Disambiguation of entities

• US 9,418,155 B2
• Filed: 10/14/2010
• Issued: 08/16/2016
• Est. Priority Date: 10/14/2010
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Shah, Sarthak Deepak, Govani, Tabreez, Hosseini, Farid
• Primary Examiner(s): Yen, Syling
• Application Number:
  US12/904,300
• Publication Number:
  US 20120096033A1
• Time in Patent Office: 2,133 Days
• Field of Search: 707/706, 707/713, 707/722, 707/736, 707/758, 707/769, 707/780, 707/781, 707999002-999006, 705/10, 382/161
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3338 Query expansion
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9532 Query formulation

Abstract

Methods, systems, algorithms, and media are provided for disambiguating entities present in a received search query. Lists of categories from semi-structured data from external sites as well as internal sources are used to detect if ambiguity exists in an entity within the search query. Multiple senses or categories of the ambiguous entity are determined by ascertaining the primary intent of an entity extracted from a main term of a document. The probability of each sense is calculated by computing a total amount of traffic received for each of the senses of the ambiguous entity. The sense with the highest amount of computed traffic is the most probable determined sense.

Claims

1. A computer-implemented method of disambiguating entities using a computing system having processor, memory, and data storage subsystems, the computer-implemented method comprising:

receiving a user input search query;

detecting that ambiguity exists in an entity within the search query;

determining multiple senses that exist within the detected ambiguous entity;

for each of the multiple senses, computing an amount of network traffic to a webpage that represents one of the multiple senses, wherein computing includes calculating a number of webpage views of the webpage and a dwell time for each of the webpage views of the webpage;

computing a total amount of network traffic to all webpages that represent at least one of the multiple senses;

for each of the multiple senses, calculating a probability based on the amount of network traffic to the webpage that represents the one of the multiple senses and the total amount of network traffic to all the webpages that represent at least one of the multiple senses;

identifying a most probable sense of the multiple senses of the detected ambiguous entity, wherein the most probable sense has a highest probability compared to remaining senses of the multiple senses of the detected ambiguous entity; and

returning search results for the most probable sense of the multiple senses of the detected ambiguous entity based on the probability calculated for each of the multiple senses from the amount of network traffic to the webpage that represents the one of the multiple senses and the total amount of network traffic to all the webpages that represent at least one of the multiple senses.

2. The computer-implemented method of claim 1, wherein said detecting utilizes lists of categories from semi-structured data.

3. The computer-implemented method of claim 1, wherein each of the determined multiple senses are determined by extracting a main term from a document to ascertain its primary intent.

4. The computer-implemented method of claim 1, wherein a viewing area allotted to the returned search results is proportional to the calculated probability of each of the multiple senses.

5. The computer-implemented method of claim 1, wherein the returned search results comprise content for all determined multiple senses with a probability above a minimum probability threshold level and omits content for all determined multiple senses with a probability below the minimum probability threshold level.

6. The computer-implemented method of claim 1, wherein the returned search results comprise content for the most probable determined sense and a module comprising links to all other determined multiple senses of the detected ambiguous entity.

7. The computer-implemented method of claim 6, wherein the module further comprises definitions of the other determined multiple senses.

8. The computer-implemented method of claim 1, wherein the calculating a probability further includes dividing the amount of network traffic to the webpage that represents the one of the multiple senses by the total amount of network traffic to all the webpages that represent at least one of the multiple senses.

9. One or more computer hardware storage media containing computer readable instructions for an algorithm embodied thereon that, when executed by a computing device, perform steps for disambiguating entities, the algorithm comprising:

detecting that ambiguity exists for an entity obtained from a search query;

determining senses that exist within the detected ambiguous entity;

for each of the senses, computing an amount of network traffic to a webpage that represents one of the senses, wherein computing includes calculating a number of webpage views of the webpage and a dwell time for each of the webpage views of the webpage;

computing a total amount of network traffic to all webpages that represent at least one of the senses;

for each of the senses, calculating a probability based on the amount of network traffic to the webpage that represents the one of the senses and the total amount of network traffic to all the webpages that represent at least one of the senses;

identifying a most probable sense of the senses, wherein the most probable sense has a highest probability compared to remaining senses of the detected ambiguous entity; and

returning search results for the most probable sense of the senses of the detected ambiguous entity based on the probability calculated for each of the senses from the amount of network traffic to the webpage that represents the one of the senses and the total amount of network traffic to all the webpages that represent at least one of the senses.

10. The one or more computer hardware storage media of claim 9, wherein the ambiguity is detected when an entity appears in multiple categorized lists.

11. The media of claim 9, further comprising returning search results comprising content for all of the senses having a probability above a minimum probability threshold level.

12. The media of claim 11, where the minimum probability threshold level is predetermined or dynamic.

13. The media of claim 9, further comprising comparing the probability of each of the senses to one another.

14. A computerized system comprising:

one or more processors; and

a non-transitory computer storage media storing computer-useable instructions that, when used by the one or more processors, cause the one or more processors to;

receive a search query from a user input via an interconnected computing network of the computing system;

identify an ambiguous term in the search query by utilizing lists of categories from semi-structured data containing the ambiguous term;

infer categories of the ambiguous term via extraction on the semi-structured data;

for each of the categories inferred for the ambiguous term, compute an amount of network traffic, wherein computing includes calculating a number of webpage views representing each category and a dwell time for each of the webpage views;

compute a total amount of network traffic to all of the webpages representing the categories inferred;

determine a probability for each category of the ambiguous term based on the amount of network traffic computed for each of the categories and the total amount of network traffic computed for all categories inferred of the ambiguous entity;

identify a most probable category of the ambiguous term, wherein the most probable category has a highest probability compared to remaining categories of the ambiguous term; and

return search results representing the most probable category of the ambiguous term to a user via a graphical user interface of the computing system based on the probability calculated for each category of the ambiguous term from the amount of network traffic computed for each of the categories and the total amount of network traffic computed for all categories inferred of the ambiguous entity.

15. The system of claim 14, wherein the semi-structure data containing the ambiguous term includes internal categorized list data and external categorized list data including published traffic data.

16. The system of claim 14, wherein the search results returned comprise content for all categories having a probability above a minimum probability threshold level.

17. The system of claim 14, wherein the search results returned are allotted a presentation area that is proportional to the probability of the category to which each of the search results belong.

18. The system of claim 14, wherein the non-transitory computer storage media further causes the one or more processors to:

for each of the categories inferred, extract a main term from a document to ascertain a primary intent of the document.

19. The system of claim 14, wherein the non-transitory computer storage media further causes the one or more processors to:

omit content for categories inferred having a probability below a minimum probability threshold level.

20. The system of claim 14, wherein a dwell time is an amount of time a user spends viewing a webpage.