US 2025/0156404 A1Published application

Enhanced methodology for optimizing data query prompts

AssigneeHitachi, Ltd.

InventorsTakuya HABARA, Shoji YUNOKI, Sudhanshu GAUR

Life of this patent

Estimating the term…

Loading patent…

Abstract

A search query generation method for information retrieval, the method comprising receiving, by a processor, a first query issued by a user; extracting, by the processor, a plurality of field status items associated with the first query; extracting, by the processor, first schema information associated with the plurality of field status items; adding, by the processor, the plurality of field status items and the first schema information as contextual information to the first query to generate a second query, generating, by the processor, an information search code based on the second query; and executing, by the processor, the information search code to retrieve information associated with the first query from a plurality of data source systems.

Claims20

Dependent claims

A search query generation method for information retrieval, the method comprising:

receiving, by a processor, a first query issued by a user;
extracting, by the processor, a plurality of field status items associated with the first query using a trained artificial intelligence (TAI) model, wherein the plurality of field status items is extracted from real-time field status information comprising at least one of employee information, order information, work order information, or manufacturing execution information;
extracting, by the processor, first schema information associated with the plurality of field status items using the TAI model, wherein the first schema information comprises at least one of data structure information of data tables, files, or application program interfaces that access data stored across the plurality of data source systems;
adding, by the processor, the plurality of field status items and the first schema information as contextual information to the first query to generate a second query, wherein the contextual information enhances a specificity of the query to improve the information retrieval;
generating, by the processor, an information search code based on the second query using the TAI model;
and
executing, by the processor, the information search code to retrieve information associated with the first query from a plurality of data source systems.

4 more elements

A search query generation system for information retrieval, the system comprising:

a plurality of data source systems;
and
a processor in communication with the plurality of data source systems, wherein the processor is configured to:
receive a first query issued by a user;
extract a plurality of field status items associated with the first query using a trained artificial intelligence (TAI) model, wherein the plurality of field status items is extracted from real-time field status information, including at least one of employee information, order information, work order information, and manufacturing execution information;
extract first schema information associated with the plurality of field status items using the TAI model, wherein the first schema information comprises at least data structure information of data tables, files, and application program interfaces that access data stored across the plurality of data source systems;
add the plurality of field status items and the first schema information as contextual information to the first query to generate a second query, wherein the contextual information enhances the specificity of the query to improve the information retrieval;
generate an information search code based on the second query using the TAI model;
and
execute the information search code to retrieve information associated with the first query from the plurality of data source systems.

7 more elements

Dependencies are inferred from the claim text.