Semantic neural network for aggregating query searches
A system, method and computer program product for implementation of a Aggregate Neural Semantic Network, which stores the relationships and semantic connections between the key search words for each user. The Aggregate Neural Semantic Network processes the search results produced by a standard search engine such as, for example, Google or Yahoo!. The set of hits produced by the standard search engine is processed by the Aggregate Neural Semantic Network, which selects the hits that are relevant to a particular user based on the previous search queries made by the user. The Aggregate Neural Semantic Network can also use the connections between the terms (i.e., key words) that are most frequently used by all of the previous Aggregate Neural Semantic Network users. The Aggregate Neural Semantic Network is constantly updating and self-teaching. The more user queries are processed by the Aggregate Neural Semantic Network, the more comprehensive processing of search engine outputs is provided by the Aggregate Neural Semantic Network to the subsequent user queries.
1. A system for processing user search requests comprising:
a memory;
a processor configured to execute instructions stored on the memory;
a semantic neural network configured to create semantic connections between one or more of words, documents, and sentences;
a session manager configured to process a user search query and provide the user search query to the semantic neural network;
a user map module configured to generate a user map of search terms based on a subset of the semantic neural network and provide the user map to the user such that the user can select relevant search terms from the user map of search terms, wherein the search terms are semantically related to the user search query;
a search controller module configured to provide a plurality of search result documents corresponding to the selected relevant search terms, wherein the user can identify relevant documents from the plurality of search result documents; and
a semantic neural network update module configured to update the semantic neural network according to at least one of the selected relevant search terms from the user map or the identified relevant documents selected by the user.
2. The system of claim 1 , wherein the semantic neural network is implemented on a server.
3. The system of claim 1 , wherein the user search query comprises keywords and/or categories.
4. The system of claim 1 , wherein the search query comprises documents considered relevant by the user.
5. The system of claim 1 , further comprising a web server configured to service the user search query, wherein the web-server is any of:
a MS ITS server;
Apache with PHP;
NGINX;
http/https server;
a server with ASP, JS, JSP, Java, Peri or Python scripting; and
a server with scripting that works with http/https protocols.
6. The system of claim 1 , Wherein updating the semantic neural network comprises changing a relevance of neurons relative to each other in response to selection of the identified relevant documents by the user.
7. The system of claim 1 , wherein the semantic neural network is a bidirectional network.
8. A method for processing user search requests comprising:
receiving a search query from a user at a web server manager;
processing the search query by a session manager and sending the search query to a neural network;
generating, at a user map module, a user map of search terms based on a subset of the neural network;
providing the user map to the user such that the user can select relevant search terms from the user map, wherein the search terms are semantically related to the user search query;
processing search terms selected by the user from the user map;
providing, via a search controller module, one or more search result documents corresponding to the selected search terms to the user;
receiving a selection of at least one of the one or more search result documents from the user; and
updating the neural network according to at least one of the selected relevant search terms from the user map or the at least one of the one or more search result documents selected by the user.
9. The method of claim 8 , wherein the neural network is implemented on a second server.
10. The method of claim 8 , wherein the neural network is implemented on a server cluster.
11. The method of claim 10 , wherein the search query is sent via a reverse proxy.
12. The method of claim 10 , wherein the search query is sent via a secure connection.
13. The method of claim 8 , wherein the search query comprises one or more of keywords and categories.
14. The method of claim 8 , wherein the search query comprises documents identified as relevant by the user.
15. The method of claim 8 , wherein updating the neural network comprises changing a relevance of neurons relative to each other in response to selection of the at least one of the one or more search result documents by the user.
16. A computer-readable storage medium having instructions stored thereon, the instructions comprising:
instructions to receive a search query from a user;
instructions to process the search query;
instructions to send the search query to a neural network;
instructions to generate a user map of search terms based on a subset of the neural network;
instructions to provide the user map to the user such that the user can select relevant search terms from the user map, wherein the search terms are semantically related to the user search query;
instructions to process search terms selected by the user from the user map;
instructions to provide to the user one or more search result documents corresponding to the selected search terms;
instructions to receive a selection of at least one of the one or more search result documents from the user; and
instructions to update the neural network according to at least one of the selected relevant search terms from the user map or the at least one of the one or more search result documents selected by the user.
17. The system of claim 1 , wherein the semantic neural network comprises semantic connections between the one or more of words, documents, and sentences based on aggregated semantic information generated from preferences of a plurality of previous users.
18. The method of claim 1 , wherein the neural network comprises semantic connections between the one or more of words, documents, and sentences based on aggregated semantic information generated from preferences of a plurality of previous users.
19. The method of claim 8 , further comprising receiving a selection from the user of one or more of the search terms from the user map.