Platform for supporting multiple virtual agent applications

Patent metadata

Field	Value
Publication number	US-11093307-B2
Application number	US-201715487061-A
Country	US
Kind code	B2
Filing date	Apr 13, 2017
Priority date	Dec 8, 2016
Publication date	Aug 17, 2021
Grant date	Aug 17, 2021

Abstract

A device may receive first information that identifies an input associated with a virtual agent application executing on a user device. The virtual agent application may provide an interface for a project involving a plurality of user devices. The device may determine, based on the first information that identifies the input, a first response based on second information. The device may determine, based on at least one of the first information that identifies the input or the first response and without user input, a second response. The device may provide, to the virtual agent application of the user device, fourth information that identifies at least one of the first response or the second response.

First claim

What is claimed is:

1. A device relating to software development, comprising:
a memory; and
one or more processors to:
receive first information that identifies an input associated with a first virtual agent application executing on a user device,
the first virtual agent application providing an interface for a project involving a plurality of user devices,
the project including the first virtual agent application and a second virtual agent application, and

the first information including a query regarding execution of software test cases;

determine, based on the first information that identifies the input, a first response including second information,
the second information being associated with a first resource,
the second information identifying first particular software test cases and execution statuses of the first particular software test cases,
the second information being associated with the second virtual agent application, and
the first particular software test cases being associated with a particular current regression test iteration of the project;

identify third information, associated with one or more other projects or other regression test iterations of the project, based on the execution statuses of the first particular software test cases,
the one or more other projects including a contemporaneous project, and
the third information being associated with a second resource that is different than the first resource;

determine, based on the first information that identifies the input, the first response, and the third information, and without user input, a second response including a recommendation to execute second particular software test cases,
the second particular software test cases being associated with the particular current regression test iteration of the project,
the second response including a same type of response as the first response, and
the second response including a same type of response as the first response; and

provide, to the first virtual agent application, fourth information that identifies at least one of the first response or the second response.

2. The device of claim 1 , where the one or more processors are further to:
identify a set of results based on the fourth information;
determine a first ranking of the set of results;
receive, from the user device, fifth information that identifies a user-defined ranking of the set of results;
perform, based on the fifth information and the set of results, a technique to adjust one or more parameters associated with one or more of a local similarity score function or a global similarity score function,
the local similarity score function being configured to produce a local similarity score,
the local similarity score including information that identifies a measure of similarity between an attribute associated with a result, of the set of results, and a corresponding attribute associated with the query, and

the global similarity score function being configured to produce a global similarity score,
the global similarity score being based on a set of local similarity scores;

determine a second ranking based on performing the technique;
determine that a condition is satisfied based on comparing the user-defined ranking and the second ranking; and
apply one or more values associated with the one or more parameters based on the condition being satisfied,
the device to use the one or more values in association with one or more additional inputs received after the input.

3. The device of claim 1 , where the one or more processors are further to:
receive fifth information that identifies feedback based on providing the fourth information;
implement a machine learning technique based on the fifth information; and
provide, to the user device, sixth information based on performing the machine learning technique.

4. The device of claim 1 , where the user device is a first user device, and
where the second virtual agent application is associated with a second user device,
the second virtual agent application being different from the first virtual agent application, and
the second user device being different from the first user device.

5. The device of claim 1 , where the user device is a first user device, and
where the one or more processors are further to:
provide the fourth information to the second virtual agent application of a second user device,
the second virtual agent application being different from the first virtual agent application, and
the second user device being different from the first user device.

6. The device of claim 1 , where the one or more processors, when providing the fourth information, are to at least one of:
provide, for display on the user device via a user interface, the fourth information;
provide the fourth information to cause the user device to generate an audible output of the fourth information; or
provide the fourth information to cause a message to be sent to the user device,
the message including the fourth information.

7. The device of claim 1 , where the one or more processors are further to:
identify a set of results based on the fourth information;
determine a first ranking of the set of results;
receive, from the user device, fifth information that identifies a user-defined ranking of the set of results; and
perform, based on the fifth information and the set of results, a technique to adjust one or more parameters associated with a global similarity score function,
the global similarity score function being configured to produce a global similarity score,
the global similarity score being based on a linear weighted sum of local similarity scores.

8. A method relating to software development, comprising:
receiving, by a device, first information that identifies an input associated with a first virtual agent application executing on a user device,
the first virtual agent application providing an interface for a project involving a plurality of user devices,
the project including the first virtual agent application and a second virtual agent application, and

the first information including a query regarding execution of software test cases;

determining, by the device and based on the input, a first response identifying first particular software test cases and execution statuses of the first particular software test cases,
the first particular software test cases being associated with a particular current regression test iteration of the project;

identifying, by the device, second information, associated with other projects or other regression test iterations of the project, based on the execution statuses,
the second information being associated with the second virtual agent application, and
the other projects including:
a contemporaneous project, and
a previously completed project;

determining, by the device, based on the first information, the first response, the second information, and without user input, a second response identifying a recommendation to execute second particular software test cases,
the second particular software test cases being associated with the particular current regression test iteration of the project;

determining, by the device, a ranking of a set of results in the second response;
providing, by the device and to the user device, the ranking;
receiving, by the device and based on providing the ranking, a user-defined ranking of the set of results;
determining, by the device, an error based on comparing the ranking and the user-defined ranking;
performing, by the device and based on determining the error, a technique to adjust one or more parameters associated with one or more functions,
t

Assignees

• Accenture Global Solutions Ltd

Inventors

• Ramnani Roshni Ramesh
• Madhukar Wabgaonkar Harshawardhan
• Sengupta Shubhashis
• Podder Sanjay
• DUBASH Neville
• Ravilla Tirupal Rao
• Ganapat Patil Sumitraj
• Thimmaiah Rakesh
• Pathania Priyavanshi
• Jose Reeja
• Hareesh Chaitra

Classifications

• G06N20/00 Primary

  Machine learning · CPC title

• G06N20/10

  using kernel methods, e.g. support vector machines [SVM] · CPC title

• G06N3/006

  based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] · CPC title

• G06F9/543 Primary

  User-generated data transfer, e.g. clipboards, dynamic data exchange [DDE], object linking and embedding [OLE] · CPC title

• G06F16/90332

  Natural language query formulation or dialogue systems · CPC title