Apparatus, system and method for providing query-based data services

Abstract

The database comparison system based on question classification and questioner classification of the present disclosure includes: a question receiving and classification module that receives and analyzes natural language questions entered by users and classifies the question type; a user profiling and questioner classification module that generates a user-customized query based on the user's profile and past interaction records; a metadata search and large-scale language model linkage module that searches a vector database for metadata matching the question after the question is classified; a database comparison and generation module that automatically generates an optimized database query based on the metalanguage generated by the large-scale language model linkage module; and a data processing and output module that transmits the generated database query to a database to retrieve the results, and provides the data processed by the data processing module with a response converted in a format suitable for the user.

Description

[Technical Field]

[0001] The present disclosure relates to the field of natural language processing (NLP), and to an apparatus, system, and method for providing a question-based data service that optimizes the database query process through question classification, user profiling, and optimized database query generation utilizing large-scale language models (LLMs). In particular, the present disclosure provides an apparatus, system, and method for providing a question-based data service that uses a group of questioners, extracts metadata from a vector database to provide personalized responses, and ensures efficient data search. [Background technology]

[0002] Modern enterprises accumulate vast amounts of data, and effectively managing and analyzing this data has emerged as a core element of enterprise competitiveness. Many database systems present the same metadata structure to all users.

[0003] Patent Document 1 (Korean Patent Registration No. 10-2094934) discloses a natural language question answering system and method that analyzes sentences and paragraphs of unstructured documents, classifies and indexes the documents by meaning, and provides answers to query language.

[0004] These conventional natural language question-answering systems and methods primarily focus on analyzing a user's natural language question and converting it into a database query language. However, most conventional natural language question-answering systems do not reflect a user's individual profile or past interactions, and instead provide the same results to all users in response to the same question, making it difficult to generate user-customized queries and obtaining optimized results. Furthermore, the process of simply converting a natural language question into a structured query language may not adequately reflect complex context and meaning. For example, in the case of polysemous or compound questions, the system may not correctly parse them, resulting in the generation of inaccurate queries. Furthermore, conventional natural language question-answering systems are primarily useful for simple questions and basic data searches, and are inadequate for handling complex data searches or advanced (advanced) questions that integrate multiple data sources. Furthermore, they have limitations in handling conditions that are not clearly defined by the user or ambiguous questions.

[0005] Recently, there has been an increasing number of attempts to utilize artificial intelligence and machine learning technologies to advance database management and data analysis. Natural language processing (NLP)-based question-answering systems have been developed that use these technologies to understand questions entered by users in natural language and provide relevant data. However, these systems often fail to adequately reflect user intent and domain information. To address this issue, recommendation system functions have been introduced that analyze user behavior patterns and recommend necessary information, but these systems have primarily focused on content consumption. Furthermore, while automated tuning tools exist to improve database query performance, they are far from providing user-customized data. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Korean Patent Registration No. 10-2094934 [Patent Document 2] Korean Patent Registration No. 10-1987915 Summary of the Invention [Problem to be solved by the invention]

[0007] The present disclosure has been devised in response to the background art discussed above, and provides an apparatus, system, and method for providing query-based data services.

[0008] In other words, the disclosed database comparison system and method based on question classification and questioner classification aims to develop a transformation matrix system for realizing user-customized data search. This aims to provide greater accuracy and efficiency in user queries and improve database query performance through system automation and optimization. This system aims to automatically generate optimal database queries according to the different contexts and needs of each user.

[0009] Another object of the present invention is to provide an apparatus and method for providing a data service using a group of interrogators.

[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] A method performed by a computing device according to some embodiments for solving the above-mentioned problems, and a database comparison device based on question classification and questioner classification according to one aspect of the present disclosure for achieving the above-mentioned object, may include: a processor; and a memory storing at least one instruction executed by the processor; wherein the at least one instruction may be configured to cause the processor to perform a question receiving and parsing step of receiving a question written by a user in natural language and converting the question into a form that can be understood by a machine; a natural language processing step of analyzing the question to understand its meaning, extracting keywords and context within the question, and converting the question into a form that can be queried to a database; and a database query generation step of generating a database query based on the extracted keywords and analyzed context, and returning results from the database.

[0012] A database comparison system based on question classification and questioner classification according to one embodiment of the present disclosure may include: a question receiving and classification module that receives and analyzes natural language questions entered by users and classifies the question type; a user profiling and questioner classification module that generates a user-customized query based on the user's profile and past interaction records; a metadata search and large-scale language model linkage module that searches a vector database for metadata matching the question after the question is classified; a database comparison and generation module that automatically generates an optimized database query based on the metalanguage generated by the large-scale language model linkage module; and a data processing and output module that transmits the generated database query to a database to retrieve results, and provides the data processed by the data processing module with a response converted in a format suitable for the user.

[0013] The query receiving and classification module determines whether a query corresponds to a data search, calculation request, or report generation task, and can identify the appropriate query type based on the user's intent and requirements.

[0014] The user profiling and questioner classification module can analyze information about what data a user has previously requested and how the data has been processed, and generate queries that are optimized for each user.

[0015] The metadata search and large-scale language model linkage module inputs the searched metadata into a large-scale language model (LLM) and converts it into a metalanguage, which can then generate a response that matches the question.

[0016] The database comparison and generation module can automatically generate optimized database queries based on a metalanguage generated from a large-scale language model (LLM), optimize database queries by taking into account a user's profile, permissions, past queries, and interaction history, and generate an improved database that provides improved performance and accuracy through comparative analysis with the user's previous queries.

[0017] A database comparison method based on question classification and questioner classification according to another aspect of the present disclosure may include a question receiving and analyzing step of receiving a question written by a user in natural language and converting the question into a form that can be understood by a machine; a natural language processing step of analyzing the question to understand its meaning, extracting keywords and context within the question, and converting the question into a form that can be queried to a database; and a database query generation step of generating a database query based on the extracted keywords and analyzed context, and returning a result from the database.

[0018] A database comparison method based on question classification and questioner classification according to another aspect of the present disclosure is a database comparison method based on question classification and questioner classification performed by a computing device including at least one processor, and may include: a question receiving and analyzing step of receiving a question written by a user in natural language and converting the question into a form that can be understood by a machine; a natural language processing step of analyzing the question to understand its meaning, extracting keywords and context within the question, and converting the question into a form that can be queried to a database; and a database query generation step of generating a database query based on the extracted keywords and analyzed context, and returning a result from the database.

