METHOD AND DEVICE FOR IDENTIFYING INFORMATION, AND COMPUTER-READABLE STORAGE MEDIUM

• US 20170147553A1
• Filed: 11/02/2016
• Published: 05/25/2017
• Est. Priority Date: 11/24/2015
• Status: Active Grant

• Current Assignee: Xiaomi Inc. (Xiaomi Corp.)
• Original Assignee: Xiaomi Inc. (Xiaomi Corp.)
• Inventors: Wang, Pingze, Zhang, Tao, Chen, Zhijun
• Granted Patent: US 10,061,762 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 40/186 Templates
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: H04W 4/14 Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]

Abstract

A method, device, and a non-transitory computer-readable storage medium are provided for identifying information in an electronic message. The information from the electronic message may be identified according to a template that has been trained to classify the information included in the electronic message.

Claims

1. A method for identifying an electronic message, comprising:

identifying a clause in the electronic message;

segmenting the clause to identify one or more words from the clause;

extracting at least one characteristic word from the identified one or more words;

labeling the at least one characteristic word as a preset keyword; and

determining an information class of the electronic message based on the preset keyword, the at least one characteristic word, and a predetermined template.

2. The method of claim 1, further comprising:

when the electronic message includes a plurality of preset keywords corresponding to a plurality of clauses, determining a greatest preset keyword in a clause having a greatest probability of being identified as information of a preset labeling result.

3. The method of claim 1, wherein extracting the at least one characteristic word comprises:

extracting the at least one characteristic word according to a chi-square test;

or

extracting the at least one characteristic word according to information gains.

4. The method of claim 1, wherein the preset keyword is digital information, and the labeling result is an attribute of the digital information.

5. A device for identifying information, comprising:

a processor; and

a memory configured to store instructions executable by the processor;

wherein the processor is in communication with the memory and configured to execute the instructions to;

identify a clause in the electronic message;

segment the clause to identify one or more words from the clause;

extract at least one characteristic word from the identified one or more words;

label the at least one character word as a preset keyword; and

determine an information class of the electronic message based on the preset keyword, the at least one characteristic word, and a predetermined template.

6. The device of claim 5, wherein the processor is further configured to execute the instructions to, when the electronic message includes a plurality of preset keywords corresponding to a plurality of clauses, determine a greatest preset keyword in a clause having a greatest probability of being identified as information of a preset labeling result.

7. The device of claim 5, wherein the processor is further configured to execute the instructions to extract the at least one characteristic word according to a chi-square test or information gains.

8. The device of claim 5, wherein the preset keyword is digital information and the labeling results are attributes of the digital information.

9. A non-transitory computer-readable storage medium having stored therein instructions that, when executed by a processor, causes the processor to perform a method for identifying information, the method comprising:

identifying a clause in the electronic message;

segmenting the clause to identify one or more words from the clause;

extracting at least one characteristic word from the identified one or more words;

labeling the at least one character word as a preset keyword; and

determining an information class of the electronic message based on the preset keyword, the at least one characteristic word, and a predetermined template.

10. The non-transitory computer-readable storage medium of claim 9, wherein the method further comprises:

when the electronic message includes a plurality of preset keywords corresponding to a plurality of clauses, determining a greatest preset keyword in a clause having a greatest probability of being identified as information of a preset labeling result.

11. The non-transitory computer-readable storage medium of claim 9, wherein extracting the at least one characteristic word comprises:

extracting at least one characteristic word according to a chi-square test;

or

extracting the at least one characteristic word according to information gains.

12. The non-transitory computer-readable storage medium of claim 9, wherein the preset keyword is digital information, and the labeling result is an attribute of the digital information.