Machine learning for technical tool selection

Patent metadata

Field	Value
Publication number	US-11514340-B2
Application number	US-201916678564-A
Country	US
Kind code	B2
Filing date	Nov 8, 2019
Priority date	Nov 8, 2019
Publication date	Nov 29, 2022
Grant date	Nov 29, 2022

Abstract

Methods and systems for selecting a tool for a project is described. In an example, a processor can run a machine learning model to generate a set of requirements to implement a project. The processor can identify a keyword from the set of requirements. The processor can search for the keyword on a search engine. The processor can receive a search result from the search engine corresponding to the keyword. The processor can identify, based on the search result, a tool that can be used to implement the project, where the tool can be in compliance with the set of requirements.

First claim

What is claimed is:

1. A system comprising:
a memory;
a processor configured to be in communication with the memory, and the processor being configured to:
run a machine learning model to generate a set of requirements to implement a project;
identify a keyword from the set of requirements;
search for the keyword on a search engine;
receive a search result from the search engine corresponding to the keyword; and
identify, based on the search result, a tool that can be used to implement the project, wherein the tool is in compliance with the set of requirements.

2. The system of claim 1 , wherein the processor is configured to:
deploy an agent to a user device;
receive, from the agent, context data representing a context of the project and the user device;
wherein the processor is configured to run the machine learning model with the context data.

3. The system of claim 2 , wherein the context data is desensitized.

4. The system of claim 2 , wherein the context data comprises at least one user preference.

5. The system of claim 1 , wherein the processor is configured to train the machine learning model using historical data.

6. The system of claim 1 , wherein the processor is configured to retrain the machine learning model using at least one of the set of requirements, the keyword, the search result, and the identified tool.

7. The system of claim 1 , wherein the processor is configured to execute natural language processing (NLP) techniques on the search result to identify the tool.

8. A computer-implemented method comprising:
running, by a processor, a machine learning model to generate a set of requirements to implement a project;
identifying, by the processor, a keyword from the set of requirements;
searching, by the processor, for the keyword on a search engine;
receiving, by the processor, a search result from the search engine corresponding to the keyword; and
identifying, by the processor, based on the search result, a tool that can be used to implement the project, wherein the tool is in compliance with the set of requirements.

9. The computer-implemented method of claim 8 , further comprising:
deploying, by the processor, an agent to a user device;
receiving, by the processor, from the agent, context data representing a context of the project and the user device;
wherein running the machine learning model comprises running, by the processor, the machine learning model with the context data.

10. The computer-implemented method of claim 9 , wherein the context data is desensitized.

11. The computer-implemented method of claim 9 , wherein the context data comprises at least one user preference.

12. The computer-implemented method of claim 8 , further comprising training, by the processor, the machine learning model using historical data.

13. The computer-implemented method of claim 8 , further comprising retraining, by the processor, the machine learning model using at least one of the set of requirements, the keyword, the search result, and the identified tool.

14. The computer-implemented method of claim 8 , further comprising executing, by the processor, natural language processing (NLP) techniques on the search result to identify the tool.

15. A computer program product for selecting a tool for a project, the computer program product comprising a computer readable storage device medium having program instructions embodied therewith, the program instructions executable by a processor of a device to cause the device to:
run a machine learning model to generate a set of requirements to implement a project;
identify a keyword from the set of requirements;
search for the keyword on a search engine;
receive a search result from the search engine corresponding to the keyword; and
identify, based on the search result, a tool that can be used to implement the project, wherein the tool is in compliance with the set of requirements.

16. The computer program product of claim 15 , wherein the program instructions are further executable by the processor of the device to cause the device to:
deploy an agent to a user device;
receive, from the agent, context data representing a context of the project and the user device;
wherein running the machine learning model comprises running, by the processor, the machine learning model with the context data.

17. The computer program product of claim 16 , wherein context data is desensitized.

18. The computer program product of claim 15 , wherein the program instructions are further executable by the processor of the device to cause the device to train the machine learning model using historical data.

19. The computer program product of claim 15 , wherein the program instructions are further executable by the processor of the device to cause the device to retrain the machine learning model using at least one of the set of requirements, the keyword, the search result, and the identified tool.

20. The computer program product of claim 15 , wherein the program instructions are further executable by the processor of the device to cause the device to execute natural language processing (NLP) techniques on the search result to identify the tool.

Assignees

• IBM

Inventors

• Zhao Wen Rui
• Zhao Yu
• Zhang li ni
• Luo Lan
• Jiang jing bo
• Chen Li Long
• Jiang Li

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/90332

  Natural language query formulation or dialogue systems · CPC title

• G06N5/04 Primary

  Inference or reasoning models · CPC title