Ordering search results based on a knowledge level of a user performing the search

• US 10,380,207 B2
• Filed: 11/10/2015
• Issued: 08/13/2019
• Est. Priority Date: 11/10/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bostick, James E., Ganci, Jr., John M., Rakshit, Sarbajit K., Trim, Craig M.
• Primary Examiner(s): Saeed, Usmaan
• Assistant Examiner(s): Zhao, Yu
• Application Number:
  US14/937,253
• Publication Number:
  US 20170132227A1
• Time in Patent Office: 1,372 Days
• Field of Search: None
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Systems and methods for ranking search results according to a knowledge level of a user. A computer-implemented method includes: receiving, by a computing device, a search query from a user via a user computer device; determining, by the computing device, a plurality of results based on the search query; determining, by the computing device, a respective expertise level for each of the plurality of results; ranking, by the computing device, the plurality of results based on a knowledge level of the user and the respective expertise level for each of the plurality of results; and outputting, by the computing device, the ranked plurality of results to the user computer device.

Claims

1. A computer-implemented method, comprising:

receiving, by a computing device, an initial search query for a topic from a remote user computer device in a network environment;

generating, by the computing device, search results for the initial search query;

determining, by the computing device, read web pages in a sequence of web pages accessed by a user of the remote user computer device by;

determining a dwell time for each page in the sequence of web pages;

determining a page length of each page in the sequence of web pages;

determining a ratio of the dwell time to the page length for each page in the sequence of web pages;

comparing the ratio, for each page in the sequence of web pages, to a threshold value;

determining the user read a particular web page when the ratio is greater than the threshold value; and

determining the user did not read the particular web page when the ratio is less than the threshold value;

determining, by the computing device, a respective expertise level of each of a plurality of read web pages in the sequence of web pages;

determining, by the computing device, a knowledge level of the user, wherein the determining the knowledge level of the user consists of determining a highest expertise level of the respective expertise levels of each of the plurality of read web pages in the sequence of web pages, and basing the knowledge level of the user on the highest expertise level of the respective expertise levels, wherein the total number of read web pages is less than the total number of web pages in the sequence of web pages;

receiving, by the computing device, a subsequent search query from the user via the remote user computer device;

determining, by the computing device, a plurality of subsequent results based on the subsequent search query;

determining, by the computing device, a respective expertise level for each of the plurality of subsequent results;

ranking, by the computing device, the plurality of subsequent results based on the knowledge level of the user and the respective expertise level for each of the plurality of subsequent results; and

outputting, by the computing device, the ranked plurality of subsequent results to the remote user computer device.

2. The method of claim 1, wherein the determining the respective expertise level for each of the plurality of results comprises one of:

determining a defined expertise level of a web page; and

deriving an expertise level of the web page by analyzing content of the web page using natural language processing.

3. The method of claim 1, further comprising:

monitoring activity of the user with the ranked plurality of results; and

adjusting the knowledge level of the user based on the monitoring.

4. The method of claim 1, further comprising outputting, by the computing device, the knowledge level of the user to the remote user computer device for display on the user computer device.

5. The method of claim 4, further comprising:

receiving, by the computing device, input from the user to change the knowledge level of the user;

re-ranking, by the computing device, the plurality of results based on the changed knowledge level of the user and the respective expertise level for each of the plurality of results; and

outputting, by the computing device, the re-ranked plurality of results to the remote user computer device.

6. The method of claim 1, wherein a service provider at least one of creates, maintains, deploys and supports the computing device.

7. The method of claim 1, wherein steps of claim 1 are provided by a service provider on a subscription, advertising, and/or fee basis.

8. The method of claim 1, further comprising:

tracking the user'"'"'s sequence of reading read web pages in the sequence of web pages accessed by the user during a previous search query to establish relationship data; and

storing the relationship data as metadata for web page links.

9. The method of claim 1, wherein the read web pages have an expertise level selected from the group consisting of:

beginner, intermediate and advanced.

10. The method of claim 9, wherein:

at least one web page accessed by the user but not read, has an advanced expertise level, the highest expertise level of each read web page is intermediate, and the knowledge level of the user is determined based on only the intermediate expertise level.

11. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:

receive an initial search query for a topic from a user via a remote user computer device in a network environment;

generate search results for the initial search query;

determine read web pages in a sequence of web pages accessed by the user of the remote user computer device by;

determining a dwell time of a user for each web page in the sequence of web pages;

determining a page length of each web page in the sequence of web pages;

determining a ratio of the dwell time to the page length for each web page in the sequence of web pages;

comparing the ratio, for each web page in the sequence of web pages, to a threshold value;

determining that the user has read a first subset of the sequence of web pages when the ratio is greater than the threshold value; and

determining that the user did not read a second subset of the sequence of web pages when the ratio is less than the threshold value;

determine a respective expertise level of each of the first subset of the sequence of web pages based on determining that the user has read the first subset of the sequence of web pages;

determine a knowledge level of a user, wherein the determining the knowledge level of the user consists of determining a highest expertise level of the respective expertise levels of each of the first subset of the sequence of web pages, and basing the knowledge level of the user on the highest expertise level of the respective expertise levels, wherein the expertise level of the second subset is not utilized in the determination of the knowledge level of the user;

receive a subsequent search query from the user via the remote user computer device;

determine a plurality of subsequent results based on the subsequent search query;

determine a respective expertise level for each of the plurality of subsequent results;

rank the plurality of subsequent results based on the knowledge level of the user and the respective expertise level for each of the subsequent results; and

output the ranked plurality of subsequent results to the remote user computer device.

12. The computer program product of claim 11, wherein the outputting comprises outputting the respective expertise level for each of the plurality of web pages and the knowledge level of the user to the remote user computer device for display on the remote user computer device.

13. The computer program product of claim 11, wherein the program instructions executable by the computing device further cause the computing device to:

track the user'"'"'s sequence of reading read web pages in the sequence of web pages accessed by the user during a previous search query to establish relationship data; and

store the relationship data as metadata for web page links.

14. A system comprising:

a CPU, a computer readable memory and a computer readable storage medium associated with a computing device;

program instructions to receive an initial search query from a user via a remote user computer device in a network environment;

program instructions to generate search results for the initial search query;

program instructions to determine read web pages in a sequence of web pages accessed by the user of the remote user computer device by;

determining a dwell time for each page in the sequence of web pages;

determining a page length of each page in the sequence of web pages;

determining a ratio of the dwell time to the page length for each page in the sequence of web pages;

comparing the ratio, for each page in the sequence of web pages, to a threshold value;

determining the user read a particular web page when the ratio is greater than the threshold value; and

determining the user did not read the particular web page when the ratio is less than the threshold value;

program instructions to determine a respective expertise level for each of the plurality of web pages;

program instructions to determine a knowledge level of the user, wherein the determining the knowledge level of the user consists of determining a highest expertise level of the respective expertise levels of each of the plurality of read web pages in the sequence of web pages, and basing the knowledge level of the user on the highest expertise level of the respective expertise levels, wherein the total number of read web pages is less than the total number of web pages in the sequence of web pages;

program instructions to receive a subsequent search query from the user via the remote user computer device;

program instructions to determine a plurality of subsequent results based on the subsequent search query;

program instructions to determine a respective expertise level for each of the plurality of subsequent results;

program instructions to rank the plurality of subsequent results based on the knowledge level of the user and the respective expertise level for each of the plurality of subsequent results; and

program instructions to output the ranked plurality of subsequent results to the remote user computer device;

wherein the program instructions are stored on the computer readable storage medium for execution by the CPU via the computer readable memory.

15. A system of claim 14, further comprising:

program instructions to track the user'"'"'s sequence of reading read web pages in the sequence of web pages to establish relationship data; and

program instructions to store the relationship data as metadata for web page links.

16. The system of claim 14, wherein the read web pages have an expertise level selected from the group consisting of:

beginner, intermediate and advanced.

17. The system of claim 16, wherein:

at least one web page accessed by the user but not read, has an advanced expertise level, the highest expertise level of each read web page is intermediate, and the knowledge level of the user is determined based on only the intermediate expertise level.