CN110059171A - Intelligent answer performance improvement method and system - Google Patents
Intelligent answer performance improvement method and system Download PDFInfo
- Publication number
- CN110059171A CN110059171A CN201910293623.5A CN201910293623A CN110059171A CN 110059171 A CN110059171 A CN 110059171A CN 201910293623 A CN201910293623 A CN 201910293623A CN 110059171 A CN110059171 A CN 110059171A
- Authority
- CN
- China
- Prior art keywords
- keyword
- answer
- question
- processed
- evaluation
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Abstract
The present invention provides a kind of intelligent answer performance improvement method and system.The intelligent answer performance improvement method includes: to evaluate keyword according to user's evaluation information extraction according to user's question and answer information extraction question and answer keyword；The sum of quantity by question and answer keyword and evaluation keyword and the quantity of identical question and answer keyword and evaluation keyword are subtracted each other, and final keyword quantity is obtained；Judge whether each question and answer keyword is question and answer keyword to be processed according to preset keyword parameter table, whether each evaluation keyword is evaluation keyword to be processed；Keyword ratio to be processed is calculated according to the quantity of final keyword quantity, the quantity of question and answer keyword to be processed and evaluation keyword to be processed；When keyword ratio to be processed is greater than preset ratio, by question and answer keyword to be processed and its corresponding user's question and answer information, evaluation keyword to be processed and its corresponding user's evaluation information update to question and answer knowledge data base, to guarantee the real-time update of knowledge base, intelligent answer accuracy rate is promoted.
Description
Technical field
The present invention relates to intelligent interaction question and answer, and in particular, to a kind of intelligent answer performance improvement method and system.
Background technique
With the fast development of internet and mobile Internet, either Internet company or each traditional industries all passes through
Backstage knowledge base provides intelligent interaction question answering system for user, can accomplish effective combing of knowledge, and processing problem is high-efficient.Such as
What ensures timely updating for knowledge base in intelligent Answer System, meets the different business demand of user comprehensively, promotes intelligent answer
Accuracy rate be an important problem to be solved.Existing knowledge library updates mainly by the daily Accumulation Mechanism of knowledge, this
Mode fails to utilize and update the stronger customer data of specific aim in time.
Summary of the invention
The main purpose of the embodiment of the present invention is to provide a kind of intelligent answer performance improvement method and system, to guarantee to know
The real-time update for knowing library, promotes the accuracy rate of intelligent answer, advanced optimizes user experience.
To achieve the goals above, the embodiment of the present invention provides a kind of intelligent answer performance improvement method, comprising:
Receive user's question and answer information and the corresponding user's evaluation information of user's question and answer information；
According to user's question and answer information extraction question and answer keyword, keyword is evaluated according to user's evaluation information extraction；
It counts question and answer keyword and evaluates the sum of the quantity of keyword；
It counts identical question and answer keyword and evaluates the quantity of keyword；
The number of the sum of quantity by question and answer keyword and evaluation keyword and identical question and answer keyword and evaluation keyword
Amount is subtracted each other, and final keyword quantity is obtained；
Successively judge whether each question and answer keyword is question and answer keyword to be processed, root according to preset keyword parameter table
Successively judge whether each evaluation keyword is evaluation keyword to be processed according to preset keyword parameter table；
The quantity of question and answer keyword to be processed and the quantity of evaluation keyword to be processed are counted respectively；
According to final keyword quantity, the quantity of the quantity of question and answer keyword to be processed and evaluation keyword to be processed, meter
Calculate keyword ratio to be processed；
Judge whether keyword ratio to be processed is greater than preset ratio；
When keyword ratio to be processed is greater than preset ratio, by question and answer keyword to be processed, question and answer keyword to be processed
Corresponding user's question and answer information, evaluation keyword to be processed and the corresponding user's evaluation information update of evaluation keyword to be processed are extremely
Question and answer knowledge data base.
The embodiment of the present invention also provides a kind of intelligent answer performance boost system, comprising:
Receiving unit, for receiving user's question and answer information and the corresponding user's evaluation information of user's question and answer information；
Keyword extraction unit, for being mentioned according to user's evaluation information according to user's question and answer information extraction question and answer keyword
Take evaluation keyword；
First statistic unit, for counting question and answer keyword and evaluating the sum of the quantity of keyword；
Second statistic unit, for counting identical question and answer keyword and evaluating the quantity of keyword；
Final key element, for the sum of quantity of question and answer keyword and evaluation keyword and identical question and answer is crucial
The quantity of word and evaluation keyword is subtracted each other, and final keyword quantity is obtained；
First judging unit, for according to preset keyword parameter table successively judge each question and answer keyword whether be to
Question and answer keyword is handled, successively judges whether each evaluation keyword is that evaluation to be processed is closed according to preset keyword parameter table
Key word；
Third statistic unit, for counting the quantity of question and answer keyword to be processed and the number of evaluation keyword to be processed respectively
Amount；
Computing unit, for being closed according to the quantity of final keyword quantity, question and answer keyword to be processed and evaluation to be processed
The quantity of key word calculates keyword ratio to be processed；
Second judgment unit, for judging whether keyword ratio to be processed is greater than preset ratio；
First updating unit, for when keyword ratio to be processed be greater than preset ratio when, by question and answer keyword to be processed,
The corresponding user's question and answer information of question and answer keyword to be processed, evaluation keyword to be processed and the corresponding use of evaluation keyword to be processed
Family evaluation information is updated to question and answer knowledge data base.
The embodiment of the present invention also provides a kind of computer equipment, including memory, processor and storage are on a memory simultaneously
The computer program that can be run on a processor, processor perform the steps of when executing computer program
Receive user's question and answer information and the corresponding user's evaluation information of user's question and answer information；
According to user's question and answer information extraction question and answer keyword, keyword is evaluated according to user's evaluation information extraction；
It counts question and answer keyword and evaluates the sum of the quantity of keyword；
It counts identical question and answer keyword and evaluates the quantity of keyword；
The number of the sum of quantity by question and answer keyword and evaluation keyword and identical question and answer keyword and evaluation keyword
Amount is subtracted each other, and final keyword quantity is obtained；
Successively judge whether each question and answer keyword is question and answer keyword to be processed, root according to preset keyword parameter table
Successively judge whether each evaluation keyword is evaluation keyword to be processed according to preset keyword parameter table；
The quantity of question and answer keyword to be processed and the quantity of evaluation keyword to be processed are counted respectively；
According to final keyword quantity, the quantity of the quantity of question and answer keyword to be processed and evaluation keyword to be processed, meter
Calculate keyword ratio to be processed；
Judge whether keyword ratio to be processed is greater than preset ratio；
When keyword ratio to be processed is greater than preset ratio, by question and answer keyword to be processed, question and answer keyword to be processed
Corresponding user's question and answer information, evaluation keyword to be processed and the corresponding user's evaluation information update of evaluation keyword to be processed are extremely
Question and answer knowledge data base.
