Automating multilingual indexing

Patent metadata

Field	Value
Publication number	US-9715490-B2
Application number	US-201514934250-A
Country	US
Kind code	B2
Filing date	Nov 6, 2015
Priority date	Nov 6, 2015
Publication date	Jul 25, 2017
Grant date	Jul 25, 2017

Abstract

In an approach to automating multilingual indexing, a computer receives text of a conversation between at least two users. The computer detects at least one language associated with the text. The computer determines whether the language associated with the text is detected with a confidence level that exceeds a threshold. The computer retrieves text from one or more previous conversations between the two users. The computer detects at least one language associated with the text. The computer determines whether the at least one language associated with the text is detected with a confidence level that exceeds a pre-defined threshold. The computer analyzes the text using at least one of the detected languages to create one or more terms. The computer indexes the one or more terms and stores a boost value associated with each of the one or more indexed terms corresponding to confidence level of the detected language.

First claim

What is claimed is:

1. A method for automating multilingual indexing, the method comprising:
receiving, by one or more computer processors, text of a first conversation between a first user and at least one second user;
detecting, by the one or more computer processors, at least one language associated with the text of the first conversation;
determining, by the one or more computer processors, whether the at least one language associated with the text of the first conversation is detected with a first confidence level that exceeds a first pre-defined threshold;
responsive to determining the at least one language associated with the text of the first conversation is not detected with the first confidence level that exceeds the first pre-defined threshold, retrieving, by the one or more computer processors, text from one or more previous conversations between the first user and the at least one second user;
detecting, by the one or more computer processors, at least one language associated with the text of the one or more previous conversations between the first user and the at least one second user;
determining, by the one or more computer processors, whether the at least one language associated with the text of the one or more previous conversations between the first user and the at least one second user is detected with a second confidence level that exceeds a second pre-defined threshold;
responsive to determining the at least one language associated with the text of the one or more previous conversations between the first user and the at least one second user is detected with the second confidence level that exceeds the second pre-defined threshold, analyzing, by the one or more computer processors, the text of the first conversation using the at least one detected language associated with the text of the one or more previous conversations between the first user and the at least one second user to create one or more index terms, wherein index terms are included in the text of the first conversation;
indexing, by the one or more computer processors, the one or more index terms, wherein indexing serves as a mapping from the index terms to the text of the first conversation as automating multilingual indexing; and
storing, by the one or more computer processors, the second confidence level of the at least one detected language associated with the text of the one or more previous conversations between the first user and the at least one second user associated with each of the one or more index terms.

2. The method of claim 1 , further comprising:
responsive to determining the at least one language associated with the text of the one or more previous conversations between the first user and the at least one second user is not detected with the second confidence level that exceeds the second pre-defined threshold, retrieving, by the one or more computer processors, text from one or more previous conversations by at least one of the first user and the at least one second user;
detecting, by the one or more computer processors, at least one language associated with the text of the one or more previous conversations by at least one of the first user and the at least one second user; and
determining, by the one or more computer processors, the at least one language associated with the text of the one or more previous conversations by at least one of the first user and the at least one second user is detected with a third confidence level that exceeds a third pre-defined threshold.

3. The method of claim 2 , further comprising, responsive to determining the at least one language associated with the text of the one or more previous conversations by at least one of the first user and the at least one second user is not detected with the second confidence level that exceeds the second pre-defined threshold, retrieving, by the one or more computer processors, one or more preferred languages of the first user and the at least one second user.

4. The method of claim 3 , wherein retrieving one or more preferred languages further comprises:
retrieving, by the one or more computer processors, text input in one or more applications by a user;
determining, by the one or more computer processors, at least one of: a language setting of the one or more applications, a language setting of the user's one or more devices that include the one or more applications, and a language of the text; and
determining, by the one or more computer processors, based, at least in part, on the at least one of the language setting of the one or more applications, the language setting of the one or more devices, and the language of the text, one or more preferred languages of the user.

5. The method of claim 4 , further comprising:
determining, by the one or more computer processors, a third confidence level of the language of the text input in one or more applications by the user;
determining, by the one or more computer processors, whether the third confidence level exceeds a third pre-defined threshold;
responsive to determining the third confidence level exceeds the third pre-defined threshold, determining, by the one or more computer processors, based, at least in part, on the at least one of the language setting of the one or more applications, the language setting of the one or more devices, and the language of the text input in one or more applications by the user, one or more preferred languages of the user; and
storing, by the one or more computer processors, the one or more preferred languages.

6. The method of claim 5 , further comprising, responsive to determining the third confidence level does not exceed the third pre-defined threshold, determining, by the one or more computer processors, based, at least in part, on the at least one of the language setting of the one or more applications and the language setting of the one or more devices, one or more preferred languages of the user.

7. The method of claim 5 , wherein the third confidence level is based, at least in part, on at least one of: a quantity of text created in each language, and a degree of matching between the text input and a base form of the text input.

8. A computer program product for automating multilingual indexing, the computer program product comprising:
one or more computer readable storage device and program instructions stored on the one or more computer readable storage device and executed by one or more computer processors, the stored program instructions comprising:
program instructions to receive text of a first conversation between a first user and at least one second user;
program instructions to detect at least one language associated with the text of the first conversation;
program instructions to determine whether the at least one language associated with the text of the first conversation is detected with a first confidence level that exceeds a first pre-defined threshold;
responsive to determining the at least one language associated with the text of the first conversation is not detected with the first confidence level that exceeds the first pre-defined threshold, program instructions to retrieve text from one or more previous conversations between the first user and the at least one second user;
program instructions to detect at least one language associated with the text of the one or more previous conversations between the first user and the at least one second user;
program instructions to determine whether the at least one language associated with the text of the one or more previous conversations between the first user and the at least one second user is detected with a second confidence level that exceeds a second pre-defined threshold;
responsive to determining the at l

Assignees

• IBM

Inventors

• Bolshinsky Leonid
• Krisher Sharon
• Shapiro Eitan

Classifications

• G06F16/316

  Indexing structures · CPC title

• G06F16/337 Primary

  Profile generation, learning or modification · CPC title

• G06F40/263 Primary

  Language identification · CPC title

• G06F17/30619

  Physics · mapped topic

• G06F17/275 Primary

  Physics · mapped topic