CN117273922A - Transaction early warning method, device, computer equipment and storage medium - Google Patents
Transaction early warning method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117273922A CN117273922A CN202311004053.6A CN202311004053A CN117273922A CN 117273922 A CN117273922 A CN 117273922A CN 202311004053 A CN202311004053 A CN 202311004053A CN 117273922 A CN117273922 A CN 117273922A
- Authority
- CN
- China
- Prior art keywords
- transaction
- target
- risk
- target transaction
- early warning
- 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 54
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000005070 sampling Methods 0.000 claims description 73
- 238000013058 risk prediction model Methods 0.000 claims description 42
- 238000004590 computer program Methods 0.000 claims description 37
- 230000015654 memory Effects 0.000 claims description 28
- 230000005856 abnormality Effects 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 20
- 238000004140 cleaning Methods 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 230000007787 long-term memory Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 abstract description 16
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000006243 chemical reaction Methods 0.000 abstract 5
- 238000004519 manufacturing process Methods 0.000 description 17
- 230000008569 process Effects 0.000 description 11
- 238000012544 monitoring process Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000000246 remedial effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000012216 screening Methods 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- 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)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a transaction early warning method, a transaction early warning device, computer equipment and a storage medium, relates to the technical field of artificial intelligence, and can be applied to the financial field or other technical fields. The method comprises the following steps: responding to a payment request of a target user, and displaying an asset conversion interface to the target user; the asset conversion interface comprises asset information of at least two contracted applications of a target user; determining a target application from at least two signed applications according to application selection operation of the target user on the asset conversion interface; according to the asset conversion rate between the target application and the payment application, converting the asset information of the target user in the target application to obtain a converted asset in the payment application; the payment request is performed using the conversion asset. By adopting the method, the abnormal transaction condition can be predicted in advance, so that serious influence on the service server is avoided.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence, and in particular, to a transaction early warning method, apparatus, computer device, and storage medium, which may be applied to the financial field or other technical fields.
Background
With the rapid development of internet technology, internet technology has gradually penetrated into the financial industry. The whole transaction process of internet finance is almost completely finished on the internet, and the transaction amount generated by the finance software is increased.
At present, financial software checks whether a transaction is stable or not through real-time monitoring, and can discover production problems, such as common problems, at the first time through monitoring: the transaction amount is excessively large, the business server is down, and the like. However, by monitoring this way in real time, in the case of finding a problem and giving an alarm, an abnormal situation has occurred, that is, a serious influence has been caused on the service server, so improvement is demanded.
Disclosure of Invention
Based on this, it is necessary to provide a transaction early warning method, a device, a computer device and a storage medium, which can predict abnormal conditions of transactions in advance, so as to avoid serious influence on a service server.
In a first aspect, the present application provides a transaction pre-warning method. The method comprises the following steps:
constructing a transaction sequence of the target transaction in a target time period according to target transaction data of the target transaction at each sampling moment in the target time period;
inputting the transaction sequence into a risk prediction model to obtain risk probability of abnormality of the target transaction in a future period;
and carrying out risk early warning processing on the target transaction according to the risk probability.
In one embodiment, the constructing a transaction sequence of the target transaction in the target time period according to the target transaction data of each sampling time of the target transaction in the target time period includes:
extracting key transaction data corresponding to each sampling moment from target transaction data of each sampling moment of the target transaction in a target period according to key indexes corresponding to the target transaction;
and constructing a transaction sequence of the target transaction in the target period according to the key transaction data corresponding to each sampling moment.
In one embodiment, the performing risk early warning on the target transaction according to the risk probability includes:
comparing the risk probability with a risk threshold corresponding to the target transaction;
and if the risk probability is greater than the risk threshold, outputting risk early warning information comprising a transaction identifier of the target transaction.
In one embodiment, the method further comprises:
constructing a risk early warning curve of the target transaction according to risk early warning conditions of the target transaction at each historical moment in a historical period;
and determining a risk threshold of the target transaction in the future period according to the risk early warning curve.
In one embodiment, the risk prediction model is comprised of a convolutional neural network and a long-term memory network.
In one embodiment, the method further comprises:
acquiring original transaction data of a target transaction at each sampling moment in a target period;
and cleaning the original transaction data to obtain target transaction data of the target transaction at each sampling moment in the target period.
