Automatically mapping natural language commands to service APIs
US-10922357-B1 · Feb 16, 2021 · US
US2022012018A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2022012018-A1 |
| Application number | US-202016927196-A |
| Country | US |
| Kind code | A1 |
| Filing date | Jul 13, 2020 |
| Priority date | Jul 13, 2020 |
| Publication date | Jan 13, 2022 |
| Grant date | — |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A natural language command from an operator is received. The command regards a task that a software system is to execute. A programming language in which to program the task is determined by analyzing a plurality of factors regarding the task and the software system. Code is output in the programming language that executes the task.
Opening claim text (preview).
What is claimed is: 1 . A computer-implemented method comprising: receiving a natural language command from an operator regarding a task that a software system is to execute; determining a programming language in which to program the task by analyzing a plurality of factors regarding the task and the software system; and outputting code in the programming language that executes the task. 2 . The computer-implemented method of claim 1 , wherein the task is a two-part task and the programming language is a first programming language and the code is a first portion of code in the first programming language that executes a first part of the two-part task, further comprising: determining a second programming language in which to program a second part of the two-part task by analyzing the plurality of factors; and outputting a second portion of code in the second programming language that executes the second part of the two-part task. 3 . The computer-implemented method of claim 1 , wherein a factor of the plurality of factors includes a competence level of a maintenance staff for the software system regarding the programming language. 4 . The computer-implemented method of claim 1 , wherein the plurality of factors includes analyses on how strengths and weaknesses of the programming language align with the task. 5 . The computer-implemented method of claim 1 , wherein a factor of the plurality of factors is a predominant programming language of the software system. 6 . The computer-implemented method of claim 1 , further comprising adding the command to documentation of the software system. 7 . The computer-implemented method of claim 1 , further comprising determining that the command relates to the task by identifying an intent of the command, wherein a set of natural language words of the command do not reference the task. 8 . The computer-implemented method of claim 1 , wherein the command includes a plurality of discrete steps. 9 . The computer-implemented method of claim 8 , wherein the task is not aligned with the plurality of discrete steps. 10 . A system comprising: a processor; and a memory in communication with the processor, the memory containing instructions that, when executed by the processor, cause the processor to: receive a natural language command from an operator regarding a task that a software system is to execute; determine a programming language in which to program the task by analyzing a plurality of factors regarding the task and the software system; and output code in the programming language that executes the task. 11 . The system of claim 10 , wherein the task is a two-part task and the programming language is a first programming language and the code is a first portion of code in the first programming language that executes a first part of the two-part task, the memory containing additional instructions that, when executed by the processor, cause the processor to: determine a second programing language in which to program a second part of the two-part task by analyzing the plurality of factors; and output a second portion of code in the second programming language that executes the second part of the two-part task. 12 . The system of claim 10 , the plurality of factors includes: a competence level of a support staff for the software system regarding the programming language; analyses on how strengths and weaknesses of the programming language align with the task; and a predominant programming language of the software system. 13 . The system of claim 10 , the memory containing additional instructions that, when executed by the processor, cause the processor to add a version of the command to documentation of the software system. 14 . The system of claim 10 , the memory containing additional instructions that, when executed by the processor, cause the processor to determine that the command relates to the task by comparing an intent of the command with capabilities of the programming language, wherein a set of natural language words of the command do not reference the task. 15 . The system of claim 10 , wherein the command includes a plurality of discrete steps, and the task is not aligned with the plurality of discrete steps. 16 . A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to: receive a natural language command from an operator regarding a task that a software system is to execute; determine a programming language in which to program the task by analyzing a plurality of factors regarding the task and the software system; and output code in the programming language that executes the task. 17 . The computer program product of claim 16 , wherein the task is a two-part task and the programming language is a first programming language and the code is a first portion of code in the first programming language that executes a first part of the two-part task, the computer readable storage medium containing additional program instructions that, when executed by the computer, cause the computer to: determine a second programing language in which to program a second part of the two-part task by analyzing the plurality of factors; and output a second portion of code in the second programming language that executes the second part of the two-part task. 18 . The computer program product of claim 16 , wherein the plurality of factors includes: a competence level of a support staff for the software system regarding the programming language; analyses on how strengths and weaknesses of the programming language align with the task; and a predominant programming language of the software system. 19 . The computer program product of claim 16 , the computer readable storage medium containing additional program instructions that, when executed by the computer, cause the computer to add a version of the command to documentation of the software system. 20 . The computer program product of claim 16 , the computer readable storage medium containing additional program instructions that, when executed by the computer, cause the computer to determine that the command relates to the task by comparing an intent of the command with capabilities of the programming language, wherein a set of natural language words of the command do not reference the task.
Machine learning · CPC title
Creation or generation of source code · CPC title
Thesauruses; Synonyms · CPC title
Semantic analysis · CPC title
Performance of employee with respect to a job function · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.