CN106095941A - Recommend method and system based on the solution in big data knowledge storehouse - Google Patents
Recommend method and system based on the solution in big data knowledge storehouse Download PDFInfo
- Publication number
- CN106095941A CN106095941A CN201610416286.0A CN201610416286A CN106095941A CN 106095941 A CN106095941 A CN 106095941A CN 201610416286 A CN201610416286 A CN 201610416286A CN 106095941 A CN106095941 A CN 106095941A
- Authority
- CN
- China
- Prior art keywords
- problem information
- solution
- knowledge base
- information
- value
- 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
Abstract
The present invention proposes a solution and recommends method, and described method includes: obtain the problem information of user, using the problem information of described user as first problem information；Described first problem information is mated with each problem information in knowledge base, determines the Second Problem information with described first problem information matches；Obtain and the corresponding solution of described Second Problem information；The described solution getting is recommended with described first problem information corresponding user.Achieve and obtain and the promptness of the corresponding solution of problem information and convenience, and owing to the method and system are no longer dependent on the subjective experience of individual, but according to the objective history data of the problem of solution, therefore, it is recommended that scheme have more reliability.Additionally, also proposed the commending system of a solution.
Description
Technical field
The present invention relates to computer disposal field, particularly relate to a kind of solution based on big data knowledge storehouse and recommend
Method and system.
Background technology
At present, when people run into oneself insurmountable problem in life, phone or aspectant can typically be passed through
Experienced stakeholder is looked for seek advice from, but owing to individual knowledge, experience are often limited, if simply simple dependence
The subjective experience of stakeholder and knowwhy, the problem that many times not can effectively solve the problem that people, and once seek advice from
Stakeholder due to the cognitive mistake of individual, it is likely that the solution of some mistakes can be given, so on the contrary can be to people
Solution problem has adverse effect on, and generally requires long waiting process when people seek advice from solution.Therefore
The reliability of the solution that traditional method is given and ageing all poor.
Content of the invention
Based on this, in order to solve the problems referred to above, it is proposed that a kind of reliable and efficiently based on the solution of big data
Proposal recommending method and system.
A solution recommends method, and described method includes: obtain the problem information of user, by the problem of described user
Described first problem information, as first problem information, is mated by information with each problem information in knowledge base, determines
With the Second Problem information of described first problem information matches, obtain and the corresponding solution of described Second Problem information, will
The described solution getting recommends the corresponding user with described first problem information.
Wherein in an embodiment, also included before the step of the problem information of described acquisition user: set up knowledge
Storehouse, described knowledge base includes multiple solution case, and described solution case includes problem information and corresponding with described problem information
Solution and the fractional value solving effect.
Wherein in an embodiment, described described first problem information is carried out with each problem information in knowledge base
Coupling, determines and includes with the step of the Second Problem information of described first problem information matches: by described first problem information and
Each problem information in knowledge base mates, and obtains the problem information set more than predetermined threshold value for the matching degree, searches described
The fractional value of each problem information corresponding solution effect in problem information set, by the solution effect pair that described fractional value is maximum
The problem information answered is as the Second Problem information with described first problem information matches.
Wherein in an embodiment, described described first problem information is carried out with each problem information in knowledge base
Coupling, determines and includes with the step of the Second Problem information of described first problem information matches: by described first problem information and
Each problem information in knowledge base mates, and obtains the problem information set more than predetermined threshold value for the matching degree, searches described
The fractional value of each problem information corresponding solution effect in problem information set, according in described problem information set, each is asked
The fractional value of the matching degree of topic information and each problem information described corresponding solution effect calculates the coupling of each problem information
Relative importance value, using the coupling relative importance value of calculated maximum as the first coupling relative importance value, by described first coupling relative importance value pair
The problem information answered is as the Second Problem information with described first problem information matches.
Wherein in an embodiment, described method also includes: obtain the feedback to described solution for the user, according to institute
State feedback and determine the fractional value of solution effect corresponding with described solution, by described in described first problem information, recommendation
The fractional value of solution and described solution effect solves case as one to be added to described knowledge base, when described knowledge base
When the quantity of middle solution case reaches the first predetermined threshold value, form big data knowledge storehouse.
A solution commending system, described system includes: problem information acquisition module, for the problem obtaining user
Information, using the problem information of described user as first problem information；Determining module, for by described first problem information with know
Each problem information known in storehouse mates, and determines the Second Problem information with described first problem information matches；Solution party
Case acquisition module, for obtaining and the corresponding solution of described Second Problem information；Recommending module, for the institute that will get
State solution and recommend the corresponding user with described first problem information.
Wherein in an embodiment, described system also includes: set up module, is used for setting up knowledge base, described knowledge base
Including multiple solution cases, described solution case includes problem information and corresponding solution and solution with described problem information
The fractional value of effect.
Wherein in an embodiment, described determining module includes: the first acquiring unit, for believing described first problem
Breath mates with each problem information in knowledge base, obtains the problem information set more than predetermined threshold value for the matching degree；First
Search unit, for searching the fractional value of the corresponding solution effect of each problem information in described problem information set；First
Join unit, for using the corresponding problem information of solution effect maximum for described fractional value as with described first problem information matches
Second Problem information.
Wherein in an embodiment, described determining module includes: second acquisition unit, for believing described first problem
Breath mates with each problem information in knowledge base, obtains the problem information set more than predetermined threshold value for the matching degree；Second
Search unit, for searching the fractional value of the corresponding solution effect of each problem information in described problem information set；Calculate single
Unit, for according to the matching degree of each problem information in described problem information set and the corresponding solution of each problem information described
The fractional value of effect calculates the coupling relative importance value of each problem information, using the coupling relative importance value of calculated maximum as first
Coupling relative importance value；Second matching unit, for mating the corresponding problem information of relative importance value as with described first using described first
The Second Problem information of problem information coupling.
Wherein in an embodiment, described system also includes: feedback module, is used for obtaining user to described solution
Feedback, according to described feedback determine with described solution corresponding solution effect fractional value；Add module, for by institute
The fractional value stating first problem information, the described solution of recommendation and described solution effect solves case interpolation extremely as one
In described knowledge base, when the quantity solving case in described knowledge base reaches the first predetermined threshold value, form big data knowledge storehouse.
Above-mentioned solution recommends method and system, by first obtaining the problem information of user, by the problem of this user
First problem information, as first problem information, is then mated by information with each problem information in knowledge base, determines
With the first Second Problem information asking information matches, then obtain the corresponding solution of Second Problem information, by get
This solution recommends user.Above-mentioned solution recommends method and system, based on knowledge base the asking user of big data
Topic information is mated with the problem information in knowledge base, is determined by the Second Problem information with first problem information matches,
So that it is determined that the solution of customer problem can be solved, solution then will be found to recommend this user, it is achieved that to obtain
The promptness of corresponding solution and convenience with problem information, and owing to the method and system are no longer dependent on the master of individual
Sight experience, but according to solve problem objective history data, therefore, it is recommended that solution have more reliability.
Brief description
Fig. 1 is the schematic flow sheet that in an embodiment, solution recommends method；
Fig. 2 is the method flow signal determining the Second Problem information with first problem information matches in an embodiment
Figure；
Fig. 3 is the method flow signal determining the Second Problem information with first problem information matches in another embodiment
Figure；
Fig. 4 is the schematic flow sheet that in another embodiment, solution recommends method；
Fig. 5 is the structured flowchart of solution commending system in an embodiment；
Fig. 6 is the structured flowchart of solution commending system in another embodiment；
Fig. 7 is the structured flowchart of determining module in an embodiment；
Fig. 8 is the structured flowchart of determining module in another embodiment；
Fig. 9 is the structured flowchart of solution commending system in another embodiment.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearer, by the following examples, and combine attached
Figure, recommends the detailed description of the invention of method and system to carry out further specifically the solution in knowledge based storehouse of the present invention
Bright.It should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
As it is shown in figure 1, in one embodiment it is proposed that a solution recommends method, the method includes following step
Rapid:
Step 102, obtains the problem information of user, using the problem information of user as first problem information.
In the present embodiment, the acquisition of customer problem information can be obtained by terminal, such as, and can be defeated by terminal
The problem information of access customer.Wherein, terminal can be smart mobile phone, panel computer, notebook computer, wearable intelligent equipment etc.
Can be with the electronic equipment of Input information.Concrete, customer problem management system can be run on terminating machine, by this system
Typing is carried out to the problem information of user.Wherein it is possible to the problem information of typing includes but is not limited to everyday problem, specialty problem
Deng.
First problem information is mated by step 104 with each problem information in knowledge base, determines and first problem
The Second Problem information of information matches.
