CN109658643A - Payment risk alarm method, server and intelligence POS - Google Patents
Payment risk alarm method, server and intelligence POS Download PDFInfo
- Publication number
- CN109658643A CN109658643A CN201811485606.3A CN201811485606A CN109658643A CN 109658643 A CN109658643 A CN 109658643A CN 201811485606 A CN201811485606 A CN 201811485606A CN 109658643 A CN109658643 A CN 109658643A
- Authority
- CN
- China
- Prior art keywords
- data
- volume
- prediction
- passengers
- flow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07G—REGISTERING THE RECEIPT OF CASH, VALUABLES, OR TOKENS
- G07G1/00—Cash registers
- G07G1/12—Cash registers electronically operated
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Security & Cryptography (AREA)
- Signal Processing (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses a kind of payment risk alarm method, server and intelligence POS, this method is applied to server, comprising: obtains the transaction data that intelligence POS is sent, and the Wi-Fi signal data for passing through Wi-Fi probe collection；The volume of the flow of passengers is determined according to the Wi-Fi signal data；By the volume of the flow of passengers and transaction data input prediction model, the prediction turnover in target time section is obtained；Obtain the real trade volume in the target time section；If the absolute difference of the real trade volume and prediction turnover is greater than preset threshold, it is determined that trading situation is abnormal, issues warning information.The safety of the fund based on intelligent POS payment can be improved in the application.
Description
Technical field
This application involves e-payment technical fields, more particularly to one kind is based on intelligent point-of-sale terminal (point of
Sale, POS) payment risk alarm method, server and intelligence POS.
Background technique
Intelligent POS is mainly used in retailing system as a kind of common electronic payment instrument, facilitates consumer
Customer carries out shopping clearing, more convenient, quick compared with cash settlement.It is universal with mobile payment, intelligent POS's
Trading volume welcomes explosive growth, and application scenarios are also more and more diversified, the peace that the e-payment based on intelligent POS is derived
Full problem is also increasingly prominent, how to guarantee the fund security paid based on intelligent POS, becomes current urgent problem to be solved.
Summary of the invention
The embodiment of the present application provides a kind of payment risk alarm method, to improve the fund based on intelligent POS payment
Safety, this method comprises:
The transaction data that intelligence POS is sent is obtained, and is visited by Wireless Fidelity (WIreless-FIdelity, Wi-Fi)
The Wi-Fi signal data of needle acquisition；The volume of the flow of passengers is determined according to the Wi-Fi signal data；By the volume of the flow of passengers and transaction data
Input prediction model obtains the prediction turnover in target time section；Obtain the real trade volume in the target time section；Such as
The absolute difference of real trade volume described in fruit and prediction turnover is greater than preset threshold, it is determined that trading situation is abnormal, issues
Warning information.
The embodiment of the present application provides a kind of payment risk alarm method, to improve the fund based on intelligent POS payment
Safety, this method comprises:
Pass through the Wi-Fi signal data of Wi-Fi probe collection user equipment (UE)；Transaction data and described is sent to server
Wi-Fi signal data, so that server determines whether trading situation is abnormal according to transaction data and Wi-Fi signal data.
The embodiment of the present application also provides a kind of server, should to improve the safety of the fund based on intelligent POS payment
Server includes:
Information collection module, the transaction data sent for obtaining intelligent POS, and the Wi- by Wi-Fi probe collection
Fi signal data；Wi-Fi probe data statistical module, the Wi-Fi signal for being obtained according to the information collection module
Data determine the volume of the flow of passengers；Associated data excavates module, the passenger flow for determining the Wi-Fi probe data statistical module
The transaction data input prediction model that amount and the information collection module obtain, obtains the prediction turnover in target time section；
The information collection module is also used to obtain the real trade volume in the target time section；Intelligent early-warning module, if for
The real trade volume and the associated data that the information collection module obtains excavate the prediction turnover of module prediction
Absolute difference is greater than preset threshold, it is determined that trading situation is abnormal, issues warning information.
The embodiment of the present application provides a kind of intelligence POS, should to improve the safety of the fund based on intelligent POS payment
Intelligent POS includes:
Wi-Fi probe module, for passing through the Wi-Fi signal data of Wi-Fi probe collection user equipment (UE)；Communicate mould
Block, for sending the Wi-Fi signal data that transaction data and the Wi-Fi probe module acquire to server, for clothes
Business device determines whether trading situation is abnormal according to transaction data and Wi-Fi signal data.
In the embodiment of the present application, the turnover of target time section is predicted by prediction model, and by the reality of target time section
Border volume is compared with prediction turnover, if the absolute value of difference is greater than default threshold between real trade volume and prediction turnover
Gap between value, i.e. real trade volume and prediction turnover is excessive, it is determined that and trading situation is abnormal, and issues warning information,
The timely alarm for abnormal conditions is realized, the safety of the fund based on intelligent POS payment is improved.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.In the accompanying drawings:
Fig. 1 is a kind of schematic diagram of payment system provided by the embodiments of the present application；
Fig. 2 is a kind of flow chart of payment risk alarm method provided by the embodiments of the present application；
Fig. 3 is the flow chart of another payment risk alarm method provided by the embodiments of the present application；
Fig. 4 is a kind of structural schematic diagram of server provided by the embodiments of the present application；
Fig. 5 is a kind of structural schematic diagram of intelligence POS provided by the embodiments of the present application.
Specific embodiment
For the purposes, technical schemes and advantages of the embodiment of the present application are more clearly understood, with reference to the accompanying drawing to this Shen
Please embodiment be described in further details.Here, illustrative embodiments of the present application and the description thereof are used to explain the present application, but simultaneously
Not as the restriction to the application.
The embodiment of the present application discloses a kind of payment risk alarm method, and this method is applied to payment system as shown in Figure 1
System 100.The payment system 100 include server 101, intelligence POS102 and at least one user equipment (User Equipment,
UE).Wherein, intelligent POS102 is used by trade company, is arranged in the management place where trade company, UE103 is by management place
The customer of shopping uses, server can be set bank or other be responsible in the mechanism for handling intelligent POS transaction.
Wi-Fi probe is installed in intelligent POS, can detect that a certain range of UE stops in management place when
Between, the Wi-Fi signals data such as the media access control address (Media Access Control Address, MAC Address) of UE.
After intelligent POS gets Wi-Fi signal data, Wi-Fi signal data and transaction data are sent to server 101, for
Server 101 carries out data summarization and the potential payment risk of analysis to the data received.Specifically, server carries out logarithm
According to the operation for carrying out data summarization and cleaning etc. and being promoted the quality of data, and to transaction data and Wi-Fi distributed number situation into
Row comprehensive analysis.
Optionally, server 101 can be Cloud Server or physical server etc..It can between server 101 and intelligence POS
To be connected by wired mode or wireless mode, specifically, wireless mode can be Wi-Fi, near-field communication (near field
Communication, NFC) etc..For the connection type between server and intelligence POS, it is not limited here.
Optionally, UE103 can be desktop type, laptop devices etc. with Wi-Fi network linkage function, specifically can be with
For mobile phone, plate, handheld computer, virtual reality (Virtual Reality, VR) equipment, augmented reality (Augmented
Reality, AR) equipment or wearable device etc..
As shown in Fig. 2, this method is applied to server, including step 201 to step 205:
Step 201 obtains the transaction data that intelligence POS is sent, and the Wi-Fi signal number for passing through Wi-Fi probe collection
According to.
Wherein, transaction data includes that profession identity, Transaction Account number, exchange hour and transaction results where intelligent data return
Code etc..Wi-Fi signal data include that information collection time, the MAC Address of UE, transmission channel, frame type and Wi-Fi signal are strong
The Wi-Fi title etc. that degree, UE are connected.
Wi-Fi probe is one of Wi-Fi equipment communication process signal frame, and the signal frame of the type is specifically used to detect
The Wi-Fi signal around the UE of Wi-Fi network can be connected, it can detect to obtain a certain range of Wi-Fi signal data,
Applied relatively broadly passenger flow statistics, analysis and in terms of.
Step 202 determines the volume of the flow of passengers according to Wi-Fi signal data.
In the embodiment of the present application, it is believed that the corresponding customer of a MAC Address, then when determining the volume of the flow of passengers
The quantity for the MAC Address for including in statistics Wi-Fi signal data, using the quantity of MAC Address as the volume of the flow of passengers.
It should be noted that server carries out persistent storage to the intelligent POS transaction data sent and the volume of the flow of passengers, so as to
Analytic learning is carried out in subsequent combination transaction data and the volume of the flow of passengers, timely update prediction model.
Step 203, by the volume of the flow of passengers and transaction data input prediction model, obtain the prediction turnover in target time section.
Target time section can be by being artificially configured, if prediction is from this trades time of origin, in three days or seven days
Turnover；Alternatively, target time section can also be set to some period in one day, such as 17 points to 21 of prediction work day
13 points to 15 points of the turnover at point or weekend, has thus obtained the stronger prediction result of specific aim.
By the volume of the flow of passengers and transaction data input prediction model, before obtaining the prediction turnover in target time section, need
First to establish prediction model.Before establishing prediction model, the historical trading data that available intelligence POS is sent, Yi Jili
History Wi-Fi signal data determine the history volume of the flow of passengers according to history Wi-Fi signal data.Later according in historical trading data
Historical trading data and the history volume of the flow of passengers are divided at least two data sets by exchange hour, and each data set is corresponding different
Period；By at least two datasets respectively as training data, prediction model is established using machine learning algorithm.
Illustratively, data set can be divided according to " period " in such as following table one, illustratively, according to the period
" WEEKDAY " divides data set, the data that exchange hour is Monday can be divided into a data and concentrated, exchange hour is Tuesday
Data be divided into data and concentrate, and and so on.For another example in view of legal festivals and holidays in addition to weekend, as the Spring Festival,
The volume of the flow of passengers and turnover of the festivals or holidays management place on International Labour Day, the Mid-autumn Festival, National Day etc. are generally higher than non-festivals or holidays, can incite somebody to action
Data of the exchange hour in festivals or holidays are divided to a data and concentrate.
It should be noted that data set can voluntarily be divided by the affiliated side of server according to actual conditions, for data set
Division mode, it is not limited here.
Table one
After determining data set, when establishing prediction model, target can be predicted with reference to " parameter " in following tables two
The turnover of period.Illustratively, for parameter " ROUBYDAY ", meaning is the day ring ratio on the same day, i.e. the turnover on the same day
With the ratio of the turnover of the day before yesterday, the mean value of the day ring ratio on the same day can be determined according to historical trading data, is being got in this way
It, can turnover and the same day using the turnover on the same day as the turnover of the day before yesterday, using the day before yesterday after the transaction data on the same day
The product of day ring ratio predict posteriori turnover.Using following different " parameters " predict target time section turnover it
Afterwards, final prediction turnover can be determined in conjunction with the turnover that different parameters are predicted.
Table two
| Parameter | Parameter meaning | Explanation |
| ROUBYDAY | The day ring ratio on the same day | Turnover/day before yesterday turnover on the same day |
| ROUBYWEK | The chow ring ratio on the same day | The turnover of the turnover on the same day/last week yesterday on the same day |
| ROUBYMON | The same day it is on a month-on-month basis | The turnover of the turnover on the same day/last month yesterday on the same day |
| ROUBYEAR | The calendar year ring ratio on the same day | The turnover on the same day/turnover of the last year yesterday Gregorian calendar on the same day |
| ROUBYEAR2 | The lunar calendar year ring ratio on the same day | The turnover on the same day/turnover of the last year yesterday lunar calendar on the same day |
| ROUBYEARWEK | The last year on the same day is the same as all number same day ring ratios | Turnover of the turnover on the same day/last year yesterday with all numbers on the same day |
Optionally, will at least two datasets respectively as training data, establish prediction model using machine learning algorithm,
It include: the data using the data of preset ratio in each data set as training data, in addition to the data of preset ratio as survey
Try data；At least two prediction models are established using at least two machine learning algorithms, utilize test data verifying at least two
The accuracy rate of prediction model；Weight is distributed according to the height of the accuracy rate of at least two prediction models, wherein accuracy rate gets over Gao Quan
It is again bigger.
Optionally, preset ratio can be 70%, i.e., remaining using in each data set 70% data as training data
30% data establish prediction model as test data, using training data, verify prediction model using test data later
Accuracy rate.
Optionally, machine learning algorithm can be the long short-term memory of Recognition with Recurrent Neural Network (Long Short Term
Memory, LSTM), random forest (Random Forest), extremely promote arest neighbors (Xgboost KNN) etc..Art technology
Personnel can also establish prediction model using other machines learning algorithm, quantity for used machine learning algorithm and
Type, it is not limited here.
In the case where determining at least two prediction models, by the volume of the flow of passengers and transaction data input prediction model, mesh is obtained
Mark the prediction turnover in the period, comprising: the volume of the flow of passengers and transaction data are inputted at least two prediction models, obtain at least two
A medium range forecast turnover；According at least two medium range forecast turnovers and the weight of corresponding prediction model, when determining prediction
Between prediction turnover in section.
Real trade volume in step 204, acquisition target time section.
Real trade volume is determined according to the transaction data that intelligent POS is sent in target time section.
If the absolute difference of step 205, real trade volume and prediction turnover is greater than preset threshold, it is determined that transaction
Situation is abnormal, issues warning information.
Preset threshold can be configured according to using the turnover of intelligent POS to fluctuate situation, illustratively, if intelligence
The turnover majority of POS is distributed between 20,000 to 2.2 ten thousand, then can set 2500 for preset threshold.Optionally, it is contemplated that
There is a certain error for prediction model itself, can be arranged referring concurrently to the turnover of intelligent POS and the error of prediction model
Preset threshold.For the specific size of preset threshold, it is not limited here.
It should be noted that prediction turnover can be a numerical value, it is also possible to a numberical range.If pre- test cross
Easy volume is a numberical range, then if real trade volume is fallen in except the numberical range, and wherein one with the numberical range
The absolute difference of a endpoint is greater than preset threshold, it is determined that trading situation is abnormal, issues warning information.Wherein, one of them
Endpoint is used to indicate illustratively to predict that turnover is between 20,000 to 2.5 ten thousand, in fact with the lesser endpoint of real trade volume difference
Border turnover is 1.6 ten thousand, and real trade volume is closer with 20,000, then by 1.6 ten thousand and 20,000 absolute difference 4,000 with preset
Threshold value is compared, if 4,000 are greater than preset threshold, it is determined that trading situation is abnormal, issues warning information.
In the embodiment of the present application, the turnover of target time section is predicted by prediction model, and by the reality of target time section
Border volume is compared with prediction turnover, if the absolute value of difference is greater than default threshold between real trade volume and prediction turnover
Gap between value, i.e. real trade volume and prediction turnover is excessive, it is determined that and trading situation is abnormal, and issues warning information,
The timely alarm for abnormal conditions is realized, the safety of the fund based on intelligent POS payment is improved.
The application also provides a kind of payment risk alarm method, is applied to intelligence POS, as shown in figure 3, this method includes step
Rapid 301 and step 302:
Step 301 passes through the Wi-Fi signal data of Wi-Fi probe collection UE.
Wi-Fi probe is at interval of the Wi-Fi signal around certain time acquisition, then by the Wi-Fi signal data of acquisition
It is uploaded to server, so that server carries out data analysis.Wherein, the time interval for acquiring surrounding Wi-Fi signal twice can be with
It is Fixed Time Interval, such as every the Wi-Fi signal of acquisition in 30 seconds or 2 minutes；Alternatively, can rule of thumb in management place
Different time in the number of the volume of the flow of passengers determine time interval, illustratively, it is contemplated that the passenger flow in festivals or holidays management place
It measures larger, shorter time interval, such as 10 seconds or 15 seconds can be set, with the volume of the flow of passengers size for the management place that timely updates；
In view of working day, the volume of the flow of passengers of 9 points to 17 management places is smaller, and longer time interval can be set, and such as 1 minute or 2 points
Clock etc., to save the resource occupied when Wi-Fi probe face.
Step 302 sends transaction data and Wi-Fi signal data to server, for server according to transaction data and
Wi-Fi signal data determine whether trading situation is abnormal.
In the embodiment of the present application, intelligent POS sends transaction data and Wi-Fi signal data to server in time, for clothes
Business device analyzes transaction data and Wi-Fi signal data, so that it is determined that whether the trading situation of intelligence POS there is exception,
And in the case where trading situation exception, warning information is issued, the timely alarm for abnormal conditions is realized, improves and be based on
The safety of the fund of intelligent POS payment.
The embodiment of the present application provides a kind of server, as shown in figure 4, the server 400 include information collection module 401,
Wi-Fi probe data statistical module 402, associated data excavate module 403 and intelligent early-warning module 404.
Wherein, information collection module 401, the transaction data sent for obtaining intelligent POS, and pass through Wi-Fi probe
The Wi-Fi signal data of acquisition.
Wi-Fi probe data statistical module 402, the Wi-Fi signal data for being obtained according to information collection module 401 are true
Determine the volume of the flow of passengers.
Associated data excavates module 403, the volume of the flow of passengers and information for determining Wi-Fi probe data statistical module 402
The transaction data input prediction model that collection module 401 obtains, obtains the prediction turnover in target time section.
Information collection module 401 is also used to obtain the real trade volume in target time section.
Intelligent early-warning module 404, if the real trade volume for information collection module 401 to obtain is excavated with associated data
The absolute difference for the prediction turnover that module 403 is predicted is greater than preset threshold, it is determined that trading situation is abnormal, issues alarm letter
Breath.
Optionally, Wi-Fi probe data statistical module 402, is used for:
Count the quantity for the MAC Address for including in the Wi-Fi signal data；
Using the quantity of the MAC Address as the volume of the flow of passengers.
Optionally, associated data excavates module 403, is used for:
Obtain the historical trading data and history Wi-Fi signal data that intelligence POS is sent；
The history volume of the flow of passengers is determined according to history Wi-Fi signal data；
According to the exchange hour in historical trading data, historical trading data and the history volume of the flow of passengers are divided at least two
In data set, each data set corresponds to the different periods；
By at least two datasets respectively as training data, prediction model is established using machine learning algorithm.
Optionally, associated data excavates module 403, is used for:
Data conduct using the data of preset ratio in each data set as training data, in addition to the data of preset ratio
Test data；
At least two prediction models are established using at least two machine learning algorithms, utilize test data verifying at least two
The accuracy rate of prediction model；
Weight is distributed according to the height of the accuracy rate of at least two prediction models, wherein accuracy rate is higher, and weight is bigger；
It is described to obtain the prediction turnover in target time section by the volume of the flow of passengers and transaction data input prediction model,
Include:
The volume of the flow of passengers and transaction data are inputted at least two prediction models, obtain at least two medium range forecasts transaction
Volume；
According at least two medium range forecast turnovers and the weight of corresponding prediction model, determine pre- in predicted time section
Survey turnover.
In the embodiment of the present application, the turnover of target time section is predicted by prediction model, and by the reality of target time section
Border volume is compared with prediction turnover, if the absolute value of difference is greater than default threshold between real trade volume and prediction turnover
Gap between value, i.e. real trade volume and prediction turnover is excessive, it is determined that and trading situation is abnormal, and issues warning information,
The timely alarm for abnormal conditions is realized, the safety of the fund based on intelligent POS payment is improved.
The embodiment of the present application also provides a kind of intelligence POS, as shown in figure 5, intelligence POS500 includes Wi-Fi probe module
501 and communication module 502.
Wherein, Wi-Fi probe module 501, for passing through the Wi-Fi signal data of Wi-Fi probe collection user equipment (UE).
Communication module 502, for sending the Wi-Fi signal that transaction data and Wi-Fi probe module 501 acquire to server
Data, so that server determines whether trading situation is abnormal according to transaction data and Wi-Fi signal data.
In the embodiment of the present application, intelligent POS sends transaction data and Wi-Fi signal data to server in time, for clothes
Business device analyzes transaction data and Wi-Fi signal data, so that it is determined that whether the trading situation of intelligence POS there is exception,
And in the case where trading situation exception, warning information is issued, the timely alarm for abnormal conditions is realized, improves and be based on
The safety of the fund of intelligent POS payment.
The embodiment of the present application provides a kind of computer equipment, including memory, processor and storage are on a memory and can
The computer program run on a processor, processor realize payment risk alarm method when executing computer program.
The embodiment of the present application provides a kind of computer readable storage medium, and computer-readable recording medium storage executes branch
Pay the computer program of risk alarm method.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Particular embodiments described above has carried out further in detail the purpose of the application, technical scheme and beneficial effects
It describes in detail bright, it should be understood that the foregoing is merely the specific embodiment of the application, is not used to limit the guarantor of the application
Range is protected, within the spirit and principles of this application, any modification, equivalent substitution, improvement and etc. done should be included in this
Within the protection scope of application.
Claims (10)
1. a kind of payment risk alarm method, which is characterized in that be applied to server, which comprises
Obtain the transaction data that intelligence POS is sent, and the Wi-Fi signal data for passing through Wi-Fi probe collection；
The volume of the flow of passengers is determined according to the Wi-Fi signal data；
By the volume of the flow of passengers and transaction data input prediction model, the prediction turnover in target time section is obtained；
Obtain the real trade volume in the target time section；
If the absolute difference of the real trade volume and prediction turnover is greater than preset threshold, it is determined that trading situation is different
Often, warning information is issued.
2. the method according to claim 1, wherein described determine the volume of the flow of passengers according to the Wi-Fi signal data,
Including
Count the quantity for the MAC Address for including in the Wi-Fi signal data；
Using the quantity of the MAC Address as the volume of the flow of passengers.
3. the method according to claim 1, wherein by the volume of the flow of passengers and transaction data input prediction mould
Type, before obtaining the prediction turnover in target time section, the method also includes；
Obtain the historical trading data and history Wi-Fi signal data that intelligence POS is sent；
The history volume of the flow of passengers is determined according to the history Wi-Fi signal data；
According to the exchange hour in the historical trading data, the historical trading data and the history volume of the flow of passengers are divided at least
In two datasets, each data set corresponds to the different periods；
By at least two datasets respectively as training data, prediction model is established using machine learning algorithm.
4. according to the method described in claim 3, it is characterized in that, it is described will at least two datasets respectively as training number
According to establishing prediction model using machine learning algorithm, comprising:
Using the data of preset ratio in each data set as training data, the data in addition to the data of preset ratio are as test
Data；
At least two prediction models are established using at least two machine learning algorithms, utilize at least two prediction of test data verifying
The accuracy rate of model；
Weight is distributed according to the height of the accuracy rate of at least two prediction models, wherein accuracy rate is higher, and weight is bigger；
It is described by the volume of the flow of passengers and transaction data input prediction model, obtain the prediction turnover in target time section, comprising:
The volume of the flow of passengers and transaction data are inputted at least two prediction models, obtain at least two medium range forecast turnovers；
According at least two medium range forecast turnovers and the weight of corresponding prediction model, the pre- test cross in predicted time section is determined
Easy volume.
5. a kind of payment risk alarm method, which is characterized in that be applied to intelligence POS, which comprises
Pass through the Wi-Fi signal data of Wi-Fi probe collection user equipment (UE)；
Transaction data and the Wi-Fi signal data are sent to server, so that server is according to transaction data and Wi-Fi signal
Data determine whether trading situation is abnormal.
6. a kind of server, which is characterized in that the server includes:
Information collection module, the transaction data sent for obtaining intelligent POS, and believed by the Wi-Fi of Wi-Fi probe collection
Number；
Wi-Fi probe data statistical module, the Wi-Fi signal data for being obtained according to the information collection module determine
The volume of the flow of passengers；
Associated data excavates module, the volume of the flow of passengers and the letter for determining the Wi-Fi probe data statistical module
The transaction data input prediction model that collection module obtains is ceased, the prediction turnover in target time section is obtained；
The information collection module is also used to obtain the real trade volume in the target time section；
Intelligent early-warning module, if the real trade volume for the information collection module to obtain is dug with the associated data
The absolute difference for digging the prediction turnover of module prediction is greater than preset threshold, it is determined that trading situation is abnormal, issues alarm letter
Breath.
7. server according to claim 6, which is characterized in that the associated data excavates module, is used for:
Obtain the historical trading data and history Wi-Fi signal data that intelligence POS is sent；
The history volume of the flow of passengers is determined according to the history Wi-Fi signal data；
According to the exchange hour in the historical trading data, the historical trading data and the history volume of the flow of passengers are divided at least
In two datasets, each data set corresponds to the different periods；
By at least two datasets respectively as training data, prediction model is established using machine learning algorithm.
8. a kind of intelligence POS, which is characterized in that the intelligence POS includes:
Wi-Fi probe module, for passing through the Wi-Fi signal data of Wi-Fi probe collection user equipment (UE)；
Communication module, for sending the Wi-Fi signal number that transaction data and the Wi-Fi probe module acquire to server
According to so that server determines whether trading situation is abnormal according to transaction data and Wi-Fi signal data.
9. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes any side of claim 1 to 5 when executing the computer program
Method.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has perform claim
It is required that the computer program of 1 to 5 any the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811485606.3A CN109658643B (en) | 2018-12-06 | 2018-12-06 | Payment risk warning method, server and intelligent POS (point of sale) |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811485606.3A CN109658643B (en) | 2018-12-06 | 2018-12-06 | Payment risk warning method, server and intelligent POS (point of sale) |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109658643A true CN109658643A (en) | 2019-04-19 |
| CN109658643B CN109658643B (en) | 2021-04-27 |
Family
ID=66112476
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811485606.3A Active CN109658643B (en) | 2018-12-06 | 2018-12-06 | Payment risk warning method, server and intelligent POS (point of sale) |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109658643B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443374A (en) * | 2019-08-14 | 2019-11-12 | 腾讯科技（深圳）有限公司 | A kind of resource information processing method, device and equipment |
| CN111324867A (en) * | 2020-02-25 | 2020-06-23 | 支付宝(杭州)信息技术有限公司 | Suspected risk transaction determination method, device and equipment |
| CN113706045A (en) * | 2021-09-02 | 2021-11-26 | 工银科技有限公司 | Fund payment method, apparatus, device, medium and program product |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060287947A1 (en) * | 2005-06-16 | 2006-12-21 | Toms Alvin D | Non-payment risk assessment |
| CN102346941A (en) * | 2011-05-23 | 2012-02-08 | 北京播思软件技术有限公司 | Financial transaction detection and prompting system and implementation method thereof |
| CN104915842A (en) * | 2015-06-04 | 2015-09-16 | 浙江力石科技股份有限公司 | Electronic commerce transaction monitoring method based on internet transaction data |
| CN106251578A (en) * | 2016-08-19 | 2016-12-21 | 深圳奇迹智慧网络有限公司 | Artificial abortion's early warning analysis method and system based on probe |
-
2018
- 2018-12-06 CN CN201811485606.3A patent/CN109658643B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060287947A1 (en) * | 2005-06-16 | 2006-12-21 | Toms Alvin D | Non-payment risk assessment |
| CN102346941A (en) * | 2011-05-23 | 2012-02-08 | 北京播思软件技术有限公司 | Financial transaction detection and prompting system and implementation method thereof |
| CN104915842A (en) * | 2015-06-04 | 2015-09-16 | 浙江力石科技股份有限公司 | Electronic commerce transaction monitoring method based on internet transaction data |
| CN106251578A (en) * | 2016-08-19 | 2016-12-21 | 深圳奇迹智慧网络有限公司 | Artificial abortion's early warning analysis method and system based on probe |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443374A (en) * | 2019-08-14 | 2019-11-12 | 腾讯科技（深圳）有限公司 | A kind of resource information processing method, device and equipment |
| CN110443374B (en) * | 2019-08-14 | 2024-07-12 | 腾讯科技（深圳）有限公司 | Resource information processing method, device and equipment |
| CN111324867A (en) * | 2020-02-25 | 2020-06-23 | 支付宝(杭州)信息技术有限公司 | Suspected risk transaction determination method, device and equipment |
| CN111324867B (en) * | 2020-02-25 | 2023-03-31 | 支付宝（中国）网络技术有限公司 | Suspected risk transaction determination method, device and equipment |
| CN113706045A (en) * | 2021-09-02 | 2021-11-26 | 工银科技有限公司 | Fund payment method, apparatus, device, medium and program product |
| CN113706045B (en) * | 2021-09-02 | 2024-05-10 | 工银科技有限公司 | Funds payment method, apparatus, device, medium and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109658643B (en) | 2021-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9661012B2 (en) | Systems and methods for identifying information related to payment card breaches | |
| US20190259095A1 (en) | Determining present and future virtual balances for a client computing device | |
| US20170024828A1 (en) | Systems and methods for identifying information related to payment card testing | |
| US8768809B1 (en) | Methods and systems for managing financial data | |
| US11403645B2 (en) | Systems and methods for cross-border ATM fraud detection | |
| CN109658643A (en) | Payment risk alarm method, server and intelligence POS | |
| US10701163B2 (en) | Lines prediction model | |
| US20200234307A1 (en) | Systems and methods for detecting periodic patterns in large datasets | |
| CN109034493A (en) | A kind of account balance prediction technique and device | |
| US11907942B2 (en) | Blockchain network risk management universal blockchain data model | |
| CN112581270A (en) | Risk account identification method and device, electronic equipment and storage medium | |
| CN112734516A (en) | Financial product recommendation method and system based on client cash flow prediction | |
| US10402764B2 (en) | Systems and methods of controlling quantities of denominations of currency at a retail shopping facility | |
| CN114282998A (en) | Foreign currency account balance processing method and device | |
| CN113610323A (en) | Cash demand prediction method and device for bank self-service equipment | |
| CA2898945C (en) | Predictive fraud screening | |
| JP6771513B2 (en) | Devices and methods for calculating default probability and programs for it | |
| CN111429251A (en) | Method and device for processing data under multiple modes | |
| US11900448B2 (en) | Liquidity engine | |
| CN111583010A (en) | Data processing method, device, equipment and storage medium | |
| US20210248512A1 (en) | Intelligent machine learning recommendation platform | |
| US11514516B2 (en) | Banking operation support system, banking operation support method, and banking operation support program | |
| CN112116253A (en) | Method, device and system for selecting central mesh point | |
| US20240259410A1 (en) | Systems and methods for triangular timestamp transformation in computer messaging | |
| US20230376874A1 (en) | An apparatus, method and computer program product for determining a level of risk |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |