Content generation method based on multimedia content, device and medium

A computer device, comprising:

• a processor and a memory, wherein the memory stores computer-readable instructions executable by the processor;
• the processor is configured to execute the computer-readable instructions stored in the memory;
• and
• when the computer-readable instructions are executed by the processor, the processor executes a content generation method based on a multimedia content, which comprises:
• in response to a user uploading a multimedia content to a server, parsing the multimedia content to obtain multiple pieces of content text information by calling a parsing plug-in corresponding to a type of the multimedia content, wherein the type of the multimedia content comprises a document type or a video type;
• storing the content text information into a vector database in a vector data form according to a text association degree between the content text information, wherein vector data in the vector database have an index relationship related to the text association degree;
• in response to receiving question information associated with the multimedia content, querying vector data matching the question information from the vector database, wherein the vector data matching the question information comprises a first vector data;
• determining additional vector data that does not match the question information but that is linked to the first vector data through the index relationship in the vector database, wherein the additional vector data comprises a second vector data;
• and
• inputting a subset of the content text information and the question information into an artificial intelligence model to obtain an answer result associated with the multimedia content, the subset of the context text information corresponding to the first vector data and the second vector data.

A non-transient computer-readable storage medium, storing computer programs, wherein when the computer programs are operated by a computer device, the computer device executes a content generation method based on a multimedia content, which comprises:

• in response to a user uploading a multimedia content to a server, parsing the multimedia content to obtain multiple pieces of content text information by calling a parsing plug-in corresponding to a type of the multimedia content, wherein the type of the multimedia content comprises a document type or a video type;
• storing the content text information into a vector database in a vector data form according to a text association degree between the content text information, wherein vector data in the vector database have an index relationship related to the text association degree;
• in response to receiving question information associated with the multimedia content, querying vector data matching the question information from the vector database, wherein the vector data matching the question information comprises a first vector data;
• determining additional vector data that does not match the question information but that is linked to the first vector data through the index relationship in the vector database, wherein the additional vector data comprises a second vector data;
• and
• inputting a subset of the content text information and the question information into an artificial intelligence model to obtain an answer result associated with the multimedia content, the subset of the context text information corresponding to the first vector data and the second vector data.