Application early warning method and device, storage medium, program product and electronic equipment

Abstract

The invention discloses an application early warning method and device, a storage medium, a program product and electronic equipment. Relates to the distributed field. The method comprises the steps that under the condition that batch job early warning of a first application is detected, the running risk value of the first application is obtained, and the running risk value of the first application is determined at least according to the running risk value of batch jobs in the first application; determining a second application having an association relationship with the batch job of the first application, and obtaining an operation risk value of the second application; and calculating a target operation risk value of the second application according to the operation risk value of the first application, the correlation influence coefficient between the first application and the second application and the operation risk value of the second application, and performing early warning on the first application and the second application under the condition that the target operation risk value is greater than a preset threshold value. Through the method and the device, the problem of poor early warning reliability caused by early warning of a single application when a problem occurs in application execution of batch jobs in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the distributed field, and specifically, to an application early warning method, device, storage medium, program product and electronic device. Background Art

[0002] Batch jobs are a key component for processing massive amounts of data and implementing various business functions. These batch jobs are usually run at night or during non-business peak hours to process large amounts of transaction records, account updates, report generation, and other tasks. However, the execution environment of batch jobs is complex, involving multiple systems, databases, and file transfer processes. The dependencies between them are intricate, and an exception in a batch job may cascade to multiple downstream jobs, and even affect other business processes across applications.

[0003] Currently, in the related technology, when problems occur when an application executes a batch job, the early warning system often focuses on a single application and only issues an early warning for the application where the problematic job is located, which leads to the problem of poor early warning reliability.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The main purpose of the present application is to provide an application warning method, device, storage medium, program product and electronic device to solve the problem of poor warning reliability caused by issuing a warning for a single application when problems occur in the application executing batch jobs in the related technology.

[0006] In order to achieve the above-mentioned purpose, according to one aspect of the present application, an application warning method is provided. The method includes: when a batch job warning of a first application is detected, obtaining an operation risk value of the first application, wherein the operation risk value of the first application is determined at least according to the operation risk value of the batch job in the first application; determining a second application that has an association relationship with the batch job of the first application, and obtaining the operation risk value of the second application; calculating a target operation risk value of the second application according to the operation risk value of the first application, the correlation influence coefficient between the first application and the second application, and the operation risk value of the second application, and when the target operation risk value is greater than a preset threshold, issuing a warning to the first application and the second application.

[0007] Furthermore, the application warning method also includes: obtaining the job feature vector of each batch job in the first application, and obtaining the application feature vector of the first application; calculating the first relevant influence coefficient of the operation risk of each batch job on the operation risk of the first application based on the job feature vector and the application feature vector of each batch job; obtaining the operation risk value of each batch job in the first application, and calculating the operation risk value of the first application based on the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job.

[0008] Furthermore, the application warning method also includes: for each batch job, obtaining the source code in the execution program corresponding to the batch job and the code called by the execution program to obtain a code set for the batch job; performing vector conversion on the code in the code set based on a preset vocabulary to obtain a processed code set, wherein the vocabulary includes a mapping relationship between multiple code words and multiple encoding vectors; encoding the processed code set using an encoder to obtain an initial feature vector corresponding to the batch job; and processing the initial feature vector using a self-attention mechanism to obtain a job feature vector for the batch job.

[0009] Furthermore, the application warning method also includes: for each batch job, using the risk prediction model to process the job feature vector to obtain a first operation risk value of the batch job; obtaining a second operation risk value of the batch job, wherein the second operation risk value is obtained by performing a simulated operation test on the batch job; and determining the operation risk value of the batch job based on the first operation risk value and the second operation risk value of the batch job.

[0010] Furthermore, the application warning method also includes: obtaining a task feature vector of each target transmission task in the first application, and obtaining an operation risk value of each target transmission task in the first application, wherein the target transmission task refers to a transmission task associated with a batch job in the first application; calculating a second correlation influence coefficient of the operation risk of the target transmission task on the operation risk of the application based on the task feature vector and the application feature vector of each target transmission task; calculating the operation risk value of the first application based on the operation risk value of each batch job in the first application and the first correlation influence coefficient corresponding to each batch job, as well as the operation risk value of each target transmission task in the first application and the second correlation influence coefficient corresponding to each target transmission task.

[0011] Furthermore, the application warning method also includes: before calculating the target operation risk value of the second application based on the operation risk value of the first application, the correlation influence coefficient between the first application and the second application, and the operation risk value of the second application, obtaining the application feature vector of the first application and obtaining the application feature vector of the second application; based on the application feature vector of the first application and the application feature vector of the second application, calculating the correlation influence coefficient between the first application and the second application.

[0012] Furthermore, the application warning method also includes: before obtaining the operation risk value of the first application, for each batch job in the first application, obtaining a detection indicator for the job information of the batch job to obtain a first detection indicator; obtaining a detection indicator for a target container to obtain a second detection indicator, wherein the target container is used to execute the batch job; during the execution of the batch job, detecting the batch job based on the first detection indicator and the second detection indicator, and determining the target information based on the detected indicator value, wherein the target information is used to characterize whether to issue a warning for the batch job.

[0013] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an application warning device is provided. The device includes: a first acquisition module, which is used to acquire the operation risk value of the first application when a batch job warning of the first application is detected, wherein the operation risk value of the first application is determined at least according to the operation risk value of the batch job in the first application; a second acquisition module, which is used to determine a second application that has an association relationship with the batch job of the first application, and acquire the operation risk value of the second application; a processing module, which is used to calculate the target operation risk value of the second application according to the operation risk value of the first application, the correlation influence coefficient between the first application and the second application, and the operation risk value of the second application, and when the target operation risk value is greater than a preset threshold, the first application and the second application are warned.

[0014] Furthermore, the first acquisition module also includes: a first acquisition sub-module, used to obtain the job feature vector of each batch job in the first application, and obtain the application feature vector of the first application; a first calculation sub-module, used to calculate the first relevant influence coefficient of the operation risk of each batch job on the operation risk of the first application based on the job feature vector and application feature vector of each batch job; a second calculation sub-module, used to obtain the operation risk value of each batch job in the first application, and calculate the operation risk value of the first application based on the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job.

[0015] Furthermore, the first acquisition submodule also includes: a first acquisition unit, used to obtain, for each batch job, the source code in the execution program corresponding to the batch job and the code called by the execution program, to obtain a code set for the batch job; a first processing unit, used to perform vector conversion on the code in the code set based on a preset vocabulary, to obtain a processed code set, wherein the vocabulary includes a mapping relationship between multiple code words and multiple encoding vectors; a second processing unit, used to encode the processed code set using an encoder, to obtain an initial feature vector corresponding to the batch job; and a third processing unit, used to process the initial feature vector using a self-attention mechanism, to obtain a job feature vector for the batch job.

[0016] Furthermore, the second calculation submodule also includes: a fourth processing unit, used to process the job feature vector for each batch job using the risk prediction model to obtain a first operation risk value of the batch job; a second acquisition unit, used to obtain a second operation risk value of the batch job, wherein the second operation risk value is obtained by performing a simulated operation test on the batch job; and a determination unit, used to determine the operation risk value of the batch job based on the first operation risk value and the second operation risk value of the batch job.

[0017] Furthermore, the second calculation submodule also includes: a third acquisition unit, used to obtain the task feature vector of each target transmission task in the first application, and obtain the operation risk value of each target transmission task in the first application, wherein the target transmission task refers to the transmission task associated with the batch job in the first application; a first calculation unit, used to calculate the second relevant influence coefficient of the operation risk of the target transmission task on the operation risk of the application based on the task feature vector and the application feature vector of each target transmission task; a second calculation unit, used to calculate the operation risk value of the first application based on the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job, as well as the operation risk value of each target transmission task in the first application and the second relevant influence coefficient corresponding to each target transmission task.

[0018] Furthermore, the application warning device also includes: a third acquisition module, used to obtain the application feature vector of the first application and the application feature vector of the second application; a calculation module, used to calculate the correlation influence coefficient between the first application and the second application based on the application feature vector of the first application and the application feature vector of the second application.

[0019] Furthermore, the application warning device also includes: a fourth acquisition module, which is used to obtain, for each batch job in the first application, a detection indicator of the job information of the batch job, and obtain a first detection indicator; a fifth acquisition module, which is used to obtain a detection indicator for a target container, and obtain a second detection indicator, wherein the target container is used to execute the batch job; a determination module, which is used to detect the batch job based on the first detection indicator and the second detection indicator during the execution of the batch job, and determine the target information based on the detected indicator value, wherein the target information is used to indicate whether to issue a warning for the batch job.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer-readable storage medium is provided, and the computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned application warning method.

[0021] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, the electronic device comprising a memory storing an executable program; and a processor for running the program, wherein the above-mentioned application warning method is executed when the program is running.

[0022] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is provided, including computer instructions, which implement the steps of the above-mentioned application warning method when executed by a processor.

[0023] In an embodiment of the present application, by determining a second application associated with the batch job of the first application and obtaining an operation risk value of the second application when a batch job warning of the first application is detected, effective determination of the operation risk of the second application related to the batch job operation of the first application is achieved. By calculating the target operation risk value of the second application based on the operation risk value of the first application, the correlation coefficient between the first application and the second application, and the operation risk value of the second application, effective determination of the probability that the second application associated with the batch job of the first application may have an abnormality when a problem occurs in the batch job of the first application is achieved. By issuing an early warning to the first application and the second application when the target operation risk value is greater than a preset threshold, when a problem occurs in the batch job of the first application, an early warning is issued to the second application that is most likely to be affected by the first application, thereby improving the reliability of the early warning.

[0024] It can be seen that the solution provided by the present application achieves the purpose of issuing early warnings to multiple applications when problems arise in the application's execution of batch jobs, achieves the technical effect of improving the reliability of early warnings, and solves the problem in related technologies of issuing early warnings to a single application when problems arise in the application's execution of batch jobs, resulting in poor early warning reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0026] Figure 1 is a hardware structure block diagram of a computer terminal provided according to an embodiment of the present application;

[0027] Figure 2 is a flow chart of an application warning method provided according to an embodiment of the present application;

[0028] Figure 3 is a schematic diagram of determining a job feature vector according to an embodiment of the present application;

[0029] Figure 4 is a schematic diagram of determining a second operation risk value according to an embodiment of the present application;

[0030] Figure 5 is a schematic diagram of an undirected job graph provided according to an embodiment of the present application;

[0031] Figure 6 is a schematic diagram of determining target information provided according to an embodiment of the present application;

[0032] Figure 7 is a schematic diagram of an application warning device provided according to an embodiment of the present application;

[0033] Figure 8 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0037] Example 1

[0038] According to an embodiment of the present application, an application warning method embodiment is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0039] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing an application early warning method. Figure 1As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0040] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0041] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the application warning method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned application warning method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0042] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0043] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0044] Under the above operating environment, this application provides Figure 2 Application warning method shown. Figure 2 It is a flowchart of an application warning method provided according to an embodiment of the present application.

[0045] Step S201, when a batch job warning of a first application is detected, an operation risk value of the first application is obtained, wherein the operation risk value of the first application is determined at least according to the operation risk value of the batch job in the first application.

[0046] Optionally, electronic devices, application systems, servers and other devices may be used as the execution subject of the present application. In this embodiment, the target processing system is used as the execution subject to execute the application warning method.

[0047] Optionally, the type of the first application and the content of the batch job vary according to the actual application scenario. For example, in a financial scenario, the first application may be a bill generation application, which is responsible for generating monthly bills for credit card users, including the collation and calculation of data such as consumption details, repayment information, and points changes. Batch jobs can be used to summarize all transaction data that occurs at the end of each day's business, update user transaction records, and generate a list of consumption for the day.

[0048] Optionally, batch jobs process big data in batches based on the program logic of scheduled task execution. It is a program method used to process large batches of data in financial institution systems. Batch jobs contain parameter definitions such as job number, application abbreviation, batch type, number of shards, planned execution date, and planned execution time, which are used to specify the execution logic of batch jobs. Batch jobs are a distributed processing method, and different batch jobs may have execution order or dependency requirements. When problems occur in the execution of a batch job, it will affect other jobs that depend on the job, which may also affect the applications where other jobs that depend on the job are located. When a batch job has a problem, an alarm will be issued on the system used to monitor the batch job to notify support personnel to solve the problem.

[0049] In some embodiments, batch jobs in the first application may be monitored by a monitoring system, and the target processing system may determine that a batch job warning of the first application is detected when receiving warning information for the batch job sent by the aforementioned monitoring system.

[0050] In some embodiments, the target processing system may also detect the index of the batch job to determine whether to issue an early warning for the batch job according to the index value obtained by the detection.

[0051] Optionally, in the case of detecting a batch job warning of the first application, the target processing system may determine the operation risk value of the first application, and the operation risk value of the first application is determined at least according to the operation risk value of the batch job in the first application. For example, the operation risk value of all batch jobs in the first application is averaged to obtain the operation risk value of the first application. For another example, the operation risk value of all batch jobs in the first application is weighted and summed to obtain the operation risk value of the first application. For another example, based on the operation risk value of the batch job, the operation risk value of the first application is determined in combination with the operation risk value of the transmission task associated with the batch job in the first application. The transmission task is used to transmit data between batch jobs, for example, the job result of a batch job is transmitted to another batch job as input, and the transmission task associated with the batch job refers to a transmission task used to receive the job result of the batch job, or a transmission task used to send the job result of other batch jobs to the batch job.

[0052] Optionally, the running risk value of the first application represents a probability of an abnormality occurring during the running of the first application, and the running risk value of the batch job represents a probability of an abnormality occurring during the running of the batch job.

[0053] Step S202: determine a second application associated with the batch job of the first application, and obtain an operation risk value of the second application.

[0054] Optionally, the second application associated with the first application may be pre-stored by a user in the target storage area, or the second application associated with the first application may be determined by the target processing system based on the transmission task in the first application. For example, the application where the target batch task is located is determined as the second application, and the target batch task refers to another batch task associated with the transmission task corresponding to the batch task of the first application.

[0055] Optionally, the method for determining the operation risk value of the second application is the same as the method for determining the operation risk value of the first application, so it is not repeated here.

[0056] Step S203, calculate the target operation risk value of the second application according to the operation risk value of the first application, the correlation influence coefficient between the first application and the second application, and the operation risk value of the second application, and issue an early warning to the first application and the second application when the target operation risk value is greater than a preset threshold.

[0057] Optionally, the correlation influence coefficient between the first application and the second application may be a preset value, or may be calculated by the target processing system.

[0058] Optionally, the target processing system may calculate the risk impact value of the first application on the second application based on the operating risk value of the first application and the correlation influence coefficient between the first application and the second application, and then calculate the target operating risk value of the second application based on the risk impact value and the operating risk value of the second application. For example, the risk impact value and the operating risk value of the second application are added to obtain the target operating risk value.

[0059] Optionally, after obtaining the target operation risk value, the target processing system may compare the target operation risk value with a preset threshold, thereby issuing an early warning to the first application and the second application when the target operation risk value is greater than the preset threshold, and issuing an early warning only to the first application when the target operation risk value is less than or equal to the preset threshold.

[0060] In an embodiment of the present application, by determining a second application associated with the batch job of the first application and obtaining an operation risk value of the second application when a batch job warning of the first application is detected, effective determination of the operation risk of the second application related to the batch job operation of the first application is achieved. By calculating the target operation risk value of the second application based on the operation risk value of the first application, the correlation coefficient between the first application and the second application, and the operation risk value of the second application, effective determination of the probability that the second application associated with the batch job of the first application may have an abnormality when a problem occurs in the batch job of the first application is achieved. By issuing an early warning to the first application and the second application when the target operation risk value is greater than a preset threshold, when a problem occurs in the batch job of the first application, an early warning is issued to the second application that is most likely to be affected by the first application, thereby improving the reliability of the early warning.

[0061] It can be seen that the solution provided by the present application achieves the purpose of issuing early warnings to multiple applications when problems arise in the application's execution of batch jobs, achieves the technical effect of improving the reliability of early warnings, and solves the problem in related technologies of issuing early warnings to a single application when problems arise in the application's execution of batch jobs, resulting in poor early warning reliability.

[0062] Optionally, in the application warning method provided in the embodiment of the present application, obtaining the operation risk value of the first application includes: obtaining the job feature vectors of each batch job in the first application, and obtaining the application feature vector of the first application; calculating the first relevant influence coefficient of the operation risk of each batch job on the operation risk of the first application based on the job feature vectors and application feature vectors of each batch job; obtaining the operation risk value of each batch job in the first application, and calculating the operation risk value of the first application based on the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job.

[0063] In some embodiments, the target processing system may determine the job feature vector of the batch job based on the source code in the execution program of the batch job and the code called by the execution program. For example, the target processing system may use an encoder to process the source code of the batch job and the called code to obtain the job feature vector of the batch job.

[0064] In some embodiments, the target processing system may determine the application feature vector of the first application based on the application information of the first application. For example, the application information of the first application is input into an encoder, and the application information of the first application is processed by the encoder to obtain the feature vector of the first application. The encoder may be a Bert encoder.

[0065] Optionally, after obtaining the job feature vector and application feature vector of each batch job in the first application, the target processing system may calculate the first relevant impact coefficient of the operation risk of each batch job on the operation risk of the first application based on the job feature vector and application feature vector of each batch job. For example, for each batch job, the target processing system may input the job feature vector of the batch job and the application feature vector of the first application into a first impact coefficient prediction model. The first impact coefficient prediction model may be a convolutional neural network. For example, the first impact coefficient prediction model is composed of 6 residual modules, a pooling layer, and a fully connected layer. The result output by the fully connected layer is normalized by Softmax to obtain the first relevant impact coefficient of the operation risk of the batch job on the operation risk of the first application.

[0066] Optionally, the first influence coefficient prediction model can be obtained in the following manner: obtain a first training sample set, wherein the training samples of the first training sample set include a sample application feature vector of a sample application and a sample job feature vector in the sample application, and the true label of the training sample represents the influence degree of the operating risk of the sample job on the operating risk of the sample application, and the true label can be manually preset; use the first training sample set to train an initial influence coefficient prediction model to obtain a first influence coefficient prediction model.

[0067] Optionally, after obtaining the first relevant impact coefficient of the operation risk of each batch job on the operation risk of the first application, the target processing system may obtain the operation risk value of each batch job in the first application. Optionally, the operation risk value of each batch job may be in a preset target storage area, or may be obtained by the target processing system performing simulation testing and / or code analysis on the batch job.

[0068] Optionally, the target processing system may calculate the operation risk value of the first application according to the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job. For example, for each batch job, the operation risk value of the batch job is multiplied by the first relevant influence coefficient corresponding to the batch job to obtain a first value, and then the first values ​​corresponding to all batch jobs in the first application are averaged to obtain the operation risk value of the first application.

[0069] Optionally, the operation risk value of the second application is calculated in the same manner as the operation risk value of the first application, so it is not repeated here.

[0070] It should be noted that, through the above process, the operation risk value of the first application is determined in combination with the degree of influence of the operation risks of each batch job on the operation risk of the first application, thereby improving the accuracy of the determined operation risk value of the first application.

[0071] Optionally, in the application warning method provided in the embodiment of the present application, a job feature vector of each batch job in the first application is obtained, including: for each batch job, obtaining the source code in the execution program corresponding to the batch job and the code called by the execution program to obtain a code set for the batch job; performing vector conversion on the code in the code set based on a preset vocabulary to obtain a processed code set, wherein the vocabulary includes a mapping relationship between multiple code words and multiple encoding vectors; encoding the processed code set using an encoder to obtain an initial feature vector corresponding to the batch job; and processing the initial feature vector using a self-attention mechanism to obtain a job feature vector for the batch job.

[0072] For example, Figure 3 is a schematic diagram of determining a job feature vector according to an embodiment of the present application, such as Figure 3 As shown, for each batch job, the target processing system can read the source program (annotated class and its calling method) in the batch job execution program, determine multiple estimation samples from the source program according to the calling class name, wherein one estimation sample corresponds to one class, and split the estimation sample according to the preset character length to obtain multiple estimation sub-samples corresponding to each estimation sample. Optionally, the target processing system can also read the code called by the batch job execution program (e.g., the source code of the file server processing related base class), and then determine multiple estimation samples from the code according to the class name, and split it into multiple estimation sub-samples. Optionally, the aforementioned multiple estimation sub-samples constitute the code set of the batch job.

[0073] like Figure 3 As shown, after obtaining the code set of the batch job, the target processing system can read the estimated subsample for each estimated subsample and format the estimated subsample according to the preset rules (such as JAVA rules). After that, the estimated subsample is processed according to the preset vocabulary, specifically, the illegal characters and control characters in the estimated subsample are deleted, the line breaks, indents, comment codes, etc. in the estimated sample are replaced with space characters, and the uppercase characters are replaced with lowercase characters. Then, the estimated sample is split into words according to space characters and punctuation marks, and then the estimated subsample is vectorized according to the vocabulary, and the split words are matched with the vocabulary. For example, according to the maximum matching method, the words in the vocabulary are taken from left to right, and the words with the maximum length containing the sample are taken as the matching object. After the match is successful, the encoding vector of the matching word in the vocabulary is used as the dictionary vector of the code word. If the match is unsuccessful, the rightmost character of the sample is deleted, and the matching and vectorization are repeated. Therefore, after all the code words in the estimated subsample are vectorized, the processed estimated subsample is obtained, and then the processed code set can be obtained. Here, different code words in the vocabulary are matched with different encoding vectors.

[0074] like Figure 3 As shown, after obtaining the processed code set, the target processing system can use the Bert encoder to process the estimated subsamples in the processed code set to obtain the initial vector representation of each estimated subsample, that is, to obtain the initial feature vector corresponding to the batch job. The steps are as follows: for each split word (i.e., code word) of the estimated subsample, generate a position code with the same length as the sequence code and slice code of the split word. The value of the position code is wx+b, where x is the sequence code, w is the weight matrix in the Bert encoder, and b is the bias matrix in the Bert encoder. For each estimated subsample, add the corresponding sequence code, slice code, and position code to obtain the initial vector representation of the estimated subsample, and concatenate the initialization vector representations of all estimated subsamples to obtain the initial feature vector corresponding to the batch job.

[0075] Optional, such as Figure 3 As shown, after obtaining the initial feature vector corresponding to the batch job, the target processing system can use the self-attention mechanism to process the initial feature vector to obtain the job feature vector of the batch job. For example, the query feature vector Q of the initial feature vector is calculated, the query matrix Wq is multiplied by the vector representation of the batch job to obtain the query feature vector Q, the key feature vector K of the batch job is calculated, the key matrix Wk is multiplied by the vector representation of the batch job to obtain the key feature vector K, the value feature vector V of the batch job is calculated, and the value matrix Wv is multiplied by the vector representation of the batch job to obtain the value feature vector V. The query feature vector Q is multiplied by the conjugate Kt of the key feature vector, and then multiplied by the value feature vector V to obtain the interaction score S. The interaction score S is input into the normalized activation function Softmax to normalize it to a value between 0 and 1 to obtain the attention feature vector of the batch job, and then the input vector representation of the batch job is linearly superimposed with the attention feature vector, and then processed by the Softmax activation function and two layers of linear transformation to obtain the job feature vector of the batch job.

[0076] In some embodiments, the self-attention mechanism is a multi-layer self-attention mechanism. For example, 12 sets of independent query feature vectors Wq, key feature matrices Wk, and value feature matrices Wv may be set, and the above processing steps are repeated to obtain 12 sets of attention feature vectors for batch jobs. Then, the 12 sets of attention feature vectors are processed to obtain the job feature vectors for the batch jobs.

[0077] In some embodiments, the self-attention mechanism belongs to a risk prediction model, and the risk prediction model is used to process the initial feature vector to obtain the job feature vector, and to process the job feature vector to obtain the first running risk value of the batch job. The risk prediction model can be a neural network model.

[0078] In some embodiments, the risk prediction model is obtained by: obtaining a second training sample set, wherein the training samples in the second training sample set are sample initial feature vectors of sample batch jobs, and the true labels of the training samples are true operating risk values ​​corresponding to the sample batch jobs; training the initial risk prediction model through the second training sample set to obtain a risk prediction model.

[0079] It should be noted that, through the above method, the job feature vector of the batch job is determined according to the source code in the execution program of the batch job and the code called by the execution program, thereby improving the accuracy of the determined job feature vector.

[0080] Optionally, in the application warning method provided in the embodiment of the present application, the operation risk value of each batch job in the first application is obtained, including: for each batch job, using a risk prediction model to process the job feature vector to obtain a first operation risk value of the batch job; obtaining a second operation risk value of the batch job, wherein the second operation risk value is obtained by performing a simulated operation test on the batch job; and determining the operation risk value of the batch job based on the first operation risk value and the second operation risk value of the batch job.

[0081] In some embodiments, the risk prediction model may be a neural network model. The risk prediction model is obtained by: obtaining a second training sample set, wherein the training samples in the second training sample set are sample initial feature vectors of sample batch jobs, and the true labels of the training samples are true operation risk values ​​corresponding to the sample batch jobs; and training the initial risk prediction model with the second training sample set to obtain the risk prediction model.

[0082] Optionally, the target processing system may process the initial feature vector using a risk prediction model to obtain a job feature vector, and then process the job feature vector to obtain a first operation risk value of the batch job.

[0083] Optionally, the target processing system may obtain a second operation risk value of the batch job. Figure 4 is a schematic diagram of determining a second operation risk value according to an embodiment of the present application, such as Figure 4As shown, the second operation risk value is obtained in the following manner: before the batch job is executed, the database or file source data read by the batch job is simulated, the simulated source data is empty, and then the real batch job execution method is called to obtain the output data of the batch job, and the output estimated value of the batch job is set. When the test value output by the batch job is the estimated value, the test result is successful, and when the test value output by the batch job is not the estimated value, the test result is unsuccessful. Then, referring to the real data of the production environment, multiple groups of source data of the batch job are randomly generated, the source data input is re-simulated, and the real batch job execution method is called. At this time, the output result of the batch job is ignored. When the execution result of the batch job is normal, the test result is successful, and when the execution result of the batch job is abnormal, the test result is unsuccessful. Execute the above two tests multiple times (for example, execute N times, N is a positive integer greater than 1), calculate the proportion of the number of test results failures in the total number of tests, and obtain the second operation risk value of the batch job.

[0084] Optionally, after obtaining the first operation risk value and the second operation risk value, the target processing system may determine the operation risk value of the batch job according to the first operation risk value and the second operation risk value of the batch job. For example, the first operation risk value and the second operation risk value are averaged to obtain the operation risk value of the batch job.

[0085] It should be noted that, through the above process, the operation risk value of the batch job is determined by combining the prediction results of the model and the actual test results, that is, the operation risk value of the batch job is evaluated from multiple dimensions, thereby improving the accuracy of the determined operation risk value. In addition, the operation risk value of the batch job calculated in this application does not depend on the parameters in the batch job operation. Before the batch job is executed, the operation risk value of the batch job can be determined, so that a quick response can be made after a warning occurs, thereby improving the timeliness of early warning for the application.

[0086] Optionally, in the application warning method provided in the embodiment of the present application, the operation risk value of the first application is calculated according to the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job, including: obtaining the task feature vector of each target transmission task in the first application, and obtaining the operation risk value of each target transmission task in the first application, wherein the target transmission task refers to the transmission task associated with the batch job in the first application; calculating the second relevant influence coefficient of the operation risk of the target transmission task on the operation risk of the application according to the task feature vector and the application feature vector of each target transmission task; calculating the operation risk value of the first application according to the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job, as well as the operation risk value of each target transmission task in the first application and the second relevant influence coefficient corresponding to each target transmission task.

[0087] In some embodiments, the target processing system may also determine the operation risk value of the first application by combining the operation risk value of the target transmission task in the first application and the second related influence coefficient. The target transmission task refers to a transmission task associated with a batch job in the first application, and the transmission task associated with the batch job refers to a transmission task for receiving the job result of the batch job, or a transmission task for sending the job result of other batch jobs to the batch job.

[0088] Optionally, for each target transmission task, the target processing system may first obtain the sending directory (the directory where the data to be sent is located) of the source node application A and the receiving directory (the directory where the data to be received is stored) of the target node application B corresponding to the target transmission task, and then encode the sending directory and the receiving directory based on the Bert encoder to obtain a first vector, and then encode task parameters such as task priority, whether to retransmit, duplicate file processing strategy, and transmission failure notification strategy to obtain a second vector, thereby determining the task feature vector of the target transmission task based on the first vector and the second vector, for example, concatenating the first vector and the second vector to obtain a task feature vector.

[0089] Optionally, the operational risk value of each target transmission task can be preset by the staff.

[0090] After obtaining the task feature vector and application feature vector of each target transmission task, the target processing system can calculate the second relevant impact coefficient of the operation risk of the target transmission task on the operation risk of the application based on the task feature vector and application feature vector of each target transmission task. For example, for each target transmission task, the target processing system can input the task feature vector of the target transmission task and the application feature vector of the first application into the second impact coefficient prediction model. The second impact coefficient prediction model can be a convolutional neural network. For example, the second impact coefficient prediction model is composed of 6 residual modules, a pooling layer, and a fully connected layer. The result output by the fully connected layer is normalized by Softmax to obtain the second relevant impact coefficient of the operation risk of the target transmission task on the operation risk of the application.

[0091] Optionally, the second influence coefficient prediction model can be obtained in the following manner: obtain a third training sample set, wherein the training samples of the third training sample set include sample application feature vectors of sample applications and sample task feature vectors of sample transmission tasks in the sample applications, and the true labels of the training samples represent the degree of influence of the operating risk of the sample transmission task on the operating risk of the sample application, and the true labels can be manually preset; use the third training sample set to train the initial influence coefficient prediction model to obtain the second influence coefficient prediction model.

[0092] Afterwards, the target processing system can calculate the operation risk value of the first application based on the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job, as well as the operation risk value of each target transmission task in the first application and the second relevant influence coefficient corresponding to each target transmission task. For example, for each batch job, the operation risk value of the batch job is multiplied by the first relevant influence coefficient corresponding to the batch job to obtain a first value, and then the first values ​​corresponding to all batch jobs in the first application are averaged to obtain a first average value. For each target transmission task, the operation risk value of the target transmission task is multiplied by the second relevant influence coefficient corresponding to the target transmission task to obtain a second value, and then the second values ​​corresponding to all target transmission tasks in the first application are averaged to obtain a second average value, thereby determining the average of the first average value and the second average value as the operation risk value of the first application.

[0093] In some embodiments, the target processing system can store the association relationship between the first application, the batch job, the target transmission task, and the second application by constructing an undirected job graph, so that the target processing system can quickly determine the required information when calculating the operation risk value of the application and the target operation risk value of the second application. For example, based on the dependency relationship of the batch job, an undirected job graph is constructed, and the undirected job graph includes application nodes, batch job nodes, and transmission task nodes. The attribute of the application node is the application feature vector of the application, the attribute of the batch job node is the job feature vector of the batch job, and the attribute of the transmission task node is the task feature vector of the transmission task node. There are edges between nodes with association relationships, and the attributes of the edges are used to record the correlation coefficient between two nodes. For example, Figure 5 is a schematic diagram of an undirected job graph provided according to an embodiment of the present application, such as Figure 5 As shown, application A can be understood as the first application, application B can be understood as the second application, application A includes batch jobs A1 and A2, and target transmission task 01, and application B includes batch job B1 and target transmission task 01.

[0094] It should be noted that, through the above process, the operation risk value of the first application is calculated by combining the batch job, the operation risk value of the transmission task associated with the batch job and the related impact coefficient, thereby further improving the accuracy of the calculated operation risk value of the application.

[0095] Optionally, in the application warning method provided in the embodiment of the present application, before calculating the target operation risk value of the second application based on the operation risk value of the first application, the correlation influence coefficient between the first application and the second application, and the operation risk value of the second application, the method also includes: obtaining an application feature vector of the first application, and obtaining an application feature vector of the second application; and calculating the correlation influence coefficient between the first application and the second application based on the application feature vector of the first application and the application feature vector of the second application.

[0096] Optionally, the target processing system may input the application information of the first application into an encoder, and process the application information of the first application through the encoder to obtain an application feature vector of the first application. The aforementioned encoder may be a Bert encoder. The target processing system may input the application information of the second application into an encoder, and process the application information of the second application through the encoder to obtain an application feature vector of the second application.

[0097] Optionally, the target processing system can calculate the correlation coefficient between the first application and the second application based on the application feature vector of the first application and the application feature vector of the second application. For example, the application feature vector of the first application and the application feature vector of the second application are input into the third influence coefficient prediction model, and the third influence coefficient prediction model can be a convolutional neural network model. For example, the third influence coefficient prediction model is composed of 6 residual modules, a pooling layer, and a fully connected layer. The result output by the fully connected layer is normalized by Softmax to obtain the correlation coefficient between the operation risk of the first application and the operation risk of the second application.

[0098] Optionally, the third influence coefficient prediction model can be obtained in the following manner: obtain a fourth training sample set, wherein the training samples of the fourth training sample set include a sample application feature vector of the first sample application and a sample application feature vector of the second sample application, and the true label of the training sample represents the influence degree of the operation risk of the first sample application on the operation risk of the second sample application, and the true label can be manually preset; use the fourth training sample set to train the initial influence coefficient prediction model to obtain the third influence coefficient prediction model.

[0099] It should be noted that, through the above method, it is possible to determine the correlation influence coefficient between applications according to the application characteristics, thereby improving the accuracy of the determined correlation influence coefficient.

[0100] Optionally, in the application warning method provided in the embodiment of the present application, before obtaining the operation risk value of the first application, the method also includes: for each batch job in the first application, obtaining a detection indicator for the job information of the batch job to obtain a first detection indicator; obtaining a detection indicator for the target container to obtain a second detection indicator, wherein the target container is used to execute the batch job; during the execution of the batch job, detecting the batch job based on the first detection indicator and the second detection indicator, and determining the target information based on the detected indicator value, wherein the target information is used to characterize whether to issue a warning for the batch job.

[0101] For example, Figure 6 is a schematic diagram of determining target information according to an embodiment of the present application, such as Figure 6 As shown, the target processing system can determine the target information through the following steps:

[0102] (1) Before executing a batch job, read the batch job data information. Read the configuration definition file of the batch job, and generate a unique batch job node based on the definition information of the batch job, including the job number, the application abbreviation, the batch type, the number of shards, the planned execution date, the planned execution time, and other execution parameters, such as the number of executions per day, the execution interval, the job submission method, whether it affects daily switching, the job group number, the batch number, the batch name, and whether it can be executed repeatedly.

[0103] (2) Before executing the batch job, read the batch job monitoring indicator (i.e., the first detection indicator). Obtain the preset monitoring configuration file of the batch job, read the monitoring configuration file, and obtain the batch job duration indicator, interruption indicator, job message sending indicator, and file delivery indicator. The monitoring configuration file also includes the threshold or expected value of each indicator.

[0104] (3) Obtain the monitoring indicators (second detection indicators) of the batch job execution container (i.e., the target container). According to the job execution task information of the batch console, query the batch job execution container, and obtain the performance indicators of the batch job execution container on the platform to which the container belongs, including the container's CPU usage, cache usage, disk read and write usage, network throughput, and abnormal messages sent by the container. You can also obtain the thresholds or expected values ​​of various container monitoring indicators from the platform to which the container belongs.

[0105] (4) During the operation of the batch job executor, based on the monitoring indicators of the batch job (i.e., the first detection indicator and the second detection indicator), it is determined whether to issue an alarm, that is, the target information is determined. For example, for threshold indicators such as job duration, container CPU usage, and container memory usage, when the obtained real-time monitoring parameters exceed the threshold, an alarm is issued for the current batch job; for expected value indicators such as interruption indicators, job upload messages, and container upload messages, when the obtained real-time monitoring parameters do not meet the expected values, an alarm is issued for the current batch job.

[0106] It should be noted that, through the above process, effective detection of batch operations is achieved, thereby improving the accuracy of early warning.

[0107] It can be seen that the solution provided by the present application achieves the purpose of issuing early warnings to multiple applications when problems arise in the application's execution of batch jobs, achieves the technical effect of improving the reliability of early warnings, and solves the problem in related technologies of issuing early warnings to a single application when problems arise in the application's execution of batch jobs, resulting in poor early warning reliability.

[0108] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0109] Example 2

[0110] The embodiment of the present application also provides an application warning device. It should be noted that the application warning device of the embodiment of the present application can be used to execute the application warning method provided by the embodiment of the present application. The application warning device provided by the embodiment of the present application is introduced below.

[0111] According to an embodiment of the present application, a device for implementing the above-mentioned application warning method is also provided. Figure 7 is a schematic diagram of an application warning device provided according to an embodiment of the present application, such as Figure 7 As shown, the device comprises:

[0112] A first acquisition module 701 is used to acquire an operation risk value of the first application when a batch job warning of the first application is detected, wherein the operation risk value of the first application is determined at least according to the operation risk value of the batch job of the first application;

[0113] A second acquisition module 702 is used to determine a second application associated with the batch job of the first application, and to acquire an operation risk value of the second application;

[0114] Processing module 703 is used to calculate the target operation risk value of the second application based on the operation risk value of the first application, the correlation influence coefficient between the first application and the second application, and the operation risk value of the second application, and to issue an early warning to the first application and the second application when the target operation risk value is greater than a preset threshold.

[0115] In an embodiment of the present application, by determining a second application associated with the batch job of the first application and obtaining an operation risk value of the second application when a batch job warning of the first application is detected, effective determination of the operation risk of the second application related to the batch job operation of the first application is achieved. By calculating the target operation risk value of the second application based on the operation risk value of the first application, the correlation coefficient between the first application and the second application, and the operation risk value of the second application, effective determination of the probability that the second application associated with the batch job of the first application may have an abnormality when a problem occurs in the batch job of the first application is achieved. By issuing an early warning to the first application and the second application when the target operation risk value is greater than a preset threshold, when a problem occurs in the batch job of the first application, an early warning is issued to the second application that is most likely to be affected by the first application, thereby improving the reliability of the early warning.

[0116] It can be seen that the solution provided by the present application achieves the purpose of issuing early warnings to multiple applications when problems arise in the application's execution of batch jobs, achieves the technical effect of improving the reliability of early warnings, and solves the problem in related technologies of issuing early warnings to a single application when problems arise in the application's execution of batch jobs, resulting in poor early warning reliability.

[0117] Optionally, in the application warning device provided in the embodiment of the present application, the first acquisition module also includes: a first acquisition sub-module, used to obtain the job feature vector of each batch job in the first application, and obtain the application feature vector of the first application; a first calculation sub-module, used to calculate the first relevant influence coefficient of the operation risk of each batch job on the operation risk of the first application based on the job feature vector and application feature vector of each batch job; a second calculation sub-module, used to obtain the operation risk value of each batch job in the first application, and calculate the operation risk value of the first application based on the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job.

[0118] Optionally, in the application warning device provided in the embodiment of the present application, the first acquisition submodule also includes: a first acquisition unit, used to obtain, for each batch job, the source code in the execution program corresponding to the batch job and the code called by the execution program, to obtain a code set for the batch job; a first processing unit, used to perform vector conversion on the code in the code set based on a preset vocabulary, to obtain a processed code set, wherein the vocabulary includes a mapping relationship between multiple code words and multiple encoding vectors; a second processing unit, used to encode the processed code set using an encoder, to obtain an initial feature vector corresponding to the batch job; a third processing unit, used to process the initial feature vector using a self-attention mechanism, to obtain a job feature vector for the batch job.

[0119] Optionally, in the application warning device provided in the embodiment of the present application, the second calculation submodule also includes: a fourth processing unit, used to process the job feature vector for each batch job using a risk prediction model to obtain a first operation risk value of the batch job; a second acquisition unit, used to obtain a second operation risk value of the batch job, wherein the second operation risk value is obtained by performing a simulated operation test on the batch job; and a determination unit, used to determine the operation risk value of the batch job based on the first operation risk value and the second operation risk value of the batch job.

[0120] Optionally, in the application warning device provided in the embodiment of the present application, the second calculation submodule also includes: a third acquisition unit, used to obtain the task feature vector of each target transmission task in the first application, and obtain the operation risk value of each target transmission task in the first application, wherein the target transmission task refers to the transmission task associated with the batch job in the first application; a first calculation unit, used to calculate the second relevant influence coefficient of the operation risk of the target transmission task on the operation risk of the application based on the task feature vector and the application feature vector of each target transmission task; a second calculation unit, used to calculate the operation risk value of the first application based on the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job, as well as the operation risk value of each target transmission task in the first application and the second relevant influence coefficient corresponding to each target transmission task.

[0121] Optionally, in the application warning device provided in the embodiment of the present application, the application warning device also includes: a third acquisition module, used to obtain the application feature vector of the first application and to obtain the application feature vector of the second application; a calculation module, used to calculate the correlation influence coefficient between the first application and the second application based on the application feature vector of the first application and the application feature vector of the second application.

[0122] Optionally, in the application warning device provided in the embodiment of the present application, the application warning device also includes: a fourth acquisition module, used to obtain, for each batch job in the first application, a detection indicator for the job information of the batch job, and obtain a first detection indicator; a fifth acquisition module, used to obtain a detection indicator for a target container, and obtain a second detection indicator, wherein the target container is used to execute the batch job; a determination module, used to detect the batch job based on the first detection indicator and the second detection indicator during the execution of the batch job, and determine the target information based on the detected indicator value, wherein the target information is used to characterize whether to issue a warning for the batch job.

[0123] It should be noted that the first acquisition module 701, the second acquisition module 702 and the processing module 703 correspond to steps S201 to S203 in Example 1, and the three modules and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the above-mentioned modules or units may be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned modules may also be part of the device and may be run in the computer terminal 10 provided in Example 1.

[0124] Example 3

[0125] An embodiment of the present application may provide an electronic device, Figure 8 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 8 As shown, the electronic device may include: one or more ( Figure 8 (only one is shown) processor 1002, memory 1004, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0126] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0127] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: when a batch job warning of the first application is detected, obtain the operation risk value of the first application, wherein the operation risk value of the first application is determined at least according to the operation risk value of the batch job in the first application; determine a second application that has an association relationship with the batch job of the first application, and obtain the operation risk value of the second application; calculate the target operation risk value of the second application according to the operation risk value of the first application, the correlation influence coefficient between the first application and the second application, and the operation risk value of the second application, and when the target operation risk value is greater than a preset threshold, issue an alarm for the first application and the second application.

[0128] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the job feature vectors of each batch job in the first application, and obtain the application feature vector of the first application; calculate the first relevant influence coefficient of the operation risk of each batch job on the operation risk of the first application based on the job feature vectors and application feature vectors of each batch job; obtain the operation risk value of each batch job in the first application, and calculate the operation risk value of the first application based on the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job.

[0129] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: for each batch job, obtain the source code in the execution program corresponding to the batch job and the code called by the execution program to obtain a code set for the batch job; perform vector conversion on the code in the code set based on a preset vocabulary to obtain a processed code set, wherein the vocabulary includes a mapping relationship between multiple code words and multiple encoding vectors; use an encoder to encode the processed code set to obtain an initial feature vector corresponding to the batch job; use a self-attention mechanism to process the initial feature vector to obtain a job feature vector for the batch job.

[0130] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: for each batch job, use the risk prediction model to process the job feature vector to obtain a first operation risk value of the batch job; obtain a second operation risk value of the batch job, wherein the second operation risk value is obtained by performing a simulated operation test on the batch job; determine the operation risk value of the batch job based on the first operation risk value and the second operation risk value of the batch job.

[0131] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the task feature vector of each target transmission task in the first application, and obtain the operation risk value of each target transmission task in the first application, wherein the target transmission task refers to the transmission task associated with the batch job in the first application; calculate the second relevant influence coefficient of the operation risk of the target transmission task on the operation risk of the application based on the task feature vector and the application feature vector of each target transmission task; calculate the operation risk value of the first application based on the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job, as well as the operation risk value of each target transmission task in the first application and the second relevant influence coefficient corresponding to each target transmission task.

[0132] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: before calculating the target operation risk value of the second application based on the operation risk value of the first application, the correlation influence coefficient between the first application and the second application, and the operation risk value of the second application, obtain the application feature vector of the first application and obtain the application feature vector of the second application; based on the application feature vector of the first application and the application feature vector of the second application, calculate the correlation influence coefficient between the first application and the second application.

[0133] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: before obtaining the operation risk value of the first application, for each batch job in the first application, obtain the detection index of the job information of the batch job to obtain the first detection index; obtain the detection index for the target container to obtain the second detection index, wherein the target container is used to execute the batch job; during the execution of the batch job, detect the batch job based on the first detection index and the second detection index, and determine the target information based on the detected indicator value, wherein the target information is used to indicate whether to issue an early warning for the batch job.

[0134] In an embodiment of the present application, by determining a second application associated with the batch job of the first application and obtaining an operation risk value of the second application when a batch job warning of the first application is detected, effective determination of the operation risk of the second application related to the batch job operation of the first application is achieved. By calculating the target operation risk value of the second application based on the operation risk value of the first application, the correlation coefficient between the first application and the second application, and the operation risk value of the second application, effective determination of the probability that the second application associated with the batch job of the first application may have an abnormality when a problem occurs in the batch job of the first application is achieved. By issuing an early warning to the first application and the second application when the target operation risk value is greater than a preset threshold, when a problem occurs in the batch job of the first application, an early warning is issued to the second application that is most likely to be affected by the first application, thereby improving the reliability of the early warning.

[0135] It can be seen that the solution provided by the present application achieves the purpose of issuing early warnings to multiple applications when problems arise in the application's execution of batch jobs, achieves the technical effect of improving the reliability of early warnings, and solves the problem in related technologies of issuing early warnings to a single application when problems arise in the application's execution of batch jobs, resulting in poor early warning reliability.

[0136] It can be understood by those skilled in the art that Figure 8 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 8 The structure of the electronic device is not limited. Figure 8 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 8 Different configurations shown.

[0137] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0138] Example 4

[0139] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the application warning method provided in the first embodiment.

[0140] Optionally, in this embodiment, the above-mentioned storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0141] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the program steps of the application warning method.

[0142] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0143] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0144] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0145] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0146] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0147] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0148] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An application early warning method, characterized in that: include: In the case where a batch job warning of a first application is detected, obtaining an operation risk value of the first application, wherein the operation risk value of the first application is determined at least according to the operation risk value of the batch job of the first application; Determine a second application associated with the batch job of the first application, and obtain an operation risk value of the second application; A target operation risk value of the second application is calculated based on the operation risk value of the first application, the correlation coefficient between the first application and the second application, and the operation risk value of the second application, and when the target operation risk value is greater than a preset threshold, an early warning is issued for the first application and the second application.

2. The method according to claim 1, characterized in that Obtaining the operation risk value of the first application includes: Obtaining a job feature vector of each batch job in the first application, and obtaining an application feature vector of the first application; Calculating a first correlation influence coefficient of the operation risk of each batch job on the operation risk of the first application according to the operation feature vector of each batch job and the application feature vector; The operation risk value of each batch job in the first application is obtained, and the operation risk value of the first application is calculated according to the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job.

3. The method according to claim 2, characterized in that Obtaining a job feature vector of each batch job in the first application includes: For each batch job, the source code in the execution program corresponding to the batch job and the code called by the execution program are obtained to obtain a code set of the batch job; Performing vector conversion on the codes in the code set based on a preset vocabulary to obtain a processed code set, wherein the vocabulary includes a mapping relationship between a plurality of code words and a plurality of encoding vectors; Encoding the processed code set using an encoder to obtain an initial feature vector corresponding to the batch job; The initial feature vector is processed by using a self-attention mechanism to obtain a job feature vector of the batch job.

4. The method according to claim 2, characterized in that: Obtaining the running risk value of each batch job in the first application includes: For each batch job, the job feature vector is processed using a risk prediction model to obtain a first operation risk value of the batch job; Acquire a second operation risk value of the batch job, wherein the second operation risk value is obtained by performing a simulated operation test on the batch job; An operation risk value of the batch job is determined according to the first operation risk value and the second operation risk value of the batch job.

5. The method according to claim 2, characterized in that: Calculating the operation risk value of the first application according to the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job includes: Obtaining a task feature vector of each target transmission task in the first application, and obtaining an operation risk value of each target transmission task in the first application, wherein the target transmission task refers to a transmission task associated with a batch job in the first application; Calculating a second correlation influence coefficient of the operation risk of the target transmission task on the operation risk of the application according to the task feature vector of each target transmission task and the application feature vector; The operation risk value of the first application is calculated based on the operation risk value of each batch job in the first application and the first relevant influence coefficient corresponding to each batch job, as well as the operation risk value of each target transmission task in the first application and the second relevant influence coefficient corresponding to each target transmission task.

6. The method according to claim 1, characterized in that Before calculating the target operation risk value of the second application according to the operation risk value of the first application, the correlation influence coefficient between the first application and the second application, and the operation risk value of the second application, the method further includes: Obtaining an application feature vector of the first application, and obtaining an application feature vector of the second application; A correlation influence coefficient between the first application and the second application is calculated according to the application feature vector of the first application and the application feature vector of the second application.

7. The method according to claim 1, characterized in that Before obtaining the operation risk value of the first application, the method further includes: For each batch job in the first application, obtaining a detection indicator for job information of the batch job to obtain a first detection indicator; Acquire a detection index for a target container to obtain a second detection index, wherein the target container is used to execute the batch job; During the execution of the batch job, the batch job is detected based on the first detection index and the second detection index, and target information is determined based on the detected index values, wherein the target information is used to indicate whether to issue an early warning for the batch job.

8. An application warning device, characterized in that: include: A first acquisition module is used to acquire an operation risk value of a first application when a batch job warning of the first application is detected, wherein the operation risk value of the first application is determined at least according to the operation risk value of the batch job of the first application; A second acquisition module, configured to determine a second application associated with the batch job of the first application, and acquire an operation risk value of the second application; A processing module is used to calculate a target operation risk value of the second application based on the operation risk value of the first application, the correlation influence coefficient between the first application and the second application, and the operation risk value of the second application, and to issue an early warning to the first application and the second application when the target operation risk value is greater than a preset threshold.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the application warning method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program executes the application warning method described in any one of claims 1 to 7 when running.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the application warning method described in any one of claims 1 to 7 are implemented.

Images