Programming in a precise syntax using natural language

• US 10,606,563 B2
• Filed: 03/29/2019
• Issued: 03/31/2020
• Est. Priority Date: 11/15/2011
• Status: Active Grant

• Current Assignee: Wolfram Alpha LLC (Wolfram Research Incorporated)
• Original Assignee: Wolfram Alpha LLC (Wolfram Research Incorporated)
• Inventors: Wolfram, Stephen, Gray, Theodore W.
• Primary Examiner(s): Das, Chameli
• Assistant Examiner(s): MacAsiano, Joanne G
• Application Number:
  US16/370,336
• Publication Number:
  US 20190227773A1
• Time in Patent Office: 368 Days
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 8/30 Creation or generation of source code

Abstract

A method facilitates development of instructions in a precise syntax, such as built-in functions of a computational system such as a spreadsheet application, using natural language (NL) input. A user may enter NL input in a workspace. An NL processing system may process the NL input to generate instruction(s) in a precise syntax that corresponds to the NL input. The instruction(s) in the precise syntax then may be included in the workspace.

Claims

1. A method, comprising:

receiving, via a user interface device, user input for inclusion in a workspace document, wherein the workspace document is displayed in a graphical user interface of a software development application that, when executed by one or more computer processors, is configured to evaluate instructions in a precise syntax;

after receiving the user input, displaying, on a display device, the user input in the workspace document;

determining, at the one or more computer processors, whether at least a portion of the user input i) is in the precise syntax, or ii) is in an imprecise syntax;

when it is determined that at least the portion of the user input is in the precise syntax,

evaluating, at the one or more computer processors, at least the portion of the user input according to the precise syntax;

when it is determined that at least the portion of the user input is in the imprecise syntax,

generating, at the one or more computer processors, an application programming interface (API) call that includes i) the at least the portion of the user input in the imprecise syntax, and ii) information indicating a result of a previous evaluation, by the software development application, of a user input previously entered into the workspace document,

sending, by the one or more computer processors, the API call to a natural language processing (NLP) system implemented by one or more computer processors,

processing, at the NLP system, the API call to determine the instruction in the precise syntax that corresponds to the user input in the imprecise syntax, wherein the instruction in the precise syntax is for generating a modification of the result of the previous evaluation,

formatting, at the NLP system, the instruction in the precise syntax according to a format recognized by the software development application,

receiving, at the one or more computer processors, the instruction in the precise syntax from the NLP system, wherein receiving the instruction in the precise syntax from the NLP system is responsive to sending the API call to the NLP system,

including, by one or more computer processors, the instruction in the precise syntax in the workspace document such that the software development application executed by one or more computer processors can evaluate the instruction in the precise syntax, and

after including the instruction in the precise syntax in the workspace document, evaluating, at one or more computing devices, the instruction in the precise syntax.

2. The method of claim 1, wherein determining whether the at least a portion of the user input i) is in the precise syntax, or ii) is in the imprecise syntax, includes:

analyzing the user input to determine if the user input includes a user indication, in the precise syntax, that indicates whether the at least the portion of the user input i) is in the precise syntax, or ii) is in an imprecise syntax.

3. The method of claim 1, wherein:

the user input is first user input;

the instruction in the precise syntax is a first instruction in the precise syntax;

the method further comprises;

receiving, via the user interface device, second user input for inclusion in the workspace document, the second user input including a second instruction in the precise syntax,

after receiving the second user input, displaying, on the display device, the second user input in the workspace document, and

after including the second instruction in the precise syntax in the workspace document, evaluating, at one or more computing devices, the second instruction in the precise syntax;

the first user input indicates an argument of the second instruction;

the first instruction is included in the workspace document such that the first instruction is included in the workspace document as an argument of the second instruction; and

evaluating the second instruction in the precise syntax comprises evaluating the first instruction as an argument of the second instruction.

4. The method of claim 1, further comprising:

displaying, on the display device, a display portion at a location in the workspace document at which at least the portion of the user input in the imprecise syntax was displayed prior to determining the instruction in the precise syntax;

wherein the display portion simultaneously includes at least the portion of the user input in the imprecise syntax and the instruction in the precise syntax.

