Mass file retrieval method and apparatus based on AI training platform, and device
AssigneeInspur Suzhou Intelligent Technology Co., Ltd.
InventorGuiyang Ji
Life of this patent
Estimating the term…
Abstract
A mass file retrieval method and apparatus based on an AI training platform, and a device. The method includes: an AI training platform acquiring a retrieval task issued by a user, the AI training platform generating a retrieval thread flow according to the retrieval task, and controlling a service logic of a retrieval process according to the retrieval thread flow; and the AI training platform, performing sequential encoding on files in a database in units of folders, generating ordered queue folders, extracting retrieval key words from the retrieval task, and performing keyword retrieval on each ordered queue folder by combining a binary search and depth-first traversal.
Claims18
A mass file retrieval method based on an artificial intelligence training platform, comprising:
- S1, acquiring, by the artificial intelligence training platform, a retrieval task issued by a user;
- S2, generating, by the artificial intelligence training platform, a retrieval thread flow based on the retrieval task, and controlling service logic of a retrieval process based on the retrieval thread flow;
- and
- S3, performing, by the artificial intelligence training platform, sequential encoding on files in a database in units of folders to generate ordered queue folders, extracting a retrieval keyword from the retrieval task, and performing keyword retrieval on each ordered queue folder by a combination of binary search and depth-first traversal,
- wherein step S2 comprises:
- S21, starting, by the artificial intelligence training platform, a retrieval thread;
- S22, determining, upon completion of each retrieval, whether a retrieval times threshold is met;
- in response to the retrieval times threshold being met, performing step S23;
- and
- in response to the retrieval times threshold being not met, performing step S24;
- S23, determining whether the retrieval task is completed;
- in response to the retrieval task being completed, performing step S28;
- and
- in response to the retrieval task being not completed, performing step S25;
- S24, continuing retrieval, and returning to step S22;
- S25, returning retrieval content, pausing the retrieval, and determining whether a total retrieval duration exceeds a retrieval duration threshold;
- in response to the total retrieval duration exceeding the retrieval duration threshold, performing step S26;
- and
- in response to the total retrieval duration not exceeding the retrieval duration threshold, performing step S27;
- S26, determining that the retrieval times out, and ending the retrieval;
- S27, waking up the retrieval, and returning to the step S24;
- and
- S28, returning the retrieval content, and ending the retrieval.
A device, comprising a processor and a memory, wherein the memory is configured to store a computer program executable on the processor;
- and when the computer program is executed by the processor, causes the processor to perform:
- S1 of setting the artificial intelligence training platform to acquire a retrieval task issued by a user;
- S2 of setting the artificial intelligence training platform to generate a retrieval thread flow based on the retrieval task, and control service logic of a retrieval process based on the retrieval thread flow;
- and
- S3 of setting the artificial intelligence training platform to perform sequential encoding on files in a database in units of folders to generate ordered queue folders, extract a retrieval keyword from the retrieval task, and perform keyword retrieval on each ordered queue folder by combining a binary search and depth-first traversal,
- wherein step S2 of setting the artificial intelligence training platform to generate a retrieval thread flow based on the retrieval task, and control service logic of a retrieval process based on the retrieval thread flow, comprises:
- S21, starting, by the artificial intelligence training platform, a retrieval thread;
- S22, determining, upon completion of each retrieval, whether a retrieval times threshold is met;
- in response to the retrieval times threshold being met, performing step S23;
- and
- in response to the retrieval times threshold being not met, performing step S24;
- S23, determining whether the retrieval task is completed;
- in response to the retrieval task being completed, performing step S28;
- and
- in response to the retrieval task being not completed, performing step S25;
- S24, continuing retrieval, and returning to step S22;
- S25, returning retrieval content, pausing the retrieval, and determining whether a total retrieval duration exceeds a retrieval duration threshold;
- in response to the total retrieval duration exceeding the retrieval duration threshold, performing step S26;
- and
- in response to the total retrieval duration not exceeding the retrieval duration threshold, performing step S27;
- S26, determining that the retrieval times out, and ending the retrieval;
- S27, waking up the retrieval, and returning to the step S24;
- and
- S28, returning the retrieval content, and ending the retrieval.
Dependencies are inferred from the claim text.