Multilingual command line interface bots enabled with a real-time language analysis service

Inventors: Jun Su (Beijing, CN); Su Liu (Austin, TX); Peng Hui Jiang (Beijing, CN); Michael Davis (Chesterfield, MO)

Assignee: International Business Machines Corporation

G10L15/22 G06F40/58 G10L15/005

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 12694874
App. No.: 18/533,162
Granted: Jul 28, 2026
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

The input of a user is monitored and a location of the user and a language of the user are detected. The input is converted to a text string in the detected user language and the converted text string is parsed into parsed tokens. A command line and correlated parameters indicated by the input are recognized based on the parsed tokens. The recognized command line with the assigned parameters is executed.

Claims (65)

1 . A method comprising:

monitoring, using at least one hardware processor, input of a user;

detecting, using the at least one hardware processor, a location of the user and a language of the user;

converting, using the at least one hardware processor, the input to a text string in the detected user language;

parsing, using the at least one hardware processor, the converted text string into parsed tokens;

recognizing, using the at least one hardware processor, a command line and correlated parameters indicated by the input based on the parsed tokens;

executing the recognized command line with the assigned parameters;

verifying, using pre-defined rules, that results of executing the recognized command line validate that the recognized command line is an accurate conversion of the input; and

updating mappings of a human command to command line mapping repository based on results of the verifying operation.

2 . The method of claim 1 , further comprising assigning, using the at least one hardware processor, one or more variables of environment and attributes for the recognized command line and the correlated parameters.

3 . The method of claim 1 , wherein the assigning operation assigns a language of the user, a date format of the user, and a location of the user.

4 . The method of claim 1 , wherein the converting the input to the text string further comprises performing speech recognition on the input.

5 . The method of claim 1 , further comprising:

defining a framework of a Multilingual Command Line Interface Bot for supporting an intelligent voice control command line interface across different languages.

6 . The method of claim 1 , further comprising:

defining a data structure with related algorithms for tracking user voice commands and related parameters.

7 . The method of claim 1 , further comprising:

repeating the monitoring, detecting, converting, parsing, recognizing, and executing operations based on additional input, wherein the executing operation further comprises controlling a computer resource based on the additional input.

8 . The method of claim 1 , further comprising comparing a summary of the parsed text string to entries of the command line mapping repository to identify a most similar command line using an edit distance algorithm.

9 . A method comprising:

monitoring, using at least one hardware processor, input of a user;

detecting, using the at least one hardware processor, a location of the user and a language of the user;

converting, using the at least one hardware processor, the input to a text string in the detected user language;

parsing, using the at least one hardware processor, the converted text string into parsed tokens;

recognizing, using the at least one hardware processor, a command line and correlated parameters indicated by the input based on the parsed tokens;

executing the recognized command line with the assigned parameters;

verifying, using pre-defined rules, that results of executing the recognized command line validate that the recognized command line is an accurate conversion of the input;

enabling the user to configure settings and criteria of the method;

learning and generating a human command to command line mapping repository for one or more languages; and

adjusting, using a machine-based learner, the settings and criteria based on a result of the validation.

10 . The method of claim 9 , further comprising:

verifying, using pre-defined rules, that results of executing the recognized command line validate that the recognized command line is an accurate conversion of the input; and

revising, using the learner, the recognized command line in the command line mapping repository based on the result of the validation.

11 . The method of claim 9 , further comprising manually initializing the command line mapping repository with a set of available command lines and updating the mapping repository using machine learning as user input is processed.

12 . A computer program product, comprising:

one or more tangible computer-readable storage media and program instructions stored on at least one of the one or more tangible computer-readable storage media, the program instructions executable by a processor, the program instructions comprising: