Batch task processing method and apparatus, electronic device, and computer-readable medium

Abstract

The application discloses a batch task processing method and device, electronic equipment and a computer readable medium, and relates to the technical field of computers, which comprises the following steps: receiving a batch task processing request, obtaining a corresponding batch task type identifier, and obtaining corresponding historical batch task data; generating a historical batch task analysis image; extracting first and second deep features in the historical batch task analysis image to generate a historical batch task portrait; predicting a preset index value corresponding to a preset index at a preset time point according to the historical batch task portrait; in response to the preset index value being greater than a preset threshold, obtaining a batch task identifier corresponding to the batch task processing request, generating early warning information based on the batch task identifier and the preset time point, and outputting the early warning information. The batch task corresponding to the preset index value that may exceed the threshold is early warned, the stable operation of the task execution system is ensured, part of the manual monitoring work can be reduced, and the work efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a batch task processing method, apparatus, electronic device, and computer-readable medium. Background Technology

[0002] The resource processing method for distributed batch task scheduling mainly determines the type of resources and their requirements for executing the current type of task based on the current task type and the relationship between the pre-configured task types and the required resources of each type and their demand.

[0003] In the process of developing this application, the inventors discovered at least the following problems in the prior art:

[0004] Insufficient source data can lead to significant deviations in the warning results for batch tasks. Summary of the Invention

[0005] In view of this, embodiments of this application provide a batch task processing method, apparatus, electronic device, and computer-readable medium, which can solve the problem that insufficient source data can lead to large deviations in the early warning results of batch tasks.

[0006] To achieve the above objectives, according to one aspect of the embodiments of this application, a batch task processing method is provided, comprising:

[0007] Receive batch task processing requests, obtain the corresponding batch task type identifier, and then obtain the corresponding historical batch task data based on the batch task type identifier.

[0008] Historical batch task data is processed based on preset indicators to generate historical batch task analysis images.

[0009] Extract the first and second depth features from the historical batch task analysis images, and then generate historical batch task profiles based on the first and second depth features.

[0010] Based on historical batch task profiles, predict the preset indicator values ​​corresponding to preset indicators at preset time points;

[0011] In response to a preset indicator value exceeding a preset threshold, the batch task identifier corresponding to the batch task processing request is obtained, and then the early warning program is invoked to generate and output early warning information based on the batch task identifier and a preset time point.

[0012] Optionally, historical batch task data is processed based on preset indicators to generate historical batch task analysis images, including:

[0013] Based on preset indicators, extract the corresponding historical preset indicator values ​​from historical batch task data;

[0014] Based on preset indicators and historical preset indicator values, generate historical batch task analysis images.

[0015] Optionally, first and second depth features are extracted from historical batch task analysis images, including:

[0016] High-level features are extracted from historical batch task analysis images as the first depth features;

[0017] Low-level features are extracted from historical batch task analysis images to serve as second-depth features.

[0018] Optionally, a historical batch task profile is generated based on the first deep feature and the second deep feature, including:

[0019] The first depth feature and the second depth feature are fused together to obtain the fused feature;

[0020] Historical batch task profiles are generated based on fusion features.

[0021] Optionally, predicting the value of a preset indicator corresponding to a preset indicator at a preset time point includes:

[0022] Historical batch task profiles and preset time points are input into the Long Short-Term Memory network to predict preset indicator values ​​corresponding to preset indicators.

[0023] Optionally, predicting the preset indicator value corresponding to the preset indicator includes:

[0024] Based on the historical batch task profile, determine the historical time point closest to the preset time point, and then determine the batch task context information corresponding to the historical time point;

[0025] Based on historical time points and batch task context information, predict the preset indicator value corresponding to the preset indicator at the preset time point.

[0026] Optionally, determine the batch task context information corresponding to the historical time point, including:

[0027] Based on historical task profiles, preset indicator information corresponding to time points adjacent to historical time points is determined, and then the preset indicator information is determined as the batch task context information.

[0028] In addition, this application also provides a batch task processing apparatus, including:

[0029] The receiving unit is configured to receive batch task processing requests, obtain the corresponding batch task type identifier, and then obtain the corresponding historical batch task data based on the batch task type identifier.

[0030] The image generation unit is configured to process historical batch task data based on preset indicators to generate historical batch task analysis images.

[0031] The image generation unit is configured to extract first depth features and second depth features from historical batch task analysis images, and then generate historical batch task images based on the first depth features and second depth features.

[0032] The prediction unit is configured to predict the value of a preset indicator at a preset time point based on the historical batch task profile.

[0033] The early warning unit is configured to respond to a preset indicator value exceeding a preset threshold by obtaining the batch task identifier corresponding to the batch task processing request, and then calling the early warning program to generate and output early warning information based on the batch task identifier and a preset time point.

[0034] Optionally, the image generation unit is further configured to:

[0035] Based on preset indicators, extract the corresponding historical preset indicator values ​​from historical batch task data;

[0036] Based on preset indicators and historical preset indicator values, generate historical batch task analysis images.

[0037] Optionally, the image generation unit is further configured to:

[0038] High-level features are extracted from historical batch task analysis images as the first depth features;

[0039] Low-level features are extracted from historical batch task analysis images to serve as second-depth features.

[0040] Optionally, the image generation unit is further configured to:

[0041] The first depth feature and the second depth feature are fused together to obtain the fused feature;

[0042] Historical batch task profiles are generated based on fusion features.

[0043] Optionally, the prediction unit is further configured to:

[0044] Historical batch task profiles and preset time points are input into the Long Short-Term Memory network to predict preset indicator values ​​corresponding to preset indicators.

[0045] Optionally, the prediction unit is further configured to:

[0046] Based on the historical batch task profile, determine the historical time point closest to the preset time point, and then determine the batch task context information corresponding to the historical time point;

[0047] Based on historical time points and batch task context information, predict the preset indicator value corresponding to the preset indicator at the preset time point.

[0048] Optionally, the prediction unit is further configured to:

[0049] Based on historical task profiles, preset indicator information corresponding to time points adjacent to historical time points is determined, and then the preset indicator information is determined as the batch task context information.

[0050] In addition, this application also provides a batch task processing electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by one or more processors, enable the one or more processors to implement the batch task processing method described above.

[0051] In addition, this application also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the batch task processing method described above.

[0052] To achieve the above objectives, according to another aspect of the embodiments of this application, a computer program product is provided.

[0053] A computer program product according to an embodiment of this application includes a computer program that, when executed by a processor, implements the batch task processing method provided in the embodiment of this application.

[0054] One embodiment of the above invention has the following advantages or beneficial effects: This application receives batch task processing requests, obtains the corresponding batch task type identifier, and then obtains the corresponding historical batch task data based on the batch task type identifier; processes the historical batch task data based on preset indicators to generate a historical batch task analysis image; extracts the first depth feature and the second depth feature from the historical batch task analysis image, and then generates a historical batch task profile based on the first depth feature and the second depth feature; predicts the preset indicator value corresponding to the preset indicator at a preset time point based on the historical batch task profile; in response to the preset indicator value being greater than a preset threshold, obtains the batch task identifier corresponding to the batch task processing request, and then calls the early warning program to generate and output early warning information based on the batch task identifier and the preset time point. This enables early warning for batch tasks corresponding to preset indicator values ​​that may exceed the threshold, ensuring the stable operation of the task execution system, reducing some manual monitoring work, and improving work efficiency.

[0055] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0056] The accompanying drawings are provided to better understand this application and do not constitute an undue limitation thereof. Wherein:

[0057] Figure 1 This is a schematic diagram of the main flow of a batch task processing method according to an embodiment of this application;

[0058] Figure 2 This is a schematic diagram of the main flow of a batch task processing method according to an embodiment of this application;

[0059] Figure 3 This is a schematic diagram illustrating an application scenario of a batch task processing method according to an embodiment of this application;

[0060] Figure 4 This is a schematic diagram of the main units of a batch task processing apparatus according to an embodiment of this application;

[0061] Figure 5 This is an exemplary system architecture diagram to which embodiments of this application can be applied;

[0062] Figure 6 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers in the embodiments of this application. Detailed Implementation

[0063] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with relevant national laws and regulations.

[0064] Figure 1 This is a schematic diagram of the main flow of a batch task processing method according to an embodiment of this application, as shown below. Figure 1 As shown, batch task processing methods include:

[0065] Step S101: Receive a batch task processing request, obtain the corresponding batch task type identifier, and then obtain the corresponding historical batch task data based on the batch task type identifier.

[0066] In this embodiment, the execution entity of the batch task processing method (e.g., a server) can receive batch task processing requests via wired or wireless connections. Specifically, the batch task processing request can be a request to issue an alert for batch tasks. After receiving the batch task processing request, the execution entity can obtain the corresponding historical batch task data based on the batch task type identifier carried in the request. Specifically, the batch task type identifier is used to characterize the type of batch task, such as the batch task's number or name. Through the historical batch task data corresponding to the batch task identifier, the conditions under which an alert occurred when the historical batch task was executed can be analyzed, such as the alert time, CPU usage, and memory usage, thereby preparing for alert work when the same type of batch task is executed again.

[0067] Step S102: Process the historical batch task data based on preset indicators to generate a historical batch task analysis image.

[0068] Preset indicators, such as CPU usage, memory usage, and the time of historical warnings during the execution of historical batch tasks, are not specifically limited in the content of the preset indicators in this embodiment. The executing entity can construct a planar coordinate system using the preset indicators as the x-axis and the preset indicator values ​​as the y-axis, and then generate a historical batch task analysis image located in this planar coordinate system based on the preset indicator values ​​corresponding to the preset indicators in historical batch tasks. It is understood that the historical batch task analysis image can be a line chart or a pie chart, and the type of historical batch task analysis image is not specifically limited in this embodiment.

[0069] Step S103: Extract the first depth feature and the second depth feature from the historical batch task analysis images, and then generate a historical batch task profile based on the first depth feature and the second depth feature.

[0070] Specifically, extracting first and second deep features from historical batch task analysis images includes: extracting high-level features from historical batch task analysis images as first deep features; and extracting low-level features from historical batch task analysis images as second deep features. The executing entity can invoke the deep neural network of the feature extraction model to extract the high-level features of the input historical batch task analysis images and use them as the first deep features, and invoke the shallow neural network of the feature extraction model to extract the low-level features of the input historical batch task analysis images and use them as the second deep features. This allows for hierarchical extraction of image features from historical batch task analysis images, resulting in more refined and diverse extracted image features, thus achieving better utilization of image features.

[0071] Specifically, generating historical batch task profiles based on first and second depth features includes fusing the first and second depth features to obtain fused features. Specifically, the executing entity can determine the dimensions of the first and second depth features, and then generate fused features based on the first depth features, their dimensions (e.g., p), and the dimensions of the second and third depth features (e.g., q) (the dimension of the fused features could be, for example, p+q). Historical batch task profiles are then generated based on the fused features. The first depth feature is a high-level feature, and the second depth feature is a low-level feature. By fusing the high-level and low-level features to obtain the fused features, and then generating historical batch task profiles based on the fused features, the generated historical batch task profiles can be more accurate. Feature fusion methods can comprehensively utilize multiple image features, achieving complementary advantages of multiple features, thereby generating more robust and accurate historical batch task profiles based on fused features.

[0072] Step S104: Based on the historical batch task profile, predict the preset indicator value corresponding to the preset indicator at the preset time point.

[0073] Specifically, predicting the preset indicator value corresponding to the preset indicator at a preset time point includes: inputting historical batch task profiles and preset time points into a long short-term memory network to predict the preset indicator value corresponding to the preset indicator.

[0074] Long Short-Term Memory (LSTM) networks, such as CNN-LSTM models, are used to predict the runtime of batch tasks. The model input consists of system metrics collected from the batch task runtime environment (e.g., historical runtime, CPU usage, memory usage, etc., where CPU usage in this embodiment refers to the CPU resources consumed when processing batch tasks, and memory usage refers to the memory resources consumed when processing batch tasks). CNNs (Convolutional Neural Networks) are used to extract features from the historical batch task profiles, and combined with LSTMs to support sequence prediction at a preset time point. This involves predicting the preset index value corresponding to the preset index at the preset time point. Based on the predicted preset index value corresponding to the preset index at the preset time point, it is determined whether similar batch tasks will experience anomalies at the preset time point, thus enabling timely warnings and reducing losses.

[0075] Specifically, the predicted preset indicator values ​​corresponding to the preset indicators include:

[0076] Based on historical batch task profiles, the closest historical time point to a preset time point is determined, and then the batch task context information corresponding to that historical time point is determined. The batch task context information may include, for example, whether an alert was issued before or after executing the historical batch task, the batch task execution time at the time of the alert, the CPU usage at the time of the alert, the memory usage at the time of the alert, and the alert duration. This embodiment does not specifically limit the batch task context information. Based on the historical time point and the batch task context information, a preset indicator value corresponding to a preset indicator at the preset time point is predicted. The executing entity can invoke a pre-trained Long Short-Term Memory (LSTM) network to predict and output the preset indicator value corresponding to the preset indicator at the preset time point based on the closest historical time point to the preset time point and the batch task context information.

[0077] As another implementation method, the batch task context information corresponding to the historical time point is determined, including: based on the historical task profile, determining the preset indicator information corresponding to the time point adjacent to the historical time point, and then determining the preset indicator information as the batch task context information.

[0078] Step S105: In response to a preset indicator value being greater than a preset threshold, obtain the batch task identifier corresponding to the batch task processing request, and then call the early warning program to generate and output early warning information based on the batch task identifier and a preset time point.

[0079] When the predicted preset indicator value at a preset time point exceeds a preset threshold, it indicates that a warning will occur at the preset time point when executing the batch task corresponding to the batch task request. The executing entity can then prepare to enter the warning procedure in advance to improve warning efficiency, prevent warning failures, and increase the success rate of warnings when executing batch tasks. Specifically, when the executing entity determines that the preset indicator value is greater than the preset threshold, it can obtain the batch task identifier corresponding to the batch task processing request and then call the warning procedure to generate warning information based on the batch task identifier and the preset time point. The warning information, for example, could be "A warning will be issued for batch task AAA at 10:00 AM and 11:00 AM on June 10, 2022," and this warning information will be output. This embodiment of the application does not specifically limit the content of the warning information.

[0080] This embodiment receives batch task processing requests, obtains the corresponding batch task type identifier, and then retrieves the corresponding historical batch task data based on the batch task type identifier. It processes the historical batch task data based on preset indicators to generate a historical batch task analysis image; extracts first and second depth features from the historical batch task analysis image, and then generates a historical batch task profile based on the first and second depth features; based on the historical batch task profile, it predicts the preset indicator value corresponding to the preset indicator at a preset time point; in response to the preset indicator value exceeding a preset threshold, it obtains the batch task identifier corresponding to the batch task processing request, and then calls an early warning program to generate and output early warning information based on the batch task identifier and the preset time point. This enables early warning for batch tasks corresponding to preset indicator values ​​that may exceed the threshold, ensuring the stable operation of the task execution system, reducing some manual monitoring work, and improving work efficiency.

[0081] Figure 2 This is a schematic flowchart of a batch task processing method according to an embodiment of this application, as shown below. Figure 2 As shown, batch task processing methods include:

[0082] Step S201: Receive a batch task processing request, obtain the corresponding batch task type identifier, and then obtain the corresponding historical batch task data based on the batch task type identifier.

[0083] Step S202: Based on preset indicators, extract the corresponding historical preset indicator values ​​from historical batch task data.

[0084] The executing entity extracts historical preset indicator values ​​corresponding to preset indicators from historical batch task data.

[0085] Step S203: Generate historical batch task analysis images based on preset indicators and historical preset indicator values.

[0086] The executing entity can generate a scatter plot on a plane, i.e., a historical batch task analysis image, with preset indicators as the x-axis and historical preset indicator values ​​as the y-axis. The historical preset indicator values ​​corresponding to the occurrence of warnings in the past are marked on the historical batch task image, so that the executing entity can quickly determine the preset indicators and preset indicator values ​​when warnings occurred in the past batch tasks, and prepare for subsequent predictions.

[0087] Step S204: Extract the first depth feature and the second depth feature from the historical batch task analysis images, and then generate a historical batch task profile based on the first depth feature and the second depth feature.

[0088] Step S205: Based on the historical batch task profile, predict the preset indicator value corresponding to the preset indicator at the preset time point.

[0089] Step S206: In response to a preset indicator value being greater than a preset threshold, obtain the batch task identifier corresponding to the batch task processing request, and then call the early warning program to generate and output early warning information based on the batch task identifier and a preset time point.

[0090] The embodiments of this application can provide early warnings for batch tasks corresponding to preset index values ​​that may exceed thresholds, ensuring the stable operation of the task execution system, reducing some manual monitoring work, and improving work efficiency.

[0091] Figure 3 This is a schematic diagram illustrating an application scenario of a batch task processing method according to an embodiment of this application. The batch task processing method of this application embodiment can be applied to scenarios where batch tasks are given early warnings.

[0092] First, acquire historical batch task data, including start time, end time, CPU usage, memory usage, and scalability-related metrics. Store this historical batch task data in a database. Subsequently, this historical batch task data is processed in the following ways: 1. Time-wise, calculate the daily runtime of the historical batch tasks based on the start and end times, and record it in the database; 2. CPU-wise, summarize the CPU usage data based on the historical batch task runtime periods, calculate the average, maximum, and minimum values, and record the periods when CPU usage exceeds 90%; 3. Memory-wise, summarize the memory usage data based on the historical batch task runtime periods, calculate the average, maximum, and minimum values, and record the periods when memory usage exceeds 90%. The above is merely an example and is not intended to limit the implementation of this application. If acquiring historical batch task data fails, exit the current program.

[0093] Secondly, the data is analyzed: based on the weekly and monthly running time, CPU, and memory usage of the historical batch tasks, the average and maximum values ​​are recorded to predict the running time, CPU, and memory usage of the same type of batch tasks for the next month or week.

[0094] Finally, configure the relevant thresholds. Configure the thresholds according to the batch task name. The threshold content includes: batch run time (alarm if it is greater than 1 hour), CPU utilization (alarm if the average value is higher than 90%), and memory utilization (alarm if the average value is higher than 90%).

[0095] The predicted data is compared with configured thresholds. Specifically, this can involve comparing the predicted memory usage, CPU usage, and batch task execution time with their corresponding thresholds. If the predicted threshold is exceeded, the data is returned to the database and recorded in the alert display table. It's understood that the thresholds for memory usage, CPU usage, and batch task execution time can be different. If retrieving the configured threshold fails, the current program exits.

[0096] To achieve the above objectives, the embodiments of this application adopt the following technical solution: Data analysis based on Python and MariaDB requires the following preparations: 1) Install the Python editor PyCharm, Python version 3.8.8, and install the pymysql, pandas, and matplotlib modules. 2) Install MariaDB, version 5.5.65, and install the driver mariadb-connector-odbc-3.0.2.

[0097] This application embodiment can predict the runtime of batch tasks and related information on system utilization in advance, and provide early warnings for information that may exceed thresholds, ensuring the stable operation of the system. It can reduce some manual monitoring work and improve work efficiency. After importing historical batch task data into a local database using Python, it can perform automated analysis based on the database content and generate predictive data. This prediction method analyzes and predicts based on monthly historical batch task data, weekly historical batch task data, and historical batch task data on fixed dates each month, thereby improving work efficiency and the accuracy of batch task warnings. The systems used in this application embodiment all use open-source systems and modules, resulting in low development costs, convenient development, and minimal maintenance requirements. The predictive metrics can be expanded. The system versions used are all current stable versions and have the advantages of simple functional development, minimal code, and simplified repetitive and complex tasks.

[0098] Figure 4 This is a schematic diagram of the main units of a batch task processing apparatus according to an embodiment of this application. Figure 4 As shown, the batch task processing device 400 includes a receiving unit 401, an image analysis and generation unit 402, an image generation unit 403, a prediction unit 404, and an early warning unit 405.

[0099] The receiving unit 401 is configured to receive batch task processing requests, obtain the corresponding batch task type identifier, and then obtain the corresponding historical batch task data based on the batch task type identifier.

[0100] The image generation unit 402 is configured to process historical batch task data based on preset indicators to generate historical batch task analysis images.

[0101] The image generation unit 403 is configured to extract first depth features and second depth features from historical batch task analysis images, and then generate historical batch task images based on the first depth features and second depth features.

[0102] Prediction unit 404 is configured to predict the value of a preset indicator corresponding to a preset indicator at a preset time point based on historical batch task profiles.

[0103] The early warning unit 405 is configured to respond to a preset indicator value being greater than a preset threshold by obtaining the batch task identifier corresponding to the batch task processing request, and then calling the early warning program to generate and output early warning information based on the batch task identifier and a preset time point.

[0104] In some embodiments, the analysis image generation unit 402 is further configured to: extract corresponding historical preset indicator values ​​from historical batch task data based on preset indicators; and generate historical batch task analysis images based on preset indicators and historical preset indicator values.

[0105] In some embodiments, the image generation unit 403 is further configured to: extract high-level features from historical batch task analysis images as first depth features; and extract low-level features from historical batch task analysis images as second depth features.

[0106] In some embodiments, the portrait generation unit 403 is further configured to: fuse the first depth feature and the second depth feature to obtain a fused feature; and generate historical batch task portraits based on the fused feature.

[0107] In some embodiments, the prediction unit 404 is further configured to input historical batch task profiles and preset time points into a long short-term memory network to predict preset indicator values ​​corresponding to preset indicators.

[0108] In some embodiments, the prediction unit 404 is further configured to: determine the historical time point closest to the preset time point based on the historical batch task profile, and then determine the batch task context information corresponding to the historical time point; and predict the preset indicator value corresponding to the preset indicator at the preset time point based on the historical time point and the batch task context information.

[0109] In some embodiments, the prediction unit 404 is further configured to: determine preset indicator information corresponding to time points adjacent to historical time points based on historical task profiles, and then determine the preset indicator information as batch task context information.

[0110] It should be noted that the batch task processing method and batch task processing device in this application are related in terms of specific implementation content, so repeated content will not be described again.

[0111] Figure 5 An exemplary system architecture 500 is shown that can be applied to the batch task processing method or batch task processing apparatus of the embodiments of this application.

[0112] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, and 503, a network 504, and a server 505. Network 504 serves as the medium for providing communication links between terminal devices 501, 502, and 503 and server 505. Network 504 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0113] Users can use terminal devices 501, 502, and 503 to interact with server 505 via network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, and 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0114] Terminal devices 501, 502, and 503 can be various electronic devices with batch task processing screens and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0115] Server 505 can be a server providing various services, such as a backend management server supporting batch task processing requests submitted by users using terminal devices 501, 502, and 503 (this is just an example). The backend management server can receive batch task processing requests, obtain the corresponding batch task type identifier, and then obtain the corresponding historical batch task data based on the batch task type identifier; process the historical batch task data based on preset indicators to generate a historical batch task analysis image; extract the first and second depth features from the historical batch task analysis image, and then generate a historical batch task profile based on the first and second depth features; predict the preset indicator value corresponding to the preset indicator at a preset time point based on the historical batch task profile; and, in response to a preset indicator value exceeding a preset threshold, obtain the batch task identifier corresponding to the batch task processing request, and then call the early warning program to generate and output early warning information based on the batch task identifier and the preset time point. This enables early warning for batch tasks corresponding to preset indicator values ​​that may exceed the threshold, ensuring the stable operation of the task execution system, reducing some manual monitoring work, and improving work efficiency.

[0116] It should be noted that the batch task processing method provided in this application embodiment is generally executed by server 505, and correspondingly, the batch task processing device is generally set in server 505.

[0117] It should be understood that Figure 5 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0118] The following is for reference. Figure 6 It shows a schematic diagram of the structure of a computer system 600 suitable for implementing a terminal device according to the embodiments of this application. Figure 6 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0119] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the computer system 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0120] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0121] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined above in the system of this application.

[0122] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0123] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0124] The units described in the embodiments of this application can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor can be described as including a receiving unit, an image analysis and generation unit, an image generation unit, a prediction unit, and an early warning unit. The names of these units do not necessarily limit the specific unit itself.

[0125] In another aspect, this application also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs that, when executed by the device, cause the device to receive a batch task processing request, obtain a corresponding batch task type identifier, and then obtain corresponding historical batch task data based on the batch task type identifier; process the historical batch task data based on preset indicators to generate a historical batch task analysis image; extract a first depth feature and a second depth feature from the historical batch task analysis image, and then generate a historical batch task profile based on the first depth feature and the second depth feature; predict a preset indicator value corresponding to a preset indicator at a preset time point based on the historical batch task profile; and, in response to a preset indicator value being greater than a preset threshold, obtain the batch task identifier corresponding to the batch task processing request, and then call an early warning program to generate and output early warning information based on the batch task identifier and the preset time point.

[0126] The computer program product of this application includes a computer program that, when executed by a processor, implements the batch task processing method in the embodiments of this application.

[0127] According to the technical solution of the embodiments of this application, it is possible to provide early warning for batch tasks corresponding to preset index values ​​that may exceed the threshold, ensuring the stable operation of the task execution system, reducing some manual monitoring work, and improving work efficiency.

[0128] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A batch task processing method, characterized in that, include: Receive a batch task processing request, obtain the corresponding batch task type identifier, and then obtain the corresponding historical batch task data based on the batch task type identifier. The historical batch task data is processed based on preset indicators to generate a historical batch task analysis image. Extract the first depth feature and the second depth feature from the historical batch task analysis image, and then generate a historical batch task profile based on the first depth feature and the second depth feature; Based on the historical batch task profile, predict the preset indicator value corresponding to the preset indicator at a preset time point; In response to the preset indicator value being greater than a preset threshold, the batch task identifier corresponding to the batch task processing request is obtained, and then the early warning program is invoked to generate and output early warning information based on the batch task identifier and the preset time point. The step of extracting the first and second depth features from the historical batch task analysis images includes: extracting high-level features from the historical batch task analysis images as the first depth features; and extracting low-level features from the historical batch task analysis images as the second depth features. The step of generating a historical batch task profile based on the first depth feature and the second depth feature includes: fusing the first depth feature and the second depth feature to obtain a fused feature; and generating a historical batch task profile based on the fused feature. The prediction of the preset indicator value corresponding to the preset indicator at a preset time point includes: inputting the historical batch task profile and the preset time point into a long short-term memory network to predict the preset indicator value corresponding to the preset indicator.

2. The method according to claim 1, characterized in that, The process of processing the historical batch task data based on preset indicators to generate a historical batch task analysis image includes: Based on preset indicators, extract the corresponding historical preset indicator values ​​from the historical batch task data; Based on the preset indicators and the historical preset indicator values, a historical batch task analysis image is generated.

3. The method according to claim 1, characterized in that, The preset index value corresponding to the predicted preset index includes: Based on the historical batch task profile, determine the historical time point closest to the preset time point, and then determine the batch task context information corresponding to the historical time point; Based on the historical time points and the batch task context information, predict the preset indicator value corresponding to the preset indicator at the preset time point.

4. The method according to claim 3, characterized in that, The determination of the batch task context information corresponding to the historical time point includes: Based on the historical batch task profile, preset indicator information corresponding to time points adjacent to the historical time points is determined, and then the preset indicator information is determined as batch task context information.

5. A batch task processing device, characterized in that, include: The receiving unit is configured to receive batch task processing requests, obtain the corresponding batch task type identifier, and then obtain the corresponding historical batch task data based on the batch task type identifier. The image generation unit is configured to process the historical batch task data based on preset indicators to generate historical batch task analysis images. The image generation unit is configured to extract a first depth feature and a second depth feature from the historical batch task analysis image, and then generate a historical batch task image based on the first depth feature and the second depth feature. The prediction unit is configured to predict the value of a preset indicator corresponding to the preset indicator at a preset time point based on the historical batch task profile. The early warning unit is configured to, in response to the preset indicator value being greater than a preset threshold, obtain the batch task identifier corresponding to the batch task processing request, and then call the early warning program to generate and output early warning information based on the batch task identifier and the preset time point. The image generation unit is further configured to: extract high-level features from the historical batch task analysis images as first depth features; Extract low-level features from the historical batch task analysis images as second-depth features; The portrait generation unit is further configured to: fuse the first depth feature and the second depth feature to obtain a fused feature; and generate historical batch task portraits based on the fused feature. The prediction unit is further configured to input the historical batch task profile and the preset time point into a long short-term memory network to predict the preset indicator value corresponding to the preset indicator.

6. The apparatus according to claim 5, characterized in that, The image analysis generation unit is further configured to: Based on preset indicators, extract the corresponding historical preset indicator values ​​from the historical batch task data; Based on the preset indicators and the historical preset indicator values, a historical batch task analysis image is generated.

7. The apparatus according to claim 5, characterized in that, The prediction unit is further configured to: Based on the historical batch task profile, determine the historical time point closest to the preset time point, and then determine the batch task context information corresponding to the historical time point; Based on the historical time points and the batch task context information, predict the preset indicator value corresponding to the preset indicator at the preset time point.

8. A batch task processing electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-4.

9. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-4.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-4.

Images