In-message suggestion by personal knowledge graph constructed from user email data

• US 9,600,769 B1
• Filed: 12/06/2013
• Issued: 03/21/2017
• Est. Priority Date: 12/06/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Buehling, Clemens, Liu, Yifang
• Primary Examiner(s): Hill, Stanley K
• Assistant Examiner(s): BUSS, BENJAMIN J
• Application Number:
  US14/099,114
• Time in Patent Office: 1,201 Days
• US Class Current: 1/1
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
• CPC Class Codes: H04L 51/52 for supporting social networking services

Abstract

Provided are methods and systems for constructing a personal knowledge graph for a user based on data contained in existing e-mail messages of the user, and using the personal knowledge graph to provide the user with contextually-relevant content and/or contact suggestions while the user is composing an e-mail message. A personal knowledge graph is constructed based on relations/connections between users and content identified from data contained in e-mail messages sent and/or received by the user. Such relations include content-content relations, user-content relations, and user-(content)-user relations. When a user is composing an e-mail message, the system responsively processes, analyzes, and indexes composing e-mail message data. The composing e-mail message data is used to fetch relevant information from the user'"'"'s personal knowledge graph and generate one or more content and/or contact suggestions for presentation to the user alongside an e-mail message composing view.

Claims

1. A computer-implemented method comprising:

extracting content entity data from existing e-mail messages of a user, wherein the content entity data includes content entities and their association with the e-mail message from which it was extracted;

extracting user entity data from the user'"'"'s existing e-mail messages, wherein the user entity data includes user entities and their association with the e-mail message from which it was extracted;

identifying content-content relations between the extracted content entities;

identifying user-content relations between the extracted user entities and the extracted content entity;

identifying entity-entity relations between different extracted user entities;

constructing a personal knowledge graph for the user including the extracted content entities, the extracted user entities, the identified content-content relations, the identified user-content relations, and the identified entity-entity relations;

analyzing contents of an e-mail message being composed by the user;

identifying, from the personal knowledge graph constructed for the user, entities related to the analyzed contents of the e-mail message, wherein the identified entities include one or more of the content entities, one or more of the user entities, or both;

generating one or more entity suggestions based on the identified entities and the content-content relations, user-content relations, and/or entity-entity relations included in the user'"'"'s personal knowledge graph; and

providing the one or more entity suggestions to the user while the e-mail message is being composed by the user.

2. The computer-implemented method of claim 1, wherein identifying, from the personal knowledge graph constructed for the user, entities related to the analyzed contents of the e-mail message includes:

identifying, based on the entity relations contained in the personal knowledge graph, one or more content entities, one or more user entities, or both, from the personal knowledge graph that are related to the analyzed contents of the e-mail message.

3. The computer-implemented method of claim 1, wherein the one or more entity suggestions include one or more content and/or contact suggestions based on the identified entities from the personal knowledge graph.

4. The computer-implemented method of claim 3, wherein the one or more content and/or contact suggestions include a reference to one of the existing e-mail messages of the user.

5. The computer-implemented method of claim 1, wherein the identified entity relations include content-content relations, user-content relations, and user-user relations.

6. The computer-implemented method of claim 1, wherein analyzing the contents of the e-mail message being composed by the user includes:

analyzing data entered by the user in one or more data fields of the e-mail message; and

indexing the analyzed data based on whether the data is determined to be content-related data or contact-related data.

7. The computer-implemented method of claim 1, wherein the entity data is extracted from the existing e-mail messages of the user using one of Singular Value Decomposition and Latent Dirichlet Allocation.

8. The computer-implemented method of claim 1, wherein the e-mail message is being composed by the user in an e-mail message composing view, further comprising:

providing the one or more entity suggestions for presentation to the user in the e-mail message composing view.

9. The computer-implemented method of claim 1, wherein the e-mail message is being composed by the user in an e-mail message composing view, further comprising:

providing the one or more entity suggestions for presentation to the user alongside the e-mail message composing view.

10. The computer-implemented method of claim 1, further comprising:

receiving, from the user, feedback about the one or more entity suggestions provided to the user; and

updating the personal knowledge graph constructed for the user based on the received feedback.

