Information searching method and device

• US 9,785,672 B2
• Filed: 12/18/2014
• Issued: 10/10/2017
• Est. Priority Date: 04/10/2014
• Status: Active Grant

• Current Assignee: Beijing Baidu Netcom Science and Technology Company Limited (Baidu Incorporated)
• Original Assignee: Beijing Baidu Netcom Science and Technology Company Limited (Baidu Incorporated)
• Inventors: Li, Tingting, Wan, Wei, Zhao, Shiqi
• Primary Examiner(s): Truong, Dennis
• Application Number:
  US14/575,364
• Publication Number:
  US 20150293970A1
• Time in Patent Office: 1,027 Days
• Field of Search: 707722, 707999003, 707E17068, 707765, 707E17014, 707E17058, 707E17069, 707E17071, 707E17078, 707E17084, 707766, 707771, 707999005, 704 9
• CPC Class Codes: G06F 16/24532 of parallel queries
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems

Abstract

An information searching method and an information searching device are provided. The information searching method includes: receiving, at one or more computing devices, a first query from a client device, and obtaining, at the one or more computing devices an intention clarification guidance sentence according to the first query; receiving a second query updated according to the intention clarification guidance sentence; obtaining a search result according to the second query; and returning the search result to the client device.

Claims

1. A computer-implemented information searching method, comprising:

receiving, at one or more computing devices, a first query from a client device;

establishing, at one or more computing devices, a sentence library;

obtaining, at the one or more computing devices, an intention clarification guidance sentence by searching the sentence library according to the first query;

receiving a second query updated according to the intention clarification guidance sentence;

obtaining a search result according to the second query; and

returning the search result to the client device;

wherein establishing a sentence library comprises;

obtaining, at one or more computing devices, a first sentence according to first information;

obtaining, at one or more computing devices, a second sentence according to second information related to the first information; and

establishing, at one or more computing devices, at least one sentence pair in the sentence library according to the first sentence and the second sentences;

wherein obtaining the intention clarification guidance sentence by searching the sentence library according to the first query comprises;

obtaining, at one or more computing devices, a first feature sentence related to the feature information according to the feature information, if determining that a semantic similarity between the first feature sentence and the first query is larger than a first preset threshold; and

obtaining, at one or more computing devices, a second feature sentence corresponding to the first feature sentence, if;

(1) determining that the first query excludes a keyword of a preset type of the second feature sentence;

or

(2) determining that a semantic similarity between the first query and the second feature sentence is smaller than a second preset threshold.

2. The method according to claim 1, further comprising:

filtering, at one or more computing devices, the sentence pair in the sentence library.

3. The method according to claim 1, wherein obtaining an intention clarification guidance sentence according to the first query further comprises:

obtaining, at one or more computing devices, feature information of the first query;

searching, at one or more computing devices, the sentence library according to the first feature sentence; and

obtaining, at one or more computing devices, the intention clarification guidance sentence according to the second feature sentence.

4. The method according to claim 3, wherein

obtaining a second sentence according to second information related to the first information comprises:

obtaining, at one or more computing devices, a plurality of second sentences according to the second information related to the first information,

wherein obtaining the intention clarification guidance sentence according to the second sentence comprises;

sequencing, at one or more computing devices, the second sentences to obtain clustered second sentences; and

sequencing, at one or more computing devices, the clustered second sentences to obtain the intention clarification guidance sentence.

5. The method according to claim 4, wherein sequencing and clustering the second sentences to obtain clustered second sentences comprises:

sequencing, at one or more computing devices, the second sentences according to

6. The method according to claim 1, wherein obtaining a first sentence according to first information comprises:

dividing, at one or more computing devices, the first information;

detecting, at one or more computing devices, whether the first information belongs to a preset sentence type according to a preset language model; and

obtaining, at one or more computing devices, the first sentence according to the first information, if it is determined that the first information belongs to the preset sentence type.

7. The method according to claim 1, wherein obtaining a second sentence according to second information related to the first information comprises:

dividing, at one or more computing devices, the second information;

detecting, at one or more computing devices, whether the second information belongs to a preset sentence type according to a preset feature; and

obtaining, at one or more computing devices, the second sentence according to the second information, if it is determined the second information belongs to the preset sentence type.

8. An information searching device, comprising:

one or more computing devices configured to execute one or more software modules, the one or more software modules including;

an establishing module configured to establish a sentence library;

a first obtaining module configured to receive a first query and to obtain an intention clarification guidance sentence by searching the sentence library according to the first query;

a second obtaining module configured to receive a second query updated according to the intention clarification guidance sentence, and to obtain a search result according to the second query; and

a returning module configured to return the search result;

wherein the first obtaining module comprises;

a first feature obtaining unit configured to obtain feature information of the first query and to obtain a first feature sentence related to the feature information according to the feature information, if determining that a semantic similarity between the first feature sentence and the first query is larger than a first preset threshold; and

a second feature obtaining unit configured to search the sentence library according to the first feature sentence and to obtain a second feature sentence corresponding to the first feature sentence, if;

(1) determining that the first query excludes a keyword of a preset type of the second feature sentence, or

(2) determining that a semantic similarity between the first query and the second feature sentence is smaller than a second preset threshold; and

wherein the establishing module is further configured to comprise;

a first obtaining unit configured to obtain a first sentence according to first information;

a second obtaining unit configured to obtain a second sentence according to second information related to the first information; and

an establishing unit configured to establish at least one sentence pair in the sentence library according to the first sentence and the second sentence.

9. The device according to claim 8, wherein the establishing module comprises:

a filtering unit configured to filter the sentence pair in the sentence library.

10. The device according to claim 8, wherein the first obtaining module further comprises:

a third obtaining unit configured to obtain the intention clarification guidance sentence according to the second feature sentence.

11. The device according to claim 10, wherein the second obtaining unit is further configured to obtain a plurality of second sentences according to second information related to the first information;

and the third obtaining unit comprises;

a clustering subunit configured to sequence and cluster the second sentences to obtain clustered second sentences; and

an obtaining subunit configured to sequence the clustered second sentences to obtain the intention clarification guidance sentence.

12. The device according to claim 11, wherein the clustering subunit is further configured to sequence the second sentences according to

13. The device according to claim 8, wherein the first obtaining unit is further configured to divide the first information, to detect whether the first information belongs to a preset sentence type according to a preset language model, and to obtain the first sentence according to the first information if it is determined that the first information belongs to the preset sentence type.

14. The device according to claim 8, wherein the second obtaining unit is further configured to divide the second information, to detect whether the second information belongs to a preset sentence type according to a preset feature, and to obtain the second sentence according to the second information if it is determined the second information belongs to the preset sentence type.

15. A non-transitory computer readable storage medium, comprising a computer program configured to execute the following steps on one or more computing devices:

receiving a first query from a client device;

establishing a sentence library;

obtaining an intention clarification guidance sentence by searching the sentence library according to the first query;

receiving a second query updated according to the intention clarification guidance sentence;

obtaining a search result according to the second query; and

returning the search result to the client device;

wherein establishing a sentence library comprises;

obtaining, at one or more computing devices, a first sentence according to first information;

obtaining, at one or more computing devices, a second sentence according to second information related to the first information; and

establishing, at one or more computing devices, at least one sentence pair in the sentence library according to the first sentence and the second sentence; and

wherein obtaining the intention clarification guidance sentence by searching the sentence library according to the first query comprises;

obtaining, at one or more computing devices, a first feature sentence related to the feature information according to the feature information, if determining that a semantic similarity between the first feature sentence and the first query is larger than a first preset threshold; and

obtaining, at one or more computing devices, a second feature sentence corresponding to the first feature sentence, if;

(1) determining that the first query excludes a keyword of a preset type of the second feature sentence;

or

(2) determining that a semantic similarity between the first query and the second feature sentence is smaller than a second preset threshold.