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

Patent metadata

Field	Value
Publication number	US-11526557-B2
Application number	US-201916697979-A
Country	US
Kind code	B2
Filing date	Nov 27, 2019
Priority date	Nov 27, 2019
Publication date	Dec 13, 2022
Grant date	Dec 13, 2022

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 a top ranked passage, a set of top ranked documents, and a top ranked frequently asked question based upon one or more invocations of one or more machine learning models, the fetched identified matched data, and the document search query;
determining a confidence value for a text portion of the top ranked passage, the confidence value reflecting how relevant the text portion is to the document search query;
selecting from among at least a first type of text emphasis, a second type of text emphasis, and a third type of text emphasis according to how relevant the text portion is to the document search query, the first type of text emphasis representing a greater relevance than the second type of text emphasis, the second type of text emphasis representing a greater relevance than the third type of text emphasis; and
causing display in a graphical user interface of the top ranked passage, an indication of the set of top ranked documents, and the top ranked frequently asked question, the graphical user interface presenting the text portion of the top ranked passage with the first type of text emphasis and presenting a remaining text portion of the top ranked passage without the first type of text emphasis.

2. The computer-implemented method of claim 1 , wherein the text portion 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 a text aspect of the search query result that has a confidence value that exceeds a confidence threshold with respect to its relevance to the search query;
selecting from among at least a first type of visual emphasis, a second type of visual emphasis, and a third type of visual emphasis based on how relevant the text aspect of the search query result is to the search query, the first type of visual emphasis representing a greater relevance than the second type of visual emphasis, the second type of visual emphasis representing a greater relevance than the third type of visual emphasis; and
displaying the search result including with the first type of visual emphasis on the text aspect of the result that exceeds the confidence threshold and without the first type of visual emphasis on a remaining text aspect of the result.

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

8. The computer-implemented method of claim 4 , further comprising:
selecting the first type of visual emphasis based on the confidence value exceeding the confidence threshold.

9. The computer-implemented method of claim 8 , wherein the first type of visual 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.

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

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

12. The computer-implemented method of claim 11 , wherein the feedback is to be used to retrain one or more machine learning models utilized in the generation of the search query result.

13. The computer-implemented method of claim 4 , wherein the second type of visual 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.

14. The method of claim 4 , wherein the first type of visual emphasis comprises bolding and underlining the text aspect, and wherein the remaining text aspect of the result is not bolded and underlined.

15. A system comprising:
a document storage to store a plurality of documents; and
one or more electronic devices to implement a search service, 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 a text aspect of the search query result that has a confidence value that exceeds a confidence threshold with respect to its relevance to the search query,
select from among at least a first type of visual emphasis, a second type of visual emphasis, and a third type of visual emphasis based on how relevant the text aspect of the search query result is to the search query, the first type of visual emphasis representing a greater relevance than the second type of visual emphasis, the second type of visual emphasis representing a greater relevance than the third type of visual emphasis, and
display the search result including with the first type of visual emphasis on the text aspect of the result and without the first type of visual emphasis on a remaining text aspect of the result.

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:
select the first type of visual emphasis based on the confidence value exceeding the confidence threshold.

18. The system of claim 15 , wherein the first type of visual 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 third type of visual emphasis does not include any 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

• G06F16/93 Primary

  Document management systems · CPC title

• G06F16/9038 Primary

  Presentation of query results · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F16/908

  using metadata automatically derived from the content · CPC title