11. A system comprising:

one or more processors; and

a non-transitory computer-readable medium coupled to said one or more processors having instructions stored thereon that, when executed by said one or more processors, cause said one or more processors to perform operations comprising;

extracting content entity data from existing e-mail messages of a user, wherein the content entity data includes content entities and their association with the e-mail message from which it was extracted;

extracting user entity data from the user'"'"'s existing e-mail messages, wherein the user entity data includes user entities and their association with the e-mail message from which it was extracted;

identifying content-content relations between the extracted content entities;

identifying user-content relations between the extracted user entities and the extracted content entity;

identifying entity-entity relations between different extracted user entities;

constructing a personal knowledge graph for the user including extracted content entities, the extracted user entities, the identified content-content relations, the identified user-content relations, and the identified entity-entity relations;

analyzing contents of an e-mail message being composed by the user;

identifying, from the personal knowledge graph constructed for the user, entities related to the analyzed contents of the e-mail message, wherein the identified entities include one or more of the content entities, one or more of the user entities, or both;

generating one or more entity suggestions based on the identified entities and the content-content relations, user-content relations, and/or entity-entity relations included in from the personal knowledge graph; and

providing the one or more entity suggestions to the user while the e-mail message is being composed by the user.

12. The system of claim 11, wherein the one or more processors are caused to perform further operations comprising:

identifying, based on the entity relations contained in the personal knowledge graph, one or more content entities, one or more user entities, or both, from the personal knowledge graph that are related to the analyzed contents of the e-mail message.

13. The system of claim 11, wherein the one or more entity suggestions include one or more content and/or contact suggestions based on the identified entities from the personal knowledge graph.

14. The system of claim 13, wherein the one or more content and/or contact suggestions include a reference to one of the existing e-mail messages of the user.

15. The system of claim 11, wherein the identified entity relations include content-content relations, user-content relations, and user-user relations.

16. The system of claim 11, wherein the one or more processors are caused to perform further operations comprising:

analyzing data entered by the user in one or more data fields of the e-mail message; and

indexing the analyzed data based on whether the data is determined to be content-related data or contact-related data.

17. The system of claim 11, wherein the e-mail message is being composed by the user in an e-mail message composing view, and wherein the one or more processors are caused to perform further operations comprising:

providing the one or more entity suggestions for presentation to the user in the e-mail message composing view.

18. The system of claim 11, wherein the e-mail message is being composed by the user in an e-mail message composing view, and wherein the one or more processors are caused to perform further operations comprising:

providing the one or more entity suggestions for presentation to the user alongside the e-mail message composing view.

19. The system of claim 11, wherein the one or more processors are caused to perform further operations comprising:

receiving, from the user, feedback about the one or more entity suggestions provided to the user; and

updating the personal knowledge graph constructed for the user based on the received feedback.

20. One or more non-transitory computer readable media storing computer-executable instructions that, when executed by one or more processors, causes the one or more processors to perform operations comprising:

extracting content entity data from existing e-mail messages of a user, wherein the content entity data includes content entities and their association with the e-mail message from which it was extracted;

extracting user entity data from the user'"'"'s existing e-mail messages, wherein the user entity data includes user entities and their association with the e-mail message from which it was extracted;

identifying content-content relations between the extracted content entities;

identifying user-content relations between the extracted user entities and the extracted content entity;

identifying entity-entity relations between different extracted user entities;

constructing a personal knowledge graph for the user including extracted content entities, the extracted user entities, the identified content-content relations, the identified user-content relations, and the identified entity-entity relations;

analyzing contents of an e-mail message being composed or viewed by the user;

identifying, from the personal knowledge graph constructed for the user, entities related to the analyzed contents of the e-mail message, wherein the identified entities include one or more of the content entities, one or more of the user entities, or both;

generating one or more entity suggestions based on the identified entities and the content-content relations, user-content relations, and/or entity-entity relations included in from the personal knowledge graph; and

providing the one or more entity suggestions to the user while the e-mail message is being composed or viewed by the user.