PERSONALIZED SEARCH USING SEARCHER FEATURES

• US 20160034466A1
• Filed: 11/12/2014
• Published: 02/04/2016
• Est. Priority Date: 07/31/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Linkedln Corporation
• Inventors: Sinha, Shakti Dhirendraji, Makhani, Asif Mansoor Ali, Ha, Viet Thuc, Guo, Lin, Sundaram, Senthil
• Granted Patent: US 9,760,610 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 67/306 User profiles

Abstract

A system and method for personalized search user searcher features may include obtaining a search term from a member of a social network at a user device via the network interface. An initial result may be generated based on the search term, including a first group of content items from a social network and stored in a content database, the content items including member profiles of members of the social network. Each of the content items of the first group may be ranked based on information indicative of interactions from an activity database with the content items of the first group, the interactions being by at least a second user of the social network different than the first user. A second group of the content items may be displayed, including at least some of the first group of the content items, based on the rank of the first group of the content items.

Claims

1. A method, comprising:

obtaining, with a processor, a search term from a first user at a user device via a network interface;

generating, based on the search term, an initial result including a first group of content items as stored in a content database, the content items from a social network, the content items including member profiles of members of the social network;

ranking, with the processor, each of the content items of the first group based, at least in part, on information indicative of interactions from an activity database with the content items of the first group, the interactions being by at least a second user of the social network different than the first user, the activity database storing the information indicative of the interactions related to the social network with search results that include ones of the content items; and

causing the user device to display a second group of the content items, including at least some of the first group of the content items, according to the rank of the first group of the content items.

2. The method of claim 1, further comprising determining an interaction score for each of the content times of the first group based on the interactions associated with the content items;

and

wherein ranking the content items of the first group is based, at least in part, on the interactions score for each of the content items of the first group.

3. The method of claim 2, wherein determining the interaction score for the content items of the first group is based, at least in part, on a number of interactions with a content item of the first group and a degree of involvement with the content item of the first group indicated by the interactions with the content item of the first group.

4. The method of claim 3, wherein the degree of involvement provides a higher score for interactions indicative of high involvement with an associated content item than interactions indicative of low involvement with an associated content item.

5. The method of claim 2, wherein the interaction score is weighted based on at least one of an elapsed time since an interaction with the content item of the first group occurred and a pervious search term that produced the interaction.

6. The method of claim 5, wherein each interaction of an interaction score for an associated content item is separately weighted based on the elapsed time since the interaction occurred.

7. The method of claim 5, wherein the interaction score is weighted based on a relationship of the previous search term to the search term as obtained from the user device.

8. The method of claim 7, wherein the relationship of the previous search term to the search term as obtained from the user device is based on a degree to which the previous search term and the search term as obtained from the user device produce similar search results.

9. The method of claim 8, wherein the interaction score is weighted higher for previous search terms that produce more search results the same as the search result as obtained.

10. The method of claim 8, further comprising obtaining, with the processor, current search results based on the previous search term and compare search results obtained by the previous search term with the initial result and wherein the interaction score is weighted based on a number of common search results between the initial result and the search results obtained by the previous search term.

11. A computer readable medium comprising instructions that, when executed on a processor, cause the processor to implement operations comprising:

obtaining a search term from a first user at a user device via a network interface;

generating an initial result including a first group of content items as stored in a content database, the content items from a social network, the content items including member profiles of members of the social network;

ranking each of the content items of the first group based, at least in part, on information indicative of interactions from an activity database with the content items of the first group, the interactions being by at least a second user of the social network different than the first user, the activity database storing the information indicative of the interactions related to the social network with search results that include ones of the content items; and

causing the user device to display a second group of the content items, including at least some of the first group of the content items, according to the rank of the first group of the content items.

12. The computer readable medium of claim 11, further comprising determining an interaction score for each of the content times of the first group based on the interactions associated with the content items;

and

wherein ranking the content items of the first group is based, at least in part, on the interactions score for each of the content items of the first group.

13. The computer readable medium of claim 12, wherein determining the interaction score for the content items of the first group is based, at least in part, on a number of interactions with a content item of the first group and a degree of involvement with the content item of the first group indicated by the interactions with the content item of the first group.

14. The computer readable medium of claim 13, wherein the degree of involvement provides a higher score for interactions indicative of high involvement with an associated content item than interactions indicative of low involvement with an associated content item.

15. The computer readable medium of claim 12, wherein the interaction score is weighted based on at least one of an elapsed time since an interaction with the content item of the first group occurred and a pervious search term that produced the interaction.

16. The computer readable medium of claim 15, wherein each interaction of an interaction score for an associated content item is separately weighted based on the elapsed time since the interaction occurred.

17. The computer readable medium of claim 15, wherein the interaction score is weighted based on a relationship of the previous search term to the search term as obtained from the user device.

18. The computer readable medium of claim 17, wherein the relationship of the previous search term to the search term as obtained from the user device is based on a degree to which the previous search term and the search term as obtained from the user device produce similar search results.

19. The computer readable medium of claim 18, wherein the interaction score is weighted higher for previous search terms that produce more search results the same as the search result as obtained.

20. The computer readable medium of claim 18, further comprising obtaining, with the processor, current search results based on the previous search term and compare search results obtained by the previous search term with the initial result and wherein the interaction score is weighted based on a number of common search results between the initial result and the search results obtained by the previous search term.