Method and apparatus for information query and storage medium

1. A method for information query, comprising:

receiving a query sentence, segmenting the query sentence to obtain word segments, and obtaining a dependency relationship between two word segments and part of speech of the word segments;

obtaining a coding sequence of the query sentence according to the dependency relationship and the part of speech of the word segments;

matching the coding sequence with a generalized template to obtain a core corpus of the query sentence, wherein the generalized template comprises part of speech to be extracted and a dependency relationship to be extracted; and

obtaining a query result corresponding to the query sentence based on the core corpus,

wherein, obtaining the query result corresponding to the query sentence based on the core corpus comprises:

retrieving, based on the core corpus, in a preset corpus database to obtain a target seed corpus corresponding to the core corpus;

determining label data corresponding to the target seed corpus as the query result corresponding to the query sentence,

wherein, retrieving, based on the core corpuses, in the preset corpus database to obtain the target seed corpus corresponding to the core corpus comprises:

retrieving, based on the core corpus, in the preset corpus database to obtain at least one candidate seed corpus corresponding to the core corpus; wherein, the preset corpus database stores a plurality of seed corpuses, and the core corpus is a generalized corpus of at least one seed corpus; and

determining the target seed corpus from the at least one candidate seed corpus.

2. The method of claim 1 , wherein, matching the coding sequence with the generalized template to obtain the core corpus of the query sentence comprises:

extracting coding fragments consistent with the part of speech to be extracted from the coding sequence according to the part of speech to be extracted;

determining a generalized boundary among the coding fragments according to the dependence relationship to be extracted, and extracting the core corpus according to the generalized boundary.

3. The method of claim 1 , wherein, retrieving, based on the core corpus, in the corpus database to obtain the at least one candidate seed corpus corresponding to the core corpus comprises:

retrieving the core corpus from the corpus database based on an inverted index and semantic similarity computation, to obtain at least one candidate seed corpus.

4. The method of claim 1 , wherein, determining the target seed corpus from the at least one candidate seed corpus comprises:

obtaining a similarity between the core corpus and each candidate seed corpus, and selecting a candidate seed corpus with the highest similarity as the target seed corpus.

5. The method of claim 1 , further comprising:

obtaining the number of the at least one candidate seed corpus; and

updating the generalized template in response to the number of the at least one candidate seed corpus greater than a first preset number or less than a second preset number.

6. An apparatus for information query, comprising:

one or more processors;

a memory storing instructions executable by the one or more processors;

wherein the one or more processors are configured to:

receive a query sentence, segment the query sentence to obtain word segments, and obtain a dependency relationship between two word segments and part of speech of the word segments;

obtain a coding sequence of the query sentence according to the dependency relationship and the part of speech of the word segments;

match the coding sequence with a generalized template to obtain a core corpus of the query sentence; wherein, the generalized template comprises part of speech to be extracted and a dependency relationship to be extracted;

obtain a query result corresponding to the query sentence based on the core corpus,

wherein the one or more processors are configured to:

retrieve, based on the core corpus, in a preset corpus database to obtain a target seed corpus corresponding to the core corpus;

determine label data corresponding to the target seed corpus as the query result corresponding to the query sentence,

wherein the one or more processors are configured to:

retrieve, based on the core corpuses, in the preset corpus database to obtain at least one candidate seed corpus corresponding to the core corpus; wherein, the preset corpus database stores a plurality of seed corpuses, and the core corpus is a generalized corpus of at least one seed corpus; and

determine the target seed corpus from the at least one candidate seed corpus.

7. The apparatus of claim 6 , wherein the one or more processors are configured to:

extract coding fragments consistent with the part of speech to be extracted from the coding information according to the part of speech to be extracted;

determine a generalized boundary among the coding fragments according to the dependence relationship to be extracted, and extract the core corpus according to the generalized boundary.

8. The apparatus of claim 6 , wherein the one or more processors are configured to:

retrieve the core corpus from the corpus database based on an inverted index and semantic similarity computation, to obtain at least one candidate seed corpus.

9. The apparatus of claim 6 , wherein the one or more processors are configured to:

obtain a similarity between the core corpus and each candidate seed corpus, and select a candidate seed corpus with the highest similarity as the target seed corpus.

10. The apparatus of claim 6 , wherein the one or more processors are configured to:

obtain the number of the at least one candidate seed corpus; and

update the generalized template in response to the number of the at least one candidate seed corpus greater than a first preset number or less than a second preset number.

11. A non-transitory computer-readable storage medium storing computer instructions, wherein when the computer instructions are executed by a computer, the computer is caused to perform a method for information query, and the method comprises:

receiving a query sentence, segmenting the query sentence to obtain word segments, and obtaining a dependency relationship between two word segments and part of speech of the word segments;

obtaining a coding sequence of the query sentence according to the dependency relationship and the part of speech of the word segments;

matching the coding sequence with a generalized template to obtain a core corpus of the query sentence, wherein the generalized template comprises part of speech to be extracted and a dependency relationship to be extracted; and

obtaining a query result corresponding to the query sentence based on the core corpus,

wherein, obtaining the query result corresponding to the query sentence based on the core corpus comprises:

retrieving, based on the core corpus, in a preset corpus database to obtain a target seed corpus corresponding to the core corpus;

determining label data corresponding to the target seed corpus as the query result corresponding to the query sentence,

wherein, retrieving, based on the core corpuses, in the preset corpus database to obtain the target seed corpus corresponding to the core corpus comprises:

retrieving, based on the core corpus, in the preset corpus database to obtain at least one candidate seed corpus corresponding to the core corpus; wherein, the preset corpus database stores a plurality of seed corpuses, and the core corpus is a generalized corpus of at least one seed corpus; and

determining the target seed corpus from the at least one candidate seed corpus.