CN114331688A - Method and device for detecting batch operation state of bank counter system business - Google Patents
Method and device for detecting batch operation state of bank counter system business Download PDFInfo
- Publication number
- CN114331688A CN114331688A CN202111655439.4A CN202111655439A CN114331688A CN 114331688 A CN114331688 A CN 114331688A CN 202111655439 A CN202111655439 A CN 202111655439A CN 114331688 A CN114331688 A CN 114331688A
- Authority
- CN
- China
- Prior art keywords
- batch
- counter system
- bank counter
- business
- service
- 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
Images
Abstract
The invention provides a method and a device for detecting service batch running states of a bank counter system, relates to the technical field of bank batch service data processing, and can be used in the financial field or other technical fields. The method comprises the following steps: periodically acquiring batch processing business volume and batch consumed time of a bank counter system, and inputting the batch processing business volume and the batch consumed time to a preset business batch operation state detection model; and determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business. The device performs the above method. The method and the device for detecting the batch operation state of the bank counter system service provided by the embodiment of the invention can realize accurate detection of the batch operation state of the bank counter system service.
Description
Technical Field
The invention relates to the technical field of bank batch business data processing, in particular to a method and a device for detecting service batch running states of a bank counter system.
Background
The bank counter system is the most basic key business system of the bank, and the main function is to schedule and execute network transaction. The stable operation of the bank counter system not only directly relates to providing business service for customers, but also directly influences the external service image and service quality of the bank.
The bank counter system is used for ensuring the accuracy of relevant service data indexes and the accuracy of service logic of the system in the daytime business hours. The bank counter system automatically checks and updates the business parameters of the bank counter system and the transaction data of the customers in the non-business hours at the end of each day, calculates and processes the business data of the day, and provides the business data for other related business systems to be synchronously loaded. The batch operation condition of the bank counter system directly influences whether the bank can normally provide business handling service for the customers the next day. Once the batch system runs abnormally, a system administrator needs to immediately process and repair the batch system, and the timeliness requirement is extremely high.
The prior art scheme is that a uniform time is set for each branch to monitor, once the batch is not executed before 8 am, an alarm is given to each manager, and at the moment, the time is possibly very short, so that the business handling of the counter of the network point is influenced. Due to the different quantities of each family branch, the actual time consumption of batch business is greatly different, the batch business cannot be monitored by using a uniform index, the batch business cannot be scattered to each operation for monitoring, and a large amount of labor cost is consumed for maintenance.
How to accurately detect the batch operation state of the bank counter system service becomes a technical problem which needs to be solved urgently.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a method and a device for detecting the batch operation state of the business of a bank counter system, which can at least partially solve the problems in the prior art.
On one hand, the invention provides a method for detecting the batch operation state of the bank counter system service, which comprises the following steps:
periodically acquiring batch processing business volume and batch consumed time of a bank counter system, and inputting the batch processing business volume and the batch consumed time to a preset business batch operation state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data;
and determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business.
Determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business, wherein the detection result comprises the following steps:
and if the output result is that abnormal points exist and the output times reach a preset time threshold, determining that the detection result of the batch operation state of the bank counter system service is an abnormal detection result.
Determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business, wherein the detection result comprises the following steps:
and if the output result is that no abnormal point exists, waiting for executing the step of periodically acquiring the batch processing service volume and batch time consumption of the bank counter system until the current batch is traversed and the output result of the preset service batch operation state detection model is that no abnormal point exists every time, and determining that the detection result of the service batch operation state of the bank counter system is a normal detection result.
The method for detecting the batch operation state of the bank counter system business further comprises the following steps:
and if the output frequency does not reach a preset frequency threshold value, waiting to execute the step of periodically acquiring the batch processing service volume and the batch consumed time of the bank counter system.
