KR-20260064765-A - Interactive data service device and method using natural language processing algorithm

KR20260064765AKR 20260064765 AKR20260064765 AKR 20260064765AKR-20260064765-A

Abstract

The present invention relates to an interactive data service device and method using a natural language processing algorithm that accurately identifies a query intended by a user and provides an answer through a conversation with a user querying in natural language. The interactive data service device according to the present invention comprises: a database unit; an interface unit that receives a natural language query from a user terminal and outputs an answer to the natural language query; and a control unit that generates a query capable of outputting an answer from the database unit using a natural language processing (NLP) model for the natural language query, and converts the natural language query into a meta-query that clarifies the natural language query by adding annotations to the natural language query through a conversation with the user via the user terminal so that the NLP model can interpret it, and transmits the meta-query to the NLP model.

Inventors

배 영 근
전 규 화

Assignees

(주)비아이매트릭스

Dates

Publication Date: 20260508
Application Date: 20241029

Claims (13)

A data service method for an interactive data service device using a natural language processing algorithm, A step of receiving a user's natural language query from a user terminal; A step of converting the natural language query into a meta-query that clarifies the natural language query by adding annotations to the natural language query through a conversation with the user via the user terminal, so that the natural language query can be interpreted by an NLP (natural language processing) model; A step of transmitting the above meta-query to an NLP model; A step of receiving a meta-answer capable of generating a query from the above NLP model; Step of generating a query based on the above meta answer; A step of generating an answer by querying the database section with the above query; and A step of providing the above answer to the above user terminal; A conversational data service method using a natural language processing algorithm including
In paragraph 1, in the step of converting into the meta-query, A method for providing interactive data services using a natural language processing algorithm, characterized in that the above-mentioned comment is generated using meta and user attribute information regarding data stored in the above-mentioned database, and the above-mentioned meta includes an item containing the table name and column name of the above-mentioned data.
In paragraph 2, the step of converting into the meta-query is, A step of extracting at least one meta capable of answering the above natural language query; A step of providing at least one meta to the user terminal and requesting the user to select a meta; and A step of including the meta selected by the user in the comment; A conversational data service method using a natural language processing algorithm characterized by including
In paragraph 3, at the step of requesting the selection of the above meta, A conversational data service method using a natural language processing algorithm characterized by displaying similarity for each meta when there are multiple metas to assist the user in making a selection.
In paragraph 4, the step of converting into the above meta-query is, A step of requesting the user to select an item by providing at least one item included in the selected meta to the user terminal; and A step of including the item selected by the user in the comment; A conversational data service method using a natural language processing algorithm characterized by further including
In paragraph 5, in the step of converting into the above meta-query, A conversational data service method using a natural language processing algorithm, characterized in that the above meta-query is based on the above natural language query, and the above items are matched to the vocabulary included in the above natural language query.
In paragraph 6, in the step of converting into the above meta-query, A conversational data service method using a natural language processing algorithm characterized by presenting at least one item that can be matched for each vocabulary included in the above natural language query and requesting a selection from the user.
In paragraph 7, in the step of converting into the above meta-query, A conversational data service method using a natural language processing algorithm characterized by distinguishing between accurate vocabulary and inaccurate vocabulary among the vocabulary included in the above natural language query.
In any one of paragraphs 1 to 8, in the step of converting into the meta-query, A conversational data service method using a natural language processing algorithm characterized by providing the meta-query that is updated through conversation with the user via the user terminal.
In claim 1, performed prior to the step of transmitting to the NLP model, Store previous natural language queries, meta-queries, meta-answers, and answers as cached data, and The method further includes the step of checking whether there is a query corresponding to the currently entered natural language query or meta-query in the above cache data; A conversational data service method using a natural language processing algorithm, characterized by performing the step of not transmitting a meta-query for the currently input natural language query to an NLP model if there is a corresponding query upon verification, and transmitting it to the NLP model if there is no corresponding query.
Database Department; An interface unit that receives a natural language query from a user terminal and outputs an answer to the natural language query; and A control unit that generates a query capable of outputting an answer from the database unit using a natural language processing (NLP) model for the above natural language query, and converts the natural language query into a meta-query that clarifies the natural language query by adding comments to the natural language query through a conversation with the user via the user terminal so that the NLP model can interpret it, and transmits the meta-query to the NLP model; An interactive data service device using a natural language processing algorithm including
In Clause 11, the control unit is, A query processing engine that converts the natural language query into the meta-query by adding comments to the natural language query through a conversation with the user via the user terminal, transmits the meta-query to the NLP model, and receives a meta-response capable of generating a query from the NLP model; and A query processing engine that generates a query based on the above meta-answer, queries the database unit with the above query to generate an answer, and provides the answer to the user terminal through the interface unit; An interactive data service device using a natural language processing algorithm characterized by including
A computer-readable recording medium having a program recorded thereon for performing an interactive data service method using a natural language processing algorithm according to any one of claims 1 to 10.

Description

Interactive data service device and method using natural language processing algorithm The present invention relates to a data service device and method using a natural language processing algorithm, and more specifically, to an interactive data service device and method using a natural language processing algorithm that provides an answer to a query through a conversation with a user querying in natural language. A typical question-and-answer system analyzes a user's natural language query using natural language processing algorithms, generates a response from a database based on the analysis results, and provides it to the user. The question-and-answer system supports queries capable of generating answers (responses) from the database based on natural language processing algorithms. The quality of the answers provided by such question-and-answer systems is determined by natural language queries and queries generated based on those natural language queries. However, if a natural language query contains vocabulary that the question answering system cannot interpret or that can be interpreted in various ways, the question answering system cannot provide an answer that corresponds to the natural language query. For example, users may use different vocabulary in their queries even if the queries are substantially the same. If a question-response system interprets the vocabulary included in those queries with different meanings, it may generate different queries for substantially identical queries. In this case, the question-response system may generate and provide different answers to users for substantially identical queries. In addition, even when a query includes vocabulary that can be interpreted in various ways, the answers provided to users by the question-answering system may differ depending on how the vocabulary included in the query is interpreted. As such, since existing question-and-answer systems are implemented by simply providing answers to user queries, there are limitations in accurately identifying the user's intended query and providing a response. FIG. 1 is a schematic diagram showing a data service system using a natural language processing algorithm according to a first embodiment of the present invention. Figure 2 is a block diagram showing the data service device of Figure 1. FIG. 3 is a flowchart showing a data service method using a natural language processing algorithm of a data service device according to a first embodiment of the present invention. FIG. 4 is a flowchart showing a data service method using a natural language processing algorithm of a data service system according to a first embodiment of the present invention. Figure 5 is a first screen example showing the answer to a user's natural language query according to the data service method of Figure 3. FIG. 6 is a schematic diagram showing an interactive data service system using a natural language processing algorithm according to a second embodiment of the present invention. FIG. 7 is a flowchart showing an interactive data service method using a natural language processing algorithm of an interactive data service device according to a second embodiment of the present invention. Figure 8 is a detailed flowchart of the step of changing to the meta-query of Figure 7. FIGS. 9 and FIGS. 10 are second screen example diagrams showing the answer to a user's natural language query according to the interactive data service method of FIG. 7. FIGS. 11 to 13 are examples of third screens showing answers to a user's natural language query according to the interactive data service method of FIG. 7. It should be noted that in the following description, only the parts necessary for understanding the embodiments of the present invention are explained, and the description of other parts will be omitted to the extent that it does not deviate from the gist of the present invention. The terms and words used in the specification and claims described below should not be interpreted as being limited to their ordinary or dictionary meanings, but should be interpreted in a meaning and concept consistent with the technical spirit of the invention, based on the principle that the inventor can appropriately define the concept of the terms to best describe his invention. Accordingly, the embodiments described in this specification and the configurations illustrated in the drawings are merely preferred embodiments of the invention and do not represent all aspects of the technical spirit of the invention; therefore, it should be understood that various equivalents and modifications capable of replacing them may exist at the time of filing this application. Hereinafter, embodiments of the present invention will be described in more detail with reference to the attached drawings. First embodiment FIG. 1 is a schematic diagram showing a data service system using a natural language processing algorithm according to a first embodiment of the present invent