GENERATIVE GRAMMAR MODELS FOR EFFECTIVE PROMOTION AND ADVERTISING

• US 20170249302A1
• Filed: 05/15/2017
• Published: 08/31/2017
• Est. Priority Date: 09/29/2014
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Churchill, Elizabeth, Das Sarma, Atish, Sherman, Corinne Elizabeth, Singh, Gyanit
• Granted Patent: US 10,073,841 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G06Q 30/0239 Online discounts or incentives
• CPC Class Codes: G06Q 30/0276 Advertisement creation
• CPC Class Codes: H04L 51/066 Format adaptation, e.g. format conversion or compression
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 51/58 Message adaptation for wireless communication

Abstract

A system comprising a computer-readable storage medium storing at least one program and a computer-implemented method for creating messages using generative grammar models is presented. Consistent with some embodiments, the method may include receiving a request to generate a message, which in an example embodiment is to be published to a social network platform. In response to receiving the request, a generative grammar model defining the structure of the message is accessed. The generative grammar model may include a number of blanks and may specify a source along with a grammatical constraint for a term to populate each blank. The method may further include generating the message in accordance with the generative grammar model, and causing the generated message to be published.

Claims

1. (canceled)

2. A system comprising:

one or more processors of a machine; and

a machine-readable medium storing instructions that, when executed by the one or more processors, cause the machine to perform operations comprising;

receiving a request to generate a message;

selecting a generative grammar model from the plurality of generative grammar models in response to receiving the request, the generative grammar model defining a message structure for the requested message, the message structure including a plurality of lexical slots, the generative grammar model specifying;

a corpus of source data to populate each lexical slot in the plurality of lexical slots; and

a grammatical constraint for each lexical slot in the plurality of lexical slots;

generating the message using the generative grammar model; and

causing the message to be published on a content publishing platform.

3. The system of claim 2, wherein each of the plurality of lexical slots includes a blank in the message structure to be populated with information from the corresponding corpus of source data.

4. The system of claim 2, wherein the request specifies the content publishing platform for publishing the message, and wherein the generative grammar model is selected based on the content publishing platform specified in the request.

5. The system of claim 2, wherein the grammatical constraint for each lexical slot specifies a part of speech for a term to populate the lexical slot.

6. The system of claim 2, wherein the generating the message comprises:

for each lexical slot in the plurality of lexical slots;

accessing the corpus of source data corresponding to the lexical slot;

extracting a term from the corpus of source data in accordance with the grammatical constraint corresponding to the lexical slot; and

populating the lexical slot with the extracted term.

7. The system of claim 6, wherein at least one of the extracted terms is a hashtag.

8. The system of claim 3, further comprising verifying that the message adheres to a particular messaging standard.

9. A method comprising:

receiving a request to generate a message;

selecting a generative grammar model from the plurality of generative grammar models in response to receiving the request, the generative grammar model defining a message structure for the requested message, the message structure including a plurality of lexical slots, the generative grammar model specifying;

a corpus of source data to populate each lexical slot in the plurality of lexical slots; and

a grammatical constraint for each lexical slot in the plurality of lexical slots;

generating, by a hardware processor, the message using the generative grammar model; and

causing the message to be published on a content publishing platform.

10. The method of claim 9, wherein the request to generate the message is generated as part of a request to share content received at a share widget presented in conjunction with the content.

11. The method of claim 9, wherein the generative grammar model is developed in accordance with messaging conventions specific to the content publishing platform.

12. The method of claim 9, wherein the generating of the message comprises:

for each lexical slot in the plurality of lexical slots;

accessing the corpus of source data corresponding to the lexical slot;

selecting a term from the corpus of source data in accordance with the grammatical constraint corresponding to the lexical slot; and

populating the lexical slot with the selected term.

13. The method of claim 12, wherein the grammatical constraint specifies a lexical category, and wherein the selected term corresponds to the lexical category.

14. The method of claim 12, wherein the generating of the message further comprises appending an octothorpe to the selected term prior to populating the lexical slot.

15. The method of claim 12, wherein the selecting of the term is based on trending information obtained from a social network platform.

16. The method of claim 9, wherein the generative grammar model is selected based on at least one of:

the content publishing platform to which the message is to published, a particular user who submitted the request, a potential viewing audience of the message, and content associated with the request.

17. The method of claim 9, wherein at least a portion of the lexical slots are prepopulated with terms.

18. The method of claim 9, wherein corpus of source data is organized in segmented into a plurality of categories, each category corresponding to one of a plurality of grammatical constraints.

19. The method of claim 9, wherein the generative grammar model corresponds to a user profile corresponding to a user of the client device from which the request is received.

20. The method of claim 9, further comprising verifying that the generated message adheres to a limitation imposed by the content publishing platform.

21. A non-transitory machine-readable storage medium embodying instructions that, when executed by a machine, cause the machine to perform operations comprising:

receiving a request to generate a message;

selecting a generative grammar model from the plurality of generative grammar models in response to receiving the request, the generative grammar model defining a message structure for the requested message, the message structure including a plurality of lexical slots, the generative grammar model specifying;

a corpus of source data to populate each lexical slot in the plurality of lexical slots; and

a grammatical constraint for each lexical slot in the plurality of lexical slots;

generating, by a hardware processor, the message using the generative grammar model; and

causing the message to be published on a content publishing platform.