Coefficients attribution for different objects based on natural language processing

• US 9,530,167 B2
• Filed: 08/12/2011
• Issued: 12/27/2016
• Est. Priority Date: 08/12/2011
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Tseng, Erick
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): THOMAS-HOMESCU, ANNE L
• Application Number:
  US13/209,207
• Publication Number:
  US 20130041653A1
• Time in Patent Office: 1,964 Days
• Field of Search: 709223-229, 709202-206, 709/217, 709/213, 709/218, 709/231, 709/250, 707/711, 707/714, 707722-723, 707/769, 707/748, 707/784, 707/607, 707/756, 707/737, 707/709, 707/798, 707/740, 707/777, 704/278, 704/9, 706/12, 706/46, 715/753, 715/230, 715/234, 715/854, 715/756, 715/751, 715/810, 715/752, 726/1, 726/2, 726/4, 705/26.5, 705/26.7, 705/14.16, 705/38, 705/321, 705/44, 705/5, 705/14.49, 705/325, 705/7.33, 705/308, 705/35, 705/2, 705/59, 705/14.12, 705/26, 705/14, 705/319, 705/7
• US Class Current: 1/1
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/904 Browsing; Visualisation therefor for navigating the web G06F16/954; browsing optimisation for the web G06F16/957
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

In one embodiment, a system includes one or more computing systems that implement a social networking environment and is operable to parse users'"'"' actions that include free form text to determine and store objects and affinities contained in the text string through natural-language processing. The method comprises accessing a text string, identifying objects and affinity declarations via natural-language processing, assessing the combination of objects and context data to determine an instance of a broader concept, and determining an affinity coefficient through a natural-language processing dictionary. Once a database of stored instances and affinities has been generated and stored, it may be leveraged to push suggestions to members of the social network to enhance their social networking experience.

Claims

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

accessing a social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, the nodes corresponding to a plurality of content objects associated with an online social network;

receiving an input from a user, wherein the input comprises free-form text;

determining, through application of natural-language processing of the free-form text, one or more objects associated with the input, each object corresponding to one of the plurality of nodes in the social graph, wherein each of the one or more objects comprises a noun detected in the free-form text;

determining, through application of natural-language processing of the free-form text, one or more affinity declarations associated with the one or more objects;

determining, from the one or more objects, a first concept and a second concept, the first concept corresponding to a first node in the social graph, the second concept corresponding to a second node in the social graph, wherein the first concept is a specific instance of the second concept;

determining a first affinity coefficient between the user and the first concept based on the one or more affinity declarations;

inferring a second affinity coefficient between the user and the second concept, wherein the inference is based on;

the first affinity coefficient; and

social networking information of the user;

storing the first affinity coefficient in a data store in association with the user and the first concept;

dynamically adjusting the inferred second affinity coefficient based on social-networking information of the user, wherein the social-networking information reinforces or reduces the inferred second affinity coefficient; and

upon determining that the inferred second affinity coefficient for a threshold number of users exceeds a predetermined number, creating a hub page associated with the first concept for display on an online social network.

2. The method of claim 1, wherein the input further comprises context data.

3. The method of claim 2, wherein the context data comprises a location.

4. The method of claim 2, wherein the context data comprises a time.

5. The method of claim 2, wherein the context data comprises a check-in to a particular location.

6. The method of claim 2, wherein the context data is inferred based on an element that the input acts on.

7. The method of claim 1, wherein the first affinity coefficient is a positive or negative numerical value.

8. The method of claim 7, wherein the natural-language processing utilizes a dictionary comprising crowd-sourced adjectives or objects.

9. The method of claim 8, wherein the first affinity coefficient is based on the relative strength of the adjectives found in the one or more affinity declarations.

10. The method of claim 1, wherein the first node is hidden from users of a social network accessing the social graph.

11. The method of claim 10, wherein storing the first affinity coefficient comprises creating an edge connecting a node representing the user and the node representing the first instance.

12. The method of claim 1, wherein the user is represented by a user node in a social graph, and the first instance is represented by a concept node in the social graph, and wherein storing the first affinity coefficient comprises creating an edge connecting the user node and concept node.

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

accessing a social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, the nodes corresponding to a plurality of content objects associated with an online social network;

receiving an input from a user, wherein the input comprises free-form text;

determining, through application of natural-language processing of the free-form text, one or more objects associated with the input, each object corresponding to one of the plurality of nodes in the social graph, wherein each of the one or more objects comprises a noun detected in the free-form text;

determining, through application of natural-language processing of the free-form text, one or more affinity declarations associated with the one or more objects;

determining, from the one or more objects, a first concept and a second concept the first concept corresponding to a first node in the social graph, the second concept corresponding to a second node in the social graph, wherein the first concept is a specific instance of the second concept;

determining a first affinity coefficient between the user and the first concept based on the one or more affinity declarations;

inferring a second affinity coefficient between the user and the second concept, wherein the inference is based on;

the first affinity coefficient; and

social networking information of the user;

storing the first affinity coefficient in a data store in association with the user and the first concept;

dynamically adjusting the inferred second affinity coefficient based on social-networking information of the user, wherein the social-networking information reinforces or reduces the inferred second affinity coefficient; and

upon determining that the inferred second affinity coefficient for a threshold number of users exceeds a predetermined number, creating a hub page associated with the first concept for display on an online social network.

14. The method of claim 13, wherein the positive affinity coefficients are above a predetermined numerical value.

15. A non-transitory, computer-readable media comprising instructions, the instructions operable, when executed, to:

access a social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, the nodes corresponding to a plurality of content objects associated with an online social network;

receive an input from a user, wherein the input comprises free-form text;

determine, through application of natural-language processing of the free-form text, one or more objects associated with the input, each object corresponding to one of the plurality of nodes in the social graph, wherein each of the one or more objects comprises a noun detected in the free-form text;

determine, through application of natural-language processing of the free-form text, one or more affinity declarations associated with the one or more objects;

determine, from the one or more objects, a first concept and a second concept, the first concept corresponding to a first node in the social graph, the second concept corresponding to a second node in the social graph, wherein the first concept is a specific instance of the second concept;

determine a first affinity coefficient between the user and the first concept based on the one or more affinity declarations;

infer a second affinity coefficient between the user and the second concept, the second instance corresponding to a second node in the social graph, wherein the inference is based on;

the first affinity coefficient; and

social networking information of the user;

store the first affinity coefficient in a data store in association with the user and the first concept;

dynamically adjust the inferred second affinity coefficient based on social-networking information of the user, wherein the social-networking information reinforces or reduces the inferred second affinity coefficient; and

upon determining that the inferred second affinity coefficient for a threshold number of users exceeds a predetermined number, creating a hub page associated with the first concept for display on an online social network.

16. The media of claim 15, wherein the input further comprises context data.

17. The media of claim 16, wherein the context data comprises a location or time.

18. The media of claim 16, wherein the context data comprises a check-in to a particular location.

19. The media of claim 16, wherein the context data is inferred based on an element that the input acts on.