Techniques for entity-level technology recommendation

1. A method comprising:

modeling a first query in a given vector space, wherein the given vector space comprises multiple word and/or term dimensions from a predetermined language source;

searching the first query against a first corpus of documents to determine a set of documents matching an entity of interest identified in the first query;

generating a list of technologies that (i) appear within the content of the set of documents and (ii) are associated to the entity of interest;

organizing said list of technologies by building a graph wherein the nodes of the graph represent technology terms and a directed edge exists from a first technology term to a second technology term if a hyperlink to the second technology term exists in a reference webpage associated with the first technology term;

modeling a second query in the given vector space, wherein the second query is based on one or more selected technologies from the graph;

searching the second query against a second corpus of documents to determine a set of documents representing a technology recommendation for the entity of interest, wherein the second corpus of documents comprises a corpus of intellectual property assets, and wherein the set of documents representing a technology recommendation comprises a subset of the intellectual property assets proposed for licensing and/or selling to the entity of interest; and

outputting the set of documents representing the technology recommendation to a user and/or a display;

wherein the steps are carried out by at least one computing device.

2. The method of claim 1 , comprising:

receiving the identification of the entity of interest from a user.

3. The method of claim 1 , wherein said determining the set of documents matching the entity of interest comprises comparing metadata of the first corpus of documents with a name of the entity of interest.

4. The method of claim 3 , wherein said metadata of the first corpus of documents comprises information pertaining to entity title and/or entity affiliation.

5. The method of claim 1 , wherein said determining the set of documents matching the entity of interest comprises applying one or more distance metrics to the first query and the first corpus of documents.

6. The method of claim 1 , wherein said searching a second query against a second corpus of documents comprises submitting the second query into a document search engine.

7. The method of claim 1 , comprising:

determining the first technology term and the second technology term to be relevant to each other if there exists (i) a first directed path in the technology graph starting from the first technology term and ending at the second technology term, and (ii) a second directed path in the technology graph starting from the second technology term and ending at the first technology term, wherein the length of each directed path is less than a given threshold.

8. The method of claim 1 , wherein said outputting the set of documents comprises outputting a pre-determined number of documents from the set of documents representing a technology recommendation to a user and/or a display.

9. The method of claim 1 , comprising:

enabling download of the set of documents output as the technology recommendation.

10. An article of manufacture comprising a non-transitory computer readable storage medium having computer readable instructions tangibly embodied thereon which, when implemented, cause a computer to carry out a plurality of method steps comprising:

modeling a first query in a given vector space, wherein the given vector space comprises multiple word and/or term dimensions from a predetermined language source;

searching the first query against a first corpus of documents to determine a set of documents matching an entity of interest identified in the first query;

generating a list of technologies that (i) appear within the content of the set of documents and (ii) are associated to the entity of interest;

organizing said list of technologies by building a graph wherein the nodes of the graph represent technology terms and a directed edge exists from a first technology term to a second technology term if a hyperlink to the second technology term exists in a reference webpage associated with the first technology term;

modeling a second query in the given vector space, wherein the second query is based on one or more selected technologies from the graph;

searching the second query against a second corpus of documents to determine a set of documents representing a technology recommendation for the entity of interest, wherein the second corpus of documents comprises a corpus of intellectual property assets, and wherein the set of documents representing a technology recommendation comprises a subset of the intellectual property assets proposed for licensing and/or selling to the entity of interest; and

outputting the set of documents representing the technology recommendation to a user and/or a display.

11. The article of manufacture of claim 10 , wherein said determining the set of documents matching the entity of interest comprises comparing metadata of the first corpus of documents with a name of the entity of interest.

12. The article of manufacture of claim 10 , wherein said determining the set of documents matching the entity of interest comprises applying one or more distance metrics to the first query and the first corpus of documents.

13. The article of manufacture of claim 10 , wherein said searching a second query against a second corpus of documents comprises submitting the second query into a document search engine.

14. The article of manufacture of claim 10 , wherein said outputting the set of documents comprises outputting a pre-determined number of documents from the set of documents representing a technology recommendation to a user and/or a display.

15. The article of manufacture of claim 10 , wherein the method steps comprise:

enabling download of the set of documents output as the technology recommendation.

16. A system comprising:

a memory; and

at least one processor coupled to the memory and configured for:

modeling a first query in a given vector space, wherein the given vector space comprises multiple word and/or term dimensions from a predetermined language source;

searching the first query against a first corpus of documents to determine a set of documents matching an entity of interest identified in the first query;

generating a list of technologies that (i) appear within the content of the set of documents and (ii) are associated to the entity of interest;

organizing said list of technologies by building a graph wherein the nodes of the graph represent technology terms and a directed edge exists from a first technology term to a second technology term if a hyperlink to the second technology term exists in a reference webpage associated with the first technology term;

modeling a second query in the given vector space, wherein the second query is based on one or more selected technologies from the graph;

searching the second query against a second corpus of documents to determine a set of documents representing a technology recommendation for the entity of interest, wherein the second corpus of documents comprises a corpus of intellectual property assets, and wherein the set of documents representing a technology recommendation comprises a subset of the intellectual property assets proposed for licensing and/or selling to the entity of interest; and

outputting the set of documents representing the technology recommendation to a user and/or a display.

17. A method comprising:

receiving a name of an entity of interest to be used as a first query;

modeling the first query in a given vector space, wherein the given vector space comprises multiple word and/or term dimensions from a predetermined language source;

searching the first query against a first corpus of documents to determine a set of documents matching the entity of interest;

generating a list of technologies that (i) appear within the content of the set of documents and (ii) are associated to the entity of interest;

organizing said list of technologies by building a graph wherein the nodes of the graph represent technology terms and a directed edge exists from a first technology term to a second technology term if a hyperlink to the second technology term exists in a reference webpage associated with the first technology term;

receiving a second query based on one or more technologies from the graph;

modeling the second query in the given vector space;

submitting the second query into a document search engine to search against a second corpus of documents to determine a set of documents representing a technology recommendation for the entity of interest, wherein the second corpus of documents comprises a corpus of intellectual property assets, and wherein the set of documents representing a technology recommendation comprises a subset of the intellectual property assets proposed for licensing and/or selling to the entity of interest; and

outputting the set of documents representing the technology recommendation to a user and/or a display as a ranked list of documents;

wherein the steps are carried out by at least one computing device.