5. The method of claim 1, wherein:

sending the API call to the NLP system comprises sending the API call to the NLP system via a communication network; and

receiving the instruction in the precise syntax from the NLP system comprises receiving the instruction in the precise syntax from the NLP system via the communication network.

6. One or more tangible, non-transitory computer readable storage media, storing machine readable instructions that, when executed by one or more computer processors, cause the one or more processors to:

receive, via a user interface device, user input for inclusion in a workspace document, wherein the workspace document is displayed in a graphical user interface of a software development application that, when executed by one or more computer processors, is configured to evaluate instructions in a precise syntax;

after receiving the user input, display, on a display device, the user input in the workspace document;

determine whether at least a portion of the user input i) is in the precise syntax, or ii) is in an imprecise syntax;

when it is determined that at least the portion of the user input is in the precise syntax, evaluate at least the portion of the user input according to the precise syntax;

when it is determined that at least the portion of the user input is in the imprecise syntax,

generate an application programming interface (API) call that includes i) the at least the portion of the user input in the imprecise syntax, and ii) information indicating a result of a previous evaluation, by the software development application, of a user input previously entered into the workspace document,

send the API call to a natural language processing (NLP) system implemented by the one or more computer processors,

process, at the NLP system, the API call to determine the instruction in the precise syntax that corresponds to the user input in the imprecise syntax, wherein the instruction in the precise syntax is for generating a modification of the result of the previous evaluation,

format, at the NLP system, the instruction in the precise syntax according to a format recognized by the spreadsheet application,

receive the instruction in the precise syntax from the NLP system, wherein receiving the instruction in the precise syntax from the NLP system is responsive to sending the API call to the NLP system,

include the instruction in the precise syntax in the workspace document such that the spreadsheet application executed by one or more computer processors can evaluate the instruction in the precise syntax, and

after including the instruction in the precise syntax in the workspace document, evaluate the instruction in the precise syntax.

7. The one or more tangible, non-transitory computer readable storage media of claim 6, further storing machine readable instructions that, when executed by the one or more computer processors, cause the one or more processors to:

determine whether the at least a portion of the user input i) is in the precise syntax, or ii) is in the imprecise syntax, at least by analyzing the user input to determine if the user input includes a user indication, in the precise syntax, that indicates whether the at least the portion of the user input i) is in the precise syntax, or ii) is in an imprecise syntax.

8. The one or more tangible, non-transitory computer readable storage media of claim 6, wherein:

the user input is first user input;

the instruction in the precise syntax is a first instruction in the precise syntax;

the one or more tangible, non-transitory computer readable storage media further store machine readable instructions that, when executed by the one or more computer processors, cause the one or more processors to;

receive, via the user interface device, second user input for inclusion in the workspace document, the second user input including a second instruction in the precise syntax,

after receiving the second user input, display, on the display device, the second user input in the workspace document, and

after including the second instruction in the precise syntax in the workspace document, evaluate the second instruction in the precise syntax;

the first user input indicates an argument of the second instruction;

the first instruction is included in the workspace document such that the first instruction is included in the workspace document as an argument of the second instruction; and

evaluating the second instruction in the precise syntax comprises evaluating the first instruction as an argument of the second instruction.

9. The one or more tangible, non-transitory computer readable storage media of claim 6, further storing machine readable instructions that, when executed by the one or more computer processors, cause the one or more processors to:

display a display portion at a location in the workspace document at which at least the portion of the user input in the imprecise syntax was displayed prior to determining the instruction in the precise syntax;

wherein the display portion simultaneously includes at least the portion of the user input in the imprecise syntax and the instruction in the precise syntax.

10. The one or more tangible, non-transitory computer readable storage media of claim 6, wherein:

the one or more computer processors comprises at least a first computer processor and at least a second computer processor; and

the one or more tangible, non-transitory computer readable storage media further stores machine readable instructions that, when executed by the one or more computer processors, cause the one or more processors to;

send the API call from a computer to a server system via a communication network, wherein the computer comprises the at least the first computer processor and the server system comprising the at least the second computer processor, and

receive the instruction in the precise syntax at the computer from the server system.

