KR-20260063063-A - METHOD AND SERVER FOR PROVIDING COMPANY SEARCH BASED ON INFERENCE MODEL

Abstract

The present disclosure relates to a method and server for providing a company search based on an inference model. A method for providing a company search based on an inference model, performed by a server according to one embodiment of the present disclosure, may include the steps of: obtaining user input related to a company; obtaining company search data by preprocessing the user input; calculating the similarity between the company search data and data within a company information database; providing a first company list corresponding to the search result and a second company list representing other companies associated with the first company as search results based on the similarity; and providing a certificate of incorporation and company information of the selected company based on the selection of one company from the first company list or the second company list.

Inventors

• 정종현
• 양성권

Assignees

• 주식회사 제제소프트

Dates

Publication Date

20260507

Application Date

20241030

Claims (20)

1. In a method for providing a company search based on an inference model performed by a server, A step of obtaining user input related to the company; A step of obtaining corporate search data by preprocessing the above user input; A step of calculating the similarity between the above-mentioned corporate search data and the data within the corporate information database; Based on the above similarity, a step of providing a first list of companies corresponding to the search result and a second list of companies representing other companies associated with the first company as search results; and A method comprising the step of providing a certified copy of the corporate registration certificate and corporate information of a selected company based on the selection of one company from the first company list or the second company list.
2. In paragraph 1, the above method is, The step of creating the above corporate information database is further included, The step of creating the above corporate information database is, Step of obtaining corporate registration certificates of multiple companies; A step of recognizing and parsing characters from each of the above corporate registration certificates; and A method comprising the step of structuring the parsed data into a hierarchical structure corresponding to registration elements to generate registration data representing machine-analyzable registration information.
3. In paragraph 1, The step of providing the above company information is, A step of generating a first relationship graph representing the relationship between a selected first company and companies in the second company list based on the selection of a company within the first company list; and A method comprising the step of visualizing and providing the first relationship graph above.
4. In paragraph 3, The step of providing the above company information is, A step of searching for a third list of companies representing other companies associated with the selected second company, based on the selection of a company within the second list of companies; and A step of generating a second relationship graph representing the relationship between the selected company and the companies within the third company list; and A method comprising the step of visualizing and providing the second relationship graph above.
5. In paragraph 1, The step of acquiring the above-mentioned company search data is, A step of determining candidate company search data based on the preprocessing results of the above user input; A step of calculating similarity between the above candidate search data and user inputs of other users; and A method comprising the step of obtaining the company search data by selecting a portion of the candidate company search data based on the above similarity.
6. In paragraph 1, The step of receiving the above user input is, A step of receiving a first user input for a first user input field that is a complete input field; It includes the step of receiving a second user input for a second user input field that is an incomplete input field, and The step of acquiring the above-mentioned company search data is, A method comprising the step of performing the preprocessing only on the second user input to obtain first corporate search data corresponding to the original of the first user input and second corporate search data corresponding to the preprocessed second user input.
7. In paragraph 6, The step of calculating the similarity between the above-mentioned corporate search data and the data within the corporate information database is: A method of applying a first weight to the first company search data and applying a second weight to the second company search data, wherein the first weight has a value greater than the second weight.
8. In Paragraph 7, The step of acquiring the above-mentioned company search data is, A step of providing a list of corrected user inputs by performing preprocessing on the second user input above; and A method comprising the step of determining the second corporate search data based on a user selection of the list of corrected user inputs.
9. In paragraph 8, The step of acquiring the above-mentioned company search data is, A method comprising the step of applying the second user input to a large-scale language model to provide a list of the corrected user inputs, wherein applying the second user input to the large-scale language model is performed only when the second user input of a predefined form for the execution of the large-scale language model is identified.
10. In Paragraph 9, The step of calculating the similarity between the above-mentioned corporate search data and the data within the corporate information database is: A method comprising the step of adjusting the first weight and the second weight such that the second weight has a value greater than the first weight when a user selection for the list of corrected user inputs is identified.
11. In a server that provides corporate search based on an inference model, Communication interface; Memory that stores one or more instructions; It includes one or more processors that execute one or more instructions stored in the memory, and The above one or more processors, by executing the above one or more instructions, Acquire user input related to the company, and The above user input is preprocessed to obtain corporate search data, and Calculate the similarity between the above corporate search data and the data within the corporate information database, and Based on the above similarity, a first list of companies corresponding to the search results and a second list of companies representing other companies associated with the first company are provided as search results, and A server that provides a certified copy of the corporate registration and corporate information of a selected company based on the selection of one company from the above-mentioned first company list or the above-mentioned second company list.
12. In Paragraph 11, The above one or more processors, by executing the above one or more instructions, Obtaining the corporate registration certificates of multiple companies, and Recognize and parse characters from each of the above corporate registration certificates, The above parsed data is structured into a hierarchical structure corresponding to registration elements to generate registration data representing machine-analyzable registration information, and A server that generates a corporate information database containing the above-mentioned registration data.
13. In Paragraph 11, The above one or more processors, by executing the above one or more instructions, Based on the selection of a company from the first company list above, a first relationship graph is generated that represents the relationship between the selected first company and the companies in the second company list above, and A server that visualizes and provides the above-mentioned first relationship graph.
14. In Paragraph 13, The above one or more processors, by executing the above one or more instructions, Based on the selection of a company within the above-mentioned second company list, a third company list representing other companies associated with the selected second company is searched, and Generate a second relationship graph representing the relationship between the selected company and the companies within the third company list, and A server that visualizes and provides the above second relationship graph.
15. In Paragraph 11, The above one or more processors, by executing the above one or more instructions, Based on the preprocessing results of the above user input, candidate company search data is determined, and Calculate the similarity between the above candidate search data and user inputs from other users, and A server that obtains the company search data by selecting a portion of the candidate company search data based on the above similarity.
16. In Paragraph 11, The above one or more processors, by executing the above one or more instructions, Receives first user input for a first user input field that is a complete input field, and Receives a second user input for a second user input field that is an incomplete input field, and A server that performs the above preprocessing only on the above second user input to obtain first corporate search data corresponding to the original of the first user input and second corporate search data corresponding to the preprocessed second user input.
17. In Paragraph 16, The above one or more processors, by executing the above one or more instructions, A server that applies a first weight to the first corporate search data and applies a second weight to the second corporate search data, wherein the first weight has a value greater than the second weight.
18. In Paragraph 17, The above one or more processors, by executing the above one or more instructions, A list of corrected user inputs is provided by performing preprocessing on the above second user input, and A server that determines the second corporate search data based on a user selection of the list of the above-mentioned corrected user inputs.
19. In Paragraph 18, The above one or more processors, by executing the above one or more instructions, A server that applies the second user input to a large-scale language model to provide a list of the corrected user inputs, wherein applying the second user input to the large-scale language model is performed only when the second user input of a predefined form for the execution of the large-scale language model is identified.
20. In Paragraph 19, The above one or more processors, by executing the above one or more instructions, A server that, when a user selection for the list of the above-mentioned corrected user inputs is identified, adjusts the first weight and the second weight so that the second weight has a value greater than the first weight.

