Method for solving problem, computing system and program product

Patent metadata

Field	Value
Publication number	US-11599801-B2
Application number	US-202016825389-A
Country	US
Kind code	B2
Filing date	Mar 20, 2020
Priority date	Feb 27, 2020
Publication date	Mar 7, 2023
Grant date	Mar 7, 2023

Abstract

Embodiments of the present disclosure provide a method for solving a problem, a computing system and a program product. A method for solving a problem includes determining information related to a to-be-solved problem; acquiring, based on the information, knowledge elements that can be used for the to-be-solved problem from a knowledge repository, the knowledge repository storing: solved problems, at least one executable task related to the solved problems, at least one processing flow for implementing the at least one executable task, and a corresponding function module included in the at least one processing flow; and determining, based at least on the acquired knowledge elements, a solution to the to-be-solved problem. By such arrangements, automatic problem solving can be achieved in a faster, simpler way with a lower cost through division of the repository and the knowledge elements.

First claim

What is claimed is:

1. A method for solving a problem, comprising:
determining information related to a to-be-solved problem;
acquiring, based on the information related to the to-be-solved problem, knowledge elements that are used for the to-be-solved problem from a knowledge repository, wherein the knowledge repository stores: solved problems, at least one executable task related to the solved problems, at least one processing flow for implementing the at least one executable task, and a corresponding function module included in the at least one processing flow;
determining, based at least on the acquired knowledge elements, a solution to the to-be-solved problem;
updating the knowledge repository based on the solution to the to-be-solved problem; and
automatically utilizing the updated knowledge repository to determine a solution to a subsequent to-be-solved problem;
wherein acquiring the knowledge elements comprises:
acquiring, based on the information related to the to-be-solved problem, a set of knowledge elements including: a target executable task related to a target solved problem matching the to-be-solved problem, a target processing flow for implementing the target executable task, and a corresponding function module included in the target processing flow from the knowledge repository.

2. The method of claim 1 , wherein the information related to the to-be-solved problem comprises a problem description of the to-be-solved problem, and wherein acquiring the knowledge elements further comprises:
searching, based on the problem description of the to-be-solved problem, the knowledge repository for the target solved problem matching the to-be-solved problem; and
acquiring, according to a finding of the target solved problem matching the to-be-solved problem, the target executable task related to the target solved problem matching the to-be-solved problem, the target processing flow for implementing the target executable task, and the corresponding function module included in the target processing flow from the knowledge repository as at least a portion of the set of knowledge elements.

3. The method of claim 1 , wherein the information related to the to-be-solved problem comprises a task description of a source executable task related to the to-be-solved problem, and wherein acquiring the knowledge elements further comprises:
searching, based on the task description of the source executable task, the knowledge repository for the target executable task matching the source executable task; and
acquiring, according to a finding of the target executable task matching the source executable task, the target processing flow for implementing the target executable task, and the corresponding function module included in the target processing flow from the knowledge repository as at least a portion of the set of knowledge elements.

4. The method of claim 3 , wherein determining the information related to the to-be-solved problem comprises:
providing to a user, according to a failure to find the target solved problem matching the to-be-solved problem from the knowledge repository, a request to designate the source executable task related to the to-be-solved problem; and
receiving the task description of the source executable task related to the to-be-solved problem.

5. The method of claim 1 , wherein the information related to the to-be-solved problem comprises a function description of a source function module included in a source processing flow which is used for implementing a source executable task related to the to-be-solved problem, and wherein acquiring the knowledge elements further comprises:
searching, based on the function description of the source function module, the knowledge repository for a target function module matching the source function module; and
acquiring, according to a finding of the target function module matching the source function module, the target function module from the knowledge repository as at least a portion of the set of knowledge elements.

6. The method of claim 5 , wherein determining the information related to the to-be-solved problem comprises:
providing to a user, according to a failure to find the target executable task matching the source executable task from the knowledge repository, a request to designate the source function module included in the source processing flow; and
receiving the function description of the source function module included in the source processing flow.

7. The method of claim 1 , wherein determining the solution to the to-be-solved problem comprises:
determining the solution to the to-be-solved problem to comprise a source executable task related to the to-be-solved problem, a source processing flow for implementing the source executable task, and a corresponding function module included in the source processing flow.

8. The method of claim 7 , further comprising:
storing the to-be-solved problem, the source executable task, the source processing flow, and the corresponding function module included in the source processing flow to the knowledge repository as the knowledge elements.

9. The method of claim 1 , further comprising:
determining a data format related to raw data to be processed for the to-be-solved problem, wherein acquiring the knowledge elements further comprises determining the knowledge elements from the knowledge repository based on the data format, so that the solution to the to-be-solved problem corresponding to the knowledge elements is suitable for the data format.

10. The method of claim 1 , wherein the to-be-solved problem and the solved problems comprise abstract problems, wherein the at least one executable task comprises a machine learning task, and wherein the at least one processing flow comprises an algorithm pipeline.

11. A computing system, comprising:
at least one processor; and
at least one memory storing computer program instructions, wherein the at least one memory and the computer program instructions are configured to control the at least one processor to perform actions, the actions comprising:
determining information related to a to-be-solved problem;
acquiring, based on the information related to the to-be-solved problem, knowledge elements that are used for the to-be-solved problem from a knowledge repository, wherein the knowledge repository stores: solved problems, at least one executable task related to the solved problems, at least one processing flow for implementing the at least one executable task, and a corresponding function module included in the at least one processing flow;
determining, based at least on the acquired knowledge elements, a solution to the to-be-solved problem;
updating the knowledge repository based on the solution to the to-be-solved problem; and
automatically utilizing the updated knowledge repository to determine a solution to a subsequent to-be-solved problem;
wherein acquiring the knowledge elements comprises:
acquiring, based on the information related to the to-be-solved problem, a set of knowledge elements including: a target executable task related to a target solved problem matching the to-be-solved problem, a target processing flow for implementing the target executable task, and a corresponding function module included in the target processing flow from the knowledge repository.

12. The computing system of claim 11 , wherein the information related to the to-be-solved problem comprises a problem description of the to-be-solved problem, and wherein acquiring the knowledge elements further comprises:
searching, based on the problem description of the to-be-solved problem, the knowledge repository fo

Assignees

• Emc Ip Holding Co Llc

Inventors

• Nie Yuhong
• Wong Wuichak
• Li Sanping
• Tang Xuwei

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F16/367

  Ontology · CPC title

• G06N5/04 Primary

  Inference or reasoning models · CPC title

• G06N5/022 Primary

  Knowledge engineering; Knowledge acquisition · CPC title

• G06F16/3329 Primary

  Natural language query formulation · CPC title