CN109840772A - Risk subscribers recognition methods and device - Google Patents
Risk subscribers recognition methods and device Download PDFInfo
- Publication number
- CN109840772A CN109840772A CN201711205636.XA CN201711205636A CN109840772A CN 109840772 A CN109840772 A CN 109840772A CN 201711205636 A CN201711205636 A CN 201711205636A CN 109840772 A CN109840772 A CN 109840772A
- Authority
- CN
- China
- Prior art keywords
- behavior
- risk
- individual
- user
- population
- 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.)
- Pending
Links
Abstract
The embodiment of the present application discloses recognition methods and the device of risk subscribers.One specific embodiment of this method includes: to obtain potential risk information according to the operation behavior of user to be identified, wherein potential risk information includes the user base information of user to be identified and the behavioural information of operation behavior；The risk information of multiple users is extracted, and generates multiple risk behavior individuals using genetic algorithm processing risk information, wherein risk information includes the behavioural information of the user base information of each user and the historical operation behavior of each user；Potential risk information is matched with the risk information of each risk behavior individual, to judge whether user to be identified is risk subscribers.The embodiment generates risk behavior individual using genetic algorithm, to improve the accuracy rate of risk subscribers identification.
Description
Technical field
The invention relates to field of computer technology, and in particular to Internet technical field more particularly to risk are used
Family recognition methods and device.
Background technique
With the development of internet technology, transaction (such as the product trading, service transacting between user are carried out using internet
Deng) more and more common.In order to ensure the safety traded using internet, need to identify that risk subscribers (such as are managed
The user etc. that the advertiser of fraudulent website, the businessman for managing illegal product, spurious information are cheated loan), and it is avoided to participate in business.
Traditional Risk Identification Method can take the mode of building regulation engine, to the user behavior for meeting rule definition
It carries out feature extraction and analyzes, to realize the risk identification of user.However, rule used by regulation engine usually requires people
For ground increase, it is seen that this method is affected by artificial subjective factor, is difficult objectively and impartially to identify risk subscribers.Again
Person, traditional Risk Identification Method can also take the mode of clustering, by user behavior carry out classification realize to
The risk identification at family.However, clustering needs to be arranged corresponding cluster class number k value, and this method is generally difficult to accurately
Select suitable k value in ground.
Summary of the invention
The embodiment of the present application proposes risk subscribers recognition methods and device.
In a first aspect, the embodiment of the present application provides a kind of risk subscribers recognition methods, this method comprises: according to be identified
The operation behavior of user obtains potential risk information, wherein potential risk information includes the user base information of user to be identified
With the behavioural information of operation behavior；The risk information of multiple users is extracted, and more using genetic algorithm processing risk information generation
A risk behavior individual, wherein risk information includes the user base information of each user and the historical operation behavior of each user
Behavioural information；Potential risk information is matched with the risk information of each risk behavior individual, to judge that user to be identified is
No is risk subscribers.
In some embodiments, multiple risk behavior individuals are generated using genetic algorithm processing risk information, comprising: to institute
The risk information of extraction is encoded, and the risk information after coding is combined and is generated including the initial of multiple behaviors individuals
Population；Risk information based on each user constructs fitness function, wherein fitness function is used to calculate the adaptation of behavior individual
Angle value；Genetic algorithm is executed to initial population, and when the number that genetic algorithm executes meets preset the number of iterations, is generated more
A risk behavior individual.
In some embodiments, genetic algorithm is executed to initial population, comprising: calculate initial population using fitness function
In each behavior individual fitness value, and multiple behavior individuals is selected according to fitness value to constitute non-hibernating eggs again from initial population
Group；The individual of the behavior in population will be regenerated and carry out crossing operation each other, generate cross-species；To the behavior in cross-species
Individual carries out mutation operator, generates variation population.
In some embodiments, multiple behavior individuals is selected to constitute regeneration population from initial population according to fitness value,
It include: the selection operator using genetic algorithm, the fitness value calculation initial population based on each behavior individual in initial population
In each behavior individual by select probability；To being summed by selection Cumulative probability for behavior individual each in initial population, obtain just
Each behavior individual is accumulative by select probability in beginning population；The random number between 0 to 1 is generated, and by random number and each behavior
The accumulative of individual is compared to determine each behavior individual for constituting regeneration population by select probability.
In some embodiments, the individual progress crossing operation each other of the behavior in population will be regenerated, generates and intersects kind
Group, comprising: determine the crossover probability of crossing operation, and several pairs of behavior individuals are extracted from regeneration population based on crossover probability
It is right；To each behavior individual extracted to crossover operation is executed, the cross-species including multiple behavior individuals are generated.
In some embodiments, mutation operator is carried out to the behavior individual in cross-species, generates variation population, comprising:
The mutation probability of definitive variation operation, and be binary coding by the code conversion of each behavior individual in cross-species；From friendship
The behavior individual chosen in population for variation is pitched, and to any volume in the binary coding of selected each behavior individual
Code carries out inversion operation, generates variation population, wherein variation population includes multiple risk behavior individuals.
In some embodiments, method further include: when the number that genetic algorithm executes meets preset the number of iterations, ring
The risk behavior individual that Ying Yu is detected is unsatisfactory for preset condition, resets the number of iterations.
In some embodiments, potential risk information is matched with the risk information of each risk behavior individual, to sentence
Whether user to be identified of breaking is risk subscribers, comprising: carries out the risk information of potential risk information and each risk behavior individual
Matching obtains matching degree, and judges whether matching degree is greater than preset threshold；If so, determining that user to be identified is risk subscribers；
If not, it is determined that user to be identified is normal users.
