CN101178711A - Chinese auto-answer method and system - Google Patents
Chinese auto-answer method and system Download PDFInfo
- Publication number
- CN101178711A CN101178711A CNA2006101459852A CN200610145985A CN101178711A CN 101178711 A CN101178711 A CN 101178711A CN A2006101459852 A CNA2006101459852 A CN A2006101459852A CN 200610145985 A CN200610145985 A CN 200610145985A CN 101178711 A CN101178711 A CN 101178711A
- Authority
- CN
- China
- Prior art keywords
- statement
- user
- answer
- question
- keyword sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title abstract description 31
- 230000002708 enhancing effect Effects 0.000 abstract 1
- 230000008878 coupling Effects 0.000 description 15
- 238000010168 coupling process Methods 0.000 description 15
- 238000005859 coupling reaction Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 12
- 230000008676 import Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 9
- 230000011218 segmentation Effects 0.000 description 9
- 230000004044 response Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000004321 preservation Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Landscapes
- Document Processing Apparatus (AREA)
Abstract
The invention discloses a Chinese automatic answering method and a system. The invention solves the problems of huge work quantity and narrow cover range for establishing a Chinese question and answer statement base in the prior art when the Chinese automatic answering is achieved by a mode matching technique. The method comprises the steps that: the style and the key word sequence of the Chinese statement input by customer are determined; a key word sequence that is the same as the style of the statement input by the customer is searched from the question and answer statement base; the key word sequence of the statement input by the customer is matched with the searched key word sequence; and the answering statement corresponding to the key word sequence which is matched successfully is returned to the customer. The system comprises a customer statement analyzing module and an inquiring module. The invention has the advantages of increasing the content cover range of the question and answer statement base, reducing the work load for establishing the base, and obviously enhancing the accuracy and the recall rate of the Chinese automatic answering system.
Description
Technical field
The present invention relates to computer application field, relate in particular to a kind of Chinese auto-answer method and system.
Background technology
Natural language understanding technology is an important research direction in the artificial intelligence field, and it makes computing machine can understand and use human natural language, can realize between people and the computing machine efficient communication based on natural language.The natural language here comprises the human various natural languages that use, for example Chinese, English or the like.QA (automatic Question Answering, auto answer) system be a kind of be core with the natural language understanding technology, finish on the one hand analyzing and processing to customer problem, finish the system that correct option generates on the other hand.
The performance of automatic answering system mainly characterizes by accuracy rate and two indexs of recall rate, is illustrated respectively below:
The accuracy rate of automatic answering system is meant that automatic answering system makes the ratio of the number of times of correctly replying and altogether response times, for example the user has imported 100 problem statements to automatic answering system, automatic answering system has been made 100 times and has been replied, wherein have 20 to be correct, the accuracy rate of this automatic answering system is exactly 20% so.
The recall rate of automatic answering system is meant that automatic answering system makes the corresponding ratio that has the number of correctly replying in the number of times of correctly replying and the automatic answering system question and answer statement library, for example the user has imported 100 problem statements in automatic answering system, automatic answering system has been made 100 times and has been replied, it is correct wherein having 20 times, but 100 problem statements at user's input, have wherein correctly replying of 25 problem statements in the automatic answering system question and answer statement library, the recall rate of this automatic answering system is exactly 80% so.
Chinese automatic answering system of the prior art is with reference to English automatic answering system mostly, adopts simple mode-matching technique to realize.Its rudimentary algorithm is exactly from first speech, to in the problem statement of the current input of user and the question and answer statement library in advance the whole issue statement of storage mate, if two identical couplings that just continue next speech of speech, repeat this process and finish, just the systems response of this problem statement correspondence in the question and answer statement library is returned to the user if the match is successful up to the whole problem statement coupling of user input.But compare english sentence, the Chinese sentence has the advantages that word is flexible, sentence structure is complicated and changeable, therefore only adopt the Chinese automatic answering system ubiquity question and answer statement library coverage rate of simple mode-matching technique narrow, the accuracy rate and the low shortcoming of recall rate of system, illustrate the shortcoming that adopts the Chinese automatic answering system that simple mode-matching technique realizes below.
It is right to suppose to exist in the question and answer statement library of automatic answering system with next group question and answer statement, comprising a problem statement and corresponding systems response:
Does the problem statement: why the earth change around the sun?
Systems response: because the earth is the planet of the sun.
Work as that like this user imports " why the earth changes around the sun? " in automatic answering system during this problem statement, system can with in the problem statement of the current input of user and the question and answer statement library in advance the whole issue statement of storage mate, it is right to find the above-mentioned question and answer statement of storing in the question and answer statement library by coupling, the systems response of this question and answer statement centering is taken out return to the user.But, identical when user input with the sentence justice of the problems referred to above statement, during different other sentences of sentence structure, owing to do not store the corresponding problem statement in system's question and answer statement library, so can't provide correct replying.For example, when user input " why the earth changes around the sun? " perhaps " The Earth Revolves round the Sun is for what reason? " the time, system can't provide correct replying.
If wish to address the above problem in existing Chinese automatic answering system, two groups of question and answer statements are right below just must constructing in the question and answer statement library of system again:
Does user's sentence: why the earth change around the sun?
Systems response: because the earth is the planet of the sun.
And
Is what reason user's sentence: The Earth Revolves round the Sun?
Systems response: because the earth is the planet of the sun.
But the sentence structure of Chinese is very flexible, and word is flexible and changeable, so by increasing the question and answer statement to solving the problems referred to above, no matter be from the workload or the angle of system effectiveness, all is unacceptable.
As fully visible, when the simple mode-matching technique of available technology adopting is realized Chinese auto answer, exist that to set up Chinese question and answer statement library workload huge, and the narrow problem of coverage rate.
Summary of the invention
The invention provides a kind of Chinese auto-answer method and system, when realizing Chinese auto answer, set up the problem that workload is huge and coverage rate is narrow of Chinese question and answer statement library in order to solve the available technology adopting mode-matching technique.
Technical solution of the present invention comprises:
A kind of Chinese auto-answer method comprises step:
A, the classification of determining the Chinese statement that the user imports and keyword sequence are searched from the question and answer statement library and the identical keyword sequence of user's read statement classification;
B, the keyword sequence and the described keyword sequence that finds of user's read statement mated, the answer statement of the keyword sequence correspondence that wherein the match is successful is returned to the user.
Preferable, determine that the classification of user's read statement and the concrete steps of keyword sequence are:
User's read statement is carried out Chinese word segmentation handle, obtain word sequence;
Determine the classification of user's read statement according to the sentence category feature speech that comprises in the described word sequence, sentence category feature speech and stop words deleted that the keyword sequence of user's read statement classified as in remaining word order from described word sequence.
Preferable, among the described step B,, then return default answer statement to the user if coupling is unsuccessful.
Preferable, described step B specifically comprises step:
First keyword in the keyword sequence of B1, extraction user read statement all adds to the described keyword sequence that finds in the results set as the coupling foundation;
B2, will mate respectively, will wherein mate unsuccessful keyword sequence and from results set, reject as the content of the relevant position of each keyword sequence in coupling keyword of foundation and the results set;
B3, judge whether remaining keyword sequence is arranged in the described results set, if, execution in step B4, otherwise, select a corresponding default answer statement of the classification with user's read statement to return to the user at random;
B4, judge in the keyword sequence of user's read statement whether have next keyword,, it as the coupling foundation, is returned step B2 if exist, otherwise, the answer statement of the keyword sequence correspondence in the current results set is returned to the user.
Preferable, among the described step B2, according to the position of keyword in the keyword sequence of user's read statement as the coupling foundation, each keyword sequence is in the content of this position in the lookup result set, if the content of this position is any speech asterisk wildcard or with identical as the keyword of coupling foundation, then this match is successful.
Preferable, it is right that described question and answer statement library is used to store defined question and answer statement, and described question and answer statement constitutes keyword sequence, classification and the corresponding answer statement by the problem statement of keeper's input.
Preferable, the question and answer statement that utilizes the keeper to import to the process of upgrading the question and answer statement library is:
Determine the classification and the keyword sequence of the problem statement of described question and answer statement centering;
Search and whether exist in the question and answer statement library and the identical keyword sequence of described problem statement classification, if exist, then the answer statement with described question and answer statement centering adds in the question and answer statement library, related preservation with the keyword sequence that finds, otherwise, with keyword sequence, the classification of described problem statement and the answer statement of question and answer statement centering is related is saved in the question and answer statement library.
Preferable, determine that the classification of problem statement of described question and answer statement centering and the detailed process of keyword sequence are:
Problem statement to keeper's input carries out the Chinese word segmentation processing, obtains word sequence;
Determine the classification of described problem statement according to the sentence category feature speech that comprises in the described word sequence, sentence category feature speech and stop words deleted that the keyword sequence of described problem statement classified as in remaining word order from described word sequence.
Preferable, if include any speech asterisk wildcard in the problem statement of keeper's input, then include any speech asterisk wildcard in the keyword sequence of this problem statement.
A kind of Chinese automatic answering system comprises:
User's statement analysis module is used for determining the classification and the keyword sequence of the Chinese statement of user's input;
Enquiry module, be used for searching and the identical keyword sequence of user's read statement classification from the question and answer statement library, the keyword sequence and the described keyword sequence that finds of user's read statement are mated, the answer statement of the keyword sequence correspondence that wherein the match is successful is returned to the user.
Preferable, described user's statement analysis module specifically comprises:
First participle submodule is used for that user's read statement is carried out Chinese word segmentation and handles, and obtains word sequence;
The first sentence category analysis (sca) submodule, the classification of user's read statement determined in the sentence category feature speech that is used for comprising according to described word sequence, and sentence category feature speech and stop words are deleted from described word sequence, obtains the keyword sequence of user's read statement.
Preferable, described enquiry module specifically comprises:
The matching treatment submodule, be used for searching and the identical keyword sequence of user's read statement classification from the question and answer statement library, the keyword sequence and the described keyword sequence that finds of user's read statement are mated, if the match is successful, then the answer statement of the keyword sequence correspondence that the match is successful is sent to the result and feed back submodule, otherwise, select a corresponding default answer statement of the classification with user's read statement to send to the result at random and feed back submodule;
The result feeds back submodule, is used for the answer statement that the matching treatment submodule sends is returned to the user.
Preferable, also comprise:
Keeper's statement analysis module is used for determining the classification and the keyword sequence of problem statement of the question and answer statement centering of keeper's input;
Update module, whether be used for searching the question and answer statement library exists and the identical keyword sequence of described problem statement classification, if exist, then the answer statement with this question and answer statement centering adds in the question and answer statement library, related preservation with the keyword sequence that finds, otherwise, be saved in question and answer statement library related of keyword sequence, classification of described problem statement with the answer statement of answer statement centering.
Preferable, described keeper's statement analysis module specifically comprises:
The second participle submodule is used for the problem statement of keeper's input is carried out the Chinese word segmentation processing, obtains word sequence;
The second sentence category analysis (sca) submodule, the classification of the problem statement that the keeper imports determined in the sentence category feature speech that is used for comprising according to described word sequence, and sentence category feature speech and stop words deleted from described word sequence, obtain the keyword sequence of the problem statement of keeper's input.
Beneficial effect of the present invention is as follows:
When technical solution of the present invention is carried out the auto answer processing at the Chinese problem statement to user's input, the classification and the keyword sequence of the Chinese problem statement by determining user input, in the question and answer statement library, search the keyword sequence of the problem statement identical then with user's read statement classification, the keyword sequence and the described keyword sequence that finds of user's read statement are mated, the answer statement of the keyword sequence correspondence that wherein the match is successful is returned to the user, thereby eliminated not matching between the problem statement of the user input that causes flexibly owing to Chinese sentence structure and the problem statement in the question and answer statement library, improved the content coverage rate of question and answer statement libraries, reduce the workload of building the storehouse, improved the accuracy rate and the recall rate of Chinese automatic answering system simultaneously significantly.
Description of drawings
Fig. 1 is the process flow diagram of the embodiment of the present invention's Chinese auto-answer method;
The process flow diagram of Fig. 2 among the present invention the content of storing in the question and answer statement library being upgraded;
Fig. 3 is the structured flowchart of the present invention's Chinese automatic answering system.
Embodiment
The main design concept of technical solution of the present invention is when adopting mode-matching technique to realize Chinese auto answer at existing Chinese automatic answering system, set up the problem that workload is huge and coverage rate is narrow of Chinese question and answer statement library, and a kind of workload that can reduce to set up Chinese question and answer statement library is proposed, and significantly improve the solution of the content coverage rate of question and answer statement library, this scheme is at first determined the classification and the keyword sequence of the Chinese statement of user's input, in the question and answer statement library, search the keyword sequence of the problem statement identical then with user's read statement classification, the keyword sequence and the described keyword sequence that finds of user's read statement are mated, the answer statement of the keyword sequence correspondence that wherein the match is successful is returned to the user.Thereby eliminated not matching between the problem statement of the user input that causes flexibly owing to Chinese sentence structure and the problem statement in the question and answer statement library, improved the content coverage rate of question and answer statement libraries, reduce the workload of building the storehouse, improved the accuracy rate and the recall rate of Chinese automatic answering system simultaneously significantly.
Below in conjunction with each accompanying drawing the specific implementation process of technical solution of the present invention is carried out further detailed elaboration.
See also Fig. 1, this figure is the process flow diagram of the embodiment of the present invention's Chinese auto-answer method, and its main implementation procedure is:
Step S10, user import Chinese problem statement to automatic answering system.
Step S11, the default dictionary of automatic answering system utilization carries out word segmentation processing to the Chinese problem statement that the user imports, and obtains word sequence.
Illustrate automatic answering system below the Chinese problem statement of user input carried out the detailed process that Chinese word segmentation is handled:
1) the Chinese problem statement to user's input carries out the atom cutting, wherein each atom is labeled as a cutting unit, described atom is the least unit of participle, and a typical Chinese character is exactly an atom, and a continuous half-angle character string also is an atom;
2) atomic series among the segmenting word figure is traveled through,, search the speech that in dictionary, occurred that comprises in this atomic series, it is labeled as the cutting unit according to the vocabulary that comprises in the described default dictionary;
3) determine the participle path of the probability maximum of this problem statement according to the annotation results of cutting unit, obtain corresponding word sequence.
Step S12, automatic answering system are determined the classification of the Chinese problem statement of user's input according to the sentence category feature speech that comprises in the described word sequence, sentence category feature speech and stop words are deleted from described word sequence, and the keyword sequence of the Chinese problem statement of user's input classified as in remaining word order.
Wherein, described sentence category feature speech is the mark words of sentence classification, can judge the classification of the Chinese problem statement of user's input according to predefined sentence category feature speech; Described stop words is the very little speech of sentence justice contribution to sentence.
Step S13, automatic answering system are searched the identical keyword sequence of Chinese problem statement classification with user's input from the question and answer statement library.
It is right that described question and answer statement library is used to store defined question and answer statement, and described question and answer statement constitutes keyword sequence, classification and the corresponding answer statement by the problem statement of keeper input.
Step S14, automatic answering system with first keyword in the keyword sequence of the problem statement of user's input as the coupling foundation, with the keyword sequence that finds among the above-mentioned steps S13 as results set.
Step S15, automatic answering system will mate respectively as the content of the relevant position of each keyword sequence in keyword that mates foundation and the results set, will wherein mate unsuccessful keyword sequence and reject from results set.
The detailed process that automatic answering system carries out matching treatment is as follows:
According to the position of keyword in the keyword sequence of user's read statement as the coupling foundation, each keyword sequence is in the content of this position in the lookup result set, if the content of this position is any speech asterisk wildcard or with identical as the keyword of coupling foundation, then this match is successful.
Step S16, automatic answering system judge whether remaining keyword sequence is arranged in the described results set, if, execution in step S18, otherwise, execution in step S17.
Step S17, select a corresponding default answer statement of the classification with user's read statement at random, and return to the user, flow process finishes.
Step S18, automatic answering system judge in the keyword sequence of user's read statement whether have next keyword, if exist, and execution in step S19, otherwise, execution in step S20.
Step S19, with the next keyword in the keyword sequence of user's read statement as the coupling foundation, return step S15.
Step S20, automatic answering system return to the user with the answer statement of the keyword sequence correspondence in the results set, and flow process finishes.
Among the present invention, it is right that the question and answer statement library is used to store defined question and answer statement, and described question and answer statement constitutes keyword sequence, classification and the corresponding answer statement by the problem statement of keeper input.See also Fig. 2, this figure is the process flow diagram that among the present invention the content of storing in the question and answer statement library is upgraded, and its main implementation procedure is:
Step S30, that the keeper imports Chinese question and answer statement to automatic answering system is right.
Step S31, the default dictionary of automatic answering system utilization carry out the Chinese word segmentation processing to the problem statement of the question and answer statement centering of keeper's input, obtain word sequence.
Step S32, automatic answering system are determined the classification of the problem statement that the keeper imports according to the sentence category feature speech that comprises in the described word sequence, sentence category feature speech and stop words are deleted from word sequence, and the keyword sequence of the problem statement of keeper's input classified as in remaining word order.
If include any speech asterisk wildcard in the problem statement of keeper's input, then include any speech asterisk wildcard in the keyword sequence of this problem statement.
Step S33, automatic answering system are judged the identical keyword sequence of problem statement classification that whether exists in the question and answer statement library with keeper's input, if exist, and execution in step S34, otherwise, execution in step S35.
Step S34, automatic answering system add in the question and answer statement library answer statement of the question and answer statement centering of keeper's input to related preservation with the keyword sequence that finds.
Step S35, automatic answering system are with the keyword sequence of described problem statement, classification related being saved in the question and answer statement library of answer statement with keeper's input.
Corresponding to the above-mentioned Chinese auto-answer method of the present invention, the present invention and then proposed a kind of Chinese automatic answering system, see also Fig. 3, this figure is the structured flowchart of the present invention's Chinese automatic answering system, it mainly comprises user's statement analysis module 30 and enquiry module 40, and the main effect of wherein respectively forming module is as follows:
User's statement analysis module 30 is used for determining the classification and the keyword sequence of the Chinese problem statement of user's input;
Described user's statement analysis module 30 specifically comprises the first participle submodule 301 and the first sentence category analysis (sca) submodule 302, and wherein the main effect of each submodule is as follows:
First participle submodule 301 is used to utilize default dictionary that the Chinese problem statement of user's input is carried out the Chinese word segmentation processing, obtains word sequence, outputs it to the first sentence category analysis (sca) submodule 302;
The first sentence category analysis (sca) submodule 302, the classification of the Chinese problem statement that the user imports determined in the sentence category feature speech that is used for comprising according to described word sequence, and sentence category feature speech and stop words deleted from described word sequence, obtain the keyword sequence of the Chinese problem statement of user's input.
Described enquiry module 40 comprises that specifically matching treatment submodule 401 and result feed back submodule 402, and wherein the main effect of each submodule is as follows:
Described matching treatment submodule 401 is as follows with the keyword sequence of the Chinese problem statement of user input and concrete steps that the described keyword sequence that finds mates:
1) first keyword in the keyword sequence of the problem statement that the user is imported is as the coupling foundation, and the keyword sequence that described Chinese problem statement classification that find and user's input is identical is as results set;
2) will mate respectively as the content of the relevant position of each keyword sequence in keyword that mates foundation and the current results set, will wherein mate unsuccessful keyword sequence and from results set, reject;
3) judge whether remaining keyword sequence is arranged in the described results set, if, execution in step 4), otherwise, execution in step 6);
4) judge in the keyword sequence of problem statement of user input whether have next keyword,, it as the coupling foundation, returned step 2 if exist), otherwise, execution in step 5);
5) answer statement of the keyword sequence correspondence in the results set is sent to the result and feed back submodule 402;
6) select a corresponding default answer statement of the classification with user's read statement to send to the result at random and feed back submodule 402.
The result feeds back submodule 402, is used for the answer statement that the matching treatment submodule sends is returned to the user.
Among the present invention, the keeper is by upgrading the content of storing in to the question and answer statement library to Chinese automatic answering system input question and answer statement, so the present invention's Chinese automatic answering system also comprises:
Keeper's statement analysis module 50 is used for determining the classification and the keyword sequence of problem statement of the question and answer statement centering of keeper's input;
Described keeper's statement analysis module 50 specifically comprises the second participle submodule 501 and the second sentence category analysis (sca) submodule 502, and wherein the concrete effect of each submodule is as follows:
The second participle submodule 501 is used for the problem statement of keeper's input is carried out the Chinese word segmentation processing, obtains word sequence;
The second sentence category analysis (sca) submodule 502, the classification of the problem statement that the keeper imports determined in the sentence category feature speech that is used for comprising according to described word sequence, and sentence category feature speech and stop words deleted from described word sequence, obtain the keyword sequence of the problem statement of keeper's input.
As fully visible, when the present invention carries out the auto answer processing at the Chinese problem statement to user's input, the classification and the keyword sequence of the Chinese problem statement by determining user input, in the question and answer statement library, search the keyword sequence of the problem statement identical then with user's read statement classification, the keyword sequence and the described keyword sequence that finds of user's read statement are mated, the answer statement of the keyword sequence correspondence that wherein the match is successful is returned to the user, thereby eliminated not matching between the problem statement of the user input that causes flexibly owing to Chinese sentence structure and the problem statement in the question and answer statement library, improved the content coverage rate of question and answer statement libraries, reduce the workload of building the storehouse, improved the accuracy rate and the recall rate of Chinese automatic answering system simultaneously significantly.
Obviously, those skilled in the art can carry out various changes and modification to the present invention and not break away from the spirit and scope of the present invention.Like this, if of the present invention these are revised and modification belongs within the scope of claim of the present invention and equivalent technologies thereof, then the present invention also is intended to comprise these changes and modification interior.
Claims (14)
1. a Chinese auto-answer method is characterized in that, comprises step:
A, the classification of determining the Chinese statement that the user imports and keyword sequence are searched from the question and answer statement library and the identical keyword sequence of user's read statement classification;
B, the keyword sequence and the described keyword sequence that finds of user's read statement mated, the answer statement of the keyword sequence correspondence that wherein the match is successful is returned to the user.
2. the method for claim 1 is characterized in that, determines that the classification of user's read statement and the concrete steps of keyword sequence are:
User's read statement is carried out Chinese word segmentation handle, obtain word sequence;
Determine the classification of user's read statement according to the sentence category feature speech that comprises in the described word sequence, sentence category feature speech and stop words deleted that the keyword sequence of user's read statement classified as in remaining word order from described word sequence.
3. the method for claim 1 is characterized in that, among the described step B, if coupling is unsuccessful, then returns default answer statement to the user.
4. as claim 1 or 3 described methods, it is characterized in that described step B specifically comprises step:
First keyword in the keyword sequence of B1, extraction user read statement all adds to the described keyword sequence that finds in the results set as the coupling foundation;
B2, will mate respectively, will wherein mate unsuccessful keyword sequence and from results set, reject as the content of the relevant position of each keyword sequence in coupling keyword of foundation and the results set;
B3, judge whether remaining keyword sequence is arranged in the described results set, if, execution in step B4, otherwise, select a corresponding default answer statement of the classification with user's read statement to return to the user at random;
B4, judge in the keyword sequence of user's read statement whether have next keyword,, it as the coupling foundation, is returned step B2 if exist, otherwise, the answer statement of the keyword sequence correspondence in the current results set is returned to the user.
5. method as claimed in claim 4, it is characterized in that, among the described step B2, according to the position of keyword in the keyword sequence of user's read statement as the coupling foundation, each keyword sequence is in the content of this position in the lookup result set, if the content of this position is any speech asterisk wildcard or with identical as the keyword of coupling foundation, then this match is successful.
6. the method for claim 1 is characterized in that, it is right that described question and answer statement library is used to store defined question and answer statement, and described question and answer statement constitutes keyword sequence, classification and the corresponding answer statement by the problem statement of keeper input.
7. method as claimed in claim 6 is characterized in that, the question and answer statement that utilizes the keeper to import to the process of upgrading the question and answer statement library is:
Determine the classification and the keyword sequence of the problem statement of described question and answer statement centering;
Search and whether exist in the question and answer statement library and the identical keyword sequence of described problem statement classification, if exist, then the answer statement with described question and answer statement centering adds in the question and answer statement library, related preservation with the keyword sequence that finds, otherwise, with keyword sequence, the classification of described problem statement and the answer statement of question and answer statement centering is related is saved in the question and answer statement library.
8. method as claimed in claim 7 is characterized in that, determines that the classification of problem statement of described question and answer statement centering and the detailed process of keyword sequence are:
Problem statement to keeper's input carries out the Chinese word segmentation processing, obtains word sequence;
Determine the classification of described problem statement according to the sentence category feature speech that comprises in the described word sequence, sentence category feature speech and stop words deleted that the keyword sequence of described problem statement classified as in remaining word order from described word sequence.
9. method as claimed in claim 7 is characterized in that, if include any speech asterisk wildcard in the problem statement of keeper's input, then includes any speech asterisk wildcard in the keyword sequence of this problem statement.
10. a Chinese automatic answering system is characterized in that, comprising:
User's statement analysis module is used for determining the classification and the keyword sequence of the Chinese statement of user's input;
Enquiry module, be used for searching and the identical keyword sequence of user's read statement classification from the question and answer statement library, the keyword sequence and the described keyword sequence that finds of user's read statement are mated, the answer statement of the keyword sequence correspondence that wherein the match is successful is returned to the user.
11. system as claimed in claim 10 is characterized in that, described user's statement analysis module specifically comprises:
First participle submodule is used for that user's read statement is carried out Chinese word segmentation and handles, and obtains word sequence;
The first sentence category analysis (sca) submodule, the classification of user's read statement determined in the sentence category feature speech that is used for comprising according to described word sequence, and sentence category feature speech and stop words are deleted from described word sequence, obtains the keyword sequence of user's read statement.
12. system as claimed in claim 10 is characterized in that, described enquiry module specifically comprises:
The matching treatment submodule, be used for searching and the identical keyword sequence of user's read statement classification from the question and answer statement library, the keyword sequence and the described keyword sequence that finds of user's read statement are mated, if the match is successful, then the answer statement of the keyword sequence correspondence that the match is successful is sent to the result and feed back submodule, otherwise, select a corresponding default answer statement of the classification with user's read statement to send to the result at random and feed back submodule;
The result feeds back submodule, is used for the answer statement that the matching treatment submodule sends is returned to the user.
13. as claim 10 or 11 described systems, it is characterized in that, also comprise:
Keeper's statement analysis module is used for determining the classification and the keyword sequence of problem statement of the question and answer statement centering of keeper's input;
Update module, whether be used for searching the question and answer statement library exists and the identical keyword sequence of described problem statement classification, if exist, then the answer statement with this question and answer statement centering adds in the question and answer statement library, related preservation with the keyword sequence that finds, otherwise, be saved in question and answer statement library related of keyword sequence, classification of described problem statement with the answer statement of answer statement centering.
14. system as claimed in claim 13 is characterized in that, described keeper's statement analysis module specifically comprises:
The second participle submodule is used for the problem statement of keeper's input is carried out the Chinese word segmentation processing, obtains word sequence;
The second sentence category analysis (sca) submodule, the classification of the problem statement that the keeper imports determined in the sentence category feature speech that is used for comprising according to described word sequence, and sentence category feature speech and stop words deleted from described word sequence, obtain the keyword sequence of the problem statement of keeper's input.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2006101459852A CN100565515C (en) | 2006-11-30 | 2006-11-30 | A kind of Chinese auto-answer method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2006101459852A CN100565515C (en) | 2006-11-30 | 2006-11-30 | A kind of Chinese auto-answer method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101178711A true CN101178711A (en) | 2008-05-14 |
| CN100565515C CN100565515C (en) | 2009-12-02 |
Family
ID=39404969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2006101459852A Active CN100565515C (en) | 2006-11-30 | 2006-11-30 | A kind of Chinese auto-answer method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100565515C (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794304A (en) * | 2010-02-10 | 2010-08-04 | 深圳先进技术研究院 | Industry information service system and method |
| CN102289431A (en) * | 2011-06-24 | 2011-12-21 | 华南理工大学 | Method for providing short message reply options based on natural language understanding |
| CN102546456A (en) * | 2010-12-22 | 2012-07-04 | 北大方正集团有限公司 | Information feedback method and device |
| CN102831207A (en) * | 2012-08-06 | 2012-12-19 | 北京小米科技有限责任公司 | Computer terminal and information interaction method |
| CN103079008A (en) * | 2013-01-07 | 2013-05-01 | 北京播思软件技术有限公司 | Method and system for automatically generating replying suggestion according to content of short message |
| CN103186616A (en) * | 2011-12-30 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Vehicle-mounted information-processing system, cloud service center and vehicle-mounted equipment |
| CN103297389A (en) * | 2012-02-24 | 2013-09-11 | 腾讯科技（深圳）有限公司 | Man-machine conversation method and device |
| WO2014187076A1 (en) * | 2013-05-23 | 2014-11-27 | 华为技术有限公司 | Natural language generating method and system |
| CN104516921A (en) * | 2013-09-30 | 2015-04-15 | 华为技术有限公司 | Automatic reply method and device |
| CN104679815A (en) * | 2014-12-08 | 2015-06-03 | 北京云知声信息技术有限公司 | Method and system for screening question and answer pairs and updating question and answer database in real time |
| CN104699708A (en) * | 2013-12-09 | 2015-06-10 | 中国移动通信集团北京有限公司 | Self-learning method and device for customer service robot |
| CN104834704A (en) * | 2015-04-29 | 2015-08-12 | 深圳市梦网科技股份有限公司 | Response method and response system |
| CN105279274A (en) * | 2015-10-30 | 2016-01-27 | 北京京东尚科信息技术有限公司 | Answer combining and matching method and system based on natural synthetic answer system |
| CN105574128A (en) * | 2015-12-12 | 2016-05-11 | 天津南大通用数据技术股份有限公司 | Method for finishing complex data operations in business intelligence system |
| CN105630917A (en) * | 2015-12-22 | 2016-06-01 | 成都小多科技有限公司 | Intelligent answering method and intelligent answering device |
| CN106021463A (en) * | 2016-05-17 | 2016-10-12 | 北京百度网讯科技有限公司 | Method for providing intelligent services on basis of artificial intelligence, intelligent service system and intelligent terminal |
| CN106055628A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | Intelligent communication method, device, system and application in the direction of automobile maintenance |
| CN106056220A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | Intelligent communication platform for car maintenance |
| CN106202270A (en) * | 2016-06-28 | 2016-12-07 | 广州幽联信息技术有限公司 | Interactive method based on natural language and device |
| CN106487660A (en) * | 2016-11-04 | 2017-03-08 | 广东亿迅科技有限公司 | A kind of method for being managed collectively multiple info-channels and its system |
| CN106503918A (en) * | 2016-11-07 | 2017-03-15 | 新乡学院 | A kind of Property Management System based on Automated library system |
| CN107393538A (en) * | 2017-07-26 | 2017-11-24 | 上海与德通讯技术有限公司 | Robot interactive method and system |
| CN108491378A (en) * | 2018-03-08 | 2018-09-04 | 国网福建省电力有限公司 | Power information O＆M intelligent response system |
| CN109002540A (en) * | 2018-07-23 | 2018-12-14 | 电子科技大学 | It is a kind of Chinese notice document problem answers to automatic generation method |
| CN110059171A (en) * | 2019-04-12 | 2019-07-26 | 中国工商银行股份有限公司 | Intelligent answer performance improvement method and system |
| CN110069614A (en) * | 2019-04-28 | 2019-07-30 | 北京车薄荷科技有限公司 | A kind of question and answer exchange method and device |
| CN110807321A (en) * | 2018-07-20 | 2020-02-18 | 北京搜狗科技发展有限公司 | Word combination method and device, electronic equipment and readable storage medium |
| CN113297362A (en) * | 2021-05-27 | 2021-08-24 | 平安科技（深圳）有限公司 | Robot question and answer method and device, computer equipment and storage medium |
| CN113392335A (en) * | 2021-06-30 | 2021-09-14 | 深圳本地宝新媒体技术有限公司 | Method and device for message reply through social platform public number interface |
| CN114168722A (en) * | 2021-11-23 | 2022-03-11 | 安徽经邦软件技术有限公司 | Financial question-answering robot based on artificial intelligence technology |
| CN114416957A (en) * | 2022-01-27 | 2022-04-29 | 建信金融科技有限责任公司 | A method and system for intelligent question answering of financial management data |
-
2006
- 2006-11-30 CN CNB2006101459852A patent/CN100565515C/en active Active
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794304A (en) * | 2010-02-10 | 2010-08-04 | 深圳先进技术研究院 | Industry information service system and method |
| CN101794304B (en) * | 2010-02-10 | 2016-05-25 | 深圳先进技术研究院 | Industry information service system and method |
| CN102546456A (en) * | 2010-12-22 | 2012-07-04 | 北大方正集团有限公司 | Information feedback method and device |
| CN102546456B (en) * | 2010-12-22 | 2015-04-08 | 北大方正集团有限公司 | A kind of information feedback method and information feedback device |
| CN102289431A (en) * | 2011-06-24 | 2011-12-21 | 华南理工大学 | Method for providing short message reply options based on natural language understanding |
| CN103186616A (en) * | 2011-12-30 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Vehicle-mounted information-processing system, cloud service center and vehicle-mounted equipment |
| CN103297389B (en) * | 2012-02-24 | 2018-09-07 | 腾讯科技（深圳）有限公司 | Interactive method and device |
| CN103297389A (en) * | 2012-02-24 | 2013-09-11 | 腾讯科技（深圳）有限公司 | Man-machine conversation method and device |
| CN102831207A (en) * | 2012-08-06 | 2012-12-19 | 北京小米科技有限责任公司 | Computer terminal and information interaction method |
| CN102831207B (en) * | 2012-08-06 | 2015-01-28 | 小米科技有限责任公司 | Computer terminal and information interaction method |
| CN103079008A (en) * | 2013-01-07 | 2013-05-01 | 北京播思软件技术有限公司 | Method and system for automatically generating replying suggestion according to content of short message |
| WO2014187076A1 (en) * | 2013-05-23 | 2014-11-27 | 华为技术有限公司 | Natural language generating method and system |
| CN104516921A (en) * | 2013-09-30 | 2015-04-15 | 华为技术有限公司 | Automatic reply method and device |
| CN104516921B (en) * | 2013-09-30 | 2018-02-06 | 华为技术有限公司 | Automatic reply method and device |
| CN104699708A (en) * | 2013-12-09 | 2015-06-10 | 中国移动通信集团北京有限公司 | Self-learning method and device for customer service robot |
| CN104699708B (en) * | 2013-12-09 | 2018-01-30 | 中国移动通信集团北京有限公司 | A kind of self-learning method and device of customer service robot |
| CN104679815A (en) * | 2014-12-08 | 2015-06-03 | 北京云知声信息技术有限公司 | Method and system for screening question and answer pairs and updating question and answer database in real time |
| CN104679815B (en) * | 2014-12-08 | 2018-02-23 | 北京云知声信息技术有限公司 | It is a kind of to screen question and answer pair and the method and system in real-time update question and answer storehouse |
| CN104834704A (en) * | 2015-04-29 | 2015-08-12 | 深圳市梦网科技股份有限公司 | Response method and response system |
| CN105279274A (en) * | 2015-10-30 | 2016-01-27 | 北京京东尚科信息技术有限公司 | Answer combining and matching method and system based on natural synthetic answer system |
| CN105279274B (en) * | 2015-10-30 | 2018-11-02 | 北京京东尚科信息技术有限公司 | Answer synthesis based on naturally semantic question answering system and matched method and system |
| CN105574128A (en) * | 2015-12-12 | 2016-05-11 | 天津南大通用数据技术股份有限公司 | Method for finishing complex data operations in business intelligence system |
| CN105630917A (en) * | 2015-12-22 | 2016-06-01 | 成都小多科技有限公司 | Intelligent answering method and intelligent answering device |
| US11651002B2 (en) | 2016-05-17 | 2023-05-16 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method for providing intelligent service, intelligent service system and intelligent terminal based on artificial intelligence |
| CN106021463B (en) * | 2016-05-17 | 2019-07-09 | 北京百度网讯科技有限公司 | Method, intelligent service system and the intelligent terminal of intelligent Service are provided based on artificial intelligence |
| CN106021463A (en) * | 2016-05-17 | 2016-10-12 | 北京百度网讯科技有限公司 | Method for providing intelligent services on basis of artificial intelligence, intelligent service system and intelligent terminal |
| CN106056220A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | Intelligent communication platform for car maintenance |
| CN106055628A (en) * | 2016-05-27 | 2016-10-26 | 大连楼兰科技股份有限公司 | Intelligent communication method, device, system and application in the direction of automobile maintenance |
| CN106202270A (en) * | 2016-06-28 | 2016-12-07 | 广州幽联信息技术有限公司 | Interactive method based on natural language and device |
| CN106487660A (en) * | 2016-11-04 | 2017-03-08 | 广东亿迅科技有限公司 | A kind of method for being managed collectively multiple info-channels and its system |
| CN106503918A (en) * | 2016-11-07 | 2017-03-15 | 新乡学院 | A kind of Property Management System based on Automated library system |
| CN107393538A (en) * | 2017-07-26 | 2017-11-24 | 上海与德通讯技术有限公司 | Robot interactive method and system |
| CN108491378A (en) * | 2018-03-08 | 2018-09-04 | 国网福建省电力有限公司 | Power information O＆M intelligent response system |
| CN108491378B (en) * | 2018-03-08 | 2021-11-09 | 国网福建省电力有限公司 | Intelligent response system for operation and maintenance of electric power information |
| CN110807321A (en) * | 2018-07-20 | 2020-02-18 | 北京搜狗科技发展有限公司 | Word combination method and device, electronic equipment and readable storage medium |
| CN110807321B (en) * | 2018-07-20 | 2024-11-12 | 北京搜狗科技发展有限公司 | A word combination method, device, electronic device and readable storage medium |
| CN109002540A (en) * | 2018-07-23 | 2018-12-14 | 电子科技大学 | It is a kind of Chinese notice document problem answers to automatic generation method |
| CN109002540B (en) * | 2018-07-23 | 2021-03-16 | 电子科技大学 | Method for automatically generating Chinese announcement document question answer pairs |
| CN110059171A (en) * | 2019-04-12 | 2019-07-26 | 中国工商银行股份有限公司 | Intelligent answer performance improvement method and system |
| CN110059171B (en) * | 2019-04-12 | 2021-01-01 | 中国工商银行股份有限公司 | Intelligent question and answer performance improving method and system |
| CN110069614A (en) * | 2019-04-28 | 2019-07-30 | 北京车薄荷科技有限公司 | A kind of question and answer exchange method and device |
| CN113297362A (en) * | 2021-05-27 | 2021-08-24 | 平安科技（深圳）有限公司 | Robot question and answer method and device, computer equipment and storage medium |
| CN113392335A (en) * | 2021-06-30 | 2021-09-14 | 深圳本地宝新媒体技术有限公司 | Method and device for message reply through social platform public number interface |
| CN114168722A (en) * | 2021-11-23 | 2022-03-11 | 安徽经邦软件技术有限公司 | Financial question-answering robot based on artificial intelligence technology |
| CN114416957A (en) * | 2022-01-27 | 2022-04-29 | 建信金融科技有限责任公司 | A method and system for intelligent question answering of financial management data |
| CN114416957B (en) * | 2022-01-27 | 2024-12-24 | 建信金融科技有限责任公司 | A method and system for intelligent question answering of financial management data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100565515C (en) | 2009-12-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101178711A (en) | Chinese auto-answer method and system | |
| CN101097573B (en) | Automatically request-answering system and method | |
| CN110647614B (en) | Intelligent question-answering method, device, medium and electronic equipment | |
| US8280902B2 (en) | High precision search system and method | |
| EP2024880B1 (en) | Demographic based classification for local word wheeling/web search | |
| CN101819578B (en) | Retrieval method, method and device for establishing index and retrieval system | |
| CN100578539C (en) | Automatic Question Answering Method and System | |
| CN109933708A (en) | Information retrieval method, device, storage medium and computer equipment | |
| CN109344230B (en) | Code library file generation, code search, coupling, optimization and migration method | |
| CN101334774A (en) | Character input method and input method system | |
| CN107861753B (en) | APP generation index, retrieval method and system and readable storage medium | |
| CN103218447B (en) | A kind of association-feeding method and device | |
| CN109522397B (en) | Information processing method and device | |
| CN102339294A (en) | Searching method and system for preprocessing keywords | |
| CN107832035B (en) | Voice input method of intelligent terminal | |
| CN119917524B (en) | NL2SQL method, device, equipment and medium based on preset industry big model | |
| CN102646124A (en) | Method for automatically identifying address information | |
| CN112417875B (en) | Configuration information updating method and device, computer equipment and medium | |
| CN101546226A (en) | English input method and system | |
| CN101470701A (en) | Text analyzer supporting semantic rule based on finite state machine and method thereof | |
| CN103020311B (en) | A kind of processing method of user search word and system | |
| CN115237805A (en) | Test case data preparation method and device | |
| CN111930911B (en) | Rapid field question-answering method and device thereof | |
| CN112861532B (en) | Address standardization processing method, device, equipment and online search system | |
| CN103544167A (en) | Backward word segmentation method and device based on Chinese retrieval |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20160111 Address after: The South Road in Guangdong province Shenzhen city Fiyta building 518057 floor 5-10 Nanshan District high tech Zone Patentee after: Shenzhen Tencent Computer System Co., Ltd. Address before: 2, 518044, East 410 room, SEG science and Technology Park, Zhenxing Road, Shenzhen, Guangdong, Futian District Patentee before: Tencent Technology (Shenzhen) Co., Ltd. |