11. A system, comprising:

one or more computer processors;

one or more tangible, non-transitory computer readable storage media storing machine readable instructions that, when executed by one or more computer processors, cause the one or more processors to;

receive, via a user interface device, user input for inclusion in a workspace document, wherein the workspace document is displayed in a graphical user interface of a software development application that, when executed by one or more computer processors, is configured to evaluate instructions in a precise syntax;

after receiving the user input, display, on a display device, the user input in the workspace document;

determine whether at least a portion of the user input i) is in the precise syntax, or ii) is in an imprecise syntax;

when it is determined that at least the portion of the user input is in the precise syntax, evaluate at least the portion of the user input according to the precise syntax;

when it is determined that at least the portion of the user input is in the imprecise syntax,

generate an application programming interface (API) call that includes i) the at least the portion of the user input in the imprecise syntax, and ii) information indicating a result of a previous evaluation, by the software development application, of a user input previously entered into the workspace document,

send the API call to a natural language processing (NLP) system implemented by the one or more computer processors,

process, at the NLP system, the API call to determine the instruction in the precise syntax that corresponds to the user input in the imprecise syntax, wherein the instruction in the precise syntax is for generating a modification of the result of the previous evaluation,

format, at the NLP system, the instruction in the precise syntax according to a format recognized by the spreadsheet application,

receive the instruction in the precise syntax from the NLP system, wherein receiving the instruction in the precise syntax from the NLP system is responsive to sending the API call to the NLP system,

include the instruction in the precise syntax in the workspace document such that the spreadsheet application executed by one or more computer processors can evaluate the instruction in the precise syntax, and

after including the instruction in the precise syntax in the workspace document, evaluate the instruction in the precise syntax.

12. The system of claim 11, wherein the one or more tangible, non-transitory computer readable storage media further store machine readable instructions that, when executed by the one or more computer processors, cause the one or more processors to:

determine whether the at least a portion of the user input i) is in the precise syntax, or ii) is in the imprecise syntax, at least by analyzing the user input to determine if the user input includes a user indication, in the precise syntax, that indicates whether the at least the portion of the user input i) is in the precise syntax, or ii) is in an imprecise syntax.

13. The system of claim 11, wherein:

the user input is first user input;

the instruction in the precise syntax is a first instruction in the precise syntax;

the one or more tangible, non-transitory computer readable storage media further store machine readable instructions that, when executed by the one or more computer processors, cause the one or more processors to;

receive, via the user interface device, second user input for inclusion in the workspace document, the second user input including a second instruction in the precise syntax,

after receiving the second user input, display, on the display device, the second user input in the workspace document, and

after including the second instruction in the precise syntax in the workspace document, evaluate the second instruction in the precise syntax;

the first user input indicates an argument of the second instruction;

the first instruction is included in the workspace document such that the first instruction is included in the workspace document as an argument of the second instruction; and

evaluating the second instruction in the precise syntax comprises evaluating the first instruction as an argument of the second instruction.

14. The system of claim 11, wherein the one or more tangible, non-transitory computer readable storage media further store machine readable instructions that, when executed by the one or more computer processors, cause the one or more processors to:

display a display portion at a location in the workspace document at which at least the portion of the user input in the imprecise syntax was displayed prior to determining the instruction in the precise syntax;

wherein the display portion simultaneously includes at least the portion of the user input in the imprecise syntax and the instruction in the precise syntax.

15. The system of claim 11, wherein:

the one or more computer processors comprises at least a first computer processor and at least a second computer processor; and

the system comprises i) a computer that includes the at least the first computer processor, and ii) a server system that includes the at least the second computer processor;

the computer is communicatively coupled to the server system via a network;

the one or more tangible, non-transitory computer readable storage media comprises i) a first one or more tangible, non-transitory computer readable storage media, and ii) a second one or more tangible, non-transitory computer readable storage media;

the computer includes the first one or more tangible, non-transitory computer readable storage media;

the server system includes the second one or more tangible, non-transitory computer readable storage media;

the first one or more tangible, non-transitory computer readable storage media further store machine readable instructions that, when executed by the at least the first computer processor, cause the at least the first computer processor to;

send the API call to the server system via the communication network; and

the second one or more tangible, non-transitory computer readable storage media further store machine readable instructions that, when executed by the at least the second computer processor, cause the at least the second computer processor to;

send the instruction in the precise syntax to the one or more computer processors via the communication network in response to the API call.