Categorizing objects for queries on online social networks

• US 10,102,255 B2
• Filed: 09/08/2016
• Issued: 10/16/2018
• Est. Priority Date: 09/08/2016
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Jain, Dinkar, Gupta, Ashish, Philip, Rose Marie, Raina, Rajat
• Primary Examiner(s): Stevens, Robert
• Application Number:
  US15/260,214
• Publication Number:
  US 20180067945A1
• Time in Patent Office: 768 Days
• Field of Search: 707731
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

In one embodiment, a method includes receiving a query inputted by the user; identifying a set of objects matching the query; calculating, for each identified object, a plurality of category-scores corresponding to a plurality of categories, respectively, wherein each category-score is calculated based on a plurality of sub-scores corresponding to a plurality of scoring axes; categorizing each identified object into a category of the plurality of categories based on the category-scores for the identified object; and sending, to the client system in response to the query, one or more search results corresponding to one or more of the categorized objects for display, each search result referencing the respective categorized object, wherein the one or more categorized objects of the search results comprises objects categorized into one or more selected categories.

Claims

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

receiving, from a client system of a user of an online social network, a query inputted by the user;

identifying a set of objects associated with the online social network matching the query;

calculating, for each identified object, a plurality of category-scores corresponding to a plurality of categories, respectively, wherein each category-score is calculated based on a plurality of sub-scores corresponding to a plurality of scoring axes, respectively, each scoring axis corresponding to a particular factor associated with the respective scoring axis, and wherein each category-score is calculated based on a weighting of the plurality of sub-scores, the weighting for each sub-score being based on the category corresponding to the respective category-score;

categorizing each identified object into a category of the plurality of categories based on the category-scores for the identified object, wherein each identified object is categorized into no more than one category of the plurality of categories; and

sending, to the client system in response to the query, one or more search results corresponding to one or more of the categorized objects for display, each search result referencing the respective categorized object, wherein the one or more categorized objects of the search results comprises objects categorized into one or more selected categories, and wherein for each selected category one of the search results corresponds to a categorized object having a highest calculated category-score corresponding to the respective selected category.

2. The method of claim 1, wherein the weighting of the plurality of sub-scores for at least one category-score comprises a weighted arithmetic mean of the plurality of sub-scores.

3. The method of claim 1, wherein the plurality of categories comprises one or more of a news category, a celebrity category, a commentary category, a domain expert category, a review category, or a how-to category.

4. The method of claim 1, wherein for each identified object, the sub-score corresponding to at least one of the scoring axes is based on one of:

a social-graph affinity of the user with respect to the identified object;

a calculated text similarity between the identified object and the query;

a recency value associated with the identified object;

a calculated topic relevance for the identified object with respect to the query;

or a calculated author quality associated with the identified object.

5. The method of claim 1, wherein the plurality of categories comprises one or more categories determined dynamically based on one or more topics associated with the identified objects.

6. The method of claim 1, wherein the plurality of categories comprises one or more categories determined dynamically based on a language-model analysis of the identified objects.

7. The method of claim 1, wherein the plurality of categories comprises one or more pre-determined categories.

8. The method of claim 1, wherein categorizing each identified object into a category of the plurality of categories is further based on a pre-filtering process.

9. The method of claim 1, wherein categorizing each identified object into a category of the plurality of categories is further based on a natural-language model analysis of the identified object.

10. The method of claim 1, further comprising adjusting the category-scores for one or more of the identified objects based on an author diversity among the categorized objects having the highest calculated category-scores.

11. The method of claim 1, wherein identifying the set of objects associated with the online social network matching the query comprises searching a plurality of verticals to identify a plurality of sub-sets of objects from the plurality of verticals, respectively, that match the search query.

12. The method of claim 11, wherein, for each selected category, the one or more search results categorized into the selected category comprise a set of blended search results, wherein the blended search results are generated by blending the plurality of sub-sets of identified objects from the plurality of verticals.

13. The method of claim 1, further comprising

receiving, from the client system, a request for additional search results associated with a particular category of the plurality of categories;

and

sending, to the client system in response to the request, one or more search results corresponding to the particular category.

14. The method of claim 1, further comprising:

accessing a social graph comprising a plurality of nodes and a plurality of edges connecting the nodes, each of the edges between two of the nodes representing a single degree of separation between them, the nodes comprising;

a first node corresponding to the user; and

a plurality of second nodes corresponding to a plurality of objects associated with the online social network, respectively.

15. The method of claim 14, wherein the one or more selected categories are selected based on a degree of separation between the first node and a one or more second nodes associated with one or more of the selected categories.

16. The method of claim 14, wherein each category-score is calculated further based on a degree of separation between the first node and a second node corresponding to the identified object.

17. The method of claim 14, wherein, for each identified object, at least one sub-score is based on a degree of separation between the first node and a second node corresponding to the identified object.

18. The method of claim 1, furthering comprising, for each selected category, ranking the search results corresponding to the selected category based on the category-score for the categorized object corresponding to the search result.

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

receive, from a client system of a user of an online social network, a query inputted by the user;

identify a set of objects associated with the online social network matching the query;

calculate, for each identified object, a plurality of category-scores corresponding to a plurality of categories, respectively, wherein each category-score is calculated based on a plurality of sub-scores corresponding to a plurality of scoring axes, respectively, each scoring axis corresponding to a particular factor associated with the respective scoring axis, and wherein each category-score is calculated based on a weighting of the plurality of sub-scores, the weighting for each sub-score being based on the category corresponding to the respective category-score;

categorize each identified object into a category of the plurality of categories based on the category-scores for the identified object, wherein each identified object is categorized into no more than one category of the plurality of categories; and

send, to the client system in response to the query, one or more search results corresponding to one or more of the categorized objects for display, each search result referencing the respective categorized object, wherein the one or more categorized objects of the search results comprises objects categorized into one or more selected categories, and wherein for each selected category one of the search results corresponds to a categorized object having a highest calculated category-score corresponding to the respective selected category.

20. A system comprising:

one or more processors; and

a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to;

receive, from a client system of a user of an online social network, a query inputted by the user;

identify a set of objects associated with the online social network matching the query;

calculate, for each identified object, a plurality of category-scores corresponding to a plurality of categories, respectively, wherein each category-score is calculated based on a plurality of sub-scores corresponding to a plurality of scoring axes, respectively, each scoring axis corresponding to a particular factor associated with the respective scoring axis, and wherein each category-score is calculated based on a weighting of the plurality of sub-scores, the weighting for each sub-score being based on the category corresponding to the respective category-score;

categorize each identified object into a category of the plurality of categories based on the category-scores for the identified object, wherein each identified object is categorized into no more than one category of the plurality of categories; and

send, to the client system in response to the query, one or more search results corresponding to one or more of the categorized objects for display, each search result referencing the respective categorized object, wherein the one or more categorized objects of the search results comprises objects categorized into one or more selected categories, and wherein for each selected category one of the search results corresponds to a categorized object having a highest calculated category-score corresponding to the respective selected category.