[0019] The method may further include a result providing step in which the final result based on the metadata is transmitted to the user in real time in a streaming manner.

[0020] According to yet another aspect of the present disclosure, there is provided a computer program stored on a computer-readable storage medium, which, when executed by one or more processors, performs a database comparison method based on question classification and questioner classification, and the method may include: a question receiving and analyzing step of receiving a question written by a user in natural language and converting the question into a form that can be understood by a machine; a natural language processing step of analyzing the question to understand its meaning, extracting keywords and context within the question, and converting the question into a form that can be queried to a database; and a database query generation step of generating a database query based on the extracted keywords and analyzed context, and returning a result from the database.

[0021] A method for providing a data service according to an embodiment of the present invention includes the steps of: when a natural language processing unit receives a user question in natural language input from a user device, extracting keyword information from the user question; a DB analysis unit searching a database for a plurality of items including tables, columns, and data to be searched based on the user's entity information and the keyword information, creating a search target list, and calculating search similarity scores between the keyword information and the plurality of items in the search target list; and an execution unit providing the search target list to the user device and receiving from the user device the search target list. the execution unit generating a query using a natural language processing model NLP based on the item selected by the user and executing the generated query; the questioner group processing unit identifying a questioner group to which the user question belongs based on the entity information, the search similarity score, the item information, and required time information which is the time it takes for the user to select an item in the search target list; and the matching unit deriving a customized question list from a question list of the questioner group, which includes a plurality of similar questions whose similarity to the user question is equal to or greater than a predetermined value, and providing the customized question list to the user device.

[0022] The method further includes, before the step of extracting the keyword information, a step of the questioner group processing unit mutually mapping and storing the entity information, the search similarity score, the item information, and the required time information corresponding to the plurality of user questions, each time user questions in natural language are received from a plurality of user devices; a step of the questioner group processing unit mapping the entity information, the search similarity score, the item information, and the required time information corresponding to the plurality of user questions onto a predetermined vector space, thereby generating a plurality of questioner vectors; and a step of clustering the plurality of questioner vectors using a clustering algorithm, thereby generating a plurality of questioner groups.

[0023] The step of identifying the questioner group includes a step in which the questioner group processing unit maps the entity information, the search similarity score, the item information, and the required time information corresponding to the user question onto a predetermined vector space to generate a questioner vector of the user question, and a step in which the questioner group processing unit identifies the questioner group to which the user question belongs based on the distance between the clustering center of multiple questioner groups and the questioner vector of the user question in the vector space.

[0024] The method further includes, after the step of providing to the user device, a step of receiving, by a feedback processing unit, feedback information from the user device, the feedback information being information regarding the user's likes and dislikes for each of the plurality of similar questions in the customized question catalog; and a step of re-training a natural language processing model NLP by the feedback processing unit using the feedback information from the user device.

[0025] The step of executing the generated query includes the steps of: the execution unit inputting the keyword information, the entity information, and the item information into a natural language processing model NLP; the execution unit deriving a JSON query script corresponding to the keyword information, the entity information, and the item information from the natural language processing model NLP; the execution unit generating a query based on the JSON query script; and the execution unit executing the generated query.

[0026] According to an embodiment of the present invention, an apparatus for providing a data service includes: a natural language processing unit that, when a user question written in natural language is received from a user device through user input, extracts keyword information from the user question; a DB analysis unit that searches a database for a plurality of items including tables, columns, and data to be searched based on entity information and keyword information of the user to create a search target list, and calculates a search similarity score between the keyword information and the plurality of items in the search target list; an execution unit that provides the search target list to the user device, receives from the user device item information indicating items selected by the user in the search target list, generates a query using a natural language processing model NLP based on the items selected by the user, and executes the generated query; a questioner group processing unit that identifies a questioner group to which the user question belongs based on the entity information, the search similarity score, the item information, and required time information indicating the time it takes the user to select an item in the search target list; and a matching unit that derives a customized question list from a question list of a questioner group, including a plurality of similar questions whose similarity to the user question is equal to or greater than a predetermined value, and provides the customized question list to the user device. [Effects of the Invention]

[0027] The present disclosure has been devised in response to the above-mentioned background art, and the database comparison system and method based on question classification and questioner classification of the present disclosure classifies questions and questioners based on natural language questions, thereby generating and comparing optimized database queries to enable accurate and efficient data retrieval from databases, thereby providing the following advantages:

[0028] The disclosed database comparison system and method based on question classification and questioner classification provides personalized responses by generating SQL queries tailored to each user's needs through user profiling, allowing users to quickly obtain only the data they need.

[0029] In the disclosed database comparison system and method based on question classification and questioner classification, a metalanguage-based SQL query generated through the LLM and vector database is compared and analyzed with previous queries, thereby continuously improving performance and enabling faster and more accurate data searches.

[0030] The disclosed database comparison system and method based on question classification and questioner classification can effectively process complex natural language questions and provide highly accurate query generation even for questions containing polysemous words and complex contexts.

[0031] The disclosed database comparison system and method based on question classification and questioner classification minimizes unnecessary data searches through optimized SQL queries, shortens database processing time, and improves overall system efficiency.

[0032] Through this, the disclosed system and method for database comparison based on question classification and questioner classification maximizes database query processing performance and provides the effect of greatly improving user experience.

[0033] According to the present disclosure, query accuracy and user convenience can be maximized by providing recommended questions from a group of questioners.

[0034] 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]

[0035] 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 showing the configuration of a database comparison system based on question classification and questioner classification according to an embodiment of the present disclosure. [Figure 3] FIG. 3 is a configuration diagram of a database comparison system based on question classification and questioner classification according to the present disclosure. [Figure 4] FIG. 4 is a schematic diagram illustrating an example of the operation of the database comparison system based on question classification and questioner classification of the present disclosure. [Figure 5] FIG. 5 is a flowchart showing information processing of the database comparison system based on question classification and questioner classification of the present disclosure. [Figure 6] FIG. 6 is a flowchart illustrating the database comparison method according to the present disclosure based on question classification and questioner classification. [Figure 7] FIG. 7 is a general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented. [Figure 8] FIG. 8 is a diagram illustrating the configuration of a system for providing data services according to an embodiment of the present disclosure. [Figure 9] FIG. 9 is a diagram illustrating the configuration of a device for providing a data service according to an embodiment of the present disclosure. [Figure 10] FIG. 10 is a diagram for explaining a detailed configuration of an apparatus for providing data services according to an embodiment of the present disclosure. [Figure 11] FIG. 11 is a flowchart illustrating a method for collecting data for forming a questioner group in a data providing service according to an embodiment of the present disclosure. [Figure 12] FIG. 12 is a flowchart illustrating a method for generating a plurality of questioner groups in a data providing service according to an embodiment of the present disclosure. [Figure 13] FIG. 13 is a flowchart illustrating a method for providing data services using a group of interrogators according to an embodiment of the present disclosure. [Figure 14] FIG. 14 is an exemplary diagram of a hardware system for implementing an apparatus for providing a data service using a group of interrogators according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0036] 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.

[0037] 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).

[0038] 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.

[0039] Also, as used herein, the terms "information" and "data" can often be used interchangeably.

[0040] 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.

[0041] 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.

[0042] 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 this specification and claims should generally be construed to mean "one or more."

[0043] 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.

[0044] 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."

[0045] 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.

[0046] 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.

[0047] [Database comparison system and method based on question classification and questioner classification] Hereinafter, a database comparison system and method based on question classification and questioner classification according to the present disclosure will be described with reference to FIGS.

[0048] FIG. 1 is a block diagram illustrating a computing device according to an embodiment of the present disclosure.

[0049] 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.

[0050] Computing device 100 may include a processor 110 , a memory 130 , and a network unit 150 .

[0051] 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.

[0052] 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).

[0053] 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 .

[0054] 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.

[0055] 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).

[0056] 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.

[0057] 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).

[0058] The techniques described herein may be used in the networks mentioned above as well as other networks.

[0059] In this specification, a database may be controlled by at least one relational database management system (RDBMS) such as ORACLE, PostgreSQL, MySQL, MS-SQL, or MS-SQL Server. The database may be one in which data is input and output using database statements.

[0060] 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 matches the syntax depending on the type of database. For example, through the present disclosure, a user can conveniently generate, check, and control statements through abstracted formulas provided in a user interface (UI) provided by the application, regardless of the type of database.

[0061] The application may also be associated with a database (SQL) statement, where the statement performs one or more of create, read, update, and delete (CRUD). Here, the database (SQL) statement 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 database (SQL) statement in a spreadsheet cell. For example, the display may be as shown in Table 1 below.

[0062] [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.

[0063] FIG. 2 is a block diagram of a database comparison system based on question classification and questioner classification of the present disclosure.

[0064] Referring to FIG. 2 , the database comparison system based on question classification and questioner classification of the present disclosure may be composed of a question receiving and classification module 10, a user profiling and questioner classification module 20, a metadata search and large-scale language model linkage module 30, a database comparison and generation module 40, and a data processing and output module 50.

[0065] The question receiving and classification module 10 receives and analyzes natural language questions entered by a user and classifies the question type. It determines whether the question corresponds to various tasks such as data search, calculation request, or report generation, and identifies the appropriate question type based on the user's intention and requirements. The conversion matrix (G-MATRIX) system receives a natural language question from a user, analyzes it, and classifies the question type. Question classification is performed based on the user's intention and requirements, and determines whether the question corresponds to a task such as data search, calculation request, or report generation.

[0066] The user profiling and questioner classification module 20 is a module that generates user-customized queries based on the questioner's (user's) profile and past interaction records. It analyzes information such as what data the user previously requested and how the data was processed to generate queries optimized for each user. The conversion matrix (G-MATRIX) system classifies appropriate questions using not only the user's question but also the user's profile and past interaction records. Through this, it generates user-customized queries based on information about what data the user previously requested and how the data was processed.

[0067] After a question is classified, the metadata search and large-scale language model linkage module 30 searches a vector database for metadata that matches the question. The searched metadata is input to a large-scale language model (LLM) and converted into a metalanguage so that a response that matches the question can be generated. The transformation matrix (G-MATRIX) system searches a vector database for metadata that matches the question after a question is classified. The searched metadata is input to the LLM and converted into a metalanguage, and the large-scale language model (LLM) generates a response that matches the question based on the searched metadata.

[0068] The SQL comparison and generation module 40 automatically generates optimized database (SQL) queries based on a meta-language generated from a large-scale language model (LLM). In this process, the query is optimized taking into account the user's profile, privileges, past queries, and interaction history, and a database (SQL) with improved performance compared to previous queries is generated.

[0069] The G-MATRIX system generates optimal database (SQL) queries based on metalinguistic responses generated from a large-scale language model (LLM). The G-MATRIX system optimizes database (SQL) queries by reflecting the user's profile, privileges, and past interactions. It is possible to generate database (SQL) queries that offer better performance and accuracy through comparative analysis with the user's previous queries.

[0070] The data processing and output module 50 transmits the generated database (SQL) query to a database to retrieve the results, and then converts the processed data into a format suitable for the user and provides it. Through personalized responses, users can accurately and quickly obtain the data they need. The conversion matrix (G-MATRIX) system transmits the generated database (SQL) query to a database to retrieve the results, and then provides a response in a format suitable for the user through the data processing module. This allows users to effectively obtain personalized results.

[0071] The database comparison system based on question classification and questioner classification disclosed herein belongs to the fields of natural language processing (NLP), large language models (LLM), database query optimization, and metadata processing utilizing vector databases.

[0072] The disclosed database comparison system based on question classification and questioner classification focuses on technologies related to user-customized question processing and database (SQL) query generation and optimization, and provides a system that analyzes the questioner's past interactions and privileges using a user profile and vector database, and converts natural language questions into optimal SQL using metadata. The disclosed database comparison system based on question classification and questioner classification maximizes the efficiency of database searches and result return by more accurately analyzing natural language questions and automatically generating optimized database (SQL) queries that meet the user's requirements.

[0073] FIG. 3 is a configuration diagram of a database comparison system based on question classification and questioner classification according to the present disclosure.

[0074] Referring to FIG. 3 , the database comparison system based on question classification and questioner classification 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 relevant results from the database.

[0075] In one embodiment, the database comparison system based on question classification and questioner classification of the present disclosure may be a system that processes a user's natural language question by converting it into a metalanguage, which can analyze the user's question, automatically generate and execute an appropriate SQL query, and provide the result data to the user in natural language. The system may also include morphological analysis and similar question management functions to process natural language questions.

[0076] The database comparison system based on question classification and questioner classification of the present disclosure 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 sends the question. The natural language processing module (NLP) receives the metalanguage question, analyzes the natural language question, and presents a metalanguage response accordingly. The natural language processing module (NLP) can be a conversational AI service based on GPT, such as Chat GPT.

[0079] 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 (DATA SET), and sends the result response to the user (USER).

[0080] In one embodiment, the disclosed database comparison system for question classification and questioner classification performs a morphological analysis of a question entered by a user in natural language, extracting main nouns and verbs and processing synonyms. The extracted information is converted into a metalanguage, and an SQL query is automatically generated based on the extracted information. The generated SQL query is executed on a database to obtain 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.

[0081] 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.

[0082] The database comparison system based on question classification and questioner classification of the present disclosure may include a function for managing similar questions, and can detect questions similar to previously used questions and process data more efficiently based on the detected questions. Furthermore, it utilizes database (SQL) optimization and data caching techniques 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.

[0083] FIG. 4 is a schematic diagram illustrating an example of the operation of the database comparison system based on question classification and questioner classification of the present disclosure.

[0084] 4, the database comparison system based on question classification and questioner classification of the present disclosure is a system that analyzes user questions expressed in natural language, generates SQL queries based on the results, queries data from databases, and provides the results in a format that the user can understand. This system is mainly used for data queries such as sales management in a specific business division such as the electric power division of a company.

[0085] In one embodiment, the database comparison system with question classification and questioner classification of the present disclosure may include the following components:

[0086] 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?"

[0087] 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."

[0088] The optimal database generator (i-META) converts natural language queries into a metalanguage and optimizes the database (SQL) based on this metalanguage.

[0089] The natural language processing module (NLP) analyzes the user's natural language question, extracts the necessary data, and converts it into a metalanguage.

[0090] In one embodiment, the question classification and questioner classification database comparison system of the present disclosure can operate as follows.

[0091] When a user types a question in natural language, such as "What are the sales figures for the Electrical Division in 2023?", the NLP module analyzes the question and extracts important time ranges and departments.

[0092] 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."

[0093] The generated SQL query is transmitted to the database via the optimal database generation unit (i-META) and executed.

[0094] The execution results are organized in a data format such as Table A and provided to the user in the form of Template B.

[0095] In one embodiment, the disclosed database comparison system based on question classification and questioner classification can use natural language processing (NLP) algorithms to efficiently manage sales data for a specific business division, such as the electrical division of a company, and provide a data service that converts users' natural language questions into database (SQL) and derives relevant information from the database.

[0096] In one embodiment, the disclosed question classification and questioner classification database comparison system can provide an automated system that allows users to request data in natural language, which is then analyzed and converted into accurate SQL queries.

[0097] In one embodiment, the database comparison system based on question classification and questioner classification of the present disclosure may include a module optimized for generating SQL queries and querying data for a specific department or time period.

[0098] In one embodiment, the result data of the database comparison system based on the question classification and questioner classification of the present disclosure can be provided in a user-customizable format, and visual reports can also be generated via templates.

[0099] In one embodiment, the database comparison system based on question classification and questioner classification of the present disclosure can operate as follows: 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 "S Corporation's electric division sales 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 as visualized data to the user using Template B.

[0100] In one embodiment, the database comparison system based on question classification and questioner classification of the present disclosure provides a convenient system that allows users to query required 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.

[0101] FIG. 5 is a flowchart showing information processing of the database comparison system based on question classification and questioner classification of the present disclosure.

[0102] 5, a database comparison system based on question classification and questioner classification 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 users' natural language questions and provide optimal answers based on metadata. The database comparison system based on question classification and questioner classification according to the present disclosure can then generate SQL queries using the learned metadata and provide results in real time.

[0103] In one embodiment, the disclosed database comparison system for question classification and questioner classification may receive natural language queries from users, learn metadata through a large-scale language model, and automatically generate SQL queries based on the learned metadata to query data from a database, where the metadata is managed in an embedded vector store and the system provides real-time responses through continuous query processing and caching.

[0104] In one embodiment, the database comparison system based on question classification and questioner classification of the present disclosure may be composed of a user, a result platform (AUD7 Platform), a transformation matrix (G-MATRIX), an optimal database generator (i-META), and an LLM (large-scale language model).

[0105] A user inputs a natural language question, such as "What are the sales figures for the Electric Power Division in 2023?"

[0106] 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.

[0107] 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).

[0108] 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.

[0109] The optimal database generation unit (i-META) constructs templates based on the metadata generated by the transformation matrix (G-MATRIX) and optimizes SQL queries.

[0110] FIG. 6 is a flowchart illustrating the database comparison method according to the present disclosure based on question classification and questioner classification.

[0111] Referring to FIG. 6, the database comparison method by question classification and questioner classification of the present disclosure may be comprised of a question receiving and parsing step S1000, a natural language processing (NLP) step S2000, and a database query generation step S3000.

[0112] The question receiving and parsing step S1000 receives a question formulated by a user in natural language and converts it into a machine understandable form.

[0113] The natural language processing (NLP) stage S2000 analyzes the question to understand its meaning, extracts keywords and context within the question, and converts it into a form that can be queried into a database.

[0114] The database query generation step S3000 generates a database query based on the extracted keywords and the analyzed context, and returns results from the database.

[0115] In one embodiment, the disclosed database comparison method based on question classification and questioner classification involves a user entering a question such as "What were the sales figures for the electric power division in 2023?" The system analyzes the question in an embedded vector store and generates meta information. The transformation matrix (G-MATRIX) executes an SQL query based on the generated meta information, and the optimal database generation unit (i-META) provides the user with an optimized template. The results are returned in real time in a streaming manner.

[0116] The disclosed database comparison method based on question classification and questioner classification stores meta-information learned through large-scale language models (LLMs) in a vector store, and can provide accurate answers to questions based on this.

[0117] The disclosed database comparison method based on question classification and questioner classification can provide a quick response by utilizing cached data related to the question, and can check the cached data in real time to ensure accuracy.

[0118] The disclosed database comparison method based on question classification and questioner classification can efficiently process data when a user continuously inputs questions, taking into account the relevance to previous questions. SQL queries can be automatically generated based on meta-information, optimized, and executed in the database.

[0119] The database comparison method based on question classification and questioner classification disclosed herein utilizes a large-scale language model (LLM) and metadata to process natural language questions and provide accurate data in real time, thereby significantly shortening the data search and analysis process and maximizing efficiency through caching and continuous query processing functions.

[0120] FIG. 7 is a general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

[0121] Referring to FIG. 7, the computer program, when executed by one or more processors, can perform actions for user authorization.

[0122] Also disclosed in accordance with one embodiment of the present disclosure is a computer-readable medium having a data structure stored thereon.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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 communication. For example, the computing device 100 may be a desktop computer, a laptop computer, a tablet PC, a portable terminal, or the like.

[0148] 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 by 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 departing from the scope of the present disclosure.

[0149] 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.

[0150] It should be understood that the specific order or hierarchy of 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 process steps can be rearranged within the scope of this disclosure. The accompanying method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

[0151] 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.

[0152] [Apparatus and method for providing data services using a group of interrogators] Hereinafter, with reference to FIGS. 8 to 14, an apparatus for providing a data service using a group of interrogators according to the present disclosure and a method therefor will be described.

[0153] A system and an apparatus for providing a data service according to an embodiment of the present disclosure will be described. Fig. 8 is a diagram for explaining the configuration of a system for providing a data service according to an embodiment of the present disclosure. Fig. 9 is a diagram for explaining the configuration of an apparatus for providing a data service according to an embodiment of the present disclosure. Fig. 10 is a diagram for explaining the detailed configuration of an apparatus for providing a data service according to an embodiment of the present disclosure.

[0154] Referring to FIG. 8, the data service system according to this embodiment is a system that performs a data service by generating a query through a natural language processing algorithm for a natural language question, executing the generated query, and providing a calculated response.

[0155] The data service system includes a user device 10 , a service server 20 and a model server 30 .

[0156] The model server 30 is a server on which a natural language processing (NLP) model is executed. In the embodiment of the present disclosure, the model server 30 is illustrated as a device separate from the service server 20. However, the natural language processing model NLP can operate on the service server 20, and in such a case, the model server 30 can operate as one component of the service server 20.

[0157] The user device 10, the service server 20, and the model server 30 can transmit and receive data via a communication network.

[0158] The user device 10 inputs a natural language question to the service server 20 and receives a response to the natural language question from the service server 20. The natural language question can be input in the form of voice or text via an input unit provided by the user device 10. Here, the input unit may include a keypad, a touch screen, a microphone, etc. The user device 10 is a communication terminal capable of communicating with the service server 20, and may be, for example, a personal computing system such as a smartphone, a laptop, a desktop computer, a handheld computer, or a tablet computer.

[0159] A user of the user device 10 may be a general user, but in this embodiment, the user may belong to a specific group. Here, the specific group is related to the access authority to the database DB. That is, the access authority to the database DB may be set differently depending on the specific group to which the user belongs. As a result, a user may or may not receive a response to a natural language question depending on the specific group to which the user belongs. For example, the specific group may be categorized as a company, a department, a job rank, etc. Information about the specific group to which the user belongs may be included in user attribute information. Here, the user attribute information includes personal information of the user, information about the user device 10, and information about the specific group to which the user belongs.

[0160] The natural language processing model NLP performs learned operations on input information received from the service server 20 to generate a JSON (JavaScript Object Notation) query script containing information necessary for query generation and returns it to the service server 20. Such a natural language processing model NLP may include a large language model (LLM) capable of inferring relationships between words within a large amount of text data. The natural language processing model NLP returns the information necessary for query generation by analyzing and extracting meaningful information from the text. Here, an LLM refers to an artificial intelligence model that can process a large amount of natural language data and generate responses that are often indistinguishable from human-generated text. Examples of such LLMs include OpenAI's Generative Pre-trained Transformer (GPT) series and Google's Bidirectional Encoder Representations from Transformers (BERT) model.

[0161] The natural language processing model NLP according to an embodiment of the present disclosure returns a JSON query script so that a query can be generated through operations on input information, such as keyword information, entity information, and item information, input from the service server 20. The JSON query script is a script for generating a query and includes commands specifying, for example, templates, tables, columns, search conditions, etc. The JSON query script may also include code capable of generating a query.

[0162] The service server 20 is a server that communicates with the user device 10 and the natural language processing model NLP to process data, and may include, for example, an application server, a computing server, a database server, a file server, a proxy server, and a web server. The service server 20 may be configured with one or more servers. The service server 20 basically serves to provide responses to user questions in natural language received from the user device 10. This will be described in more detail as follows.

[0163] Referring to FIG. 9, the service server 20 includes an interface unit IF, a processing unit PM, and a database DB.

[0164] The database DB stores data that can respond to user questions. The database DB includes a vector DB containing index terms for the stored data. The vector DB can be provided to the natural language processing model NLP by a control. The index terms may include table names and column names of the data. The database DB can store previously received user questions, queries corresponding to the user questions, and execution plans corresponding to the queries.

[0165] The interface unit IF provides an environment in which the user device 10 can connect to the service server 20. The user device 10 can input a natural language question via the interface unit IF and receive a response to the input natural language question. That is, the interface unit IF receives a natural language question from the user device 10, provides it to the processing unit PM, and returns a response to the natural language question from the processing unit PM to the user device 10. That is, the interface unit IF can perform the function of the platform of the service server 20.

[0166] The processing unit PM generates a query based on a user question, executes the generated query on the database DB to obtain a response, and then returns the response to the user device 10 via the interface unit IF. In particular, the processing unit PM can derive a JSON query script through a natural language processing model NLP and generate a query SQL from the JSON query script.

[0167] Referring to FIG. 10, the calculation unit PM includes a natural language processing unit 100, a DB analysis unit 200, an execution unit 300, a questioner group processing unit 400, a matching unit 500, and a feedback processing unit 600.

[0168] When the natural language processing unit 100 receives a user question in natural language input by the user from the user device 10 via the interface unit IF, it can extract keyword information and the intent of the question from the user question and extract entity information of the user of the user device 10 that has already been stored. Here, the entity information may include personal information of the user, information about the user device 10, and information about a specific group to which the user belongs (e.g., company, department, job rank, etc.).

[0169] The DB analysis unit 200 can search a database (DB) for a table to be searched, a column of the table, and a plurality of items including data of the column, based on the user's entity information and keyword information, and create a search target list. At the same time, the DB analysis unit 200 calculates a search similarity score, which is the similarity between the keyword information and a plurality of items in the search target list, in step S130. Here, a higher search similarity score indicates that the user is more familiar with the structure of the database to be searched and is a more suitable user.

[0170] The execution unit 300 may provide a search target list to the user device 10 and receive item information indicating an item selected by the user from the search target list from the user device 10. In this case, the execution unit 300 may measure required time information, which is the time it takes for a user to select an item from the search target list, based on the time it takes to provide the search target list and receive item information indicating the item selected by the user. In particular, when the execution unit 300 inputs keyword information, entity information, and item information into the natural language processing model NLP, the natural language processing model NLP may perform learned operations on the keyword information, entity information, and item information to derive a JSON query script. The execution unit 300 may also generate a query based on the JSON query script, generate an execution plan corresponding to the generated query for the database DB, execute the query using the generated execution plan, and receive a response corresponding to the user's question from the database DB. The execution unit 300 may then transmit the response to the user device 10 via the interface unit IF.

[0171] After a query is executed for multiple user questions, the questioner cluster processing unit 400 can generate a questioner cluster based on entity information corresponding to the multiple user questions, search similarity scores, item information indicating items selected by the user in the search target list, and required time information indicating the time it takes the user to select an item in the search target list.

[0172] In addition, when a new user question is input, the questioner group processing unit 400 can identify the questioner group to which the user question belongs after a query is executed based on the entity information corresponding to the new user question, the search similarity score, item information indicating the item selected by the user in the search target list, and required time information indicating the time it takes the user to select an item in the search target list.

[0173] The matching unit 500 extracts multiple similar questions having a similarity to the user's question that is greater than or equal to a predetermined value from a question list that includes multiple user questions belonging to a questioner group identified to which the user's user question belongs, deriving a customized question list, and can provide the derived customized question list to the user device 10.

[0174] The feedback processing unit 600 can receive feedback information from the user device 10, which is information about the user's likes and dislikes (e.g., "like" or "dislike") for each of the multiple similar questions in the customized question catalog. Next, the feedback processing unit 600 can retrain the natural language processing model NLP using the feedback information from the user device 10. Alternatively, the feedback processing unit 600 can update the customized question catalog and provide it to the user device 10.

[0175] Next, a method for collecting data for forming questioner groups in a data provision service according to an embodiment of the present disclosure and generating questioner groups based on the collected data will be described. Figure 11 is a flowchart illustrating a method for collecting data for forming questioner groups in a data provision service according to an embodiment of the present disclosure. Figure 12 is a flowchart illustrating a method for generating multiple questioner groups in a data provision service according to an embodiment of the present disclosure.

[0176] Referring to FIG. 11, the natural language processing unit 100 may receive a user question in natural language input from the user device 10 via the interface unit IF in step S110.

[0177] Next, the natural language processing unit 100 may extract keyword information and the intent of the question from the user question in step S120. Also, the natural language processing unit 100 may extract entity information of the user of the user device 10 that has already been stored in step S120. Here, the entity information may include personal information of the user, information about the user device 10, and information about a specific group to which the user belongs (e.g., company, department, job rank, etc.).

[0178] Next, the DB analysis unit 200 may search a database (DB) for a plurality of items including a search target table, a column of the table, and data of the column based on the user's entity information and keyword information in step S130, thereby creating a search target list. At the same time, the DB analysis unit 200 may calculate a search similarity score, which is the degree of similarity between the keyword information and the plurality of items in the search target list, in step S130. Here, a higher search similarity score indicates that the user is more familiar with the structure of the searched database and is a more suitable user.

[0179] Next, the execution unit 300 provides the search target list to the user device 10 in step S140, and receives item information indicating an item selected by the user in the search target list from the user device 10 in step S150. In steps S140 and S150, the execution unit 300 can measure required time information, which is the time it takes for the user to select an item in the search target list, based on the time it takes to provide the search target list and receive the item information indicating the item selected by the user.

[0180] Accordingly, the execution unit 300 can generate a query using a natural language processing model NLP based on the items selected by the user and execute the generated query. This will be described in more detail as follows.

[0181] In operation S160, the execution unit 300 inputs keyword information, entity information, and item information into the natural language processing model NLP, and the natural language processing model NLP performs learned operations on the keyword information, entity information, and item information to derive a JSON query script. The JSON query script is a script for generating a query and includes, for example, commands specifying templates, tables, columns, search conditions, etc.

[0182] Next, the execution unit 300 generates a query based on the JSON query script, generates an execution plan corresponding to the generated query for the database DB, executes the query according to the generated execution plan, and receives a response corresponding to the user query from the database DB in step S170. Next, the execution unit 300 transmits the response to the user device 10 via the interface unit IF in step S180.

[0183] The above-described steps S110 to S180 are repeated every time a user question is received from each of the plurality of users, ie, the plurality of user devices 10.

[0184] Accordingly, referring to FIG. 12, each time user questions in natural language are received from a plurality of user devices, the questioner group processing unit 400 cross-maps and stores entity information corresponding to the plurality of user questions, search similarity scores, item information indicating items selected by the user from the search target list, and required time information indicating the time it takes for the user to select an item from the search target list in step S210.

[0185] Next, in step S220, the questioner group processing unit 400 maps entity information, search similarity scores, item information, and required time information corresponding to a plurality of user questions into a predetermined vector space to generate a plurality of questioner vectors.

[0186] Next, the questioner cluster processing unit 400 may perform clustering on the plurality of questioner vectors using a clustering algorithm in step S230 to generate a plurality of questioner clusters.

[0187] Next, a method for providing a data service using a group of questioners according to an embodiment of the present disclosure after a plurality of groups of questioners have been generated as described above will be described. Figure 13 is a flowchart illustrating a method for providing a data service using a group of questioners according to an embodiment of the present disclosure.

[0188] Referring to FIG. 13, the natural language processing unit 100 may receive a user question in natural language input from the user device 10 via the interface unit IF in step S310.

[0189] Next, the natural language processing unit 100 may extract keyword information and the intent of the question from the user question in step S320. Also, the natural language processing unit 100 may extract entity information of the user of the user device 10 that has been stored in step S320.

[0190] Next, the DB analysis unit 200 may search a database (DB) for a table to be searched, a column of the table, and a plurality of items including data of the column, based on the user's entity information and keyword information, and create a search target list in step S330. At the same time, the DB analysis unit 200 may calculate a search similarity score, which is the similarity between the keyword information and a plurality of items in the search target list, in step S330.

[0191] Next, the execution unit 300 provides the search target list to the user device 10 in step S340, and receives item information indicating an item selected by the user in the search target list from the user device 10 in step S350. In steps S340 and S350, the execution unit 300 can measure required time information, which is the time it takes for the user to select an item in the search target list, based on the time it takes to provide the search target list and receive the item information indicating the item selected by the user.

[0192] Accordingly, the execution unit 300 generates a query using the natural language processing model NLP based on the items selected by the user in operation S360, and executes the generated query to provide a response to the user device 10. This will be described in more detail as follows: The execution unit 300 first inputs keyword information, entity information, and item information into the natural language processing model NLP, and the natural language processing model NLP performs learned operations on the keyword information, entity information, and item information to derive a JSON query script. Next, the execution unit 300 generates a query based on the JSON query script, generates an execution plan corresponding to the generated query for the database DB, and executes the query according to the generated execution plan to receive a response corresponding to the user question from the database DB. Next, the execution unit 300 transmits the response to the user device 10 via the interface unit IF.

[0193] As described above, after executing a query and providing a response, the questioner group processing unit 400 identifies a questioner group corresponding to the user question in step S370. To this end, the questioner group processing unit 400 can identify a questioner group to which the user question belongs based on entity information, search similarity score, item information, and required time information.

[0194] Step S370 will be described in more detail as follows. The questioner group processing unit 400 maps entity information, search similarity scores, item information, and required time information corresponding to the user question onto a predetermined vector space to generate a questioner vector of the user question. Next, the questioner group processing unit 400 identifies the questioner group to which the user question belongs based on the distance between the clustering center of the multiple questioner groups and the questioner vector of the user question in the vector space. That is, the questioner group processing unit 400 can identify the questioner group to which the user question belongs, the questioner group in which the clustering center of the multiple questioner groups is closest to the questioner vector of the user question and is within a predetermined distance in the vector space.

[0195] Next, in step S380, the matching unit 500 extracts a plurality of similar questions having a similarity to the user question of a predetermined value or more from a question list including a plurality of user questions belonging to the questioner group identified to which the user's user question belongs, thereby deriving a customized question list, and provides the derived customized question list to the user device 10.

[0196] Next, in step S390, the feedback processing unit 600 may receive feedback information from the user device 10, which is information regarding the user's likes and dislikes (e.g., "like" or "dislike") for each of the multiple similar questions in the customized question list.

[0197] Next, in step S400, the feedback processing unit 600 may retrain the natural language processing model NLP using the feedback information from the user device 10. Alternatively, the feedback processing unit 600 may update the customized question list and further provide it to the user device 10.

[0198] FIG. 14 is an exemplary diagram of a hardware system for implementing an apparatus for providing a data service using a group of interrogators according to an embodiment of the present disclosure.

[0199] As shown in FIG. 14, a hardware system 2000 according to an embodiment of the present disclosure may have a configuration including a processor unit 2100, a memory interface unit 2200, and a peripheral device interface unit 2300.

[0200] Each of these components in the hardware system 2000 may be a discrete component or may be integrated into one or more integrated circuits, and each of these components may be coupled together by a bus system (not shown).

[0201] Here, a bus system is an abstraction that represents any one or more discrete physical buses, communication lines / interfaces, and / or multi-drop or point-to-point links linked by appropriate bridges, adapters, and / or controllers.

[0202] The processor unit 2100 communicates with the memory unit 2210 via the memory interface unit 2200 to execute various software modules stored in the memory unit 2210 in order to perform various functions in the hardware system.

[0203] Here, the memory unit 2210 may store each of the components including the natural language processing unit 100, the DB analysis unit 200, the execution unit 300, the questioner group processing unit 400, the matching unit 500, and the feedback processing unit 600 in the form of a software module, and may further store an operating system OS. The components including the natural language processing unit 100, the DB analysis unit 200, the execution unit 300, the questioner group processing unit 400, the matching unit 500, and the feedback processing unit 600 may be loaded into the processor unit 2100 and executed.

[0204] Each of the components including the natural language processing unit 100, the DB analysis unit 200, the execution unit 300, the questioner group processing unit 400, the matching unit 500 and the feedback processing unit 600 described above may be implemented in the form of a software module executed by a processor or a hardware module, or may be implemented in the form of a combination of a software module and a hardware module.

[0205] In this manner, the software modules, hardware modules, or a combination of software modules and hardware modules executed by a processor may be embodied in an actual hardware system (e.g., a computer system).

[0206] In the case of an operating system (e.g., an embedded operating system such as I-OS, Android®, Darwin, RTXC, LINUX®, UNIX®, OS X, WINDOWS®, or VxWorks), it includes various procedures, command sets, software components, and / or drivers that control and manage common system tasks (e.g., memory management, storage control, power management, etc.) and facilitates communication between various hardware and software modules.

[0207] For reference, the memory unit 2210 may include a memory hierarchy including, but not limited to, cache, main memory, and secondary memory, and such a memory hierarchy may be implemented through any combination of, for example, RAM (e.g., SRAM, DRAM, DDRAM), ROM, FLASH, magnetic and / or optical storage devices (e.g., disk drives, magnetic tapes, compact disks (CDs), and digital video discs (DVDs)).

[0208] The peripheral device interface unit 2300 serves to enable communication between the processor unit 2100 and peripheral devices.

[0209] Here, in the case of a peripheral device, it is intended to provide different functions to the hardware system 2000, and in one embodiment of the present disclosure, may include, for example, a communication unit 2310.

[0210] Here, the communication unit 2310 serves to provide communication functions with other devices, and for this purpose may include, but is not limited to, known circuits for performing this function, such as an antenna system, an RF transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a codec (CODEC) chipset, and memory.

[0211] Examples of communication protocols supported by the communication unit 2310 include wireless LAN (WLAN), DLNA (Digital Living Network Alliance), Wibro (Wireless Broadband), Wimax (World Interoperability for Microwave Access), GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), IEEE 802.16, LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), 5G communication system, and wireless mobile broadband communication service (Wireless Mobile Broadband). These may include Wireless Multimedia Services (WMBS), Bluetooth (registered trademark), Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra-Wideband (UWB), ZigBee (registered trademark), Near Field Communication (NFC), Ultra Sound Communication (USC), Visible Light Communication (VLC), Wi-Fi, Wi-Fi Direct, and the like.In addition, examples of wired communication networks include wired local area networks (LANs), wired wide area networks (WANs), power line communications (PLCs), USB communications, Ethernet, serial communications, optical / coaxial cables, etc., and are not limited to these, but may include any protocol that can provide a communication environment with other devices.

[0212] In the hardware system 2000 according to one embodiment of the present disclosure, each component stored in the memory unit 2210 in the form of a software module interfaces with the communication unit 2310 via the memory interface unit 2200 and the peripheral device interface unit 2300 in the form of an instruction executed by the processor unit 2100.

[0213] As explained above, while this specification contains details of numerous specific embodiments, these should not be construed as limiting the scope of any invention or claimable therein, but rather as descriptions of features specific to particular embodiments of particular inventions. Certain features described herein in the context of a separate embodiment may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any suitable subcombination. Furthermore, while features may operate in a particular combination and may be initially described as being so claimed, one or more features from a claimed combination may, in some cases, be excluded from that combination, or the claimed combination may be modified into a subcombination or a variation of that subcombination.

[0214] Similarly, although acts are depicted in the figures in a particular order, this should not be understood as requiring that such acts be performed in the particular order or sequential order shown to achieve desirable results, or that all of the depicted acts be performed. In certain cases, multitasking and parallel processing may be advantageous. Also, the separation of various system components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems may generally be integrated together in a single software product or packaged in multiple software products.

[0215] Specific embodiments of the subject matter described herein have been described. Other embodiments are within the scope of the following claims. For example, the actions recited in the claims may be performed in a different order and still achieve desirable results. By way of example, the processes illustrated in the accompanying figures do not necessarily require the particular illustrated order or sequential order to achieve desirable results. In certain implementations, multitasking and parallel processing may be advantageous.

[0216] The written description sets forth the best mode of the invention and provides examples to explain the invention and to enable one skilled in the art to make and use the invention. The specification so written is not intended to limit the invention to the specific terms set forth. Thus, although the invention has been described in detail with reference to the foregoing examples, those skilled in the art may make modifications, changes, and variations to the examples without departing from the scope of the invention.

[0217] Therefore, the scope of the invention should be defined not by the illustrated embodiments, but by the appended claims.

Claims

1. a processor; a memory having stored therein at least one instruction for execution by the processor; The at least one instruction may cause the processor to: a query receiving and parsing stage that receives a query formulated by a user in natural language and converts it into a machine-understandable form; A natural language processing stage that analyzes the question to understand its meaning, extracts keywords and context within the question, and converts it into a form that can be queried into a database; and A database comparison device based on question classification and questioner classification, configured to perform a database query generation step of generating a database query based on the extracted keywords and the analyzed context, and returning results from the database.

2. a question receiving and classification module that receives and analyzes a natural language question entered by a user and classifies the question type; a user profiling and questioner classification module that generates user-customized queries based on the user's profile and past interaction records; a metadata retrieval and large-scale language model linkage module for retrieving metadata matching the query from the vector database after the query is classified; a database comparison and generation module that automatically generates optimized database queries based on the metalanguage generated from the large-scale language model linkage module; A database comparison system based on question classification and questioner classification, including: a data processing and output module that transmits the generated database query to a database to retrieve results, and provides the data processed through the data processing module with the response converted in a format suitable for the user.

3. The question receiving and classification module Determine whether the question constitutes a data retrieval, calculation request, or report generation task; 3. The database comparison system based on question classification and questioner classification according to claim 2, wherein an appropriate question type is identified based on the user's intention and requirements.

4. The user profiling and questioner classification module 3. The database comparison system according to claim 2, wherein a query optimized for each user is generated by analyzing information on what data the user has previously requested and how the data has been processed.

5. The metadata search and large-scale language model linkage module The retrieved metadata is input into a large-scale language model and converted into a metalanguage.

3. The database comparison system with question classification and questioner classification according to claim 2, wherein the large-scale language model is used to generate a response that matches the question.

6. The database comparison and generation module Automatically generate optimized database queries based on the generated meta-language using a large-scale language model. Optimize database queries by taking into account user profile, permissions, previous queries and interaction history; 3. The database comparison system according to claim 2, which generates an improved database that provides improved performance and accuracy through comparative analysis of users' previous queries.

7. a query receiving and parsing stage for receiving a query formulated by a user in natural language and converting the query into a machine understandable form; A natural language processing stage that analyzes the question to understand its meaning, extracts keywords and context within the question, and converts it into a form that can be queried into a database; A database comparison method based on question classification and questioner classification, including: a database query generation step of generating a database query based on the extracted keywords and the analyzed context, and returning results from the database.

8. 1. A method of database comparison by question classification and questioner classification performed by a computing device including at least one processor, comprising: a query receiving and parsing stage for receiving a query formulated by a user in natural language and converting the query into a machine understandable form; A natural language processing stage that analyzes the question to understand its meaning, extracts keywords and context within the question, and converts it into a form that can be queried into a database; A database comparison method based on question classification and questioner classification, including: a database query generation step of generating a database query based on the extracted keywords and the analyzed context, and returning results from the database.

9. The method comprises: The method for database comparison according to question classification and questioner classification according to claim 8, further comprising a result providing step in which the final result based on the metadata is transmitted to the user in real time in a streaming manner.

10. 1. A computer program stored on a computer-readable storage medium, the computer program, when executed by one or more processors, performing a database comparison method according to question classification and questioner classification, the method comprising: a query receiving and parsing stage for receiving a query formulated by a user in natural language and converting the query into a machine understandable form; A natural language processing stage that analyzes the question to understand its meaning, extracts keywords and context within the question, and converts it into a form that can be queried into a database; A computer program stored on a computer-readable storage medium, the computer program comprising: a database query generation step of generating a database query based on the extracted keywords and the analyzed context, and returning results from the database.

Images