System and method for domain-based user-customized database generation through question and intent classification

Abstract

The present disclosure relates to an artificial intelligence system and method capable of generating a user-customized SQL query based on a user question entered in natural language to query data. The system and method provide a domain-based user-customized database generation system and method based on question and intent classification that analyzes the user's question, accurately grasps the user's intent, and only if the intent is to generate a database query, classifies the question and determines the domain, generates and updates an execution plan through interaction with the user, and finally generates an appropriate database query to query data.

Description

[Technical Field]

[0001] The present disclosure relates to an artificial intelligence system and method capable of generating a user-customized database query based on a user question entered in natural language and querying data. In particular, the present disclosure provides a system and method for domain-based user-customized database generation through question and intent classification, which analyzes the user's question, accurately grasps the intent, and only if the intent is to generate a database query, classifies the question, determines the domain, generates and updates an execution plan through interaction with the user, and ultimately generates an adapted database query to query data. [Background technology]

[0002] With the development of computer technology, businesses and government agencies are using a variety of computer programs for business and administrative tasks. These computer programs can store and process a large amount of data necessary for business and administrative tasks such as accounting, human resources, finance, sales, trade, purchasing, materials, production, and inventory. By using these computer programs, users (business practitioners, executives, and managers of businesses and government agencies) can easily store and manage data used by businesses and government agencies. Computer programs used by businesses and government agencies support functions for creating, editing, and managing various types of documents.

[0003] Patent Document 1 (Korean Patent Publication No. 10-2024-0100779) discloses a syntax generation method for a database for adding or updating original data to the database.

[0004] However, in conventional database generation systems, the model of converting natural language processing into SQL to provide data services became mainstream. Such database generation systems required that each user be able to access only specific data, which required access control for specific items for each user, making it difficult to control the permissions of the generated SQL. In addition, since large amounts of data were queried, it was difficult to prevent load on the database, and the generated SQL was likely to cause load on the database service.

[0005] In addition, since corrections were limited after SQL generation, it was difficult to guarantee performance compared to SQL created by users.Furthermore, tokens were generated for each natural language question, which increased costs, resulting in excessive costs for natural language questions.

[0006] In addition, there is a risk that internal data generated by SQL may be exposed to external networks, and there is a drawback in that security issues may arise due to the use of external networks for natural language processing.

[0007] Such conventional database generation systems have limitations in accurately understanding users' natural language queries and grasping their intent, do not fully utilize user information, making it difficult to provide personalized data, and have difficulty in properly classifying queries and determining domains, which reduces the accuracy and efficiency of data queries. Furthermore, conventional database generation systems do not reflect detailed user requirements, making it difficult to provide personalized data queries, and have fixed execution plans that do not flexibly respond to changing user requirements or data environments. [Prior art documents] [Patent documents]

[0008] [Patent Document 1] Korean Patent Publication No. 10-2024-0100779 Summary of the Invention [Problem to be solved by the invention]

[0009] The present disclosure has been devised in response to the above-mentioned background art, and can provide a system and method for generating a domain-based user-customized database through question and intent classification using artificial intelligence technology that can automatically generate a user-customized database query based on a user question entered in natural language and efficiently query data.

[0010] The technical problems of the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0011] To solve the aforementioned problems, a method according to some embodiments is performed by a computing device, comprising: To achieve the above object, one embodiment of the present disclosure provides a system for generating a domain-based user-customized database through question and intent classification, which may include: a question receiving module that receives a question in natural language via a user interface; an intent classification module that utilizes user information and uses a large-scale language model to understand and classify the intent of the user's question; a question classification module that uses a natural language processing engine and a vector database to determine whether the question belongs to a predefined domain; a domain determination module that is configured with a domain mapping table and a determination algorithm and determines an appropriate domain based on the analyzed question; and an execution module that is configured with a basic execution plan and a database linkage module and establishes and executes a basic execution plan based on the domain determination information.

[0012] The intent classification module classifies the user's intent by combining the received question and user information, and the user's intent may be composed of at least one of daily conversation, SQL generation, API call, and instruction word saving.

[0013] The execution module establishes a basic execution plan based on the domain information transmitted from the domain determination module, acquires related data and parameters, executes the execution plan, and temporarily stores the basic execution results so that they can be used for comparison in subsequent stages.

[0014] The system may further include a user interaction module that requests a user to select data and parameters related to a query in response to basic execution results of the execution module or additional information needs, receives the user's selection or input, and transmits it to the execution plan generation module, and is configured with a user interface and input processing logic to interact with the user to select additional data and parameters.

[0015] The system may further include an execution plan generation module that generates a new execution plan based on user-selected data and parameters received from the user interaction module, the execution plan including an optimized query structure for querying data from the database, the execution plan generation module being configured with an execution plan generation engine and an optimization algorithm, and that generates the new execution plan in response to the user selection.

[0016] The system may further include a Jason generation and update module that executes the new execution plan transmitted from the execution plan generation module, compares the execution results with previous basic execution results to evaluate performance and result excellence, combines user information, questions, and intentions using a large-scale language model to generate customized Jason meta, and if the comparison results show that the new execution plan produces better results, updates the domain data, parameters, and execution plan to achieve system learning and optimization; and is composed of a Jason generator and a result comparison algorithm and executes the new execution plan to generate and update Jason meta.

[0017] The system may further include an optimal database generation module that generates an adapted database query based on the customized Jason meta generated by the Jason generation and update module, the generated database query being optimized to query required data from the database, and transmitting the generated database query to the database to query final data; the optimal database generation module is configured with a database generation engine and a metadata parser and generates an optimized database query based on the Jason meta to query data from the database.

[0018] A method for generating a domain-based user-customized database through question and intent classification according to another aspect of the present disclosure may include a question receiving and intent understanding step in which a question receiving module receives a natural language question entered by a user and an intent classification module understands the user's intent using user information and a large-scale language model; a question classification and domain determination step in which the question classification module analyzes the question and checks whether the question belongs to a predefined domain through a vector database search, and a domain determination module determines the domain of the question based on the question classification result; a basic execution and user interaction step in which an execution module executes a basic execution plan corresponding to the determined domain to query initial data, and a user interaction module requests the user to select additional data and parameters; an execution plan generation and update step in which an execution plan generation module generates a new execution plan based on the user's selection and updates the execution plan by comparing it with previous execution results; a step in which an optimal database generator module generates an appropriate database query based on the generated Jason meta; and a database query generation and data query step in which the generated database query queries data from a database.

[0019] According to yet another aspect of the present disclosure, there is provided a computer program stored on a computer-readable storage medium, the computer program being stored on a computer-readable storage medium, which, when executed by one or more processors, performs a method for generating a domain-based user-customized database by question and intent classification, the method including: a question receiving and intent understanding step in which a question receiving module receives a natural language question entered by a user, and an intent classification module understands the user's intent by utilizing user information and a large-scale language model; the question classification module analyzes the question and checks whether the question belongs to a predefined domain by searching a vector database; and a domain determination module determines whether the question belongs to a predefined domain based on the question classification result. The process may include a question classification and domain determination step for determining the domain of the query; a basic execution and user interaction step for an execution module to execute a basic execution plan corresponding to the determined domain to query initial data and a user interaction module to request the user to select additional data and parameters; an execution plan generation and update step for an execution plan generation module to generate a new execution plan based on the user's selection and update the execution plan by comparing it with previous execution results; a step in which an optimal database generation module generates an appropriate database query based on the generated Jason meta; and a database query generation and data query step for querying data from a database using the generated database query. [Effects of the Invention]

[0020] The present disclosure has been devised in response to the background art described above, and provides an artificial intelligence system and method for automatically generating user-customized SQL queries based on user questions entered in natural language, thereby enabling efficient querying of data.

[0021] Through this, users can quickly and accurately obtain desired data by simply asking natural language questions without having to understand complex SQL grammar or database structures. Specifically, the effects of the present invention are as follows.

[0022] Using a large-scale language model (LLM), it analyzes users' natural language questions in depth and combines them with user information (department, position, past question records, etc.) to accurately understand the user's intent. Through this, it can accurately determine whether the user's question corresponds to database generation, and only if it does, it can proceed with appropriate processing.

[0023] The system analyzes received questions and checks whether the question belongs to a predefined domain (meta) using a Vector Database (Vector DB) search. It then determines the domain of the question based on the question classification results, allowing it to select data and execution plans that fit the domain, thereby contributing to improving the accuracy and efficiency of data queries.

[0024] The user may be prompted to select additional data and parameters related to the query to generate a new execution plan that reflects the user's requirements and preferences, thereby enabling personalized data queries for the user and improving user satisfaction.

[0025] The generated execution plan is executed, and if it provides better results compared to previous execution results, the data, parameters, and execution plan for that domain are updated, and through this, the system can continuously learn and improve through user interaction, enabling more efficient and accurate data queries over time.

[0026] Finally, appropriate SQL queries are automatically generated based on the generated JSON metadata. In this process, the i-META module is used to automate complex SQL grammar, enabling efficient querying of required data from the database, thereby helping to improve data query speed and system performance.

[0027] By enabling users to query desired data in natural language without complex technical knowledge, the user experience can be improved, the time required to query data can be reduced, business processes can be simplified, and overall business efficiency and productivity can be increased.

[0028] By providing only accessible data based on user information and permissions, it can contribute significantly to maintaining data security and integrity, preventing unauthorized access to sensitive information, and complying with corporate data management policies.

[0029] By achieving these objectives, the present disclosure provides a user-friendly and efficient data query system, and by providing users with customized data quickly and accurately, can contribute to business process innovation and improved productivity.

[0030] Further scope of applicability of the present disclosure will become apparent from the following detailed description. However, it should be understood that the detailed description and specific embodiments, such as preferred embodiments of the present invention, are given by way of example only, since various changes and modifications within the spirit and scope of the invention will be apparent to those skilled in the art. [Brief explanation of the drawings]

[0031] Various aspects are described with reference to the drawings, wherein like reference numerals are used to generally refer to like components. In the following embodiments, for purposes of explanation, numerous specific details are presented to provide a general understanding of one or more aspects. However, it will be apparent that such aspects may be practiced without such specific details. In other instances, well-known structures and devices are shown in block diagram form to facilitate describing one or more aspects. [Figure 1] FIG. 1 is a block diagram illustrating a computing device according to an embodiment of the present disclosure. [Figure 2]FIG. 2 is a block diagram illustrating the configuration of a system for domain-based user-customized database generation through question and intent classification according to an embodiment of the present disclosure. [Figure 3] FIG. 3 is a block diagram of a system for domain-based user-customized database generation through question and intent classification according to the present disclosure. [Figure 4] FIG. 4 is a schematic diagram illustrating an example of the operation of the system for domain-based user-customized database generation through question and intent classification of the present disclosure. [Figure 5] FIG. 5 is a flowchart illustrating the information processing of the system for domain-based user-customized database generation through question and intent classification of the present disclosure. [Figure 6] FIG. 6 is a flow chart illustrating the method for domain-based user-customized database generation through question and intent classification of the present disclosure. [Figure 7] FIG. 7 is a general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION OF THE INVENTION

[0032] Various embodiments are described below with reference to the drawings. Various descriptions are provided herein to facilitate understanding of the present disclosure. However, these embodiments can undoubtedly be practiced without these specific descriptions.

[0033] As used herein, terms such as "component," "module," and "system" refer to computer-related entities, hardware, firmware, software, a combination of software and hardware, or the execution of software. For example, a component may be, but is not limited to, a procedure running on a processor, a processor, an object, a thread of execution, a program, and / or a computer. For example, both an application running on a computing device and the computing device may be a component. One or more components may reside within a processor and / or thread of execution. A component may be localized within one computer. A component may also be distributed across two or more computers. Such components may also execute from various computer-readable media having various data structures stored therein. Components may communicate, for example, through local and / or remote processing, by signals comprising one or more data packets (e.g., data from one component interacting with other components in a local system, a distributed system, or data transmitted over a network such as the Internet to other systems).

[0034] The suffixes "module" and "section" used in the following description are given or mixed together solely for the convenience of writing the specification, and do not have any meanings or roles that are distinct from each other.

[0035] Also, as used herein, the terms "information" and "data" can often be used interchangeably.

[0036] When a component is said to be "coupled" or "connected" to another component, it should be understood that it may be directly coupled or connected to the other component, but that there may be other components in between. On the other hand, when a component is said to be "directly coupled" or "directly connected" to another component, it should be understood that there are no other components in between.

[0037] Additionally, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from the context, "X utilizes A or B" is intended to mean one of the natural inclusive permutations. That is, if X utilizes A, or X utilizes B, or X utilizes both A and B, then "X utilizes A or B" can apply to any of these. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the associated listed items.

[0038] Additionally, the predicate "comprises" and / or modifier "comprises" should be understood to mean the presence of the feature and / or component in question. However, the predicate "comprises" and / or modifier "comprises" should be understood not to exclude the presence or addition of one or more other features, components, and / or groups thereof. Additionally, unless otherwise specified or unless the context makes clear that a singular form is indicated, the singular in the present specification and claims should generally be construed to mean "one or more."

[0039] Hereinafter, the same or similar components will be denoted by the same reference numerals, and repeated explanations will be omitted. Furthermore, when describing the embodiments disclosed herein, if a detailed description of related publicly known technology is deemed to obscure the gist of the embodiments disclosed herein, the detailed description will be omitted. Furthermore, the accompanying drawings are intended to facilitate understanding of the embodiments disclosed herein, and the technical ideas disclosed herein are not limited by the accompanying drawings.

[0040] Furthermore, the term "at least one of A or B" should be interpreted as meaning "when only A is included," "when only B is included," or "when a combination of A and B is included."

[0041] Those skilled in the art should further appreciate that the various illustrative logical blocks, configurations, modules, circuits, means, logic, and algorithm steps described in accordance with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the various illustrative components, blocks, configurations, means, logic, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints of the overall system. Skilled artisans can implement the described functionality in various ways for each particular application. However, such implementation decisions should not be interpreted as departing from the scope of the present disclosure.

[0042] The description of the embodiments set forth herein is provided to enable one of ordinary skill in the art to make and practice the invention. Various modifications to these embodiments will be apparent to those of ordinary skill in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not intended to be limited by the embodiments set forth herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0043] 1 to 7, the present disclosure describes a system and method for generating a domain-based user-customized database through question and intent classification.

[0044] FIG. 1 is a block diagram illustrating a computing device according to an embodiment of the present disclosure.

[0045] 1, the configuration of computing device 100 shown in FIG. 1 is merely a simplified example. For example, computing device 100 may include other components for implementing the computing environment of computing device 100, and only some of the disclosed components may constitute computing device 100.

[0046] Computing device 100 may include a processor 110 , a memory 130 , and a network unit 150 .

[0047] According to an embodiment of the present disclosure, the processor 110 may generally include any type of device capable of processing data and operations of the computing device 100. For example, the processor 110 may refer to a data processing device embedded in hardware having circuits physically structured to perform functions expressed by code or instructions contained in a program. Examples of such data processing devices embedded in hardware include a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc., but the scope of the present invention is not limited thereto.

[0048] The processor 110 may be configured with one or more cores and may include a central processing unit (CPU) of a computing device, and may further include a processor for data analysis and deep learning, such as a general purpose graphics processing unit (GPGPU) or a tensor processing unit (TPU).

[0049] According to one embodiment of the present disclosure, the memory 130 may store any type of information generated or determined by the processor 110 and any type of information received by the network unit 150 .

[0050] According to one embodiment of the present disclosure, the memory 130 may include at least one type of storage medium selected from the group consisting of flash memory, hard disk, micro multimedia card, card-type memory (e.g., SD or XD memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, and optical disk. The computing device 100 may also operate in conjunction with web storage that performs storage functions for the memory 130 over the Internet. The foregoing description of memory is merely exemplary, and the present disclosure is not limited thereto.

[0051] The network unit 150 according to an embodiment of the present disclosure can use various wired communication systems such as a Public Switched Telephone Network (PSTN), x Digital Subscriber Line (xDSL), Rate Adaptive DSL (RADSL), Multi Rate DSL (MDSL), Very High Speed ​​DSL (VDSL), Universal Asymmetric DSL (UADSL), High Bit Rate DSL (HDSL), and a Local Area Network (LAN).

[0052] In addition, the network unit 150 presented in this specification can use various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA (Single Carrier-FDMA) and other systems.

[0053] In the present disclosure, the network unit 150 may be configured regardless of the communication mode, such as wired or wireless, and may be configured as various communication networks such as a short-range communication network (LAN: Local Area Network), a personal communication network (PAN: Personal Area Network), a wide area communication network (WAN: Wide Area Network), etc. In addition, the network may be the well-known World Wide Web (WWW), or may use a wireless transmission technology used for short-range communication, such as infrared data association (IrDA) or Bluetooth (registered trademark).

[0054] The techniques described herein may be used in the networks mentioned above as well as other networks.

[0055] In this specification, the database may be controlled by at least one relational database management system (RDBMS) selected from the group consisting of ORACLE, PostgreSQL, MySQL (registered trademark), SQL Server (MS-SQL), and SQLite. The database may be one in which data is input and output using database statements.

[0056] The application of the present disclosure may include a separate syntax execution module. When the database statement inputs or outputs data to or from the database management system (RDBMS), the syntax execution module may generate a customized statement that conforms to the syntax of the database type. For example, through the present disclosure, a user can conveniently generate, check, and control statements through abstracted mathematical expressions provided in a user interface (UI) provided by the application, regardless of the type of database.

[0057] The application may also be associated with SQL syntax, where the syntax performs one or more of create, read, update, and delete (CRUD). Here, the SQL syntax may be a signal associated with one of commands, insert, update, or delete, and the signal may be input or displayed as the name or abbreviation of the SQL syntax in a spreadsheet cell. For example, the display may be as shown in Table 1 below.

[0058] [Table 1] The user input information may also be used to set columns related to syntax generation or to specify record conditions. For example, SQL syntax can be executed even when the column order or column names between the original data and the output data are changed. The user input information may also display annotations for the output data.

[0059] FIG. 2 is a block diagram of a system for domain-based user-customized database generation through question and intent classification of the present disclosure.

[0060] 2, the block diagram of the system for generating a domain-based user-customized database by question and intent classification of the present disclosure shows the overall structure of the system and method for generating a domain-based user-customized database by question and intent classification of the present disclosure, through which it is possible to see how each module of the system for generating a domain-based user-customized database by question and intent classification of the present disclosure interacts to convert a user's natural language question into a customized database (SQL) query and query and provide appropriate data.

[0061] The system for generating a domain-based user-customized database through question and intent classification of the present disclosure shown in FIG. 2 is an artificial intelligence (AI) system that can generate user-customized SQL queries based on user questions entered in natural language and efficiently query data, and is composed of the following main components and their functions:

[0062] The system for domain-based user-customized database generation through question and intent classification of the present disclosure may be composed of a question receiving module 10, an intent classification module 20, a question classification module 30, a domain determination module 40, an execution module 50, a user interaction module 60, an execution plan generation module 70, a Jason (JSON) generation and update module 80, and an optimal database generation unit (i-META) module 90.

[0063] The question receiving module 10 is a module that receives a question in natural language from a user via a user interface (UI). The question receiving module 10 receives a natural language question entered by a user in real time and transmits it to the first processing stage of the system.

[0064] The intent classification module 20 is a module that classifies the intent of a question using user information. User intent can be classified into SQL generation, API call, daily conversation, etc. The intent classification module 20 uses user information (department, job title, past question records, etc.) and understands the user intent using a large-scale language model (LLM). The intent classification module 20 combines the received question with the user information to accurately classify the user intent. Here, the user intent classified by the intent classification module 20 can be classified into daily conversation, SQL generation (data query, item and condition addition), API call, and instruction word saving.

[0065] In one embodiment, the intent classification module 20 may communicate a question to the next stage, the question classification module, only if the intent is to generate SQL.

[0066] The question classification module 30 is a module that uses natural language processing and a vector database (Vector DB) to determine whether a question belongs to a predefined domain. The question classification module 30 is composed of a natural language processing engine and a vector database (Vector DB). The question classification module 30 analyzes the received question and determines whether the question belongs to a predefined domain (meta). Next, it searches the vector database (DB) to find domain meta information similar to the question. The analysis result is then transmitted to the domain determination module.

[0067] The domain determination module 40 determines the appropriate domain (meta) based on the analyzed question. The domain determination module 40 is composed of a domain mapping table and a determination algorithm. The domain determination module 40 determines the domain (meta) of the question based on the analysis results transmitted from the question classification module. Here, the domain refers to a specific business area or database table, etc., and serves as a basis for appropriate data queries. The domain determination module 40 then transmits the determined domain information to the execution module.

[0068] The execution module 50 is a module that establishes and executes a basic execution plan based on domain determination information. The execution module 50 is composed of a basic execution plan and database connection module. The execution module 50 establishes a basic execution plan based on domain information transmitted from the domain determination module. Then, the execution module 50 acquires related data and parameters and executes the execution plan. The execution module 50 temporarily stores the basic execution results and uses them for comparison in subsequent stages.

[0069] The user interaction module 60 is a module that interacts with the user to select additional data or parameters. The user interaction module 60 is composed of a user interface (UI) and input processing logic. The user interaction module 60 requests the user to select data and parameters related to a question depending on the basic execution results of the execution module or the need for additional information. For example, the user is prompted to select detailed conditions for a specific period, region, product, etc. The user interaction module 60 receives the user's selection or input and transmits it to the execution plan generation module.

[0070] The execution plan generation module 70 is a module that generates a new execution plan in response to user selection. The execution plan generation module 70 is composed of an execution plan generation engine and an optimization algorithm. The execution plan generation module 70 generates a new execution plan based on user-selected data and parameters received from the user interaction module. Here, the execution plan includes an optimized query structure for efficiently querying data from the database. Next, the execution plan generation module 70 transmits the generated execution plan to the Jason (JSON) generation and update module.

[0071] The Jason (JSON) generation and update module 80 executes a new execution plan and generates and updates Jason (JSON) meta (META). The Jason (JSON) generation and update module 80 consists of a Jason (JSON) generator and a result comparison algorithm. The Jason (JSON) generation and update module 80 executes the new execution plan received from the execution plan generation module. The Jason (JSON) generation and update module 80 then compares the execution results with the previous baseline execution results to evaluate performance and the superiority of the results. The Jason (JSON) generation and update module 80 combines user information, the question, and the intent using a large-scale language model (LLM) to generate customized Jason (JSON) meta (META). If the comparison results show that the new execution plan produces better results, the Jason (JSON) generation and update module 80 updates the domain data, parameters, and execution plan, enabling system learning and optimization.

[0072] The optimal database generation unit (i-META) module 90 generates optimized SQL queries based on Jason (JSON) meta (META) and queries data from a database. The optimal database generation unit (i-META) module 90 consists of an SQL generation engine and a metadata parser. The optimal database generation unit (i-META) module 90 generates appropriate SQL queries based on the customized Jason (JSON) meta (META) generated by the Jason (JSON) generation and update module. The generated SQL queries are optimized to efficiently query the required data from the database. The optimal database generation unit (i-META) module 90 transmits the generated SQL queries to the database and queries the final data.

[0073] FIG. 3 is a block diagram of a system for domain-based user-customized database generation through question and intent classification according to the present disclosure.

[0074] Referring to FIG. 3 , a questioner-informed meta generation and database optimization system according to one embodiment of the present disclosure may be a data service system based on natural language processing (NLP) technology that can utilize a metalanguage to process natural language questions and generate and optimize database (SQL) to derive appropriate results from the database.

[0075] In one embodiment, the presently disclosed system for generating meta data based on user information and optimizing databases can convert natural language queries submitted by users into a metalanguage for processing, which can analyze the user queries, automatically generate and execute appropriate SQL queries, and provide the resulting data to the users in natural language. This system may also include morphological analysis and similar question management functions for processing natural language queries.

[0076] The disclosed meta generation and database optimization system using questioner information can be composed of a user (USER), a transformation matrix (G-MATRIX), a natural language processing module (NLP), and an optimal database generation unit (i-META).

[0077] The user enters a question into the system in natural language.

[0078] The conversion matrix (G-MATRIX) converts natural language into metalanguage and transmits the query content.

[0079] The natural language processing module (NLP) receives the metalinguistic question, analyzes the natural language question, and provides a metalinguistic response accordingly.

[0080] The optimal database generation unit (i-META) receives the metalanguage command, generates an optimal SQL query, prepares a query result response from the resulting data SET result, and sends the result response to the user (USER).

[0081] In the disclosed system for generating meta data based on questioner information and optimizing databases, when a user inputs a question in natural language, the system extracts main nouns and verbs through morphological analysis and then processes synonyms. The extracted information is converted into a metalanguage, and an SQL query is automatically generated based on this. The generated SQL query is executed in a database to derive results, which are then converted into natural language via the metalanguage and provided to the user. The metalanguage plays an important role in the processes of sending questions, commands, and receiving results, and the user ultimately receives the results processed in natural language.

[0082] For example, when a user inputs a natural language query such as "Show me the current sales status of the sales department this year," the system can convert this into meta information such as "x = this year," "y = sales department," and "sales = sales amount." An SQL query can be generated based on this information, and the sales status desired by the user can ultimately be provided.

[0083] The presently disclosed meta generation and database optimization system based on questioner information may include a similar question management function, and can detect questions similar to previously used queries and process data more efficiently based on the detected queries. It also utilizes database (SQL) optimization and data caching technologies to improve query performance and shorten system response time. Furthermore, meta-language-based query processing allows users to easily obtain desired information without having to create database (SQL) queries themselves. Furthermore, processing database queries based on natural language provides a system that allows users to easily query data without having to create SQL queries, thereby improving data accessibility and making it easy for non-experts to use.

[0084] FIG. 4 is a schematic diagram illustrating an example of the operation of the system for domain-based user-customized database generation through question and intent classification of the present disclosure.

[0085] 4, the presently disclosed meta generation and database optimization system based on questioner information analyzes user questions expressed in natural language, generates SQL queries based on the queries, queries data from a database, and provides the results in a form that can be easily understood by the user. This system is primarily used for data queries such as sales management in a specific business division, such as the electric power division of a company.

[0086] In one embodiment, the questioner-informed meta generation and database optimization system of the present disclosure may include the following components:

[0087] The user asks in natural language about the current sales status of a particular business unit, for example, "How much did we sell this year?" or "What are the sales figures for the Electrical Division in 2023?"

[0088] The transformation matrix (G-MATRIX) is a module that analyzes the user's natural language questions and generates SQL queries. For example, it processes a query such as "Sales of the Electrical Division of S Company from January 1, 2023 to today."

[0089] The optimal database generator (i-META) converts natural language queries into a metalanguage and optimizes the database (SQL) based on this metalanguage.

[0090] The natural language processing module (NLP) analyzes the user's natural language question, extracts the necessary data, and converts it into a metalanguage.

[0091] In one embodiment, the questioner-informed meta generation and database optimization system of the present disclosure can operate as follows.

[0092] When a user types a question in natural language, such as "What were the sales figures for the Electrical Division in 2023?", the NLP module analyzes the question and extracts important time ranges and departments.

[0093] The transformation matrix (G-MATRIX) module generates a specific SQL query based on the analyzed data: "Sales of S Company's Electrical Division from January 1, 2023 to today."

[0094] The generated SQL query is transmitted to the database via the optimal database generation unit (i-META) and executed.

[0095] The execution results are organized in a data format such as Table A and provided to the user in the form of Template B.

[0096] In one embodiment, the disclosed questioner-informed meta generation and database optimization system can use natural language processing (NLP) algorithms to efficiently manage sales data for a specific business division, such as a company's electrical division, and provide data services that convert users' natural language questions into database (SQL) queries and derive relevant information from the database.

[0097] In one embodiment, the disclosed questioner-informed meta generation and database optimization system can provide an automated system that allows users to request data in natural language and then analyzes and converts it into precise SQL queries.

[0098] In one embodiment, the questioner-informed meta generation and database optimization system of the present disclosure may include a module optimized to generate SQL queries and query data for a specific department or time period.

[0099] In one embodiment, the result data of the questioner-informed meta generation and database optimization system of the present disclosure can be provided in a user-customized format, and visual reports can also be generated via templates.

[0100] In one embodiment, the questioner-informed meta generation and database optimization system of the present disclosure can operate as follows.

[0101] When a user inputs a natural language question such as "Show me the sales of the electric division this year," the system converts the question into "Sales of S Company's electric division from January 1, 2023 to today," and then executes an SQL query to derive the results. The results are provided in the form of Table A and output to the user as visualized data using Template B.

[0102] In one embodiment, the disclosed meta generation and database optimization system based on query information provides a convenient system that allows users to query necessary data through natural language queries without having to understand complex query languages ​​such as SQL, allowing non-experts to easily access data and efficiently create sales management and reports.

[0103] FIG. 5 is a flowchart illustrating the information processing of the system for domain-based user-customized database generation through question and intent classification of the present disclosure.

[0104] 5, a questioner-informed meta generation and database optimization system according to an embodiment of the present disclosure may be a data service system that combines natural language processing (NLP) technology and large-scale language models (LLMs) to analyze a user's natural language question and provide an optimal response based on metadata. The questioner-informed meta generation and database optimization system of the present disclosure can then utilize the learned metadata to generate SQL queries and provide results in real time.

[0105] In one embodiment, the disclosed system and method for questioner-informed meta generation and database optimization may be a system that receives a user's natural language question, learns metadata through a large-scale language model, and automatically generates SQL queries based on the learned metadata to query data from a database, where the meta information is managed in an embedded vector store and the system provides responses in real time through continuous query processing and caching.

[0106] In one embodiment, the disclosed questioner-informed meta generation and database optimization system may be composed of a user, a result platform (AUD7 Platform), a transformation matrix (G-MATRIX), an optimal database generator (i-META), and a large-scale language model (LLM).

[0107] A user inputs a natural language question, such as "What are the sales figures for the Electric Power Division in 2023?"

[0108] The result platform (AUD7 Platform) transmits the user's natural language query to the transformation matrix (G-MATRIX) and then returns the results to the user.

[0109] The transformation matrix (G-MATRIX) processes the user's natural language query to generate metadata and converts the natural language query into an embedded vector form using a large-scale language model (LLM).

[0110] The large-scale language model (LLM) converts users' natural language questions into meta-information, transmits the metadata to the optimal database generator (i-META), and the optimal database generator (i-META) can use the learned data in the process of generating and optimizing SQL queries.

[0111] The optimal database generation unit (i-META) constructs templates based on the metadata generated by the transformation matrix (G-MATRIX) and optimizes SQL queries.

[0112] The disclosed system for generating a domain-based user-customized database through question and intent classification attempts to solve the conventional problems by utilizing large-scale language models (LLMs) to deeply analyze user questions and combine user information to accurately understand user intent.

[0113] The disclosed system for generating a domain-based user-customized database through question and intent classification solves this problem by checking whether a question belongs to a predefined domain (meta) through a Vector DB search in the question classification module, and determining the exact domain through a domain determination module.

[0114] The disclosed system for domain-based user-customized database generation through question and intent classification enables user-customized data queries by requesting additional data and parameter selections related to the query from the user via a user interaction module, and generating a new execution plan based on the user's selections in an execution plan generation module.

[0115] The disclosed system for generating a domain-based, user-customized database through question and intent classification executes the generated execution plan, and if it provides better results compared to previous execution results, updates the domain's data, parameters, and execution plan. Through this, the system continuously learns and improves through interaction with the user, enabling more efficient and accurate data queries over time.

[0116] The disclosed system for generating a domain-based user-customized database through question and intent classification automatically generates appropriate SQL queries through an optimal database generation unit (i-META) module based on Jason (JSON) metadata generated by a Jason (JSON) generation and update module, so that even users who do not have knowledge of complex SQL grammar or database structures can query desired data.

[0117] The disclosed system for domain-based user-customized database generation through question and intent classification increases the efficiency of data queries and improves user experience by combining user information and intent to generate personalized SQL queries, which contributes to reducing the time required for data queries, simplifying business processes, and increasing overall business efficiency.

[0118] Enforce user authorization and access control to prevent unauthorized access to sensitive data and maintain data security and integrity. This is achieved through access control based on user information and questions.

[0119] Therefore, the disclosed system for generating a domain-based user-customized database through question and intent classification combines natural language processing technology and user information management technology to provide a user-friendly, yet efficient and secure data query system, thereby overcoming the limitations of existing systems and contributing to improved business productivity.

[0120] FIG. 6 is a flowchart of the method for domain-based user-customized database generation through question and intent classification of the present disclosure.

[0121] Referring to FIG. 6, the overall operational flow of the method for domain-based user-customized database generation through question and intent classification of the present disclosure is as follows.

[0122] Step S1000 is the question receiving and intent understanding step. The question receiving module receives a natural language question entered by a user (S1100). The intent classification module understands the user's intent using user information and a large-scale language model (LLM) (S1200). Only if the intent is to generate SQL, the question is transmitted to the question classification module (S1300).

[0123] Step S2000 is a question classification and domain determination step. The question classification module analyzes the question and checks whether the question belongs to a predefined domain (meta) by searching a vector database (DB) (S2100). The domain determination module determines the domain (meta) of the question based on the question classification result (S2200). The determined domain information is transmitted to the execution module (S2300).

[0124] Step S3000 is the basic execution and user interaction step. The execution module executes the basic execution plan corresponding to the determined domain and queries for initial data (S3100). The user interaction module requests the user to select additional data and parameters (S3200). For example, additional conditions such as a specific time period, region, or product can be selected. The user's selection is transmitted to the execution plan generation module (S3300).

[0125] Step S4000 is the execution plan generation and update step. The execution plan generation module generates a new execution plan based on the user's selection (S4100). The Jason (JSON) generation and update module executes the generated execution plan and compares it with the previous execution results (S4200). A large-scale language model (LLM) is used to combine user information, the question, and the intent to generate customized Jason (JSON) meta (S4300). If the comparison results in a better result for the new execution plan, the domain data, parameters, and execution plan are updated (S4400).

[0126] Step S5000 is the database query generation and data query step. The optimal database generation module (i-META) generates an appropriate SQL query based on the generated JSON meta (S5100). The generated SQL query queries data from the database (S5200). The queried data is provided to the user in an appropriate format (S5300).

[0127] The characteristic functions of the method for domain-based user-customized database generation through question and intent classification of the present disclosure are as follows.

[0128] The disclosed method for domain-based user-customized database generation through question and intent classification enables user-customized data querying. By combining user information with questions and intents to generate personalized SQL queries, data can be efficiently queried according to each user's role and needs.

[0129] The disclosed method for generating a domain-based user-customized database through question and intent classification enables continuous improvement of the execution plan. The execution plan is continuously updated through user interaction and result comparison, improving the system's performance and accuracy.

[0130] The disclosed method for generating a domain-based user-customized database through question and intent classification can utilize large-scale language models (LLMs) to improve the accuracy of natural language question comprehension and intent understanding, enabling even complex questions to be accurately processed.

[0131] The disclosed method for domain-based user-customized database generation through question and intent classification can perform domain-based processing by accurately identifying database tables and fields that match the query through question classification and domain determination using a vector database (DB).

[0132] The disclosed method for domain-based user-customized database generation through question and intent classification can perform automated SQL generation. Complex SQL queries are automatically generated through the Jason (JSON) Meta (META) and i-META (optimal database generator) modules, improving the efficiency and accuracy of database queries.

[0133] An example scenario according to one embodiment of the method for domain-based user-customized database generation through question and intent classification of the present disclosure is as follows.

[0134] 1. Question input: The user inputs the question "Tell me about the sales trends of our customers in the last quarter."

[0135] 2. Intention Understanding: The intention classification module classifies the user's intention through SQL generation and transmits the question to the question classification module.

[0136] 3. Question classification and domain (meta) determination: · The question classification module verifies that the question belongs to the "Sales Data" domain (meta). The domain determination module determines the domain (meta) based on this.

[0137] 4. Basic Execution: The execution module executes the basic execution plan and queries the overall sales data.

[0138] 5. User Interaction: The user interaction module asks the user to select additional data (e.g., period, department, etc.). The user selects "Leave Quarter" and "Our Customers."

[0139] 6. Execution plan generation and update: The execution plan generation module generates a new execution plan that reflects the user's selection. The Jason (JSON) Generate and Update module runs a new execution plan and compares it with the previous results to get more accurate results. If the results are better, update the execution plan for that domain.

[0140] 7. SQL query generation and data interrogation: The optimal database generation module (i-META) generates the final SQL query. · Query data from the database and provide the results to the user.

[0141] The configuration and operation of the system and method for generating a domain-based user-customized database through question and intent classification disclosed herein combines natural language processing technology and user information management technology to realize a user-friendly and efficient data query system.

[0142] Through this, users can quickly and accurately query desired data in natural language without having to understand complex SQL grammar or database structures, and the system continuously learns and improves through user interaction.

[0143] The disclosed system and method for generating a domain-based user-customized database through question and intent classification provides an AI system and method that can automatically generate user-customized SQL queries based on user questions entered in natural language and efficiently query data, thereby achieving the following effects:

[0144] 1.Improved user convenience Natural language query support: Users can query desired data in natural language without knowledge of complex SQL grammar or database structure. · Improved user interaction: Requesting additional data and parameter selection from users improves the user experience and provides more accurate information.

[0145] 2. Personalized data provision Utilizing user information: By combining user information (department, past question records, etc.) with questions and intent to generate personalized SQL queries, we provide optimal data based on each user's role and needs. Customized Execution Plan Generation: Enables personalized data queries through execution plans that reflect user selections and preferences.

[0146] 3. Improved efficiency and accuracy of data queries Utilizing Large-Scale Language Models (LLM): Large-scale language models (LLM) improve the accuracy of natural language question understanding and intent understanding, enabling even complex questions to be handled accurately. Domain-based processing: Accurately identify appropriate database tables and fields through question classification and domain determination using a vector database (Vector DB), improving the efficiency and accuracy of data queries.

[0147] 4. Continuous improvement of the action plan · Continuous learning and updating: Continuously update the execution plan through user interaction and execution result comparison to improve system performance and accuracy. - Adaptive system implementation: The system automatically optimizes itself by flexibly responding to changing user demands and data environments.

[0148] 5. Increased operational efficiency and productivity Reduced data access time: Reduce the time it takes to query data, streamlining business processes and speeding up decision-making. · Improved user satisfaction: Users can be provided with the information they want quickly and accurately, which increases their job satisfaction.

[0149] 6. Strengthening data security and access control · Permission-based access control: Prevent unauthorized access to sensitive data through user permissions and access control, maintaining data security and integrity. · Data management policy compliance: Comply with corporate data management policies through access control based on user information and questions.

[0150] 7. Improved user experience · More intuitive interface: Improved usability and a reduced learning curve through natural language questions and user interaction. - Additional function support: Provides additional functions such as auto-complete and recommended questions to enhance user convenience.

[0151] Therefore, the disclosed system and method for generating a domain-based user-customized database through question and intent classification combines natural language processing technology and user information management technology to realize a user-friendly and efficient data query system, thereby increasing the accessibility and efficiency of data utilization and contributing to improved business productivity and strengthened data security.

[0152] FIG. 7 is a general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0153] Referring to FIG. 7, the computer program, when executed by one or more processors, can perform actions for user authorization.

[0154] Also disclosed in accordance with one embodiment of the present disclosure is a computer-readable medium having a data structure stored thereon.

[0155] A data structure can refer to the organization, management, and storage of data that allows efficient access and modification. A data structure can refer to the organization of data to solve a specific problem (e.g., data retrieval, data storage, data modification) in the shortest possible time. A data structure can also be defined as a physical or logical relationship between data elements designed to support a specific data processing function. Logical relationships between data elements may include user-defined interlinking relationships between data elements. Physical relationships between data elements may include actual relationships between data elements physically stored in a computer-readable storage medium (e.g., a permanent storage device). Specifically, a data structure may include a collection of data, relationships between data, and functions or instructions that can be applied to the data. Effectively designed data structures enable computing devices to perform operations while minimizing the use of computing device resources. Specifically, effectively designed data structures enable computing devices to increase the efficiency of operations, retrieval, ingestion, deletion, comparison, exchange, and search.

[0156] Data structures can be classified into linear and non-linear data structures depending on their form. A linear data structure may be a structure in which only one piece of data is linked after another. Linear data structures may include lists, stacks, queues, and deques. A list may refer to a series of data sets that are internally ordered. A list may include a linked list. A linked list may be a data structure in which data is linked in a linear fashion, with each piece of data having a pointer. In a linked list, the pointer may contain information about the connection to the next or previous piece of data. A linked list may be expressed as a singly linked list, a doubly linked list, or a circularly linked list depending on its form. A stack may be a data array structure in which access to data is restricted. A stack may be a linear data structure in which data can be manipulated (e.g., inserted or deleted) only at one end of the data structure. Data stored in a stack may be a last-in, first-out (LIFO) data structure. A queue is a data structure that has limited access to data and, unlike a stack, may be a first-in, first-out (FIFO) data structure. A deck may be a data structure that allows data to be processed at both ends of the data structure.

[0157] The nonlinear data structure may be a structure in which multiple pieces of data are concatenated after one piece of data. The nonlinear data structure may include a graph data structure. The graph data structure may be defined by vertices and edges, and an edge may include a line connecting two different vertices. The graph data structure may include a tree data structure. The tree data structure may be a data structure in which there is one path connecting two different vertices among the multiple vertices included in the tree. In other words, the graph data structure may be a data structure that does not form a loop.

[0158] The data structure may include data to be input to a neural network. The data structure including the data to be input to a neural network may be stored on a computer-readable medium. The data to be input to a neural network may include training data input during a neural network training process and / or input data to a neural network after training has been completed. The data to be input to a neural network may include data that has undergone pre-processing and / or data to be pre-processed. Pre-processing may include a data processing process for inputting data to a neural network. Therefore, the data structure may include data to be pre-processed and data generated by pre-processing. The above-described data structures are merely examples, and the present disclosure is not limited thereto.

[0159] The data structure may include neural network weights. In this specification, the terms "weight" and "parameter" may be used interchangeably. The data structure including the neural network weights may be stored on a computer-readable medium. The neural network may include multiple weights. The weights may be variable and may be adjusted by a user or algorithm to enable the neural network to perform a desired function. For example, if one or more input nodes are interconnected to an output node by respective links, the output node may determine a data value to be output from the output node based on the values ​​input to the input nodes connected to the output node and the weights assigned to the links corresponding to each input node. The above-described data structure is merely exemplary, and the present disclosure is not limited thereto.

[0160] While the present disclosure has been described above as generally capable of being embodied in computing devices, those skilled in the art will appreciate that the present disclosure can also be embodied in combination with computer-executable instructions and / or other program modules that can be executed on one or more computers and / or as a combination of hardware and software.

[0161] Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Those skilled in the art will also appreciate that the methods of the present disclosure can be practiced with other computer system configurations, including single-processor or multi-processor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like, any of which can operate in conjunction with one or more associated devices.

[0162] Moreover, the embodiments described in this disclosure may be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0163] A computer typically includes a variety of computer-readable media. Any medium accessible by a computer can be computer-readable, including volatile and non-volatile media, transitory and non-transitory media, and portable and non-portable media. By way of example, and not limitation, computer-readable media can include computer-readable storage media and computer-readable transmission media. Computer-readable storage media include volatile and non-volatile media, transitory and non-transitory media, portable and non-portable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules, or other data. Computer-readable storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage devices, magnetic cassettes, magnetic tape, magnetic disk storage devices or other magnetic storage devices, or any other medium that can be accessed by a computer and used to store information.

[0164] Computer-readable transmission media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and includes all information delivery media. The term modulated data signal means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, computer-readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above media should also be included within the scope of computer-readable transmission media.

[0165] An exemplary environment 1100 embodying various aspects of the present disclosure is shown including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. The system bus 1108 couples system components, including but not limited to the system memory 1106, to the processing unit 1104. The processing unit 1104 may be any of a variety of commercially available processors. Dual processors and other multi-processor architectures may also be utilized as the processing unit 1104.

[0166] The system bus 1108 may be any of several types of bus structures that may be further interconnected: a memory bus, a peripheral bus, and a local bus using any of a variety of commercially available bus architectures. The system memory 1106 includes read-only memory (ROM) 1110 and random access memory (RAM) 1112. The basic input / output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, or EEPROM, and contains the basic routines that help transfer information between components within the computer 1102, such as during start-up. The RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

[0167] The computer 1102 also includes an internal hard disk drive (HDD) 1114 (e.g., EIDE, SATA)—which may be configured for external use in a suitable chassis (not shown)—a magnetic floppy disk drive (FDD) 1116 (e.g., for reading from and writing to a removable diskette 1118), and an optical disk drive 1120 (e.g., for reading a CD-ROM disk 1122 or reading from and writing to other high-capacity optical media such as DVDs). The hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 may be coupled to the system bus 1108 by a hard disk drive interface 1124, a magnetic disk drive interface 1126, and an optical drive interface 1128, respectively. The interface 1124 for external drive implementations includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

[0168] These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, etc. In the case of computer 1102, the drives and media accommodate storing any data in a suitable digital format. While the foregoing description of computer-readable media refers to hard disk drives, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will recognize that other types of computer-readable media, such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc., may also be used in the exemplary operating environment, and that any such media may contain computer-executable instructions for performing the methods of the present disclosure.

[0169] A number of program modules, including an operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136, may be stored on the drives and in RAM 1112. All or portions of the operating system, applications, modules, and / or data may be cached in RAM 1112. It will be apparent that the present disclosure may be embodied in various commercially available operating systems or combinations of operating systems.

[0170] A user can enter commands and information into the computer 1102 through one or more wired or wireless input devices, such as a keyboard 1138 and a pointing device, such as a mouse 1140. Other input devices (not shown) may include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, or the like. These and other input devices are often coupled to the processing unit 1104 through an input device interface 1142 that is coupled to the system bus 1108, but may also be coupled by a variety of interfaces, such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, or the like.

[0171] The term "user input" in this disclosure may refer to any form of user input related to a user request made within a user interface (or within a web page). For example, the user input may include a user input for moving a pointer object. As another example, the user input may include a user input for selecting a specific object on the user interface. For example, a user input for an object (e.g., a module, a tap, etc.) may be made by touching or clicking the object. When a user input related to a selection is received, a new object may be displayed on the user interface or web page in response to the input, or the attributes of the object may be changed and displayed.

[0172] As yet another example, the user input may include information such as language, letters, numbers, and symbols input by various input means. The user input is not limited to the above examples, and various forms of user actions are possible, such as mouse cursor control, mouse wheel scrolling, keyboard directional keys, mouse click, and touch.

[0173] A monitor 1144 or other type of display device is also coupled to the system bus 1108 via an interface, such as a video adapter 1146. In addition to the monitor 1144, a computer typically includes other peripheral output devices (not shown), such as speakers, printers, and the like. For example, the monitor 1144 or other type of display device may include at least one of a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), a flexible display, a 3D display, and an e-ink display. The display also outputs (displays) data processed by the processor 110.

[0174] The computer 1102 can operate in a networked environment using logical connections to one or more remote computers, such as a remote computer 1148, via wired and / or wireless communications. The remote computer 1148 may be a workstation, computing device computer, router, personal computer, handheld computer, microprocessor-based entertainment appliance, peer device or other conventional network node and typically includes many or all of the components described for the computer 1102, although for simplicity, only a memory storage device 1150 is shown. The logical connections shown include wired or wireless connections to a local area network (LAN) 1152 and / or larger networks, e.g., a wide area network (WAN) 1154. Such LAN and WAN networking environments are commonplace in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which may be connected to a worldwide computer network, e.g., the Internet.

[0175] When used in a LAN networking environment, the computer 1102 is coupled to the local network 1152 via a wired and / or wireless communication network interface or adapter 1156. The adapter 1156 can facilitate wired or wireless communication to the LAN 1152, which may also include a wireless access point installed for communicating with the wireless adapter 1156. When used in a WAN networking environment, the computer 1102 may include a modem 1158 or other means of establishing communications over the WAN 1154, such as coupled to a communications computing device on the WAN 1154 or via the Internet. The modem 1158, which may be internal or external and a wired or wireless device, is coupled to the system bus 1108 via the serial port interface 1142. In a networked environment, program modules described for the computer 1102, or portions thereof, may be stored in the remote memory / storage device 1150. It will be appreciated that the network connections shown are exemplary and other means of establishing a communications link between the computers may be used.

[0176] The computer 1102 operates to communicate with any wireless device or entity that is located and operating in wireless communication, such as a printer, a scanner, a desktop and / or handheld computer, a portable data assistant (PDA), a communication satellite, any equipment or location associated with a radio-detectable tag, and a telephone. This includes at least Wi-Fi® and Bluetooth® wireless technologies. Thus, communication may be in a predefined structure, such as a traditional network, or simply ad hoc communication between at least two devices.

[0177] Wi-Fi® (Wireless Fidelity) enables connections to the Internet and other networks without wires. Wi-Fi® is a wireless technology similar to cell phones, allowing such devices, e.g., computers, to send and receive data indoors or outdoors, i.e., from anywhere within the coverage area of ​​a base station. Wi-Fi® networks use IEEE 802.11 (a, b, g, etc.) radio technologies to provide secure, reliable, and high-speed wireless connections. Wi-Fi® can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi® networks can operate in the unlicensed 2.4 and 5 GHz radio bands, e.g., at 11 Mbps (802.11a) or 54 Mbps (802.11b) data rates, or with products that include both bands (dual band).

[0178] Those skilled in the art will appreciate that information and signals may be represented using any of a variety of different technologies and techniques. For example, the data, instructions, commands, information, signals, bits, symbols, and chips referred to in the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0179] The computer 1102 may also be embodied as a user terminal. Therefore, the method according to an embodiment of the present disclosure may be applied without limitation to a terminal as hardware capable of installing software. The user terminal described in the present disclosure may include a mobile phone, a smartphone, a laptop computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a navigation system, a slate PC, a tablet PC, an ultrabook, a wearable device (e.g., a smartwatch, smart glass, or a head-mounted display (HMD)), and the like. The user terminal may include, but is not limited to, a device capable of inputting and outputting data by a user, a device capable of displaying data to a user, and a device capable of wired or wireless communication. For example, the computing device 100 may be a desktop computer, a laptop computer, a tablet PC, a portable terminal, or the like.

[0180] Those skilled in the art will appreciate that the various illustrative logic blocks, modules, processors, means, circuits, and algorithm steps described in the description of the embodiments disclosed herein can be implemented with electronic hardware, various forms of program or design code (referred to herein as "software" for ease of description), or a combination of all of these. To clearly illustrate this interoperability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been generally described above by focusing on their functionality. Whether such functionality is implemented as hardware or software is determined by the particular application and design constraints imposed on the overall system. Those skilled in the art will appreciate that the described functionality can be implemented in various ways for each particular application, and such implementation decisions should not be interpreted as a departure from the scope of the present disclosure.

[0181] The various embodiments described herein may be implemented by a method, apparatus, or article of manufacture using standard programming and / or engineering techniques. The term "article of manufacture" includes a computer program, carrier, or media accessible by any computer-readable device. For example, computer-readable storage media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Additionally, the various storage media described herein may include one or more devices and / or other machine-readable media for storing information.

[0182] It should be understood that the specific order or hierarchy of the process steps presented herein is an example of an exemplary approach. Based on design priorities, it should be understood that the specific order or hierarchy of the process steps can be rearranged within the scope of this disclosure. The accompanying method claims provide sample orders and elements of the various steps, but are not meant to be limited to the specific order or hierarchy presented.

[0183] The description of the embodiments set forth herein is provided to enable any person skilled in the art to use or practice the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not intended to be limited by the embodiments set forth herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein. [Explanation of symbols]

[0184] 10 Question Receiving Module 20 Intent Classification Module 30 Question Classification Module 40 Domain Determination Module 50 Execution Modules 60 User Interaction Module 70 Execution plan generation module 80 Jason Generation and Update Modules 90 Optimal database generation module

Claims

1. a question receiving module for receiving a question in natural language via a user interface; An intent classification module that utilizes user information and uses a large-scale language model to understand and classify the intent of the user's question; A question classification module that uses a natural language processing engine and a vector database to check whether a question belongs to a predefined domain; a domain decision module, consisting of a domain mapping table and a decision algorithm, for determining the appropriate domain based on the analyzed question; and An execution module, which is composed of a basic execution plan and a database connection module, and establishes and executes a basic execution plan based on domain determination information; A system for domain-based user-customized database generation through question and intent classification.

2. The intent classification module Combine the received question with user information to classify the user's intent, 2. The system for generating a domain-based user-customized database through question and intent classification according to claim 1, wherein the user intent is comprised of at least one of daily conversation, SQL generation, API call, and directive word storage.

3. The execution module is Establish a basic action plan based on the domain information transmitted from the domain determination module, Retrieve the relevant data and parameters and execute the execution plan, 2. The system for generating a domain-based user-customized database by question and intent classification according to claim 1, wherein the basic execution results are temporarily saved and utilized for comparison in a subsequent stage.

4. The system comprises: Requesting the user to select data and parameters related to the query depending on the basic execution results of the execution module and the need for additional information; receiving and communicating user selections or inputs to the execution plan generation module; 10. The system for domain-based user-customized database generation through question and intent classification of claim 1, further comprising: a user interaction module comprising a user interface and input processing logic for interacting with a user to select additional data or parameters.

5. The system comprises: generating a new execution plan based on the user-selected data and parameters received from the user interaction module; The execution plan includes an optimized query structure for querying data from the database; 2. The system for domain-based user-customized database generation through question and intent classification of claim 1, further comprising: an execution plan generation module, comprising an execution plan generation engine and an optimization algorithm, for generating a new execution plan in response to user selection.

6. The system comprises: Execute the new execution plan transmitted from the execution plan generation module; Compare the results of the run with those of the previous baseline run to evaluate the performance and the superiority of the results; It uses a large-scale language model to combine user information, questions, and intent to generate customized Jason Meta. If the comparison results in a better performance from the new execution plan, update the data, parameters, and execution plan for that domain to achieve system learning and optimization; 2. The system for domain-based user-customized database generation through question and intent classification of claim 1, further comprising: a Jason generation and update module, comprising a Jason generator and result comparison algorithm, that executes new execution plans to generate and update Jason meta.

7. The system comprises: Generate appropriate database queries based on the customized Jason meta generated by the Jason Generate and Update module; The generated database queries are optimized to query the required data from the database. Communicating the generated database query to the database to query the final data; 2. The system for domain-based user-customized database generation through question and intent classification of claim 1, further comprising: an optimal database generator module, comprising a database generation engine and a metadata parser, for generating optimized database queries based on Jason Meta and querying data from the database.

8. a question receiving and intent understanding step in which a question receiving module receives a natural language question input by a user, and an intent classification module understands the user's intent by utilizing user information and a large-scale language model; a question classification and domain determination step in which a question classification module analyzes the question and checks whether the question belongs to a predefined domain through a vector database search, and a domain determination module determines the domain of the question based on the question classification result; a basic execution and user interaction phase in which the execution module executes the basic execution plan corresponding to the determined domain and queries for initial data, and the user interaction module requests the user to select additional data and parameters; an execution plan generation and update phase in which the execution plan generation module generates a new execution plan based on the user's selection and updates the execution plan by comparing it with the previous execution results; The optimal database generator module generates an appropriate database query based on the generated Jason meta; and A method for domain-based user-customized database generation through question and intent classification, comprising: a database query generation and data query stage; wherein the generated database query queries data from a database.

9. 1. A computer program stored on a computer-readable storage medium, the computer program, when executed by one or more processors, performing a method for domain-based user-customized database generation through question and intent classification, the method comprising: a question receiving and intent understanding step in which a question receiving module receives a natural language question input by a user, and an intent classification module understands the user's intent by utilizing user information and a large-scale language model; a question classification and domain determination step in which a question classification module analyzes the question and checks whether the question belongs to a predefined domain through a vector database search, and a domain determination module determines the domain of the question based on the question classification result; a basic execution and user interaction phase in which the execution module executes the basic execution plan corresponding to the determined domain and queries for initial data, and the user interaction module requests the user to select additional data and parameters; an execution plan generation and update phase in which the execution plan generation module generates a new execution plan based on the user's selection and updates the execution plan by comparing it with the previous execution results; The optimal database generator module generates an appropriate database query based on the generated Jason meta; and A computer program stored on a computer-readable storage medium, the computer program comprising: a database query generation and data querying step; wherein the generated database query queries data from a database.

Images