The embodiment of the present invention also provides a kind of computer readable storage medium, is stored thereon with computer program, computer
It is performed the steps of when program is executed by processor
Receive user's question and answer information and the corresponding user's evaluation information of user's question and answer information；
According to user's question and answer information extraction question and answer keyword, keyword is evaluated according to user's evaluation information extraction；
It counts question and answer keyword and evaluates the sum of the quantity of keyword；
It counts identical question and answer keyword and evaluates the quantity of keyword；
The number of the sum of quantity by question and answer keyword and evaluation keyword and identical question and answer keyword and evaluation keyword
Amount is subtracted each other, and final keyword quantity is obtained；
Successively judge whether each question and answer keyword is question and answer keyword to be processed, root according to preset keyword parameter table
Successively judge whether each evaluation keyword is evaluation keyword to be processed according to preset keyword parameter table；
The quantity of question and answer keyword to be processed and the quantity of evaluation keyword to be processed are counted respectively；
According to final keyword quantity, the quantity of the quantity of question and answer keyword to be processed and evaluation keyword to be processed, meter
Calculate keyword ratio to be processed；
Judge whether keyword ratio to be processed is greater than preset ratio；
When keyword ratio to be processed is greater than preset ratio, by question and answer keyword to be processed, question and answer keyword to be processed
Corresponding user's question and answer information, evaluation keyword to be processed and the corresponding user's evaluation information update of evaluation keyword to be processed are extremely
Question and answer knowledge data base.
The intelligent answer performance improvement method and system of the embodiment of the present invention are first closed according to user's question and answer information extraction question and answer
Key word evaluates keyword according to user's evaluation information extraction, successively judges each question and answer further according to preset keyword parameter table
Whether keyword is question and answer keyword to be processed, whether successively judges each evaluation keyword according to preset keyword parameter table
For evaluation keyword to be processed, then according to final keyword quantity, the quantity of question and answer keyword to be processed and evaluation to be processed
The quantity of keyword calculates keyword ratio to be processed, finally judges whether keyword ratio to be processed is greater than preset ratio；When
When keyword ratio to be processed is greater than preset ratio, by question and answer keyword to be processed, the corresponding user of question and answer keyword to be processed
Question and answer information, evaluation keyword to be processed and the corresponding user's evaluation information update of evaluation keyword to be processed are to question and answer knowledge number
According to library, it is ensured that the real-time update of knowledge base promotes the accuracy rate of intelligent answer, has timeliness and specific aim, further
Optimize user experience.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, embodiment will be described below
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without creative efforts, can also be attached according to these
Figure obtains other attached drawings.
Fig. 1 is the flow chart of intelligent answer performance improvement method in one embodiment of the invention；
Fig. 2 is the schematic diagram of message store table in one embodiment of the invention；
Fig. 3 is the flow chart of S106 in the embodiment of the present invention；
Fig. 4 is the schematic diagram of keyword parameter table in one embodiment of the invention；
Fig. 5 is the schematic diagram that information table is judged in one embodiment of the invention；
Fig. 6 is the schematic diagram of question and answer knowledge data table in one embodiment of the invention；
Fig. 7 is the schematic diagram of message store table in another embodiment of the present invention；
Fig. 8 is the schematic diagram of keyword parameter table in another embodiment of the present invention；
Fig. 9 is the schematic diagram that information table is judged in another embodiment of the present invention；
Figure 10 is the schematic diagram of updated question and answer knowledge data table in one embodiment of the invention；
Figure 11 is the structural block diagram of intelligent answer performance boost system in the embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Those skilled in the art will understand that embodiments of the present invention can be implemented as a kind of system, device, equipment,
Method or computer program product.Therefore, the present disclosure may be embodied in the following forms, it may be assumed that complete hardware, complete soft
The form that part (including firmware, resident software, microcode etc.) or hardware and software combine.
It updates mainly in view of current existing knowledge library through the daily Accumulation Mechanism of knowledge, cannot utilize in time and update and be directed to
The stronger customer data of property, the embodiment of the present invention provides a kind of intelligent answer performance improvement method and system, to guarantee knowledge base
Real-time update, promote the accuracy rate of intelligent answer, advanced optimize user experience.The present invention is carried out below in conjunction with attached drawing detailed
It describes in detail bright.
Fig. 1 is the flow chart of intelligent answer performance improvement method in one embodiment of the invention.As shown in Figure 1, intelligent answer
Performance improvement method includes:
S101: user's question and answer information and the corresponding user's evaluation information of user's question and answer information are received.
Wherein, the corresponding unique identification of user's question and answer information can also be received.
S102: according to user's question and answer information extraction question and answer keyword, keyword is evaluated according to user's evaluation information extraction.
Wherein it is possible to extract question and answer keyword and evaluation using the Chinese keyword extraction algorithms based on High Dimensional Clustering Analysis technology
Keyword.The question and answer keyword of extraction can for account, site, system, place of opening an account, bank of deposit, credit card, refund, amount,
Due date etc..
S103: statistics question and answer keyword and the sum of the quantity for evaluating keyword.
S104: counting identical question and answer keyword and evaluates the quantity of keyword.
S105: by the sum of quantity of question and answer keyword and evaluation keyword and identical question and answer keyword and evaluation keyword
Quantity subtract each other, obtain final keyword quantity.
S106: successively judge whether each question and answer keyword is that question and answer to be processed are crucial according to preset keyword parameter table
Word successively judges whether each evaluation keyword is evaluation keyword to be processed according to preset keyword parameter table.
S107: the quantity of question and answer keyword to be processed and the quantity of evaluation keyword to be processed are counted respectively.
S108: according to the number of final keyword quantity, the quantity of question and answer keyword to be processed and evaluation keyword to be processed
Amount, calculates keyword ratio to be processed.
S109: judge whether keyword ratio to be processed is greater than preset ratio.
S110: when keyword ratio to be processed is greater than preset ratio, question and answer keyword to be processed, question and answer to be processed are closed
The corresponding user's question and answer information of key word, evaluation keyword to be processed and the corresponding user's evaluation information of evaluation keyword to be processed are more
Newly to question and answer knowledge data base.
The executing subject of intelligent answer performance improvement method shown in FIG. 1 can be computer.Process as shown in Figure 1 can
Know, the intelligent answer performance improvement method of the embodiment of the present invention first according to user's question and answer information extraction question and answer keyword, according to
Family evaluation information extract evaluation keyword, further according to preset keyword parameter table successively judge each question and answer keyword whether be
Question and answer keyword to be processed successively judges whether each evaluation keyword is evaluation to be processed according to preset keyword parameter table
Keyword, then according to final keyword quantity, the quantity of the quantity of question and answer keyword to be processed and evaluation keyword to be processed
Keyword ratio to be processed is calculated, finally judges whether keyword ratio to be processed is greater than preset ratio；When keyword to be processed
When ratio is greater than preset ratio, by question and answer keyword to be processed, the corresponding user's question and answer information of question and answer keyword to be processed, wait locate
Reason evaluates keyword and the corresponding user's evaluation information update of evaluation keyword to be processed to question and answer knowledge data base, it is ensured that
The real-time update of knowledge base promotes the accuracy rate of intelligent answer, has timeliness and specific aim, has advanced optimized user's body
It tests.
Fig. 2 is the schematic diagram of message store table in one embodiment of the invention.As shown in Fig. 2, can be incited somebody to action after executing S102
The corresponding unique identification of user's question and answer information, question and answer information, question and answer keyword, user's evaluation information and evaluation keyword store to
In message store table.
Fig. 3 is the flow chart of S106 in the embodiment of the present invention.As shown in figure 3, S106 includes:
S201: successively judge each question and answer keyword whether in keyword parameter table.
S202: when question and answer keyword is not in keyword parameter table, which is question and answer keyword to be processed.
S203: successively judge each evaluation keyword whether in keyword parameter table.
S204: when evaluating keyword not in keyword parameter table, which is evaluation keyword to be processed.
When it is implemented, the question and answer keyword is question and answer to be processed when question and answer keyword is not in keyword parameter table
Keyword, crucial word state are to be processed；When question and answer keyword is in keyword parameter table, which is to have deposited
In question and answer keyword, crucial word state is existing.When evaluating keyword not in keyword parameter table, the evaluation is crucial
Word is evaluation keyword to be processed, and crucial word state is to be processed；When evaluating keyword in keyword parameter table, this is commented
Valence keyword is existing evaluation keyword, and crucial word state is existing.
Fig. 4 is the schematic diagram of keyword parameter table in one embodiment of the invention.As shown in figure 4, being wrapped in keyword parameter table
Include the date of formation of keyword (including question and answer keyword and evaluation keyword) and keyword.Keyword parameter table can be by business
Department carries out the initialization of data according to the scope of business.
After executing S106, further includes: by question and answer keyword to be processed and the equal real-time update of evaluation keyword to be processed
Into keyword parameter table.
Furthermore it is also possible to according to the corresponding unique identification of user's question and answer information, question and answer keyword, evaluation keyword, key
The generation of the corresponding user's question and answer information of word state, keyword or user's evaluation information, the date of formation of keyword and keyword
Source (shows that keyword is question and answer keyword or evaluation keyword), and record, which generates, judges information table.
Fig. 5 is the schematic diagram that information table is judged in one embodiment of the invention.As shown in figure 5, judging includes using in information table
The corresponding unique identification of family question and answer information, keyword (including question and answer keyword and evaluation keyword), (1 represents crucial word state
Crucial word state be it is existing, 2 to represent key word state be untreated), the corresponding user's question and answer information of keyword or user comment
(1 represents keyword represents keyword as question and answer keyword, 2 to the generating resource of valence information, the date of formation of keyword and keyword
To evaluate keyword).
In one embodiment, keyword ratio to be processed is calculated by following formula:
Wherein, s is keyword ratio to be processed, and a is the quantity of question and answer keyword to be processed, and b is that evaluation to be processed is crucial
The quantity of word, c are final keyword quantity, and d is default weight.
When it is implemented, evaluation keyword to be processed is the objective feedback of user, presets weight and be greater than 1.Of the invention real
3 can be set as default weight by applying in example.Default weight can carry out dynamic adjustment according to service operation situation.
Those skilled in the art can judge the solution for the problem of embodiment of the present invention proposes user by keyword ratio
Certainly effect, by keyword ratio from high to low will solve effect be divided into it is unresolved, it is preferable solve, be fully solved three
Grade.Specific division proportion can carry out dynamic adjustment according to service operation situation.For example, when keyword ratio is greater than or waits
When 0.8, it is unresolved for solving effect；When keyword ratio is greater than 0.5 and when less than 0.8, solving effect is preferably to solve；It closes
When key word ratio is less than or equal to 0.5, solving effect is to be fully solved.It, will when solving effect is unresolved or preferably solution
Question and answer keyword to be processed, the corresponding user's question and answer information of question and answer keyword to be processed, evaluation keyword to be processed and to be processed
Evaluate question and answer knowledge data table of the corresponding user's evaluation information update of keyword into question and answer knowledge data base.In this embodiment
Preset ratio be 0.5.
Fig. 6 is the schematic diagram of question and answer knowledge data table in one embodiment of the invention.As shown in fig. 6, question and answer knowledge data table
In include keyword (including question and answer keyword and evaluate keyword), problem (including the corresponding user of question and answer keyword to be processed
Question and answer information and the corresponding user's evaluation information of evaluation keyword to be processed), answer, the date of formation of keyword, problem state
(1 representative automatically updates the generating resource of (1 represents answer to be safeguarded, 2 representatives have supplemented answer) and problem, and 2 represent record by hand
Enter).Those skilled in the art can log in question and answer knowledge data base, check the problem of same day problem state is answer to be safeguarded, and
Timely update answer content in one column of answer, guarantees the real-time update of knowledge base, improves the accuracy rate of intelligent answer.It updates
After answer content, corresponding problem state is updated to supplement answer.
One of specific embodiment of the invention is as follows:
1, user enters intelligent Answer System consulting following problems:
User: I wants to inquire the affiliated site of account.
Intelligent Answer System: the problem of I does not understand you.
User: I wants that the account for inquiring me is opened an account place.
Intelligent Answer System: the problem of I does not understand you.
User: well, that goodbye be thanks.
Intelligent Answer System: goodbye is very glad for your service.
The evaluation feedback of user is as follows:
System can not identify account bank of deposit.
2, intelligent Answer System generates the corresponding unique identification of user's question and answer information according to above- mentioned information, and by user's question and answer
The corresponding unique identification of information, user's question and answer information and the corresponding user's evaluation information of user's question and answer information are sent to intelligent answer
Performance boost system.
3, intelligent answer performance boost system receives the corresponding unique identification of user's question and answer information, user's question and answer information and use
The corresponding user's evaluation information of family question and answer information.
The corresponding unique identification of user's question and answer information is as follows:
ac45k57e9l0120a。
User's question and answer information is as follows:
User: I wants to inquire the affiliated site of account.
User: I wants that the account for inquiring me is opened an account place.
User: well, that goodbye be thanks.
User's evaluation information is as follows:
System can not identify account bank of deposit.
4, intelligent answer performance boost system is as follows according to user's question and answer information extraction question and answer keyword:
Client: account site.
Client: account is opened an account place.
Intelligent answer performance boost system evaluates keyword according to user's evaluation information extraction, as follows:
System account bank of deposit.
5, intelligent answer performance boost system is crucial by the corresponding unique identification of user's question and answer information, question and answer information, question and answer
Word, user's evaluation information and evaluation keyword are stored into message store table.
Fig. 7 is the schematic diagram of message store table in another embodiment of the present invention.As shown in fig. 7, including: in message store table
1. the corresponding unique identification of user's question and answer information, as follows:
ac45k57e9l0120a；
2. question and answer information, as follows:
User: I wants to inquire the affiliated site of account.
Intelligent Answer System: the problem of I does not understand you.
User: I wants that the account for inquiring me is opened an account place.
Intelligent Answer System: the problem of I does not understand you.
User: well, that goodbye be thanks.
Intelligent Answer System: goodbye is very glad for your service.
3. question and answer keyword, as follows:
Client: account site.
Client: account is opened an account place.
4. user's evaluation information, as follows:
System can not identify account bank of deposit.
5. keyword is evaluated, as follows:
System bank of deposit.
6, the sum of the quantity of intelligent answer performance boost system statistics question and answer keyword and evaluation keyword, counts identical
The quantity of question and answer keyword and evaluation keyword closes the sum of quantity of question and answer keyword and evaluation keyword with identical question and answer
The quantity of key word and evaluation keyword is subtracted each other, and final keyword quantity is obtained.
In the present embodiment, different question and answer keywords includes account, site, place totally three keywords of opening an account, evaluation
Keyword includes system, account, bank of deposit totally three keywords.Wherein " account " had not only been question and answer keyword but also had been that evaluation is crucial
Word, then the quantity of identical question and answer keyword and evaluation keyword is 1.Therefore, the final keyword quantity in the present embodiment is 3
+ 3-1=5.
7, whether intelligent answer performance boost system successively judges each question and answer keyword in preset keyword parameter table
In, when question and answer keyword is not in keyword parameter table, which is question and answer keyword to be processed.Successively judgement is every
Whether a evaluation keyword is in preset keyword parameter table, and when evaluating keyword not in keyword parameter table, this is commented
Valence keyword is evaluation keyword to be processed.
Fig. 8 is the schematic diagram of keyword parameter table in another embodiment of the present invention.As shown in figure 8, preset keyword ginseng
Include: in number table
Keyword: account, site；
The date of formation of keyword: 2018-12-04.
After above-mentioned judgement is completed, by question and answer keyword to be processed and evaluation keyword real-time update to be processed to above-mentioned pass
In key word parameter list.
8, intelligent answer performance boost system is according to the corresponding unique identification of user's question and answer information, question and answer keyword, evaluation
Keyword, crucial word state, the corresponding user's question and answer information of keyword or user's evaluation information, the date of formation of keyword and pass
The generating resource (showing that keyword is question and answer keyword or evaluation keyword) of key word, record, which generates, judges information table.
Fig. 9 is the schematic diagram that information table is judged in another embodiment of the present invention.As shown in figure 9, judge include: in information table
The corresponding unique identification of user's question and answer information: ac45k57e9l0120a；
Keyword: account, site, place of opening an account, system and bank of deposit.
Crucial word state: the corresponding crucial word state of account and site is 1, and place of opening an account, system and bank of deposit are corresponding
Crucial word state is 2.
The corresponding user's question and answer information of keyword or user's evaluation information: the corresponding information of account and site is that " I wants to look into
Ask the affiliated site of account "；The corresponding information in place of opening an account is " I want that the account for inquiring me open an account place "；System and bank of deposit
Corresponding information is " system can not identify account bank of deposit ".
The date of formation of keyword: 2018-12-21.
The generating resource of keyword: account, site the generating resource corresponding with place of opening an account are 1, system and bank of deposit pair
The generating resource answered is 2.
9, intelligent answer performance boost system calculates keyword ratio to be processed by following formula:
Wherein, s is keyword ratio to be processed, and a is the quantity of question and answer keyword to be processed, and b is that evaluation to be processed is crucial
The quantity of word, c are final keyword quantity, and d is default weight.
In the present embodiment, presetting weight is 3, keyword ratio
10, intelligent answer performance boost system judges whether keyword ratio to be processed is greater than preset ratio: when to be processed
When keyword ratio is greater than preset ratio, question and answer keyword to be processed, the corresponding user's question and answer of question and answer keyword to be processed are believed
Breath, evaluation keyword to be processed and the corresponding user's evaluation information update of evaluation keyword to be processed to question and answer knowledge data base.
In the present embodiment, keyword ratio (1.4) is greater than preset ratio (0.5), it is therefore desirable to close question and answer to be processed
Key word, the corresponding user's question and answer information of question and answer keyword to be processed, evaluation keyword to be processed and evaluation keyword pair to be processed
Question and answer knowledge data table of the user's evaluation information update answered into question and answer knowledge data base.
Figure 10 is the schematic diagram of updated question and answer knowledge data table in one embodiment of the invention.As shown in Figure 10, it updates
Include: in question and answer knowledge data table afterwards
Keyword: place of opening an account, system and bank of deposit.
Problem: problem corresponding to place of opening an account is " I want that the account for inquiring me open an account place ", and system and bank of deposit are corresponding
The problem of be " system can not identify account bank of deposit ".
Answer.
The date of formation of keyword: 2018-12-21.
Problem state: those skilled in the art do not update answer content also, and answer waits safeguarding, state is 1.
The generating resource of problem: the above problem is to automatically update, and the generating resource is 1.
Those skilled in the art can log in question and answer knowledge data base, check that same day problem state is asking for answer to be safeguarded
Topic, and the answer content that timely updates in one column of answer.After updating answer content, corresponding problem state is updated to 2.
To sum up, the intelligent answer performance improvement method of the embodiment of the present invention is first crucial according to user's question and answer information extraction question and answer
Word evaluates keyword according to user's evaluation information extraction, successively judges that each question and answer are closed further according to preset keyword parameter table
Whether key word is question and answer keyword to be processed, according to preset keyword parameter table successively judge each evaluation keyword whether be
Then evaluation keyword to be processed is closed according to final keyword quantity, the quantity of question and answer keyword to be processed and evaluation to be processed
The quantity of key word calculates keyword ratio to be processed, finally judges whether keyword ratio to be processed is greater than preset ratio；When to
When handling keyword ratio greater than preset ratio, question and answer keyword to be processed, the corresponding user of question and answer keyword to be processed are asked
Information, evaluation keyword to be processed and the corresponding user's evaluation information update of evaluation keyword to be processed are answered to question and answer knowledge data
Library, it is ensured that the real-time update of knowledge base promotes the accuracy rate of intelligent answer, has timeliness and specific aim, further excellent
User experience is changed.
Based on the same inventive concept, the embodiment of the invention also provides a kind of intelligent answer performance boost systems, due to this
The principle that system solves the problems, such as is similar to intelligent answer performance improvement method, therefore the implementation of the system may refer to the reality of method
It applies, overlaps will not be repeated.
Figure 11 is the structural block diagram of intelligent answer performance boost system in the embodiment of the present invention.As shown in figure 11, it intelligently asks
Answering performance boost system includes:
Receiving unit, for receiving user's question and answer information and the corresponding user's evaluation information of user's question and answer information；
Keyword extraction unit, for being mentioned according to user's evaluation information according to user's question and answer information extraction question and answer keyword
Take evaluation keyword；
First statistic unit, for counting question and answer keyword and evaluating the sum of the quantity of keyword；
Second statistic unit, for counting identical question and answer keyword and evaluating the quantity of keyword；
Final key element, for the sum of quantity of question and answer keyword and evaluation keyword and identical question and answer is crucial
The quantity of word and evaluation keyword is subtracted each other, and final keyword quantity is obtained；
First judging unit, for according to preset keyword parameter table successively judge each question and answer keyword whether be to
Question and answer keyword is handled, successively judges whether each evaluation keyword is that evaluation to be processed is closed according to preset keyword parameter table
Key word；
Third statistic unit, for counting the quantity of question and answer keyword to be processed and the number of evaluation keyword to be processed respectively
Amount；
Computing unit, for being closed according to the quantity of final keyword quantity, question and answer keyword to be processed and evaluation to be processed
The quantity of key word calculates keyword ratio to be processed；
Second judgment unit, for judging whether keyword ratio to be processed is greater than preset ratio；
First updating unit, for when keyword ratio to be processed be greater than preset ratio when, by question and answer keyword to be processed,
The corresponding user's question and answer information of question and answer keyword to be processed, evaluation keyword to be processed and the corresponding use of evaluation keyword to be processed
Family evaluation information is updated to question and answer knowledge data base.
In a kind of wherein embodiment, further includes:
Second updating unit, for by question and answer keyword to be processed and the equal real-time update of evaluation keyword to be processed to key
In word parameter list.
In a kind of wherein embodiment, the first judging unit is specifically used for:
Successively judge each question and answer keyword whether in keyword parameter table；
When question and answer keyword is not in keyword parameter table, which is question and answer keyword to be processed；
Successively judge each evaluation keyword whether in keyword parameter table；
When evaluating keyword not in keyword parameter table, which is evaluation keyword to be processed.
In a kind of wherein embodiment, keyword ratio to be processed is calculated by following formula:
Wherein, s is keyword ratio to be processed, and a is the quantity of question and answer keyword to be processed, and b is that evaluation to be processed is crucial
The quantity of word, c are final keyword quantity, and d is default weight.
To sum up, the intelligent answer performance boost system of the embodiment of the present invention is first crucial according to user's question and answer information extraction question and answer
Word evaluates keyword according to user's evaluation information extraction, successively judges that each question and answer are closed further according to preset keyword parameter table
Whether key word is question and answer keyword to be processed, according to preset keyword parameter table successively judge each evaluation keyword whether be
Then evaluation keyword to be processed is closed according to final keyword quantity, the quantity of question and answer keyword to be processed and evaluation to be processed
The quantity of key word calculates keyword ratio to be processed, finally judges whether keyword ratio to be processed is greater than preset ratio；When to
When handling keyword ratio greater than preset ratio, question and answer keyword to be processed, the corresponding user of question and answer keyword to be processed are asked
Information, evaluation keyword to be processed and the corresponding user's evaluation information update of evaluation keyword to be processed are answered to question and answer knowledge data
Library, it is ensured that the real-time update of knowledge base promotes the accuracy rate of intelligent answer, has timeliness and specific aim, further excellent
User experience is changed.
The embodiment of the invention also provides a kind of computer equipments, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor perform the steps of when executing computer program
Receive user's question and answer information and the corresponding user's evaluation information of user's question and answer information；
According to user's question and answer information extraction question and answer keyword, keyword is evaluated according to user's evaluation information extraction；
It counts question and answer keyword and evaluates the sum of the quantity of keyword；
It counts identical question and answer keyword and evaluates the quantity of keyword；
The number of the sum of quantity by question and answer keyword and evaluation keyword and identical question and answer keyword and evaluation keyword
Amount is subtracted each other, and final keyword quantity is obtained；
Successively judge whether each question and answer keyword is question and answer keyword to be processed, root according to preset keyword parameter table
Successively judge whether each evaluation keyword is evaluation keyword to be processed according to preset keyword parameter table；
The quantity of question and answer keyword to be processed and the quantity of evaluation keyword to be processed are counted respectively；
According to final keyword quantity, the quantity of the quantity of question and answer keyword to be processed and evaluation keyword to be processed, meter
Calculate keyword ratio to be processed；
Judge whether keyword ratio to be processed is greater than preset ratio；
When keyword ratio to be processed is greater than preset ratio, by question and answer keyword to be processed, question and answer keyword to be processed
Corresponding user's question and answer information, evaluation keyword to be processed and the corresponding user's evaluation information update of evaluation keyword to be processed are extremely
Question and answer knowledge data base.
