Systems, apparatuses, and methods for providing emphasis in query results

Patent metadata

Field	Value
Publication number	US-2021157854-A1
Application number	US-201916697979-A
Country	US
Kind code	A1
Filing date	Nov 27, 2019
Priority date	Nov 27, 2019
Publication date	May 27, 2021
Grant date	—

Abstract

Techniques for displaying a search are described. An exemplary method includes receiving a search query, performing the search query on a plurality of documents, the documents including text passages, to generate a search query result, determining an aspect of the search query result that has a confidence value that exceeds a first confidence threshold with respect to its relevance to the search query; and, displaying the search result including an emphasis on the aspect of the result exceeds the first confidence threshold.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
receiving a document search query; querying at least one index based upon the document search query to identify matching data; fetching the identified matched data; determining one or more of a top ranked passage, top ranked documents, and a top ranked frequently asked question from set of documents based upon one or more invocations of one or more machine learning models based at least on the fetched identified matched data and the document search query; determining an aspect of the one or more of a top ranked passage, top ranked documents, and a top ranked frequently asked question has a confidence value that exceeds a first confidence threshold with respect to its relevance to the document search query; and displaying the one or more of the top ranked passage, the proper subset of documents, and the top ranked frequently asked question including an emphasis on the aspect of the result exceeds the first confidence threshold.

2 . The computer-implemented method of claim 1 , wherein the aspect does not include text from the document search query.

3 . The computer-implemented method of claim 1 , wherein the confidence value is derived from an output of one or more of the machine learning models.

4 . A computer-implemented method comprising:
receiving a search query; performing the search query on a plurality of documents, the documents including text passages, to generate a search query result; determining an aspect of the search query result that has a confidence value that exceeds a first confidence threshold with respect to its relevance to the search query; and displaying the search result including an emphasis on the aspect of the result exceeds the first confidence threshold.

5 . The computer-implemented method of claim 4 , wherein the search query utilizes a one or more machine learning models in the generation of the search query result.

6 . The computer-implemented method of claim 5 , wherein the confidence value is derived from an output of one or more of the machine learning models.

7 . The computer-implemented method of claim 4 , where the result includes a one or more of the top ranked passage and the proper subset of documents.

8 . The computer-implemented method of claim 4 , wherein the document search query includes a question to be answered and the result includes the answer.

9 . The computer-implemented method of claim 4 , further comprising:
determining the aspect of the one or more of a top ranked passage, top ranked documents, and a top ranked frequently asked question has a confidence value that exceeds a second confidence threshold with respect to its relevance to the document search query, wherein when the first and second confidence thresholds are exceeded the emphasis is highlighting.

10 . The computer-implemented method of claim 9 , wherein when only the first confidence threshold is exceeded the emphasis is one or more of bolding, text coloring, underlining, a change in font size, a change in font, or a stylization of a font.

11 . The computer-implemented method of claim 4 , wherein the documents comprise at least word processing documents, text files, and postscript-based files.

12 . The computer-implemented method of claim 4 , further comprising:
receiving feedback on the displayed result.

13 . The computer-implemented method of claim 12 , wherein the feedback is to be used to retrain one or more machine learning models utilized in the generation of the search query result.

14 . The computer-implemented method of claim 4 , wherein the emphasis is one or more of highlighting, text coloring, bolding, underlining, a change in font size, a change in font, or a stylization of a font.

15 . A system comprising:
data storage to store a plurality of documents; and a search service implemented by one or more electronic devices, the search service including instructions that upon execution cause the search service to:
receive a search query,
perform the search query on a plurality of documents, the documents including text passages, to generate a search query result,
determine an aspect of the search query result that has a confidence value that exceeds a first confidence threshold with respect to its relevance to the search query, and
display the search result including an emphasis on the aspect of the result exceeds the first confidence threshold.

16 . The system of claim 15 , wherein the document search query includes a question to be answered and the result includes the answer.

17 . The system of claim 15 , wherein the search service is further to:
determine the aspect of the one or more of a top ranked passage, top ranked documents, and a top ranked frequently asked question has a confidence value that exceeds a second confidence threshold with respect to its relevance to the document search query, wherein when the first and second confidence thresholds are exceeded the emphasis is highlighting.

18 . The system of claim 15 , wherein when only the first confidence threshold is exceeded the emphasis is one or more of bolding, text coloring, underlining, a change in font size, a change in font, or a stylization of a font.

19 . The system of claim 15 , wherein the documents comprise at least word processing documents, text files, and postscript-based files.

20 . The system of claim 15 , wherein the emphasis is one or more of highlighting, text coloring, bolding, underlining, a change in font size, a change in font, or a stylization of a font.

Assignees

• Amazon Tech Inc

Inventors

• Wang Zhiguo
• Huang Zhiheng
• Nallapati Ramesh M
• Xiang Bing

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F16/93 Primary

  Document management systems · CPC title

• G06F16/908

  using metadata automatically derived from the content · CPC title

• G06F16/9038 Primary

  Presentation of query results · CPC title