System and method for targeting information based on message content in a reply

• US 9,911,144 B1
• Filed: 02/10/2017
• Issued: 03/06/2018
• Est. Priority Date: 09/04/2009
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Sheinberg, Alan B., Chen, Stanley
• Primary Examiner(s): Gilles, Jude Jean
• Application Number:
  US15/429,661
• Time in Patent Office: 389 Days
• Field of Search: 709200, 709204-207, 709247, 709218, 709219, 709224
• 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: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: G06Q 30/0244 Optimization
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: G06Q 30/0278 Product appraisal
• CPC Class Codes: H04L 51/00 User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
• CPC Class Codes: H04L 51/04 Real-time or near real-time messaging, e.g. instant messaging [IM]
• CPC Class Codes: H04L 51/18 Commands or executable codes

Abstract

A method of presenting information to a party through a messaging application is described. Responsive to receipt of a communication from a party (e.g., the first user), a reply is sent. The communication and the reply is presented in an interface to the sender. The messaging system determines matching content that is relevant to one or both of the communication and the reply and determines a quality of the match. Determining the quality of the match may include determining a score for an advertisement based on the advertisement'"'"'s responsiveness to content identified in the reply message that was sent. Based on a determination that the quality is above a threshold, the matching content is presented along with the communication and the reply.

Claims

1. A method performed by one or more processing devices, the method comprising:

identifying, by at least one processing device, an electronic conversation between at least two users, the electronic conversation comprising at least;

(i) a communication message of the electronic conversation, and

(ii) a reply message of the electronic conversation that is responsive to the communication message;

determining, by the at least one processing device, one or more content categories that correspond to at least;

(i) the communication message of the electronic conversation, or

(ii) the reply message of the electronic conversation;

generating, by the at least one processing device, content based on the determined one or more content categories, where generating the content comprises;

extracting a subset of terms from the electronic conversation;

identifying information relevant to the electronic conversation based on analysis of the extracted subset of terms; and

generating the content using the identified information relevant to the electronic conversation; and

generating, by the at least one processing device, a concurrent presentation of the content and the reply message in a graphical user interface.

2. The method of claim 1, wherein determining the one or more content categories comprises:

associating, by the at least one processing device, the electronic conversation with at least a first category of the one or more content categories, the first category comprising a category identifier.

3. The method of claim 2, wherein generating the content comprises:

extracting the subset of terms from at least one message of the electronic conversation based on the category identifier, where extracting the subset of terms comprises using the category identifier to extract terms that correspond to the category identifier.

4. The method of claim 3, wherein of the electronic conversation, the subset of terms are extracted from a body of the communication message or a body of the reply message.

5. The method of claim 1, wherein determining the one or more content categories comprises:

determining, by the at least one processing device, a number of content elements that are associated with a particular category of a category content list, the content elements comprising one or more terms included in the electronic conversation; and

determining, by the at least one processing device, the one or more content categories when the number of content elements has reached a threshold number.

6. The method of claim 5, wherein determining the number of content elements that are associated with a particular category of the category content list comprises:

comparing the category content list to content of the electronic conversation by at least one of;

identifying a number of times a particular content element of the category content list appears in the electronic conversation;

or

determining the highest ratio of content elements which belong to the particular category as compared to a total number of content elements present in the electronic conversation.

7. The method of claim 1, wherein the communication message comprises text that was sent from a first user account for delivery to a second user account, and wherein the reply message comprises at least text being drafted by a user of the second user account for delivery to the first user account.

8. The method of claim 7, generating the presentation of the content and the reply in a graphical user interface comprises:

causing the content to be positioned proximate to the reply in the graphical user interface at a display of a computer that is logged into the second user account while the reply is being drafted by a user of the second account at the computer.

9. The method of claim 1, wherein determining the one or more content categories comprises:

identifying a first selected message of the electronic conversation based on at least one of a display mode of the first selected message or a time factor of the first selected message, the first selected message being one of the communication message or the reply message; and

determining, by the at least one processing device, one or more content categories using text of the first selected message.

10. The method of claim 9, wherein the display mode is an expanded display mode and the time factor indicates that a particular message is the most recently received message.

11. The method of claim 9, wherein the content comprises one of an advertisement or active content, and the one or more content categories comprises one of categories of things, categories of activities, categories of processes, or categories of concepts.

21. The method of claim 1, wherein the determining the one or more content categories includes:

accessing the reply message of the electronic conversation;

analyzing one or more terms included in the reply message; and

determining the one or more content categories based on the analysis of the one or more terms included in the reply message.

22. The method of claim 1, wherein the electronic conversation is accessible via a client device and generating the content comprises:

receiving, at the client device, the content from a content source that is external to the client device, the external content source being an information service that is configured to extract one or more terms of the electronic conversation.

23. The method of claim 2, wherein generating the content comprises:

accessing a filter data structure that stores a filtering list, the filtering list including the category identifier and content elements that correspond to the first category; and

extracting the subset of terms from a portion of the electronic conversation using the filtering list, where extracting the subset of terms includes filtering out terms in the portion of the electronic conversation that match the content elements of the filtering list.

24. The method of claim 2, wherein generating the content comprises:

accessing an anonymization filter configured to anonymize personally identifiable information included in the electronic conversation, the personally identifiable information comprising an identifier for a participant in the electronic conversation; and

extracting the subset of terms from a portion of the electronic conversation using the anonymization filter, where extracting the subset of terms includes filtering out the personally identifiable information.

12. An electronic system comprising:

one or more processing devices; and

one or more non-transitory computer-readable media storing instructions that are executable by the one or more processing devices to cause performance of operations comprising;

identifying, by at least one processing device, an electronic conversation between at least two users, the electronic conversation comprising at least;

(i) a communication message of the electronic conversation, and

(ii) a reply message of the electronic conversation that is responsive to the communication message;

determining, by the at least one processing device, one or more content categories that correspond to at least;

(i) a communication message of the electronic conversation, or

(ii) a reply message of the electronic conversation that is responsive to the communication message;

generating, by the at least one processing device, content based on the determined one or more content categories, where generating the content comprises;

extracting a subset of terms from the electronic conversation;

identifying information relevant to the electronic conversation based on analysis of the extracted subset of terms; and

generating the content using the identified information relevant to the electronic conversation; and

generating, by the at least one processing device, a concurrent presentation of the content and the reply message in a graphical user interface.

13. The electronic system of claim 12, wherein determining the one or more content categories comprises:

associating, by the at least one processing device, the electronic conversation with at least a first category of the one or more content categories, the first category comprising a category identifier.

14. The electronic system of claim 13, wherein generating the content comprises:

extracting the subset of terms from at least one message of the electronic conversation based on the category identifier, where extracting the subset of terms comprises using the category identifier to extract terms that correspond to the category identifier.

15. The electronic system of claim 14, wherein of the electronic conversation, the subset of terms are extracted from a body of the communication message or a body of the reply message.

16. The electronic system of claim 12, wherein determining the one or more content categories comprises:

determining, by the at least one processing device, a number of content elements that are associated with a particular category of a category content list, the content elements comprising one or more terms included in the electronic conversation; and

determining, by the at least one processing device, the one or more content categories when the number of content elements has reached a threshold number.

17. The electronic system of claim 12, wherein determining the one or more content categories comprises:

identifying a first selected message of the electronic conversation based on at least one of a display mode of the first selected message or a time factor of the first selected message, the first selected message being one of the communication message or the reply message; and

determining, by the at least one processing device, one or more content categories using text of the first selected message.

18. The electronic system of claim 12, wherein the communication message comprises text that was sent from a first user account for delivery to a second user account, and wherein the reply message comprises at least text being drafted by a user of the second user account for delivery to the first user account.

19. The electronic system of claim 12, wherein the content comprises one of an advertisement or active content, and the one or more content categories comprises one of categories of things, categories of activities, categories of processes, or categories of concepts.

20. One or more non-transitory computer-readable media storing instructions that are executable by one or more processing devices to cause performance of operations comprising:

identifying, by at least one processing device, an electronic conversation between at least two users, the electronic conversation comprising at least;

(i) a communication message of the electronic conversation, and

(ii) a reply message of the electronic conversation that is responsive to the communication message;

determining, by the at least one processing device, one or more content categories that correspond to at least;

(i) a communication message of the electronic conversation, or

(ii) a reply message of the electronic conversation that is responsive to the communication message;

generating, by the at least one processing device, content based on the determined one or more content categories, where generating the content comprises;

extracting a subset of terms from the electronic conversation;

identifying information relevant to the electronic conversation based on analysis of the extracted subset of terms; and

generating the content using the identified information relevant to the electronic conversation; and

generating, by the at least one processing device, a concurrent presentation of the content and the reply message in a graphical user interface.