CN106126541A - Personalized solution based on big data knowledge storehouse recommends method and system - Google Patents
Personalized solution based on big data knowledge storehouse recommends method and system Download PDFInfo
- Publication number
- CN106126541A CN106126541A CN201610424463.XA CN201610424463A CN106126541A CN 106126541 A CN106126541 A CN 106126541A CN 201610424463 A CN201610424463 A CN 201610424463A CN 106126541 A CN106126541 A CN 106126541A
- Authority
- CN
- China
- Prior art keywords
- information
- solution
- personal information
- user
- problem information
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention proposes a solution and recommends method, and described method includes: obtain problem information and the personal information of user, using the problem information of described user as first problem information, using the personal information of described user as first man information；Described first problem information and described first man information are mated with the problem information in knowledge base and personal information, determines and described first problem information and the Second Problem information of first man information matches and the second personal information；Obtain the solution corresponding with described Second Problem information and the second personal information；The described solution got is recommended described user.Achieve promptness and the agility obtaining solution, 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, and the personal information combining user recommends, it is recommended that solution have more reliability.Additionally, also proposed a solution commending system.
Description
Technical field
The present invention relates to computer technology and field of artificial intelligence, particularly relate to a kind of based on big data knowledge storehouse
Personalized solution recommend method and system.
Background technology
At present, traditional Resolving probiems communication model is that user needs to professional institution to look for expert, carry out with expert faced by
The problem in face is linked up, and expert, according to the problem of user, is entered by existing data in consulting result, experience or experts database
Row, with reference to reasoning, obtains recommending user for the issue-resolution of this user.Above-mentioned this mode excessively rely on expert or
The subjective experience of experts database and theoretical knowledge, meanwhile, once the knowledge of expert or experts database is wrong, then can produce the solution of mistake
Scheme recommendation results, it is recommended that scheme has deviation, the solution on customer problem has bad impact, and having delayed user to obtain has
Imitate the ageing of solution.
Summary of the invention
Based on this, it is necessary to provide a kind of can be according to the individualized feature of different user, accurate and effective and base timely
Personalized solution in big data knowledge storehouse recommends method and system.
A solution recommends method, described in include: obtain the problem information of user and personal information, by described user
Problem information as first problem information, using the personal information of described user as first man information；Ask described first
Topic information and described first man information are mated with the problem information in knowledge base and personal information, determine and described first
The Second Problem information of problem information and first man information matches and the second personal information；Obtain and described Second Problem information
And second solution corresponding to personal information；The described solution got is recommended described user.
Wherein in an embodiment, also wrapped before the step of the described problem information obtaining user and personal information
Include: set up knowledge base, described knowledge base include multiple solution case, described solution case include problem information, personal information and
The solution corresponding with described problem information and personal information and the fractional value of solution effect.
Wherein in an embodiment, described by described first problem information and described first man information and knowledge base
Problem information and personal information mate, determine and ask with the second of described first problem information and first man information matches
The step of topic information and the second personal information includes: by described first problem information and the piecemeal solution case in described knowledge base
Problem information mate, obtain matching degree more than the first predetermined threshold value first solution case set；Calculate described first
Solve the personal information of each solution case and the matching degree of described first man information in case set, obtain matching degree and be more than
Second solution case set of the second predetermined threshold value；Search the described second solution effect solving each solution case in case set
The fractional value of fruit；Problem information corresponding for the solution effect that described fractional value is maximum and personal information are asked as with described first
The Second Problem information of topic information and first man information matches and the second personal information.
Wherein in an embodiment, described by described first problem information and described first man information and knowledge base
Problem information and personal information mate, determine and ask with the second of described first problem information and first man information matches
The step of topic information and the second personal information includes: by described first problem information and the piecemeal solution case in described knowledge base
Problem information mate, obtain matching degree more than the first predetermined threshold value first solution case set；Calculate described first
Solve the personal information of each solution case and the matching degree of described first man information in case set, obtain matching degree and be more than
Second solution case set of the second predetermined threshold value；Search the described second solution effect solving each solution case in case set
The fractional value of fruit；According to obtaining described second solves the problem information matching degree of each solution case, individual in case set
The fractional value of information matches degree and solution effect calculates the coupling relative importance value of each solution case, by calculated maximum match
Relative importance value is as the first coupling relative importance value；Using described first coupling problem information corresponding to relative importance value and personal information as with institute
State Second Problem information and second personal information of first problem information and first man information matches.
Wherein in an embodiment, described calculating described first solves individual's letter of each solution case in case set
Breath and the matching degree of described first man information, obtain the matching degree step more than the second solution case set of the second predetermined threshold value
Suddenly include: calculate the described first age of user and described first solved in case set in the personal information of each solution case
The absolute value of the difference of the age of user of personal information；Calculate described first and solve the individual of each solution case in case set
The user location of information and the on-site distance of user in described first man information；According to calculated age of user
The absolute value of difference and the on-site distance of described user determine that described first solves each solution case in case set
Matching degree between personal information and described first man information.
Wherein in an embodiment, described method also includes: obtain user's feedback to described solution, according to institute
State feedback and determine the fractional value of the solution effect corresponding with described solution；By described first problem information, first man letter
The fractional value of breath, the described solution recommended and described solution effect solves case as one to be added to described knowledge base
In, when the quantity solving case in described knowledge base reaches the first predetermined threshold value, form big data knowledge storehouse.
A solution commending system, described system includes: data obtaining module, for obtaining the problem information of user
And personal information, using the problem information of described user as first problem information, using the personal information of described user as first
Personal information；Determine module, for described first problem information and described first man information being believed with the problem in knowledge base
Breath and personal information are mated, determine with described first problem information and the Second Problem information of first man information matches and
Second personal information；Solution acquisition module is corresponding with described Second Problem information and the second personal information for obtaining
Solution；Recommending module, for recommending described user by the described solution got.
Wherein in an embodiment, described device also includes: set up module, is used for setting up knowledge base, described knowledge base
Including multiple solution cases, described solution case include problem information, personal information and with described problem information and personal information
Corresponding solution and the fractional value of solution effect.
Wherein in an embodiment, described determine that module includes: the first acquiring unit, for being believed by described first problem
Breath mates with the problem information of the piecemeal solution case in described knowledge base, obtains matching degree more than the first predetermined threshold value
First solves case set；First computing unit, for calculate described first solve each solution case in case set
People's information and the matching degree of described first man information, obtain the matching degree the second solution casebook more than the second predetermined threshold value
Close；First searches unit, solves the fractional value of the solution effect of each solution case in case set for searching described second；
First matching unit, the problem information corresponding for the solution effect that described fractional value is maximum and personal information are as with described
The Second Problem information of first problem information and first man information matches and the second personal information.
Wherein in an embodiment, described determine that module includes: second acquisition unit, for being believed by described first problem
Breath mates with the problem information of the piecemeal solution case in described knowledge base, obtains matching degree more than the first predetermined threshold value
First solves case set；Second computing unit, for calculate described first solve each solution case in case set
People's information and the matching degree of described first man information, obtain the matching degree the second solution casebook more than the second predetermined threshold value
Close；Second searches unit, solves the fractional value of the solution effect of each solution case in case set for searching described second；
Coupling relative importance value computing unit, for solving the problem information of each solution case in case set according to obtain described second
The fractional value of matching degree, personal information matching degree and solution effect calculates the coupling relative importance value of each solution case, will calculate
The maximum match relative importance value arrived is as the first coupling relative importance value；Second matching unit, by corresponding for described first coupling relative importance value
Problem information and personal information are as the Second Problem information and with described first problem information and first man information matches
Two personal information.
Wherein in an embodiment, described first computing unit or the second computing unit include: age computation subunit,
For calculate the described first age of user solved in case set in the personal information of each solution case with described first
The absolute value of the difference of the age of user of people's information；Distance computation subunit, is used for calculating described first and solves in case set
The user location of the personal information of each solution case and the on-site distance of user in described first man information；Individual
Information matches subelement, for personal information according to the absolute value of the difference of calculated age of user and described user place
The distance on ground determine described first solve in case set the personal information of each solution case and described first man information it
Between matching degree.
Wherein in an embodiment, described system also includes: feedback module, is used for obtaining user to described solution
Feedback, determine the fractional value of the solution effect corresponding with described solution according to described feedback；Add module, for by institute
State the fractional value of first problem information, first man information, the described solution of recommendation and described solution effect as one
Solve case to add to described knowledge base, when the quantity solving case in described knowledge base reaches the first predetermined threshold value, shape
Become big data knowledge storehouse.
Above-mentioned solution recommends method and system, by obtaining problem information and the personal information of user, by user's
Problem information is as first problem information, using the personal information of user as first man information, then by first problem information
And first man information mates with the problem information in knowledge base and personal information, determine and first problem information and first
The Second Problem information of personal information coupling and the second personal information, and then obtain and Second Problem information and the second personal information
Corresponding solution, recommends user by the solution got.Above-mentioned solution recommend method and system, by
The Second Problem information mated with problem information and the personal information of user of search and the second personal information in knowledge base, thus really
The fixed solution that can solve customer problem, then recommends user by the program, it is achieved that obtain the timely of solution
Property and agility, and due to the method and system be no longer dependent on individual subjective experience, but according to solve problem objective
Historical data, and the personal information combining user recommends, it is recommended that solution have more reliability.
Accompanying drawing explanation
Fig. 1 is the flow chart that in an embodiment, solution recommends method；
Fig. 2 be an embodiment determines the Second Problem information with first problem information and first man information matches and
The method flow diagram of the second personal information；
Fig. 3 is to determine the Second Problem information with first problem information and first man information matches in another embodiment
And second method flow diagram of personal information；
Fig. 4 be in an embodiment calculate first solution case set in each solution case personal information with first
The method flow diagram of the matching degree of people's information；
Fig. 5 is the flow chart that in another embodiment, solution recommends method；
Fig. 6 is the structured flowchart of solution commending system in an embodiment；
Fig. 7 is the structured flowchart determining module in an embodiment；
Fig. 8 is the structured flowchart determining module in another embodiment；
Fig. 9 is the structured flowchart of computing unit in an embodiment；
Figure 10 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, personalized solution based on big data knowledge storehouse to the present invention recommends the detailed description of the invention of method and system to enter
One step describes in detail.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not used to limit this
Bright.
As it is shown in figure 1, in one embodiment it is proposed that a solution recommends method, the method includes:
Step 102, obtains problem information and the personal information of user, is believed as first problem by the problem information of user
Breath, using the personal information of user as first man information.
In the present embodiment, the acquisition of customer problem information and personal information can be obtained by terminal, such as, permissible
By problem information and the personal information of terminal input user.Wherein, terminal can be smart mobile phone, panel computer, notebook
Computer, wearable intelligent equipment etc. can be with the electronic equipments of Input information.Concrete, user can be run on terminating machine and ask
Topic management system, carries out typing by the problem information of this system of users and the personal information of user.Wherein, problem information bag
Including but be not limited to everyday problem, specialty problem etc., the personal information of user includes but not limited to the age of user, sex, place
The information such as ground.
Step 104, enters first problem information and first man information with the problem information in knowledge base and personal information
Row coupling, determines the Second Problem information with first problem information and first man information matches and the second personal information.
Concrete, first problem information is mated with each problem information in knowledge base, calculates each respectively and ask
Topic information and the matching degree of first problem information, obtain the matching degree problem information set more than predetermined threshold value, then by first
The personal information personal information corresponding with each problem information in problem information set is mated, in computational problem information aggregate
Matching degree between personal information and first man information that each problem information is corresponding, asks according in calculated knowledge base
The matching degree between matching degree and personal information and first man information between topic information and first problem information, determines and the
The Second Problem information of one problem information and first man information matches and the second personal information.Concrete, knowledge base prestores
Multiple solution case, each solution case is had to include problem information, personal information and corresponding with this problem information and personal information
Solution and solve effect fractional value.In same solution case, problem information, personal information, solution, solution
It is the most corresponding between the fractional value of effect.Determine the Second Problem letter with first problem information and first man information matches
Breath and the method for the second personal information have multiple, in one embodiment, first by each with knowledge base of first problem information
The problem information of individual solution case mates, and obtains the matching degree the first solution case set more than the first predetermined threshold value, so
Rear calculating first solves the personal information of each solution case and the matching degree of first man information in case set, obtains coupling
Degree, more than the second solution case set of the second predetermined threshold value, then obtains each solution case in the second solution case set
Solve the fractional value of effect, using problem information corresponding for solution effect maximum for fractional value and personal information as with first problem
The Second Problem information of information and first man information matches and the second personal information.In another embodiment, by first
Problem information mates with the problem information of the piecemeal solution case in knowledge base, obtains matching degree more than the first predetermined threshold value
The first solution case set, then calculate the personal information of each solution case and first man in the first solution case set
The matching degree of information, obtains the matching degree the second solution case set more than the second predetermined threshold value, then obtains the second solution case
The fractional value of the solution effect of each solution case in example set, finally according to each solution in the second solution case set obtained
The certainly matching degree of the problem information of case and first problem information, personal information and the matching degree of first man information and corresponding
The fractional value solving effect calculates the coupling relative importance value of each solution case, using calculated maximum match relative importance value as the
One coupling relative importance value, using the first coupling problem information corresponding to relative importance value and personal information as with first problem information and first
The Second Problem information of personal information coupling and the second personal information.
Step 106, obtains the solution corresponding with Second Problem information and the second personal information.
Concrete, knowledge base has prestored substantial amounts of solution case, each solution case includes problem information, individual
Information and the solution corresponding with this problem information and personal information, the fractional value of solution effect.Wherein, dividing of effect is solved
Numerical value reflects the quality solving effect, and fractional value is the highest, illustrates to solve effect the best.Be calculated with first problem information and
After the Second Problem information of first man information matches and the second personal information, obtain and this Second Problem information and second people
The solution that information is corresponding.Owing to first asks between information and personal information and Second Problem information and the second personal information
Matching degree is maximum, and its similarity is the most maximum, it is possible to the solution solving Second Problem information has the biggest probability can solve to use
The problem at family, therefore can utilize the solution of Second Problem information to come for user's answering questions.
Step 108, recommends user by the solution got.
Concrete, the solution that the problem information with user got and personal information mate can be recommended this
User.The information of solution can be by network push to user, it is also possible to be sent to and user couple by the form of note
The terminal answered, it is also possible to be sent to user by forms such as mails.User is received for problem information that is first of this user and asks
After the solution of topic information, this solution can be marked, by user's according to the solution effect of this solution
Mark as the fractional value of the solutions effect corresponding with solution, then by first problem information and for first problem letter
Solution and the fractional value of solution effect that breath is recommended add in knowledge base together as a new solution case, make to know
Know storehouse the most perfect.
In the present embodiment, by obtaining the problem information of user and personal information, using the problem information of user as the
One problem information, using the personal information of user as first man information, then by first problem information and first man information
Mate with the problem information in knowledge base and personal information, determine and first problem information and first man information matches
Second Problem information and the second personal information, and then obtain the solution party corresponding with Second Problem information and the second personal information
Case, recommends user by the solution got.Above-mentioned solution recommends method, by search and user in knowledge base
Problem information and the Second Problem information of personal information coupling and the second personal information, so that it is determined that customer problem can be solved
Solution, then the program is recommended user, it is achieved that obtain the promptness of solution and agility, and due to this
Method and system is no longer dependent on the subjective experience of individual, but according to the objective history data of the problem of solution, and combine use
The personal information at family is recommended, it is recommended that solution have more reliability.
In one embodiment, also included before the step of the problem information and personal information that obtain user: set up and know
Know storehouse, wherein, knowledge base include multiple solution case, each solution case include problem information, personal information and with this
Problem information and solution corresponding to personal information and solve the fractional value of effect.
In the present embodiment, pre-build that knowledge base, knowledge base include multiple solution case.Each solution case is wrapped
Include problem information, personal information and the solution corresponding with this problem information and personal information and solve the fractional value of effect,
Solving the fractional value of effect for reflecting the quality of solutions effect corresponding to this solution, fractional value is the biggest, illustrate that solution is imitated
Fruit is the best, otherwise, fractional value is the least, solves effect the poorest.Fractional value derives from user's feedback to solution, user's
Feedback can be realized by scoring.In the embodiment of the present invention, knowledge base can be the big data knowledge storehouse of solution, solves
Scheme big data knowledge storehouse is structuring in knowledge engineering, easily operation, easily utilization, comprehensive organized knowledge cluster, can be with pin
Demand to professional field problem solving, use Professional knowledge representation store in computer storage, organize, manage and
The knowledge sheet set interknited used.These knowledge sheets include the theoretical knowledge relevant to professional field, factual data.Example
As, definition, theorem and operational rule and common sense knowledge etc. relevant in professional field.
As in figure 2 it is shown, in one embodiment, by the problem in first problem information and first man information and knowledge base
Information and personal information are mated, and determine the Second Problem information with first problem information and first man information matches and
The step of two personal information includes:
Step 104A, mates the problem information of first problem information with the piecemeal solution case in knowledge base, obtains
Take the matching degree the first solution case set more than the first predetermined threshold value.
In the present embodiment, the problem information of first problem information with the piecemeal solution case in knowledge base is carried out one by one
Coupling, and calculate the matching degree between each problem information and first problem information, then according to calculated matching degree, obtain
Take all problems information more than the first predetermined threshold value, using solution case corresponding for all problems information that gets as first
Solve case.The span of the predetermined threshold value of matching degree is between 0 to 1.The method calculating matching degree can have multiple, than
As, can mate according to key word, using the key word number that the match is successful as matching degree.Wherein, key word is being carried out
During coupling, using key word as character string, both can use the accurate coupling of character string, it would however also be possible to employ fuzzy of character string
Join.Concrete, the key word in extraction first problem information, as the first key word, then utilizes the first key word and knowledge base
In problem information mate, the key word number of coupling is the most, and corresponding matching degree is the biggest, by matching degree more than preset
The problem information of threshold value (such as, 80%) all collects one problem information set of composition.In another embodiment, from
In the problem information of the user obtained, extracting keywords is as the first key word, solves asking in case from big data knowledge storehouse
In topic information, extracting keywords is as the second key word, customer problem information with in knowledge base each problem information mate reality
On be exactly the first key word and the second key word mates, and by the key word number that the match is successful in the first key word number
Accounting is as corresponding matching degree.Such as, the number of times of the first key word extracted from the problem information of user is 10, then
If the key word in certain problem information in data base has 7 and the success of the first Keywords matching, then this problem information
It is exactly 70% with the matching degree of first problem information.
Step 104B, calculates personal information and the first man information of each solution case in the first solution case set
Matching degree, obtains the matching degree the second solution case set more than the second predetermined threshold value.
In the present embodiment, the problem information of the piecemeal solution case in first problem information and knowledge base is carried out
Join, after obtaining the first solution case set that matching degree is more than the first predetermined threshold value, solve each solution in case set by first
Certainly the personal information of case is mated with first man information, by calculating each solution case in the first solution case set
The matching degree of personal information and first man information, obtain the matching degree the second solution casebook more than the second predetermined threshold value
Close.Concrete, personal information includes but not limited to the information such as age of user, sex, user location.Mate between personal information
The calculating of degree has multiple, in one embodiment, in calculating the first solution case set in the personal information of each solution case
The absolute value of difference of age of user of age of user and first man information, absolute value more novel difference in age in next year is the least,
Its corresponding matching degree is the biggest, can count the function of absolute value with matching degree inverse correlation by arranging an age difference
Calculate corresponding age-matched degree.In another embodiment, the problem of user has region feature sometimes, it is possible to logical
Cross the user location in the personal information calculating each solution case next with the on-site distance of user of first man information
Calculate corresponding location matching degree.Additionally, can consider user's to mate the personal information of user more accurately
In personal information, age matching degree and user location matching degree calculate the matching degree of personal information.
Step 104C, searches the fractional value of the solution effect of each solution case in the second solution case set.
In the present embodiment, the second solution case set more than the second predetermined threshold value of the personal information matching degree is got
After, further removing to obtain the fractional value of the solution effect of each solution case in this solution case set, fractional value is the biggest, says
Bright solution effect is the best.Concrete, such as, first obtain the first solution case set more than 90% of the problem information matching degree,
Now the first problem information solved in case set is substantially all more similar with first problem information, next needs to obtain
First solves personal information and the matching degree of first man information in case set, the matching degree solution case more than 95% is made
Being the second solution case set, now in the second solution case set, not only problem information is more similar, the personal information of user
The most similar.Then remove to obtain the fractional value of the solution effect of each solution case, fractional value in the second solution case set
The biggest, illustrate to solve effect the best, illustrate that the solution of correspondence more meets the demand of user the most simultaneously.
Step 104D, using problem information corresponding for solution effect maximum for fractional value and personal information as with described first
The Second Problem information of problem information and first man information matches and the second personal information.
In the present embodiment, the mark of the solution effect that each solution case is corresponding in the second solution case set is got
After value, by comparing the fractional value of the solution effect of piecemeal solution case, by problem corresponding for the solution effect of fractional value maximum
Information is as the Second Problem information and the second personal information with first problem information and first man information matches, and then obtains
The solution corresponding with this Second Problem information and the second personal information, recommends user by this solution.
As it is shown on figure 3, in one embodiment, by the problem in first problem information and first man information and knowledge base
Information and personal information are mated, and determine the Second Problem information with first problem information and first man information matches and
The step of two personal information includes:
Step 104a, is carried out the problem information of the piecemeal solution case in first problem information and described knowledge base
Join, obtain the matching degree the first solution case set more than the first predetermined threshold value.
In the present embodiment, the problem information of first problem information with the piecemeal solution case in knowledge base is carried out one by one
Coupling, and calculate the matching degree between each problem information and first problem information, then according to calculated matching degree, obtain
Take all problems information more than the first predetermined threshold value, using solution case corresponding for all problems information that gets as first
Solve case.The span of the predetermined threshold value of matching degree is between 0 to 1.The method calculating matching degree can have multiple, than
As, can mate according to key word, using the key word number that the match is successful as matching degree.Wherein, key word is being carried out
During coupling, using key word as character string, both can use the accurate coupling of character string, it would however also be possible to employ fuzzy of character string
Join.Concrete, the key word in extraction first problem information, as the first key word, then utilizes the first key word and knowledge base
In problem information mate, the key word number of coupling is the most, and corresponding matching degree is the biggest, by matching degree more than preset
The problem information of threshold value (such as, 80%) all collects one problem information set of composition.In another embodiment, from
In the problem information of the user obtained, extracting keywords is as the first key word, solves asking in case from big data knowledge storehouse
In topic information, extracting keywords is as the second key word, customer problem information with in knowledge base each problem information mate reality
On be exactly the first key word and the second key word mates, and by the key word number that the match is successful in the first key word number
Accounting is as corresponding matching degree.Such as, the number of times of the first key word extracted from the problem information of user is 10, then
If the key word in certain problem information in data base has 7 and the success of the first Keywords matching, then this problem information
It is exactly 70% with the matching degree of first problem information.
Step 104b, calculates personal information and the first man information of each solution case in the first solution case set
Matching degree, obtains the matching degree the second solution case set more than the second predetermined threshold value.
In the present embodiment, the problem information of the piecemeal solution case in first problem information and knowledge base is carried out
Join, after obtaining the first solution case set that matching degree is more than the first predetermined threshold value, solve each solution in case set by first
Certainly the personal information of case is mated with first man information, by calculating each solution case in the first solution case set
The matching degree of personal information and first man information, obtain the matching degree the second solution casebook more than the second predetermined threshold value
Close.Concrete, personal information includes but not limited to the information such as age of user, user location.Matching degree between personal information
Calculating has multiple, in one embodiment, calculates the use in the personal information of each solution case in the first solution case set
The absolute value of the difference of the age of user of family age and first man information, absolute value more novel difference in age in next year is the least, its phase
The matching degree answered is the biggest, the function of absolute value with matching degree inverse correlation by arranging an age difference can calculate phase
The age-matched degree answered.In another embodiment, the problem of user has region feature sometimes, it is possible to by meter
On-site distance calculates with the user of first man information to calculate the user location in the personal information of each solution case
Corresponding location matching degree.Additionally, the individual of user can be considered in order to mate the personal information of user more accurately
In information, age matching degree and user location matching degree calculate the matching degree of personal information.
Step 104c, searches the fractional value of the solution effect of each solution case in the second solution case set.
In the present embodiment, the second solution case set more than the second predetermined threshold value of the personal information matching degree is got
After, further removing to obtain the fractional value of the solution effect of each solution case in this solution case set, fractional value is the biggest, says
Bright solution effect is the best.
Step 104d, according to the problem information matching degree, individual of each solution case in the second solution case set obtained
The fractional value of people's information matches degree and solution effect calculates the coupling relative importance value of each solution case, by calculated maximum
Join relative importance value as the first coupling relative importance value.
In the present embodiment, the problem information matching degree of each solution case, individual in the second solution case set is obtained
Information matches degree and the fractional value of solution effect, use each solution case in average weighted method computational problem information aggregate
Coupling relative importance value.Concrete, the matching degree of problem information is set to P1, the matching degree of personal information is set to P2, will solve
The fractional value of effect is set to P3, and the weight parameter being then respectively provided with problem information matching degree P1 is k1, personal information matching degree
The weight parameter of P2 is k2, and the weight parameter of the fractional value P3 solving effect is k3.Wherein, k1+k2+k3=1, k1, k2, k3 are
The number of 1 it is less than more than 0.The matching degree relative importance value of the most each solution case is P1*k1+P2*k2+P3*k3.Then will calculate
The maximum coupling relative importance value arrived is as the first coupling relative importance value.
Step 104e, believes problem information corresponding for the first coupling relative importance value and personal information as with described first problem
Breath and the Second Problem information of first man information matches and the second personal information.
Concrete, using the coupling relative importance value of calculated maximum as the first coupling relative importance value, then obtain with this
One coupling problem information corresponding to relative importance value and personal information, problem information that this first coupling relative importance value is corresponding and personal information
Second Problem information and the second personal information as first problem information and first man information matches.
As shown in Figure 4, in one embodiment, the personal information of each solution case in the first solution case set is calculated
With the matching degree of first man information, obtain the matching degree step bag more than the second solution case set of the second predetermined threshold value
Include:
Step 402, the age of user calculated in the first solution case set in the personal information of each solution case and institute
State the absolute value of the difference of the age of user of first man information.
Concrete, personal information includes the information such as the age of user, sex, user location.Get problem information
After degree of joining is more than the first solution case set of the first predetermined threshold value, obtain each solution case in the first solution case set
Age of user in personal information, and compare with the age of user of first man information, it is calculated each solution case
Personal information in age of user and the age of user of first man information between the absolute value of difference.Such as, if obtaining
First user information in age of user be 36 years old, one of them age of user solved in the personal information in case is 32
Year, then the difference at both ages is 32-36=-4, and the absolute value of difference is exactly 4 years old.
Step 404, calculates user location and the institute of the personal information of each solution case in the first solution case set
State the on-site distance of the user in first man information.
In the present embodiment, the user place of the personal information of each solution case in the first solution case set is obtained
Ground, and compare with the user location in first man information, calculate distance between the two.Concrete, the meter of distance
Calculation can use fuzzy estimation, such as, if both are respectively in two cities, then can be by the distance between two cities
Distance as both.If both are in the zones of different in same city, then can using the distance between two regions as
Both distances, if both are at same city the same area, then it is believed that both distances are close, can be set to close
In the positive number of 0.
Step 406, absolute value and the on-site distance of user according to the difference of calculated age of user determine
One solves the matching degree in case set between personal information and the first man information of each solution case.
In the present embodiment, after being calculated absolute value and the on-site distance of user of the difference of age of user, according to
In functional relationship calculating the first solution case set preset between personal information and the first man information of each solution case
Matching degree.Concrete, it is assumed that the absolute value of the difference of calculated age of user is X, and the on-site distance of user is Y,
So personal information matching degree can be expressed as the function of X and Y, i.e. f (X, Y), and wherein, X and Y is greater than or equal to the number of 0,
And X function f (X, Y) becomes inverse correlation, Y function f (X, Y) also becomes inverse correlation.It is to say, the absolute value of age difference is more
Greatly, its matching degree is the least, and distance is the biggest, and its matching degree is the least, otherwise, the absolute value of age difference is the least, and distance is more
Little, the matching degree of the personal information of its correspondence is the biggest.
As it is shown in figure 5, in one embodiment, above-mentioned solution recommends method also to include:
Step 110, obtains user's feedback to solution, determines the solution corresponding with solution according to described feedback
The fractional value of effect.
In the present embodiment, obtain the feedback of user's solution to recommending, determine according to the feedback of user and solve
The certainly fractional value of the solution effect that scheme is corresponding.Concrete, the feedback of user can be with directly by the form of marking, such as full marks
Being 100 points, suggested design is given a mark by effect according to solving accordingly, then using the marking of user as solution effect
Fractional value.Then the satisfaction of user can also be converted to accordingly by obtaining user's satisfaction to solution
Mark store, concrete, it is assumed that satisfaction is divided into five kinds, be to be satisfied with very much respectively, satisfied, general as, dissatisfied,
The most dissatisfied, pre-set every kind of fractional value corresponding to satisfaction, such as, very satisfied corresponding fractional value is 100 points,
Satisfied corresponding fractional value is 80 points, general as corresponding fractional value be 60 points, dissatisfied corresponding fractional value is 30 points, very
Dissatisfied corresponding mark is 0 point.Such as, as solution is evaluated as typically by user, then backstage is automatically by correspondence 60
It is allocated as the fractional value for solving effect.
Step 112, by first problem information, first man information, the solution of recommendation and the fractional value solving effect
Solve case as one to add to knowledge base, when the quantity solving case in knowledge base reaches the first predetermined threshold value, shape
Become big data knowledge 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, personal information, the solution recommended for this first problem information and individual's letter
Add to knowledge base together as a new solution case with the fractional value of above-mentioned solution effect, can not by the method
Improve knowledge base disconnectedly.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 sets
It is 10,000) time, it being the formation of big data knowledge storehouse, the quantity solving case in big data knowledge storehouse is the biggest, can find and more mate
The probability of problem information the biggest.Thus, it is recommended that solution also can be more and more reliable.
As shown in Figure 6, in one embodiment it is proposed that a solution commending system, this system includes:
Data obtaining module 602, for obtaining problem information and the personal information of user, by the problem information of described user
As first problem information, using the personal information of described user as first man information；
Determine module 604, for by the problem in described first problem information and described first man information and knowledge base
Information and personal information are mated, and determine the Second Problem information with described first problem information and first man information matches
And second personal information；
Solution acquisition module 606, for obtaining the solution corresponding with described Second Problem information and the second personal information
Certainly scheme；
Recommending module 608, for recommending described user by the described solution got.
In one embodiment, above-mentioned solution recommendation apparatus also includes: set up module, is used for setting up knowledge base, institute
State knowledge base include multiple solution case, described solution case include problem information, personal information and with described problem information and
Solution corresponding to personal information and solve the fractional value of effect.
As it is shown in fig. 7, in one embodiment, determine that module includes:
First acquiring unit 604A, for by described first problem information and the piecemeal solution case in described knowledge base
Problem information mates, and obtains the matching degree the first solution case set more than the first predetermined threshold value；
First computing unit 604B, solves the personal information of each solution case in case set for calculating described first
With the matching degree of described first man information, obtain the matching degree the second solution case set more than the second predetermined threshold value；
First searches unit 604C, solves the solution effect of each solution case in case set for searching described second
Fractional value；
First matching unit 604D, the problem information corresponding for the solution effect that described fractional value is maximum and individual's letter
Breath is as the Second Problem information and the second personal information with described first problem information and first man information matches.
As shown in Figure 8, in one embodiment, determine that module includes:
Second acquisition unit 604a, for by described first problem information and the piecemeal solution case in described knowledge base
Problem information mates, and obtains the matching degree the first solution case set more than the first predetermined threshold value；
Second computing unit 604b, solves the personal information of each solution case in case set for calculating described first
With the matching degree of described first man information, obtain the matching degree the second solution case set more than the second predetermined threshold value；
Second searches unit 604c, solves the solution effect of each solution case in case set for searching described second
Fractional value；
Coupling relative importance value computing unit 604d, for solving each solution case in case set according to obtain described second
The coupling that the fractional value of the problem information matching degree of example, personal information matching degree and solution effect calculates each solution case is preferential
Degree, using calculated maximum match relative importance value as the first coupling relative importance value；
Second matching unit 604e, using described first coupling problem information corresponding to relative importance value and personal information as with institute
State Second Problem information and second personal information of first problem information and first man information matches.
As it is shown in figure 9, in one embodiment, the first computing unit includes:
Age computation subunit 902, for calculating the described first individual's letter solving each solution case in case set
The absolute value of the difference of the age of user of the age of user in breath and described first man information；
Distance computation subunit 904, for calculating the described first individual's letter solving each solution case in case set
The user location of breath and the on-site distance of user in described first man information；
Personal information coupling subelement 906, for absolute according to the difference of calculated age of user of personal information
Value and the on-site distance of described user determine the described first personal information solving each solution case in case set and institute
State the matching degree between first man information.
As shown in Figure 10, in one embodiment, above-mentioned solution commending system also includes:
Feedback module 610, for obtaining user's feedback to described solution, determines and described solution according to described feedback
The certainly fractional value of the solution effect that scheme is corresponding；
Add module 612, for by described first problem information, first man information, the described solution of recommendation and
The fractional value of described solution effect solves case as one to be added to described knowledge base, when solving case in described knowledge base
Quantity when reaching the first predetermined threshold value, form big data knowledge storehouse.
For a solution commending system being better understood from and apply the present invention to propose, carry out the example below, need
It is noted that the scope that the present invention is protected does not limits to the example below.
Concrete, the problem information obtaining party a subscriber is: the most what if stung by mosquito？；Personal information: 26 years old, female
Property, location are Guangzhou.First, the problem information of piecemeal solution case in the problem information of party a subscriber and knowledge base is carried out
Joining, obtain the matching degree the first solution case set more than the first predetermined threshold value (such as, 80%), now, first solves case
The most what if problem information in set all " has been stung " similar or identical with the problem information of party a subscriber by mosquito.Then one is entered
Walk and the personal information of party a subscriber is mated with the first personal information solving each solution case in case set, due to
The possible difference of reaction of all ages and classes, different sexes after having been stung by mosquito, and the mosquito of different regions also has difference, is snapped
The reaction that after, skin occurs is the most different.Believe so needing to calculate personal information in each solution case with the individual of party a subscriber
The matching degree of breath.Concrete computational methods can obtain the matching degree at age, the matching degree of sex, on-site of user respectively
Degree of joining, then consider the age, sex, three factors in location matching degree to calculate the matching degree of personal information.Obtain
The matching degree of personal information is more than the second solution case set of the second predetermined threshold value (such as, 90%), now, the second solution case
In example set, not only problem information is same or similar with the problem information of party a subscriber, and personal information is believed with the individual of party a subscriber
Cease the most same or similar.Afterwards, obtain the fractional value of the solution effect that each solution case is corresponding in the second solution case set,
Assume one of them solve case solution be: smear in the place stung by mosquito suds can reach antipruritic disappear red
Swollen.The fractional value of the solution effect of the program is 100 points to the maximum.The most just the program is recommended as best solution
Party a subscriber.
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 relevant 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
In contradiction, all it is 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 also
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, it is also possible to make some deformation and improvement, 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 problem information and the personal information of user, using the problem information of described user as first problem information, by described
The personal information of user is as first man information；
Described first problem information and described first man information and the problem information in knowledge base and personal information are carried out
Join, determine and described first problem information and the Second Problem information of first man information matches and the second personal information；
Obtain the solution corresponding with described Second Problem information and the second personal information；
The described solution got is recommended described user.
Method the most according to claim 1, it is characterised in that in the described problem information of user and the personal information of obtaining
Also include before step:
Set up knowledge base, described knowledge base include multiple solution case, described solution case include problem information, personal information,
And the solution corresponding with described problem information and personal information and solve effect fractional value.
Method the most according to claim 2, it is characterised in that described by described first problem information and described first man
Information is mated with the problem information in knowledge base and personal information, determines and believes with described first problem information and first man
The Second Problem information of breath coupling and the step of the second personal information include:
The problem information of described first problem information with the piecemeal solution case in described knowledge base is mated, obtains coupling
Degree is more than the first solution case set of the first predetermined threshold value；
Calculate described first and solve the personal information of each solution case and mating of described first man information in case set
Degree, obtains the matching degree the second solution case set more than the second predetermined threshold value；
Search described second and solve the fractional value of the solution effect of each solution case in case set；
Using problem information corresponding for solution effect maximum for described fractional value and personal information as with described first problem information
And the Second Problem information of first man information matches and the second personal information.
Method the most according to claim 1, it is characterised in that described by described first problem information and described first man
Information is mated with the problem information in knowledge base and personal information, determines and believes with described first problem information and first man
The Second Problem information of breath coupling and the step of the second personal information include:
The problem information of described first problem information with the piecemeal solution case in described knowledge base is mated, obtains coupling
Degree is more than the first solution case set of the first predetermined threshold value；
Calculate described first and solve the personal information of each solution case and mating of described first man information in case set
Degree, obtains the matching degree the second solution case set more than the second predetermined threshold value；
Search described second and solve the fractional value of the solution effect of each solution case in case set；
The problem information matching degree of each solution case in case set, personal information coupling is solved according to described second obtained
The fractional value of degree and solution effect calculates the coupling relative importance value of each solution case, is made by calculated maximum match relative importance value
It it is the first coupling relative importance value；
Using described first coupling problem information corresponding to relative importance value and personal information as with described first problem information and first
The Second Problem information of personal information coupling and the second personal information.
5. according to the method described in claim 3 or 4, it is characterised in that described calculating described first solves in case set every
The matching degree of the personal information of individual solution case and described first man information, obtains matching degree more than the of the second predetermined threshold value
Two steps solving case set include:
Calculate the described first age of user solved in case set in the personal information of each solution case with described first
The absolute value of the difference of the age of user of people's information；
Calculate described first solve in case set the user location of the personal information of each solution case with described first
The on-site distance of user in people's information；
The absolute value of the difference according to calculated age of user and the on-site distance of described user determine that described first solves
Certainly matching degree between personal information and the described first man information of each solution case in case set.
Method the most according to claim 1, it is characterised in that described method also includes:
Obtain user's feedback to described solution, determine the solution effect corresponding with described solution according to described feedback
Fractional value；
By described first problem information, first man information, the described solution of recommendation and the fractional value of 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.
7. a solution commending system, it is characterised in that described system includes:
Data obtaining module, for obtaining problem information and the personal information of user, using the problem information of described user as the
One problem information, using the personal information of described user as first man information；
Determine module, for by described first problem information and described first man information and the problem information in knowledge base and individual
People's information is mated, and determines and described first problem information and the Second Problem information of first man information matches and second
People's information；
Solution acquisition module, for obtaining the solution corresponding with described Second Problem information and the second personal information；
Recommending module, for recommending described user by the described solution got.
System the most according to claim 7, it is characterised in that described determine that module includes:
First acquiring unit, for the problem information by described first problem information with the piecemeal solution case in described knowledge base
Mate, obtain the matching degree the first solution case set more than the first predetermined threshold value；
First computing unit, solves in case set the personal information of each solution case and described for calculating described first
The matching degree of one personal information, obtains the matching degree the second solution case set more than the second predetermined threshold value；
First searches unit, solves the mark of the solution effect of each solution case in case set for searching described second
Value；
First matching unit, for using problem information corresponding for solution effect maximum for described fractional value and personal information as with
Described first problem information and the Second Problem information of first man information matches and the second personal information.
System the most according to claim 8, it is characterised in that described determine that module includes:
Second acquisition unit, for the problem information by described first problem information with the piecemeal solution case in described knowledge base
Mate, obtain the matching degree the first solution case set more than the first predetermined threshold value；
Second computing unit, solves in case set the personal information of each solution case and described for calculating described first
The matching degree of one personal information, obtains the matching degree the second solution case set more than the second predetermined threshold value；
Second searches unit, solves the mark of the solution effect of each solution case in case set for searching described second
Value；
Coupling relative importance value computing unit, for solving the problem of each solution case in case set according to obtain described second
The fractional value of information matches degree, personal information matching degree and solution effect calculates the coupling relative importance value of each solution case, will meter
The maximum match relative importance value obtained is as the first coupling relative importance value；
Second matching unit, asks problem information corresponding for described first coupling relative importance value and personal information as with described first
The Second Problem information of topic information and first man information matches and the second personal information.
System the most according to claim 8 or claim 9, it is characterised in that described first computing unit or the second computing unit bag
Include:
Age computation subunit, for calculating the described first use solved in case set in the personal information of each solution case
The absolute value of the difference of the age of user of family age and described first man information；
Distance computation subunit, solves the user of the personal information of each solution case in case set for calculating described first
Location and the on-site distance of user in described first man information；
Personal information coupling subelement, for personal information according to the absolute value of the difference of calculated age of user and described
The on-site distance of user determine described first solve in case set the personal information of each solution case with described first
Matching degree between people's information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610424463.XA CN106126541B (en) | 2016-06-14 | 2016-06-14 | Personalized solution recommended method and system based on big data knowledge base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610424463.XA CN106126541B (en) | 2016-06-14 | 2016-06-14 | Personalized solution recommended method and system based on big data knowledge base |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106126541A true CN106126541A (en) | 2016-11-16 |
| CN106126541B CN106126541B (en) | 2019-07-19 |
Family
ID=57469575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610424463.XA Active CN106126541B (en) | 2016-06-14 | 2016-06-14 | Personalized solution recommended method and system based on big data knowledge base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106126541B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009795A (en) * | 2017-12-15 | 2018-05-08 | 安徽长泰信息安全服务有限公司 | A kind of E-Government IT application in management platform and method |
| CN112996024A (en) * | 2021-01-20 | 2021-06-18 | 国网西藏电力有限公司信息通信公司 | Network communication problem judgment and processing device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101441660A (en) * | 2008-12-16 | 2009-05-27 | 腾讯科技（深圳）有限公司 | Knowledge evaluating system and method in inquiry and answer community |
| CN103369009A (en) * | 2012-03-31 | 2013-10-23 | 腾讯科技（深圳）有限公司 | Method, equipment and system for online question answering |
| 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 |
| CN104572982A (en) * | 2014-12-31 | 2015-04-29 | 东软集团股份有限公司 | Personalized recommendation method and system based on question guide |
| CN104978360A (en) * | 2014-04-11 | 2015-10-14 | 俞志晨 | Realization method of question-answering system with account identity |
| CN105260598A (en) * | 2015-09-29 | 2016-01-20 | 中南大学 | Oral diagnosis and treatment decision support system and decision method |
-
2016
- 2016-06-14 CN CN201610424463.XA patent/CN106126541B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101441660A (en) * | 2008-12-16 | 2009-05-27 | 腾讯科技（深圳）有限公司 | Knowledge evaluating system and method in inquiry and answer community |
| CN103369009A (en) * | 2012-03-31 | 2013-10-23 | 腾讯科技（深圳）有限公司 | Method, equipment and system for online question answering |
| 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 |
| CN104978360A (en) * | 2014-04-11 | 2015-10-14 | 俞志晨 | Realization method of question-answering system with account identity |
| CN104572982A (en) * | 2014-12-31 | 2015-04-29 | 东软集团股份有限公司 | Personalized recommendation method and system based on question guide |
| CN105260598A (en) * | 2015-09-29 | 2016-01-20 | 中南大学 | Oral diagnosis and treatment decision support system and decision method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009795A (en) * | 2017-12-15 | 2018-05-08 | 安徽长泰信息安全服务有限公司 | A kind of E-Government IT application in management platform and method |
| CN112996024A (en) * | 2021-01-20 | 2021-06-18 | 国网西藏电力有限公司信息通信公司 | Network communication problem judgment and processing device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106126541B (en) | 2019-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106126582A (en) | Recommend method and device | |
| CN107688605B (en) | Cross-platform data matching process, device, computer equipment and storage medium | |
| CN103916436B (en) | Information-pushing method, device, terminal and server | |
| CN105912881A (en) | Individual-based treatment scheme recommendation system based on big data knowledge base | |
| CN103729359A (en) | Method and system for recommending search terms | |
| CN110033097B (en) | Method and device for determining association relation between user and article based on multiple data fields | |
| Al-Ghazali et al. | Antecedents of continuous usage intention of mobile banking services from the perspective of Delone and Mclean model of information system success | |
| CN103034963B (en) | A kind of service selection system and system of selection based on correlation | |
| CN103077177B (en) | A kind of Web service fuzzy Q oS system of selection of merging expert opinion and user preference | |
| CN107895038A (en) | A kind of link prediction relation recommends method and device | |
| CN106844407A (en) | Label network production method and system based on data set correlation | |
| Wang et al. | Personalized news recommendation based on consumers' click behavior | |
| Yang et al. | Exploring user expertise and descriptive ability in community question answering | |
| CN106095941A (en) | Recommend method and system based on the solution in big data knowledge storehouse | |
| CN105281925A (en) | Network service user group dividing method and device | |
| CN110288350A (en) | User's Value Prediction Methods, device, equipment and storage medium | |
| CN112131261B (en) | Community query method and device based on community network and computer equipment | |
| CN115270007B (en) | POI recommendation method and system based on mixed graph neural network | |
| CN112632296B (en) | Knowledge graph-based paper recommendation method and system with interpretability and terminal | |
| CN106126541A (en) | Personalized solution based on big data knowledge storehouse recommends method and system | |
| CN104408189B (en) | The methods of exhibiting and device of keyword ranking | |
| CN116611884A (en) | Product recommendation method and system based on multidimensional different-composition neural network | |
| CN114722086A (en) | Method and device for determining search rearrangement model | |
| Eisgruber | Developments in the economic theory of information | |
| CN114387103A (en) | Transaction risk identification method and device |
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 |