Description

Method and Server for Providing Company Search Based on Inference Model The present disclosure relates to a method and server for providing corporate search based on an inference model, and more specifically, to a method and server that provides an inference model capable of obtaining desired corporate search results by applying preprocessing and weights to user input even if the user does not accurately know corporate information, and enables the user to view information included in corporate information and corporate registration certificates as data in a refined form. Currently, users wishing to inquire about a company's Certificate of Incorporation utilize a method where they register with the Online Registry Office to search for companies and access the service directly. The Online Registry Office serves as the primary means for obtaining Certificates of Incorporation; users can access the site, enter the necessary company information, and download the Certificate through a search. During this process, users must accurately enter company details such as the company name, representative, and corporate registration number to obtain the Certificate of Incorporation for the desired company. However, if users do not know the exact corporate information required for a search, they may experience difficulties in finding the desired company. For example, if they do not know the exact corporate name or the name of the representative, the search results may be inaccurate or fail to find anything at all. This causes users to spend a significant amount of time obtaining the necessary information and results in inconvenience during the search process. Furthermore, certified copies of land registers downloaded from the online registry are provided as documents in formats such as PDF, which are not machine-readable structured data. Such unstructured data is difficult to process in automated systems and requires additional data conversion. This reduces data usability and hinders users from efficiently utilizing the information they desire. Consequently, given the current level of technology, there are various issues regarding corporate search and the utilization of certified copies of land registers. FIG. 1 is a diagram for schematically explaining the operation of a server according to one embodiment of the present disclosure. FIG. 2 is a flowchart for explaining the operation of a server according to one embodiment of the present disclosure. FIG. 3 is a block diagram illustrating the process of a server creating an enterprise information database according to one embodiment of the present disclosure. FIG. 4 is a flowchart illustrating the operation of a server providing corporate information according to one embodiment of the present disclosure. FIG. 5 is a flowchart illustrating the operation of a server generating corporate search data according to one embodiment of the present disclosure. FIG. 6 is a flowchart illustrating the operation of a server correcting corporate search data according to one embodiment of the present disclosure. FIG. 7 is a flowchart illustrating the operation of a server correcting corporate search data according to one embodiment of the present disclosure. FIG. 8 is a block diagram illustrating the configuration of a server according to one embodiment of the present disclosure. In the following, embodiments are described in detail with reference to the attached drawings. However, various modifications may be made to the embodiments, and thus the scope of the patent application is not limited or restricted by these embodiments. It should be understood that all modifications, equivalents, and substitutions to the embodiments are included within the scope of the rights. Specific structural or functional descriptions of the embodiments are disclosed merely for illustrative purposes and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to specific disclosed forms, and the scope of this specification includes modifications, equivalents, or substitutions that fall within the technical concept. Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component. Furthermore, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly and specifically defined otherwise. In certain cases, terms have been selected at the applicant's discretion, and in such cases, their meanings will be described in detail in the relevant explanatory sections. Accordingly, terms used in this disclosure should be defined not merely by their names, but based on their meanings and the content throughout this disclosure. When it is stated that a component is "connected" to another co