Deep command search within and across applications

Patent metadata

Field	Value
Publication number	US-11921730-B2
Application number	US-202217730829-A
Country	US
Kind code	B2
Filing date	Apr 27, 2022
Priority date	Aug 26, 2019
Publication date	Mar 5, 2024
Grant date	Mar 5, 2024

Abstract

Described herein are mechanisms to allow users to access functionality of applications in a suite of applications. In a first aspect, when a query relating to functionality of an application is received from a user, an index containing both top-level and sub-level functionality is searched. Results are ranked using a trained machine learning model using both context describing user interactions and the search results. A subset of the ranked results are presented to the user as options. In a second aspect the index can comprise entries describing functionality from other applications so that results presented to the user can include cross-application functionality. In a third aspect, the index can be searched using the context prior to receiving a query and adjusting the user interface based on the results. In a fourth aspect, the system can recommend other applications and/or devices that are better suited to a user's intent.

First claim

What is claimed is:

1. A computing system comprising:
a processor; and
memory storing instructions that, when executed by the processor, cause the processor to perform acts comprising:
receiving, by way of a productivity application that belongs to a suite of productivity applications, a query from a user who is associated with a tenancy, the query representing a request about functionality of the application;
searching an index based upon the query, the index indexes information about both top level and sub top-level functionality of the application, the top level and sub-top level functionality is accessible to the user within the application;
receiving results in response to the search;
providing the results to a trained machine learning model that is customized for the tenancy, the trained machine learning model having been previously trained based upon training data that is associated with the tenancy;
receiving, from the trained machine learning model, a respective ranking for each result in the results;
selecting a result from the ranked results; and
causing the selected result to be presented to the user.

2. The computing system of claim 1 , wherein the tenancy is associated with an installation of the productivity application across several computing devices of a company.

3. The computing system of claim 1 , the acts further comprising:
accessing context for the user, the context comprising results of interactions of the user with the application;
providing the context to the trained machine learning model, wherein the respective ranking for each result in the results is based upon the context.

4. The computing system of claim 3 , wherein the context further comprises second results of second interactions of users in the tenancy with the application.

5. The computing system of claim 1 , the acts further comprising:
accessing context for the user, the context comprising results of interactions of the user with a second application in the suite of productivity applications; and
providing the context to the trained machine learning model, wherein the respective ranking for each result in the results is based upon the context.

6. The computing system of claim 5 , wherein the context further comprises second results of second interactions of users in the tenancy with the second application.

7. The computing system of claim 1 , the acts further comprising:
identifying a top-level command accessible by the user through a user interface of the application;
identifying a sub top-level command of the top-level command, the sub top-level function accessible by the user through a second user interface;
creating an index entry in the index for the top-level command, the index entry comprises a top-level function; and
creating a second index entry for the sub top-level command, the second index entry comprising a sub top-level function.

8. The computing system of claim 1 , the acts further comprising:
selecting the trained machine learning model from amongst several machine learning models based upon the tenancy.

9. The computing system of claim 1 , the acts further comprising:
providing the query to a second application in the suite of productivity applications;
receiving a search result from the second application in response to providing the query to the second application; and
causing the search result to be presented to the user together with the selected result.

10. The computing system of claim 1 , wherein the index includes an entry that comprises functionality of a second application in the suite of productivity applications, the acts further comprising:
identifying the entry based upon the query; and
causing the functionality of the second application to be presented to the user concurrently with the search result.

11. A method performed by a computing system, the method comprising:
receiving, by way of an application that belongs to a suite of productivity applications, a query pertaining to functionality of the application from a user who is associated with a tenancy;
in response to receipt of the query, searching a computer-implemented index to identify search results, wherein the computer-implemented index includes first entries that represent top-level functions of the application and second entries that represent sub top-level functions of the application;
ranking the search results based upon the tenancy, wherein a most highly ranked search result in the search results represents a sub top-level function;
selecting the most highly ranked search result; and
causing the most highly ranked search result to be presented to the user such that the sub top-level function is presented.

12. The method of claim 11 , wherein ranking the search results based upon the tenancy comprises providing the search results to a machine learning model that has been trained based upon training data that comprises interactions of users associated with the tenancy with the application, wherein the machine learning model ranks the search results.

13. The method of claim 12 , wherein the training data further comprises interactions of the users associated with the tenancy with a second application in the suite of productivity applications.

14. The method of claim 11 , wherein the tenancy is associated with an installation of the productivity application across several computing devices of a company.

15. The method of claim 11 , further comprising selecting the trained machine learning model from amongst several machine learning models based upon the tenancy.

16. The method of claim 11 , wherein ranking the search results based upon the tenancy comprises providing the search results to a machine learning model that is customized for the tenancy.

17. A computer storage medium comprising instructions that, when executed by a processor, cause the processor to perform acts comprising:
receiving, by way of an application that belongs to a suite of productivity applications, a query pertaining to functionality of the application from a user who is associated with a tenancy;
in response to receipt of the query, searching a computer-implemented index to identify search results, wherein the computer-implemented index includes first entries that represent top-level functions of the application and second entries that represent sub top-level functions of the application;
ranking the search results based upon the tenancy, wherein a most highly ranked search result in the search results represents a sub top-level function;
selecting the most highly ranked search result; and
causing the most highly ranked search result to be presented to the user such that the sub top-level function is presented.

18. The computer storage medium of claim 17 , wherein ranking the search results based upon the tenancy comprises providing the search results to a machine learning model that has been trained based upon training data that comprises interactions of users associated with the tenancy with the application, wherein the machine learning model ranks the search results.

19. The computer storage medium of claim 18 , wherein the training data further comprises interactions of the users associated with the tenancy with a second application in the suite of productivity applications.

20. The computer storage medium of claim 17 , wherein the tenancy is associated with an installation of the productivity application across several computing devices of a company.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Kleiner Madeline Schuster
• Freier Nathaniel George
• Kohlmeier Bernhard
• Agashe Amod Anil
• Shah Jignesh
• Religa Tomasz Lukasz

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06F16/24578 Primary

  using ranking · CPC title

• G06F16/22

  Indexing; Data structures therefor; Storage structures · CPC title

• G06F16/248

  Presentation of query results · CPC title