Operating method of electronic device for performing inter-company matching based on data collected through web crawling

Abstract

The present disclosure relates to an operating method of an electronic device for matching a customer with a company. The operating method comprises the steps of: obtaining technology information of a customer company upon receiving a matching request for an investment company or a partner company from a terminal of the customer company; identifying an event corresponding to at least one of investment and partnership related to a technology keyword by performing web crawling on the basis of at least one technology keyword constituting the technology information; classifying and grouping each of companies included in the identified event into at least one of a technology-holding company, an investment company, and a partner company; and selecting a plurality of candidate companies that can be matched with the customer company on the basis of a result of the grouping.

Description

A method of operation of an electronic device that performs inter-company matching based on data collected through web crawling.

[0001] The present disclosure relates to an operating method of an electronic device, and more particularly, to an operating method of an electronic device that performs inter-company matching based on data collected through web crawling.

[0002] Startups often possess technological prowess, but lack sufficient human resources, hindering their growth. This can be due to difficulties in establishing local customer networks. Furthermore, they often face challenges in managing their businesses due to insufficient initial capital or difficulty in finding partner companies.

[0003] Meanwhile, for companies that must meet customer needs, it is important to meet customer demands by promptly introducing companies with technologies that meet customer needs.

[0004] To ensure inter-company matching that satisfies both of these conditions, it is necessary to collect and classify data in real time to provide information that increases the likelihood of a contract being concluded.

[0005] The present disclosure seeks to provide a method of operating an electronic device that performs inter-company matching based on data collected through web crawling.

[0006] The purposes of the present disclosure are not limited to those mentioned above, and other purposes and advantages of the present disclosure not mentioned above can be understood through the following description and will be more clearly understood through the embodiments of the present disclosure. Furthermore, it will be readily apparent that the purposes and advantages of the present disclosure can be realized by the means and combinations thereof set forth in the claims.

[0007] A method for operating an electronic device for performing inter-company matching according to an embodiment of the present disclosure includes, when a request for matching for an investment company or a partner company is received from a terminal of a customer company, a step of obtaining technology information of the customer company, a step of performing web crawling based on at least one technology keyword constituting the technology information to identify an event corresponding to at least one of investment and partnership related to the technology keyword, a step of classifying and grouping each of the companies included in the identified event into at least one of a technology-holding company, an investment company, and a partner company, and a step of selecting a plurality of candidate companies that can be matched with the customer company based on a result of the grouping.

[0008] At this time, the grouping step may include identifying at least one company included in the identified event, classifying each of the identified companies into at least one of a first group including the technology-holding company, a second group including the investment company, and a third group including the partner company, and grouping the identified companies, and setting evaluation items for each group to evaluate the degree to which the companies included in each group match the matching request of the customer company.

[0009] In addition, the operating method of the electronic device may include a step of selecting at least one group that needs to be matched with the customer company according to a matching request from the customer company based on the result of the grouping and identifying it as a target group.

[0010] At this time, the step of selecting multiple candidate companies that can be matched with the customer company may include identifying companies included in the target group as target companies, calculating scores for each evaluation item set for the target group for each target company, calculating a total score for each target company based on the scores for each evaluation item calculated for each target company, setting a ranking for each target company based on the total score for each target company, and selecting at least one candidate company whose ranking is higher than a reference ranking from among the target companies.

[0011] Meanwhile, the method of operating the electronic device may include a step of identifying whether the customer company's matching request includes a priority for the evaluation item, and a step of selecting at least one candidate company among the selected plurality of candidate companies as a recommended company when the customer company's matching request is identified as including a priority for the evaluation item.

[0012] Specifically, the step of selecting at least one candidate company as a recommended company may include: setting a rank for each of the target companies based on a score of each of the target companies for an evaluation item set as the first rank according to a priority for the evaluation item included in the matching request of the customer company; selecting at least one first candidate company whose rank is higher than or equal to the reference rank; selecting at least one second candidate company whose rank is higher than or equal to the reference rank according to the calculated total score; selecting target companies simultaneously selected as the first candidate company and the second candidate company as the recommended company; and if candidate companies simultaneously selected as the first candidate company and the second candidate company are not identified, the first candidate company may be selected as the recommended company.

[0013] Meanwhile, the method of operating the electronic device includes a step of selecting at least one recommended company from among the plurality of selected candidate companies, and the step of selecting the recommended company may include performing web crawling based on the company name of each of the plurality of selected candidate companies to identify the latest event of each of the plurality of candidate companies, identifying the positivity of the identified event, and selecting the candidate company with the highest identified positivity as the recommended company.

[0014] An electronic device according to one embodiment of the present disclosure can perform a keyword-based web search to collect data related to the keyword.

[0015] In addition, an electronic device according to an embodiment of the present disclosure can extract necessary information from data related to a keyword.

[0016] Additionally, an electronic device according to an embodiment of the present disclosure can select a company that matches a customer according to a customer's request.

[0017] FIG. 1 is a flowchart illustrating an operation of an electronic device selecting a candidate company according to one embodiment of the present disclosure;

[0018] FIG. 2 is a diagram for explaining an operation of an electronic device communicating with a terminal of a customer company according to one embodiment of the present disclosure;

[0019] FIG. 3 is a flowchart illustrating an operation of an electronic device identifying an event according to an embodiment of the present disclosure;

[0020] FIG. 4 is a diagram illustrating an operation of an electronic device classifying and grouping businesses according to an embodiment of the present disclosure;

[0021] [Revised 29.07.2024 under Rule 91] FIG. 5 is a drawing for explaining the operation of an electronic device selecting a recommended company by considering recent events of candidate companies according to one embodiment of the present disclosure.

[0022] FIG. 6 is a block diagram illustrating a configuration of an electronic device according to an embodiment of the present disclosure.

[0023] Before describing the present disclosure in detail, the description method of the specification and drawings will be described.

[0024] First, the terms used in this specification and claims are general terms selected based on their functions in the various embodiments of the present disclosure. However, these terms may vary depending on the intentions of those skilled in the art, legal or technical interpretations, and the emergence of new technologies. Furthermore, some terms may have been arbitrarily selected by the applicant. These terms may be interpreted according to the meanings defined in this specification. In the absence of a specific definition, they may be interpreted based on the overall content of this specification and common technical knowledge in the relevant field.

[0025] Additionally, the same reference numbers or symbols in each drawing attached to this specification represent parts or components that perform substantially the same functions. For convenience of explanation and understanding, the same reference numbers or symbols are used in different embodiments. In other words, even if components with the same reference numbers are all depicted in multiple drawings, the multiple drawings do not necessarily represent a single embodiment.