In a second aspect, the present application further provides a transaction pre-warning device. The device comprises:
the construction module is used for constructing a transaction sequence of the target transaction in the target time period according to the target transaction data of the target transaction at each sampling moment in the target time period;
the prediction module is used for inputting the transaction sequence into a risk prediction model to obtain the risk probability of abnormality of the target transaction in a future period;
and the early warning module carries out risk early warning processing on the target transaction according to the risk probability.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
constructing a transaction sequence of the target transaction in a target time period according to target transaction data of the target transaction at each sampling moment in the target time period;
inputting the transaction sequence into a risk prediction model to obtain risk probability of abnormality of the target transaction in a future period;
and carrying out risk early warning processing on the target transaction according to the risk probability.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
constructing a transaction sequence of the target transaction in a target time period according to target transaction data of the target transaction at each sampling moment in the target time period;
inputting the transaction sequence into a risk prediction model to obtain risk probability of abnormality of the target transaction in a future period;
and carrying out risk early warning processing on the target transaction according to the risk probability.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
constructing a transaction sequence of the target transaction in a target time period according to target transaction data of the target transaction at each sampling moment in the target time period;
inputting the transaction sequence into a risk prediction model to obtain risk probability of abnormality of the target transaction in a future period;
and carrying out risk early warning processing on the target transaction according to the risk probability.
According to the transaction early warning method, the transaction early warning device, the computer equipment and the storage medium, a risk early warning model is introduced, and a transaction sequence of target transaction in a target period is constructed according to target transaction data of the target transaction at each sampling moment in the target period; inputting the transaction sequence into a risk prediction model to obtain the risk probability of abnormality of the target transaction in a future period; and then, performing risk early warning processing on the target transaction according to the risk probability. According to the scheme, the probability of abnormality of the target transaction in the future period can be predicted based on the risk prediction model by utilizing the target transaction data, namely, the possible risk is predicted in advance, and remedial measures are taken in time before the problem occurs, so that the occurrence of abnormal conditions is effectively avoided, and serious influence on a service server is avoided.
Drawings
FIG. 1 is an application environment diagram of a transaction pre-warning method in one embodiment;
FIG. 2 is a flow chart of a transaction pre-warning method according to an embodiment;
FIG. 3 is a flow diagram of a build transaction sequence in one embodiment;
FIG. 4 is a schematic diagram of a production log of target transactions in one embodiment;
FIG. 5 is a flow chart of risk early warning for a target transaction in one embodiment;
FIG. 6 is a flow diagram of acquiring target transaction data in one embodiment;
FIG. 7 is a flow chart of a transaction pre-warning method according to another embodiment;
FIG. 8 is a block diagram of a transaction pre-warning device in one embodiment;
fig. 9 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The transaction early warning method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the operation and maintenance terminal 102 communicates with the monitoring server 104 through a network. The data storage system may store data that the monitoring server 104 needs to process, such as target transaction data for each sample time instant of a target transaction during a target period. The data storage system may be integrated on the monitoring server 104 or may be located on the cloud or other network server. After the monitoring server 104 acquires target transaction data of each sampling moment of the target transaction in a target time period, a transaction sequence of the target transaction in the target time period is constructed; inputting the transaction sequence into a risk prediction model to obtain the risk probability of abnormality of the target transaction in a future period; and finally, according to the risk probability, early warning risk early warning information is sent to the operation and maintenance terminal 102, and risk early warning is carried out on the target transaction. The operation and maintenance terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, etc. The monitoring server 104 may be implemented as a stand-alone server or as a cluster of servers.
In one embodiment, as shown in fig. 2, a transaction pre-warning method is provided, which is taken as an example of application of the method to the monitoring server 104 in fig. 1, and includes the following steps:
s202, constructing a transaction sequence of the target transaction in the target time period according to the target transaction data of the target transaction at each sampling moment in the target time period.
The target period of time refers to a preset period of time, and may be, for example, a period of time before the current time, for example, 5 minutes or 10 minutes. The sampling time can be determined according to a preset sampling frequency; alternatively, the sampling instant may be accurate to seconds.
