IP Library › Granted Patent US 10,977,323
Granted Patent B2
US 10,977,323 · App. 15/408,966 · Granted Apr 13, 2021

Determining domain expertise and providing tailored internet search results

Inventors: Lisa Seacat DeLuca (Baltimore, MD); Stefan A. Gert van der stockt (Johannesburg, ZA)
Assignee: International Business Machines Corporation
G06F16/9535
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 10,977,323
App. No.
15/408,966
Granted
Apr 13, 2021
Kind
B2
Abstract

An apparatus, method and associated system is described for the production of search results that are determined to be of interest to the user based on both the search phrase and the level of expertise of the user. Literature is analyzed from a plurality of different domains, and a database, map and/or lexicon is built that categorizes the literature by different levels of expertise. Each item of literature is assigned a particular level of expertise. At least one keyword in a user's search query is analyzed and compared with at least part of the database, and a user's level of expertise is based, at least in part, on the comparison. A set of search results is generated for the search query that is weighted, at least in part, based on a correlation between the user's level of expertise and the particular level of expertise assigned to each item of literature.

Claims (61)

1. A method implemented by a computer for generating search results categorized by expertise level of a user, said method comprising:

analyzing, by the computer, literature from a plurality of different domains,

building, by the computer, a corpus for literature of a domain of the plurality of domains, the corpus categorized by different levels of expertise, wherein building the corpus includes dividing a plurality of items of said literature of the domain into a first series of trigrams, bigrams, and unigrams and assigning each item of the plurality of items of said literature of the domain to a particular level of expertise from said different levels of expertise;

analyzing, by the computer, at least one keyword in a user's search query submitted to a search engine, wherein analyzing the at least one keyword includes dividing the at least one keyword into a second series of trigrams, bigrams, and unigrams;

comparing said at least one keyword with at least part of said corpus by comparing the second series of trigrams, bigrams, and unigrams with the first series of trigrams, bigrams, and unigrams and computing a closest item of said literature of the domain;

determining a user's level of expertise based on said step of comparing said at least one keyword with said at least part of said corpus and without considering a history of the user;

generating a set of search results for the search query that are weighted, at least in part, based on a correlation between said user's determined level of expertise and a respective level of expertise assigned to the closest item of said literature of the domain; and

including, in said search results, at least one product that is determined to be of interest to the user based on both the search query and the determined level of expertise of the user and without considering the history of the user.

2. The method of claim 1 , further comprising:

building, by the computer, a lexicon that is associated with said different levels of expertise;

comparing said at least one keyword with at least part of said lexicon; and

determining a user's level of expertise based, at least in part, on comparing said at least one keyword with said at least part of said lexicon.

3. The method of claim 1 , further comprising:

generating a sales promotion based on the determination of the user's level of expertise based on said step of comparing said at least one keyword with said at least part of said corpus and without considering a history of the user.

4. The method of claim 1 , further comprising:

assigning said at least one keyword in said user's search query submitted to said search engine a level of expertise prior to said step of comparing.

5. The method of claim 1 , further comprising:

comparing at least one term contained within said at least one item of said literature with said corpus, said particular level of expertise for each item defined by a complexity of prose contained in said at least one item of said literature.

6. The method of claim 2 , further comprising:

defining said lexicon based on said plurality of terms associated with said particular domain.

7. The method of claim 1 , further comprising:

presenting, to the user, an advertisement for at least one product that is determined to be of interest to the user based on both the search query and the determined level of expertise of the user without considering the history of the user.

8. A computer program product, comprising a computer readable storage device having computer readable program code stored therein, said program code containing instructions executable by a processor of a computer system to implement a method to generate expertise tailored search results, said method comprising:

analyzing, by the computer, literature from a plurality of different domains;

building, by the computer, a corpus for literature of a domain of the plurality of domains, the corpus categorized by different levels of expertise, wherein building the corpus includes dividing a plurality of items of said literature of the domain into a first series of trigrams, bigrams, and unigrams and assigning each item of the plurality of items of said literature of the domain to a particular level of expertise from said different levels of expertise;

analyzing, by the computer, at least one keyword in a user's search query submitted to a search engine, wherein analyzing the at least one keyword includes dividing the at least one keyword into a second series of trigrams, bigrams, and unigrams;

comparing said at least one keyword with at least part of said corpus by comparing the second series of trigrams, bigrams, and unigrams with the first series of trigrams, bigrams, and unigrams and computing a closest item of said literature of the domain;

determining a user's level of expertise based on said step of comparing said at least one keyword with said at least part of said corpus and without considering a history of the user;

generating a set of search results for the search query that are weighted, at least in part, based on a correlation between said user's determined level of expertise and a respective level of expertise assigned to the closest item of said literature of the domain; and

including, in said search results, at least one product that is determined to be of interest to the user based on both the search query and the determined level of expertise of the user and without considering the history of the user.

9. The computer program product of claim 8 , further comprising:

building, by the computer, a lexicon that is associated with said different levels of expertise;

comparing said at least one keyword with at least part of said lexicon; and

determining a user's level of expertise based, at least in part, on comparing said at least one keyword with said at least part of said lexicon.

10. The computer program product of claim 8 , further comprising:

generating a sales promotion based on the determination of the user's level of expertise based on said step of comparing said at least one keyword with said at least part of said corpus and without considering a history of the user.

11. The computer program product of claim 8 , further comprising:

assigning said at least one keyword in said user's search query submitted to said search engine a level of expertise prior to said step of comparing.

12. The computer program product of claim 8 , further comprising:

comparing at least one term contained within said at least one item of said literature with said corpus, said particular level of expertise for each item defined by a complexity of prose contained in said at least one item of said literature.

13. The computer program product of claim 9 , further comprising:

defining said lexicon based on said plurality of terms associated with said particular domain.

14. The computer program product of claim 8 , further comprising:

determining a domain category for said at least one keyword.

15. The computer program product of claim 8 , further comprising:

assigning a particular domain to each item of said literature from said plurality of domains.

16. The computer program product of claim 8 , further comprising:

presenting, to the user, an advertisement for at least one product that is determined to be of interest to the user based on both the search query and the determined level of expertise of the user without considering the history of the user.

17. A computer system, comprising a processor, a memory coupled to the processor, and a computer readable storage device coupled to the processor, said storage device containing program code executable by the processor via the memory to implement a method for generating search results based upon an expertise level of a user, said method comprising:

analyzing, by the computer, literature from a plurality of different domains;

building, by the computer, a database for literature of a domain of the plurality of domains, the database categorized by different levels of expertise, wherein building the database includes dividing a plurality of items of said literature of the domain into a first series of trigrams, bigrams, and unigrams and assigning each item of the plurality of items of said literature of the domain a particular level of expertise from said different levels of expertise;

analyzing, by the computer, at least one keyword in a user's search query submitted to a search engine, wherein analyzing the at least one keyword includes dividing the at least one keyword into a second series of trigrams, bigrams, and unigrams;

comparing said at least one keyword with at least part of said database by comparing the second series of trigrams, bigrams, and unigrams with the first series of trigrams, bigrams, and unigrams and computing a closest item of said literature of the domain;

determining a user's level of expertise based on said step of comparing said at least one keyword with said at least part of said database and without considering a history of the user;

generating a set of search results for the search query that are weighted, at least in part, based on a correlation between said user's determined level of expertise and a respective level of expertise assigned to the closest item of said literature of the domain;

identifying a product, the product determined to be of interest to the user based on both the search query and the determined level of expertise of the user and without considering a history of the user; and

presenting, along with the search results, at least one of the product and an advertisement for the product to the user.

18. The computer system of claim 17 , further comprising:

building, by the computer, a lexicon that is associated with said different levels of expertise;

comparing said at least one keyword with at least part of said lexicon; and

determining a user's level of expertise based, at least in part, on comparing said at least one keyword with said at least part of said lexicon.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 18, 2017
From: DELUCA, LISA SEACAT; GERT VAN DER STOCKT, STEFAN A.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 041008/0393 →
Continuity (1)
Related Publication 20180203933A1 · Jul 19, 2018