[0026] Additionally, terms including ordinal numbers, such as "first," "second," etc., may be used in this specification and claims to distinguish between components. These ordinal numbers are used to distinguish identical or similar components from each other, and the use of these ordinal numbers should not be interpreted in a limited manner. For example, components associated with these ordinals should not be restricted in their order of use or arrangement by their numbers. If necessary, each ordinal number may be used interchangeably.

[0027] In this specification, singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as "comprise" or "consist of" are intended to indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but should be understood not to preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0028] In the embodiments of the present disclosure, terms such as "module," "unit," "part," etc. are terms used to refer to components that perform at least one function or operation, and such components may be implemented as hardware or software, or a combination of hardware and software. In addition, a plurality of "modules," "units," "parts," etc. may be integrated into at least one module or chip and implemented as at least one processor, except in cases where each needs to be implemented as a separate, specific hardware.

[0029] Additionally, in the embodiments of the present disclosure, when a part is said to be connected to another part, this includes not only a direct connection but also an indirect connection through another medium. Furthermore, unless specifically stated otherwise, the statement that a part includes a certain component does not exclude other components, but rather implies that other components may be included.

[0030] FIG. 1 is a flowchart illustrating an operation of an electronic device selecting a candidate company according to one embodiment of the present disclosure.

[0031] The electronic device (100) is a device for matching candidate companies at the request of a client company, and may be implemented as an electronic device or system comprising at least one computer. Alternatively, the electronic device (100) may be implemented as a server, smartphone, tablet PC, laptop PC, desktop PC, etc., but is not limited thereto.

[0032] Referring to FIG. 1, when an electronic device (100) receives a matching request for an investment company or partner company from a terminal (200) of a customer company, the electronic device (100) can obtain technical information of the customer company (S110).

[0033] The matching request received from the terminal (200) of the customer company may include the type of company that the customer company wants to match with (e.g., investment company, partner company) and may also include priorities for evaluation items.

[0034] The priority for the evaluation items may include information provided so that when the electronic device (100) performs matching between customer companies and companies, evaluation items with higher priorities are considered first.

[0035] Investment companies are those that discover and invest in competitive venture companies based on the company's growth potential or technological prowess. These companies may include accelerators (AC) or angel investors that invest in companies in the early stages of their startups, and venture capitalists (VC) that invest in established companies.

[0036] Partner companies are companies that collaborate to increase mutual benefits. Companies with different technologies and resources can form partnerships to increase mutual benefits, thereby becoming each other's partner companies.

[0037] Meanwhile, when the electronic device (100) receives a matching request for a company from the terminal (200) of the customer company, it can obtain the technical information of the customer company necessary to select an investment company or partner company that matches the request of the customer company.

[0038] Technical information may include technologies that the customer company possesses or is developing, technologies that the customer company needs, etc.

[0039] For example, the electronic device (100) can acquire technical information of a customer company by performing web scraping based on data collected by performing web crawling to identify events related to the customer company name (e.g., history of new technology announcements, information on technology development trends, articles related to commercialized technology, etc.).

[0040] Web crawling is the process of collecting and classifying information (e.g., web pages, web documents, etc.) on the Internet, and is used for large-scale data collection and site analysis. Web scraping is the process of extracting specific data on the Internet, and can extract necessary information from specific web pages.

[0041] As an example, the electronic device (100) may perform web crawling and web scraping using at least one first artificial intelligence model to analyze web pages and collect data based on keywords.

[0042] Specifically, the first artificial intelligence model can identify a web document containing a keyword among at least one web document included in each of a plurality of web pages included in the target website as an event related to the keyword.

[0043] At this time, the target website may be a preset website or a website acquired through external input (e.g., administrator input).

[0044] For example, the electronic device (100) may input a website and keywords obtained according to external input into the first artificial intelligence model so that the first artificial intelligence model performs web crawling on a plurality of web pages included in the website obtained according to external input.

[0045] A website is a collection of multiple web pages. Web pages can be implemented using various languages ​​such as HTML (HyperText Markup Language), CSS (Cascading Style Sheets), and JavaScript, and displayed through a user interface. A web page can be composed of multiple web documents, and a web document can contain data such as text and images.

[0046] For example, the first artificial intelligence model can identify web documents that contain words that match keywords by extracting multiple words from text data of web documents included in each of multiple web pages included in the target website, converting each extracted word into a vector form, and comparing it with the vector of the keyword.

[0047] Specifically, the first artificial intelligence model measures the angle between the vector of the keyword and the vector of each extracted word using cosine similarity, which divides the inner product between vectors by the product of the vector sizes, and if the measured angle is less than a threshold, determines that the keyword and the word match, and identifies a web document containing a word matching the keyword as an event related to the keyword.

[0048] For example, if a corporate customer name is entered as a keyword, the first artificial intelligence model can identify a web document that contains a word matching the customer company name among at least one web document included in each of multiple web pages as an event containing content related to the company (e.g., articles, papers, technology announcement information, interviews, etc. related to the company).

[0049] Meanwhile, the first artificial intelligence model may be a model trained by the electronic device (100), or may be a model trained by an external device and acquired by the electronic device (100), and the first artificial intelligence model may be a model that utilizes various learning algorithms such as natural language processing (NLP), convolutional neural networks (CNN), and K-Means clustering, but is not limited thereto.

[0050] As an additional example, the electronic device (100) may also receive technical information of the customer company from the terminal (200) of the customer company.

[0051] The electronic device (100) can perform web crawling based on technical keywords constituting technical information to identify an event corresponding to at least one of investments and partnerships related to the technical keywords (S120).

[0052] At least one technology keyword that constitutes the customer company's technology information may include a keyword related to a technology that the customer company possesses or is developing, or a technology that the customer company needs.

[0053] For example, if a customer company provides a simple payment service, the electronic device (100) can set simple payment, escrow, etc. as technical keywords.

[0054] In one embodiment, the electronic device (100) can extract at least one technical keyword constituting technical information of a customer company by using at least one second artificial intelligence model trained to extract keywords constituting information.

[0055] At this time, the second artificial intelligence model may include a model trained to divide text data into sentence units, identify the part of speech or sentence component of each word included in the text data, and extract words excluding stop words (e.g., particles, suffixes, adjectives, etc.), and accordingly, the second artificial intelligence model may extract multiple words from the text data constituting the information, convert each extracted word into a vector form, and identify the frequency of occurrence of words and the degree of association between words based on the vector of each word to extract at least one keyword.

[0056] Specifically, the second artificial intelligence model determines that the closer the distance between vectors, the higher the frequency of co-occurrence, and the smaller the angle between vectors, the higher the correlation. Therefore, words that frequently co-occur and have high correlation within text data can be selected through the vector of each word and identified as keywords.

[0057] Meanwhile, the second artificial intelligence model may be a model trained by the electronic device (100), or may be a model trained by an external device and acquired by the electronic device (100), and the second artificial intelligence model may be a model that uses various learning algorithms such as natural language processing (NLP), convolutional neural networks (CNN), and term frequency-inverse document frequency (TF-IDF), but is not limited thereto.

[0058] Meanwhile, the electronic device (100) can obtain an event including a technology keyword by inputting at least one keyword output by the second artificial intelligence model into the first artificial intelligence model, and at this time, the electronic device (100) can identify whether an investment keyword (e.g., investment, attraction, funds, etc.) and a partnership keyword (e.g., partner, cooperation, collaboration, alliance, etc.) are included among a plurality of words included in the text data constituting the obtained event.

[0059] At this time, the investment keyword and partnership keyword may be information pre-stored in the memory (110) or information acquired through external input.

[0060] Specifically, the electronic device (100) can identify an event that includes a word matching an investment keyword or a partnership keyword among events including a technology keyword output by the first artificial intelligence model.

[0061] For example, the electronic device (100) may convert each of a plurality of words, investment keywords, and partnership keywords included in text data constituting an event output by the first artificial intelligence model into a vector form, and may identify a word that matches the investment keyword or partnership keyword among the plurality of words included in the text data by using cosine similarity, which divides the inner product between vectors by the product of the vector sizes.

[0062] Specifically, the electronic device (100) measures the angle between the vector of each of a plurality of words included in the text data and the vector of the investment keyword, determines that the investment keyword and the word match when the measured angle is less than a threshold, and identifies an event including a word matching the investment keyword as an event related to investment.

[0063] In addition, the electronic device (100) can measure the angle between the vector of each of the plurality of words included in the text data and the vector of the partnership keyword, determine that the partnership keyword and the word match if the measured angle is less than a threshold, and identify an event including a word matching the partnership keyword as an event related to the partnership.

[0064] The electronic device (100) can classify and group companies included in the event (S130).

[0065] As an example, the electronic device (100) may group and classify each of the companies included in the event identified using the first artificial intelligence model into at least one of a technology holding company, an investment company, and a partner company.

[0066] Specifically, the electronic device (100) can group each company included in the event by classifying it into at least one of a first group including technology-holding companies, a second group including investment companies, and a third group including a partner group.

[0067] At this time, the electronic device (100) can set evaluation items for each group created according to grouping to evaluate the degree to which the companies included in each group match the matching request of the customer company.

[0068] Evaluation items may be set differently for each group, or may include, but are not limited to, common evaluation items.

[0069] The electronic device (100) can select multiple candidate companies that can be matched with the customer company based on the results of grouping (S140).

[0070] As an example, the electronic device (100) may calculate scores for companies included in each group based on evaluation items set for each group generated according to grouping, and select multiple candidate companies based on the calculated scores.

[0071] Specifically, the electronic device (100) can select a group that needs to be matched with a customer company according to a matching request from the customer company, identify the group as a target group, calculate a score for a company included in the target group based on evaluation items set for the target group, and select a company whose rank is higher than a standard rank based on the calculated score as a candidate company.

[0072] At this time, the standard ranking may be set according to the number of investment companies or partner companies for which the customer company has requested matching, and if the number of investment companies or partner companies for which the customer company has requested matching is not identified, it may be set according to a predefined value.

[0073] FIG. 2 is a diagram for explaining an operation of an electronic device communicating with a terminal of a customer company according to one embodiment of the present disclosure.

[0074] Referring to FIG. 2, the electronic device (100) can communicate with a terminal (200) of a customer company.

[0075] The terminal (200) of the customer company is a device for the customer company to transmit a matching request to an electronic device (100), and may be implemented as an electronic device consisting of at least one computer, and the terminal (200) of the customer company may be implemented as a server, a smartphone, a tablet PC, a laptop PC, a desktop PC, etc.

[0076] As an example, the electronic device (100) may receive a matching request for an investment company or partner company from a terminal (200) of a customer company.

[0077] Additionally, the electronic device (100) may receive technical information of the customer company from the terminal (200) of the customer company.

[0078] As an additional example, the electronic device (100) may select a plurality of candidate companies that can be matched with the customer company upon receiving a matching request for an investment company or partner company from the terminal (200) of the customer company, and transmit information about the plurality of selected candidate companies to the terminal (200) of the customer company.

[0079] FIG. 3 is a flowchart illustrating an operation of an electronic device identifying an event according to one embodiment of the present disclosure.

[0080] Referring to FIG. 3, the electronic device (100) can perform web crawling or web scraping using the first artificial intelligence model (31).

[0081] Specifically, the electronic device (100) inputs the technical information of the customer company into the second artificial intelligence model, inputs the output technical keywords into the first artificial intelligence model (31), and performs web crawling based on the technical keywords input by the first artificial intelligence model (31) to acquire multiple web documents (32) from various websites.

[0082] At this time, the first artificial intelligence model (31) can extract events (33) related to technical keywords from multiple web documents (32) and output them as result data.

[0083] Event (33) is data containing information related to the company, and may include articles, papers, technology announcement information, interviews, etc. related to the company.

[0084] For example, event (33) may include an interview with the company's Chief Executive Officer (CEO) or executives.

[0085] In addition, the electronic device (100) can identify a company included in an event (33) obtained based on the result data output by the first artificial intelligence model (31).

[0086] For example, the electronic device (100) can identify a company name included in an event (33) using a second artificial intelligence model trained to extract keywords.

[0087] For example, the electronic device (100) can identify a word that matches a subject among the sentence components of each of a plurality of words included in text data identified through the second artificial intelligence model, and can identify a word whose appearance frequency exceeds a preset value among the words that match the subject as a company name.

[0088] Meanwhile, the electronic device (100) can register an event (33) obtained through the result data output by the first artificial intelligence model (31) in a database (34).

[0089] For example, even if a matching request is not received from a terminal (200) of a customer company, the electronic device (100) can perform web crawling or web scraping using preset keywords to identify an event (33) in real time and register it in a database (34), and can also classify the event (33) according to the keyword or company included in the event (33) and register it in the database (34).

[0090] In addition, when a matching request is received from a terminal (200) of a customer company, the electronic device (100) may select multiple candidate companies that match the customer company by using an event (33) registered in the database (34).

[0091] For example, the electronic device (100) can input keywords stored in relation to regulations or policies by industrial sector into the first artificial intelligence model (31), thereby obtaining events related to regulations or policies by industrial sector output by the first artificial intelligence model (31), and can identify the country that implemented or announced the regulations or policies included in the obtained events, and classify the events according to the identified country and record them in the database (34).

[0092] Accordingly, when a request for matching with an investment company or partner company for a country is received from a terminal (200) of a customer company, the electronic device (100) can identify events (e.g., regulations or policies by sector) classified by country and recorded in a database (34) and utilize them to match the customer company with the investment company or partner company.

[0093] FIG. 4 is a diagram illustrating an operation of an electronic device classifying and grouping businesses according to one embodiment of the present disclosure.

[0094] Referring to FIG. 4, the electronic device (100) can identify at least one enterprise (41) from an event (33) and classify and group each identified enterprise (41).

[0095] In one embodiment, the electronic device (100) may identify at least one company (41) included in the event (33) using the second artificial intelligence model or the first artificial intelligence model, and group each identified company (41) by classifying it into at least one of a first group including technology-holding companies, a second group including investment companies, and a third group including partner companies.

[0096] At this time, as shown in Fig. 4, multiple companies (41) can be identified through an event (33), and one company can be classified into multiple groups.

[0097] A technology-holding company is a company that holds technology, and in the case of an electronic device (100), if keywords related to technology, such as disclosure of developed technology, technology scheduled for commercialization, and the company's unique technology, are identified in an event, the company can be classified as a technology-holding company.

[0098] The electronic device (100) can classify a company as an investment company if a company name including 'ventures', 'capital', 'investment', etc. is identified, or if a keyword related to investment such as investment plan or investment in progress is identified in an event, the company can be classified as a partner company if a keyword related to partnership or cooperation is identified in an event.

[0099] Meanwhile, the electronic device (100) can set evaluation items for evaluating companies included in each type for each group created based on the grouping results.

[0100] Specifically, the electronic device (100) can match the evaluation items for the first group including technology-holding companies, such as company size, location, technology relevance with the customer company's technology, credit rating, sales, and operating profit.

[0101] The company size is an item evaluated based on the number of employees, assets, etc. of the technology-holding company identified in response to the matching request of the customer company. For example, the electronic device (100) identifies the company size of the technology-holding company as one of small and medium-sized enterprises, medium-sized enterprises, and large enterprises based on the number of employees, assets, etc. of the technology-holding company, and identifies the company size of the company for which the customer company has requested a matching as one of small and medium-sized enterprises, medium-sized enterprises, and large enterprises based on the number of employees, assets, etc. identified in response to the matching request of the customer company. A score for the company size item can also be calculated based on whether the company size of the technology-holding company and the company size identified in response to the matching request of the customer company match.

[0102] Location is an item evaluated based on the distance between the country or region where the technology-holding company is located and the location identified in response to the customer company's matching request. For example, the electronic device (100) can calculate the distance between the requested location identified in response to the customer company's matching request and the location of the technology-holding company, and the shorter the calculated distance, the higher the score for the location item.

[0103] Technology relevance is an item that evaluates the relevance between the technology that a technology-holding company possesses, develops, or requires and the technology that a customer company possesses, develops, or requires. For example, an electronic device (100) can produce a high score for technology relevance if the technology that a customer company requires matches the technology that the technology-holding company possesses or develops, or if the technology that the customer company possesses or develops matches the technology that the technology-holding company requires.

[0104] Credit rating is an item evaluated based on the credit information of a technology-holding company. For example, the electronic device (100) may receive a credit rating of a technology-holding company from an external server (e.g., Public Procurement Service, credit rating agency), and the higher the received credit rating, the higher the score for the credit rating item may be calculated. As an additional example, the electronic device (100) may identify whether or not the technology-holding company has a history of bankruptcy, and if a history of bankruptcy is identified, the electronic device may calculate a lower score for the credit rating item.

[0105] Sales and operating profit are items evaluated based on the financial status of a technology-holding company. For example, the electronic device (100) performs web crawling and web scraping to obtain financial information of a technology-holding company, and identifies debt, capital, operating profit ratio, return on equity (ROE), etc. based on the obtained financial information. If the financial status of the technology-holding company is determined to be stable based on the identified information, a high score can be calculated for the sales and operating profit items.

[0106] The electronic device (100) can match the capital size, investment field, investment size, credit rating, business experience, etc. as evaluation items for the second group including the investment company.

[0107] Capital size is an item evaluated based on the size of capital held by the investment company. For example, the electronic device (100) can identify the capital size of the investment company by obtaining financial information of the investment company and identifying the assets and liabilities or stock price of the investment company based on the obtained financial information. The larger the identified capital size, the higher the score for the capital size item can be calculated.

[0108] The investment field is an item evaluated based on the technology field (e.g., AI, fintech, bio, etc.) in which the investment company mainly invests. For example, the electronic device (100) identifies the main investment field of the investment company based on keywords included in an event for the investment company, and if the main investment field of the investment company and the technology field of the customer company match, the score for the investment field item can be calculated as high.

[0109] The investment size is an item evaluated based on the amount invested by an investment company in a company. For example, the electronic device (100) can identify the amount invested by an investment company in a company based on keywords included in an event for the investment company, calculate an average value of the identified amount, and compare it with the investment size required by the customer company, thereby calculating a score for the investment size item.

[0110] As an additional example, the electronic device (100) may identify the field and amount in which the investment company wishes to invest based on keywords included in an event for the investment company, and compare the identified field and amount with the technology field and required investment scale of the customer company to calculate a score for the investment scale item.

[0111] Credit rating is an item evaluated based on the credit information of the investment company. For example, the electronic device (100) may receive the investment company's credit rating from an external server (e.g., Public Procurement Service, credit rating agency), and the higher the received credit rating, the higher the score for the credit rating item may be calculated. As a further example, the electronic device (100) may identify whether the investment company has a history of default, and if a history of default is identified, the score for the credit rating item may be calculated lower.

[0112] Business performance is an item evaluated based on the business history of the investment company. For example, the electronic device (100) can calculate the business performance of the investment company by identifying the date of establishment of the investment company, and the longer the calculated business performance, the higher the score for the business performance item can be calculated. As a further example, the electronic device (100) can identify the number of investments made since the investment company was established based on events involving the investment company, and calculate a score for the business performance item based on the number of investments compared to the business history of the investment company.

[0113] Electronic devices (100) can be matched with evaluation items for a third group including partner companies, such as company size, location, technology relevance with the customer company's technology, partner relevance, credit rating, sales, and operating profit.

[0114] The company size is an item evaluated based on the number of employees, assets, etc. identified in response to a matching request from a customer company. For example, the electronic device (100) identifies the company size of the partner company as one of small and medium-sized enterprises, medium-sized enterprises, and large enterprises based on the number of employees, assets, etc. identified in response to a matching request from a customer company. The electronic device (100) identifies the company size of the partner company, for which the customer company has requested a matching, as one of small and medium-sized enterprises, medium-sized enterprises, and large enterprises based on the number of employees, assets, etc. identified in response to a matching request from a customer company. A score for the company size can also be calculated based on whether the company size of the partner company and the company size identified in response to a matching request from a customer company match.

[0115] Location is an item evaluated based on the distance between the country or region where the partner company is located and the location identified in response to the customer company's matching request. For example, the electronic device (100) can calculate the distance between the requested location identified in response to the customer company's matching request and the location of the partner company, and the shorter the calculated distance, the higher the score for the location item.

[0116] Technology relevance is an item that evaluates the relevance between the technology that a partner company possesses, develops, or requires and the technology that a customer company possesses, develops, or requires. For example, an electronic device (100) can produce a high score for technology relevance if the technology that a customer company requires matches the technology that a partner company possesses or develops, or if the technology that a customer company possesses or develops matches the technology that a partner company requires.

[0117] Partner relevance is an item evaluated based on the similarity between a partner company's cooperating company and a customer company. For example, the electronic device (100) can identify an event that includes the partner company to identify the partner company's partnership information, and identify the partner company's cooperating company based on the partnership information. At this time, the electronic device (100) can identify the industry, owned or developed technology, etc. of the cooperating company based on data acquired by performing web crawling or web scraping based on the partner company's cooperating company name, and can identify the similarity between the cooperating company and the customer company. The higher the similarity (the more similar the cooperating company and the customer company), the lower the score can be calculated for the partner relevance item.

[0118] Credit rating is an item evaluated based on the credit information of a partner company. For example, the electronic device (100) may receive a credit rating of a partner company from an external server (e.g., Public Procurement Service, credit rating agency), and the higher the received credit rating, the higher the credit score of the partner company may be calculated. As an additional example, the electronic device (100) may identify whether a partner company has a history of default, and may calculate a lower credit score for a partner company with a history of default.

[0119] Sales and operating profit are items evaluated based on the financial status of the partner company. For example, the electronic device (100) performs web crawling and web scraping to obtain financial information of the partner company, and identifies debt, capital, operating profit ratio, return on equity (ROE), etc. based on the obtained financial information. If the financial status of the partner company is determined to be stable based on the identified information, the electronic device may calculate a high score for the sales and operating profit of the partner company.

[0120] Accordingly, the electronic device (100) can calculate a score related to the degree to which the company matches the customer company's matching request based on the evaluation items set for each group.

[0121] In one embodiment, the electronic device (100) may select at least one group requiring matching with the customer company based on a matching request received from the customer company's terminal (200), identify the group as a target group, and identify a company included in the target group as the target company. In this case, if the target group includes multiple groups, multiple target companies may be identified.

[0122] At this time, the electronic device (100) can calculate a score for each target company based on the identified event based on the evaluation items and technical keywords set for the target group.

[0123] For example, assuming that a customer company is identified as requesting matching with an investment company based on a matching request received from a terminal (200) of the customer company, the electronic device (100) may select a second group to identify it as a target group, and calculate a score for each target company included in the second group based on an event related to a technical keyword that constitutes the evaluation items set for the second group and the technical information of the customer company.

[0124] Specifically, the electronic device (100) can calculate a score for each evaluation item set for each target company and target group, and calculate a total score based on the calculated score for each evaluation item.

[0125] For example, the electronic device (100) can calculate a total score by adding up the scores for each evaluation item.

[0126] As an additional example, the electronic device (100) may also calculate a total score by applying a weight for each evaluation item to the score for each evaluation item.

[0127] The weights may be updated based on the matching evaluation information described later or the suitability of the matching, and the initial value may be a preset value.

[0128] At this time, the electronic device (100) can set a ranking for each target company based on the total score for each target company, and select at least one candidate company whose set ranking is higher than the standard ranking.

[0129] The criteria ranking may be set based on the number of investment firms or partner firms for which the client company has requested matching, or may be set based on a predefined value if the number of investment firms or partner firms for which the client company has requested matching is not identified.

[0130] Specifically, the electronic device (100) can set a ranking by sorting target companies according to the total score, and select target companies whose set ranking is higher than a standard ranking as candidate companies.

[0131] Additionally, the electronic device (100) can identify whether a matching request received from a customer company's terminal (200) includes a priority for an evaluation item.

[0132] In one embodiment, if the electronic device (100) identifies that the matching request received from the terminal (200) of the customer company includes a priority of evaluation items, the electronic device (100) may select at least one candidate company among a plurality of candidate companies as a recommended company.

[0133] Specifically, if the electronic device (100) is identified as including a priority of evaluation items in the matching request of the customer company, the electronic device can identify the score of each target company for the evaluation item set as the first priority according to the priority included in the matching request of the customer company, and set the ranking of each target company based on the score for the identified evaluation item.

[0134] At this time, the electronic device (100) can select a target company whose ranking is higher than the above-mentioned standard ranking based on the score for the first-priority evaluation item as the first candidate company.

[0135] In addition, the electronic device (100) can select at least one second candidate company whose ranking is higher than the above-mentioned standard ranking based on the total score of each target company.

[0136] Accordingly, the electronic device (100) can select the target company selected as the first candidate company and the second candidate company at the same time as the recommended company, and if the candidate company selected as the first candidate company and the second candidate company at the same time is not identified, the first candidate company can be selected as the recommended company.

[0137] As an additional example, if the electronic device (100) determines that the matching request received from the terminal (200) of the customer company does not include the priority of the evaluation items, the electronic device (100) can identify the score of the target company calculated for each evaluation item and identify the target company with the highest score among the scores calculated for each evaluation item as the main company.

[0138] At this time, the electronic device (100) can identify a major company for each evaluation item and select a recommended company from among the target companies based on the number of times each target company has been identified as a major company.

[0139] For example, if a target company identified as a major company more than twice is identified, the electronic device (100) may select the target company identified as a major company more than twice as a recommended company.

[0140] As an additional example, if a target company identified as a major company more than twice is not identified, the electronic device (100) may calculate an average value of the scores for each evaluation item of the major companies and select the major company with the highest calculated average value as the recommended company.

[0141] As an additional example, the electronic device (100) can identify a partner company that collaborates with a competitor of the customer company or an investment company that invests in a competitor of the customer company, set the partner company as a company of interest, and determine whether to select the partner company as a candidate company based on the score for each evaluation item of the partner company of interest.

[0142] Specifically, the electronic device (100) can input the customer company name into the first artificial intelligence model (31) to obtain company evaluation information including the customer company name, and identify a company included in the obtained company evaluation information as a competitor of the customer company.

[0143] For example, the electronic device (100) inputs website information including corporate evaluation information and the customer company name into the first artificial intelligence model (31), and the first artificial intelligence model (31) performs web crawling and web scraping based on the input website and customer company name to obtain and output corporate evaluation information including the customer company name.

[0144] At this time, the electronic device (100) can identify a company that matches a ranking that shows a difference of less than a preset value from the ranking of the customer company included in the corporate evaluation information as a competitor of the customer company.

[0145] For example, when a matching request for a partner company is received from a terminal (200) of a customer company, the electronic device (100) inputs the name of the competing company and a partnership keyword into the first artificial intelligence model to identify the company included in the acquired event as a partner company collaborating with a competing company of the customer company and set it as a company of interest.

[0146] As an additional example, when a matching request for an investment company is received from a terminal (200) of a customer company, the electronic device (100) inputs the name of a competing company and an investment keyword into the first artificial intelligence model to identify the company included in the acquired event as an investment company collaborating with a competing company of the customer company and sets it as a company of interest.

[0147] At this time, if multiple partner companies or multiple investment companies are identified, multiple companies of interest may be set.

[0148] Meanwhile, when a matching request for a partner company is received from a terminal (200) of a customer company, the electronic device (100) can calculate a score for each evaluation item for each company of interest (a partner company of a competing company) using the evaluation items set for the third group.

[0149] In addition, when a matching request for an investment company is received from a terminal (200) of a customer company, the electronic device (100) can use the evaluation items set for the second group to calculate a score for each evaluation item for each company of interest (an investment company investing in a competing company).

[0150] At this time, the electronic device (100) can calculate the total score of each company of interest by adding up the scores for each evaluation item produced, and select a company of interest with a total score higher than a preset score as a candidate company.

[0151] Meanwhile, the electronic device (100) can compare a candidate company selected from among companies of interest and a candidate company selected from among target companies and select a matching company as a recommended company.

[0152] [Revised 29.07.2024 under Rule 91] FIG. 5 is a diagram illustrating an operation of an electronic device selecting a recommended company by considering recent events of candidate companies according to one embodiment of the present disclosure.

[0153] [Revised 29.07.2024 under Rule 91] Referring to Fig. 5, the electronic device (100) can select at least one recommended company (54) among multiple candidate companies (51).

[0154] As an example, the electronic device (100) may perform web crawling based on the company name of each of a plurality of candidate companies (51) that can be matched with the customer company based on the results of grouping, thereby identifying the latest event (53) of each of the plurality of candidate companies (51).

[0155] Specifically, as the electronic device (100) inputs the company name of each of the plurality of candidate companies (51) into the first artificial intelligence model (31), the first artificial intelligence model (31) performs web crawling based on the company name of each of the plurality of candidate companies (51) to obtain at least one web document (52) including at least one company name among the company names of each of the plurality of candidate companies (51).

[0156] Accordingly, the first artificial intelligence model (31) can extract events related to each of a plurality of candidate companies (51) based on the company name included in each web document (52), classify the extracted events by candidate company (51), and output the results as data.

[0157] At this time, the electronic device (100) can identify the latest event (53) of each of the multiple candidate companies (51) based on the result data output by the first artificial intelligence model.

[0158] Specifically, the electronic device (100) can identify the event that occurred most recently among the events related to each candidate company (51) as the latest event.

[0159] As an example, the electronic device (100) can identify the positivity of the latest event (53) and select the candidate company with the highest identified positivity as the recommended company (54).

[0160] For example, the electronic device (100) can identify the positivity of a recent event (53) using at least one first artificial intelligence model trained to identify positivity or negativity of a text.

[0161] Specifically, the electronic device (100) can identify the positivity of the latest event (53) related to each candidate company (51) by inputting the latest event (53) related to each candidate company (51) into the first artificial intelligence model.

[0162] The first artificial intelligence model may be a model trained by the electronic device (100), or may be a model trained by an external device and acquired by the electronic device (100), and the first artificial intelligence model may be a model that uses various learning algorithms such as random forest, natural language processing (NLP), convolutional neural networks (CNN), term frequency-inverse document frequency (TF-IDF), long short-term memory (LSTM), recurrent neural networks (RNN), transformer, etc., but is not limited thereto.

[0163] For example, the electronic device (100) can train a first artificial intelligence model to identify the positivity, negativity, or neutrality of each text included in an event using training data including a plurality of positive texts, a plurality of negative texts, and a plurality of neutral texts, and to identify the positivity of the event based on the frequency of appearance of the positive texts, negative texts, and neutral texts.

[0164] At this time, the electronic device (100) can select the candidate company related to the latest event with the highest positivity among the positivity ratings of the latest events (53) related to each candidate company (51) identified through the first artificial intelligence model as the recommended company (54).

[0165] As an additional example, the electronic device (100) may calculate a marketing score for each of a plurality of candidate companies (51) and select at least one recommended company (54) based on the calculated marketing score.

[0166] Specifically, the electronic device (100) can identify the advertising exposure of each of the plurality of candidate companies (51) and calculate the marketing score of each of the plurality of candidate companies (51) based on the identified advertising exposure.

[0167] For example, the electronic device (100) can identify the media (e.g., website, TV, etc.) through which each of the plurality of candidate companies (51) conducts advertising, and identify the advertising exposure for the identified media.

[0168] For example, the electronic device (100) can identify the advertisement exposure of the candidate company based on the time or number of times the advertisement of the candidate company is exposed for a preset period of time.

[0169] At this time, the electronic device (100) can identify the positivity of netizens' reactions to the advertisement of the candidate company, set a coefficient according to the positivity of netizens' reactions, and apply the set coefficient to the advertisement exposure, thereby calculating the marketing score of the candidate company.

[0170] For example, the electronic device (100) can set the coefficient to be higher as the positivity of netizen reactions increases.

[0171] Specifically, the electronic device (100) inputs keywords for advertisements of candidate companies into the first artificial intelligence model (31), and based on the input keywords, the first artificial intelligence model (31) performs web crawling or web scraping to output result data including netizen reactions (e.g., comments, posts on a website, etc.), and inputs the result data output by the first artificial intelligence model (31) into the first artificial intelligence model, thereby identifying the positivity of netizen reactions and setting a coefficient according to the positivity of netizen reactions.

[0172] Accordingly, the electronic device (100) can calculate the marketing score of each of the plurality of candidate companies (51) by applying a coefficient set based on the positivity of netizens' reactions to the advertisements of each of the plurality of candidate companies (51) to the advertisement exposure of each of the plurality of candidate companies (51).

[0173] At this time, if the number of multiple candidate companies (51) is less than a preset number, the electronic device (100) selects one candidate company with the highest marketing score as a recommended company, and if the number of multiple candidate companies (51) is greater than or equal to a preset number, the electronic device (100) sets the ranking of each of the multiple candidate companies (51) based on the marketing score of each of the multiple candidate companies (51), and selects a candidate company whose set ranking is greater than or equal to the preset ranking as a recommended company.

[0174] As a result, if matching is performed only by considering the degree to which the client company's request and the target company match, a situation may arise where the client company cooperates with a company that netizens have a negative reaction to, which may damage the client company's evaluation. However, by selecting a candidate company that netizens have a positive reaction to as a recommended company and providing it to the client company, the client company can provide the possibility of a positive change in the client company's evaluation as the client company cooperates with the recommended company.

[0175] Additionally, the electronic device (100) can receive matching evaluation information from the terminal (200) of the customer company after a plurality of candidate companies are provided to the terminal (200) of the customer company.

[0176] Match evaluation information may include the client company's assessment of the suitability of the match, including whether to enter into a contract with the candidate company and the suitability of each of the multiple candidate companies.

[0177] Meanwhile, the electronic device (100) can update the weight applied to the score for each evaluation item based on the matching evaluation information received from the customer company's terminal (200).

[0178] At this time, the electronic device (100) can classify multiple candidate companies provided to the customer company's terminal (200) into suitable candidate companies and unsuitable candidate companies based on the matching evaluation information.

[0179] For example, the electronic device (100) may identify, for each suitable candidate company, the evaluation item for which the highest score was calculated among the scores for each evaluation item of each suitable candidate company, and increase the weight of the evaluation item for which the highest score was calculated the most times.

[0180] As an additional example, the electronic device (100) may identify, for each of the unsuitable candidate companies, the evaluation item for which the highest score was calculated among the scores for each evaluation item, and may reduce the weight of the evaluation item for which the highest score was calculated the most times.

[0181] Meanwhile, the electronic device (100) can identify the suitability of the match based on the progress information of an investment contract or partnership contract between at least one candidate company among a plurality of candidate companies provided to the terminal (200) of the customer company and the customer company.

[0182] For example, the electronic device (100) may obtain an event including a customer company name or a candidate company name through the first artificial intelligence model, and if it is identified that a contract has been concluded between the customer company and the candidate company provided to the customer company's terminal (200) through the obtained event, it may be identified that a suitable match has been made.

[0183] As an additional example, if the contract progress information between the candidate companies and the customer company is not identified through an event obtained through the first artificial intelligence model within a preset period after information on multiple candidate companies is provided to the customer company's terminal (200), the electronic device (100) may request transmission of the contract progress information to the customer company's terminal (200).

[0184] At this time, the electronic device (100) can identify that a suitable match has been made if it is determined that a contract with a candidate company is in progress or has been concluded based on the contract progress information received from the terminal (200) of the customer company, and can identify that an unsuitable match has been made if it is determined that the contract has not been concluded.

[0185] If it is identified that a suitable match has been made, the electronic device (100) may increase the weight for the evaluation item for which the highest score was calculated among the scores for each evaluation item of the candidate company that has entered into a contract with the customer company.

[0186] If it is identified that an inappropriate matching has been performed, the electronic device (100) can identify, for each of the plurality of candidate companies, the evaluation item for which the highest score was calculated among the scores for each evaluation item of each of the plurality of candidate companies, and reduce the weight of the evaluation item for which the highest score was calculated the most times.

[0187] As a result, the reliability of matching can be improved by selecting candidate companies and performing matching based on the total score calculated using weights that reflect the suitability of matching performed in the past, thereby increasing the possibility of selecting a suitable candidate company.

[0188] FIG. 6 is a block diagram illustrating a configuration of an electronic device according to an embodiment of the present disclosure.

[0189] Referring to FIG. 6, the electronic device (100) may include a memory (110), a processor (120), and a communication unit (130).

[0190] The memory (110) is a configuration for storing an operating system (OS) for controlling the overall operation of components of the electronic device (100) and at least one instruction or data related to the components of the electronic device (100).

[0191] In one embodiment, the memory (110) may store at least one artificial intelligence model among at least one second artificial intelligence model, at least one first artificial intelligence model, and at least one first artificial intelligence model.

[0192] The memory (110) may include non-volatile memory such as ROM, flash memory, etc., and may include volatile memory composed of DRAM, etc. In addition, the memory (110) may include a hard disk, SSD (Solid state drive), etc.

[0193] The processor (120) is configured to control the overall electronic device (100).

[0194] In one embodiment, the processor (120) can train at least one artificial intelligence model stored in the memory (110).

[0195] The processor (120) may include a general-purpose processor such as a CPU (Central Processing Unit), an AP, a DSP (Digital Signal Processor), a graphics-only processor such as a GPU (Graphics Processor Unit), a VPU (Vision Processing Unit), or an artificial intelligence-only processor such as an NPU (Neural Processing Unit). The artificial intelligence-only processor may be designed with a hardware structure specialized for training or using a specific artificial intelligence model.

[0196] The communication unit (130) is configured to perform communication with the outside.

[0197] As an example, the electronic device (100) can perform communication with a terminal (200) of a customer company through a communication unit (130) and receive technical information of the customer company from the terminal (200) of the customer company.

[0198] The communication unit (130) may include circuits, modules, chips, etc. for performing communication using various wired and wireless communication methods. The communication unit (130) may also be connected to external devices and servers through various networks.

[0199] Depending on the area or scale, a network may be a personal area network (PAN), a local area network (LAN), or a wide area network (WAN), and depending on the openness of the network, it may be an intranet, an extranet, or the Internet.

[0200] The communication unit (130) can be connected to external devices and servers through various wireless communication methods such as LTE (long-term evolution), LTE-A (LTE Advance), 5G (5th Generation) mobile communication, CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), GSM (Global System for Mobile Communications), DMA (Time Division Multiple Access), WiFi (Wi-Fi), WiFi Direct, Bluetooth, BLE (Bluetooth Low Energy), NFC (near field communication), Zigbee, and LoRa.

[0201] Additionally, the communication unit (130) may be connected to external devices and servers through wired communication methods such as Ethernet, optical network, Universal Serial Bus (USB), and ThunderBolt.

[0202] In addition, the communication unit (130) may be configured to utilize various communication methods / technologies that will be newly designed in the future.

[0203] Meanwhile, the electronic device (100) can communicate with an external server including a generative AI (Artificial Intelligence), input at least one keyword into the generative AI, and obtain an event related to the input keyword through the generative AI.

[0204] Generative AI is a large language model (LLM) that performs natural language processing (NLP). It can be an artificial intelligence model trained to understand the context of data acquired based on user input, predict the next sequence of data acquired based on user input based on the understood context, and generate result data (e.g., text, audio, etc.) that includes the predicted data.

[0205] As an example, the electronic device (100) may input technical keywords that constitute technical information of a customer company into a generative AI to obtain output data of the generative AI that includes events related to investments or partnerships related to the technical keywords.

[0206] As an additional example, the electronic device (100) can input the event output by the first artificial intelligence model into the generative AI to identify whether the event output by the first artificial intelligence model is true or not, thereby obtaining information on whether the event output by the first artificial intelligence model is true or not.

[0207] At this time, if the event output by the first artificial intelligence model by the generative AI is identified as false, the electronic device (100) can calculate a score for each evaluation item for each target company included in the target group, excluding the event identified as false.

[0208] As an additional example, the electronic device (100) may input the latest event into the generative AI to identify the positivity of the latest event output by the first artificial intelligence model, identify the positivity of the latest event by comparing the positivity of the latest event output by the first artificial intelligence model and the positivity of the latest event output by the generative AI, identify the final positivity of the latest event, and select a recommended company based on the final positivity of the latest event of each of the plurality of candidate companies.

[0209] Meanwhile, the electronic device (100) can input preset keywords into the generative AI in real time, even if a matching request is not received from the customer company's terminal (200), to acquire events related to the keywords, and classify the acquired events according to the type of keywords included in the acquired events and store them in a database.

[0210] The keyword types may include technology, investment, partnership, etc., and at least one keyword may be matched for each type.

[0211] At this time, if one event includes multiple keywords, the electronic device (100) may store one event by matching it with each type of the multiple keywords.

[0212] Additionally, even if a matching request is not received from a customer company's terminal (200), the electronic device (100) may input preset keywords into the generative AI in real time to acquire events related to the keywords, classify the acquired events according to the companies included in the acquired events, and store them in a database. In this case, if multiple companies are included in a single event, the electronic device (100) may match one event with each of the multiple companies and store the event.

[0213] Meanwhile, the various embodiments described above may be implemented in a recording medium readable by a computer or similar device using software, hardware, or a combination thereof.

[0214] In terms of hardware implementation, the embodiments described in the present disclosure may be implemented using at least one of Application Specific Integrated Circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, micro-controllers, microprocessors, and other electrical units for performing functions.

[0215] In some cases, the embodiments described herein may be implemented within the processor itself. In a software implementation, the embodiments described herein, such as the procedures and functions described herein, may be implemented as separate software modules. Each of the software modules described above may perform one or more of the functions and operations described herein.

[0216] Meanwhile, computer instructions for performing processing operations in electronic devices and the like according to the various embodiments of the present disclosure described above may be stored in a non-transitory computer-readable medium. When the computer instructions stored in such a non-transitory computer-readable medium are executed by a processor of a specific device, they cause the specific device to perform processing operations according to the various embodiments described above.

[0217] A non-transitory computer-readable medium refers to a medium that permanently stores data and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specific examples of non-transitory computer-readable media include CDs, DVDs, hard disks, Blu-ray discs, USBs, memory cards, and ROMs.

[0218] Although the preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above, and various modifications may be made by a person having ordinary skill in the art to which the present disclosure pertains without departing from the gist of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical idea or prospect of the present disclosure.

Claims

1. In the operating method of an electronic device that performs inter-company matching, When a matching request for an investment company or partner company is received from a terminal of a customer company, a step of acquiring technical information of the customer company; A step of performing web crawling based on at least one technical keyword constituting the technical information to identify an event corresponding to at least one of investments and partnerships related to the technical keyword; A step of grouping each company included in the above-mentioned identified event into at least one of technology holding companies, investment companies, and partner companies; and An operating method of an electronic device, comprising: a step of selecting a plurality of candidate companies that can be matched with the customer company based on the results of the grouping; 2. In paragraph 1, The above grouping steps are: Identify at least one business involved in the above identified event, Each of the identified companies is grouped into at least one of a first group including the technology-holding company, a second group including the investment company, and a third group including the partner company. An operating method of an electronic device, wherein evaluation items are set for each group to evaluate the extent to which a company included in each group matches the matching request of the customer company.

3. In paragraph 2, The method of operating the above electronic device is as follows: An operating method of an electronic device, comprising: a step of selecting at least one group that needs to be matched with the customer company based on the result of the grouping, and identifying the group as a target group, according to a matching request from the customer company.

4. In paragraph 3, The step of selecting multiple candidate companies that can be matched with the above customer company is: Identify the companies included in the above target group as target companies, The scores for each evaluation item set for the above target group are calculated for each target company, Based on the scores for each evaluation item calculated for each target company above, a total score is calculated for each target company above, An operating method of an electronic device, wherein a ranking of each target company is set based on the total score of each target company, and at least one candidate company whose set ranking is higher than a reference ranking is selected from among the target companies.

5. In paragraph 3, The method of operating the above electronic device is as follows: A step of identifying whether the above customer company's matching request includes a priority for the above evaluation items; and An operating method of an electronic device, comprising: a step of selecting at least one candidate company among the plurality of selected candidate companies as a recommended company, when the matching request of the customer company is identified as including a priority for the evaluation items.

6. In paragraph 5, The step of selecting at least one candidate company as a recommended company is: Set a rank for each of the target companies based on the score for the evaluation item set as the first priority according to the priority of the evaluation item included in the matching request of the customer company, and select at least one first candidate company whose set rank is higher than the standard rank. Select at least one second candidate company whose ranking is higher than the above-mentioned standard ranking based on the calculated total score, Select the target company selected simultaneously as the first candidate company and the second candidate company as the recommended company, An operating method of an electronic device, wherein if a candidate company selected as the first candidate company and the second candidate company at the same time is not identified, the first candidate company is selected as the recommended company.

7. In paragraph 1, The method of operating the above electronic device is as follows: A step of selecting at least one recommended company from among the plurality of selected candidate companies; The steps for selecting the above recommended companies are: Perform web crawling based on the company name of each of the multiple candidate companies selected above to identify the latest event of each of the multiple candidate companies, A method of operating an electronic device, wherein the positivity of the identified event is identified, and the candidate company with the highest identified positivity is selected as the recommended company.

Images