Concrete, first problem information is mated with each problem information in knowledge base, calculates each respectively and ask
The problem information that calculated matching degree is maximum can be asked by topic information and the matching degree of first problem information as with first
The Second Problem information of topic information matches.In one embodiment, first, each problem information and first problem information are calculated
Then matching degree is formed a set more than all problems information of predetermined threshold value (such as threshold value is set to 0.8) by matching degree, or
Calculated matching degree according to smooth arrangement from big to small, is then chosen (the such as front 10) coupling coming above by person
Spend one the problem information set of composition of corresponding problem information, and obtain corresponding solution of each problem information in this set again and imitate
The fractional value of fruit, and using the corresponding problem information of solution effect maximum for fractional value as second with first problem information matches
Problem information.In another embodiment, first, calculate the matching degree of each problem information and first problem information, then obtain
Take the problem information set more than predetermined threshold value for the matching degree, then obtain each problem information in this problem information set corresponding
Solving the fractional value of effect, matching degree and corresponding solution of each problem information finally according to each problem information obtaining are imitated
The fractional value of fruit calculates the coupling relative importance value of each problem information, using the coupling relative importance value of calculated maximum as first
Join relative importance value, using this first coupling corresponding problem information of relative importance value as the Second Problem letter with first problem information matches
Breath.
Step 106, obtains and the corresponding solution of Second Problem information.
Concrete, knowledge base has prestored substantial amounts of solution case, each solve case include problem information and with
The corresponding solution of this problem information, the fractional value solving effect.Wherein, the fractional value solving effect reflects solution effect
Quality, fractional value is higher, illustrate solve effect better.It is calculated the Second Problem information with first problem information matches
After, obtain and this corresponding solution of Second Problem information.First problem information and Second Problem information matches, illustrate both
Problem information as similar or identical, then its solution also can be the most similar or identical.So obtaining and Second Problem
After the corresponding solution of information, the solution getting is recommended with first problem information corresponding user, Jin Erbang
User is helped to answer questions.
The solution getting is recommended with first problem information corresponding user by step 108.
Concrete, the solution that the problem information with user getting mates can be recommended this user.Solve
The information of scheme can be by network push to user, it is also possible to be sent to the corresponding terminal with user by the form of note,
User can also be sent to by forms such as mails.What user was received for this user asks the information i.e. solution of first problem information
After scheme, according to the solution effect of this solution, this solution can be marked, using the scoring of user as with solution
The certainly fractional value of scheme corresponding solution effect, the then solution by first problem information and for first problem information recommendation
The fractional value of scheme and solution effect adds in knowledge base together as a new solution case, makes knowledge base gradually complete
Kind.
In the present embodiment, by first obtaining the problem information of user, the problem information of this user is asked as first
Then first problem information mated by topic information with each problem information in knowledge base, determines and asks information with first
The Second Problem information joined, obtains the corresponding solution of Second Problem information then, recommends this solution getting
To user.Above-mentioned solution recommends method, based on the knowledge base of big data by the problem information of user and asking in knowledge base
Topic information is mated, and is determined by the Second Problem information with first problem information matches, so that it is determined that can solve user
The solution of problem, then will find solution to recommend this user, it is achieved that obtain and the corresponding solution of problem information
The promptness of scheme and convenience, and owing to the method and system are no longer dependent on the subjective experience of individual, but according to solution
The objective history data of problem, therefore, it is recommended that solution have more reliability.
In one embodiment, also included before obtaining the step of problem information of user: set up knowledge base, wherein,
Knowledge base include multiple solution case, each solve case include problem information and with this problem information corresponding solution party
Case and the fractional value solving effect.
In the present embodiment, pre-building knowledge base, this knowledge base is that big data knowledge storehouse is it can be understood as the inside has greatly
Amount solution case, each solve case include problem information and with this problem information corresponding solution and solution effect
Fractional value, solve effect fractional value for reflect this solution corresponding solution effect quality, fractional value is bigger, says
Bright solution effect is better, otherwise, fractional value is less, solves effect poorer.Fractional value derives from anti-to solution of user
Feedback, the feedback of user can be realized by scoring.In the embodiment of the present invention, big data knowledge storehouse is the big data of solution
Knowledge base, solution big data knowledge storehouse is structuring in knowledge engineering, easily operation, easily utilization, comprehensive organized knowledge
Cluster, can for the demand of professional domain problem solving, use professional knowledge representation store in computer storage,
Tissue, management and the knowledge piece set interkniting using.These knowledge pieces include the knowwhy related to professional domain,
Factual data.For example, relevant in professional domain definition, theorem and operation rule and common sense knowledge etc..