To sum up, the computer equipment of the embodiment of the present invention is first according to user's question and answer information extraction question and answer keyword, according to
Family evaluation information extract evaluation keyword, further according to preset keyword parameter table successively judge each question and answer keyword whether be
Question and answer keyword to be processed successively judges whether each evaluation keyword is evaluation to be processed according to preset keyword parameter table
Keyword, then according to final keyword quantity, the quantity of the quantity of question and answer keyword to be processed and evaluation keyword to be processed
Keyword ratio to be processed is calculated, finally judges whether keyword ratio to be processed is greater than preset ratio；When keyword to be processed
When ratio is greater than preset ratio, by question and answer keyword to be processed, the corresponding user's question and answer information of question and answer keyword to be processed, wait locate
Reason evaluates keyword and the corresponding user's evaluation information update of evaluation keyword to be processed to question and answer knowledge data base, it is ensured that
The real-time update of knowledge base promotes the accuracy rate of intelligent answer, has timeliness and specific aim, has advanced optimized user's body
It tests.
The embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer program, calculate
Machine program performs the steps of when being executed by processor
Receive user's question and answer information and the corresponding user's evaluation information of user's question and answer information；
According to user's question and answer information extraction question and answer keyword, keyword is evaluated according to user's evaluation information extraction；
It counts question and answer keyword and evaluates the sum of the quantity of keyword；
It counts identical question and answer keyword and evaluates the quantity of keyword；
The number of the sum of quantity by question and answer keyword and evaluation keyword and identical question and answer keyword and evaluation keyword
Amount is subtracted each other, and final keyword quantity is obtained；
Successively judge whether each question and answer keyword is question and answer keyword to be processed, root according to preset keyword parameter table
Successively judge whether each evaluation keyword is evaluation keyword to be processed according to preset keyword parameter table；
The quantity of question and answer keyword to be processed and the quantity of evaluation keyword to be processed are counted respectively；
According to final keyword quantity, the quantity of the quantity of question and answer keyword to be processed and evaluation keyword to be processed, meter
Calculate keyword ratio to be processed；
Judge whether keyword ratio to be processed is greater than preset ratio；
When keyword ratio to be processed is greater than preset ratio, by question and answer keyword to be processed, question and answer keyword to be processed
Corresponding user's question and answer information, evaluation keyword to be processed and the corresponding user's evaluation information update of evaluation keyword to be processed are extremely
Question and answer knowledge data base.
To sum up, the computer readable storage medium of the embodiment of the present invention is first crucial according to user's question and answer information extraction question and answer
Word evaluates keyword according to user's evaluation information extraction, successively judges that each question and answer are closed further according to preset keyword parameter table
Whether key word is question and answer keyword to be processed, according to preset keyword parameter table successively judge each evaluation keyword whether be
Then evaluation keyword to be processed is closed according to final keyword quantity, the quantity of question and answer keyword to be processed and evaluation to be processed
The quantity of key word calculates keyword ratio to be processed, finally judges whether keyword ratio to be processed is greater than preset ratio；When to
When handling keyword ratio greater than preset ratio, question and answer keyword to be processed, the corresponding user of question and answer keyword to be processed are asked
Information, evaluation keyword to be processed and the corresponding user's evaluation information update of evaluation keyword to be processed are answered to question and answer knowledge data
Library, it is ensured that the real-time update of knowledge base promotes the accuracy rate of intelligent answer, has timeliness and specific aim, further excellent
User experience is changed.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
Describe in detail it is bright, it should be understood that the above is only a specific embodiment of the present invention, the guarantor being not intended to limit the present invention
Range is protected, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should be included in this
Within the protection scope of invention.
Claims (10)
1. a kind of intelligent answer performance improvement method characterized by comprising
Receive user's question and answer information and the corresponding user's evaluation information of user's question and answer information；
According to user's question and answer information extraction question and answer keyword, keyword is evaluated according to the user's evaluation information extraction；
Count the sum of the quantity of the question and answer keyword and the evaluation keyword；
It counts identical question and answer keyword and evaluates the quantity of keyword；
The sum of quantity by the question and answer keyword and the evaluation keyword is closed with the identical question and answer keyword and evaluation
The quantity of key word is subtracted each other, and final keyword quantity is obtained；
Successively judge whether each question and answer keyword is question and answer keyword to be processed according to preset keyword parameter table, according to pre-
If keyword parameter table successively judge whether each evaluation keyword is evaluation keyword to be processed；
The quantity of question and answer keyword to be processed and the quantity of evaluation keyword to be processed are counted respectively；
According to the final keyword quantity, the quantity of the question and answer keyword to be processed and the evaluation keyword to be processed
Quantity calculates keyword ratio to be processed；
Judge whether the keyword ratio to be processed is greater than preset ratio；
When the keyword ratio to be processed is greater than the preset ratio, by the question and answer keyword to be processed, described wait locate
It is corresponding to manage the corresponding user's question and answer information of question and answer keyword, the evaluation keyword to be processed and the evaluation keyword to be processed
User's evaluation information update to question and answer knowledge data base.
2. intelligent answer performance improvement method according to claim 1, which is characterized in that further include:
By the question and answer keyword to be processed and the equal real-time update of the evaluation keyword to be processed to the keyword parameter table
In.
3. intelligent answer performance improvement method according to claim 1, which is characterized in that according to preset keyword parameter
Table successively judges whether each question and answer keyword is question and answer keyword to be processed, is successively judged according to preset keyword parameter table
Whether each evaluation keyword is evaluation keyword to be processed, comprising:
Successively judge each question and answer keyword whether in the keyword parameter table；
When the question and answer keyword is not in the keyword parameter table, which is question and answer keyword to be processed；
Successively judge each evaluation keyword whether in the keyword parameter table；
When the evaluation keyword is not in the keyword parameter table, which is evaluation keyword to be processed.
4. intelligent answer performance improvement method according to claim 1, which is characterized in that calculated by following formula wait locate
Manage keyword ratio:
Wherein, s is keyword ratio to be processed, and a is the quantity of question and answer keyword to be processed, and b is evaluation keyword to be processed
Quantity, c are final keyword quantity, and d is default weight.
5. a kind of intelligent answer performance boost system characterized by comprising
Receiving unit, for receiving user's question and answer information and the corresponding user's evaluation information of user's question and answer information；
Keyword extraction unit, for being believed according to the user's evaluation according to user's question and answer information extraction question and answer keyword
Breath extracts evaluation keyword；
First statistic unit, for counting the sum of the quantity of the question and answer keyword and the evaluation keyword；
Second statistic unit, for counting identical question and answer keyword and evaluating the quantity of keyword；
Final key element, for by the sum of the quantity of the question and answer keyword and the evaluation keyword with it is described identical
The quantity of question and answer keyword and evaluation keyword is subtracted each other, and final keyword quantity is obtained；
First judging unit, for successively judging whether each question and answer keyword is to be processed according to preset keyword parameter table
Question and answer keyword successively judges whether each evaluation keyword is that evaluation to be processed is crucial according to preset keyword parameter table
Word；
Third statistic unit, for counting the quantity of question and answer keyword to be processed and the quantity of evaluation keyword to be processed respectively；
Computing unit, for according to the quantity of the final keyword quantity, the question and answer keyword to be processed with described wait locate
The quantity of reason evaluation keyword, calculates keyword ratio to be processed；
Second judgment unit, for judging whether the keyword ratio to be processed is greater than preset ratio；
First updating unit, for be processed being asked described when the keyword ratio to be processed is greater than the preset ratio
Answer keyword, the corresponding user's question and answer information of the question and answer keyword to be processed, the evaluation keyword to be processed and it is described to
Processing evaluates the corresponding user's evaluation information update of keyword to question and answer knowledge data base.
6. intelligent answer performance boost system according to claim 5, which is characterized in that further include:
Second updating unit, for by the question and answer keyword to be processed and the equal real-time update of the evaluation keyword to be processed extremely
In the keyword parameter table.
7. intelligent answer performance boost system according to claim 5, which is characterized in that first judging unit is specific
For:
Successively judge each question and answer keyword whether in the keyword parameter table；
When the question and answer keyword is not in the keyword parameter table, which is question and answer keyword to be processed；
Successively judge each evaluation keyword whether in the keyword parameter table；
When the evaluation keyword is not in the keyword parameter table, which is evaluation keyword to be processed.
8. intelligent answer performance boost system according to claim 5, which is characterized in that calculated by following formula wait locate
Manage keyword ratio:
Wherein, s is keyword ratio to be processed, and a is the quantity of question and answer keyword to be processed, and b is evaluation keyword to be processed
Quantity, c are final keyword quantity, and d is default weight.
9. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor performs the steps of when executing the computer program
Receive user's question and answer information and the corresponding user's evaluation information of user's question and answer information；
According to user's question and answer information extraction question and answer keyword, keyword is evaluated according to the user's evaluation information extraction；
Count the sum of the quantity of the question and answer keyword and the evaluation keyword；
It counts identical question and answer keyword and evaluates the quantity of keyword；
The sum of quantity by the question and answer keyword and the evaluation keyword is closed with the identical question and answer keyword and evaluation
The quantity of key word is subtracted each other, and final keyword quantity is obtained；
Successively judge whether each question and answer keyword is question and answer keyword to be processed according to preset keyword parameter table, according to pre-
If keyword parameter table successively judge whether each evaluation keyword is evaluation keyword to be processed；
The quantity of question and answer keyword to be processed and the quantity of evaluation keyword to be processed are counted respectively；
According to the final keyword quantity, the quantity of the question and answer keyword to be processed and the evaluation keyword to be processed
Quantity calculates keyword ratio to be processed；
Judge whether the keyword ratio to be processed is greater than preset ratio；
When the keyword ratio to be processed is greater than the preset ratio, by the question and answer keyword to be processed, described wait locate
It is corresponding to manage the corresponding user's question and answer information of question and answer keyword, the evaluation keyword to be processed and the evaluation keyword to be processed
User's evaluation information update to question and answer knowledge data base.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
It is performed the steps of when being executed by processor
Receive user's question and answer information and the corresponding user's evaluation information of user's question and answer information；
According to user's question and answer information extraction question and answer keyword, keyword is evaluated according to the user's evaluation information extraction；
Count the sum of the quantity of the question and answer keyword and the evaluation keyword；
It counts identical question and answer keyword and evaluates the quantity of keyword；
The sum of quantity by the question and answer keyword and the evaluation keyword is closed with the identical question and answer keyword and evaluation
The quantity of key word is subtracted each other, and final keyword quantity is obtained；
Successively judge whether each question and answer keyword is question and answer keyword to be processed according to preset keyword parameter table, according to pre-
If keyword parameter table successively judge whether each evaluation keyword is evaluation keyword to be processed；
The quantity of question and answer keyword to be processed and the quantity of evaluation keyword to be processed are counted respectively；
According to the final keyword quantity, the quantity of the question and answer keyword to be processed and the evaluation keyword to be processed
Quantity calculates keyword ratio to be processed；
Judge whether the keyword ratio to be processed is greater than preset ratio；
When the keyword ratio to be processed is greater than the preset ratio, by the question and answer keyword to be processed, described wait locate
It is corresponding to manage the corresponding user's question and answer information of question and answer keyword, the evaluation keyword to be processed and the evaluation keyword to be processed
User's evaluation information update to question and answer knowledge data base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910293623.5A CN110059171B (en) | 2019-04-12 | 2019-04-12 | Intelligent question and answer performance improving method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910293623.5A CN110059171B (en) | 2019-04-12 | 2019-04-12 | Intelligent question and answer performance improving method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110059171A true CN110059171A (en) | 2019-07-26 |
| CN110059171B CN110059171B (en) | 2021-01-01 |
Family
ID=67317615
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910293623.5A Active CN110059171B (en) | 2019-04-12 | 2019-04-12 | Intelligent question and answer performance improving method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110059171B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340366A (en) * | 2020-02-26 | 2020-06-26 | 中国联合网络通信集团有限公司 | Structured knowledge quality improvement method and equipment |
| CN114124860A (en) * | 2021-11-26 | 2022-03-01 | 中国联合网络通信集团有限公司 | Session management method, device, equipment and storage medium |
| CN114706795A (en) * | 2022-06-07 | 2022-07-05 | 湖南智擎科技有限公司 | Turing test method, device and system for SaaS artificial intelligence application |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101178711A (en) * | 2006-11-30 | 2008-05-14 | 腾讯科技（深圳）有限公司 | Chinese auto-answer method and system |
| CN102236677A (en) * | 2010-04-28 | 2011-11-09 | 北京大学深圳研究生院 | Question answering system-based information matching method and system |
| CN103914570A (en) * | 2014-04-25 | 2014-07-09 | 北京中讯爱乐科技有限公司 | Intelligent customer service searching method and system based on character string similarity algorithm |
| CN105631032A (en) * | 2015-12-31 | 2016-06-01 | 上海智臻智能网络科技股份有限公司 | Method, device and system for establishing question and answer knowledge base based on abstract semantic recommendation |
| CN106202288A (en) * | 2016-06-30 | 2016-12-07 | 北京智能管家科技有限公司 | The optimization method of a kind of man-machine interactive system knowledge base and system |
| CN106294616A (en) * | 2016-08-02 | 2017-01-04 | 长江大学 | A kind of intelligent answer robot system based on mobile Internet |
| CN106649742A (en) * | 2016-12-26 | 2017-05-10 | 上海智臻智能网络科技股份有限公司 | Database maintenance method and device |
| CN106844558A (en) * | 2016-12-31 | 2017-06-13 | 深圳市优必选科技有限公司 | Intelligent answer method and system |
| US20170323008A1 (en) * | 2016-05-09 | 2017-11-09 | Fujitsu Limited | Computer-implemented method, search processing device, and non-transitory computer-readable storage medium |
| CN107818164A (en) * | 2017-11-02 | 2018-03-20 | 东北师范大学 | A kind of intelligent answer method and its system |
| CN108345610A (en) * | 2017-01-24 | 2018-07-31 | 北京搜狗科技发展有限公司 | It is a kind of to obtain the method and apparatus of data resource, the device for obtaining data resource |
| CN108376151A (en) * | 2018-01-31 | 2018-08-07 | 深圳市阿西莫夫科技有限公司 | Question classification method, device, computer equipment and storage medium |
-
2019
- 2019-04-12 CN CN201910293623.5A patent/CN110059171B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101178711A (en) * | 2006-11-30 | 2008-05-14 | 腾讯科技（深圳）有限公司 | Chinese auto-answer method and system |
| CN102236677A (en) * | 2010-04-28 | 2011-11-09 | 北京大学深圳研究生院 | Question answering system-based information matching method and system |
| CN103914570A (en) * | 2014-04-25 | 2014-07-09 | 北京中讯爱乐科技有限公司 | Intelligent customer service searching method and system based on character string similarity algorithm |
| CN105631032A (en) * | 2015-12-31 | 2016-06-01 | 上海智臻智能网络科技股份有限公司 | Method, device and system for establishing question and answer knowledge base based on abstract semantic recommendation |
| US20170323008A1 (en) * | 2016-05-09 | 2017-11-09 | Fujitsu Limited | Computer-implemented method, search processing device, and non-transitory computer-readable storage medium |
| CN106202288A (en) * | 2016-06-30 | 2016-12-07 | 北京智能管家科技有限公司 | The optimization method of a kind of man-machine interactive system knowledge base and system |
| CN106294616A (en) * | 2016-08-02 | 2017-01-04 | 长江大学 | A kind of intelligent answer robot system based on mobile Internet |
| CN106649742A (en) * | 2016-12-26 | 2017-05-10 | 上海智臻智能网络科技股份有限公司 | Database maintenance method and device |
| CN106844558A (en) * | 2016-12-31 | 2017-06-13 | 深圳市优必选科技有限公司 | Intelligent answer method and system |
| CN108345610A (en) * | 2017-01-24 | 2018-07-31 | 北京搜狗科技发展有限公司 | It is a kind of to obtain the method and apparatus of data resource, the device for obtaining data resource |
| CN107818164A (en) * | 2017-11-02 | 2018-03-20 | 东北师范大学 | A kind of intelligent answer method and its system |
| CN108376151A (en) * | 2018-01-31 | 2018-08-07 | 深圳市阿西莫夫科技有限公司 | Question classification method, device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 刘增健: "基于网络搜索的问答系统", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 张婉: "问答社区信息质量评价指标体系构建研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340366A (en) * | 2020-02-26 | 2020-06-26 | 中国联合网络通信集团有限公司 | Structured knowledge quality improvement method and equipment |
| CN114124860A (en) * | 2021-11-26 | 2022-03-01 | 中国联合网络通信集团有限公司 | Session management method, device, equipment and storage medium |
| CN114706795A (en) * | 2022-06-07 | 2022-07-05 | 湖南智擎科技有限公司 | Turing test method, device and system for SaaS artificial intelligence application |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110059171B (en) | 2021-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10477012B2 (en) | Fraud detection system and method | |
| US11714793B2 (en) | Systems and methods for providing searchable customer call indexes | |
| CN110059171A (en) | Intelligent answer performance improvement method and system | |
| CN105768433B (en) | A kind of method of intellectual piggy bank and its currency access | |
| CN107862402A (en) | A kind of method for processing business and terminal device | |
| CN108830696A (en) | Reference reports analyzing and processing method, device, computer equipment and storage medium | |
| CN110399533A (en) | Funds flow querying method and device | |
| CN106254543A (en) | Distributed interconnection Network and Finance Network based on cloud computing framework borrows method and system | |
| CN102289721A (en) | Carbon emission monitoring and measuring service system for daily life | |
| CN109615389A (en) | Electronic-payment transaction risk control method, device, server and storage medium | |
| CN107832291A (en) | Client service method, electronic installation and the storage medium of man-machine collaboration | |
| CN113379530A (en) | User risk determination method and device and server | |
| CN104063772B (en) | A kind of logistics information certificate authenticity method and device | |
| CN111061704B (en) | Financial analysis report generation method and equipment | |
| CN106294611A (en) | Core banking system and the old and new's core system data exchange method | |
| CN109145050A (en) | A kind of calculating equipment | |
| CN108563776A (en) | Off-line data acquisition methods and system, server and storage medium | |
| CN103297419A (en) | Method and system for fusing off-line data and on-line data | |
| CN206497498U (en) | A kind of integrated system of credit rating information data based on enterprise's reference business | |
| CN111754330A (en) | Interest-counting device and method for regular account to be paid in advance | |
| CN106204960A (en) | The method of commerce of financial self-service equipment and system | |
| CN113590604B (en) | Service data processing method, device and server | |
| CN110489394A (en) | Intermediate data processing method and equipment | |
| CN110930238A (en) | Method, device, equipment and computer readable medium for improving audit task efficiency | |
| CN107798417B (en) | Optimization method, device and computer equipment based on connected transaction data processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |