# US 12,602,373 B2 · System and method for generating database queries based on natural language input > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,602,373 B2 - Document ID: US12602373B2 - Status: Granted - Kind: B2 - Application number: 18/976,323 - Filed: 2024-12-10 - Published: 2025-06-19 - Granted: 2026-04-14 - Earliest claimed: 2023-12-19 - Assignees: Shopee IP Singapore Private Limited - Applicants: Shopee IP Singapore Private Limited - Inventors: Bin Fu; Hao-Tong Ye - Web page: https://patentgrep.com/patent/US12602373B2 ## CPC - G06F 16/2423: {Interactive query statement specification based on a database schema} - G06F 16/242: Query formulation - G06F 16/243: {Natural language query formulation} - G06F 16/24522: {Translation of natural language queries to structured queries} - G06F 16/3329: Natural language query formulation - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Provided herein are systems, methods, and computer-readable media for generating one or more database queries based on a natural language input data. An example method comprises configuring, using a conversational artificial intelligence (AI) editing module, information for a task. Moreover, the method may further comprise parsing the configured information based on a database schema to obtain a parsed database schema. Further, the method may further comprise generating, using a natural language question-answering system, one or more database queries based on the parsed database schema and natural language input data. ## Claims ### Claim 1 A method for generating one or more database queries based on natural language input data, the method comprising: configuring, using a conversational artificial intelligence (AI) editing module, information for completing a task-oriented dialogue based on natural language input data; parsing the configured information based on a database schema; generating a parsed database schema based on the parsed configured information; generating, using a natural language question-answering system, one or more database queries based on the parsed database schema and the natural language input data; obtaining at least one database entry from one or more databases by executing the one or more database queries; comparing the at least one database entry with the configured information; and generating a clarification prompt based on the comparison. ### Claim 2 (depends on 1) The method of claim 1, wherein the natural language question-answering system is a table question-answering (TableQA) system or a knowledge-graph question-answering system. ### Claim 3 (depends on 1) The method of claim 1, wherein the at least one database entry comprises a table, the table having at least one row and at least one column. ### Claim 4 (depends on 3) The method of claim 3, further comprising: determining whether there are multiple possible values based on the natural language input data and the table of the at least one database entry. ### Claim 5 (depends on 4) The method of claim 4, further comprising: determining there are multiple possible values; and generating, using the natural language question-answering system, a clarification information based on the natural language input data. ### Claim 6 (depends on 1) The method of claim 1, wherein the natural language input data comprises at least one of a text-based data, an audio data, or any combination thereof. ### Claim 7 (depends on 1) The method of claim 1, wherein the database schema is Structured Query Language (SQL) database schema and the one or more database queries includes a SQL query. ### Claim 8 (depends on 1) The method of claim 1, further comprising: parsing, using a resource description framework schema, the natural language input data, wherein the generated one or more database queries includes a SPARQL query. ### Claim 9 (depends on 1) The method of claim 1, wherein the conversational AI editing module comprises a chatbot dialogue flow editor module. ### Claim 10 (depends on 1) The method of claim 1, wherein generating the clarification prompt comprises: revising the configured information, wherein the clarification prompt is based on the revised configured information. ### Claim 11 A system for generating one or more database queries based on natural language input data, the system comprises: at least one memory storing instruction; and at least one processor coupled to the at least one memory, the at least one processor is configured to execute the instructions to: configure information for completing a task-oriented dialogue based on natural language input data; parse the configured information based on a database schema; generate a parsed database schema based on the parsed configured information; generate, using a natural language question-answering system, one or more database queries based on the parsed database schema and the natural language input data; obtain at least one database entry from one or more databases by executing the one or more database queries; compare the at least one database entry with the configured information; and generate a clarification prompt based on the comparison. ### Claim 12 (depends on 11) The system of claim 11, wherein the natural language question-answering system is a table question-answering (Table QA) system or a knowledge-graph question-answering system. ### Claim 13 (depends on 11) The system of claim 11, wherein the at least one database entry comprises a table, the table having at least one row and at least one column. ### Claim 14 (depends on 13) The system of claim 13, wherein the at least one processor is further configured to execute the instructions to: determine whether there are multiple possible values based on the natural language input data and the table of the at least one database entry. ### Claim 15 (depends on 14) The system of claim 14, wherein the at least one processor is further configured to execute the instructions to: determine there are multiple possible values; and generate, using the natural language question-answering system, a clarification information in response to the natural language input data. ### Claim 16 (depends on 14) The system of claim 14, wherein the natural language input data comprises a text-based data, an audio data, or any combination thereof. ### Claim 17 (depends on 14) The system of claim 14, wherein the database schema is Structured Query Language (SQL) database schema and the one or more database queries include a SQL query. ### Claim 18 (depends on 14) The system of claim 14, wherein the at least one processor is further configured to execute the instructions to: parse, using a resource description framework schema, the natural language input data, wherein the generated one or more database queries include a SPARQL query. ### Claim 19 (depends on 14) The system of claim 14, wherein to generate the clarification prompt, the at least one processor is further configured to execute the instructions to: revise the configured information, wherein the clarification prompt is based on the revised configured information. ### Claim 20 A non-transitory computer-readable medium comprising program instructions, which, when executed by one or more processors, cause the one or more processors to perform operations comprising: configuring information for completing a task-oriented dialogue based on natural language input data; parsing the configured information based on a database schema; generating a parsed database schema based on the parsed configured information; generating, using a natural language question-answering system, one or more database queries based on the parsed database schema and the natural language input data; retrieving, from an associated database, at least one database entry by executing the one or more database queries; comparing the at least one database entry with the information for the task-oriented dialogue; and generating a clarification prompt based on the comparison.