Method and system for generating synthetic video advertisements

Patent metadata

Field	Value
Publication number	US-12334115-B2
Application number	US-202418440353-A
Country	US
Kind code	B2
Filing date	Feb 13, 2024
Priority date	Dec 26, 2022
Publication date	Jun 17, 2025
Grant date	Jun 17, 2025

Abstract

In one aspect, an example method includes (i) obtaining a set of user attributes for a user of a content-presentation device; (ii) based on the set of user attributes, obtaining structured data and determining a textual description of the structured data; (iii) transforming, using a text-to-speech engine, the textual description of the structured data into synthesized speech; and (iv) generating, using the synthesized speech and for display by the content-presentation device, a synthetic video of a targeted advertisement comprising the synthesized speech.

First claim

What is claimed is:

1. A computing system comprising a processor and a non-transitory computer-readable medium having stored thereon program instructions that upon execution by the processor cause performance of a set of acts comprising:
obtaining a set of user attributes for a user, the user being a user of a content-presentation device, wherein the set of user attributes comprises a user-preferred product or a user-preferred service;
based on the obtained set of user attributes, obtaining structured data and determining a textual description of the obtained structured data, wherein the structured data comprises one or more images of the user-preferred product or the user-preferred service and wherein the textual description of the structured data comprises a narrative advertising the user-preferred product or the user-preferred service;
transforming, using a text-to-speech engine, the textual description of the obtained structured data into synthesized speech; and
generating, using the synthesized speech and for display by the content-presentation device, a synthetic video of a targeted advertisement comprising the synthesized speech.

2. The computing system of claim 1 , wherein:
obtaining the structured data and determining the textual description of the structured data based on the set of user attributes comprises selecting one or more images and text having parameters that match one or more user attributers of the set of user attributes and determining a textual description of the structured data that includes the selected text, and
generating the synthetic video of the targeted advertisement comprises generating a synthetic video of a targeted advertisement that includes the selected one or more images.

3. The computing system of claim 1 , wherein determining the textual description of the structured data based on the set of user attributes comprises generating, using a natural language generator, a textual description of the structured data that includes a textual representation of at least one of the user attributes from the set of user attributes.

4. The computing system of claim 1 , wherein the set of user attributes comprises one or more of a name of the user, a geographic area of the user, or an employer of the user.

5. The computing system of claim 1 , wherein:
the set of user attributes comprises a user-preferred language, and
determining the textual description of the structured data based on the set of user attributes comprises generating, using a natural language generator, a textual description of the structured data in the user-preferred language.

6. The computing system of claim 1 , wherein:
the set of acts further comprises determining one or more of a time of year and current weather associated with a geographic area of the user,
obtaining the structured data is further based on one or more of the determined time of year or the determined current weather.

7. The computing system of claim 1 , wherein:
the set of acts further comprises selecting a set of characteristics of an advertisement spokesperson based on the set of user attributes,
generating the synthetic video comprises generating a synthetic video including a spokesperson for the targeted advertisement, the spokesperson being synthetically-generated according to the selected set of characteristics.

8. The computing system of claim 1 , wherein:
the set of acts further comprises selecting, from a plurality of advertisement templates, an advertisement template corresponding to one or more user attributes of the set of user attributes,
generating the synthetic video comprises generating the synthetic video according to the selected advertisement template.

9. A method performed by a computing system, the method comprising:
obtaining a set of user attributes for a user, the user being a user of a content-presentation device, wherein the set of user attributes comprises a user-preferred product or a user-preferred service;
based on the obtained set of user attributes, obtaining structured data and determining a textual description of the obtained structured data, wherein the structured data comprises one or more images of the user-preferred product or the user-preferred service and wherein the textual description of the structured data comprises a narrative advertising the user-preferred product or the user-preferred service;
transforming, using a text-to-speech engine, the textual description of the obtained structured data into synthesized speech; and
generating, using the synthesized speech and for display by the content-presentation device, a synthetic video of a targeted advertisement comprising the synthesized speech.

10. The method of claim 9 , wherein:
obtaining the structured data and determining the textual description of the structured data based on the set of user attributes comprises selecting one or more images and text having parameters that match one or more user attributers of the set of user attributes and determining a textual description of the structured data that includes the selected text, and
generating the synthetic video of the targeted advertisement comprises generating a synthetic video of a targeted advertisement that includes the selected one or more images.

11. The method of claim 9 , wherein determining the textual description of the structured data based on the set of user attributes comprises generating, using a natural language generator, a textual description of the structured data that includes a textual representation of at least one of the user attributes from the set of user attributes.

12. The method of claim 9 , wherein the set of user attributes comprises one or more of a name of the user, a geographic area of the user, or an employer of the user.

13. The method of claim 9 , wherein:
the set of user attributes comprises a user-preferred language, and
determining the textual description of the structured data based on the set of user attributes comprises generating, using a natural language generator, a textual description of the structured data in the user-preferred language.

14. The method of claim 9 , further comprising determining a time of year and current weather associated with a geographic area of the user,
wherein obtaining the structured data is further based on one or more of the determined time of year or the determined current weather.

15. The method of claim 9 , further comprising selecting a set of characteristics of an advertisement spokesperson based on the set of user attributes,
wherein generating the synthetic video comprises generating a synthetic video including a spokesperson for the targeted advertisement, the spokesperson being synthetically-generated according to the selected set of characteristics.

16. The method of claim 9 , further comprising selecting, from a plurality of advertisement templates, an advertisement template corresponding to one or more user attributes of the set of user attributes,
wherein generating the synthetic video comprises generating the synthetic video according to the selected advertisement template.

17. A non-transitory computer-readable medium having stored thereon program instructions that upon execution by a computing system, cause performance of a set of acts comprising:
obtaining a set of user attributes for a user, the user being a user of a content-presentation device, wherein the set of user attributes comprises a user-preferred product or a user-preferred service;
based on the obtained set of user attributes, obtaining structured data and determining a textual descri

Assignees

• Roku Inc

Inventors

• Ramesh Sunil
• Cutter Michael
• Pinkerton Charles Brian
• Levitian Karina

Classifications

• G10L13/02

  Methods for producing synthetic speech; Speech synthesisers · CPC title

• G06Q30/0271 Primary

  Personalized advertisement · CPC title

• G10L13/047

  Architecture of speech synthesisers · CPC title

• G11B27/031 Primary

  Electronic editing of digitised analogue information signals, e.g. audio or video signals · CPC title

• G06Q30/0255

  based on user history · CPC title