Data query method and related apparatus

A data query apparatus, the apparatus comprising:

• processing circuitry configured to:
• obtain a first query result of a first database in response to a query request, the first database storing data of a first time window;
• obtain a second query result of a second database when the first query result does not meet a preset check condition, the second database storing data of a second time window, a start time of the second time window being after a start time of the first time window;
• and
• generate a target query result based on at least one of the first query result or the second query result, wherein
• an update frequency of the second database is higher than an update frequency of the first database;
• the second database includes a vector database and a document database, associations between the vector database and the document database being indicated in an index file;
• and
• the processing circuitry is configured to:
• add a second service document that is generated within the second time window to the document database;
• and
• slice the second service document to obtain a plurality of document slices and store a plurality of slice vectors corresponding to the plurality of document slices in the vector database.

A non-transitory computer-readable storage medium, storing instructions which when executed by a processor cause the processor to perform:

• obtaining a first query result of a first database in response to a query request, the first database storing data of a first time window;
• obtaining a second query result of a second database when the first query result does not meet a preset check condition, the second database storing data of a second time window, a start time of the second time window being after a start time of the first time window;
• and
• generating, by processing circuitry, a target query result based on at least one of the first query result or the second query result, wherein
• an update frequency of the second database is higher than an update frequency of the first database;
• the second database includes a vector database and a document database, associations between the vector database and the document database being indicated in an index file;
• and
• the instructions when executed by the processor further cause the processor to perform:
• adding, to the document database, a second service document generated within the second time window;
• and
• slicing the second service document to obtain a plurality of document slices, and storing a plurality of slice vectors corresponding to the plurality of document slices in the vector database.