The method comprises the steps of obtaining a bank counter system identification and a batch job number of a bank counter system; correspondingly, the method for detecting the batch operation state of the bank counter system business further comprises the following steps:
determining a target abnormal point with the output frequency reaching a preset frequency threshold value, and determining a target bank counter system identifier and a target batch job number corresponding to the target abnormal point;
sending an interrupt instruction to a target bank counter system according to the target bank counter system identifier; and the interrupt instruction carries a target batch job number corresponding to the target abnormal point.
The method comprises the steps of obtaining a bank counter system identification and a batch job number of a bank counter system; correspondingly, the method for detecting the batch operation state of the bank counter system business further comprises the following steps:
determining a target abnormal point with the output frequency reaching a preset frequency threshold value, and determining a target bank counter system identifier and a target batch job number corresponding to the target abnormal point;
sending a skipping instruction to a downstream system of the target bank counter system determined according to the target bank counter system identification; and the skipping instruction carries a target batch job number corresponding to the abnormal detection result.
After the step of determining that the detection result of the batch operation state of the bank counter system service is an abnormal detection result, the method for detecting the batch operation state of the bank counter system service further comprises the following steps:
and determining a target abnormal point corresponding to the abnormal detection result, and inputting the target abnormal point to a historical abnormal detection point data set in the batch processing service sample data.
After the step of determining that the detection result of the batch operation state of the bank counter system service is an abnormal detection result, the method for detecting the batch operation state of the bank counter system service further comprises the following steps:
and determining a normal point corresponding to a normal detection result, and inputting the normal point to a historical normal detection point data set in the batch processing service sample data.
On one hand, the invention provides a device for detecting the batch operation state of the bank counter system service, which comprises:
the input unit is used for periodically acquiring batch processing business volume and batch consumed time of the bank counter system and inputting the batch processing business volume and the batch consumed time to a preset business batch operation state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data;
and the detection unit is used for determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business.
In another aspect, an embodiment of the present invention provides an electronic device, including: a processor, a memory, and a bus, wherein,
the processor and the memory are communicated with each other through the bus;
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform a method comprising:
periodically acquiring batch processing business volume and batch consumed time of a bank counter system, and inputting the batch processing business volume and the batch consumed time to a preset business batch operation state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data;
and determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business.
An embodiment of the present invention provides a non-transitory computer-readable storage medium, including:
the non-transitory computer readable storage medium stores computer instructions that cause the computer to perform a method comprising:
periodically acquiring batch processing business volume and batch consumed time of a bank counter system, and inputting the batch processing business volume and the batch consumed time to a preset business batch operation state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data;
and determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business.
The method and the device for detecting the service batch running state of the bank counter system provided by the embodiment of the invention periodically acquire the batch processing service volume and the batch consumed time of the bank counter system, and input the batch processing service volume and the batch consumed time to a preset service batch running state detection model; and determining the detection result of the service batch running state of the bank counter system according to the output result of the preset service batch running state detection model, wherein the batch processing service volume and the batch time consumption of the input model are dynamically changed batch indexes, so that the accurate detection of the service batch running state of the bank counter system can be realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a schematic flow chart of a method for detecting a batch operation state of a business of a bank counter system according to an embodiment of the present invention.
FIG. 2 is a schematic diagram illustrating an LOF algorithm model according to an embodiment of the present invention.
Fig. 3 is a schematic flow chart of a method for detecting a batch operation state of a business of a bank counter system according to an embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a device for detecting a batch running state of a bank counter system service according to an embodiment of the present invention.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
Fig. 1 is a schematic flow chart of a method for detecting a batch running state of a bank counter system service according to an embodiment of the present invention, and as shown in fig. 1, the method for detecting a batch running state of a bank counter system service according to an embodiment of the present invention includes:
step S1: periodically acquiring batch processing business volume and batch consumed time of a bank counter system, and inputting the batch processing business volume and the batch consumed time to a preset business batch operation state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data.
Step S2: and determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business.
In the step S1, the device periodically obtains batch processing traffic and batch consumed time of the bank counter system, and inputs the batch processing traffic and the batch consumed time to a preset service batch operation state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data. The apparatus may be a computer device, including a bank management server, that performs the method.
The execution period of the step of periodically acquiring the batch processing traffic and the batch time consumption of the bank counter system can be set independently according to the actual situation, and can be selected to be 5 minutes. Batch traffic may be understood as completed batch traffic and batch elapsed time may be understood as batch elapsed time for completed batch traffic.
Local Outlier Factor (LOF), also known as Local anomaly Factor algorithm, is shown in FIG. 2, with the abscissa representing batch traffic and the ordinate representing batch time consumption. A brief description of the LOF algorithm model follows:
for the points of the C1 set, the overall spacing, density and dispersion are uniform and consistent, and the points can be considered as the same cluster; for the point of the C2 set, it can be considered as a cluster as well. The o1 and o2 points are relatively isolated and can be considered as outliers or discrete points. Judging whether the p point is an abnormal point or not by calculating a local outlier factor of the p point, wherein if the value is closer to 1, the density of the neighborhood points of the p is almost the same, and the p possibly belongs to the same cluster with the neighborhood; if the ratio is less than 1, the density of p is higher than that of the neighborhood points, and p is a dense point; if this value is greater than 1, indicating that the density of p is less than its neighborhood point density, p is more likely to be an outlier.
The embodiment of the invention adopts an LOF algorithm model to construct a detection model of the batch running state of the preset service, and the reason is as follows:
the inventor discovers that the batch processing service volume and the batch processing service volume are positively correlated by analyzing and counting the batch processing service volume and the batch processing service volume of different service types of the bank counter system, namely the batch processing service volume and the batch processing service volume processed in the period are linearly and positively correlated. Due to the large difference of batch processing traffic of each branch, the difference of corresponding batch time consumption is large, and the service batch operation state detection cannot be performed by using a uniform index.
By utilizing the positive correlation characteristic of batch processing traffic and batch time consumption, a scatter diagram can be determined according to batch state points, and a plurality of aggregation clusters with different positions can be obtained in a two-dimensional coordinate system with the batch processing traffic as an abscissa and the batch time consumption as an ordinate, which is called a normal batch domain of each branch.
Because the server performance and the branch network bandwidth which are depended by the batch operation of the bank counter system are different, the aggregation degree of the normal batch domains of each branch is different, but because of the special positive correlation between the counter batch and the service volume, the normal batch domains of each branch are all in an aggregation state, and the abnormal points are far away from the aggregation state. The batch state points to be detected only need to be calculated in the local clusters nearby without judging the difference between the batch state points and the global nodes, and completely accord with the characteristics of local outlier factors, so that high accuracy of abnormal judgment is realized. It is the local aggregation characteristic of the normal batch domain of each branch line, and the local calculation algorithm of LOF can be used to detect abnormal points without being influenced by the difference between the whole branch lines. The method and the device are based on the LOF algorithm, the local outlier factor of the batch coordinate point is calculated, and if the local outlier factor exceeds the abnormal point threshold value, the batch abnormality is judged.
As shown in fig. 3, the batch processing service sample data includes historical abnormal point data and historical normal point data, and a historical abnormal point data set and a historical normal point data set may be respectively constructed according to the historical abnormal point data and the historical normal point data.
The branch batch log information can be collected through an open source log collection tool fluent, and the log information is analyzed and written into the Mysql database of the server. The log information may include information such as a line number, a batch job number, batch traffic, batch elapsed time, and whether there is an exception.
The method comprises the steps of collecting batch processing service sample data from log information, forming an array [ A, B ] by using the taken batch processing service volume A and the batch consumed time B, inputting a full-scale sample set D and a preset initial k as 5 into a calculation model.
The following steps of training the LOF algorithm model are performed:
1. the euclidean distance of each object is calculated.
2. And sorting the Euclidean distances, and calculating the kth distance and the kth field.
3. The achievable density for each object is calculated.
4. A local outlier factor is calculated for each object.
5. And sequencing the local outlier factors of each object, and outputting abnormal nodes (an abnormal threshold value can be preset to be 2).
6. And comparing the output abnormal object with the abnormal object recorded in the actual Mysql library to identify whether the admission rate is higher than 90%. If the target value is not reached, k + + (adding one to the k value), and continuing to execute the steps of 1-6. Until the recognition accuracy is higher than 90%. And finally, taking the trained standard reaching model as a preset service batch operation state detection model.
The specific implementation manner of the steps 1 to 6 is a mature technology in the field and is not described in detail.
In the step S2, the device determines the result of detecting the batch operation state of the bank counter system service according to the output result of the preset service batch operation state detection model.
As shown in fig. 3, further, the determining a detection result of the batch operation state of the service of the bank counter system according to the output result of the preset batch operation state detection model of the service includes:
and if the output result is that abnormal points exist and the output times reach a preset time threshold, determining that the detection result of the batch operation state of the bank counter system service is an abnormal detection result. The preset time threshold can be set independently according to actual conditions, and can be selected as 3 times.
If the output result indicates that the abnormal point exists and the output frequency reaches the preset frequency threshold, it can be understood that if the first output result of the preset service batch operation state detection model indicates that the abnormal point exists, the abnormal point cannot be completely determined to exist at the moment, then the second output result is output through the preset service batch operation state detection model, if the abnormal point exists, the abnormal point cannot be completely determined to exist at the moment, then the third output result is output through the preset service batch operation state detection model, and if the abnormal point exists, the abnormal point can be determined to exist.
It can be understood that, because the batch processing traffic and the batch time consumption of the bank counter system are periodically obtained, the dynamic batch index of the preset service batch running state detection model is dynamically changed every time the preset service batch running state detection model is input.
According to the method for detecting the batch operation state of the bank counter system service, provided by the embodiment of the invention, the abnormal detection result is determined according to the output result with the abnormal points, so that the inaccuracy of determining the abnormal detection result according to the output result with the abnormal points at a single time is avoided, and the accurate detection of the batch operation state of the bank counter system service can be further realized.
As shown in fig. 3, further, the determining a detection result of the batch operation state of the service of the bank counter system according to the output result of the preset batch operation state detection model of the service includes:
and if the output result is that no abnormal point exists, waiting for executing the step of periodically acquiring the batch processing service volume and batch time consumption of the bank counter system until the current batch is traversed and the output result of the preset service batch operation state detection model is that no abnormal point exists every time, and determining that the detection result of the service batch operation state of the bank counter system is a normal detection result. The dynamic batch indicator in FIG. 3 corresponds to batch traffic and batch elapsed time.
According to the method for detecting the batch operation state of the bank counter system service, provided by the embodiment of the invention, all current batches are traversed, and if the output result of the preset service batch operation state detection model does not have abnormal points every time, the detection result is determined to be a normal detection result, so that the accurate detection of the batch operation state of the bank counter system service can be further realized.
If the execution cycle of the step of acquiring the batch processing service volume and the batch consumed time of the bank counter system is 5 minutes, waiting for the next 5 minutes when the abnormal point does not exist, inputting a dynamic batch index, updating the finished batch processing service volume and the finished batch consumed time, and then determining whether the current batch is finished according to the status flag bit of whether the current batch is finished.
As shown in fig. 3, further, the method for detecting the batch operation state of the bank counter system service further includes:
and if the output frequency does not reach a preset frequency threshold value, waiting to execute the step of periodically acquiring the batch processing service volume and the batch consumed time of the bank counter system. Reference is made to the above description and no further description is made.
The method for detecting the service batch running state of the bank counter system provided by the embodiment of the invention effectively executes the steps of periodically acquiring the batch processing service volume and batch time consumption of the bank counter system, and further can accurately detect the service batch running state of the bank counter system.
As shown in fig. 3, this step corresponds to exception handling, and further, a bank counter system identifier and a batch job number of the bank counter system are also obtained; the bank counter system identifier may include a branch number, and the batch job number may be understood as a mark number for marking a dynamic batch index for inputting a preset service batch operation state detection model each time.
Correspondingly, the method for detecting the batch operation state of the bank counter system business further comprises the following steps:
determining a target abnormal point with the output frequency reaching a preset frequency threshold value, and determining a target bank counter system identifier and a target batch job number corresponding to the target abnormal point; examples are as follows:
the dynamic batch index of the preset service batch running state detection model is input for the first time is A1, the batch job number is 001, and the output results are an abnormal point 10, an abnormal point 15 and an abnormal point 17.
And after 5 minutes, updating the dynamic batch index A2, inputting A2 into a preset service batch running state detection model, marking the batch job number as 002, and outputting results of an abnormal point 15, an abnormal point 17 and an abnormal point 21.
And after 5 minutes, updating the dynamic batch index mark A3, inputting A3 into a preset service batch running state detection model, marking the batch job number as 003, and outputting results of a sum abnormal point 15, an abnormal point 21 and an abnormal point 26.
And if the preset time threshold value is 3 times, determining that the abnormal point 15 is the target abnormal point, if the abnormal point 15 belongs to the No. 1 branch, determining that the No. 1 branch is the target bank counter system identifier, and determining that the No. 003 batch job number is the target batch job number.
And after 5 minutes, updating the dynamic batch index A4, inputting A4 into a preset service batch running state detection model, recording the batch job number as 004, and outputting results of the abnormal point 21, the abnormal point 26 and the abnormal point 33. And determining the abnormal point 21 as a target abnormal point, if the abnormal point 21 belongs to the No. 2 branch, determining the No. 2 branch as a target bank counter system identifier, and determining the No. 004 batch job number as a target batch job number.
Sending an interrupt instruction to a target bank counter system according to the target bank counter system identifier; and the interrupt instruction carries a target batch job number corresponding to the target abnormal point. Referring to the above example, an interrupt instruction is sent to the branch 1, and the interrupt instruction carries the batch job number 003 corresponding to the exception point 15. (the interrupt command corresponding to the exception point 21 is not sent temporarily). And the batch executer in the No. 1 branch interrupts the No. 003 batch job number after receiving the interrupt instruction, and continues to execute the No. 004 batch job number.
In order to more accurately determine the batch job number to be subjected to interrupt processing, batch job numbers adjacent to the target batch job number may be carried in the interrupt instruction, for example, the No. 002 batch job number to No. 004 batch job number is transmitted to the No. 1 branch, so that the No. 1 branch accurately determines the No. 003 batch job number as the target batch job number according to the No. 002 batch job number and the No. 004 batch job number.
The method for detecting the service batch running state of the bank counter system provided by the embodiment of the invention sends an interrupt instruction to a target bank counter system; the interruption instruction carries a target batch job number corresponding to the target abnormal point, so that service interruption can be avoided, and the target bank counter system can skip the target batch job number and continue to perform subsequent operations.
As shown in fig. 3, this step corresponds to exception handling, and further, a bank counter system identifier and a batch job number of the bank counter system are also obtained; correspondingly, the method for detecting the batch operation state of the bank counter system business further comprises the following steps:
determining a target abnormal point with the output frequency reaching a preset frequency threshold value, and determining a target bank counter system identifier and a target batch job number corresponding to the target abnormal point; reference is made to the above description and no further description is made.
Sending a skipping instruction to a downstream system of the target bank counter system determined according to the target bank counter system identification; and the skipping instruction carries a target batch job number corresponding to the abnormal detection result. Referring to the above example, a skip instruction is sent to a downstream system of the No. 1 branch, for example, a mobile banking system, and the skip instruction carries the No. 003 batch job number corresponding to the abnormal point 15. (the skip instruction corresponding to the exception point 21 is not sent for the time being). And the mobile banking system in the No. 1 branch skips the No. 003 batch job number after receiving the skip instruction, and continues to execute the No. 004 batch job number.
According to the method for detecting the service batch running state of the bank counter system, provided by the embodiment of the invention, the skipping instruction is sent to the downstream system of the target bank counter system, and the skipping instruction carries the target batch job number, so that service interruption can be avoided, the downstream system can skip the target batch job number and continue to perform subsequent operations.
As shown in fig. 3, further, after the step of determining that the detection result of the batch operation state of the service of the bank counter system is an abnormal detection result, the method for detecting the batch operation state of the service of the bank counter system further includes:
and determining a target abnormal point corresponding to the abnormal detection result, and inputting the target abnormal point to a historical abnormal detection point data set in the batch processing service sample data. Referring to the above example, the outlier 15 may be input into the historical outlier detection point data set, or after the batch processing is completed, all the outliers may be input into the historical outlier detection point data set at a time, for example, other subsequent outliers such as the outlier 15 and the outlier 21 may be input into the historical outlier detection point data set at a time.
The method for detecting the service batch running state of the bank counter system, provided by the embodiment of the invention, can ensure the freshness of batch processing service sample data in the database, and is beneficial to improving the detection accuracy of the preset service batch running state detection model.
As shown in fig. 3, further, after the step of determining that the detection result of the batch operation state of the service of the bank counter system is an abnormal detection result, the method for detecting the batch operation state of the service of the bank counter system further includes:
and determining a normal point corresponding to a normal detection result, and inputting the normal point to a historical normal detection point data set in the batch processing service sample data. The normal points can be input into the historical normal detection point data set at one time.
The method for detecting the service batch running state of the bank counter system, provided by the embodiment of the invention, can ensure the freshness of batch processing service sample data in the database, and is beneficial to improving the detection accuracy of the preset service batch running state detection model.
The method for detecting the service batch running state of the bank counter system provided by the embodiment of the invention periodically acquires the batch processing service volume and the batch consumed time of the bank counter system, and inputs the batch processing service volume and the batch consumed time to a preset service batch running state detection model; and determining the detection result of the batch operation state of the bank counter system service according to the output result of the preset service batch operation state detection model, so that the accurate detection of the batch operation state of the bank counter system service can be realized.
It should be noted that the method for detecting the batch operation state of the business of the bank counter system provided by the embodiment of the invention can be used in the financial field and can also be used in any technical field except the financial field.
Fig. 4 is a schematic structural diagram of a device for detecting a batch running state of a bank counter system service according to an embodiment of the present invention, and as shown in fig. 4, the device for detecting a batch running state of a bank counter system service according to an embodiment of the present invention includes an input unit 401 and a detection unit 402, where:
the input unit 401 is configured to periodically obtain batch processing traffic and batch consumed time of the bank counter system, and input the batch processing traffic and the batch consumed time to a preset service batch operation state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data; the detection unit 402 is configured to determine a detection result of the batch operation state of the service of the bank counter system according to an output result of the preset detection model of the batch operation state of the service.
Specifically, an input unit 401 in the device for detecting the service batch running state of the bank counter system is used for periodically acquiring the batch processing service volume and the batch consumed time of the bank counter system, and inputting the batch processing service volume and the batch consumed time to a preset service batch running state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data; the detection unit 402 is configured to determine a detection result of the batch operation state of the service of the bank counter system according to an output result of the preset detection model of the batch operation state of the service.
The device for detecting the service batch running state of the bank counter system, provided by the embodiment of the invention, periodically obtains the batch processing service volume and the batch consumed time of the bank counter system, and inputs the batch processing service volume and the batch consumed time to a preset service batch running state detection model; and determining the detection result of the batch operation state of the bank counter system service according to the output result of the preset service batch operation state detection model, so that the accurate detection of the batch operation state of the bank counter system service can be realized.
The embodiment of the device for detecting the batch running state of the business of the bank counter system provided by the embodiment of the invention can be specifically used for executing the processing flows of the method embodiments, the functions of the device are not repeated herein, and reference can be made to the detailed description of the method embodiments.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 5, the electronic device includes: a processor (processor)501, a memory (memory)502, and a bus 503;
the processor 501 and the memory 502 complete communication with each other through a bus 503;
the processor 501 is configured to call program instructions in the memory 502 to perform the methods provided by the above-mentioned method embodiments, for example, including:
periodically acquiring batch processing business volume and batch consumed time of a bank counter system, and inputting the batch processing business volume and the batch consumed time to a preset business batch operation state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data; and determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business.
The present embodiment discloses a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the method provided by the above-mentioned method embodiments, for example, comprising: periodically acquiring batch processing business volume and batch consumed time of a bank counter system, and inputting the batch processing business volume and the batch consumed time to a preset business batch operation state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data; and determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business.
The present embodiment provides a computer-readable storage medium, which stores a computer program, where the computer program causes the computer to execute the method provided by the above method embodiments, for example, the method includes: periodically acquiring batch processing business volume and batch consumed time of a bank counter system, and inputting the batch processing business volume and the batch consumed time to a preset business batch operation state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data; and determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the description herein, reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," "an example," "a particular example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (11)
1. A bank counter system service batch operation state detection method is characterized by comprising the following steps:
periodically acquiring batch processing business volume and batch consumed time of a bank counter system, and inputting the batch processing business volume and the batch consumed time to a preset business batch operation state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data;
and determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business.
2. The method for detecting the service batch running state of the bank counter system according to claim 1, wherein the step of determining the detection result of the service batch running state of the bank counter system according to the output result of the preset service batch running state detection model comprises the following steps:
and if the output result is that abnormal points exist and the output times reach a preset time threshold, determining that the detection result of the batch operation state of the bank counter system service is an abnormal detection result.
3. The method for detecting the service batch running state of the bank counter system according to claim 1, wherein the step of determining the detection result of the service batch running state of the bank counter system according to the output result of the preset service batch running state detection model comprises the following steps:
and if the output result is that no abnormal point exists, waiting for executing the step of periodically acquiring the batch processing service volume and batch time consumption of the bank counter system until the current batch is traversed and the output result of the preset service batch operation state detection model is that no abnormal point exists every time, and determining that the detection result of the service batch operation state of the bank counter system is a normal detection result.
4. The method for detecting the service batch running state of the bank counter system according to claim 2, wherein the method for detecting the service batch running state of the bank counter system further comprises the following steps:
and if the output frequency does not reach a preset frequency threshold value, waiting to execute the step of periodically acquiring the batch processing service volume and the batch consumed time of the bank counter system.
5. The method for detecting the batch running state of the business of the bank counter system according to claim 2, characterized in that the identification of the bank counter system and the batch job number of the bank counter system are also obtained; correspondingly, the method for detecting the batch operation state of the bank counter system business further comprises the following steps:
determining a target abnormal point with the output frequency reaching a preset frequency threshold value, and determining a target bank counter system identifier and a target batch job number corresponding to the target abnormal point;
sending an interrupt instruction to a target bank counter system according to the target bank counter system identifier; and the interrupt instruction carries a target batch job number corresponding to the target abnormal point.
6. The method for detecting the batch running state of the business of the bank counter system according to claim 2, characterized in that the identification of the bank counter system and the batch job number of the bank counter system are also obtained; correspondingly, the method for detecting the batch operation state of the bank counter system business further comprises the following steps:
determining a target abnormal point with the output frequency reaching a preset frequency threshold value, and determining a target bank counter system identifier and a target batch job number corresponding to the target abnormal point;
sending a skipping instruction to a downstream system of the target bank counter system determined according to the target bank counter system identification; and the skipping instruction carries a target batch job number corresponding to the abnormal detection result.
7. The method for detecting the batch running state of the business of the bank counter system according to claim 2, wherein after the step of determining that the detection result of the batch running state of the business of the bank counter system is an abnormal detection result, the method for detecting the batch running state of the business of the bank counter system further comprises:
and determining a target abnormal point corresponding to the abnormal detection result, and inputting the target abnormal point to a historical abnormal detection point data set in the batch processing service sample data.
8. The method for detecting the batch running state of the business of the bank counter system according to claim 2, wherein after the step of determining that the detection result of the batch running state of the business of the bank counter system is an abnormal detection result, the method for detecting the batch running state of the business of the bank counter system further comprises:
and determining a normal point corresponding to a normal detection result, and inputting the normal point to a historical normal detection point data set in the batch processing service sample data.
9. The utility model provides a bank counter system business is running state detection device in batches which characterized in that includes:
the input unit is used for periodically acquiring batch processing business volume and batch consumed time of the bank counter system and inputting the batch processing business volume and the batch consumed time to a preset business batch operation state detection model; the preset service batch operation state detection model is obtained by training an LOF algorithm model according to batch processing service sample data;
and the detection unit is used for determining the detection result of the batch operation state of the business of the bank counter system according to the output result of the preset detection model of the batch operation state of the business.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 8 are implemented when the computer program is executed by the processor.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111655439.4A CN114331688A (en) | 2021-12-30 | 2021-12-30 | Method and device for detecting batch operation state of bank counter system business |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111655439.4A CN114331688A (en) | 2021-12-30 | 2021-12-30 | Method and device for detecting batch operation state of bank counter system business |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114331688A true CN114331688A (en) | 2022-04-12 |
Family
ID=81019773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111655439.4A Pending CN114331688A (en) | 2021-12-30 | 2021-12-30 | Method and device for detecting batch operation state of bank counter system business |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114331688A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116383083A (en) * | 2023-04-23 | 2023-07-04 | 中航信移动科技有限公司 | Multi-interface connection-based abnormal data source determining method and storage medium |
-
2021
- 2021-12-30 CN CN202111655439.4A patent/CN114331688A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116383083A (en) * | 2023-04-23 | 2023-07-04 | 中航信移动科技有限公司 | Multi-interface connection-based abnormal data source determining method and storage medium |
| CN116383083B (en) * | 2023-04-23 | 2024-01-12 | 中航信移动科技有限公司 | Multi-interface connection-based abnormal data source determining method and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107871190B (en) | Service index monitoring method and device | |
| CN111143102B (en) | Abnormal data detection method and device, storage medium and electronic equipment | |
| CN113518011B (en) | Abnormality detection method and apparatus, electronic device, and computer-readable storage medium | |
| CN107766533B (en) | Automatic detection method and system for telephone traffic abnormality, storage medium and electronic equipment | |
| CN111796957B (en) | Transaction abnormal root cause analysis method and system based on application log | |
| CN113037595B (en) | Abnormal device detection method and device, electronic device and storage medium | |
| CN115033463B (en) | System exception type determining method, device, equipment and storage medium | |
| CN110647447B (en) | Abnormal instance detection method, device, equipment and medium for distributed system | |
| CN112148733A (en) | Method, device, electronic device and computer readable medium for determining fault type | |
| WO2018122890A1 (en) | Log analysis method, system, and program | |
| CN111753875A (en) | Power information system operation trend analysis method and device and storage medium | |
| CN114331688A (en) | Method and device for detecting batch operation state of bank counter system business | |
| CN110889597A (en) | Method and device for detecting abnormal business timing sequence indexes | |
| CN108363024B (en) | Method and device for positioning fault point of charging pile | |
| CN108306997B (en) | Domain name resolution monitoring method and device | |
| JP6252309B2 (en) | Monitoring omission identification processing program, monitoring omission identification processing method, and monitoring omission identification processing device | |
| KR102059112B1 (en) | IoT STREAM DATA QUALITY MEASUREMENT INDICATORS AND PROFILING METHOD FOR INTERNET OF THINGS AND SYSTEM THEREFORE | |
| CN110287114B (en) | Method and device for testing performance of database script | |
| CN111125195A (en) | Data anomaly detection method and device | |
| CN114157486B (en) | Communication flow data abnormity detection method and device, electronic equipment and storage medium | |
| CN110058811A (en) | Information processing unit, data management system, method and computer-readable medium | |
| CN115510998A (en) | Transaction abnormal value detection method and device | |
| CN115509797A (en) | Method, device, equipment and medium for determining fault category | |
| CN114938339A (en) | Data processing method and related device | |
| CN114881112A (en) | System anomaly detection method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |