Intelligent short text information retrieve based on deep learning

Abstract

Text based searching can return results based on the system determining the searched text includes keywords or search terms. The present solution can return results based on a semantic analysis. The solutions described herein can provide high accuracy compared against the full-text or keyword-based retrieval algorithms. The solution can sort the results by semantic relevance based on the user's input search request. The present solution can provide meaningful results to the user even when the search text does not include the exact search keywords or phrases entered by the user.

What is claimed is: 
     
         1 . A method comprising:
 generating, by one or more processors, a sentence vector from one or more terms of a request;   identifying, by the one or more processors, a plurality of sentence vectors, each of the plurality of sentence vectors trained using a respective sentence from a respective one of a plurality of electronic documents;   determining, by the one or more processors, a similarity score for each of the plurality of sentence vectors with respect to the generated sentence vector for the request;   selecting, by the one or more processors, an electronic document from the plurality of electronic documents based at least on a ranking of the similarity score for each of the plurality of sentence vectors;   providing, by the one or more processors responsive to the request, at least the selected electronic document.   
     
     
         2 . The method of  claim 1 , further comprising receiving, by the one or more processors, the request comprising a plurality of terms. 
     
     
         3 . The method of  claim 1 , further comprising generating, by the one or more processors, a word vector for each of the plurality of terms. 
     
     
         4 . The method of  claim 3 , wherein word vector for each of the plurality of terms comprise a vector of one or more weights indicating a probability of one of the plurality of terms occurring. 
     
     
         5 . The method of  claim 3 , further comprising generating, by the one or more processors, the sentence vector using the word vector for each of the plurality of terms. 
     
     
         6 . The method of  claim 1 , wherein the each of sentence vectors and the generated sentence vector are mapped to a vector space. 
     
     
         7 . The method of  claim 1 , further comprising selecting, by the one or more processors, a subset of the plurality of electronic documents with the similarity score greater than a threshold. 
     
     
         8 . The method of  claim 7 , further comprising providing, by the one or more processors responsive to the request, a list of the subset of the plurality of electronic documents. 
     
     
         9 . A system comprising:
 one or more processors, coupled to memory and configured to:   generate a sentence vector from one or more terms of a request;   identify a plurality of sentence vectors, each of the plurality of sentence vectors trained using a respective sentence from a respective one of a plurality of electronic documents;   determine a similarity score for each of the plurality of sentence vectors with respect to the generated sentence vector for the request;   select an electronic document from the plurality of electronic documents based at least on a ranking of the similarity score for each of the plurality of sentence vectors;   provide, responsive to the request, at least the selected electronic document.   
     
     
         10 . The system of  claim 9 , wherein the one or more processors are further configured to receive the request comprising a plurality of terms. 
     
     
         11 . The system of  claim 9 , wherein the one or more processors are further configured to generate a word vector for each of the plurality of terms. 
     
     
         12 . The system of  claim 11 , wherein word vector for each of the plurality of terms comprise a vector of one or more weights indicating a probability of one of the plurality of terms occurring. 
     
     
         13 . The system of  claim 11 , wherein the one or more processors are further configured to generate the sentence vector using the word vector for each of the plurality of terms. 
     
     
         14 . The system of  claim 9 , wherein the each of sentence vectors and the generated sentence vector are mapped to a vector space. 
     
     
         15 . The system of  claim 9 , wherein the one or more processors are further configured to select a subset of the plurality of electronic documents with the similarity score greater than a threshold. 
     
     
         16 . The system of  claim 15 , wherein the one or more processors are further configured to provide, responsive to the request, a list of the subset of the plurality of electronic documents. 
     
     
         17 . A non-transitory computer-readable medium comprising processor-executable instructions that when executed by one or more processors, cause the one or more processors to:
 generate a sentence vector from one or more terms of a request;   identify a plurality of sentence vectors, each of the plurality of sentence vectors trained using a respective sentence from a respective one of a plurality of electronic documents;   determine a similarity score for each of the plurality of sentence vectors with respect to the generated sentence vector for the request;   select an electronic document from the plurality of electronic documents based at least on a ranking of the similarity score for each of the plurality of sentence vectors;   provide, responsive to the request, at least the selected electronic document.   
     
     
         18 . The computer-readable medium of  claim 17 , further comprising instructions that cause the one or more processors to generate a word vector for each of the plurality of terms. 
     
     
         19 . The computer-readable medium of  claim 18 , wherein word vector for each of the plurality of terms comprise a vector of one or more weights indicating a probability of one of the plurality of terms occurring. 
     
     
         20 . The computer-readable medium of  claim 18 , further comprising instructions that cause the one or more processors to generate the sentence vector using the word vector for each of the plurality of terms.