The target transaction may be any transaction that the business server is capable of conducting; alternatively, the target transaction may include one or more services. The target transaction data are various index data generated in the target transaction process, and can be obtained from a production log of the target transaction stored in the service server. Production logs refer to transaction information for each target transaction occurrence process, including, for example, but not limited to, transaction codes, transaction time, transaction quantity, transaction effort, transaction success rate, and the like.
Alternatively, the target transaction data of the target transaction at each sampling time may be ordered according to a time sequence, and the ordering result is used as a transaction sequence of the target transaction at the target time period.
For example, the risk early-warning period of the target transaction is 5 minutes, the production logs of each sampling moment in the current risk early-warning period can be obtained to obtain target transaction data, and the target transaction data are arranged according to the time sequence, namely, a transaction sequence of the target transaction within 5 minutes is constructed.
S204, inputting the transaction sequence into a risk prediction model to obtain the risk probability of abnormality of the target transaction in a future period.
The risk prediction model is a neural network model, and can be used for predicting the probability of risk of a transaction in a future period of time. Optionally, the risk prediction model in the embodiment of the present application is formed by a convolutional neural network and a long-short-term memory network, where the convolutional neural network is used to extract digital spatial information features of a transaction sequence, and the long-short-term memory network is used to extract time sequence features of the transaction sequence, so as to classify and predict probability that the transaction sequence is an outlier, that is, consider probability that a target transaction is problematic, that is, risk probability.
By way of example, the risk prediction model may be obtained by the following training process:
step one: the method comprises the steps of obtaining a sample set, obtaining the sample set through a production log of nearly three months, extracting key transaction data of target transactions from the production log, namely, forming input data of a risk prediction model by a transaction code, a transaction time, a transaction quantity, a transaction effort and a transaction success rate at each moment in a fixed time period, and marking a normal value (for example, 0) or an abnormal value (for example, 1) corresponding to the input data at each moment as output of the risk prediction model.
Step two: the risk prediction model is built based on a convolutional neural network and a long-short-term memory network, for example, various functions provided by a Python language and a Pytorch library are adopted, convolutional operation, the long-short-term memory network, pooling, full connection, a loss function, two classification functions and the like are adopted, and the risk prediction model of the adaptive sample set is built.
Step three: training a risk prediction model, dividing the sample set obtained in the first step into a plurality of sub-sample sets, inputting the sub-sample sets into the risk prediction model built in the second step, training the risk prediction model, adjusting the risk prediction model parameters in an optimization mode of a random gradient descent function through counter propagation, updating the parameters through multiple iterations, and obtaining each parameter value of the risk prediction model when the loss function descends to a specified value to form the trained risk prediction model.
The future time period corresponds to the target time period, namely the duration of the future time period is the same as the duration of the target time period; further, the target period is 5 minutes before the current time, the future period is 5 minutes after the current time, and each sampling time of the target period corresponds to each future time of the future period.
Optionally, after the transaction sequence is input into the trained risk prediction model, the risk prediction model predicts a risk probability of abnormality of the target transaction at each future time of the future period.
S206, performing risk early warning processing on the target transaction according to the risk probability.
Alternatively, the risk probability of each future time in the future period may be obtained by the risk prediction model, so that a risk threshold may be set for the future period, or a risk threshold may be set for each future time in the future period.
Further, after the risk probability of the target transaction is obtained, based on the risk threshold set in advance, risk early warning is performed on the target transaction when the risk probability at any future time exceeds the risk threshold. Or if the risk probability exceeds the risk threshold value at each future time, the number of the future times is more than half of the total number of all the future times, risk early warning is carried out on the target transaction, and the like.
Optionally, different early warning modes can be set according to the influence degree of the target transaction on the production risk, for example, the transaction type with larger influence degree on the production risk can be set into a striking and easy-to-notice mode such as voice broadcasting, the transaction type with smaller influence degree on the production risk can be set into mail, red mark and the like, and meanwhile, the voice broadcasting content or the mail carries risk early warning information comprising the transaction identifier of the target transaction.
Further, if the risk probability of any future moment in the future period is not greater than the risk threshold, risk early warning is not carried out on the target transaction. Or if the risk probability exceeds the risk threshold value at each future time, the number of the future times is less than half of the total number of all the future times, risk early warning is not performed on the target transaction, and the like.
