NLP-based content recommender
View Patent ↗Methods, techniques, and systems for using natural language processing to recommend related content to an associated text segment or document. Example embodiments provide a NLP-based content recommender (“NCR”) which uses NLP-based search techniques, potentially in conjunction with context or other related information, to locate and provide content related to entities that are recognized in the associated material. NCRs may be embedded as widgets, for example on Web pages to assist users in their perusal and search for information, provided by means of browser plug-ins or other application plug-ins, provided in libraries or in standalone environments, or otherwise integrated into other code, programs, or devices. This abstract is provided to comply with rules requiring an abstract, and it is submitted with the intention that it will not be used to interpret or limit the scope or meaning of the claims.
1. A computer-implemented method for providing natural language based content recommendations, comprising:
receiving an indication of text content;
processing the indicated text content using natural language processing (“NLP”) parsing and linguistic analysis to derive a list of named entities present in the indicated text;
presenting an ordered list of the derived named entities, the list reflective of what the text content concerns; and
presenting indicators of additional content associated with the derived named entities wherein the additional content is provided upon receiving an indication that at least one of the presented indicators has been navigated to, and wherein additional content is determined as relevant based upon a natural language processing analysis of the derived named entities relative to the indicated text content and of the derived named entities relative to a larger corpus of document information or a knowledge repository, wherein the additional content includes a representation of connections to at least one named entity, and wherein the additional content is determined as relevant using context information associated with the derived named entities.
2. The method of claim 1 wherein the presented indicators are at least one of text, graphical indicators, symbols, icons, links, hyperlinks, or hypertext.
3. The method of claim 1 wherein the additional content is determined using a search of an ontology knowledge repository.
4. The method of claim 1 provided by at least one of a downloadable widget or a plug-in.
5. The method of claim 1 accessible by a user interface control embedded on a web page.
6. The method of claim 1 accessible by a user interface control implemented as a browser plug-in.
7. The method of claim 1 wherein the additional content includes a representation of connections.
8. The method of claim 7 wherein the connections are derived using NLP-based relationship searches based upon one or more of the derived named entities.
9. The method of claim 7 wherein the connections are presented graphically.
10. A non-transitory computer-readable medium containing content that, when executed, causes a computing system to perform a method comprising:
receiving an indication of text content;
processing the indicated text content using natural language processing (NLP) parsing and linguistic analysis to derive a list of named entities present in the indicated text;
presenting an ordered list of the derived named entities, the list reflective of what the text content concerns; and
presenting indicators of recommended content associated with the derived named entities wherein the recommended content is provided upon receiving an indication that at least one of the presented indicators has been navigated to, and wherein the recommended content is determined as relevant based upon a natural language processing analysis of the derived named entities relative to the indicated text content and of the derived named entities relative to a larger corpus of document information or a knowledge repository, wherein the recommended content includes a representation of connections to at least one derived named entity, and wherein the additional content is determined as relevant using context information associated with the derived named entities.
11. The computer-readable medium of claim 10 , wherein the medium is a memory in a computing system.
12. The computer-readable medium of claim 10 wherein the contents are instructions that, when executed, cause a computer processor in the computing device to perform the method.
13. A computer-implemented NLP-based content recommendation system, comprising:
a memory; and
a content recommender module, having instructions that are configured to, when executed,
receive a text segment for processing;
identify, one or more named entities to which a received text segment refers based, at least in part, upon a natural language processing (NLP) parsing and linguistic analysis of the text segment; and
derive and present related content based at least in part upon a natural language processing parsing and linguistic analysis of entity based information and of context related information, wherein the related content includes a representation of connections to at least one identified named entity, and wherein the related content is determined as relevant using context information associated with the derived named entities.
14. The system of claim 13 , wherein the module is further configured, when executed, to display one or more indicators for navigating to the related content.
15. The system of claim 14 wherein the module is further configured, when executed, to present the related content in response to detecting selection of at least one of the navigation indicators.
16. The system of claim 14 wherein the indicators are links.
17. The system of claim 14 wherein the indicators are at least one of graphical symbols, icons, shapes, logos, or trademarks.
18. The system of claim 14 wherein the natural language processing parsing and linguistic analysis is initiated using a natural language query.
19. The system of claim 18 wherein the natural language query is a relationship search query.