Template-based identification of user interest

• US 10,387,559 B1
• Filed: 11/22/2016
• Issued: 08/20/2019
• Est. Priority Date: 11/22/2016
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Wendt, James, Yang, Jie, Sheng, Ying, Xie, Jing, Pueyo, Luis Garcia
• Primary Examiner(s): Baderman, Scott T
• Assistant Examiner(s): Smith, Benjamin
• Application Number:
  US15/359,101
• Time in Patent Office: 1,001 Days
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 40/186 Templates
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]

Abstract

Methods and apparatus are described herein for creating associations between user interests and electronic document templates generated from B2C electronic documents. Once these associations are created, interest(s) of a user (e.g., a user profile) may be determined automatically based on B2C electronic documents addressed to the user. In various implementations, an electronic document addressed to a user may be identified. A particular electronic document template that corresponds to the electronic document addressed to the user may be selected from a plurality of electronic document templates. The selecting may be based on attribute(s) shared between the electronic document addressed to the user and the selected electronic document template. The particular electronic template may be generated from a plurality of electronic documents that share fixed content. Interest(s) associated with the particular electronic document template may be identified, and association(s) between the user and the identified interest(s) may be stored.

Claims

1. A computer-implemented method, comprising:

generating a plurality of electronic document templates, wherein each electronic document template is generated from a plurality of emails or text messages that share fixed content;

determining one or more user interests associated with each of the electronic document templates, wherein the one or more user interests are determined based on one or more aggregate attributes of a corpus of emails or text messages associated with the electronic document template;

storing, in one or more databases, the plurality of electronic document templates, wherein each of the electronic document templates is stored in association with one or more corresponding user interests;

identifying an email or text message addressed to a user;

selecting, from the plurality of electronic document templates, a particular electronic document template that corresponds to the email or text message addressed to the user, wherein the selecting is based on one or more attributes shared between the email or text message addressed to the user and the selected electronic document template;

detecting, based on interactions by the user with one or more computing devices, engagement by the user with the email or text message;

determining that the detected engagement satisfies a criterion, wherein satisfaction of the criterion indicates that the user is interested in the email or text message, and wherein determining that the detected engagement satisfies the criterion comprises;

determining that at least a predetermined time interval elapsed between the user first receiving the email or text message and the user scrolling down an inbox to open the email or text message, or

determining that the user had the email or text message open for at least a threshold time interval, and wherein determining that the user had the email or text message open for at least the threshold time interval indicates the user fully consumed the email or text message;

based on the determining, identifying one or more interests associated with the particular electronic document template;

storing, in one or more of the databases, one or more associations between the user and the identified one or more interests;

receiving, from a remote computing device operated by the user, a search query;

obtaining content that is responsive to the search query;

ranking the obtained content based on the identified one or more interests; and

providing, to the remote computing device, the ranked content, wherein the providing causes the ranked content to be presented as output at the remote computing device operated by the user.

2. The computer-implemented method of claim 1, wherein detecting the engagement includes determining that the user selected or otherwise operated one or more graphical elements in the email or text message.

3. The computer-implemented method of claim 1, wherein detecting the engagement includes determining that the user labeled the email or text message.

4. The computer-implemented method of claim 1, wherein the one or more interests are identified based on annotations of the particular electronic document template.

5. The computer-implemented method of claim 1, further comprising associating the one or more interests with the particular electronic document template based on a sender address associated with the particular electronic document template.

6. The computer-implemented method of claim 5, wherein the one or more interests include one or more entities mentioned in one or more web documents sharing a domain with the sender address.

7. The computer-implemented method of claim 1, further comprising associating the one or more interests with the particular electronic document template based on one or more entities mentioned in a plurality of emails or text messages used to generate the particular electronic document template.

8. A computer-implemented method comprising:

generating a plurality of electronic correspondence templates, wherein each electronic correspondence template is generated from a plurality of emails or text messages that share fixed content;

determining one or more user interests associated with each of the electronic correspondence templates, wherein the one or more user interests are determined based on one or more aggregate attributes of a corpus of emails or text messages associated with the electronic correspondence template;

storing, in one or more databases, the plurality of electronic correspondence templates, wherein each of the electronic correspondence templates is stored in association with one or more corresponding user interests;

identifying a new email or text message addressed to a user;

selecting, from the one or more databases, a particular electronic correspondence template that corresponds to the new email or text message, wherein the selecting is based on one or more attributes shared between the new email or text message addressed to the user and the selected electronic correspondence template;

detecting, based on interactions by the user with one or more computing devices, engagement by the user with the new email or text message;

determining that the detected engagement satisfies a criterion, wherein satisfaction of the criterion indicates that the user is interested in the new email or text message, and wherein determining that the detected engagement satisfies the criterion comprises determining that at least a predetermined time interval elapsed between the user first receiving the new email or text message and the user scrolling down an inbox to open the new email or text message;

based on the determining, storing, in one or more databases, one or more associations between the user and the one or more interests associated with the particular electronic correspondence template;

receiving, from a remote computing device operated by the user, a search query;

obtaining content that is responsive to the search query;

ranking the obtained content based on the identified one or more interests; and

providing, to the remote computing device, the ranked content, wherein the providing causes the ranked content to be presented as output at the remote computing device operated by the user.

9. The computer-implemented method of claim 8, wherein detecting the engagement further includes determining that the user labeled the new email or text message.

10. The computer-implemented method of claim 8, wherein detecting the engagement further includes determining that at least a predetermined time interval elapsed between the user opening and closing the new email or text message.

11. The computer-implemented method of claim 9, wherein the corpus of emails or text messages includes the plurality of emails or text messages that share fixed content.

12. The computer-implemented method of claim 11, wherein the one or more aggregate attributes are identified based on annotations of the particular electronic correspondence template.

13. The computer-implemented method of claim 11, wherein the one or more aggregate attributes include one or more mentioned entities.

14. The computer-implemented method of claim 8, wherein the corpus of emails or text messages includes one or more web documents associated with a sender of the email or text message addressed to the user.

15. The computer-implemented method of claim 14, wherein the one or more web documents are responsive to a search query that includes a sender of the email or text message addressed to the user.

16. At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to perform the following operations:

generating a plurality of electronic document templates, wherein each electronic document template is generated from a plurality of emails or text messages that share fixed content;

determining one or more user interests associated with each of the electronic document templates, wherein the one or more user interests are determined based on one or more aggregate attributes of a corpus of emails or text messages associated with the electronic document template;

storing, in one or more databases, the plurality of electronic document templates, wherein each of the electronic document templates is stored in association with one or more corresponding user interests;

identifying a given email or text message addressed to a user;

selecting, from the one or more databases, a particular electronic document template that corresponds to the given email or text message, wherein the selecting is based on one or more attributes shared between the given email or text message addressed to the user and the selected electronic document template;

detecting, based on interactions by the user with one or more computing devices, engagement by the user with the given email or text message;

determining that the detected engagement satisfies a criterion, wherein satisfaction of the criterion indicates that the user is interested in the given email or text message, wherein determining that the detected engagement satisfies the criterion comprises determining that the user had the given email or text message open for at least a threshold time interval, and wherein determining that the user had the given email or text message open for at least the threshold time interval indicates the user fully consumed the given email or text message;

based on the determining, identifying, in one or more of the databases, one or more interests associated with the particular electronic document template;

storing, in one or more of the databases, one or more associations between the user and the identified one or more interests;

receiving, from a remote computing device operated by the user, a search query;

obtaining content that is responsive to the search query;

ranking the obtained content based on the identified one or more interests; and

providing, to the remote computing device, the ranked content, wherein the providing causes the ranked content to be presented as output at the remote computing device operated by the user.