Second aspect, the embodiment of the present application provide a kind of risk subscribers identification device, and device includes: acquiring unit, match
It sets for obtaining potential risk information according to the operation behavior of user to be identified, wherein potential risk information includes use to be identified
The user base information at family and the behavioural information of operation behavior；Generation unit is configured to extract the risk information of multiple users,
And multiple risk behavior individuals are generated using genetic algorithm processing risk information, wherein risk information includes the user of each user
The behavioural information of the historical operation behavior of basic information and each user；Matching unit is configured to potential risk information and each
The risk information of risk behavior individual is matched, to judge whether user to be identified is risk subscribers.
In some embodiments, generation unit includes: coding module, is configured to compile extracted risk information
Code, and the risk information after coding is combined and generates the initial population including multiple behavior individuals；Constructing module, configuration are used
Fitness function is constructed in the risk information based on each user, wherein fitness function is used to calculate the fitness of behavior individual
Value；Generation module is configured to execute initial population genetic algorithm, and meets preset change in the number that genetic algorithm executes
When generation number, multiple risk behavior individuals are generated.
In some embodiments, generation module includes: computational submodule, is configured to calculate using fitness function initial
The fitness value of each behavior individual in population, and select multiple behavior individuals to constitute regeneration from initial population according to fitness value
Population；Intersect submodule, is configured to regenerate the individual progress crossing operation each other of behavior in population, generates and intersect kind
Group；Make a variation submodule, is configured to carry out mutation operator to the behavior individual in cross-species, generates variation population.
In some embodiments, computational submodule is further configured to: using the selection operator of genetic algorithm, based on just
Each behavior individual by select probability in the fitness value calculation initial population of each behavior individual in beginning population；To initial kind
Each behavior is individual in group is summed by selection Cumulative probability, and each behavior individual adds up by selection generally in acquisition initial population
Rate；The random number between 0 to 1 is generated, and random number and each the accumulative of behavior individual are compared to determine by select probability
Constitute each behavior individual of regeneration population.
In some embodiments, intersect submodule to be further configured to: determining the crossover probability of crossing operation, and be based on
It is right that crossover probability extracts several pairs of behavior individuals from regeneration population；To each behavior individual extracted to execute crossover operation,
Generate the cross-species including multiple behavior individuals.
In some embodiments, variation submodule is further configured to: the mutation probability of definitive variation operation, and will be handed over
The code conversion for pitching each behavior individual in population is binary coding；The behavior for variation is chosen from cross-species
Body, and inversion operation is carried out to binary-coded any coding of selected each behavior individual, variation population is generated,
In, variation population includes multiple risk behavior individuals.
In some embodiments, device further include: setting unit, the number for being configured to execute when genetic algorithm meet pre-
If the number of iterations when, be unsatisfactory for preset condition in response to the risk behavior individual detected, reset the number of iterations.
In some embodiments, matching unit is further configured to: by potential risk information and each risk behavior individual
Risk information matched, obtain matching degree, and judge whether matching degree is greater than preset threshold；If so, determination is to be identified
User is risk subscribers；If not, it is determined that user to be identified is normal users.
Risk subscribers recognition methods provided by the embodiments of the present application and device, can be with by the operation behavior of user to be identified
The corresponding potential risk information of the user to be identified is obtained, the risk information of multiple users is then extracted, at genetic algorithm
Reason risk information generates multiple risk behavior individuals for risk subscribers match cognization, finally can be by the latent of user to be identified
It is matched with each risk behavior individual in risk information to judge whether user to be identified is risk subscribers, to improve risk use
The accuracy rate of family identification.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 shows that this application can be applied to exemplary system architecture figures therein；
Fig. 2 shows the flow charts according to one embodiment of the risk subscribers recognition methods of the application；
Fig. 3 shows the flow chart of another embodiment of the risk subscribers recognition methods according to the application；
Fig. 4 shows the structural schematic diagram of one embodiment of the risk subscribers identification device according to the application；
Fig. 5 shows the structure of the computer system of the terminal device or server that are suitable for being used to realize the embodiment of the present application
Schematic diagram.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the embodiment of the risk subscribers recognition methods or risk subscribers identification device of the application
Exemplary system architecture 100.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications, such as the application of shopping class, net can be installed on terminal device 101,102,103
The application of page browsing device, searching class application, instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be with display screen and support the operation behaviors such as user's click, browsing
Various electronic equipments, including but not limited to smart phone, tablet computer, E-book reader, MP3 player (Moving
Picture Experts Group Audio Layer III, dynamic image expert's compression standard audio level 3), MP4
(Moving Picture Experts Group Audio Layer IV, dynamic image expert's compression standard audio level 4) is broadcast
Put device, pocket computer on knee and desktop computer etc..
Server 105 can be to provide the server of various services, such as terminal device 101,102,103 is received
The operation behaviors such as click, browsing provide the background server supported.Background server can operation row to the user received
For etc. be analyzed and processed, and processing result (such as risk identification result of user to be identified) is fed back into terminal device.
It should be noted that risk subscribers recognition methods provided by the embodiment of the present application is generally executed by server 105,
Correspondingly, risk subscribers identification device is generally positioned in server 105.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, the process 200 of one embodiment of the risk subscribers recognition methods according to the application is shown.
Risk subscribers recognition methods in the embodiment, comprising the following steps:
Step 201, potential risk information is obtained according to the operation behavior of user to be identified.
In the present embodiment, electronic equipment (such as the service shown in FIG. 1 of risk subscribers recognition methods operation thereon
Device) user to be identified click on the terminal device, browsing can be obtained by wired connection mode or radio connection
Etc. operation behaviors, and analyze user to be identified operation behavior obtain potential risk information.Specifically, above-mentioned electronic equipment can be with
The user base information of user to be identified is obtained, which may include such as IP address, role, the pet name of user
Deng；And the electronic equipment can obtain corresponding behavior according to operation behaviors such as click, the browsings of above-mentioned user to be identified and believe
Breath, e.g., during browsing on commodity website and buying commodity, user is browsed on commodity website user by terminal device
While commodity (that is, user performs browse operation), the corresponding user of user's browse operation is can be generated in above-mentioned electronic equipment
Browsing behavior information, and the browsing behavior information of the user is obtained, user pays 100RMB (that is, user performs delivery operation)
While, the corresponding customer transaction behavioural information of user's delivery operation can be generated in above-mentioned electronic equipment, and obtains the user's
Trading activity information.The potential risk information that above-mentioned electronic equipment obtains may include user to be identified user base information and
The behavioural information of operation behavior.It should be pointed out that above-mentioned radio connection can include but is not limited to 3G/4G connection,
WiFi connection, bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection and other now
The radio connection known or developed in the future.
Step 202, the risk information of multiple users is extracted, and generates multiple risks using genetic algorithm processing risk information
Behavior individual.
In the present embodiment, the risk information of the available multiple users of above-mentioned electronic equipment, risk information here can
With include each user user base information and each user historical operation behavior behavioural information.Specifically, above-mentioned electronics is set
It is standby to determine multiple users first, it then obtains and determines the corresponding user base information of user, IP address, angle such as user
Color, pet name etc., while above-mentioned electronic equipment can also obtain corresponding behavioural information according to the historical operation behavior of each user, such as
The browsing behavior information of user, the History Order information generated based on user's operation etc..The above-mentioned extracted risk of electronic equipment
Information may include the behavioural information of the user base information of each user and the historical operation behavior of each user.Finally, above-mentioned electricity
Sub- equipment can use genetic algorithm and handle its extracted risk information, to generate multiple risk behavior individuals.Therefore, this
In risk behavior individual can accordingly include through the processed risk information of genetic algorithm.
It is understood that above-mentioned electronic equipment can determine the type of user to be identified and the behaviour of user to be identified first
Make the type of behavior, can then be determined according to the type of user to be identified and the type of operation behavior for extracting risk information
User and extracted risk information, i.e., above-mentioned electronic equipment can extract with potential risk information have general character risk believe
Breath.Further, when above-mentioned electronic equipment judges that the user to be identified is wind based on the potential risk information of user to be identified
When dangerous user, which can be intercepted the operation of user to be identified, when above-mentioned electronic equipment is based on use to be identified
When the potential risk information at family judges that the user to be identified is normal users, which can be to the behaviour of user to be identified
Make normal execute.
Step 203, potential risk information is matched with the risk information of each risk behavior individual, it is to be identified to judge
Whether user is risk subscribers.
In the present embodiment, the risk behavior of the potential risk information and step 202 generation that are obtained based on step 201
Body, the wind that above-mentioned electronic equipment can will be handled included by potential risk information and each risk behavior individual by genetic algorithm
Dangerous information matches, and determines whether above-mentioned user to be identified is risk subscribers according to matching result.As an example, above-mentioned electronics
Equipment can correspondingly obtain potential risk information after matching potential risk information with the risk information of each risk behavior individual
With the similarity of the risk information of each risk behavior individual, and according to the value of similarity determine user to be identified whether be risk use
Family；Alternatively, above-mentioned electronic equipment can also match potential risk information in the risk information of each risk behavior individual, and according to
Whether the information content for the potential risk information being matched in the risk information of each risk behavior individual determines the user to be identified
For risk subscribers.
Risk subscribers recognition methods provided by above-described embodiment of the application, can by the operation behavior of user to be identified
To obtain the corresponding potential risk information of the user to be identified, the risk information of multiple users is then extracted, and calculate using heredity
Method handles risk information and generates multiple risk behavior individuals, finally can be by the potential risk information of user to be identified and each risk
Behavior individual matches to judge whether user to be identified is risk subscribers, to improve the accuracy rate of risk subscribers identification.
With continued reference to FIG. 3, it illustrates the processes according to another embodiment of the risk subscribers recognition methods of the application
300.Risk subscribers recognition methods in the embodiment may comprise steps of:
Step 301, potential risk information is obtained according to the operation behavior of user to be identified.
In the present embodiment, electronic equipment (such as the service shown in FIG. 1 of risk subscribers recognition methods operation thereon
Device) user to be identified click on the terminal device, browsing can be obtained by wired connection mode or radio connection
Etc. operation behaviors, and analyze user to be identified operation behavior obtain potential risk information.Specifically, above-mentioned electronic equipment can be with
The user base information of user to be identified is obtained, which may include such as IP address, role, the pet name of user
Deng；And the electronic equipment can obtain corresponding click according to operation behaviors such as click, the browsings of above-mentioned user to be identified and go
For information and browsing behavior information etc..Above-mentioned electronic equipment obtains user's base that potential risk information may include user to be identified
The behavioural information of plinth information and operation behavior.
Step 302, the risk information for extracting multiple users encodes extracted risk information, and will be after coding
Risk information be combined generate include multiple behavior individuals initial population.
In the present embodiment, above-mentioned electronic equipment can determine multiple users first, and be extracted according to identified user
The behavioural information of the historical operation behavior of the user base information of each user and each user.Then, above-mentioned electronic equipment can select
Suitable coding mode is taken to encode extracted risk information.Here, the coding mode of risk information may include but
It is not limited to gray encoding, real coding etc..Finally, above-mentioned electronic equipment can be by the risk information random coded group after coding
It closes, generates initial population F0.Initial population F0It may include multiple behavior individuals, such as initial population F0It may include n behavior
Individual, i.e. F0={ x1,x2,x3...xn, wherein n is positive integer.
Step 303, the risk information based on each user constructs fitness function, calculates initial population using fitness function
In each behavior individual fitness value.
In the present embodiment, above-mentioned electronic equipment can construct fitness function S (x based on the risk information of each useri),
Fitness function S (xi) it can be used for calculating behavior individual xiFitness value.Therefore, above-mentioned electronic equipment can be by each row
Fitness function S (x is inputted as variable for the risk information of individuali), to calculate the fitness value of each behavior individual.?
In genetic algorithm, fitness value can be the main indicator that lines of description is individual performance.It, can be right according to the size of fitness value
Each behavior individual is selected the superior and eliminated the inferior.Optionally, preset the number of iterations can also be arranged for genetic algorithm in above-mentioned electronic equipment,
So that multiple risk behavior individuals can be generated after executing preset the number of iterations in genetic algorithm.
Step 304, multiple behavior individuals is selected to constitute regeneration population from initial population according to fitness value.
In the present embodiment, the fitness value based on the calculated each behavior individual of step 303, above-mentioned electronic equipment can be with
Handle each behavior individual using the fitness value of each behavior individual, in order to its can be selected from initial population it is multiple outstanding
Behavior individual constitutes regeneration population F1, the regeneration population F1It may include from initial population F0In select multiple behaviors individual,
Such as initial population F1It may include m behavior individual, i.e. F1={ x1,x2,x3...xm, wherein m is positive integer.
In general, the purpose of the selection step in genetic manipulation is the mode of the natural imitation circle survival of the fittest, it is initial from currently
Outstanding individual is selected in population, it is replicated and retains generation regeneration population, for carrying out heredity as parent.
Specifically, above-mentioned electronic equipment can choose suitable genetic algorithm selection operator first, such as ratio selection is calculated
Son utilizes initial population F0In the fitness value calculation of each behavior individual initial population F0In each behavior individual it is selected
Select probability.Then, above-mentioned electronic equipment can be to initial population F0In each behavior individual asked by selection Cumulative probability
With obtain initial population F0In each behavior individual it is accumulative by select probability.Finally, above-mentioned electronic equipment can produce 0 to 1
Between random number, and the random number is compared with calculated the accumulative of each behavior individual by select probability, thus really
It is scheduled on the behavior individual selected in initial population, and selected each behavior individual is constituted into regeneration population F1。
As an example, when above-mentioned electronic equipment calculates initial population F using ratio selection operator0={ x1,x2,x3...xn}
Each behavior individual by select probability when, can be such that by the calculation formula of select probability
Wherein, S (xi) be initial population in i-th of behavior individual xiFitness value, S (xj) be initial population in j-th
Behavior individual xjFitness value, P (xi) be initial population in i-th of behavior individual xiBy select probability, i and j are positive whole
Number.Therefore, above-mentioned electronic equipment, which can use, above-mentioned calculates initial population F by the calculation formula of select probability0In each behavior
Individual by select probability.Then, above-mentioned electronic equipment can calculate initial population F0In the accumulative of each behavior individual selected
Probability, the accumulative of behavior individual can be such that by the calculation formula of select probability
Wherein, P (xj) be initial population in i-th of behavior individual by select probability, Q (xi) i-th of behavior in initial population
Individual adds up by select probability, and wherein i is the positive integer greater than 1.Finally, above-mentioned electronic equipment generates at random between 0 to 1
Number α, then by random number α and by select probability Q (xi) compare, if Q (xi-1) < α < Q (xi), then it can choose out i-th
A behavior individual, it is seen that above-mentioned electronic equipment can use this method from initial population F0In select multiple behavior individuals and constitute
Regenerate population F1.It should be noted that for initial population F0In each behavior individual can repeatedly be selected, therefore it is above-mentioned again
Non-hibernating eggs group F1In there may be identical behavior individuals.
Step 305, the individual of the behavior in population will be regenerated and carries out crossing operation each other, generate cross-species.
In the present embodiment, the regeneration population F constituted based on step 3041, above-mentioned electronic equipment can will regenerate population F1
In behavior individual each other intersected so that regeneration population F1In the corresponding coding of risk information of behavior individual can
Multiple new behavior individuals are generated to carry out crossing operation, each new behavior individual may be constructed cross-species.By cross steps
Suddenly the Risk Evaluation effect of the cross-species generated, behavior individual therein is more excellent.
In general, the intersection step in genetic manipulation is that mating generates this side of the offspring of new gene type to simulation biology two-by-two
Method, according to crossover probability Pc, by the chromosome of two behavior individuals, disconnected in a certain position of its chromosome, intersect, generate
Offspring with new gene type；During gene intersects, the filial generation that there is more excellent fitness than parent is generated, is embodied
The theory searched for out；It is noted that the cross-species fitness of acquisition is towards more excellent really using this method is intersected
Direction it is mobile, this is the characteristic and advantage of genetic algorithm.
Specifically, above-mentioned electronic equipment can determine the crossover probability P of crossing operation firstc, then according to determined by
Crossover probability PcIt is right that several pairs of multiple behavior individuals of behavior individuals composition are randomly selected from regeneration population.Then, above-mentioned electronics
Each behavior individual that equipment can extract it generates the cross-species including multiple behavior individuals to crossover operation is executed.
As an example, above-mentioned electronic equipment can be according to crossover probability PcValue from regeneration population F1={ x1,x2,
x3...xmIn to extract multiple behavior individuals right.Here with behavior individual to xixjFor, behavior individual x can be choseniAnd xjIn
Two behaviors individuals are then carried out crossing operation by the position of the identical risk information coding in several positions each other.
Here, behavior individual xiRisk information coding it is as follows, wherein being encoded in grey table be selected to
The risk information of intersection encodes.
Behavior individual xjRisk information coding it is as follows, wherein being encoded in grey table is selected to be intersected
Risk information coding.
Holding behavior individual xiAnd xjIn unselected risk information coding it is constant, switch-activity individual xiAnd xjIt
Between the identical risk information coding of the coding site that is selected, and the sequence for saving the coding of the risk information selected is constant,
To obtain the behavior individual after crossing operation.Therefore, the behavior individual x after crossing operationiRisk information coding can
With as follows:
Behavior individual x after crossing operationjRisk information coding can be as follows:
Above-mentioned electronic equipment can be completed using this method from regeneration population F1={ x1,x2,x3...xmIn extract it is multiple
The crossing operation of behavior individual pair, and each behavior individual is obtained to crossing operation as a result, constituting cross-species.
Step 306, mutation operator is carried out to the behavior individual in cross-species, generates variation population.
In the present embodiment, the cross-species generated based on step 305, above-mentioned electronic equipment can will be in the cross-species
Behavior individual make a variation, allow the corresponding coding of risk information of the behavior individual in cross-species to pass through variation fortune
It calculates and generates multiple new behavior individuals, constitute variation population.
In general, the variation step in genetic manipulation is that meeting this phenomenon of gene mutation occurs for simulation biology, it is general according to variation
Rate Pm, morph in a certain position of genes of individuals；Usual mutation probability PmValue obtain it is very small (in nature individual occur
The probability of gene mutation is also very small)；Become the purpose that step is made to be to keep the diversity of population, meanwhile, gene can generate change
It is different, the shortcomings that falling into local optimum can be overcome to a certain extent.The step that makes a variation in genetic manipulation and intersection step are usual
It can cooperate.
Specifically, above-mentioned electronic equipment first can be with the mutation probability P of definitive variation operationm, and by above-mentioned cross-species
In each behavior individual risk information code conversion be binary coding.Then, above-mentioned electronic equipment can be from intersection kind
The behavior individual for variation is chosen in group, and to the binary-coded any position in selected each behavior individual
Coding carries out inversion operation and generates new risk behavior individual composition variation population.
In some optional implementations of the present embodiment, after executing mutation operator, above-mentioned electronic equipment can be after
Whether the continuous number for judging that genetic algorithm executes meets preset the number of iterations, if it is not, repeating step 303-
Step 306, until the execution of genetic algorithm meets preset the number of iterations.Further, when genetic algorithm execute number
Met preset the number of iterations, whether above-mentioned electronic equipment can detecte quality and quantity of risk behavior individual of generation etc.
Meet preset condition.If risk behavior individual meets preset condition, risk subscribers recognition methods its can be continued to execute
Its step；If risk behavior individual is not able to satisfy preset condition, the number of iterations of genetic algorithm execution can be reset,
In order to which electronic equipment can meet the wind of preset condition by executing the genetic algorithm generation of the number of iterations reset
Dangerous behavior individual.
Step 307, potential risk information is matched with the risk information of each risk behavior individual, obtains matching knot
Fruit, and judge whether matching degree is greater than preset threshold.
In the present embodiment, the risk behavior individual obtained based on step 306, above-mentioned electronic equipment can be by use to be identified
The potential risk information at family is matched with the risk information of each risk behavior individual, and obtains corresponding matching degree.On then
Stating electronic equipment may determine that whether the matching degree is greater than preset threshold, when determining that the matching result is greater than preset threshold, then
Step 308 can be gone to, when determining the matching result no more than preset threshold, then can go to step 309.
Step 308, determine that user to be identified is risk subscribers.
In the present embodiment, preset threshold is greater than based on the matching result that step 307 determines, above-mentioned electronic equipment can be true
The fixed user to be identified is risk subscribers.At this point, above-mentioned electronic equipment can block the operation behavior of the user to be identified
It cuts.
Step 309, determine that user to be identified is normal users.
In the present embodiment, preset threshold is not more than based on the matching result that step 307 determines, above-mentioned electronic equipment can be with
Determine that the user to be identified is normal users.At this point, the operation behavior that above-mentioned electronic equipment can continue as user to be identified mentions
For supporting.
From figure 3, it can be seen that compared with the corresponding embodiment of Fig. 2, risk subscribers recognition methods in the present embodiment
Process 300 highlights the step that risk behavior individual is generated using genetic algorithm.The scheme of the present embodiment description can draw as a result,
Enter it is multiple objectively, meet expected risk behavior individual and carry out match cognization risk subscribers, to improve risk subscribers identification
Accuracy rate.
With further reference to Fig. 4, as the realization to method shown in above-mentioned each figure, this application provides a kind of knowledges of risk subscribers
One embodiment of other device, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which can specifically apply
In various electronic equipments.
As shown in figure 4, the risk subscribers identification device 400 of the present embodiment includes: acquiring unit 401,402 and of generation unit
Matching unit 403.Wherein, acquiring unit 401 is configured to obtain potential risk information according to the operation behavior of user to be identified,
Wherein, potential risk information includes the user base information of user to be identified and the behavioural information of operation behavior；Generation unit 402
It is configured to extract the risk information of multiple users, and generates multiple risk behaviors using genetic algorithm processing risk information
Body, wherein risk information includes the behavioural information of the user base information of each user and the historical operation behavior of each user；Matching
Unit 403 is configured to match potential risk information with the risk information of each risk behavior individual, to be identified to judge
Whether user is risk subscribers.
In some optional implementations of the present embodiment, generation unit 402 includes: coding module, is configured to pair
Extracted risk information is encoded, and the risk information after coding is combined and is generated including the first of multiple behaviors individuals
Beginning population；Constructing module is configured to the risk information construction fitness function based on each user, wherein fitness function is used
In the fitness value for calculating behavior individual；Generation module is configured to execute genetic algorithm to initial population, and in genetic algorithm
When the number of execution meets preset the number of iterations, multiple risk behavior individuals are generated.
In some optional implementations of the present embodiment, generation module includes: computational submodule, is configured to utilize
Fitness function calculates the fitness value of each behavior individual in initial population, and is selected from initial population according to fitness value more
A behavior individual constitutes regeneration population；Intersect submodule, is configured to regenerate the behavior individual in population and carries out each other
Crossing operation generates cross-species；Make a variation submodule, is configured to carry out mutation operator to the behavior individual in cross-species,
Generate variation population.
In some optional implementations of the present embodiment, computational submodule is further configured to: being calculated using heredity
The selection operator of method, each behavior individual in the fitness value calculation initial population based on each behavior individual in initial population
By select probability；To being summed by selection Cumulative probability for behavior individual each in initial population, each behavior in initial population is obtained
Individual adds up by select probability；The random number between 0 to 1 is generated, and random number and each the accumulative of behavior individual are selected
Probability is compared to determine each behavior individual for constituting regeneration population.
In some optional implementations of the present embodiment, intersects submodule and be further configured to: determining and intersect fortune
The crossover probability of calculation, and to extract several pairs of behavior individuals right from regeneration population based on crossover probability；Each behavior to being extracted
Individual generates the cross-species including multiple behavior individuals to crossover operation is executed.
In some optional implementations of the present embodiment, variation submodule is further configured to: definitive variation fortune
The mutation probability of calculation, and be binary coding by the code conversion of each behavior individual in cross-species；It is selected from cross-species
The behavior individual in variation is taken, and binary-coded any coding of selected each behavior individual is carried out negating behaviour
Make, generate variation population, wherein variation population includes multiple risk behavior individuals.
In some optional implementations of the present embodiment, device 400 further include: setting unit is configured to when something lost
When the number that propagation algorithm executes meets preset the number of iterations, default item is unsatisfactory in response to the risk behavior individual detected
Part resets the number of iterations.
In some optional implementations of the present embodiment, matching unit 403 is further configured to: by potential risk
Information is matched with the risk information of each risk behavior individual, obtains matching degree, and judge whether matching degree is greater than default threshold
Value；If so, determining that user to be identified is risk subscribers；If not, it is determined that user to be identified is normal users.
Below with reference to Fig. 5, it illustrates the terminal device/server computers for being suitable for being used to realize the embodiment of the present application
The structural schematic diagram of system 500.Terminal device/server shown in Fig. 5 is only an example, should not be to the embodiment of the present application
Function and use scope bring any restrictions.
As shown in figure 5, computer system 500 includes central processing unit (CPU) 501, it can be read-only according to being stored in
Program in memory (ROM) 502 or be loaded into the program in random access storage device (RAM) 503 from storage section 508 and
Execute various movements appropriate and processing.In RAM 503, also it is stored with system 500 and operates required various programs and data.
CPU 501, ROM 502 and RAM 503 are connected with each other by bus 504.Input/output (I/O) interface 505 is also connected to always
Line 504.
I/O interface 505 is connected to lower component: the importation 506 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 507 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 508 including hard disk etc.；
And the communications portion 509 of the network interface card including LAN card, modem etc..Communications portion 509 via such as because
The network of spy's net executes communication process.Driver 510 is also connected to I/O interface 505 as needed.Detachable media 511, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 510, in order to read from thereon
Computer program be mounted into storage section 508 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 509, and/or from detachable media
511 are mounted.When the computer program is executed by central processing unit (CPU) 501, limited in execution the present processes
Above-mentioned function.It should be noted that computer-readable medium described herein can be computer-readable signal media or
Computer readable storage medium either the two any combination.Computer readable storage medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.
The more specific example of computer readable storage medium can include but is not limited to: have one or more conducting wires electrical connection,
Portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer readable storage medium, which can be, any include or stores
The tangible medium of program, the program can be commanded execution system, device or device use or in connection.And
In the application, computer-readable signal media may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium other than readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, described program design language include object oriented program language-such as Java, Smalltalk, C+
+, further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute, partly execute on the user computer on the user computer, be executed as an independent software package,
Part executes on the remote computer or executes on a remote computer or server completely on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including local area network (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor packet
Include acquiring unit, generation unit and matching unit.Wherein, the title of these units is not constituted under certain conditions to the unit
The restriction of itself, for example, acquiring unit is also described as " obtaining potential risk letter according to the operation behavior of user to be identified
The unit of breath ".
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in device described in above-described embodiment；It is also possible to individualism, and without in the supplying device.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the device, so that should
Device: potential risk information is obtained according to the operation behavior of user to be identified, wherein potential risk information includes user to be identified
User base information and operation behavior behavioural information；The risk information of multiple users is extracted, and is handled using genetic algorithm
Risk information generates multiple risk behaviors individual, wherein risk information include each user user base information and each user
The behavioural information of historical operation behavior；Potential risk information is matched with the risk information of each risk behavior individual, to sentence
Whether user to be identified of breaking is risk subscribers.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (18)
1. a kind of risk subscribers recognition methods, comprising:
Obtain potential risk information according to the operation behavior of user to be identified, wherein the potential risk information include it is described to
Identify the user base information of user and the behavioural information of the operation behavior；
The risk information of multiple users is extracted, and handles the risk information using genetic algorithm and generates multiple risk behaviors
Body, wherein the risk information includes the user base information of each user and the historical operation behavior of each user
Behavioural information；
The potential risk information is matched with the risk information of each risk behavior individual, it is described to be identified to judge
Whether user is risk subscribers.
2. according to the method described in claim 1, wherein, the utilization genetic algorithm handles the risk information and generates multiple wind
Dangerous behavior individual, comprising:
Extracted risk information is encoded, and it includes multiple rows that the risk information after coding, which is combined generation,
For the initial population of individual；
Risk information based on each user constructs fitness function, wherein the fitness function is for calculating the row
For the fitness value of individual；
Genetic algorithm is executed to the initial population, and meets preset the number of iterations in the number that the genetic algorithm executes
When, generate multiple risk behavior individuals.
3. described to execute genetic algorithm to the initial population according to the method described in claim 2, wherein, comprising:
The fitness value of each behavior individual in the initial population is calculated using the fitness function, and according to the fitness
Value selects multiple behavior individuals to constitute regeneration population from the initial population；
Behavior individual in the regeneration population is subjected to crossing operation each other, generates cross-species；
Mutation operator is carried out to the behavior individual in the cross-species, generates variation population.
4. according to the method described in claim 3, wherein, it is described selected from the initial population according to the fitness value it is more
A behavior individual constitutes regeneration population, comprising:
Using the selection operator of genetic algorithm, described in the fitness value calculation based on each behavior individual in the initial population just
Each behavior individual by select probability in beginning population；
It is individual to the behavior each in the initial population to be summed by selection Cumulative probability, it obtains each in the initial population
The behavior individual adds up by select probability；
The random number between 0 to 1 is generated, and the random number and each the accumulative of behavior individual are compared by select probability
Relatively each behavior individual for regenerating population is constituted to determine.
5. according to the method described in claim 3, wherein, the behavior individual by the regeneration population carries out each other
Crossing operation generates cross-species, comprising:
It determines the crossover probability of the crossing operation, and several pairs of rows is extracted from the regeneration population based on the crossover probability
It is right for individual；
To each behavior individual extracted to crossover operation is executed, the intersection kind including multiple behavior individuals is generated
Group.
6. according to the method described in claim 3, wherein, the behavior individual in the cross-species carries out variation fortune
It calculates, generates variation population, comprising:
It determines the mutation probability of the mutation operator, and is by the code conversion of each behavior individual in the cross-species
Binary coding；
Choose the behavior individual for variation from the cross-species, and to the two of each of selected behavior individual into
Any coding in system coding carries out inversion operation, generates variation population, wherein the variation population includes multiple risk behaviors
Individual.
7. according to the method described in claim 2, wherein, the method also includes:
When the number that the genetic algorithm executes meets preset the number of iterations, in response to the risk behavior detected
Body is unsatisfactory for preset condition, resets the number of iterations.
It is described by the potential risk information and each risk behavior individual 8. according to the method described in claim 1, wherein
Risk information matched, to judge whether the user to be identified is risk subscribers, comprising:
The potential risk information is matched with the risk information of each risk behavior individual, obtains matching degree, and sentence
Whether the matching degree of breaking is greater than preset threshold；
If so, determining that the user to be identified is risk subscribers；
If not, it is determined that the user to be identified is normal users.
9. a kind of risk subscribers identification device, comprising:
Acquiring unit is configured to obtain potential risk information according to the operation behavior of user to be identified, wherein the potential wind
Dangerous information includes the user base information of the user to be identified and the behavioural information of the operation behavior；
Generation unit is configured to extract the risk information of multiple users, and handles the risk information life using genetic algorithm
At multiple risk behaviors individual, wherein the risk information include each user user base information and each user
Historical operation behavior behavioural information；
Matching unit is configured to the progress of the risk information of the potential risk information and each risk behavior individual
Match, to judge whether the user to be identified is risk subscribers.
10. device according to claim 9, wherein the generation unit includes:
Coding module is configured to encode extracted risk information, and the risk information after coding is carried out
Combination producing includes the initial population of multiple behavior individuals；
Constructing module is configured to the risk information construction fitness function based on each user, wherein the fitness letter
Count the fitness value for calculating the behavior individual；
Generation module is configured to execute the initial population genetic algorithm, and full in the number that the genetic algorithm executes
When the preset the number of iterations of foot, multiple risk behavior individuals are generated.
11. device according to claim 10, wherein the generation module includes:
Computational submodule is configured to calculate the fitness of each behavior individual in the initial population using the fitness function
Value, and select multiple behavior individuals to constitute regeneration population from the initial population according to the fitness value；
Intersect submodule, is configured to the behavior individual in the regeneration population carrying out crossing operation each other, generates and hand over
Pitch population；
Make a variation submodule, is configured to carry out mutation operator to the behavior individual in the cross-species, generates variation population.
12. device according to claim 11, wherein the computational submodule is further configured to:
Using the selection operator of genetic algorithm, described in the fitness value calculation based on each behavior individual in the initial population just
Each behavior individual by select probability in beginning population；
It is individual to the behavior each in the initial population to be summed by selection Cumulative probability, it obtains each in the initial population
The behavior individual adds up by select probability；
The random number between 0 to 1 is generated, and the random number and each the accumulative of behavior individual are compared by select probability
Relatively each behavior individual for regenerating population is constituted to determine.
13. device according to claim 11, wherein the intersection submodule is further configured to:
It determines the crossover probability of the crossing operation, and several pairs of rows is extracted from the regeneration population based on the crossover probability
It is right for individual；
To each behavior individual extracted to crossover operation is executed, the intersection kind including multiple behavior individuals is generated
Group.
14. device according to claim 11, wherein the variation submodule is further configured to:
It determines the mutation probability of the mutation operator, and is by the code conversion of each behavior individual in the cross-species
Binary coding；
Choose the behavior individual for variation from the cross-species, and to the two of each of selected behavior individual into
Any coding of system coding carries out inversion operation, generates variation population, wherein the variation population includes multiple risk behaviors
Body.
15. device according to claim 10, wherein described device further include:
Setting unit is configured to when the number that the genetic algorithm executes meets preset the number of iterations, in response to detection
To the risk behavior individual be unsatisfactory for preset condition, reset the number of iterations.
16. device according to claim 9, wherein the matching unit is further configured to:
The potential risk information is matched with the risk information of each risk behavior individual, obtains matching degree, and sentence
Whether the matching degree of breaking is greater than preset threshold；
If so, determining that the user to be identified is risk subscribers；
If not, it is determined that the user to be identified is normal users.
17. a kind of server, comprising:
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method described in any one of claims 1-8.
18. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that described program is processed
Such as method described in any one of claims 1-8 is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711205636.XA CN109840772A (en) | 2017-11-27 | 2017-11-27 | Risk subscribers recognition methods and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711205636.XA CN109840772A (en) | 2017-11-27 | 2017-11-27 | Risk subscribers recognition methods and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109840772A true CN109840772A (en) | 2019-06-04 |
Family
ID=66880231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711205636.XA Pending CN109840772A (en) | 2017-11-27 | 2017-11-27 | Risk subscribers recognition methods and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109840772A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105590055A (en) * | 2014-10-23 | 2016-05-18 | 阿里巴巴集团控股有限公司 | Method and apparatus for identifying trustworthy user behavior in network interaction system |
| CN105844526A (en) * | 2015-01-14 | 2016-08-10 | 阿里巴巴集团控股有限公司 | Networked transaction risk identification method and networked transaction risk identification device based on computer system |
| CN106296195A (en) * | 2015-05-29 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of Risk Identification Method and device |
| CN106845999A (en) * | 2017-02-20 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | Risk subscribers recognition methods, device and server |
| CN107294902A (en) * | 2016-03-30 | 2017-10-24 | 阿里巴巴集团控股有限公司 | A kind of Risk Identification Method and equipment |
-
2017
- 2017-11-27 CN CN201711205636.XA patent/CN109840772A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105590055A (en) * | 2014-10-23 | 2016-05-18 | 阿里巴巴集团控股有限公司 | Method and apparatus for identifying trustworthy user behavior in network interaction system |
| CN105844526A (en) * | 2015-01-14 | 2016-08-10 | 阿里巴巴集团控股有限公司 | Networked transaction risk identification method and networked transaction risk identification device based on computer system |
| CN106296195A (en) * | 2015-05-29 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of Risk Identification Method and device |
| CN107294902A (en) * | 2016-03-30 | 2017-10-24 | 阿里巴巴集团控股有限公司 | A kind of Risk Identification Method and equipment |
| CN106845999A (en) * | 2017-02-20 | 2017-06-13 | 百度在线网络技术（北京）有限公司 | Risk subscribers recognition methods, device and server |
Non-Patent Citations (2)
| Title |
|---|
| GIA SIRBILADZE: "Genetic Algorithm approach for the prediction of business risks" dynamics of enterprise", 《2012 6TH INTERNATIONAL CONFERENCE ON APPLICATION OF INFORMATION AND COMMUNICATION TECHNOLOGIES》 * |
| 逯宇铎等: "跨境电子商务项目风险识别及其评价模型研究", 《项目技术管理》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112148987B (en) | Message pushing method based on target object activity and related equipment | |
| CN106845999A (en) | Risk subscribers recognition methods, device and server | |
| CN107730389A (en) | Electronic installation, insurance products recommend method and computer-readable recording medium | |
| CN107908740A (en) | Information output method and device | |
| CN110298547A (en) | Methods of risk assessment, device, computer installation and storage medium | |
| CN109492772A (en) | The method and apparatus for generating information | |
| WO2022105117A1 (en) | Method and device for image quality assessment, computer device, and storage medium | |
| CN107944481A (en) | Method and apparatus for generating information | |
| CN110148053B (en) | User credit line evaluation method and device, electronic equipment and readable medium | |
| CN109886699A (en) | Activity recognition method and device, electronic equipment, storage medium | |
| CN107368499B (en) | Client label modeling and recommending method and device | |
| CN109389660A (en) | Image generating method and device | |
| CN115935185A (en) | Training method and device for recommendation model | |
| CN109255646A (en) | Deep learning is carried out using big data to provide method, the system of value-added service | |
| CN112995414B (en) | Behavior quality inspection method, device, equipment and storage medium based on voice call | |
| CN116402625B (en) | Customer evaluation method, apparatus, computer device and storage medium | |
| CN110335061A (en) | Trade mode portrait method for building up, device, medium and electronic equipment | |
| CN110197317A (en) | Target user determines method and device, electronic equipment and storage medium | |
| CN108984681A (en) | The method, apparatus storage medium and electronic equipment that insurance information is recommended | |
| CN110427546A (en) | A kind of information displaying method and device | |
| CN112100491A (en) | Information recommendation method, device and equipment based on user data and storage medium | |
| CN116186541A (en) | Training method and device for recommendation model | |
| CN115392361A (en) | Intelligent sorting method and device, computer equipment and storage medium | |
| CN109840772A (en) | Risk subscribers recognition methods and device | |
| CN113592315A (en) | Method and device for processing dispute order |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190604 |
|
| RJ01 | Rejection of invention patent application after publication |