It should be noted that the target transaction data can reflect server performance and resource utilization, network conditions, and other faults to some extent. For example: the target transaction is longer in time consumption than the prior art, and the possible thread occupation is presumed to be more; the success rate of the target transaction is reduced, and the possible network congestion is presumed; furthermore, according to the early warning information content of the target transaction, the problem can be analyzed and checked, and corresponding solving measures can be made, so that the influence and loss are minimized.
In the transaction early warning method, a transaction sequence of the target transaction in the target time period is constructed according to the target transaction data of the target transaction at each sampling moment in the target time period by introducing a risk early warning model; inputting the transaction sequence into a risk prediction model to obtain the risk probability of abnormality of the target transaction in a future period; and then, performing risk early warning processing on the target transaction according to the risk probability. According to the scheme, the probability of abnormality of the target transaction in the future period can be predicted based on the risk prediction model by utilizing the target transaction data, namely, the possible risk is predicted in advance, and remedial measures are taken in time before the problem occurs, so that the occurrence of abnormal conditions is effectively avoided, and serious influence on a service server is avoided.
It will be appreciated that the target transaction data includes multi-dimensional data and there is no useful data, so that in order to reduce the amount of subsequent computation, on the basis of the above embodiments, the embodiments of the present application provide an alternative way of constructing a transaction sequence. As shown in fig. 3, the method specifically comprises the following steps:
s302, extracting key transaction data corresponding to each sampling moment from target transaction data of each sampling moment of the target transaction in a target period according to the key indexes corresponding to the target transaction.
The formats of the target transaction data at each sampling time in the target period are the same, and the target transaction data are extracted from the production log, as shown in fig. 4, wherein '2023-02-02:02:00' represents transaction time, '6' represents transaction quantity, '2' represents transaction work amount, '0.33' represents transaction success rate, '25' represents transaction time consumption, the unit is millisecond, and 'XXXXXX' represents transaction code and the like.
Since useless data exists in the target transaction data, in order to improve the processing efficiency, key transaction data in the target transaction data, namely data corresponding to key indexes in the target transaction data, can be extracted. The key index refers to an index capable of reflecting target transaction, and can be, but is not limited to, transaction codes, transaction time, transaction quantity, transaction work amount, transaction success rate, transaction time consumption and the like; the key transaction data refers to data corresponding to key indexes extracted from the target transaction data.
S304, constructing a transaction sequence of the target transaction in the target period according to the key transaction data corresponding to each sampling moment.
Optionally, extracting key transaction data in the target transaction data, then sorting the key transaction data of the target transaction at each sampling moment according to the time sequence, and taking the sorting result as a transaction sequence of the target transaction in the target period.
In this embodiment, by extracting the key transaction data corresponding to each sampling time, the transaction data having little or no influence on the production risk is filtered, and the accuracy and efficiency of the subsequent prediction of the production risk probability are improved.
In order to early warn of abnormal situations of a target transaction, the early warning needs to be performed according to a risk probability and a risk threshold, and in one embodiment, as shown in fig. 5, the early warning determining process according to the risk probability and the risk threshold specifically includes the following steps:
s502, comparing the risk probability with a risk threshold corresponding to the target transaction.
The risk threshold value can be determined according to historical risk early warning conditions; specifically, a risk early warning curve of the target transaction can be constructed according to risk early warning conditions of the target transaction at each historical moment in a historical period, and then a risk threshold of the target transaction in a future period is determined according to the risk early warning curve.
Wherein, the history period refers to a period before the target period, and the history time refers to any time in the history period; the risk early warning condition of any historical moment can comprise that the risk early warning is carried out on the target transaction at the historical moment, and the risk threshold value of the historical moment; or the risk early warning is not carried out on the target transaction at the historical moment, and the risk threshold value at the historical moment is included.
The risk early warning curve of the target transaction reflects the change of the risk threshold of the target transaction in a past period of time to a certain extent. Optionally, the time is taken as a horizontal axis, the risk threshold is taken as a vertical axis, and the risk early warning curve of the target transaction can be constructed according to the risk early warning conditions of the target transaction at each historical moment in the historical period. Further, after the risk early warning curve is constructed, the risk threshold value of the future period can be predicted according to the fluctuation condition of the risk early warning curve. The risk threshold corresponding to each future time in the future period can be predicted.
It can be understood that the future risk threshold is determined according to the risk early-warning condition at the historical moment, so that the risk threshold is set more dependently and reasonably, and further, the risk early warning is more accurate.
Specifically, after the risk probability output by the risk prediction model of the target transaction in the target time period is obtained, the risk probability is compared with a risk threshold value determined according to the historical risk early warning condition, and early warning is carried out according to the comparison result.
And S504, outputting risk early warning information comprising the transaction identification of the target transaction if the risk probability is greater than the risk threshold.
If the risk probability is greater than the risk threshold, it indicates that the target transaction is most likely to be abnormal in a future period of time, where the abnormality generally includes that the target transaction takes longer time than before, has an excessively low transaction success rate, and the like; the risk probability being greater than the risk threshold specifically includes: the risk probability at any future time exceeds the risk threshold, or the number of future times at which the risk probability exceeds the risk threshold at each future time is greater than half the total number of all future times.
The transaction identifier of the target transaction refers to a symbol for identifying the target transaction, such as a name of the target transaction or a transaction code of the target transaction, and is used for indicating the abnormal target transaction type during early warning.
Optionally, if the risk probability of any future time exceeds the risk threshold, or if the number of future times in which the risk probability exceeds the risk threshold is greater than half of the total number of all future times, then risk early warning information including the transaction identifier of the target transaction is sent to the operation and maintenance terminal.
In this embodiment, through the risk early warning information, the problem can be found before the abnormal situation of the target transaction occurs, so that early precaution can be performed, and the abnormal situation of the target transaction is avoided.
It should be noted that, the production log data of each time in the target period directly acquired needs to be processed, so as to obtain the target transaction data of each sampling time of the target transaction in the target period, and on the basis of the above embodiment, in one embodiment, as shown in fig. 6, the process of acquiring the target transaction data is related, and specifically includes the following steps:
s602, acquiring original transaction data of each sampling moment of a target transaction in a target period.
Wherein the original transaction data is the data of a production log file of the directly acquired, unprocessed target transaction.
For example, the data of the production log record of the target transaction may be periodically grabbed using a grabbing tool, such as every 5 minutes.
S604, cleaning the original transaction data to obtain target transaction data of the target transaction at each sampling moment in the target period.
The cleaning process refers to a process of screening abnormal data in the original transaction data, wherein the abnormal data can be blank data, obvious error data and the like.
Optionally, after the original transaction data of each sampling moment of the target transaction in the target period is obtained, the abnormal data in each original transaction data can be cleaned by a data processing tool, blank data can be removed, and the target transaction data of each sampling moment can be obtained by selecting to re-capture after the obvious error data is removed.
In the embodiment, the original data is cleaned, abnormal data is removed, so that the prediction result of the risk early-warning model is more accurate, and the accuracy of risk early warning is improved.
Fig. 7 is a schematic flow chart of a transaction pre-warning method in another embodiment, and on the basis of the foregoing embodiment, this embodiment provides an alternative example of the transaction pre-warning method. With reference to fig. 7, the specific implementation procedure is as follows:
s701, acquiring original transaction data of each sampling moment of a target transaction in a target period.
S702, cleaning the original transaction data to obtain target transaction data of the target transaction at each sampling moment in the target period.
S703, extracting the key transaction data corresponding to each sampling time from the target transaction data of each sampling time in the target period according to the key index corresponding to the target transaction.
S704, constructing a transaction sequence of the target transaction in the target period according to the key transaction data corresponding to each sampling moment.
S705, inputting the transaction sequence into a risk prediction model to obtain the risk probability of abnormality of the target transaction in a future period.
S706, constructing a risk early warning curve of the target transaction according to the risk early warning conditions of the target transaction at each historical moment in the historical period.
And S707, determining a risk threshold of the target transaction in a future period according to the risk early warning curve.
And S708, performing risk early warning processing on the target transaction according to the risk probability and the risk threshold.
Specifically, the risk probability is compared with a risk threshold corresponding to the target transaction; and if the risk probability is greater than the risk threshold, outputting risk early warning information comprising the transaction identification of the target transaction.
The specific process of S701 to S708 may refer to the description of the foregoing method embodiment, and its implementation principle and technical effects are similar, and are not repeated herein.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a transaction early-warning device for realizing the transaction early-warning method. The implementation scheme of the solution provided by the device is similar to the implementation scheme described in the above method, so the specific limitation in one or more embodiments of the transaction early-warning device provided below may refer to the limitation of the transaction early-warning method hereinabove, and will not be repeated here.
In one embodiment, as shown in fig. 8, there is provided a transaction pre-warning device 1, including: a construction module 10, a prediction module 20 and an early warning module 30, wherein:
the construction module 10 is configured to construct a transaction sequence of the target transaction in the target time period according to the target transaction data of the target transaction at each sampling time in the target time period;
the prediction module 20 inputs the transaction sequence into a risk prediction model to obtain risk probability of abnormality of the target transaction in a future period;
the early warning module 30 performs risk early warning processing on the target transaction according to the risk probability.
In the transaction early warning device, a transaction sequence of the target transaction in the target time period is constructed according to the target transaction data of the target transaction at each sampling moment in the target time period by introducing a risk early warning model; inputting the transaction sequence into a risk prediction model to obtain the risk probability of abnormality of the target transaction in a future period; and then, performing risk early warning on the target transaction according to the risk probability. According to the scheme, the probability of abnormality of the target transaction in the future period can be predicted based on the risk prediction model by utilizing the target transaction data, namely, the possible risk is predicted in advance, and remedial measures are taken in time before the problem occurs, so that the occurrence of abnormal conditions is effectively avoided, and serious influence on a service server is avoided.
In one embodiment, the building block 10 is specifically configured to:
extracting key transaction data corresponding to each sampling moment from target transaction data of each sampling moment of target transaction in a target period according to key indexes corresponding to the target transaction; and constructing a transaction sequence of the target transaction in the target period according to the key transaction data corresponding to each sampling moment.
In one embodiment, the early warning module 30 in fig. 8 may be specifically configured to:
comparing the risk probability with a risk threshold corresponding to the target transaction; and if the risk probability is greater than the risk threshold, outputting risk early warning information comprising the transaction identification of the target transaction.
In one embodiment, the transaction pre-warning device 1 further comprises: a threshold determination module, the threshold determination module may be configured to:
constructing a risk early warning curve of the target transaction according to the risk early warning conditions of the target transaction at each historical moment in the historical period; and determining a risk threshold of the target transaction in a future period according to the risk early warning curve.
In one embodiment, the transaction pre-warning device 1 further comprises:
the data acquisition module is used for acquiring original transaction data of each sampling moment of the target transaction in the target period;
and the data cleaning module is used for cleaning all the original transaction data to obtain target transaction data of all the sampling moments of the target transaction in the target period.
The modules in the transaction early warning device can be realized in whole or in part by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 9. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing production log information of the target transaction occurrence process, and can be specifically stored in a format of a txt file. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a transaction pre-warning method.
It will be appreciated by those skilled in the art that the structure shown in fig. 9 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the computer device to which the present application applies, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
constructing a transaction sequence of the target transaction in the target time period according to the target transaction data of the target transaction at each sampling moment in the target time period;
inputting the transaction sequence into a risk prediction model to obtain the risk probability of abnormality of the target transaction in a future period;
and carrying out risk early warning processing on the target transaction according to the risk probability.
In one embodiment, the processor executes the computer program to construct a transaction sequence of the target transaction in the target time period according to the target transaction data of each sampling time point of the target transaction in the target time period, and the following steps are further realized:
extracting key transaction data corresponding to each sampling moment from target transaction data of each sampling moment of target transaction in a target period according to key indexes corresponding to the target transaction; and constructing a transaction sequence of the target transaction in the target period according to the key transaction data corresponding to each sampling moment.
In one embodiment, the execution of the computer program by the processor performs the following steps when performing risk early warning on the target transaction according to the risk probability:
comparing the risk probability with a risk threshold corresponding to the target transaction; and if the risk probability is greater than the risk threshold, outputting risk early warning information comprising the transaction identification of the target transaction.
In one embodiment, the processor when executing the computer program further performs the steps of:
constructing a risk early warning curve of the target transaction according to the risk early warning conditions of the target transaction at each historical moment in the historical period; and determining a risk threshold of the target transaction in a future period according to the risk early warning curve.
In one embodiment, the risk prediction model is comprised of a convolutional neural network and a long-term memory network when the processor executes the computer program.
In one embodiment, the processor when executing the computer program further performs the steps of:
acquiring original transaction data of a target transaction at each sampling moment in a target period; and cleaning the original transaction data to obtain target transaction data of the target transaction at each sampling moment in the target period.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
constructing a transaction sequence of the target transaction in the target time period according to the target transaction data of the target transaction at each sampling moment in the target time period;
inputting the transaction sequence into a risk prediction model to obtain the risk probability of abnormality of the target transaction in a future period;
and carrying out risk early warning processing on the target transaction according to the risk probability.
In one embodiment, the computer program constructs a target transaction based on target transaction data for each sampling instant of the target transaction during the target time period, the transaction sequence of the target transaction during the target time period when executed by the processor further implementing the steps of:
extracting key transaction data corresponding to each sampling moment from target transaction data of each sampling moment of target transaction in a target period according to key indexes corresponding to the target transaction; and constructing a transaction sequence of the target transaction in the target period according to the key transaction data corresponding to each sampling moment.
In one embodiment, the computer program further performs the following steps when executing the risk pre-warning for the target transaction by the processor according to the risk probability:
comparing the risk probability with a risk threshold corresponding to the target transaction; and if the risk probability is greater than the risk threshold, outputting risk early warning information comprising the transaction identification of the target transaction.
In one embodiment, the computer program when executed by the processor further performs the steps of:
constructing a risk early warning curve of the target transaction according to the risk early warning conditions of the target transaction at each historical moment in the historical period; and determining a risk threshold of the target transaction in a future period according to the risk early warning curve.
In one embodiment, the risk prediction model is comprised of a convolutional neural network and a long-term memory network when the computer program is executed by the processor.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring original transaction data of a target transaction at each sampling moment in a target period; and cleaning the original transaction data to obtain target transaction data of the target transaction at each sampling moment in the target period.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
constructing a transaction sequence of the target transaction in the target time period according to the target transaction data of the target transaction at each sampling moment in the target time period;
inputting the transaction sequence into a risk prediction model to obtain the risk probability of abnormality of the target transaction in a future period;
and carrying out risk early warning processing on the target transaction according to the risk probability.
In one embodiment, the computer program constructs a target transaction based on target transaction data for each sampling instant of the target transaction during the target time period, the transaction sequence of the target transaction during the target time period when executed by the processor further implementing the steps of:
extracting key transaction data corresponding to each sampling moment from target transaction data of each sampling moment of target transaction in a target period according to key indexes corresponding to the target transaction; and constructing a transaction sequence of the target transaction in the target period according to the key transaction data corresponding to each sampling moment.
In one embodiment, the computer program further performs the following steps when executing the risk pre-warning for the target transaction by the processor according to the risk probability:
comparing the risk probability with a risk threshold corresponding to the target transaction; and if the risk probability is greater than the risk threshold, outputting risk early warning information comprising the transaction identification of the target transaction.
In one embodiment, the computer program when executed by the processor further performs the steps of:
constructing a risk early warning curve of the target transaction according to the risk early warning conditions of the target transaction at each historical moment in the historical period; and determining a risk threshold of the target transaction in a future period according to the risk early warning curve.
In one embodiment, the risk prediction model is comprised of a convolutional neural network and a long-term memory network when the computer program is executed by the processor.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring original transaction data of a target transaction at each sampling moment in a target period; and cleaning the original transaction data to obtain target transaction data of the target transaction at each sampling moment in the target period.
The data (including, but not limited to, target transaction data, original transaction data, etc.) referred to in the present application are all data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A transaction pre-warning method, the method comprising:
constructing a transaction sequence of the target transaction in a target time period according to target transaction data of the target transaction at each sampling moment in the target time period;
inputting the transaction sequence into a risk prediction model to obtain risk probability of abnormality of the target transaction in a future period;
and carrying out risk early warning processing on the target transaction according to the risk probability.
2. The method according to claim 1, wherein constructing the transaction sequence of the target transaction in the target period according to the target transaction data of each sampling time of the target transaction in the target period comprises:
extracting key transaction data corresponding to each sampling moment from target transaction data of each sampling moment of the target transaction in a target period according to key indexes corresponding to the target transaction;
and constructing a transaction sequence of the target transaction in the target period according to the key transaction data corresponding to each sampling moment.
3. The method of claim 1, wherein said performing risk pre-warning processing on said target transaction according to said risk probability comprises:
comparing the risk probability with a risk threshold corresponding to the target transaction;
and if the risk probability is greater than the risk threshold, outputting risk early warning information comprising a transaction identifier of the target transaction.
4. A method according to claim 3, characterized in that the method further comprises:
constructing a risk early warning curve of the target transaction according to risk early warning conditions of the target transaction at each historical moment in a historical period;
and determining a risk threshold of the target transaction in the future period according to the risk early warning curve.
5. The method of any one of claims 1-4, wherein the risk prediction model is comprised of a convolutional neural network and a long-term memory network.
6. The method according to claim 1, wherein the method further comprises:
acquiring original transaction data of a target transaction at each sampling moment in a target period;
and cleaning the original transaction data to obtain target transaction data of the target transaction at each sampling moment in the target period.
7. A transaction pre-warning device, the device comprising:
the construction module is used for constructing a transaction sequence of the target transaction in the target time period according to the target transaction data of the target transaction at each sampling moment in the target time period;
the prediction module is used for inputting the transaction sequence into a risk prediction model to obtain the risk probability of abnormality of the target transaction in a future period;
and the early warning module carries out risk early warning processing on the target transaction according to the risk probability.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311004053.6A CN117273922A (en) | 2023-08-10 | 2023-08-10 | Transaction early warning method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311004053.6A CN117273922A (en) | 2023-08-10 | 2023-08-10 | Transaction early warning method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117273922A true CN117273922A (en) | 2023-12-22 |
Family
ID=89220318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311004053.6A Pending CN117273922A (en) | 2023-08-10 | 2023-08-10 | Transaction early warning method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117273922A (en) |
-
2023
- 2023-08-10 CN CN202311004053.6A patent/CN117273922A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10025813B1 (en) | Distributed data transformation system | |
| CN109523117A (en) | Risk Forecast Method, device, computer equipment and storage medium | |
| US10824694B1 (en) | Distributable feature analysis in model training system | |
| CN117033424A (en) | Query optimization method and device for slow SQL (structured query language) statement and computer equipment | |
| Arslan et al. | On the distribution modeling of heavy-tailed disk failure lifetime in big data centers | |
| CN116933035A (en) | Data anomaly detection method, device, computer equipment and storage medium | |
| CN116737373A (en) | Load balancing method, device, computer equipment and storage medium | |
| CN110874601B (en) | Method for identifying running state of equipment, state identification model training method and device | |
| CN116149895A (en) | Big data cluster performance prediction method and device and computer equipment | |
| CN117273922A (en) | Transaction early warning method, device, computer equipment and storage medium | |
| CN111737319B (en) | User cluster prediction method, device, computer equipment and storage medium | |
| US11281689B1 (en) | Distributed interaction feature generation system | |
| CN116881092A (en) | Method, device, equipment and storage medium for predicting alarm data | |
| CN117014290A (en) | Alarm method, alarm device, computer equipment and storage medium | |
| CN117829904A (en) | Investment decision prediction method, apparatus, device, storage medium and program product | |
| CN118014425A (en) | Emergency system electric power emergency capacity prediction method and device and computer equipment | |
| CN116681164A (en) | Resource information processing method, device, computer equipment and storage medium | |
| CN117453248A (en) | Gray scale issuing method, device, computer equipment and storage medium | |
| CN117437004A (en) | Risk identification method and device for resource borrowing service and computer equipment | |
| CN117354842A (en) | Network quality difference root cause positioning method, device, computer equipment and storage medium | |
| CN117278381A (en) | Processing method, device, computer equipment and medium for server alarm data | |
| CN117909797A (en) | Electric power emergency capacity prediction method and device for electric power construction enterprises and computer equipment | |
| CN117573498A (en) | Log analysis model training method and device for multi-application system | |
| CN117078441A (en) | Method, apparatus, computer device and storage medium for identifying claims fraud | |
| CN117459576A (en) | Data pushing method and device based on edge calculation and computer equipment |
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 |