CN110009127A - Indulge game Risk Identification Method, device, computer equipment and storage medium - Google Patents
Indulge game Risk Identification Method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110009127A CN110009127A CN201910068556.7A CN201910068556A CN110009127A CN 110009127 A CN110009127 A CN 110009127A CN 201910068556 A CN201910068556 A CN 201910068556A CN 110009127 A CN110009127 A CN 110009127A
- Authority
- CN
- China
- Prior art keywords
- risk
- data
- user
- user identifier
- principal component
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 206010012335 Dependence Diseases 0.000 claims abstract description 30
- 230000000737 periodic effect Effects 0.000 claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 10
- 238000007477 logistic regression Methods 0.000 claims description 8
- 238000000513 principal component analysis Methods 0.000 claims description 8
- 239000000470 constituent Substances 0.000 claims 1
- 239000013589 supplement Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 230000001502 supplementing effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003442 weekly effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000004615 ingredient Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- VIKNJXKGJWUCNN-XGXHKTLJSA-N norethisterone Chemical compound O=C1CC[C@@H]2[C@H]3CC[C@](C)([C@](CC4)(O)C#C)[C@@H]4[C@@H]3CCC2=C1 VIKNJXKGJWUCNN-XGXHKTLJSA-N 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves a kind of addiction game Risk Identification Method, system, computer equipment and storage medium based on algorithm model.The described method includes: periodic operation risk profile task；User's history data are obtained according to risk profile task, include user identifier and achievement data in user's history data；Portrait model is called, prediction operation is carried out based on achievement data, obtains risk data corresponding with user identifier；It include risk score in risk data；When risk score is more than threshold value, risk label is added for user identifier.It can identify that user indulges the risk of game in advance using this method.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of addiction game Risk Identification Method, device, calculating
Machine equipment and storage medium.
Background technique
Most of game players can influence normal life and work because indulging game, and user indulges game in order to prevent,
Gaming platform generally can all be arranged indulging system and be limited.It is all the game added up by player in traditional mode
Whether time identification player indulges in game.
However, the Anti-addiction limitation of traditional game platforms is occurred subsequent, only reached when playtime is accumulative
Limit, could identify whether user has indulged game after player has indulged game, have hysteresis quality.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of addiction game risk that can identify risk in advance
Recognition methods, device, computer equipment and storage medium.
A kind of addiction game Risk Identification Method, which comprises
Periodic operation risk profile task；
Obtain user's history data according to the risk profile task, include in the user's history data user identifier and
Achievement data；
Portrait model is called, prediction operation is carried out based on the achievement data, obtains wind corresponding with the user identifier
Dangerous data；It include risk score in the risk data；
When the risk score is more than threshold value, risk label is added for the user identifier.
In one of the embodiments, the method also includes:
The predetermined registration operation request that terminal is sent is received, carries user identifier in the predetermined registration operation request；
Inquire whether the user identifier is added corresponding risk label；
If so, requesting corresponding permission to be adjusted the predetermined registration operation.
The calling portrait model in one of the embodiments, carries out prediction operation based on the achievement data, obtains
Risk data corresponding with the user identifier includes:
The evidence weight for calculating the achievement data carries out branch mailbox processing according to the evidence weight；
The branch mailbox treated achievement data is subjected to principal component analysis, obtains principal component coefficient matrix；
The principal component coefficient matrix, which is calculated, by logistic regression determines principal component scores coefficient；
Risk data is determined according to the principal component scores coefficient.
It is described in one of the embodiments, that the branch mailbox treated achievement data is subjected to principal component analysis, it obtains
Principal component coefficient matrix includes:
It is standardized the achievement data to obtain standardized data, be established according to the standardized data related
Coefficient matrix；
The characteristic root and contribution rate for calculating the correlation matrix determine master according to the characteristic root and the contribution amount
Ingredient；
It calculates the principal component load and obtains principal component coefficient matrix.
The user identifier includes identity information and scene identity in one of the embodiments,；The inquiry use
Family identifies whether that being added corresponding risk label includes:
Multiple risk labels are matched according to the scene identity；
Inquire whether have risk mark corresponding with identity information from the multiple risk label according to the identity information
Label.
A kind of addiction game recognition device, described device include:
Module is run, periodic operation risk profile task is used for；
Data acquisition module, for obtaining user's history data, the user's history number according to the risk profile task
It include user identifier and achievement data in；；
Risk profile module, for call portrait model, prediction operation is carried out based on the achievement data, obtain with it is described
The corresponding risk data of user identifier；It include risk score in the risk data；
Label adding module, for adding risk label for the user identifier when the risk score is more than threshold value.
Described device further includes permission adjustment module in one of the embodiments, for receiving the default of terminal transmission
Operation requests carry user identifier in predetermined registration operation request；Inquire whether the user identifier is added corresponding wind
Dangerous label；If so, requesting corresponding permission to be adjusted the predetermined registration operation.
The risk profile module is also used to calculate the evidence weight of the achievement data in one of the embodiments,
Branch mailbox processing is carried out according to the evidence weight；The branch mailbox treated achievement data is subjected to principal component analysis, is led
Ingredient coefficient matrix；The principal component coefficient matrix, which is calculated, by logistic regression determines principal component scores coefficient；According to the master
Component score coefficient determines risk data.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes addiction game Risk Identification Method described in above-mentioned any one when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Addiction game risk identification described in above-mentioned any one is realized when row.
Above-mentioned addiction game Risk Identification Method, device, computer equipment and storage medium, pass through server periodic operation
Risk profile task obtains user's history data according to the demand of risk profile task from database, and historical data includes user
Mark and achievement data.Again by calling portrait model, prediction operation is carried out based on achievement data, is obtained corresponding to user identifier
Risk data, include risk score in risk data.When risk score is more than threshold value, risk mark is added for user identifier
Label.By calling historical data to identify whether user has the risk of addiction game using portrait model realization look-ahead.
Detailed description of the invention
Fig. 1 is the applied environment figure that game Risk Identification Method is indulged in one embodiment；
Fig. 2 is the flow diagram that game Risk Identification Method is indulged in one embodiment；
Fig. 3 is the step flow diagram of user right adjustment in one embodiment；
Fig. 4 is the step flow diagram that portrait model is called in one embodiment；
Fig. 5 is the step process signal that whether inquiry user identifier is added corresponding risk label in one embodiment
Figure；
Fig. 6 is the timing diagram of user right adjustment in one embodiment；
Fig. 7 is the structural block diagram that game risk identification device is indulged in one embodiment；
Fig. 8 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Addiction game Risk Identification Method provided by the present application, can be applied in application environment as shown in Figure 1.Its
In, terminal 102 is communicated with server 104 by network.Wherein, terminal 102 can be, but not limited to be various individual calculus
Machine, laptop, smart phone, tablet computer and portable wearable device, server 104 can use independent server
The either server cluster of multiple servers composition is realized.104 periodic operation risk profile task of server.Server
104 obtain user's history data according to the demand of risk profile task from database, and historical data includes user identifier and refers to
Mark data.Server 104 calls portrait model, carries out prediction operation based on achievement data, obtains wind corresponding with user identifier
Dangerous data include risk score in risk data.It is then user when server 104 judges that risk score is more than given threshold
Mark addition risk label.When server 104 receives the predetermined registration operation request for carrying user identifier of the transmission of terminal 102
When, inquire whether the user identifier is added risk label according to request.If so, server 104 then requests predetermined registration operation
Corresponding permission is adjusted.
In one embodiment, it as shown in Fig. 2, providing a kind of addiction game Risk Identification Method, applies in this way
It is illustrated for server in Fig. 1, comprising the following steps:
S202, periodic operation risk profile task.
S204, obtains user's history data according to risk profile task, includes user identifier in user's history data and refers to
Mark data.
Risk profile task can voluntarily dispose according to actual needs in task platform.Server periodic operation is deployed
Risk profile task, the period can be weekly or once a month, to predict that task is set according to practical risk.Clothes
Business device obtains user's history data according to the demand of risk profile task from database, and user's history data include user identifier
And achievement data.Wherein, if user data derives from local data base, server in database in real time required for obtaining
User data.If user data derives from other data platforms, server obtains user from data platform so that T+1 mode is asynchronous
Data.Wherein, T+1 mode refers to that the same day obtains next day arrival, that is, uses when server today initiates to obtain to data platform
When family historical data is requested, server, which wants next day just, can receive the data that data platform sends over.User identifier includes using
The personally identifiable information etc. at family, each user have unique user identifier, and server is according to the available use of user identifier
The identity information at family, achievement data are historical game play data and personal asset data of the user in gaming platform.
In task Platform deployment risk profile task, the sets itself time started and frequency can be executed according to demand
Rate.Time started refers to the time that task brings into operation, and reaches i.e. executable risk profile task after the time started, executes frequency
It can be set according to day, the moon, the end of month.Such as when risk profile task setting at the beginning of be 27 days eight June in 2018
When point, if execution frequency is day, risk profile task will be run for the first time at 8 points of on June 27th, 2018, and subsequent daily eight
Point will run primary.If execution frequency is the moon, then 8 points of 27 days monthly will be run primary.If execution frequency is the moon
End will then be run for the first time in 8 points of on June 30th, 2018, and then the eight of last day monthly point will run once.
Wherein, it when execution frequency is set as 0, represents risk profile task and is only run once at the beginning of setting, then will not
Operation.If at the beginning of setting being 30, when execution frequency is the moon, then 30 days monthly can all be run once, but by
In 2 months without 30 days, therefore the risk profile task in 2 months will not be triggered operation.
S206 calls portrait model, carries out prediction operation based on achievement data, obtain risk number corresponding with user identifier
According to；It include risk score in risk data.
S208 adds risk label when risk score is more than threshold value for user identifier.
Model of drawing a portrait is that addiction games personnel draws a portrait model, portrait model correspond to it is multiple enter modular character, achievement data is
What portrait model needed enters modular character.The case where user indulges game and Assets can be embodied by achievement data.Root
It is predicted to obtain the risk data of each user according to the achievement data of user, includes risk score in risk data, pass through wind
Danger scoring can directly reflect the probability that user indulges game.When the risk score of user is more than the threshold value of setting, show
The user has the risk of addiction game or has indulged game, then adds risk label for user identifier corresponding to user.
Wherein, by taking chess/card game as an example, achievement data may include: nearly one month bet total value of user, nearly trimestral bet increasing
Long rate, nearly 1 year supplement with money median, nearly half a year supplement median with money, nearly 1 year discount coupon supplements total amount with money, one month 24 nearly
Play a game total degree, the game trend of work hours, nearly exchange in 1 year of total degree, nearly month work hours of playing a game after point is always secondary
The loan coefficient of variation in several, close March, nearly one month assets growth rate, the assets weight of nearly half a year, the loan of nearly half a year are equal
Value etc..
Wherein, the risk data increment that periodic operation risk profile task obtains is stored in server.That is, when fortune
When the row period is weekly, after the prediction of first week risk data of user generates and stores, second week is waited until again
It is equally stored when obtaining the risk data of the user, and first week risk data is not deleted.That is, cut-off this week
Until have two corresponding risk datas under the user identifier.Also, working as first week risk score of user is more than threshold value, is right
The user identifier answered is added to risk label.But the risk score that the second weekly forecasting generates is not above threshold value, then will
The risk label of the user is cancelled, and the addition and cancellation of risk label are determined by risk score.
In the present embodiment, by server periodic operation risk profile task, according to the demand of risk profile task from
User's history data are obtained in database, historical data includes user identifier and achievement data.Again by calling portrait model, it is based on
Achievement data carries out prediction operation, obtains risk data corresponding with user identifier, includes risk score in risk data.Work as wind
When danger is scored above threshold value, risk label is added for user identifier.By calling historical data to mention using model realization of drawing a portrait
Whether preceding Forecasting recognition user has the risk of addiction game.
In one embodiment, as shown in figure 3, this method further includes the steps that user right adjusts, comprising:
S302 receives the predetermined registration operation request that terminal is sent, carries user identifier in predetermined registration operation request.
Whether S304, inquiry user identifier are added corresponding risk label.If so, thening follow the steps S306；Otherwise, it returns
Return step S302.
S306 requests corresponding permission to be adjusted predetermined registration operation.
Synchronization call server is requested to inquire user mark by the predetermined registration operation for carrying user identifier that terminal is sent
Know and whether is added risk identification.Such as user identifier user is added to risk label, then shows that the user has addiction to swim
The risk of play has indulged game, then the adjustment of permission is carried out to the predetermined registration operation of the user.For example, being with predetermined registration operation
For supplementing with money or betting, when user is when game terminal interface is clicked and supplements or bet button with money, game terminal is synchronous to send operation
It requests to server, and carries the corresponding user identifier of user in operation requests.If server, which inquires the user identifier, to be had
Corresponding risk label is then adjusted the amount of supplementing with money or bet of user, and it is daily or each can to limit the user
The amount of money amount upper limit supplemented with money or betted.After user right is adjusted, by message push inform user its supplement with money or under
Limit and limit amount are infused, and reminds user's appropriateness game.Wherein, when server inquire the user have it is corresponding
After risk label, server obtains the risk score of the user, and the amount upper limit value of user is determined according to risk score.If according to
Scoring determines user's only slight addiction game, then can adjust supervision by limit appropriate prevents user from further indulging trip
Play.If user is to have indulged game user, user right can be directly closed, limitation user supplements with money or bets.?
In the present embodiment, by risk label and risk score, different adjustment can be carried out for the different situations of different user, prevented
The only immoderate addiction game of user's milli.
In one embodiment, when server receives the predetermined registration operation request of game terminal transmission, predetermined registration operation is asked
User identifier is carried in asking.Server gets the corresponding risk data of the user according to user identifier, and by with trip
Risk data is returned to game terminal by the interface that play terminal has been made an appointment.Game terminal carries out user according to risk data
Decision in the face of risk obtains decision in the face of risk data.Permission adjustment is carried out to user according to decision in the face of risk data and by decision in the face of risk data
Server is returned to be stored.Wherein, decision in the face of risk data include user identifier, risk data, whether adjust permission and
Permission adjusted.In the present embodiment, risk data is sent to game terminal, game terminal can be autonomous according to user
Risk data carry out decision without by server decision.Server receives the decision in the face of risk of game terminal return
When data, decision in the face of risk data are sent to Risk Monitoring management system and are monitored management by synchronization.
In one embodiment, as shown in figure 4, call portrait model, prediction operation is carried out based on achievement data, obtain with
Further include before the corresponding risk data of user identifier establish portrait model the following steps are included:
S402, the evidence weight of parameter data carry out branch mailbox processing according to evidence weight.
Branch mailbox treated achievement data is carried out principal component analysis, obtains principal component coefficient matrix by S404.
S406 calculates principal component coefficient matrix by logistic regression and determines principal component scores coefficient.
S408 determines risk data according to principal component scores coefficient.
The achievement data refers to that finally chooses enters modular character.The evidence weight of server parameter data first, root
Branch mailbox processing is carried out again to achievement data according to evidence weight.Principal component analysis will be carried out by the achievement data of branch mailbox processing,
Obtain principal component coefficient matrix.Then the score system that principal component coefficient matrix determines principal component is calculated using logistic regression algorithm
Number, the risk data of user is determined according to principal component scores coefficient.Wherein, achievement data is carried out standard first by principal component analysis
Change handles to obtain standardized data, establishes correlation matrix according to standardized data.Calculate the characteristic root of correlation matrix
And contribution rate, selected characteristic root is greater than 1 and contribution rate is greater than 85% achievement data for principal component, calculates separately each principal component
Load value obtain principal component coefficient matrix.Also, determine using before logistic regression algorithm also using analyzing nerve net
Network algorithm and gradient promote decision Tree algorithms, compare the modelling effect under algorithms of different.Due to the AUC of neural network algorithm
(Area under the Curve of ROC, sensitivity area under curve) value is not high, and uses neural network algorithm
The recall rate of portrait model is minimum.Although and gradient promoted decision Tree algorithms recall rate increase than neural network algorithm,
But AUC value is not still high, and accuracy rate also has dropped.Therefore, final choice AUC value and the highest logistic regression of recall rate
Algorithm is as modeling algorithm.
The evidence weight of parameter data further includes the choosing of achievement data before carrying out branch mailbox processing according to evidence weight
It takes.The training sample for model of drawing a portrait has been divided into sample and bad sample according to user type by server, good sample be be layered with
The mode that machine extracts does not have to extract in the user for indulging game within the observation period, bad sample from registered game account
To have indulged games personnel within the observation period.Observation period be the previous year of point of observation, good sample point of observation can be according to reality
Border situation sets itself.The point of observation of bad sample is determined by the account of the history that the user indulges game, can be sunk according to user
The time point of fan's game establishes point of observation.After sample determines, server is from database by all indexs of different samples
Data extract, the availability of analysis indexes data, the achievement data for selecting availability high.Analyze the high index number of availability
According to missing values, delete the big achievement data of missing values and obtain index long list.Secondly, doing phase to all indexs in long list
The small index of correlation is chosen in the matrix analysis of closing property.The achievement data small to correlation carries out optimal branch mailbox, calculates each progress
The information value of achievement data after branch mailbox.In conjunction between each achievement data correlation and information value choose final index
Data, that is, enter modular character.
In the present embodiment, Analysis and Screening is carried out to achievement data, choosing suitable achievement data is into modular character.To
When carrying out addiction game prediction operation to user by the portrait model, the accuracy of prediction can be effectively improved.
In one embodiment, as shown in figure 5, it includes following that whether inquiry user identifier, which is added corresponding risk label,
Step:
S502 matches multiple risk labels according to scene identity.
S504 inquires whether have risk label corresponding with identity information according to identity information from multiple risk labels.
The user identifier that terminal is sent not only includes the identity information of user, further comprises scene identity.When server connects
When receiving the predetermined registration operation request of the carrying user identifier of terminal transmission, inquire whether the user identifier is added to according to request
Corresponding risk label judges whether user carries out the adjustment of permission to the predetermined registration operation request of user.Game terminal usually divides
For many different scene of game, server stores the risk data and risk label of user according to different scene of game.Often
A scene of game has unique scene ID number, that is, scene identity.Therefore, when terminal sends predetermined registration operation request, clothes
Business device judges the current scene of game of the user according to the scene identity that request carries first, finds out under the scene of game and owns
Be added to the user of risk label, further according to user identity information therefrom inquire whether have it is opposite with the subscriber identity information
The risk label answered.Wherein, identity information can be, but not limited to game account, cell-phone number and name of user etc..In this reality
It applies in example, realizes whether quick search user is added risk label according to scene identity and subscriber identity information.
In one embodiment, as shown in fig. 6, after the completion of portrait model construction, plug-in application is encapsulated into slotting
In part platform.One kind is provided when user preset operation is supplements or bet with money, the timing diagram of user right method of adjustment, including with
Lower step: terminal user logs in gaming platform by phone number, when user is when gaming platform is supplemented with money or is betted, supplements with money
Or bet module synchronization calls plug-in unit, plug-platform calls the model result of portrait model acquisition user.Model draw a portrait for user
Model result return to plug-in unit, plug-platform obtains the addiction game risk score of user according to model, and by the heavy of user
Fan's game risk score returns to gaming platform.Gaming platform adjusts the limit that user supplements with money or bets according to the risk score of user
Volume.Gaming platform reminds user to adjust limit of supplementing with money or bet by sending pop-up after limit of supplementing with money or bet adjustment.
In one embodiment, plug-platform is also attached with task platform, Risk Monitoring management system.When game is flat
When platform synchronization call plug-in unit, plug-platform generates risk profile task in real time and is sent to task platform, and receives gaming platform reality
When the partial data that sends.Task platform obtains required historical data according to mission requirements from database, will go through
History data return to plug-platform.Plug-platform calls portrait model, the data that gaming platform is sent in real time and task platform
The historical data of acquisition is input to portrait model and carries out prediction operation acquisition risk data, that is, model result, by model knot
Fruit stores into model result library.Also, determine that the risk score of user's addiction game returns to game and puts down by model result
Platform.Wherein, task platform does not remove the risk profile task received, and pre- by preset rules setting timing operation risk
Survey task.When task platform timing operation risk profile task, institute is obtained from database and gaming platform with the mode of asynchronous T+1
Data are needed, and enters data into portrait model and carries out prediction operation, model result is saved into model result library.Work as game
Platform, can be according to user identifier directly from model result library when synchronization call plug-in unit obtains the model result of the user next time
The middle model result for obtaining the user, determines the addiction game risk score of user.
Since plug-platform can add multiple plug-in units, when portrait model encapsulation at plug-in application when plug-platform, insert
Part platform is that portrait model generates the identification informations such as corresponding plug-in unit ID number, plugin name automatically.Plug-in unit ID number is for identifying
The unique identification of portrait model, can not modify, plugin name can modify according to actual needs.When gaming platform is sent together
Portrait model is carried when step is requested with plug-platform, in call request and correspond to the plug-in unit ID number of plug-in unit, and plug-platform passes through
Portrait model is called with ID number.Plug-platform also provides model result query function, can inquire mould by plug-in unit identification information
The model result data of type prediction operation.
It should be understood that although each step in the flow chart of Fig. 2-5 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-5
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in fig. 7, providing a kind of addiction game risk identification device, comprising: operation module
702, data acquisition module 704, risk profile module 706 and label adding module 708, in which:
Module 702 is run, periodic operation risk profile task is used for.
Data acquisition module 704 wraps in user's history data for obtaining user's history data according to risk profile task
Include user identifier and achievement data.
Risk profile module 706 carries out prediction operation based on achievement data, obtains and user for calling portrait model
Identify corresponding risk data；It include risk score in risk data.
Label adding module 708, for adding risk label for user identifier when risk score is more than threshold value.
In one embodiment, addiction game risk identification device further includes permission adjustment module, for receiving terminal hair
The predetermined registration operation sent is requested, and carries user identifier in predetermined registration operation request；Whether inquiry user identifier is added corresponding wind
Dangerous label；If so, requesting corresponding permission to be adjusted predetermined registration operation.
In one embodiment, risk profile module 706 is also used to the evidence weight of parameter data, according to weight evidence
Branch mailbox processing is carried out again；Branch mailbox treated achievement data is subjected to principal component analysis, obtains principal component coefficient matrix；By patrolling
It collects recurrence calculating principal component coefficient matrix and determines principal component scores coefficient；Risk data is determined according to principal component scores coefficient.
In one embodiment, risk profile module 706 is also used to for achievement data being standardized to obtain standard
Change data, correlation matrix is established according to standardized data；The characteristic root and contribution rate for calculating correlation matrix, according to spy
Sign root and the contribution amount determine principal component；It calculates principal component load and obtains principal component coefficient matrix.
In one embodiment, permission adjustment module is also used to match multiple risk labels according to scene identity；According to body
Part information inquires whether have risk label corresponding with identity information from multiple risk labels.
Specific restriction about addiction game risk identification device may refer to above for addiction game risk identification
The restriction of method, details are not described herein.Modules in above-mentioned addiction game risk identification device can be fully or partially through
Software, hardware and combinations thereof are realized.Above-mentioned each module can be embedded in the form of hardware or independently of the place in computer equipment
It manages in device, can also be stored in a software form in the memory in computer equipment, in order to which processor calls execution or more
The corresponding operation of modules.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 8.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing risk data.The network interface of the computer equipment is used to pass through network with external terminal
Connection communication.To realize a kind of addiction game Risk Identification Method when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 8, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor realize the step in above-mentioned each embodiment of the method when executing computer program.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the step in above-mentioned each embodiment of the method when being executed by processor.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of addiction game Risk Identification Method, which comprises
Periodic operation risk profile task；
User's history data are obtained according to the risk profile task, include user identifier and index in the user's history data
Data；
Portrait model is called, prediction operation is carried out based on the achievement data, obtains risk number corresponding with the user identifier
According to；It include risk score in the risk data；
When the risk score is more than threshold value, risk label is added for the user identifier.
2. the method according to claim 1, wherein the method also includes:
The predetermined registration operation request that terminal is sent is received, carries user identifier in the predetermined registration operation request；
Inquire whether the user identifier is added corresponding risk label；
If so, requesting corresponding permission to be adjusted the predetermined registration operation.
3. the method according to claim 1, wherein the calling draw a portrait model, based on the achievement data into
Row prediction operation, obtaining risk data corresponding with the user identifier includes:
The evidence weight for calculating the achievement data carries out branch mailbox processing according to the evidence weight；
The branch mailbox treated achievement data is subjected to principal component analysis, obtains principal component coefficient matrix；
The principal component coefficient matrix, which is calculated, by logistic regression determines principal component scores coefficient；
Risk data is determined according to the principal component scores coefficient.
4. according to the method described in claim 3, it is characterized in that, described by the branch mailbox, treated that achievement data is led
Constituent analysis, obtaining principal component coefficient matrix includes:
It is standardized the achievement data to obtain standardized data, related coefficient is established according to the standardized data
Matrix；
The characteristic root and contribution rate for calculating the correlation matrix, according to the characteristic root and the contribution amount determine it is main at
Point；
It calculates the principal component load and obtains principal component coefficient matrix.
5. according to the method described in claim 2, it is characterized in that, the user identifier includes identity information and scene identity；
Whether the inquiry user identifier, which is added corresponding risk label, includes:
Multiple risk labels are matched according to the scene identity；
Inquire whether have risk label corresponding with identity information from the multiple risk label according to the identity information.
6. a kind of addiction game risk identification device, which is characterized in that described device includes:
Module is run, periodic operation risk profile task is used for；
Data acquisition module, for obtaining user's history data according to the risk profile task, in the user's history data
Including user identifier and achievement data；；
Risk profile module carries out prediction operation based on the achievement data, obtains and the user for calling portrait model
Identify corresponding risk data；It include risk score in the risk data；
Label adding module, for adding risk label for the user identifier when the risk score is more than threshold value.
7. device according to claim 6, which is characterized in that described device further includes permission adjustment module, for receiving
The predetermined registration operation that terminal is sent is requested, and carries user identifier in the predetermined registration operation request；Whether inquire the user identifier
It is added corresponding risk label；If so, requesting corresponding permission to be adjusted the predetermined registration operation.
8. device according to claim 7, which is characterized in that the risk profile module is also used to calculate the index number
According to evidence weight, according to the evidence weight carry out branch mailbox processing；By the branch mailbox treated achievement data carries out it is main at
Analysis, obtains principal component coefficient matrix；The principal component coefficient matrix, which is calculated, by logistic regression determines principal component scores system
Number；Risk data is determined according to the principal component scores coefficient.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 5 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 5 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910068556.7A CN110009127A (en) | 2019-01-24 | 2019-01-24 | Indulge game Risk Identification Method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910068556.7A CN110009127A (en) | 2019-01-24 | 2019-01-24 | Indulge game Risk Identification Method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110009127A true CN110009127A (en) | 2019-07-12 |
Family
ID=67165478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910068556.7A Pending CN110009127A (en) | 2019-01-24 | 2019-01-24 | Indulge game Risk Identification Method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110009127A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110609935A (en) * | 2019-08-29 | 2019-12-24 | 湖南草花互动网络科技有限公司 | User identity tag generation method and device, computer equipment and storage medium |
| CN111629235A (en) * | 2020-01-20 | 2020-09-04 | 全息空间(深圳)智能科技有限公司 | Live broadcast platform user data analysis method and device and storage medium |
| CN112402953A (en) * | 2020-04-16 | 2021-02-26 | 上海哔哩哔哩科技有限公司 | Game anti-addiction method and system based on real-time calculation |
| CN113693596A (en) * | 2021-07-30 | 2021-11-26 | 阿呆科技（北京）有限公司 | Game addiction degree and addiction risk assessment method and system |
| CN117177014A (en) * | 2023-11-03 | 2023-12-05 | 帕科视讯科技(杭州)股份有限公司 | IPTV-based children anti-addiction early warning method, storage medium and server |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012056038A1 (en) * | 2010-10-28 | 2012-05-03 | Cms Hasche Sigle - Partnerschaft Von Rechtsanwälten Und Steuerberatern | Device and method for organizing a game of chance with suppression of problem gambling |
| CN106055100A (en) * | 2016-05-26 | 2016-10-26 | 广东欧珀移动通信有限公司 | Anti-addiction method, device and mobile device |
| KR20180046433A (en) * | 2016-10-27 | 2018-05-09 | 가톨릭대학교 산학협력단 | Method and Apparatus for Prediction of Smart Phone Addiction |
| CN108174036A (en) * | 2017-12-28 | 2018-06-15 | 广东小天才科技有限公司 | A kind of method and system of management and control application program |
-
2019
- 2019-01-24 CN CN201910068556.7A patent/CN110009127A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012056038A1 (en) * | 2010-10-28 | 2012-05-03 | Cms Hasche Sigle - Partnerschaft Von Rechtsanwälten Und Steuerberatern | Device and method for organizing a game of chance with suppression of problem gambling |
| CN106055100A (en) * | 2016-05-26 | 2016-10-26 | 广东欧珀移动通信有限公司 | Anti-addiction method, device and mobile device |
| KR20180046433A (en) * | 2016-10-27 | 2018-05-09 | 가톨릭대학교 산학협력단 | Method and Apparatus for Prediction of Smart Phone Addiction |
| CN108174036A (en) * | 2017-12-28 | 2018-06-15 | 广东小天才科技有限公司 | A kind of method and system of management and control application program |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110609935A (en) * | 2019-08-29 | 2019-12-24 | 湖南草花互动网络科技有限公司 | User identity tag generation method and device, computer equipment and storage medium |
| CN111629235A (en) * | 2020-01-20 | 2020-09-04 | 全息空间(深圳)智能科技有限公司 | Live broadcast platform user data analysis method and device and storage medium |
| CN112402953A (en) * | 2020-04-16 | 2021-02-26 | 上海哔哩哔哩科技有限公司 | Game anti-addiction method and system based on real-time calculation |
| CN112402953B (en) * | 2020-04-16 | 2022-06-03 | 上海哔哩哔哩科技有限公司 | Game anti-addiction method and system based on real-time calculation |
| CN113693596A (en) * | 2021-07-30 | 2021-11-26 | 阿呆科技（北京）有限公司 | Game addiction degree and addiction risk assessment method and system |
| CN117177014A (en) * | 2023-11-03 | 2023-12-05 | 帕科视讯科技(杭州)股份有限公司 | IPTV-based children anti-addiction early warning method, storage medium and server |
| CN117177014B (en) * | 2023-11-03 | 2024-01-30 | 帕科视讯科技(杭州)股份有限公司 | IPTV-based children anti-addiction early warning method, storage medium and server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110009127A (en) | Indulge game Risk Identification Method, device, computer equipment and storage medium | |
| CN110489520A (en) | Event-handling method, device, equipment and the storage medium of knowledge based map | |
| CN110443284B (en) | Artificial intelligence AI model training method, calling method, server and readable storage medium | |
| CN109410071A (en) | Core protects data processing method, device, computer equipment and storage medium | |
| CN106993104A (en) | Call processing method, device and terminal | |
| CN108932974A (en) | Method, apparatus, computer equipment and the storage medium of online interrogation distribution doctor | |
| CN110415036A (en) | Determination method, apparatus, computer equipment and the storage medium of user gradation | |
| CN110147967A (en) | Risk prevention system method and device | |
| CN111312406B (en) | Epidemic situation label data processing method and system | |
| CN107636653A (en) | Pattern information processing system | |
| CN108074027A (en) | Pure orphan's list distribution method and device | |
| CN109255747A (en) | A kind of intelligent checks method that information is declared | |
| CN108182633A (en) | Loan data processing method, device, computer equipment and storage medium | |
| CN109165516A (en) | A kind of access control method and device | |
| CN109840680A (en) | Service request processing method, device, computer equipment and storage medium | |
| CN110288350A (en) | User's Value Prediction Methods, device, equipment and storage medium | |
| CN110276677A (en) | Refund prediction technique, device, equipment and storage medium based on big data platform | |
| CN108492005A (en) | Project data processing method, device, computer equipment and storage medium | |
| CN110276369A (en) | Feature selection approach, device, equipment and storage medium based on machine learning | |
| CN109508964A (en) | Project method for building up, device, computer equipment and storage medium | |
| CN109543442A (en) | Data safety processing method, device, computer equipment and storage medium | |
| CN109543073A (en) | Enterprise's supply and marketing relation map generation method, device and computer equipment | |
| CN110135943A (en) | Products Show method, apparatus, computer equipment and storage medium | |
| CN109325868A (en) | Questionnaire data processing method, device, computer equipment and storage medium | |
| CN110166498A (en) | Class of subscriber determines method and device, computer equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190712 |