Automated enhancement of metadata in media program database using embedded vectors
AssigneeDISH Network Technologies India Private Limited
InventorsMelvin Perinchery, Shanmugam Ramaswamy
Life of this patent
Estimating the term…
Abstract
Systems, devices and automated processes are described for automated enhancement of metadata in a database of information about movies, television shows or other media programs. Gaps or errors in metadata describing the different programs in the database can be corrected using a digital architecture in which one or more sources are queried for missing information. Queries may be directed toward a large language model (LLM) or other artificial intelligence (AI) engine, if desired, that represents information about the media programs as embedded vectors that can be compared to query data to identify additional information about the media programs.
Claims15
An automated process performed by a computer system to automatically update information in a database of media program information that is stored on a non-transitory digital storage, the automated process comprising:
- identifying, by querying the database of media programs by a first processor of the computer system, one or more missing data fields in metadata about a particular media program that is stored in the database;
- automatically formatting, by the first processor of the computer system, a query related to the one or more missing data fields to obtain additional information about the media program from an artificial intelligence (AI) engine executing on a second processor of the computer system, wherein the AI engine comprises embedded vectors representing data previously obtained about the particular media program;
- forwarding the query from the first processor to the second processor;
- in response to the query, the second processor identifying additional information corresponding to the one or more missing data fields based upon the embedded vectors, wherein the identifying comprises the second processor converting the query from a natural language format to one or more query vectors and comparing the query vectors to the embedded vectors by the second processor to identify one or more embedded vectors that are most relevant to the query vectors;
- providing, by the AI engine, the data previously obtained about the particular media program to the first processor in response to the query;
- updating, by the first processor, the missing data fields in the metadata stored in the database about the particular media program with the additional information data received from the AI engine;
- and
- subsequently providing the updated metadata about the particular media program from the database for publication in an electronic program guide.
A computer system comprising a first processor and a second processor, a non-transitory digital storage and an interface to a network, wherein the non-transitory digital storage comprises computer-executable instructions stored thereon that, when executed by the processors, perform an automated process comprising:
- identifying, by querying the database of media programs by the first processor of the computer system, one or more missing data fields in metadata about a particular media program that is stored in the database;
- automatically formatting, by the first processor of the computer system, a query related to the one or more missing data fields to obtain additional information about the media program from an artificial intelligence (AI) engine executing on the second processor of the computer system, wherein the AI engine comprises embedded vectors representing data previously obtained about the particular media program;
- forwarding the query from the first processor to the second processor;
- in response to the query, the second processor identifying additional information corresponding to the one or more missing data fields based upon the embedded vectors, wherein the identifying comprises the second processor converting the query from a natural language format to one or more query vectors and comparing the query vectors to the embedded vectors by the second processor to identify one or more embedded vectors that are most relevant to the query vectors;
- providing, by the AI engine, the data previously obtained about the particular media program to the first processor in response to the query;
- updating, by the first processor, the missing data fields in the metadata stored in the database about the particular media program with the data received from the AI engine;
- and
- subsequently providing the updated metadata about the particular media program from the database for publication in an electronic program guide.
Dependencies are inferred from the claim text.