Systems and methods for contextual ranking of search results

Patent metadata

Field	Value
Publication number	US-2020004876-A1
Application number	US-201816025423-A
Country	US
Kind code	A1
Filing date	Jul 2, 2018
Priority date	Jul 2, 2018
Publication date	Jan 2, 2020
Grant date	—

Abstract

Systems, apparatuses, methods, and computer program products are disclosed for searching electronic documents. An example method includes receiving a set of electronic documents, wherein each electronic document in the set of electronic documents comprises a set of sentences. The example method further includes generating a contextual index that associates each sentence with one or more of contexts. The example method further includes receiving an electronic search query comprising a plurality of search terms. Subsequently, the example method includes generating a contextual search ranking for a subset of the set of electronic documents based on the search terms and the contextual index.

First claim

What is claimed is:

1 . A computing system for searching electronic documents, the computing system comprising:
preprocessing circuitry configured to
receive a set of electronic documents, wherein each electronic document in the set of electronic documents comprises a set of sentences,
identify a set of terms for each sentence, wherein each term in the set of terms is associated with one or more contexts in a set of contexts,
generate, based on the set of terms, a context score for each sentence with respect to each context in the set of contexts, and
generate a contextual index that associates each sentence with one or more of the contexts in the set of contexts based on the context score; and
query processing circuitry in communication with the preprocessing circuitry and configured to
receive an electronic search query provided by a user, wherein the electronic search query comprises a plurality of search terms, and
generate a contextual search ranking for a subset of the set of electronic documents based on the search terms and the contextual index.

2 . The computing system of claim 1 , wherein the preprocessing circuitry is further configured to identify the set of terms for each sentence based on natural language processing.

3 . The computing system of claim 1 , wherein (a) the set of contexts comprises a hierarchical set of contexts, and (b) the preprocessing circuitry and the query processing circuitry are the same.

4 . The computing system of claim 3 , wherein the preprocessing circuitry is further configured to:
generate a pathscore for each sentence with respect to each context in the hierarchical set of contexts; and generate the contextual index based on the pathscore.

5 . The computing system of claim 1 , wherein the preprocessing circuitry is further configured to generate the contextual index based on supervised text classification.

6 . The computing system of claim 1 , wherein the query processing circuitry is further configured to:
generate contextual field level normalization information based on the set of terms; and generate the contextual search ranking further based on the contextual field level normalization information.

7 . The computing system of claim 1 , wherein the query processing circuitry is further configured to:
generate keyword strength information based on the set of sentences and the set of terms; and generate the contextual search ranking further based on the keyword strength information.

8 . The computing system of claim 1 , wherein the query processing circuitry is further configured to:
generate context strength information based on the context score; and generate the contextual search ranking further based on the context strength information.

9 . The computing system of claim 8 ,
wherein the set of contexts comprises a hierarchical set of contexts; wherein the preprocessing circuitry is further configured to generate a pathscore for each sentence with respect to each context in the hierarchical set of contexts; and wherein the query processing circuitry is further configured to generate the context strength information further based on the pathscore.

10 . The computing system of claim 1 , wherein the query processing circuitry is further configured to:
generate relevancy ranking information for each electronic document based on one or more of contexts; and generate the contextual search ranking further based on the relevancy ranking information.

11 . The computing system of claim 10 , wherein the query processing circuitry is further configured to:
generate a cumulative ranking score for each electronic document based on the relevancy ranking information; and generate the contextual search ranking further based on the cumulative ranking score for each electronic document.

12 . The computing system of claim 1 , further comprising user interface circuitry configured to:
generate user interface data based on the contextual search ranking, wherein the user interface data is configured to be displayed by a display device; and transmit the user interface data to the display device.

13 . A computing method for searching electronic documents, the method comprising:
receiving, by preprocessing circuitry, a set of electronic documents, wherein each electronic document in the set of electronic documents comprises a set of sentences; identifying, by the preprocessing circuitry, a set of terms for each sentence, wherein each term in the set of terms is associated with one or more contexts in a set of contexts; generating, by the preprocessing circuitry based on the set of terms, a context score for each sentence with respect to each context in the set of contexts; generating, by the preprocessing circuitry, a contextual index that associates each sentence with one or more of the contexts in the set of contexts based on the context score; receiving, by query processing circuitry, an electronic search query provided by a user, wherein the electronic search query comprises a plurality of search terms; and generating, by the query processing circuitry, a contextual search ranking for a subset of the set of electronic documents based on the search terms and the contextual index.

14 . The computing method of claim 13 , further comprising:
generating, by the query processing circuitry, contextual field level normalization information based on the set of terms; and generating, by the query processing circuitry, the contextual search ranking further based on the contextual field level normalization information.

15 . The computing method of claim 13 , further comprising:
generating, by the query processing circuitry, keyword strength information based on the set of sentences and the set of terms; and generating, by the query processing circuitry, the contextual search ranking further based on the keyword strength information.

16 . The computing method of claim 13 , further comprising:
generating, by the query processing circuitry, context strength information based on the context score; and generating, by the query processing circuitry, the contextual search ranking further based on the context strength information.

17 . The computing method of claim 16 , wherein the set of contexts comprises a hierarchical set of contexts, and wherein the computing method further comprises:
generating, by the preprocessing circuitry, a pathscore for each sentence with respect to each context in the hierarchical set of contexts; and generating, by the query processing circuitry, context strength information further based on the pathscore.

18 . The computing method of claim 13 , further comprising:
generating, by the query processing circuitry, relevancy ranking information for each electronic document based on one or more of contexts; and generating, by the query processing circuitry, a cumulative ranking score for each electronic document based on the relevancy ranking information; and generating, by the query processing circuitry, the contextual search ranking further based on the relevancy ranking information and the cumulative ranking score for each electronic document.

19 . The computing method of claim 13 , further comprising:
generating, by user interface circuitry, user interface data based on the contextual search ranking, wherein the user interface data is configured to be displayed by a display device; and transmitting, by the user interface circuitry, the user interface data to the display device, wherein the pr

Assignees

• Optum Tech Inc

Inventors

• Sinha Anshuman
• Singh Sanjay Kumar
• Sagar Nilabh

Classifications

• G06F16/313 Primary

  Selection or weighting of terms for indexing · CPC title

• G06F16/353

  into predefined classes · CPC title

• G06F16/338

  Presentation of query results · CPC title

• G06F16/93

  Document management systems · CPC title

• G06F16/3344 Primary

  using natural language analysis · CPC title