Dynamic creation of topical keyword taxonomies

• US 9,208,435 B2
• Filed: 05/10/2010
• Issued: 12/08/2015
• Est. Priority Date: 05/10/2010
• Status: Active Grant

• Current Assignee: Oracle OTC Subsidiary LLC (Oracle Corporation)
• Original Assignee: Oracle OTC Subsidiary LLC (Oracle Corporation)
• Inventors: Zelevinsky, Vladimir
• Primary Examiner(s): PARK, GRACE A
• Application Number:
  US12/776,715
• Publication Number:
  US 20110276581A1
• Time in Patent Office: 2,038 Days
• Field of Search: 704/9, 707/722, 707/736, 707/737, 707/738, 707/739, 707/754, 707/765, 707/766, 707/767, 707/769, 707/771, 707/778, 707/794, 707/E17.074, 707/E17.005, 707/999.003, 707/999.004, 707/999.005
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3323 using document space presentation or visualization, e.g. category, hierarchy or range presentation and selection
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation

Abstract

System and methods for dynamically generating taxonomies of keywords and/or descriptors are provided. In one example, a navigation system for accessing a corpus of information provides for dynamic taxonomy generation expanding upon a topic entered by a user in a user interface. The navigation system generates, dynamically, at least one term associated with the received topic from at least one sense or meaning retrieved from a semantic network. The navigation system is further configured to present to the user the at least one term as a selectable refinement in response to receiving the topic entered by the user in the user interface. The system can also be configured to retrieve terms and/or senses from the semantic network and evaluate any retrieved terms for their informativeness. The system can further cache any information generated during taxonomy creation and update the corpus to reflect useful refinements.

Claims

1. A computer implemented method for generating refinements within a corpus, the method comprising:

receiving a topic from a user in a user interface;

generating, dynamically, a plurality of terms associated with the topic, wherein the generating the plurality of terms comprises;

communicating a query to a semantic network based on the topic;

receiving the plurality of terms from the semantic network in response to the query;

evaluating each of the plurality of terms against the corpus, the evaluating comprising determining that an informativeness measure for the term is within acceptable limits; and

presenting automatically to the user, before a further interaction by the user with the user interface after receiving the topic, only the plurality of terms that are determined to have the informativeness measure within the acceptable limits, each presented term being a selectable refinement in response to receiving the topic from the user entered in the user interface, the selectable refinement associated with at least one action of a plurality of available associated actions;

wherein the presenting automatically to the user, before the further interaction by the user with the user interface after receiving the topic, comprises displaying initial search results from the topic in the user interface, the initial search results comprising links to one or more items of the corpus, and the selectable refinement displays a number of items of the initial search results that correspond to each of the plurality of terms;

wherein the generating comprises receiving a plurality of meanings for the topic, and the presenting comprises displaying for each of the meanings a set of one or more of the plurality of terms that relate to the meaning;

wherein one of the selectable refinements, when selected by the user and associated with an action comprising a text search, generates additional search results that are a subset of the initial search results and that correspond to the term of the selected refinement.

2. The method according to claim 1, wherein the receiving the plurality of terms from the semantic network includes receiving at least one sense of the received topic, and wherein each of the plurality of terms corresponds to the at least one sense.

3. The method according to claim 2, wherein the threshold value that identifies informativeness of each of the plurality of terms includes a value for at least one of precision, recall, f-measure, or a salience metric.

4. The method according to claim 2, wherein the receiving the plurality of terms from the semantic network includes receiving at least one candidate term that corresponds to each sense of the at least one sense of the received topic.

5. The method according to claim 4, further comprising identifying the plurality of terms from the at least one candidate term, wherein the identifying the plurality of terms comprises:

evaluating the at least one candidate term against a threshold value that identifies informativeness of each of the plurality of terms; and

determining that the at least one candidate term meets the threshold value.

6. The method according to claim 2, wherein the identifying at least one sense of the topic from the semantic network includes restricting the identified at least one sense by semantic relationship.

7. The method according to claim 6, wherein the semantic relationship includes at least one of a meronym, holonym, or hyponym.

8. The method according to claim 1, further comprising comparing the plurality of terms against a threshold value that identifies informativeness of each of the plurality of terms.

9. The method according to claim 8, further comprising dynamically determining the threshold value.

10. The method according to claim 1, further comprising caching the generated plurality of terms.

11. The method according to claim 1, further comprising updating the corpus with the plurality of terms.

12. The method according to claim 1, further comprising:

tracking a usage pattern associated with received topics; and

updating the corpus with the plurality of terms in response to the usage pattern indicating an established user demand.

13. The method according to claim 1, further comprising associating a second action comprising a navigation operation with the plurality of terms.

14. The method of claim 1, further comprising:

tracking selections of particular refinements on a per user basis, and tracking terms generated in response to each received topic, wherein refinement options presented to the user are displayed only when a threshold is exceeded based on the tracking.

15. A system for dynamically generating taxonomies, the system comprising:

a processor;

a memory coupled to the processor storing components that are executed by the processor;

a communication component stored in the memory and configured to receive a topic from a user input in a user interface on a host computer system;

a generation component stored in the memory and configured to dynamically generate a plurality of terms associated with the received topic;

wherein the generation component is further configured to;

communicate a query to a semantic network based on the received topic, and

receive the plurality of terms from the semantic network in response to the query;

evaluate each of the plurality of terms against the corpus, the evaluating comprising determining that an informativeness measure for the term is within acceptable limits; and

wherein the communication component is further configured to communicate to the host computer system only the plurality of terms that are determined to have the informativeness measure within the acceptable limits as a selectable refinement displayed in the user interface in response to receiving the topic from the user in the user interface, the selectable refinement associated with at least one action of a plurality of available associated actions;

wherein the displayed selectable refinement comprises displaying automatically to the user, before a further interaction by the user with the user interface after receiving the topic, initial search results from the topic in the user interface, the initial search results comprising links to one or more items of the corpus, and displaying a number of items of the initial search results that correspond to each of the plurality of terms;

wherein the generate comprises receiving a plurality of meanings for the topic, and the displaying comprises displaying automatically to the user, before the further interaction by the user with the user interface after receiving the topic, for each of the meanings a set of one or more of the plurality of terms that relate to the meaning;

wherein one of the selectable refinements, when selected by the user and associated with an action comprising a text search, generates additional search results that are a subset of the initial search results and that correspond to the term of the selected refinement.

16. The system according to claim 15, wherein each of the received plurality of terms correspond to at least one sense of the received topic.

17. The system according to claim 15, further comprising an evaluation component stored in the memory and configured to compare the plurality of terms against a threshold value that identifies informativeness of each of the plurality of terms.

18. The system according to claim 17, wherein the evaluation component is further configured to dynamically generate the threshold value.

19. The system according to claim 17, wherein the evaluation component calculates for the plurality of terms a value for at least one of precision, recall, f-measure, or a salience metric.

20. The system according to claim 15, wherein the generation component is further configured to retrieve at least one candidate term that corresponds to each sense of the at least one sense of the topic.

21. The system according to claim 20, wherein the evaluation component is further configured to:

compare the at least one candidate term against a threshold value that identifies informativeness of each of the plurality of terms; and

present the at least one candidate term as each of the plurality of terms in response to a determination that the at least one candidate term meets the threshold value.

22. The system according to claim 15, further comprising a storage component configured to:

track usage patterns associated with submitted topics; and

update the corpus with at least one term in response to the usage pattern indicating a predetermined user demand.

23. The system according to claim 15, further comprising an evaluation component configured to automatically filter each of the plurality of terms retrieved.

24. The system according to claim 15, wherein the generation component is further configured to receive the plurality of terms including the plurality of terms from the semantic network, and the system further comprises an evaluation component configured to filter, automatically, at least one of the plurality of terms.

25. The system of claim 15, wherein the generation component is further configured to track selections of particular refinements on a per user basis, and track terms generated in response to each received topic, wherein refinement options presented to the user are displayed only when a threshold is exceeded based on the tracking.

26. A non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, cause the processor to generate refinements within a corpus, the generating comprising:

receiving a topic from a user in a user interface;

generating, dynamically, a plurality of terms associated with the topic, wherein the generating the plurality of terms comprises;

communicating a query to a semantic network based on the topic;

receiving the plurality of terms from the semantic network in response to the query;

evaluating each of the plurality of terms against the corpus, the evaluating comprising determining that an informativeness measure for the term is within acceptable limits; and

presenting automatically to the user, before a further interaction by the user with the user interface after receiving the topic, only the plurality of terms that are determined to have the informativeness measure within the acceptable limits, each presented term being a selectable refinement in response to receiving the topic from the user entered in the user interface, the selectable refinement associated with at least one action of a plurality of available associated actions;

wherein the presenting automatically to the user, before the further interaction by the user with the user interface after receiving the topic, comprises displaying initial search results from the topic in the user interface, the initial search results comprising links to one or more items of the corpus, and the selectable refinement displays a number of items of the initial search results that correspond to each of the plurality of terms;

wherein the generating comprises receiving a plurality of meanings for the topic, and the presenting comprises displaying for each of the meanings a set of one or more of the plurality of terms that relate to the meaning;

wherein one of the selectable refinements, when selected by the user and associated with an action comprising a text search, generates additional search results that are a subset of the initial search results and that correspond to the term of the selected refinement.

27. The non-transitory computer readable medium of claim 26, further comprising tracking selections of particular refinements on a per user basis, and tracking terms generated in response to each received topic, wherein refinement options presented to the user are displayed only when a threshold is exceeded based on the tracking.