Granted Patent B1

US 11,100,179 · App. 16/103,775 · Granted Aug 24, 2021

Inventors: Zheng Zhou (San Jose, CA); Kun Han (Mountain View, CA); Fuchun Peng (Cupertino, CA)

Assignee: Facebook, Inc.

G06F16/9535G06F16/248G06F16/24578G06F16/285G06N3/08

Abstract

Claims (71)

1. A method comprising, by one or more computing systems:

receiving, from a client system associated with a first user, a request from the first user for a content digest from an online social network, wherein the content digest comprises a plurality of content objects associated with the online social network that are accessible by the first user;

retrieving, by the one or more computing systems, the plurality of content objects, wherein each content object has a unique identifier;

determining, by the one or more computing systems, a semantical-embedding for each retrieved content object based on a query model, wherein the semantical-embedding for each content object represents a semantical meaning of the respective content object;

generating, by the one or more computing systems, a set of content suggestions for each retrieved content object of the plurality of content objects based on the semantical-embedding of the content object, wherein the set of content suggestions for each content object comprises one or more content suggestions responsive to the respective content object;

ranking, by the one or more computing systems, for each retrieved content object, the one or more content suggestions in the respective set based on a comparison of a semantical-embedding associated with each content suggestion to the semantical-embedding of the content object; and

sending, by the one or more computing systems, instructions for presenting the content digest to the first user within a user interface element, wherein the content digest comprises the plurality of retrieved content objects all within the user interface element, and wherein each content object is presented with the set of content suggestions corresponding to the content object, the content suggestions being presented based on their respective rankings.

2. The method of claim 1 , further comprising:

determining, for each retrieved content object, whether the content object is accessible by the first user based on a privacy setting associated with content object.

3. The method of claim 1 , wherein the request from the first user for the content digest comprises a command to invoke the retrieval of the one or more content objects associated with the online social network.

4. The method of claim 1 , further comprising training the query model by:

accessing a plurality of prior content objects, wherein each of the prior content objects is associated with a predefined category from the plurality of predefined categories;

determining a plurality of semantical-embeddings for the plurality of prior content objects, respectively; and

generating a plurality of clusters of prior content objects based on the semantical-embeddings of the plurality of prior content objects.

5. The method of claim 4 , further comprising training a response model by:

accessing a plurality of prior content responses, wherein each prior content response is associated with a prior content object from the plurality of prior content objects;

determining a plurality of semantical-embeddings for the plurality of prior content responses, respectively; and

generating, for the prior content objects within each predefined category, a plurality of clusters of prior content responses based on the semantical-embeddings of the plurality of prior content responses.

6. The method of claim 5 , wherein training the response model further comprises training a pair NN model by:

selecting a prior content response associated with a prior content object as a positive input for the pair NN model; and

selecting a random prior content response as a negative input for the pair NN model.

7. The method of claim 5 , further comprising:

assigning each of the prior content responses of the plurality prior content responses to its corresponding prior content object, wherein the semantical-embedding of the prior content response is associated with the semantical-embedding of the corresponding prior content object; and

assigning the one or more clusters of prior content responses to one or more clusters of prior content objects.

8. The method of claim 7 , wherein generating the set of content suggestions for each retrieved content object further comprises:

identifying, for each of the retrieved content objects, which cluster of prior content objects the retrieved content object is associated with based on a comparison of the semantical-embedding of the retrieved content object with the semantical-embeddings of the prior content objects in the respective cluster; and

selecting, for each of the retrieved content objects, one or more of the prior content responses from the cluster of prior content responses assigned to the identified cluster of prior content objects as content suggestions for the set of content suggestions for the retrieved content object.

9. The method of claim 1 , wherein the instructions for presenting the content digest comprises presenting a horizontal scroll containing the one or more of the retrieved content objects.

10. The method of claim 1 , wherein the content suggestions comprise one or more of:

a comment;

a like;

an audio clip;

an image;

a video;

a link;

a message; or

a review.

11. The method of claim 1 , wherein the content suggestion comprises an activatable link to generate a comment to be displayed with the corresponding content object.

12. The method of claim 1 , further comprising sending instructions for presenting an updated content digest to the first user responsive to receiving a selection of a content suggestion.

13. The method of claim 12 , wherein the instructions for presenting the updated content digest comprises one or more of:

removing the content digest from presentation to the first user;

removing the non-selected content suggestions from presentation to the first user; or

removing the content object associated with the selected content suggestion from presentation to the first user.

14. The method of claim 1 , further comprising:

accessing a user profile of the first user from a user context engine; and

modifying one or more of the content suggestions based on the user profile of the first user.

15. One or more computer-readable non-transitory storage media embodying software that is configured when executed to:

receive, from a client system associated with a first user, a request from the first user for a content digest from an online social network, wherein the content digest comprises a plurality of content objects associated with the online social network that are accessible by the first user;

retrieve, by the one or more computing systems, the plurality of content objects, wherein each content object has a unique identifier;

determine, by the one or more computing systems, a semantical-embedding for each retrieved content object based on a query model, wherein the semantical-embedding for each content object represents a semantical meaning of the respective content object;

generate, by the one or more computing systems, a set of content suggestions for each retrieved content object of the plurality of content objects based on the semantical-embedding of the content object, wherein the set of content suggestions for each content object comprises one or more content suggestions responsive to the respective content object;

rank, by the one or more computing systems, for each retrieved content object, the one or more content suggestions in the respective set based on a comparison of a semantical-embedding associated with each content suggestion to the semantical-embedding of the content object; and

send, by the one or more computing systems, instructions for presenting the content digest to the first user within a user interface element, wherein the content digest comprises the plurality of retrieved content objects all within the user interface element, and wherein each content object is presented with the set of content suggestions corresponding to the content object, the content suggestions being presented based on their respective rankings.

16. A system comprising: one or more processors; and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors configured when executing the instructions to:

receive, from a client system associated with a first user, a request from the first user for a content digest from an online social network, wherein the content digest comprises a plurality of content objects associated with the online social network that are accessible by the first user;

retrieve, by the one or more computing systems, the plurality of content objects, wherein each content object has a unique identifier;

determine, by the one or more computing systems, a semantical-embedding for each retrieved content object based on a query model, wherein the semantical-embedding for each content object represents a semantical meaning of the respective content object;

generate, by the one or more computing systems, a set of content suggestions for each retrieved content object of the plurality of content objects based on the semantical-embedding of the content object, wherein the set of content suggestions for each content object comprises one or more content suggestions responsive to the respective content object;

rank, by the one or more computing systems, for each retrieved content object, the one or more content suggestions in the respective set based on a comparison of a semantical-embedding associated with each content suggestion to the semantical-embedding of the content object; and

send, by the one or more computing systems, instructions for presenting the content digest to the first user within a user interface element, wherein the content digest comprises the plurality of retrieved content objects all within the user interface element, and wherein each content object is presented with the set of content suggestions corresponding to the content object, the content suggestions being presented based on their respective rankings.

17. The system of claim 16 , wherein the processors are further operable when executing the instructions to:

determine, for each retrieved content object, whether the content object is accessible by the first user based on a privacy setting associated with content object.

18. The system of claim 16 , wherein the request from the first user for the content digest comprises a command to invoke the retrieval of the one or more content objects associated with the online social network.

19. The system of claim 16 , wherein the processors are further operable when executing the instructions to:

access a plurality of prior content objects, wherein each of the prior content objects is associated with a predefined category from the plurality of predefined categories;

determine a plurality of semantical-embeddings for the plurality of prior content objects, respectively; and

generate a plurality of clusters of prior content objects based on the semantical-embeddings of the plurality of prior content objects.

20. The system of claim 16 , wherein the processors are further operable when executing the instructions to:

access a plurality of prior content responses, wherein each prior content response is associated with a prior content object from the plurality of prior content objects;

determine a plurality of semantical-embeddings for the plurality of prior content responses, respectively; and

generate, for the prior content objects within each predefined category, a plurality of clusters of prior content responses based on the semantical-embeddings of the plurality of prior content responses.

Assignments (2)

Cited By (10)

US 12,353,897 US 12,373,478 US 12,443,797 US 12,450,276 US 12,495,098 US 12,541,562 US 12,567,404 US 12,592,017 US 12,625,557 US 12,670,671