METHOD AND APPARATUS FOR IDENTIFYING TYPE OF TEXT INFORMATION, STORAGE MEDIUM, AND ELECTRONIC APPARATUS

• US 20190325019A1
• Filed: 07/02/2019
• Published: 10/24/2019
• Est. Priority Date: 04/20/2017
• Status: Active Grant

• Current Assignee: Tencent Technology Shenzhen Company Limited (Tencent Holdings Limited)
• Original Assignee: Tencent Technology Shenzhen Company Limited (Tencent Holdings Limited)
• Inventors: FAN, Lin
• Granted Patent: US 10,929,600 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/083 Recognition networks G10L15/142, G10L15/16 take precedence
• CPC Class Codes: G10L 2015/088 Word spotting

Abstract

A method, apparatus, and computer-readable storage medium for identifying a type of text information is provided. Target text information is received from a terminal by a server. The server obtains usage information of the terminal within a preset time period in which the target text information is received. Scenario information of the terminal is determined by the server based on the usage information. The usage information corresponds to a target scenario indicated by the scenario information. Further, a target type of the target text information is identified by the server. The target type is identified by the target scenario.

Claims

1. A method for identifying a type of text information, comprising:

receiving, by a server, target text information from a terminal;

obtaining, by the server, usage information of the terminal within a preset time period in which the target text information is received;

determining, by the server, scenario information of the terminal based on the usage information, the usage information corresponding to a target scenario indicated by the scenario information; and

identifying, by the server, a target type of the target text information that is identified by the target scenario.

2. The method according to claim 1, wherein the usage information is contextual information for identifying the target type of the target text information.

3. The method according to claim 1, wherein the identifying comprises:

segmenting, by the server, target text of the target text information into a plurality of separate words;

determining, by the server when a target separate word is included in the plurality of separate words, whether a first type of a plurality of candidate types corresponding to the target separate word is included in a preset type list of the target scenario; and

determining, by the server after the first type is determined to be included in the preset type list, the first type as the target type of the target separate word.

4. The method according to claim 3, wherein before the determining whether the first type of the plurality of candidate types corresponding to the target separate word is included in the preset type list of the target scenario, the method further comprises:

determining, by the server based on a first correspondence between the target scenario and the preset type list, the preset type list corresponding to the target scenario from a plurality of type lists.

5. The method according to claim 1, wherein the determining the scenario information comprises:

determining, by the server, the scenario information of the terminal based on a second correspondence between the usage information and the scenario information, the scenario information corresponding to the usage information being one of a plurality of pieces of preset scenario information.

6. The method according to claim 1, wherein after the identifying the target type, the method further comprises:

outputting, by the server, the target type; and

sending, by the server indication information to the terminal based on the target type, the indication information instructing the terminal to perform a preset process.

7. The method according to claim 1, wherein the usage information of the terminal includes at least one or more of:

information about an application executed on the terminal;

information about a character displayed by the terminal;

information about a picture displayed by the terminal;

information about a web page displayed by the terminal;

information about a voice recorded on the terminal; and

information about a chat on the terminal.

8. An apparatus, comprising:

processing circuitry configured to

receive target text information from a terminal;

obtain usage information of the terminal within a preset time period in which the target text information is received;

determine scenario information of the terminal based on the usage information, the usage information corresponding to a target scenario indicated by the scenario information; and

identify a target type of the target text information that is identified by the target scenario.

9. The apparatus according to claim 8, wherein the usage information is contextual information for identifying the target type of the target text information.

10. The apparatus according to claim 8, wherein the processing circuitry is further configured to

segment target text of the target text information into a plurality of separate words;

determine, when a target separate word is included in the plurality of separate words, whether a first type of a plurality of candidate types corresponding to the target separate word is included in a preset type list of the target scenario; and

determine, after the first type is determined to be included in the preset type list, the first type as the target type of the target separate word.

11. The apparatus according to claim 10, wherein the processing circuitry is further configured to

determine, based on a first correspondence between the target scenario and the preset type list, the preset type list corresponding to the target scenario from a plurality of type list before the determination of whether the first type of the plurality of candidate types corresponding to the target separate word is included in the preset type list of the target scenario s.

12. The apparatus according to claim 8, wherein the processing circuitry is further configured to

determine the scenario information of the terminal based on a second correspondence between the usage information and the scenario information, the scenario information corresponding to the usage information being one of a plurality of pieces of preset scenario information.

13. The apparatus according to claim 8, wherein the processing circuitry is further configured to:

output the target type; and

send indication information to the terminal based on the target type, the indication information instructing the terminal to perform a preset process.

14. The apparatus according to claim 8, wherein the usage information of the terminal includes at least one or more of:

information about an application executed on the terminal;

information about a character displayed by the terminal;

information about a picture displayed by the terminal;

information about a web page displayed by the terminal;

information about a voice recorded on the terminal; and

information about a chat on the terminal.

15. A non-transitory computer readable storage medium storing instructions which when executed by at least one processor cause the at least one processor to perform:

receiving target text information from a terminal;

obtaining usage information of the terminal within a preset time period in which the target text information is received;

determining scenario information of the terminal based on the usage information, the usage information corresponding to a target scenario indicated by the scenario information; and

identifying a target type of the target text information that is identified by the target scenario.

16. The non-transitory computer readable storage medium according to claim 15, wherein the usage information is contextual information for identifying the target type of the target text information.

17. The non-transitory computer readable storage medium according to claim 15, wherein the identifying comprises:

segmenting target text of the target text information into a plurality of separate words;

determining, when a target separate word is included in the plurality of separate words, whether a first type of a plurality of candidate types corresponding to the target separate word is included in a preset type list of the target scenario; and

determining, after the first type is determined to be included in the preset type list, the first type as the target type of the target separate word.

18. The non-transitory computer readable storage medium according to claim 17, wherein before the determining whether the first type of the plurality of candidate types corresponding to the target separate word is included in the preset type list of the target scenario, the instructions when executed by the at least one processor further cause the at least one processor to perform:

determining, based on a first correspondence between the target scenario and the preset type list, the preset type list corresponding to the target scenario from a plurality of type lists.

19. The non-transitory computer readable storage medium according to claim 15, wherein the determining the scenario information comprises:

determining, by the server, the scenario information of the terminal based on a second correspondence between the usage information and the scenario information, the scenario information corresponding to the usage information being one of a plurality of pieces of preset scenario information.

20. The non-transitory computer readable storage medium according to claim 15, wherein after the identifying the target type, the instructions when executed by the at least one processor further cause the at least one processor to perform:

outputting the target type; and

sending indication information to the terminal based on the target type, the indication information instructing the terminal to perform a preset process.