As in figure 2 it is shown, in one embodiment, first problem information and each problem information in knowledge base are carried out
Join, determine that the step with the Second Problem information of first problem information matches includes:
First problem information is mated by step 104a with each problem information in knowledge base, obtains matching degree big
Problem information set in predetermined threshold value.
In the present embodiment, first problem information is mated one by one with each problem information in knowledge base, and count
Calculate the matching degree between each problem information and first problem information in knowledge base, then according to calculated matching degree, obtain
Take all problems information more than predetermined threshold value, all problems information one the problem information set of composition that will get.Calculate
The method of matching degree can have multiple, such as, can mate according to keyword, using the keyword number that the match is successful as
Degree of joining.Wherein, when carrying out the coupling of keyword, using keyword as character string, the accurate coupling of character string can both have been used,
Also the fuzzy matching of character string can be used.Concrete, the keyword in extraction first problem information is as the first keyword, so
Rear utilizing the first keyword to mate with the problem information in knowledge base, the keyword number of coupling is more, corresponding matching degree
Also bigger, matching degree is all collected one problem letter of composition more than the problem information of predetermined threshold value (such as, 80%)
Breath set.In another embodiment, from the problem information of the user obtaining, extracting keywords is as the first keyword, from greatly
Data knowledge storehouse solves in the problem information in case extracting keywords as the second keyword, customer problem information and knowledge
In storehouse, the coupling of each problem information is actually the first keyword and the second keyword mates, and by the match is successful
Accounting in the first keyword number for the keyword number is as corresponding matching degree.Such as, extract from the problem information of user
The number of times of the first keyword is 10, then if the keyword in certain problem information in database has 7 to close with first
The match is successful for keyword, then this problem information is exactly 70% with the matching degree of first problem information.
Step 104b, the fractional value of each problem information corresponding solution effect in the information aggregate that searches problem.
In the present embodiment, after getting the problem information set that matching degree is more than predetermined threshold value, further go to obtain
The fractional value of each problem information corresponding solution effect in this problem information set, fractional value is bigger, illustrates that solving effect gets over
Good.Concrete, such as, first obtain the problem information set more than 90% for the matching degree, the problem in now problem information set
Information is substantially all more similar with first problem information, next needs to obtain each problem information pair in problem information set
The fractional value of the solution effect answered.Fractional value is bigger, illustrates to solve effect better, also illustrates that corresponding solution gets over symbol simultaneously
Share the demand at family.
Step 104c, using the corresponding problem information of solution effect maximum for fractional value as with first problem information matches
Second Problem information.
In the present embodiment, the fractional value of the corresponding solution effect of each problem information in problem information set is got
After, by comparing the fractional value of the solution effect of each problem information, by solution effect corresponding problem letter maximum for fractional value
Breath is as the Second Problem information with first problem information matches, and then obtains and the corresponding solution party of this Second Problem information
This solution is recommended the corresponding user of first problem information by case.
As it is shown on figure 3, in one embodiment, first problem information and each problem information in knowledge base are carried out
Join, determine that the step with the Second Problem information of first problem information matches includes:
First problem information is mated by step 104A with each problem information in knowledge base, obtains matching degree big
Problem information set in predetermined threshold value.
In the present embodiment, first problem information is mated one by one with each problem information in knowledge base, and count
Calculate the matching degree between each problem information and first problem information in knowledge base, then according to calculated matching degree, obtain
Take all problems information more than predetermined threshold value, all problems information one the problem information set of composition that will get.Coupling
The span of the predetermined threshold value of degree is between 0 to 1.The method calculating matching degree can have multiple, such as, and can be according to key
Word mates, using the keyword number that the match is successful as matching degree.Wherein, when carrying out the coupling of keyword, by keyword
As character string, the accurate coupling of character string both can be used, it would however also be possible to employ the fuzzy matching of character string.Concrete, extract
Keyword in first problem information, as the first keyword, then utilizes the first keyword to enter with the problem information in knowledge base
Row coupling, the keyword number of coupling is more, and corresponding matching degree is also bigger, by matching degree more than predetermined threshold value (such as,
80%) problem information all collects one problem information set of composition.In another embodiment, from the user obtaining
Problem information in extracting keywords as the first keyword, solve the problem information in case is taken out from big data knowledge storehouse
Take keyword and be actually first as the second keyword, customer problem information with mating of each problem information in knowledge base
Keyword and the second keyword mate, and using the keyword number that the match is successful the accounting in the first keyword number as phase
The matching degree answered.Such as, the number of times of the first keyword extracting from the problem information of user is 10, then if database
In certain problem information in keyword have 7 with first Keywords matching success, then this problem information and first problem
The matching degree of information is exactly 70%.
Step 104B, the fractional value of each problem information corresponding solution effect in the information aggregate that searches problem.
In the present embodiment, after getting the problem information set that matching degree is more than predetermined threshold value, further go to obtain
The fractional value of each problem information corresponding solution effect in this problem information set, fractional value is bigger, illustrates that solving effect gets over
Good.
Step 104C, the matching degree according to each problem information in problem information set and first problem information and each ask
The fractional value of topic information corresponding solution effect calculates the coupling relative importance value of each problem information, by calculated maximum
Join relative importance value as the first coupling relative importance value.
In the present embodiment, first, mating of each problem information and first problem information in problem information set is obtained
Degree, then obtains the fractional value of each problem information corresponding solution effect in problem information set.Use average weighted side
The coupling relative importance value of each problem information in method computational problem information aggregate.Concrete, the matching degree of problem information is set to P1,
The fractional value of corresponding for problem information solution effect is set to P2, and the weight being then respectively provided with matching degree P1 is k1, solves effect
The weight of the fractional value P2 of fruit is k2, wherein, and k1+k2=1, and k1 and k2 for being less than the number of 1 more than 0.So corresponding problem
The coupling relative importance value of information is P1*k1+P2*k2.Then the coupling relative importance value of calculated maximum is excellent as the first coupling
First spend.
The first coupling corresponding problem information of relative importance value is asked by step 104D as with the second of first problem information matches
Topic information.
Concrete, using the coupling relative importance value of calculated maximum as the first coupling relative importance value, then obtain with this
The one coupling corresponding problem information of relative importance value, this first coupling corresponding problem information of relative importance value is as first problem information matches
Second Problem information.
As shown in Figure 4, in one embodiment, above-mentioned solution recommends method also to include:
Step 110, obtains the feedback to solution for the user, determines solution effect corresponding with solution according to feedback
Fractional value.
In the present embodiment, after the problem information for user recommends solution, user is obtained to the solution recommended
Feedback, according to the feedback of user determine corresponding with solution solution effect fractional value.Concrete, the feedback of user
Can be with directly by the form of marking, such as full marks are 100 points, and suggested design is beaten by effect according to solving accordingly
Point, then using the marking of user as the fractional value solving effect.By obtaining user journey can also be satisfied with to solution
Then the satisfaction of user is converted to corresponding fraction and stores by degree, concrete, it is assumed that satisfaction is divided into five kinds,
To be satisfied with very much respectively, satisfied, general as, dissatisfied, very dissatisfied, pre-set the corresponding fraction of every kind of satisfaction
Value, such as, being satisfied with very much corresponding fractional value is 100 points, and being satisfied with corresponding fractional value is 80 points, general as corresponding fractional value
Being 60 points, being unsatisfied with corresponding fractional value is 30 points, and being unsatisfied with very much corresponding fraction is 0 point.Such as, user is to solution
Be evaluated as general as, then backstage is allocated as the fractional value for solving effect automatically by corresponding 60.
Step 112, by the fractional value of first problem information, the solution of recommendation and solution effect together as a solution
Certainly case is added to knowledge base, when the quantity solving case in knowledge base reaches the first predetermined threshold value, forms big data and knows
Know storehouse.
Concrete, after acquisition user is to the scoring of suggested design, namely obtain the fractional value solving effect.Will before
The problem information of user i.e. first problem information, for the solution of this first problem information recommendation and above-mentioned solution effect point
Numerical value adds to knowledge base together as a new solution case, can constantly improve knowledge base by the method.When
It when the quantity of the solution case in knowledge base is more than the first predetermined threshold value (such as, the first predetermined threshold value is set to 10,000), is the formation of
Big data knowledge storehouse, the quantity solving case in big data knowledge storehouse is bigger, can find the probability of the problem information more mating
Bigger.Thus, it is recommended that solution also can be more and more reliable.
A solution in order to be better understood from and apply the present invention to propose recommends method, carries out the example below, needs
It is noted that the scope that the present invention is protected is not limited to the example below.
In one embodiment, the problem information of the user of acquisition is: " computer crash card machine what if ".Pre-building
Big data knowledge storehouse in search the Second Problem information mated with the problem information of user.Concrete, by the problem letter of user
Breath mates with the problem information in big data knowledge storehouse, then calculates asking of each problem information and user in knowledge base
The matching degree of topic information, then obtains the problem information set more than 80% for the matching degree or by suitable by from big to small of matching degree
Sequence is ranked up, then select matching degree front 10 problem information.Such as, find from the problem information set obtaining and be somebody's turn to do
One of them problem information of the problem information coupling of user is " what if computer deadlock card machine occurs ".Further, obtain
The fractional value of each problem information corresponding solution effect, the then solution effect pair by fractional value maximum in problem information set
The solution answered is as the scheme recommended.Such as, the solution of problem information for " what if computer deadlock card machine occurs "
Scheme is: uses Ctrl+Alt+Delete to start task manager, then selects to terminate corresponding program process etc..The program
Fractional value be 99 points, be the solution that fractional value is the highest, then this solution be exactly obtain optimum recommending scheme.
As it is shown in figure 5, in one embodiment, a solution commending system, this system includes:
Problem information acquisition module 502, for obtaining the problem information of user, using the problem information of described user as the
One problem information；
Determining module 504, for mating described first problem information with each problem information in knowledge base, really
The fixed Second Problem information with described first problem information matches；
Solution acquisition module 506, for obtaining and the corresponding solution of described Second Problem information；
Recommending module 508, corresponding with described first problem information for recommending the described solution getting
User.
As shown in Figure 6, in one embodiment, above-mentioned solution commending system also includes:
Setting up module 501, being used for setting up knowledge base, described knowledge base includes multiple solution case, described solution case bag
Include problem information and with described problem information corresponding solution and solve effect fractional value.
As it is shown in fig. 7, in one embodiment, determining module 504 includes:
First acquiring unit 504a, for carrying out each problem information in described first problem information and knowledge base
Join, obtain the problem information set more than predetermined threshold value for the matching degree；
First lookup unit 504b, is used for searching the corresponding solution effect of each problem information in described problem information set
Fractional value；
First matching unit 504c, for using the corresponding problem information of solution effect maximum for fractional value as with described the
The Second Problem information of one problem information coupling.
As shown in Figure 8, in one embodiment, determining module 504 includes:
Second acquisition unit 504A, for carrying out each problem information in described first problem information and knowledge base
Join, obtain the problem information set more than predetermined threshold value for the matching degree.
Second lookup unit 504B, solves dividing of effect for each problem information in the information aggregate that searches problem is corresponding
Numerical value.
Computing unit 504C, for the matching degree according to each problem information in problem information set and each problem information
The fractional value of corresponding solution effect calculates the coupling relative importance value of each problem information, by preferential for the coupling of calculated maximum
Degree is as the first coupling relative importance value.
Second matching unit 504D, for using first coupling the corresponding problem information of relative importance value as with first problem information
The Second Problem information of coupling.
As it is shown in figure 9, in one embodiment, the commending system of above-mentioned solution also includes:
Feedback module 510, for obtaining the feedback to described solution for the user, determines and described solution according to described feedback
The certainly fractional value of scheme corresponding solution effect.
Add module 512, be used for the fractional value of first problem information, the solution of recommendation and solution effect as one
Individual solution case is added to knowledge base, when the quantity solving case in knowledge base reaches the first predetermined threshold value, forms big number
According to knowledge base.
One of ordinary skill in the art will appreciate that all or part of flow process realizing in above-described embodiment method, be permissible
Instructing related hardware by computer program to complete, described program can be stored in a computer read/write memory medium
In, this program is upon execution, it may include such as the flow process of the embodiment of above-mentioned each method.Wherein, described storage medium can be magnetic
Dish, CD, read-only store-memory body (Read-Only Memory ROM) or random store-memory body (Random Access
Memory, RAM) etc..
Each technical characteristic of embodiment described above can combine arbitrarily, for making description succinct, not to above-mentioned reality
The all possible combination of each technical characteristic executed in example is all described, but, as long as the combination of these technical characteristics is not deposited
It in contradiction, is all considered to be the scope that this specification is recorded.
Embodiment described above only have expressed the several embodiments of the present invention, and it describes more concrete and detailed, but simultaneously
Therefore the restriction to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that, for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, some deformation can also be made and improve, these broadly fall into the guarantor of the present invention
Protect scope.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (10)
1. a solution recommends method, and described method includes:
Obtain the problem information of user, using the problem information of described user as first problem information；
Described first problem information is mated with each problem information in knowledge base, determines and described first problem information
The Second Problem information of coupling；
Obtain and the corresponding solution of described Second Problem information；
The described solution getting is recommended with described first problem information corresponding user.
2. method according to claim 1, it is characterised in that before the step of the problem information of described acquisition user also
Including: setting up knowledge base, described knowledge base includes multiple solution case, and described solution case includes problem information and asks with described
The corresponding solution of topic information and the fractional value solving effect.
3. method according to claim 2, it is characterised in that described by described first problem information each with knowledge base
Individual problem information mates, and determines that the step with the Second Problem information of described first problem information matches includes:
Described first problem information is mated with each problem information in knowledge base, obtains matching degree and be more than predetermined threshold value
Problem information set；
Search the fractional value of the corresponding solution effect of each problem information in described problem information set；
Using the corresponding problem information of solution effect maximum for described fractional value as second with described first problem information matches
Problem information.
4. method according to claim 2, it is characterised in that described by described first problem information each with knowledge base
Individual problem information mates, and determines that the step with the Second Problem information of described first problem information matches includes:
Described first problem information is mated with each problem information in knowledge base, obtains matching degree and be more than predetermined threshold value
Problem information set；
Search the fractional value of the corresponding solution effect of each problem information in described problem information set；
Imitate according to matching degree and corresponding solution of each problem information described of each problem information in described problem information set
The fractional value of fruit calculates the coupling relative importance value of each problem information, using the coupling relative importance value of calculated maximum as first
Join relative importance value；
Using the described first coupling corresponding problem information of relative importance value as the Second Problem letter with described first problem information matches
Breath.
5. method according to claim 1, it is characterised in that described method also includes:
Obtain the feedback to described solution for the user, determine solution effect corresponding with described solution according to described feedback
Fractional value；
Using the fractional value of described first problem information, the described solution of recommendation and described solution effect as a solution case
Example is added to described knowledge base, when the quantity solving case in described knowledge base reaches the first predetermined threshold value, forms big number
According to knowledge base.
6. a solution commending system, it is characterised in that described system includes:
Problem information acquisition module, for obtaining the problem information of user, using the problem information of described user as first problem
Information；
Determining module, for mating described first problem information with each problem information in knowledge base, determines and institute
State the Second Problem information of first problem information matches；
Solution acquisition module, for obtaining and the corresponding solution of described Second Problem information；
Recommending module, for recommending the corresponding user with described first problem information by the described solution getting.
7. system according to claim 6, it is characterised in that described system also includes:
Setting up module, being used for setting up knowledge base, described knowledge base includes multiple solution case, and described solution case includes that problem is believed
Cease and corresponding solution and the fractional value solving effect with described problem information.
8. system according to claim 7, it is characterised in that described determining module includes:
First acquiring unit, for mating described first problem information with each problem information in knowledge base, obtains
Matching degree is more than the problem information set of predetermined threshold value；
First lookup unit, for searching the fraction of the corresponding solution effect of each problem information in described problem information set
Value；
First matching unit, believes as with described first problem for the corresponding problem information of solution effect that fractional value is maximum
The Second Problem information of breath coupling.
9. system according to claim 7, it is characterised in that described determining module includes:
Second acquisition unit, for mating described first problem information with each problem information in knowledge base, obtains
Matching degree is more than the problem information set of predetermined threshold value；
Second lookup unit, for searching the fraction of the corresponding solution effect of each problem information in described problem information set
Value；
Computing unit, for according to the matching degree of each problem information in described problem information set and each problem information described
The fractional value of corresponding solution effect calculates the coupling relative importance value of each problem information, by preferential for the coupling of calculated maximum
Degree is as the first coupling relative importance value；
Second matching unit, for will described first mate the corresponding problem information of relative importance value as with described first problem information
The Second Problem information of coupling.
10. system according to claim 6, it is characterised in that described system also includes:
Feedback module, for obtaining the feedback to described solution for the user, determines and described solution according to described feedback
The fractional value of corresponding solution effect；
Add module, for by the fractional value of described first problem information, the described solution of recommendation and described solution effect
Solve case as one to add to described knowledge base, preset threshold when the quantity solving case in described knowledge base reaches first
During value, form big data knowledge storehouse.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610416286.0A CN106095941B (en) | 2016-06-14 | 2016-06-14 | Big data knowledge base-based solution recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610416286.0A CN106095941B (en) | 2016-06-14 | 2016-06-14 | Big data knowledge base-based solution recommendation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106095941A true CN106095941A (en) | 2016-11-09 |
| CN106095941B CN106095941B (en) | 2020-03-20 |
Family
ID=57846697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610416286.0A Active CN106095941B (en) | 2016-06-14 | 2016-06-14 | Big data knowledge base-based solution recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106095941B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875014A (en) * | 2018-06-20 | 2018-11-23 | 大国创新智能科技(东莞)有限公司 | Accurate item recommendation method and robot system based on big data and artificial intelligence |
| CN109299224A (en) * | 2018-10-23 | 2019-02-01 | 广州九乐维信息科技有限公司 | Solution querying method based on Zabbix, device, computer equipment |
| CN110471961A (en) * | 2019-08-22 | 2019-11-19 | 北京锐安科技有限公司 | A kind of product demand acquisition methods, device, equipment and storage medium |
| CN111507550A (en) * | 2019-01-30 | 2020-08-07 | 广州泰迪智能科技有限公司 | Automatic recommendation method for optimal solution of work order problem |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN103853842A (en) * | 2014-03-20 | 2014-06-11 | 百度在线网络技术（北京）有限公司 | Automatic question and answer method and system |
| CN104133817A (en) * | 2013-05-02 | 2014-11-05 | 深圳市世纪光速信息技术有限公司 | Online community interaction method and device and online community platform |
| CN105159996A (en) * | 2015-09-07 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Deep question-and-answer service providing method and device based on artificial intelligence |
-
2016
- 2016-06-14 CN CN201610416286.0A patent/CN106095941B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN104133817A (en) * | 2013-05-02 | 2014-11-05 | 深圳市世纪光速信息技术有限公司 | Online community interaction method and device and online community platform |
| CN103853842A (en) * | 2014-03-20 | 2014-06-11 | 百度在线网络技术（北京）有限公司 | Automatic question and answer method and system |
| CN105159996A (en) * | 2015-09-07 | 2015-12-16 | 百度在线网络技术（北京）有限公司 | Deep question-and-answer service providing method and device based on artificial intelligence |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875014A (en) * | 2018-06-20 | 2018-11-23 | 大国创新智能科技(东莞)有限公司 | Accurate item recommendation method and robot system based on big data and artificial intelligence |
| CN109299224A (en) * | 2018-10-23 | 2019-02-01 | 广州九乐维信息科技有限公司 | Solution querying method based on Zabbix, device, computer equipment |
| CN111507550A (en) * | 2019-01-30 | 2020-08-07 | 广州泰迪智能科技有限公司 | Automatic recommendation method for optimal solution of work order problem |
| CN110471961A (en) * | 2019-08-22 | 2019-11-19 | 北京锐安科技有限公司 | A kind of product demand acquisition methods, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106095941B (en) | 2020-03-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020048084A1 (en) | Resource recommendation method and apparatus, computer device, and computer-readable storage medium | |
| CN103729359B (en) | A kind of method and system recommending search word | |
| US20190018900A1 (en) | Method and Apparatus for Displaying Search Results | |
| US8332418B1 (en) | Collaborative filtering to match people | |
| US7725414B2 (en) | Method for developing a classifier for classifying communications | |
| US9639602B2 (en) | Method for matching queries with answer items in a knowledge base | |
| US20150332373A1 (en) | Method and system for pushing mobile application | |
| CN103902538B (en) | Information recommending apparatus and method based on decision tree | |
| CN103916436B (en) | Information-pushing method, device, terminal and server | |
| CN104794207B (en) | A kind of commending system and its method of work based on cooperation | |
| CN106095941A (en) | Recommend method and system based on the solution in big data knowledge storehouse | |
| CN109241451B (en) | Content combination recommendation method and device and readable storage medium | |
| CN108629671B (en) | Restaurant recommendation method integrating user behavior information | |
| Wang et al. | Personalized recommendation for new questions in community question answering | |
| CN108876536A (en) | Collaborative filtering recommending method based on arest neighbors information | |
| US9239863B2 (en) | Method and apparatus for graphic code database updates and search | |
| Wang et al. | Personalized news recommendation based on consumers' click behavior | |
| CN112507139B (en) | Knowledge graph-based question and answer method, system, equipment and storage medium | |
| KR20190086126A (en) | Manual retrieval service providing server and method using chatbot | |
| WO2020073526A1 (en) | Trust network-based push method, apparatus, computer device, and storage medium | |
| CN103927339B (en) | Knowledge Reorganizing system and method for knowledge realignment | |
| CN111310046B (en) | Object recommendation method and device | |
| CN111078997A (en) | Information recommendation method and device | |
| US20170109411A1 (en) | Assisted creation of a search query | |
| CN106126541B (en) | Personalized solution recommended method and system based on big data knowledge base |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |