a specific task or mission.

[0608] "Generative intelligence" is a form of artificial intelligence that learns from large amounts of data and performs inference and prediction.

[0609] "Collaboration" refers to different organizations or individuals working together on a project.

[0610] "Integration" refers to the process of bringing together multiple elements or organizations into a single, unified entity.

[0611] "Absorption" refers to the process where one organization incorporates another organization and makes it a part of itself.

[0612] "Aptitude" refers to qualities or abilities that are suitable for a particular purpose or condition.

[0613] An "evaluation value" is a numerical or level representation of the value or performance of something, based on specific criteria.

[0614] "Emotional state" refers to the emotions and psychological conditions an individual is experiencing at a given time.

[0615] "Information presentation method" refers to the methods and means of how information is presented and provided to users.

[0616] Users can initiate a search based on company attributes by entering specific identifiers, such as industry names or regional conditions, through an application installed on their mobile device. The device sends this information to a server. The server extracts relevant organizations from the information set, including company attributes, and then analyzes the resource data and capabilities of the extracted organizations using generative intelligence. This calculates an evaluation value indicating the suitability of each relevant organization for collaboration, integration, or acquisition.

[0617] Furthermore, the server uses an emotion engine to analyze the user's emotional state and dynamically adjusts how information is presented based on the evaluation score and the user's emotions. This adjustment of information presentation is supported by a generative AI model. For example, if the user's emotions are positive, the results are presented in a way that includes detailed information and additional suggestions. Conversely, if the emotions are negative, the results are presented in a concise format that summarizes the key points.

[0618] This system is based on communication between a cloud server and a smartphone, and utilizes machine learning models (Python, TensorFlow / PyTorch) and sentiment analysis APIs (e.g., Google Cloud Natural Language API). This approach allows users to receive the most relevant information and suggestions without being bothered by unnecessary information.

[0619] As a concrete example, consider a case where a company is looking for a partner for an electronic payment system in the Asian market. When a user enters "electronic payment" and "Asian market" into the app, the device communicates with a server to search for and analyze relevant company candidates. Finally, information is presented to the user based on the analysis results and the user's sentiment.

[0620] Examples of prompts for generative AI models:

[0621] "We would like to select a new business partner. Please incorporate a results display method based on user sentiment data."

[0622] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0623] Step 1:

[0624] The user enters a specific identifier into the application on their mobile device. This identifier may include the industry name or regional conditions. This input data is generated by the device and sent to the server.

[0625] Step 2:

[0626] The server searches the information set based on identifiers received from the user and extracts relevant organizations. During data processing, a database query is generated, and data matching the company attributes is selected. The output is a list of relevant organizations.

[0627] Step 3:

[0628] The server analyzes the extracted organizational resource data and capabilities using generative intelligence. Here, machine learning models are applied as data calculations to determine the suitability of each organization. The output is the evaluation score for each organization.

[0629] Step 4:

[0630] The server uses an emotion engine to analyze the user's emotional state. It takes emotional data obtained from the user's terminal as input, analyzes it, and outputs the user's emotional state.

[0631] Step 5:

[0632] The server dynamically adjusts the information presentation method based on the evaluation value and the user's emotional state. It evaluates the input evaluation value and emotional state, applies logic to change the format of information delivery, and selects the optimal information display format.

[0633] Step 6:

[0634] The server sends information in a formatted manner to the user's terminal and presents the results. The user's terminal receives the output from the server and displays the information to the user in an appropriately visualized format.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] [Fourth Embodiment]

[0639] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0640] 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.

[0641] 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).

[0642] 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.

[0643] 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.

[0644] 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).

[0645] 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.

[0646] 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.

[0647] 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.

[0648] 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.

[0649] 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.

[0650] 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.

[0651] 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".

[0652] This invention is a system for streamlining the selection of candidate companies when companies are considering alliances, mergers, or acquisitions. Specifically, it enables users to quickly and objectively select candidate companies through the use of a database containing company information and analysis by generative artificial intelligence.

[0653] The terminal has an interface that accepts user input. Users enter specific keywords into the terminal to narrow down potential alliance, merger, or acquisition candidates. These keywords may include desired industries, relevant technical terms, and geographical conditions.

[0654] The server uses keywords received from the terminal to search a database containing company information. This search results in a list of relevant companies. Company information includes company name, location, industry, as well as publicly available financial data and capabilities.

[0655] Next, the server uses generative artificial intelligence to analyze the extracted financial data and capabilities of the companies. As a result of this analysis, a score is generated indicating the suitability of each company for alliances, mergers, and acquisitions. The generated score reflects each company's strategic fit, growth potential, and financial health.

[0656] For example, if a user wishes to form an alliance with a North American company that possesses AI technology, they would enter keywords such as "AI technology" and "North America" ​​into their terminal. Based on this, the server searches its database for relevant companies, analyzes the financial data of the extracted companies, and generates an optimal score. As a result, companies with high scores are prioritized and listed, providing the user with the basic information needed to proceed to the next step.

[0657] This process allows users to efficiently select candidate companies and focus on subsequent negotiations and analysis. The system reduces the burden of manual information gathering, enabling faster and more accurate decision-making.

[0658] The following describes the processing flow.

[0659] Step 1:

[0660] Users enter keywords into their terminals to identify target companies for alliances, mergers, or acquisitions. These keywords can include industry names, technical terms, geographical locations, and more.

[0661] Step 2:

[0662] The terminal collects the entered keywords and sends them to the server.

[0663] Step 3:

[0664] The server uses the received keywords to search a database containing company information and then generates a list of companies that match the criteria.

[0665] Step 4:

[0666] The server then retrieves more detailed financial and capability information for each company from a database or external data source from the generated list of companies.

[0667] Step 5:

[0668] The server inputs the acquired data into generative artificial intelligence to perform analysis including each company's financial health, strategic fit, and growth potential.

[0669] Step 6:

[0670] The server assigns a score to each company based on the analysis results, and evaluates their suitability for alliances, mergers, and acquisitions.

[0671] Step 7:

[0672] The server returns the scoring results and an overview of each company to the terminal.

[0673] Step 8:

[0674] Users review the scoring results displayed on their device and decide which companies to proceed to the next selection process with.

[0675] (Example 1)

[0676] 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".

[0677] When companies engage in alliances, mergers, or acquisitions, quickly and efficiently identifying suitable candidates is challenging. The process of gathering and analyzing relevant information is time-consuming, labor-intensive, and often relies on subjective judgment. Therefore, a system is needed to select candidate companies based on objective and fair criteria.

[0678] 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.

[0679] In this invention, the server includes means for receiving specific input information, means for searching for information in an information aggregate based on the input information and extracting relevant information, and means for utilizing generative automated intelligence to analyze the numerical data and skill information of the extracted information. This enables the user to quickly and objectively evaluate the suitability of linking, retrieving, and integrating tasks and select the optimal candidate.

[0680] "Specific input information" refers to information provided by the user to the system, including industry names, technical terms, and regional conditions.

[0681] An "information aggregate" refers to a database or other means of collecting information used to store data about a company.

[0682] "Related information" refers to company-related data that the system presents to the user, extracted based on specific input information.

[0683] "Numerical data and skills information" refers to detailed information about a company's financial situation and capabilities, and serves as evaluation criteria in company selection.

[0684] "Generative automated intelligence" is a form of artificial intelligence technology that is equipped with algorithms that analyze diverse data and generate evaluation values.

[0685] "Suitability for mergers, acquisitions, and integrations" refers to evaluation criteria that demonstrate a company's suitability for alliances, mergers, and acquisitions with other companies.

[0686] The "evaluation value" is a numerical value calculated by generative automated intelligence, indicating the suitability of a particular company for alliances, mergers, or acquisitions.

[0687] This invention is for selecting appropriate candidates when considering corporate alliances, mergers, or acquisitions using an information processing device. Specifically, it involves the interaction of a server, a terminal, and a user.

[0688] First, the user provides specific input information through the terminal interface. This includes the name of the relevant industry sector, technical terms, and regional conditions. The user can do this through text input or voice input.

[0689] Next, the terminal sends this input information to the server. The server searches a database, which is a collection of information, and extracts company information related to the input information. This process utilizes a high-speed search algorithm and a database management system.

[0690] The server then uses generative automated intelligence to analyze the extracted numerical data and skills information of the companies. The generative automated intelligence assesses each company's financial health, growth potential, and strategic suitability, generating evaluation values ​​that indicate its suitability for merger-related or acquisition and integration work. This analysis utilizes software powered by machine learning algorithms.

[0691] Finally, the server sends the evaluation results to the terminal, which then presents them to the user. Based on the presented evaluation values, the user can then make the next decision.

[0692] For example, if a user wishes to form an alliance with a North American company possessing AI technology, they would enter prompts such as "AI technology" or "North America" ​​into their terminal. Based on this, the server would search its database to extract relevant companies, analyze them, and present the optimal evaluation score. This allows the user to efficiently select candidate companies.

[0693] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0694] Step 1:

[0695] The user provides specific input information through the terminal's interface. Specifically, they input industry names, technical terms, geographical conditions, etc., using the keyboard or voice input function. The input information is converted into digital data within the terminal and prepared for transmission to the server.

[0696] Input: Specific input information provided via keyboard or voice input.

[0697] Output: Digital information data for transmission to the server.

[0698] Step 2:

[0699] The terminal sends the input information received from the user to the server. A secure communication protocol is used for transmission via the internet connection. The server then formats the received data directly into a query for database retrieval.

[0700] Input: Digital information data from a terminal.

[0701] Output: Search queries that reached the server

[0702] Step 3:

[0703] The server searches the corporate information database, which is a collection of information, based on the received query. A high-speed search algorithm is used to extract relevant corporate information. The found information is organized in a list format and passed on to the next processing step.

[0704] Input: Search query on the server

[0705] Output: List of related company information

[0706] Step 4:

[0707] The server uses generative automated intelligence to analyze the numerical and skills data of extracted company information. In this process, machine learning algorithms evaluate each company's financial health and growth potential, and generate evaluation values ​​indicating their suitability for integration.

[0708] Input: List of extracted company information

[0709] Output: Evaluation values ​​for each company

[0710] Step 5:

[0711] The server ranks companies based on the generated evaluation scores and sends this ranking to the terminal. The ranked information is then organized in order of priority to support the user's decision-making.

[0712] Input: Evaluation value for each company

[0713] Output: Ranked company information

[0714] Step 6:

[0715] The terminal displays ranked company information received from the server on its screen. The user reviews this information and makes decisions for the next step based on the evaluation scores. Specifically, they can request additional data or view detailed information about the selected companies.

[0716] Input: Ranked company information

[0717] Output: Specific company information displayed to the user

[0718] (Application Example 1)

[0719] 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".

[0720] Traditional company selection processes have presented challenges in efficiently selecting potential alliance, merger, and acquisition candidates. Furthermore, the time-consuming and labor-intensive information gathering and analysis required for selection often led to delays in decision-making. Additionally, a lack of objective criteria and tools for evaluating each company's suitability prevented users from quickly comparing and evaluating options. There is a need for solutions to these challenges, enabling more efficient and accurate company selection.

[0721] 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.

[0722] In this invention, the server includes means for extracting relevant companies from a database containing company information based on specific keywords; means for utilizing generative data processing technology to analyze the financial data and capabilities of the extracted companies; means for calculating the strength indicating the suitability of each company for collaboration or organizational restructuring; means for visually presenting the results to the user based on the strength; and an intuitive information display device for displaying candidates that meet the criteria based on user input. This enables the user to quickly grasp the details of candidate companies and make the optimal selection.

[0723] A "database containing corporate information" is a digital collection of information about various companies, including company name, location, industry, and publicly available financial data and capabilities.

[0724] "Methods for extracting relevant companies based on specific keywords" refers to algorithms or processes for selecting companies from a database that match the conditions specified by the user.

[0725] "Methods that utilize generative data processing technology" refer to techniques that use generative artificial intelligence and advanced data analysis technologies to process extracted company information and obtain meaningful analytical results.

[0726] "Means for calculating the strength of suitability for collaboration or organizational restructuring" refers to a method for quantitatively evaluating how suitable companies are for collaboration or integration and displaying it as a score or index.

[0727] "Means of visually presenting results to users" refers to interfaces and tools that visualize analysis results in an easy-to-understand way for users and display information in various forms.

[0728] An "intuitive information display device" refers to a display device or software designed to allow users to easily understand and operate information.

[0729] This invention includes a system for efficiently selecting and evaluating the suitability of companies. This system realizes the invention through the following main processes.

[0730] The system's core server utilizes a database of stored company information to extract relevant companies that match specific keywords based on user input data. Specific database searches include SQL query processing and full-text searches using Apache Lucene. Users access the system using smartphones or desktop terminals and input their desired criteria (e.g., "AI technology," "North America").

[0731] The server analyzes the extracted financial data and capabilities of companies using generative data processing technologies, such as TensorFlow and PyTorch. This technology is crucial for evaluating a company's financial situation and strategic fit in the market. The analysis of the generated data yields a strength score indicating the suitability of each company's collaborations and organizational restructuring.

[0732] Users receive results in a visually easy-to-understand format, such as dashboards or graphs, to check their intensity. Data visualization libraries like D3.js are used to achieve this. In addition, frameworks such as React and Angular are used in the user interface to provide an intuitive information display system, enhancing usability.

[0733] For example, if a user wants to find the best partner in a particular technology field as part of their preparations for participating in an industrial trade show, they can use the system to quickly list companies that meet their criteria and narrow down promising candidates by comparing the strengths of each company.

[0734] An example of a prompt message is, "List companies that meet the following criteria and generate scores for financial health and growth potential: AI technology, North America." This helps users make appropriate decisions quickly and efficiently.

[0735] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0736] Step 1:

[0737] The server receives user input data sent from the terminal. This input data includes conditions and keywords selected by the user (e.g., "AI technology," "North America"). The server uses this data to query a database containing company information and extract companies that match the conditions. A list of related companies is generated as output.

[0738] Step 2:

[0739] The server uses a generative AI model to analyze the extracted list of companies. Financial data and capability information for each company are used as input. The server processes and calculates the strength of each company's suitability for collaboration or restructuring using machine learning algorithms. This information is necessary for subsequent processing.

[0740] Step 3:

[0741] The server prepares data to visually present the results to the user based on the generated intensity. Using a data visualization library, it processes the data into graphs and dashboards for visualization. The output is a visual representation of the intensity in a user-friendly format.

[0742] Step 4:

[0743] The terminal receives visualization data sent from the server and displays it on the user interface. Users can intuitively view and compare information through operations on the terminal. The output provides detailed information on companies individually selected by the user, which can then be used for subsequent decision-making.

[0744] Step 5:

[0745] Based on the information presented, the user retrieves further details about companies that match their selected criteria and generates additional prompts as needed. This allows them to instruct the system to take the next action, enabling further information gathering and analysis.

[0746] 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.

[0747] This invention is a system for companies to select appropriate candidate companies when forming alliances, mergers, or acquisitions, and further provides more personalized information by combining it with an emotion engine that recognizes user emotions.

[0748] The terminal has an interface that accepts specific keywords from the user. The user enters keywords such as industry names, technical terms, and geographical conditions based on their preferences. The terminal then sends this information to the server.

[0749] The server uses the received keywords to search a database containing company information and generates a list of relevant companies that match the criteria. The server then retrieves financial and capability information for the listed companies from the database and external data sources.

[0750] Furthermore, the server uses generative artificial intelligence to analyze the acquired data and generate a score that quantifies the suitability of each company for alliances, mergers, and acquisitions. This scoring allows users to efficiently select companies based on scientifically supported information.

[0751] A key feature of this invention is the integration of an emotion engine to analyze the user's emotions during input and when reviewing scoring results. This emotion analysis allows the server to dynamically adjust the format and method of information presented according to the user's emotions. For example, if the user has negative emotions, the engine simplifies the list display and provides only important highlights. Conversely, if positive emotions are detected, more detailed analysis results and recommendations are presented more explicitly.

[0752] For example, if a user wishes to partner with a technology company in an emerging market, they would enter keywords such as "technology" and "emerging market" into their device. The server would then extract relevant companies from its database and perform scoring based on these keywords. The emotion engine would analyze the user's response, and the resulting information would flexibly change to match the user's intentions and desires, thus supporting optimal decision-making.

[0753] This system is a comprehensive tool designed to improve user convenience while also enhancing the accuracy and efficiency of candidate company selection.

[0754] The following describes the processing flow.

[0755] Step 1:

[0756] Users enter keywords related to their desired conditions for alliances, mergers, or acquisitions with companies into the terminal. This allows them to set criteria to narrow down potential companies that meet their objectives.

[0757] Step 2:

[0758] The terminal sends the received keywords to the server as structured data. This information acts as a trigger for database searches.

[0759] Step 3:

[0760] The server searches multiple databases containing company information based on the received keywords and extracts relevant companies that match the criteria. This process takes into account factors such as the company's industry, location, and technology.

[0761] Step 4:

[0762] The server collects detailed financial and capability information for the selected companies from databases and external sources. This clarifies the economic and technological background of each company.

[0763] Step 5:

[0764] The server inputs the collected data into generative artificial intelligence to analyze companies' financial health, growth potential, and strategic fit. As a result, it generates a score indicating the suitability of each company.

[0765] Step 6:

[0766] The server sends the scoring results to the sentiment engine, which infers the user's emotions based on the user's past response data and real-time feedback. This information is then used to dynamically adjust how the information is displayed.

[0767] Step 7:

[0768] The device presents the user with a customized scoring result based on the analysis of the emotion engine. The content is adjusted as needed, providing detailed information for positive emotions and a summary for negative emotions.

[0769] Step 8:

[0770] Based on the information displayed on their device, users select companies that are potential candidates for alliances, mergers, or acquisitions. Throughout this process, the sentiment engine continuously observes the user's reactions and modifies the information presented as needed.

[0771] (Example 2)

[0772] 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".

[0773] When companies engage in alliances, mergers, or acquisitions, selecting the right candidates from a vast amount of information is extremely difficult. Furthermore, user subjectivity and emotions can influence the selection process, leading to inefficient decision-making. There is a need to solve this problem and provide users with the optimal choice.

[0774] 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.

[0775] In this invention, the server includes means for extracting relevant organizations from a data bank containing corporate information, means for utilizing a generative intelligence model to analyze the financial information and capabilities of the extracted organizations, and means for dynamically adjusting the information using sentiment analysis. This makes it possible to select candidate companies based on scientific evidence while adjusting the display method according to the user's emotions.

[0776] "Company information" refers to all information about a company, including its name, address, industry, business activities, financial information, business partners, and other related matters.

[0777] A "data bank" is a collection of information that is systematically organized and stored in a format that allows for searching and analysis.

[0778] "Relevant organizations" refers to companies and organizations extracted based on specified conditions or keywords.

[0779] "Means of extraction" refers to methods and techniques for retrieving data that meets specific conditions from a data bank.

[0780] A "generative intelligence model" is a type of artificial intelligence trained to automatically make predictions and classifications based on input data.

[0781] "Emotion analysis" is a technology that estimates a user's emotions from their facial expressions, voice, and input content, and adjusts the system's operation based on those emotions.

[0782] "Means of dynamic adjustment" refers to methods for flexibly changing the way information is presented or its content in response to changes in circumstances or conditions.

[0783] A description of embodiments for carrying out this invention will be given.

[0784] The server first builds a database containing company information. This database includes detailed information about companies, such as their financial information, industry, business activities, and geographical location. This allows the server to efficiently search and extract relevant organizations based on specific keywords. The server performs data retrieval using database query languages ​​such as SQL.

[0785] Next, the server utilizes generative intelligence models to analyze the extracted financial information and capabilities of the companies. These are implemented using programming languages ​​such as Python and machine learning frameworks like TensorFlow and PyTorch. This generative intelligence model quantifies the suitability of companies for alliances and mergers / acquisitions, generating a score. The generated score is based on scientific evidence and serves as an important indicator in company selection.

[0786] Furthermore, the server implements emotion analysis technology to estimate the user's emotions as they view information through the interface. It uses the device's built-in camera and microphone to capture the user's facial expressions and voice tone, and performs emotion analysis based on this data. This analysis utilizes libraries such as Python's OpenCV and Emotion SDK. Based on the analysis results, the server dynamically adjusts the information displayed to reflect the user's emotions. For example, if the user is showing positive emotions, it presents detailed results from the generative AI model's analysis.

[0787] As a concrete example, consider a scenario where a user is seeking partnerships with technology companies in emerging markets. In this case, the user enters keywords such as "emerging markets" and "technology" into their device. The server extracts relevant companies from a database based on these keywords and generates evaluation scores using a generative intelligence model.

[0788] An example of a prompt message used by the server is, "Analyze the candidates for the best technology companies in emerging markets," which is input to the generative AI model. This prompt allows the generative AI model to perform appropriate information analysis and ultimately provide the information the user is looking for.

[0789] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0790] Step 1:

[0791] The user enters keywords indicating their desired conditions using a terminal. This interface allows users to enter industry names, technical terms, geographical conditions, and more. The entered keywords are sent to the server as search criteria for the data.

[0792] Step 2:

[0793] Upon receiving keywords sent from the terminal, the server searches a database containing company information. The server manipulates the database using SQL queries to extract companies that match the criteria. This process generates a list of companies matching the keywords, which is then used in the next processing step.

[0794] Step 3:

[0795] The server collects detailed financial and capability information for each company based on the extracted list. Here, in addition to information within the data bank, the latest data is obtained using external APIs. All collected data is prepared for analysis by generative intelligence models.

[0796] Step 4:

[0797] The server uses a generative intelligence model to analyze the collected corporate data. Specifically, it uses Python and machine learning frameworks (e.g., TensorFlow, PyTorch) to convert the suitability of each company for alliances, mergers, and acquisitions into a numerical score. This score serves as reference information for users when making decisions.

[0798] Step 5:

[0799] The server receives data in real time from the device's camera and microphone to analyze the user's emotions. Using libraries such as Python's OpenCV and Emotion SDK, it analyzes the user's facial expressions and tone of voice to estimate their emotions.

[0800] Step 6:

[0801] Based on the sentiment analysis results, the server dynamically adjusts the information presented to the user. If positive emotions are detected, detailed analysis results are presented; if negative emotions are detected, concise information focusing on key points is presented.

[0802] Step 7:

[0803] Finally, the server sends the generated score and analysis results to the terminal, where the user can view the information on the interface. This information forms the basis for the user to efficiently and effectively select a company.

[0804] (Application Example 2)

[0805] 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".

[0806] Selecting the right partner is crucial in the process of considering collaboration and integration between companies, but making such selections based on vast amounts of company information and complex criteria is not easy. Therefore, there is a need for efficient and scientifically-based selection methods. Furthermore, there is a demand for user-friendly systems that flexibly adapt information presentation based on the user's emotional state.

[0807] 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.

[0808] In this invention, the server includes means for extracting relevant organizations from an information set including corporate attributes based on specific identifiers; means for utilizing generative intelligence to analyze the resource data and capabilities of the extracted organizations; means for generating evaluation values ​​indicating the suitability of each organization for collaboration, integration, and absorption; and means for dynamically adjusting the information presentation method based on the evaluation values ​​and the user's emotional state. This enables efficient selection of appropriate collaboration candidates and the presentation of appropriate information in accordance with the user's emotions.

[0809] "Company attributes" is a general term for information that indicates the characteristics and features of a company, and includes information such as industry, location, size, technological capabilities, and financial status.

[0810] An "information collection" refers to a database or recording medium in which diverse information is aggregated and systematized.

[0811] An "identifier" is a string of characters or symbols used to identify an object, and is used as a search condition in a database.

[0812] An "organization" is a group or structure formed by people coming together for a specific purpose.

[0813] "Resource data" refers to data that a company possesses, including financial information, human resources, and technological resources.

[0814] "Capability" refers to the ability and efficiency with which an organization or individual can perform a specific task or mission.

[0815] "Generative intelligence" is a form of artificial intelligence that learns from large amounts of data and performs inference and prediction.

[0816] "Collaboration" refers to different organizations or individuals working together on a project.

[0817] "Integration" refers to the process of bringing together multiple elements or organizations into a single, unified entity.

[0818] "Absorption" refers to the process where one organization incorporates another organization and makes it a part of itself.

[0819] "Aptitude" refers to qualities or abilities that are suitable for a particular purpose or condition.

[0820] An "evaluation value" is a numerical or level representation of the value or performance of something, based on specific criteria.

[0821] "Emotional state" refers to the emotions and psychological conditions an individual is experiencing at a given time.

[0822] "Information presentation method" refers to the methods and means of how information is presented and provided to users.

[0823] Users can initiate a search based on company attributes by entering specific identifiers, such as industry names or regional conditions, through an application installed on their mobile device. The device sends this information to a server. The server extracts relevant organizations from the information set, including company attributes, and then analyzes the resource data and capabilities of the extracted organizations using generative intelligence. This calculates an evaluation value indicating the suitability of each relevant organization for collaboration, integration, or acquisition.

[0824] Furthermore, the server uses an emotion engine to analyze the user's emotional state and dynamically adjusts how information is presented based on the evaluation score and the user's emotions. This adjustment of information presentation is supported by a generative AI model. For example, if the user's emotions are positive, the results are presented in a way that includes detailed information and additional suggestions. Conversely, if the emotions are negative, the results are presented in a concise format that summarizes the key points.

[0825] This system is based on communication between a cloud server and a smartphone, and utilizes machine learning models (Python, TensorFlow / PyTorch) and sentiment analysis APIs (e.g., Google Cloud Natural Language API). This approach allows users to receive the most relevant information and suggestions without being bothered by unnecessary information.

[0826] As a concrete example, consider a case where a company is looking for a partner for an electronic payment system in the Asian market. When a user enters "electronic payment" and "Asian market" into the app, the device communicates with a server to search for and analyze relevant company candidates. Finally, information is presented to the user based on the analysis results and the user's sentiment.

[0827] Examples of prompts for generative AI models:

[0828] "We would like to select a new business partner. Please incorporate a results display method based on user sentiment data."

[0829] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0830] Step 1:

[0831] The user enters a specific identifier into the application on their mobile device. This identifier may include the industry name or regional conditions. This input data is generated by the device and sent to the server.

[0832] Step 2:

[0833] The server searches the information set based on identifiers received from the user and extracts relevant organizations. During data processing, a database query is generated, and data matching the company attributes is selected. The output is a list of relevant organizations.

[0834] Step 3:

[0835] The server analyzes the extracted organizational resource data and capabilities using generative intelligence. Here, machine learning models are applied as data calculations to determine the suitability of each organization. The output is the evaluation score for each organization.

[0836] Step 4:

[0837] The server uses an emotion engine to analyze the user's emotional state. It takes emotional data obtained from the user's terminal as input, analyzes it, and outputs the user's emotional state.

[0838] Step 5:

[0839] The server dynamically adjusts the information presentation method based on the evaluation value and the user's emotional state. It evaluates the input evaluation value and emotional state, applies logic to change the format of information delivery, and selects the optimal information display format.

[0840] Step 6:

[0841] The server sends information in a formatted manner to the user's terminal and presents the results. The user's terminal receives the output from the server and displays the information to the user in an appropriately visualized format.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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."

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] The following is further disclosed regarding the embodiments described above.

[0864] (Claim 1)

[0865] A method for extracting related companies from a database containing company information based on specific keywords,

[0866] A means of utilizing generative artificial intelligence to analyze the financial data and capabilities of extracted companies,

[0867] A means for generating a score indicating the suitability of each company for alliances, mergers, and acquisitions,

[0868] A means of presenting the results to the user based on the aforementioned score,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, wherein specific keywords include industry names, technical keywords, and geographical conditions.

[0872] (Claim 3)

[0873] The system according to claim 1, further comprising means for collecting detailed financial data and capability information of extracted companies from external data sources.

[0874] "Example 1"

[0875] (Claim 1)

[0876] A means of receiving specific input information,

[0877] A means for searching for information in an information aggregate based on the input information and extracting relevant information,

[0878] A means of utilizing generative automated intelligence to analyze the numerical data and skill information of the extracted information,

[0879] A means for generating an evaluation value indicating the suitability of the combination-related or acquisition and integration work of each piece of information,

[0880] A means for displaying the results to the user based on the aforementioned evaluation value,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, wherein specific input information includes industry name, technical terminology, and regional conditions.

[0884] (Claim 3)

[0885] The system according to claim 1, further comprising means for collecting detailed numerical data and skill information of the extracted information from external sources.

[0886] "Application Example 1"

[0887] (Claim 1)

[0888] A method for extracting related companies from a database containing company information based on specific keywords,

[0889] A means of utilizing generative data processing technology to analyze the financial data and capabilities of extracted companies,

[0890] A means of calculating the strength of the suitability of collaboration or organizational restructuring among various companies,

[0891] A means for visually presenting the results to the user based on the aforementioned intensity,

[0892] An intuitive information display device that shows candidates that match the criteria based on user input,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, wherein specific keywords include industrial fields, technical terms, and regional conditions.

[0896] (Claim 3)

[0897] The system according to claim 1, further comprising means for collecting detailed financial data and capability information of extracted companies from external sources.

[0898] "Example 2 of combining an emotion engine"

[0899] (Claim 1)

[0900] A means of extracting relevant organizations from a database containing corporate information based on specific keywords,

[0901] A means of utilizing generative intelligence models to analyze the financial information and capabilities of extracted organizations,

[0902] A means of generating numerical values ​​that indicate the suitability of each organization's cooperative relationship or merger and acquisition,

[0903] A sentiment analysis method that analyzes user emotions and dynamically adjusts information,

[0904] A means of providing results to stakeholders based on the aforementioned figures,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, wherein specific keywords include industry names, technical terms, and geographical conditions.

[0908] (Claim 3)

[0909] The system according to claim 1, further comprising means for obtaining detailed financial and capability information of the extracted organizations from external data sources.

[0910] "Application example 2 when combining with an emotional engine"

[0911] (Claim 1)

[0912] A means for extracting related organizations from a set of information including corporate attributes based on a specific identifier,

[0913] A means of utilizing generative intelligence to analyze the extracted organizational resource data and capabilities,

[0914] A means for generating evaluation values ​​that indicate the suitability of each organization for collaboration, integration, and absorption,

[0915] A means for dynamically adjusting the information presentation method based on the evaluation value and the user's emotional state,

[0916] A means for presenting the results to the user in the aforementioned adjusted format,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, wherein a specific identifier includes an industry name, a technical term, and a regional condition.

[0920] (Claim 3)

[0921] The system according to claim 1, further comprising means for collecting detailed resource data and capability information of the extracted organization from external sources. [Explanation of Symbols]

[0922] 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. A method for extracting related companies from a database containing company information based on specific keywords, A means of utilizing generative artificial intelligence to analyze the financial data and capabilities of extracted companies, A means for generating a score indicating the suitability of each company for alliances, mergers, and acquisitions, A means of presenting the results to the user based on the aforementioned score, A system that includes this.

2. The system according to claim 1, wherein specific keywords include industry names, technical keywords, and geographical conditions.

3. The system according to claim 1, further comprising means for collecting detailed financial data and capability information of extracted companies from external data sources.

Images