Methods, devices, and systems for constructing intelligent knowledge base

1. An abstract semantic recommending device, comprising:

an abstract semantic expression obtaining unit to obtain a plurality of abstract semantic expressions;

a receiving unit to receive an initial request message;

a word segmentation unit to perform a word segmentation process on the initial request message to obtain one or more single words;

a part-of-speech tagging unit to perform a part-of-speech tagging process on at least one of the one or more single words to obtain its part-of-speech information;

a wordclass determination unit to perform a wordclass determination process on at least one of the one or more single words to obtain its wordclass information;

a searching unit to perform a searching process on the obtained plurality of abstract semantic expressions to acquire an abstract semantic candidate set relevant to the initial request message, wherein the abstract semantic candidate set comprises several abstract semantic expressions; and

a matching unit to derive one or more abstract semantic expressions corresponding to the initial request message by performing a matching process on the several abstract semantic expressions in the abstract semantic candidate set based on the part-of-speech information and the wordclass information.

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

a rule word identification unit to identify each of the one or more single words as a semantic rule word or a non-semantic rule word; wherein

the part-of-speech tagging unit performs the part-of-speech tagging process on each non-semantic rule word during the part-of-speech tagging process to obtain part-of-speech information of the each non-semantic rule word; and

the wordclass determination unit performs the wordclass determination process on each semantic rule word during the wordclass determination process to obtain wordclass information of the each semantic rule word.

3. The device according to claim 2 , wherein:

the derived one or more abstract semantic expressions comprise a semantic rule word; and

at least one of semantic rule words of the several abstract semantic expressions in the abstract semantic candidate set obtained by the searching unit is the same as or belongs to a same wordclass as one of the one or more single words of the initial request message.

4. The device according to claim 3 , wherein the derived one or more abstract semantic expressions comprise a semantic-lacking element and satisfy the following conditions:

a part-of-speech corresponding to the semantic-lacking element comprises a part-of-speech of a filling element, the filling element being extracted from the initial request message and corresponding to the semantic-lacking element;

a keyword of the initial request message excluding the filling element is the same or belongs to a same wordclass as the semantic rule word; and

the derived one or more abstract semantic expressions have a same order as the initial request message.

5. The device according to claim 1 , further comprising:

the part-of-speech tagging unit performs the part-of-speech tagging process on each of the one or more of single words to obtain its part-of-speech information; and

the wordclass determination unit performs the wordclass determination process on each of the one or more of single words to obtain its wordclass information.

6. The device according to claim 5 , further comprising:

a number determination unit to determine whether a number of the several abstract semantic expressions in the abstract semantic candidate set is within a predetermined range;

a removing unit to remove, when the number of the several abstract semantic expressions in the abstract semantic candidate set is above the predetermined range, one or more of the several abstract semantic expressions; and

a supplementing unit to supplement, when the number of the several abstract semantic expressions in the abstract semantic candidate set is under the predetermined range, one or more of the several abstract semantic expressions from a default set.

7. The device according to claim 1 :

wherein the derived one or more abstract semantic expression comprise a semantic-lacking element; and

the device further comprises:

a filling unit to exact from the initial request message an element corresponding to the semantic-lacking element of the derived one or more abstract semantic expressions, and to fill the extracted element into the semantic-lacking element to obtain one or more specific semantic expressions corresponding to the initial request message.

8. The device according to claim 7 , further comprising:

a scoring unit to:

when a number M of the derived one or more abstract semantic expressions corresponding to the initial request message is greater than a predetermined number N, perform a scoring process on each of the derived one or more abstract semantic expressions corresponding to the initial request message;

wherein the filling unit further:

fills the extracted element into a semantic-lacking element of N abstract semantic expressions having higher scores; and

obtains N specific semantic expressions corresponding to the initial request message based on the filling.

9. The device according to claim 8 , wherein the scoring unit performs a scoring process according to one or more methods selected from a group comprising:

setting a higher score to an abstract semantic expression corresponding to the initial request message if a number of the matched semantic-lacking elements is higher;

defining a semantic-lacking element of a certain abstract semantic expression as a core semantic element, and setting a higher score to an abstract semantic expression if the abstract semantic expression's semantic-lacking element is closer to the core semantic element;

setting a higher score to an abstract semantic expression if a confidence value of the abstract semantic expression's part-of-speech is higher;

setting a higher score to an abstract semantic expression if a priority level is higher, wherein the priority level is pre-assigned to the abstract semantic expression; and/or

setting a higher score to an abstract semantic expression if a probability is higher, wherein the probability is determined based on a natural language model and corresponds to whether data information obtained by filling segmentation words of a large amount of crawled corpus data into the abstract semantic expression has correct semantic information.

10. A computer-implemented abstract semantic recommending method, comprising:

providing an abstract semantic database, wherein the abstract semantic database comprises a plurality of abstract semantic expressions;

receiving an initial request message;

performing a word segmentation process on the initial request message to obtain one or more single words;

performing a part-of-speech tagging process on at least one of the one or more single words to obtain its part-of-speech information;

performing a wordclass determination process on at least one of the one or more single words to obtain its wordclass information;

performing a searching process on the obtained one or more abstract semantic database to acquire an abstract semantic candidate set relevant to the initial request message, wherein the abstract semantic candidate set comprises several abstract semantic expressions; and

deriving one or more abstract semantic expressions corresponding to the initial request message by performing a matching process on the several abstract semantic expressions in the abstract semantic candidate set based on the part-of-speech information and the wordclass information.

11. The method according to claim 10 , further comprising:

identifying each of the one or more single words as a semantic rule word or a non-semantic rule word after the word segmentation process;

performing a part-of-speech tagging process on each non-semantic rule word to obtain part-of-speech information of the each non-semantic rule word; and

performing a wordclass determination process on each semantic rule word to obtain wordclass information of the each semantic rule word.

12. The method according to claim 11 , further comprising:

the derived one or more abstract semantic expressions comprises a semantic rule word; and

at least one of semantic rule words of the several abstract semantic expressions in the abstract semantic candidate set is the same or belongs to a same wordclass as one of the single words of the initial request message.

13. The method according to claim 12 , wherein the derived one or more abstract semantic expressions comprises a semantic lacking element and satisfy the following conditions:

a part-of-speech corresponding to the semantic-lacking element comprises a part-of-speech of a filling element, the filling element being extracted from the initial request message and corresponding to the semantic-lacking element;

a keyword of the initial request message excluding the filling element is the same or belongs to a same wordclass as the semantic rule word; and

the derived one or more abstract semantic expressions have a same order as the initial request message.

14. The method according to claim 10 , further comprising:

performing a part-of-speech tagging process on each of the one or more single words to obtain its part-of-speech information; and

performing a wordclass determination process on each of the one or more single words to obtain its wordclass information.

15. The method according to claim 14 , further comprising:

determining, before the matching process, whether a number of the several abstract semantic expressions in the abstract semantic candidate set is within a predetermined range;

removing, when the number of the several abstract semantic expressions in the abstract semantic candidate set is above the predetermined range, one or more of the several abstract semantic expressions;

supplementing, when the number of the several abstract semantic expressions in the abstract semantic candidate set is under the predetermined range, one or more of the several abstract semantic expressions from a default set.

16. The method according to claim 10 :

wherein the derived one or more abstract semantic expressions comprise a semantic-lacking element; and

the method further comprises:

extracting from the initial request message an element corresponding to the semantic-lacking element of the derived one or more abstract semantic expressions; and

filling the extracted element into the semantic-lacking element to obtain one or more specific semantic expressions corresponding to the initial request message.

17. The method according to claim 16 , further comprising:

determining a number M of the derived one or more abstract semantic expressions corresponding to the initial request message is larger than a predetermined number N;

performing, based on the determination, a scoring process on each abstract semantic expression corresponding to the initial request message;

extracting, from the initial request message, an element corresponding to a semantic-lacking element of N abstract semantic expressions having higher scores;

filling the extracted element into the corresponding semantic-lacking element of the N abstract semantic expressions having higher scores; and

obtaining N specific semantic expressions corresponding to the initial request message based on the filling.

18. The method according to claim 17 , wherein the scoring process employs one or more methods selected from a group comprising:

setting a higher score to an abstract semantic expression corresponding to the initial request message if a number of the matched semantic-lacking elements is higher;

defining a semantic-lacking element of a certain abstract semantic expression as a core semantic element, and setting a higher score to an abstract semantic expression if the abstract semantic expression's semantic-lacking element is closer to the core semantic element;

setting a higher score to an abstract semantic expression if the confidence value of the abstract semantic expression's part-of-speech is higher;

setting a higher score to an abstract semantic expression if a priority level is higher, wherein the priority level is pre-assigned to the abstract semantic expression; and/or

setting a higher score to an abstract semantic expression if a probability is higher, wherein the probability is determined based on a natural language model, and corresponds to whether data information obtained by filling segmentation words of a large amount of crawled corpus data into the abstract semantic expression has correct semantic information.

19. A non-transitory computer-readable-medium storing instructions that, when executed, cause a computer to perform an abstract semantic recommending method, comprising:

providing an abstract semantic database, wherein the abstract semantic database comprises a plurality of abstract semantic expressions;

receiving an initial request message;

performing a word segmentation process on the initial request message to obtain one or more single words;

performing a part-of-speech tagging process on at least one of the one or more single words to obtain its part-of-speech information;

performing a wordclass determination process on at least one of the one or more single words to obtain its wordclass information;

performing a searching process on the obtained one or more abstract semantic database to acquire an abstract semantic candidate set relevant to the initial request message, wherein the abstract semantic candidate set comprises several abstract semantic expressions; and

deriving one or more abstract semantic expressions corresponding to the initial request message by performing a matching process on the several abstract semantic expressions in the abstract semantic candidate set based on the part-of-speech information and the wordclass information.