IP Library › Granted Patent US 10,007,719
Granted Patent B2
US 10,007,719 · App. 14/611,110 · Granted Jun 26, 2018

Compensating for individualized bias of search users

Inventors: Eric Joel Horvitz (Kirkland, WA); Ahmed Hassan Awadallah (Redmond, WA); Ryen William White (Woodinville, WA)
Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
G06F17/30637
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,007,719
App. No.
14/611,110
Granted
Jun 26, 2018
Kind
B2
Abstract

Biases in search and retrieval (i.e., situations where searchers seek or are presented with information that significantly deviates from the truth) may be detected by comparison to one or more authoritative sources. Once bias or potential bias is detected, techniques may be applied to indicate and/or compensate for the bias. Such techniques may allow users to more easily assess the veracity of search results, and increase the chances that users will locate accurate answers to their questions.

Claims (83)

1. A computing device comprising:

one or more communication connections;

one or more processors; and

memory communicatively coupled to the one or more communication connections and the one or more processors, the memory storing instructions that, when executed, configure the one or more processors to perform operations comprising:

receiving a search query including one or more search terms input by a user;

detecting a first term, from among the one or more search terms, by comparing terms of the one or more search terms with a collection of predetermined biasing terms stored in the memory, the first term previously having been determined to be biasing based on one of aggregate search behavior or an authority;

reformulating the search query to generate a reformulated search query to compensate for the biasing, wherein reformulating the search query includes at least one of replacing the first term with a second term or removing the first term;

obtaining search results based at least in part on the reformulated search query; and

outputting the search results for presentation to the user.

2. The computing device of claim 1 , wherein:

the first term comprises a colloquial term; and

the second term having substantially the same meaning as the first term but previously having been determined to produce search results that are more authoritative than search results produced by the first term.

3. The computing device of claim 1 , wherein:

the first term comprises affirmative terms that imply an affirmative relationship between other terms of the one or more search terms in the search query; and

second term includes a neutral term that does not imply an affirmative relationship between the other terms of the one or more search terms in the search query.

4. The computing device of claim 1 , wherein:

the computing device comprises a search engine computing device;

the search query is received from a client device via the one or more communication connections;

reformulating the search query comprises the second term being stored in memory of the search engine computing device;

obtaining the search results based at least in part on the reformulated search query comprises uses a ranking algorithm stored in the memory of the search engine computing device; and

outputting the search results for presentation comprises transmitting, via the one or more communication connections, the search results to the client device for presentation of the search results on a display of the client device.

5. The computing device of claim 1 , wherein:

the computing device comprises a client computing device;

the search query is received via a browser of the client computing device;

reformulating the search query comprises the second term being stored in memory of the client computing device;

obtaining the search results based at least in part on the reformulated search query comprises:

transmitting the reformulated search query, via the one or more communication connections, to a remote search engine computing device to perform a search based on the reformulated search query; and

receiving the search results from the remote search engine computing device via the one or more communication connections; and

outputting the search results for presentation comprises displaying the search results on a display of the client computing device.

6. The computing device of claim 1 , the operations further comprising:

receiving click-through data input by the user responsive to the search results;

inferring one or more beliefs of the user based at least in part on the click-through data; and

updating a ranking algorithm based at least in part on the one or more beliefs of the user.

7. The computing device of claim 6 , the operations further comprising:

receiving an additional search query including one or more additional search terms input by the user;

obtaining search results based at least in part on:

the additional search query; and

the one or more beliefs of the user; and

outputting the search results for presentation to the user.

8. A method comprising:

under control of one or more computing devices:

receiving a search query from a client device of a user;

determining one or more beliefs of the user relevant to the search query received from the client device of the user, the one or more beliefs based at least in part on one of user behavior or aggregate search behavior of the user;

generating custom search results customized for the user based at least in part on:

the search query received from the client device of the user; and

the one or more beliefs of the user; and

transmitting the custom search results to the client device of the user,

wherein the generating generates the custom search results to compensate for a bias of the user related to the one or more beliefs.

9. The method of claim 8 , wherein generating the custom search results comprises:

performing a search based on the search query received from the client device of the user to generate preliminary search results; and

modifying the preliminary search results based at least in part on the one or more beliefs of the user to generate the custom search results from the preliminary search results.

10. The method of claim 8 , wherein obtaining the custom search results comprises:

determining one or more biases of the user based at least in part on the one or more beliefs of the user; and

ordering entries of the custom search results to compensate for the one or more biases of the user.

11. The method of claim 8 , further comprising determining one or more preferences of the user, and wherein the custom search results are generated based additionally on the one or more preferences of the user.

12. The method of claim 8 , wherein determining the one or more beliefs of the user relevant to the search query comprises:

transmitting one or more prompts to the client device soliciting information from the user of the client device; and

receiving explicit belief information about the user from the client device in response to the one or more prompts.

13. The method of claim 12 , wherein transmitting the one or more prompts to the client device is performed prior to receiving the search query.

14. The method of claim 12 , wherein transmitting the one or more prompts to the client device is performed responsive to receiving the search query.

15. The method of claim 8 , wherein the aggregate search behavior of the user comprises at least one of:

search history of the user or client device;

click through history of the user or client device; or

browser history of the user or client device.

16. The method of claim 8 , further comprising modifying the search query based at least in part on the one or more beliefs for the user to obtain a modified search query, and wherein generating the custom search results is performed based on the modified search query.

17. One or more computer-readable storage devices storing instructions that when executed by one or more processors of a search engine computing device program the search engine computing device to perform operations comprising:

receiving a search query from a client device of a user;

determining a subject of the search query based at least in part on one or more terms included in the search query or syntax of the search query;

selecting at least one of a first ranking algorithm and a second ranking algorithm to apply, from among multiple available ranking algorithms, based at least in part on determining the subject of the search query;

based on a result of the selecting, performing at least one of:

obtaining search results responsive to the search query based at least in part on the first ranking algorithm selected, and

obtaining search results responsive to the search query based at least in part on the second ranking algorithm; and

transmitting the search results to the client device for presentation.

18. The one or more computer-readable storage devices of claim 17 , wherein the multiple available ranking algorithms include at least the first ranking algorithm that is based at least in part on veracity of content of the search results, and the second ranking algorithm that does not take into account veracity of the content of the search results.

19. The one or more computer-readable storage devices of claim 18 , wherein:

the subject of the search query is determined to be diagnostic; and

the selecting comprises selecting the first ranking algorithm.

20. The one or more computer-readable storage devices of claim 18 , wherein:

the subject of the search query is determined to be a matter of opinion; and

the selecting comprises selecting the second ranking algorithm.

21. The one or more computer-readable storage devices of claim 17 , the operations further comprising:

determining a preference of the user,

wherein the selecting is further based at least in part on the preference of the user.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 3, 2015
From: HORVITZ, ERIC JOEL; AWADALLAH, AHMED HASSAN; WHITE, RYEN WILLIAM
To: MICROSOFT TECHNOLOGY LICENSING, LLC.
Reel/Frame 034880/0245 →
Continuity (1)
Related Publication 20160224574A1 · Aug 4, 2016
Cited By (2)
US 12,229,202 US 12,499,378