Context-based search and relevancy generation

• US 10,169,432 B2
• Filed: 03/19/2018
• Issued: 01/01/2019
• Est. Priority Date: 11/06/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Vogel, Matthew, Seto, Julie C., Stepanich, Darron, Kikin-Gil, Erez
• Primary Examiner(s): Baker, Charlotte M
• Application Number:
  US15/925,287
• Publication Number:
  US 20180239803A1
• Time in Patent Office: 288 Days
• Field of Search: 704275, 705 1449, 7079991, 707724, 707731, 707748, 707E17061, 707E17108, 707737, 707741, 707E17046, 707780, 715745, 715751, 715765
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 3/0484 for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
• CPC Class Codes: H04L 2101/69 using geographic information, e.g. room number

Abstract

A computing device receives a trigger to surface relevant content. The device also obtains a variety of different types of cross-source contextual information. Items of content are identified and relevancy weights are obtained based on the contextual information. A relevancy is calculated, based on the relevancy weights, for each item of content. The items of content are surfaced.

Claims

1. A computing system comprising:

at least one processor; and

memory storing instructions executable by the at least one processor, wherein the instructions, when executed, configure the computing system to;

based on a plurality of sensor inputs, identify a plurality of different items of context from a plurality of different sources of context;

search a plurality of different content sources to identify a set of documents based on a trigger input;

generate a relevancy metric corresponding to each document in the identified set of documents, based on the plurality of different items of context; and

generate a user interface display that selectively displays the documents in the set of documents based on the corresponding relevancy metric.

2. The computing system of claim 1 wherein the instructions configure the computing system to:

determine whether a user is using the computing system in a work context or a non-work context; and

generate the relevancy metric for the documents based on the detected work context or non-work context.

3. The computing system of claim 2 wherein the instructions configure the computing system to:

detect a user location; and

generate the relevancy metric for the documents based on the detected user location.

4. The computing system of claim 2 wherein the instructions configure the computing system to:

identify temporal document usage patterns corresponding to the documents, each temporal document usage pattern being indicative of a pattern of usage of a corresponding document, by the user, over time; and

generate the relevancy metric for the documents based on the identified temporal document usage patterns corresponding to each document.

5. The computing system of claim 2 wherein the instructions configure the computing system to:

detect user interactions corresponding to each of the documents; and

generate the relevancy metric for the documents based on the detected user interactions.

6. The computing system of claim 5 wherein the instructions configure the computing system to:

detect recency of user interactions; and

generate the relevancy metric based on the detected recency.

7. The computing system of claim 5 wherein the instructions configure the computing system to:

detect interaction type; and

generate the relevancy metric based on the detected interaction type.

8. The computing system of claim 5 wherein the instructions configure the computing system to:

detect frequency of interaction; and

generate the relevancy metric based on the detected frequency of interaction.

9. The computing system of claim 2 wherein the instructions configure the computing system to:

access a calendar system;

identify user interactions with the documents relative to calendar items of the user; and

generate the relevancy metric for the documents based on the identified user interactions with the documents relative to the calendar items.

10. The computing system of claim 9 wherein the instructions configure the computing system to:

identify whether the user is interacting with the documents in temporal proximity to meetings or deadlines.

11. The computing system of claim 2 wherein the instructions configure the computing system to:

detect other personnel that are related to the documents, other than the user; and

generate the relevancy metric for the documents based on the detected other personnel.

12. The computing system of claim 11 wherein the instructions configure the computing system to:

detect a proximity of the user to the other personnel; and

generate the relevancy metric based on the detected proximity to the other personnel.

13. The computing system of claim 2 wherein the instructions configure the computing system to:

detect a type of user device being used by the user; and

generate the relevancy metric for the documents based on the detected type of user device.

14. The computing system of claim 13 wherein the instructions configure the computing system to:

detect open applications on the user device; and

generate the relevancy metric for the documents based on the detected open applications.

15. The computing system of claim 2 wherein the instructions configure the computing system to:

detect biometric data corresponding to the user; and

generate the relevancy metric for the documents based on the biometric data.

16. The computing system of claim 2 wherein the instructions configure the computing system to:

generate a confidence score associated with each of the documents; and

engage a dialog engine to obtain additional context information from the user when one or more confidence scores fall below a threshold value.

17. The computing system of claim 2 wherein the instructions configure the computing system to:

generate the relevancy metric for the documents based on weighted relevancy criteria; and

vary weights on the weighted relevancy criteria based on the items of context.

18. A computer implemented method, comprising:

identifying a plurality of different items of context, from a plurality of different sources of context;

receiving a trigger input;

in response to the trigger input, searching a plurality of different content sources, to identify a set of documents, based on the trigger input;

detecting a user location;

generating a relevancy measure corresponding to each document in the identified set of documents, based on the user location and the plurality of different items of context; and

generating a user interface that selectively renders the documents, in the set of documents, to a user based on the corresponding relevancy score.

19. The computer implemented method of claim 18 wherein detecting a plurality of different sensor inputs comprises:

detecting a usage pattern sensor input that identifies temporal document usage patterns corresponding to the documents, each temporal document usage pattern being indicative of a pattern of usage of a corresponding document, by the user, over time, wherein generating a relevancy metric includes generating the relevancy metric for the documents based on the identified temporal document usage patterns corresponding to each document.

20. A computing system, comprising:

at least one processor; and

memory storing instructions executable by the at least one processor, wherein the instructions, when executed, configure the computing system to provide;

a context identification system configured to identify a plurality of different items of context, from a plurality of different sources of context, including whether a user is using the computing system in a work context or a non-work context;

a document interaction detector configured to detect user interactions corresponding to each of the documents;

a cross-source search component configured to search a plurality of different content sources, to identify a set of documents, based on a trigger input;

a relevancy generator configured to generate a relevancy metric corresponding to each document in the identified set of documents, based on the plurality of different items of context and the detected user interactions; and

a user interface component configured to generate a user interface display that selectively displays the documents in the set of documents based on the corresponding relevancy metric.