Providing automatic actions for mobile onscreen content

• US 9,965,559 B2
• Filed: 08/21/2014
• Issued: 05/08/2018
• Est. Priority Date: 08/21/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Marcin, David, Patel, Rajan
• Primary Examiner(s): Lu, Charles
• Application Number:
  US14/465,265
• Publication Number:
  US 20160055246A1
• Time in Patent Office: 1,356 Days
• CPC Class Codes: G06F 16/903 Querying for retrieval from the web G06F16/953
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06F 40/295 Named entity recognition

Abstract

Implementations provide an interface for initiating actions related to content the user is viewing on a mobile device. A method includes performing recognition on content captured from a display of a mobile device and identifying a plurality of entities in the content. The method may include issuing a query for each of the plurality of entities, ranking the plurality of entities based on the search results, generating an action card for at least some of the highest ranked entities, and providing the action cards for display on the mobile device. Alternatively or additionally, the method may include determining at least one contact in a contacts data store that corresponds to an entity and generating an action card for the entity, the action card having a first action that uses first information from the contacts data store and a second action that uses second information from the contacts data store.

Claims

1. A method comprising:

performing recognition on content captured from a display of a mobile device;

identifying a plurality of entities in the content;

issuing a respective query for each of the plurality of entities;

ranking the plurality of entities based on search results returned for the respective queries;

determining that the search results for a first entity of the highest ranked entities includes a knowledge panel;

extracting information from the knowledge panel for the first entity;

generating a respective action card for at least one of the highest ranked entities, including the first entity, wherein each of the respective action cards includes at least three actions per entity and the actions for the respective action card for the first entity are generated from the information extracted from the knowledge panel and the action card for the first entity includes text extracted from the knowledge panel; and

providing the respective action cards for display to a user of the mobile device, wherein the mobile device displays the action cards.

2. The method of claim 1, wherein issuing a query for a first entity of the plurality of entities includes:

determining, using a name classifier, that the first entity is classified as a name;

querying a contacts data store associated with the user of the mobile device using the first entity; and

returning information from the contacts data store as search results for the query when the first entity corresponds to a contact in the contacts data store.

3. The method of claim 2, wherein issuing the query for the first entity further includes:

issuing the query for the first entity to a search engine when the first entity fails to correspond to a contact in the contacts data store.

4. The method of claim 1, wherein the actions for the first entity are extracted from the knowledge panel by a machine learning algorithm trained on feedback regarding previously selected actions.

5. The method of claim 1, wherein an entity of the plurality of entities having search results that include results from a graph-based data store receives a boost in rank.

6. The method of claim 1, wherein generating the respective action card for an entity of the highest ranked entities includes:

identifying a link in the search results for the entity;

determining that a domain for the link corresponds to a mobile application installed on the mobile device; and

generating a deep link into the mobile application, the deep link having a state that relates to the entity,

wherein the action card includes an action that opens the mobile application using the deep link.

7. The method of claim 1, wherein a second entity of the plurality of entities corresponds to a contact in a contacts data store and generating the action card for the second entity includes:

determining default actions selected by the user for contact entities; and

generating the action card using information from the contacts data store for the contact that corresponds to the default actions.

8. A system comprising:

at least one processor;

an indexed document corpus;

a graph-based data store; and

memory storing instructions that, when executed by the at least one processor cause the system to perform operations comprising;

performing recognition on content captured from a display of a mobile device,

identifying a plurality of entities in the content,

for each of the plurality of entities, issuing a respective query to a search engine for the entity, the search engine searching the graph-based data store and the indexed document corpus and generating search results for the entity,

ranking the plurality of entities based on the search results, the search results for a first entity including a knowledge panel,

extracting information from the knowledge panel for the first entity, and

providing the plurality of entities with respective ranks and search results to the mobile device, the mobile device generating action cards for at least one of the highest ranked entities using the respective search results, wherein the action cards include at least three actions per entity and wherein the actions for the action card for the first entity are generated from the information extracted from the knowledge panel.

9. The system of claim 8, wherein a first entity of the plurality of entities that has a corresponding entity in the graph-based data store receives a boost in rank.

10. The system of claim 8, wherein ranking the plurality of entities includes:

determining a frequency of queries relating to a first entity; and

boosting the rank of the first entity when the frequency meets a threshold or is greater than a frequency of queries relating to a second entity.

11. A system comprising:

a contacts data store;

at least one processor; and

memory storing instructions that, when executed by the at least one processor, cause the system to;

perform recognition on content displayed on a display of a mobile device,

identify a first entity and a second entity in the content,

determine a contact in the contacts data store that corresponds to the first entity,

generate a first action card for the first entity, the action card having a first action that uses first information from the contacts data store for the contact and a second action that uses second information from the contacts data store for the contact,

obtain search results for the second entity from a search engine, the search results including a knowledge panel for the second entity,

extract information from the knowledge panel for the second entity,

generate a second action card for the second entity from the information extracted from the knowledge panel, the action card including at least three actions, and

display the first action card and the second action card on the display.

12. The system of claim 11, wherein the memory further stores instructions that, when executed by the at least one processor, cause the mobile device to:

determine a frequency of interactions with the contact;

determine that the frequency fails to meet a threshold; and

display the second action card in a position of prominence over the first action card.

13. The system of claim 11, wherein the first action card is displayed in a position of prominence based on the first entity corresponding to the contact.

14. The system of claim 11, wherein the at least three actions for the second entity are extracted from the knowledge panel by a machine learning algorithm trained on feedback regarding previously selected actions for entities having an entity type of the second entity.

15. The system of claim 11, wherein the first action initiates a first mobile application and the second action initiates a second mobile application.

16. The system of claim 15, wherein the memory further stores instructions that, when executed by the at least one processor, cause the mobile device to:

receive a selection of the first action; and

launch the first mobile application using the first information.

17. The system of claim 11, wherein performing recognition on the content displayed on the display includes:

examining accessibility data generated for the content displayed on the display.

18. The system of claim 11, wherein identifying the entity includes using a name classifier to determine a set of words that are classified as a name.

19. The system of claim 11, wherein the contact is a first contact and the memory further stores instructions that, when executed by the at least one processor, cause the mobile device to:

determine a second contact in the contacts data store that corresponds to a third entity identified in the content;

generate a third action card for the second contact;

determine a frequency of interaction for the first contact is higher than a frequency of interaction for the second contact; and

display the first action card in a position of prominence with regard to the third action card.

20. The system of claim 11, wherein the contact is a first contact and the memory further stores instructions that, when executed by the at least one processor, cause the mobile device to:

determine a second contact in the contacts data store that corresponds to the entity;

determine a frequency of interaction for the first contact is higher than a frequency of interaction for the second contact; and

select the first contact as corresponding to the first entity.

21. The system of claim 11, wherein the contacts data store is a contacts data store for a user of the mobile device that is stored remote from the mobile device.