A method, apparatus, device, and storage medium for root cause treatment of task backlog.

Abstract

This invention relates to a method, apparatus, device, and storage medium for addressing the root cause of task backlog. The method includes: when the number of current tasks exceeds a set threshold, determining multiple information dimensions corresponding to all the tasks, and determining multiple information categories corresponding to the multiple information dimensions; determining a target information dimension from the multiple information dimensions based on the surprise factor of each information dimension; determining a target information category from at least one information category corresponding to the target information dimension based on the interpretability of each information category; and determining the task corresponding to the target information category as the root cause. This allows for the rapid identification of information dimensions and subdivided information categories associated with the task backlog problem, thereby saving significant time and improving operational efficiency.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of task processing, and in particular to a method, apparatus, device and storage medium for root cause processing of task backlog. Background Technology

[0002] In the processing of video tasks, the number of tasks can reach millions per day, and task backlogs often occur. When tasks are backlogged, it is usually necessary to find the root cause before resolving it promptly.

[0003] However, tasks involve numerous information dimensions, exceeding 100, and the subcategories within these dimensions are also quite complex, with over 30 subcategories within the clarity dimension alone. Therefore, current technologies that rely on manual screening to identify the root causes of task backlogs are inefficient and inaccurate. Summary of the Invention

[0004] In view of this, in order to solve the above-mentioned technical problems or some of the technical problems, the present invention provides a method, apparatus, device and storage medium for root cause processing of task backlog.

[0005] In a first aspect, embodiments of the present invention provide a root cause treatment method for task backlog, comprising:

[0006] When the number of current tasks exceeds a set threshold, determine multiple information dimensions corresponding to all the tasks, and determine multiple information types corresponding to the multiple information dimensions. Each task corresponds to at least one information dimension, and each information dimension corresponds to at least one information type.

[0007] The target information dimension is determined from the plurality of information dimensions based on the surprise of each of the information dimensions.

[0008] Based on the interpretability of each of the information types, the target information type is determined from at least one information type corresponding to the target information dimension;

[0009] The task corresponding to the type of target information is identified as the root cause.

[0010] In one possible implementation, determining the target information dimension from the plurality of information dimensions based on the surprise of each of the information dimensions includes:

[0011] For any of the aforementioned information dimensions, determine the sub-surprise degree for each of the aforementioned information types to obtain multiple sub-surprise degrees corresponding to any of the aforementioned information dimensions;

[0012] The sum of the multiple sub-surprise values ​​is determined as the surprise value corresponding to any one of the information dimensions;

[0013] The information dimension whose surprise level is greater than the first threshold is determined as the target information dimension.

[0014] In one possible implementation, determining the sub-surprise of each of the information categories for any of the information dimensions includes:

[0015] For any of the aforementioned information dimensions, determine the number of CPU cores and the time required for each of the aforementioned information types;

[0016] The core hour for any of the aforementioned information types is determined based on the number of cores and the occupancy time.

[0017] Determine the total number of cores in the central processing unit;

[0018] For any of the aforementioned information types, the daily percentage of core hours is determined based on the core hours and the total number of cores;

[0019] Determine the initial surprise level for any of the aforementioned information types;

[0020] The initial surprise level is weighted and calculated based on the daily percentage of the nuclear hour to obtain the sub-surprise level.

[0021] In one possible implementation, determining the target information category from multiple information categories corresponding to the target information dimension based on the interpretability of each information category includes:

[0022] Determine the interpretability of each information category corresponding to the target information dimension;

[0023] The information types whose interpretability is greater than the second threshold are taken as the target information types.

[0024] In one possible implementation, determining the interpretability of each information category corresponding to the target information dimension includes:

[0025] Determine the initial interpretability of any of the information types corresponding to the target information dimension;

[0026] The initial explanatory power is calculated by weighting the initial explanatory power based on the daily percentage of nuclear hours, and the explanatory power is obtained.

[0027] In one possible implementation, after determining that the task corresponding to the target information type is the root cause, the method further includes:

[0028] Identify the task initiator corresponding to the root cause;

[0029] Reduce the number of tasks initiated by the task initiator, or reduce the number of tasks that meet preset conditions.

[0030] In one possible implementation, before determining the multiple information dimensions corresponding to the task, the method further includes:

[0031] Get the current number of tasks at preset time intervals;

[0032] An alarm event is triggered when the number of tasks exceeds the set threshold.

[0033] In a second aspect, embodiments of the present invention provide a root cause processing apparatus for task backlog, comprising:

[0034] The determination module is used to determine multiple information dimensions corresponding to all the tasks when the number of current tasks is greater than a set threshold, and to determine multiple information types corresponding to the multiple information dimensions, wherein each task corresponds to at least one information dimension and each information dimension corresponds to at least one information type.

[0035] The determining module is further configured to determine a target information dimension from multiple information dimensions based on the surprise of each information dimension.

[0036] The determining module is further configured to determine the target information type from at least one information type corresponding to the target information dimension based on the interpretability of each information type.

[0037] The determining module is further configured to determine that the task corresponding to the target information type is the root cause.

[0038] Thirdly, embodiments of the present invention provide an apparatus comprising: a processor and a memory, the processor being configured to execute a root cause processing program for a task backlog stored in the memory, to implement the root cause processing method for a task backlog as described in any one of the first aspects above.

[0039] Fourthly, embodiments of the present invention provide a storage medium storing one or more programs, which can be executed by one or more processors to implement the root cause processing method for task backlog as described in any of the first aspects.

[0040] The root cause processing scheme for task backlog provided in this embodiment of the invention determines multiple information dimensions corresponding to all tasks and multiple information categories corresponding to the multiple information dimensions when the number of current tasks exceeds a set threshold; determines a target information dimension from the multiple information dimensions based on the surprise factor of each information dimension; determines a target information category from at least one information category corresponding to the target information dimension based on the interpretability of each information category; and determines the task corresponding to the target information category as the root cause. This allows for the rapid identification of information dimensions and subdivided information categories associated with the task backlog problem, thereby saving significant time and improving operational efficiency. Attached Figure Description

[0041] Figure 1 A flowchart illustrating a root cause treatment method for task backlog provided in an embodiment of the present invention;

[0042] Figure 2 A flowchart illustrating another method for addressing the root causes of task backlog provided in an embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram of the structure of a root cause treatment device for task backlog provided in an embodiment of the present invention;

[0044] Figure 4 This is a schematic diagram of the structure of a device provided in an embodiment of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] To facilitate understanding of the embodiments of the present invention, further explanations and descriptions will be provided below with reference to the accompanying drawings and specific embodiments. These embodiments do not constitute a limitation on the embodiments of the present invention.

[0047] Figure 1 This is a flowchart illustrating a root cause treatment method for task backlog provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the method specifically includes:

[0048] S11. When the number of current tasks exceeds a set threshold, determine multiple information dimensions corresponding to all the tasks, and determine multiple information types corresponding to the multiple information dimensions.

[0049] The root cause processing method for task backlog provided in this embodiment of the invention is applied to a server. The server has a task processing platform that can acquire and process video tasks. Specifically, when a task backlog occurs, the root cause of the task backlog is quickly determined based on the information dimension and information type of the task.

[0050] In this embodiment, when a video task is initiated, the task is recorded, and information related to information dimensions such as the type, clarity, resolution, and encoding method of the video task is obtained. A threshold is preset to determine whether tasks are backlogged. When the number of tasks within the current preset time period is detected to be greater than the set threshold, it is determined that there is a backlog of tasks, and the root cause of the backlog needs to be further determined.

[0051] Information dimensions and information types can be pre-defined by developers. Information dimensions may include, but are not limited to, resolution dimensions and encoding method dimensions. When a video task is acquired, the information dimensions involved in the task are determined and recorded, with each task corresponding to at least one information dimension. When tasks are piling up, the multiple information dimensions involved in all current tasks are determined, and the subdivided information types under each information dimension are identified, with each information dimension corresponding to at least one information type. For example, information types under the resolution dimension include 360P, 720P, etc., and information types under the encoding method dimension include H.264, H.265, etc.

[0052] S12. Determine the target information dimension from the plurality of information dimensions based on the surprise of each of the information dimensions.

[0053] In this embodiment, the Adtributor algorithm is implemented in Python based on AIOPs intelligent operation and maintenance. The Adtributor algorithm outputs the surprise value S for each information dimension. The surprise value (S) is defined as follows: a dimension with a large variation in its distribution is more likely to be the root cause than a dimension that does not show such variation. The difference between the true value and the predicted value of all elements under all information dimensions is calculated to obtain the surprise value of each information dimension.

[0054] From the multiple information dimensions, the information dimension whose surprise level is within a set threshold range is determined as the target information dimension, or the information dimension with the highest surprise level is determined as the target information dimension. The target information dimension is the root cause that may cause task backlog, and it is necessary to further determine the types of information that cause the root cause under the target information dimension.

[0055] S13. Based on the interpretability of each of the information types, determine the target information type from at least one information type corresponding to the target information dimension.

[0056] In this embodiment, the Explainability Power (Ep) value for each information category is calculated using the Adtributor algorithm. Explainability Power (Ep) is the percentage of indicator fluctuations explained by the information categories subdivided under a certain information dimension. For information dimensions with high S values, information categories whose sum of Ep values ​​exceeds a set threshold (e.g., 0.01) can be considered as the root cause of anomalies leading to task backlogs.

[0057] For each dimension of target information, the interpretability of each information type is calculated, and information types with interpretability greater than a set threshold are identified as target information types.

[0058] S14. Determine the task corresponding to the target information type as the root cause.

[0059] In this embodiment, the target information type represents the type of information that may be a backlog of root causes. Tasks involving the target information type are identified as root causes from all tasks. For example, if the target information dimension is resolution and the target information type is 360P, then tasks with a resolution of 360P are identified as root causes.

[0060] Furthermore, after identifying the root cause task, the source of the task can be traced to find the relevant task initiator, and the number of tasks can be adjusted. The backlog can be resolved by eliminating low-priority tasks, and the initiation strategy for future tasks can be optimized to reduce the occurrence of backlog.

[0061] The root cause processing method for task backlog provided in this invention determines multiple information dimensions corresponding to all tasks and multiple information categories corresponding to the multiple information dimensions when the number of current tasks exceeds a set threshold; determines a target information dimension from the multiple information dimensions based on the surprise factor of each information dimension; determines a target information category from at least one information category corresponding to the target information dimension based on the interpretability of each information category; and determines the task corresponding to the target information category as the root cause. This allows for the rapid identification of information dimensions and subdivided information categories associated with the task backlog problem, thereby saving significant time and improving operational efficiency.

[0062] Figure 2 A flowchart illustrating another root cause treatment method for task backlog provided in an embodiment of the present invention is shown below. Figure 2 As shown, the method specifically includes:

[0063] S21. At preset time intervals, obtain the current number of tasks; when the number of tasks exceeds the set threshold, trigger an alarm event.

[0064] In this embodiment, the Venus agent real-time data acquisition and processing platform, which is pre-built on the server, collects task information to the real-time data acquisition and processing platform while initiating a task, thereby integrating and storing the detailed information of each task. The detailed information may include, but is not limited to, the information dimensions involved in the task, the information types, the time when the task was generated, the task type, etc.

[0065] At preset time intervals, the system retrieves the number of tasks initiated within the current time period and continuously sends this data to the alarm system to trigger a task backlog alarm. A task backlog threshold is set; an alarm is triggered when the number of tasks exceeds this threshold. For example, if the number of tasks in the same time period is historically 1000 per minute, a backlog may occur when the number of tasks reaches 3000 per minute. Therefore, a threshold of 3000 is set. When the number of tasks reaches this threshold, an alarm is triggered. The alarm can be triggered by generating an alarm message, which can then initiate root cause analysis of the task backlog.

[0066] S22. When the number of current tasks exceeds a set threshold, determine multiple information dimensions corresponding to all the tasks, and determine multiple information types corresponding to the multiple information dimensions.

[0067] In this embodiment, similar to step S11, the details can be found in step S11, but for the sake of brevity, they will not be repeated here.

[0068] S23. For any of the information dimensions, determine the sub-surprise value of each of the information types to obtain multiple sub-surprise values ​​corresponding to any of the information dimensions; determine the sum of the multiple sub-surprise values ​​as the surprise value corresponding to any of the information dimensions; determine the information dimension whose surprise value is greater than the first threshold as the target information dimension.

[0069] In this embodiment, the information type corresponding to each information dimension is determined, and the sub-surprise degree of each information type is determined according to the Adtributor algorithm.

[0070] Sub-surprise is determined as follows: For any information dimension, determine the number of CPU cores and the time occupied by each information type; determine the core hours for any information type based on the number of cores and the time occupied; determine the total number of CPU cores; for any information type, determine the daily percentage of core hours based on the core hours and the total number of cores; determine the initial surprise of any information type; and calculate the sub-surprise by weighting the initial surprise based on the daily percentage of core hours.

[0071] Specifically, in task backlog scenarios, there are many information dimensions, and the importance of each dimension varies greatly. Some information dimensions, while significantly impacting the number of tasks, actually only consume a small number of CPU cores per task and do not cause task backlog. Therefore, based on the Adtributor algorithm, "core hours" are introduced. This involves obtaining the number of CPU cores and the time consumed by tasks of each information type. The core hours for an information type are calculated as: Core hours = Number of CPU cores * Time consumed. The total number of CPU cores per day = Total number of CPU cores * 24 hours. Dividing the core hours by the total number of cores yields the daily percentage of core hours.

[0072] The higher the daily percentage of core hours, the greater the importance of that information type. The surprise value directly output by the Adtributor algorithm is the initial surprise value. Sub-surprise values ​​are obtained by weighting the daily percentage of core hours on top of the initial surprise value.

[0073] Furthermore, the sum of the sub-surprise values ​​of all information types corresponding to each information dimension is determined to obtain the surprise value, thereby determining the surprise value of each information dimension. Information dimensions with a surprise value greater than a first threshold are identified as target information dimensions, or the information dimension with the highest surprise value is identified as the target information dimension.

[0074] S24. Determine the interpretability of each information type corresponding to the target information dimension; and take the information type with interpretability greater than the second threshold as the target information type.

[0075] In this embodiment, the initial interpretability of any information type corresponding to the target information dimension is determined; the initial interpretability is weighted and calculated according to the daily proportion of core hours to obtain the interpretability.

[0076] Specifically, all information categories corresponding to the target information dimension are identified. The interpretability of each information category is calculated using the Adtributor algorithm as the initial interpretability. Based on the initial interpretability, the daily percentage of kernel hours is weighted to obtain the final interpretability. From all information categories, information categories with interpretability greater than a second threshold are identified as target information categories, and the tasks corresponding to these target information categories are identified as root causes.

[0077] S25. Determine the task corresponding to the target information type as the root cause.

[0078] In this embodiment, similar to step S14, the details can be found in step S14, but for the sake of brevity, they will not be repeated here.

[0079] S26. Determine the task initiator corresponding to the root cause; reduce the number of tasks initiated by the task initiator, or reduce the number of tasks that meet preset conditions.

[0080] In this embodiment, after determining the root cause, the initiator of the root cause task is found from the detailed information collected from the real-time data acquisition and processing platform. A message to reduce the number of tasks is sent to the initiator, or the initiator's tasks are stopped, or preset conditions are set to reduce the number of tasks that meet the preset conditions.

[0081] In one possible implementation, the surprise factor of each information type can be directly determined, and the root cause task can be identified based on the surprise factor. For example, the surprise factor for the clarity dimension -720p is 0.09, and its daily core hour share is 0.05, having a relatively small impact on daily task resources. The surprise factor for the encoding method dimension -h264 is 0.05, but its daily core hour share reaches 0.2. After weighting, the weighted surprise factor of the clarity dimension -720p (0.0045) is less than the surprise factor of the encoding method dimension -h264 (0.01), so the root cause can be initially considered to be the task in the encoding method dimension -h264. After identifying the root cause, the task source can be traced to find the relevant task initiator, and the number of tasks can be adjusted. The backlog can be resolved by killing low-priority tasks, and the initiation strategy for future tasks can be optimized to reduce the occurrence of backlogs.

[0082] In one possible implementation, the theoretical number of tasks can be predicted using methods such as ARMA timing prediction, replacing the current four-week average as a reference data. This method is more universally applicable. For example, if a backlog of 100 video production tasks is expected within a given time period, with 30 tasks at 720p and 70 at 360p in terms of resolution, and 50 at h264 and h265 in terms of encoding method, the average values ​​for each dimension over the past four weeks can be used as reference data. For instance, if the average number of tasks sent during this period is 10, and the average number of tasks for each dimension is 5, these values ​​can be compared with the abnormal data to calculate the Ep and S values ​​for each information type, identifying potential root causes of the anomaly. The calculation results are shown in the table below. Setting the Ep threshold to 0.5 reveals a high S value for resolution, and the Ep value for 720p exceeds the threshold. Therefore, tasks with a resolution of -720p can be considered the root cause of the task backlog.

[0083] Information Dimensions Types of information Ep value S value Clarity 360p 0.278 0.013 Clarity 720p 0.722 0.008 Encoding method H264 0.500 0 Encoding method H265 0.500 0

[0084] The root cause handling method for task backlog provided in this invention involves: obtaining the current number of tasks at preset time intervals; triggering an alarm event when the number of tasks exceeds a set threshold; determining multiple information dimensions corresponding to all tasks, and determining multiple information categories corresponding to these information dimensions; determining the sub-surprise value of each information category for any information dimension, resulting in multiple sub-surprise values ​​for that information dimension; determining the sum of these sub-surprise values ​​as the surprise value for any information dimension; determining the information dimension with a surprise value greater than a first threshold as the target information dimension; determining the interpretability of each information category corresponding to the target information dimension; selecting information categories with interpretability greater than a second threshold as the target information category; determining the task corresponding to the target information category as the root cause; determining the task initiator corresponding to the root cause; reducing the number of tasks initiated by the task initiator, or reducing the number of tasks that meet preset conditions. This allows for replacing manual operations and maintenance with AIOps, performing root cause analysis based on the Adtributor. It reduces troubleshooting time from several hours to 40 seconds, weights the "core hour" factor, flexibly adapts to task backlog scenarios, eliminates the need for manual root cause searching, and improves operational efficiency.

[0085] Figure 3 A schematic diagram of a root cause treatment device for task backlog provided in an embodiment of the present invention includes:

[0086] The determining module 31 is used to determine multiple information dimensions corresponding to all the tasks when the number of current tasks is greater than a set threshold, and to determine multiple information types corresponding to the multiple information dimensions, wherein each task corresponds to at least one information dimension and each information dimension corresponds to at least one information type.

[0087] The determining module 31 is further configured to determine a target information dimension from multiple information dimensions based on the surprise of each information dimension;

[0088] The determining module 31 is further configured to determine the target information type from at least one information type corresponding to the target information dimension based on the interpretability of each information type.

[0089] The determining module 31 is further configured to determine that the task corresponding to the target information type is the root cause.

[0090] In one possible implementation, the determining module 31 is specifically used to determine the sub-surprise degree of each of the information types for any one of the information dimensions, thereby obtaining multiple sub-surprise degrees corresponding to any one of the information dimensions.

[0091] The sum of the multiple sub-surprise values ​​is determined as the surprise value corresponding to any one of the information dimensions;

[0092] The information dimension whose surprise level is greater than the first threshold is determined as the target information dimension.

[0093] In one possible implementation, the determining module 31 is specifically used to determine, for any one of the information dimensions, the number of CPU cores and the time occupied by each of the information types.

[0094] The core hour for any of the aforementioned information types is determined based on the number of cores and the occupancy time.

[0095] Determine the total number of cores in the central processing unit;

[0096] For any of the aforementioned information types, the daily percentage of core hours is determined based on the core hours and the total number of cores;

[0097] Determine the initial surprise level for any of the aforementioned information types;

[0098] The calculation module 32 is used to perform a weighted calculation on the initial surprise value based on the daily percentage of the core hour to obtain the sub-surprise value.

[0099] In one possible implementation, the determining module 31 is specifically used to determine the interpretability of each of the information categories corresponding to the target information dimension;

[0100] The information types whose interpretability is greater than the second threshold are taken as the target information types.

[0101] In one possible implementation, the determining module 31 is specifically used to determine the initial interpretability of any of the information types corresponding to the target information dimension;

[0102] The calculation module is specifically used to perform a weighted calculation of the initial explanatory power based on the daily proportion of nuclear hours, thereby obtaining the explanatory power.

[0103] In one possible implementation, the determining module 31 is further configured to determine the task initiator corresponding to the root cause;

[0104] Processing module 33 is used to reduce the number of tasks initiated by the task initiator, or to reduce the number of tasks that meet preset conditions.

[0105] In one possible implementation, the acquisition module 34 is used to acquire the current number of tasks at preset time intervals;

[0106] The alarm module 35 is used to trigger an alarm event when the number of tasks exceeds the set threshold.

[0107] The root cause processing device for task backlog provided in this embodiment can be as follows: Figure 3The apparatus shown can perform, for example Figure 1-2 All steps of the root cause treatment method for task backlog, thereby achieving Figure 1-2 For details on the technical effectiveness of the root cause treatment method for task backlog, please refer to [link / reference needed]. Figure 1-2 The relevant descriptions are presented concisely and will not be elaborated upon here.

[0108] Figure 4 This is a schematic diagram of the structure of a device provided in an embodiment of the present invention. Figure 4 The illustrated device 400 includes at least one processor 401, a memory 402, at least one network interface 404, and other user interfaces 403. The various components in device 400 are coupled together via a bus system 405. It is understood that the bus system 405 is used to implement communication between these components. In addition to a data bus, the bus system 405 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 4 The general designated all buses as Bus System 405.

[0109] The user interface 403 may include a display, keyboard, or clicking device (e.g., mouse, trackball, touchpad, or touchscreen).

[0110] It is understood that the memory 402 in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 402 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0111] In some implementations, memory 402 stores elements, executable units or data structures, or subsets thereof, or extended sets thereof: operating system 4021 and application program 4022.

[0112] The operating system 4021 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 4022 includes various applications, such as a media player and a browser, used to implement various application functions. The program implementing the method of this embodiment can be included in the application program 4022.

[0113] In this embodiment of the invention, by calling the program or instructions stored in the memory 402, specifically the program or instructions stored in the application program 4022, the processor 401 executes the method steps provided in each method embodiment, including, for example:

[0114] When the number of current tasks exceeds a set threshold, determine multiple information dimensions corresponding to all the tasks, and determine multiple information types corresponding to the multiple information dimensions. Each task corresponds to at least one information dimension, and each information dimension corresponds to at least one information type.

[0115] The target information dimension is determined from the plurality of information dimensions based on the surprise of each of the information dimensions.

[0116] Based on the interpretability of each of the information types, the target information type is determined from at least one information type corresponding to the target information dimension;

[0117] The task corresponding to the type of target information is identified as the root cause.

[0118] In one possible implementation, for any of the information dimensions, the sub-surprise degree of each of the information types is determined to obtain multiple sub-surprise degrees corresponding to any of the information dimensions;

[0119] The sum of the multiple sub-surprise values ​​is determined as the surprise value corresponding to any one of the information dimensions;

[0120] The information dimension whose surprise level is greater than the first threshold is determined as the target information dimension.

[0121] In one possible implementation, for any of the information dimensions, the number of CPU cores and the time occupied by each of the information types are determined.

[0122] The core hour for any of the aforementioned information types is determined based on the number of cores and the occupancy time.

[0123] Determine the total number of cores in the central processing unit;

[0124] For any of the aforementioned information types, the daily percentage of core hours is determined based on the core hours and the total number of cores;

[0125] Determine the initial surprise level for any of the aforementioned information types;

[0126] The initial surprise level is weighted and calculated based on the daily percentage of the nuclear hour to obtain the sub-surprise level.

[0127] In one possible implementation, the interpretability of each of the information categories corresponding to the target information dimension is determined;

[0128] The information types whose interpretability is greater than the second threshold are taken as the target information types.

[0129] In one possible implementation, the initial interpretability of any of the information types corresponding to the target information dimension is determined;

[0130] The initial explanatory power is calculated by weighting the initial explanatory power based on the daily percentage of nuclear hours, and the explanatory power is obtained.

[0131] In one possible implementation, the task initiator corresponding to the root cause is determined;

[0132] Reduce the number of tasks initiated by the task initiator, or reduce the number of tasks that meet preset conditions.

[0133] In one possible implementation, the current number of tasks is obtained at preset time intervals;

[0134] An alarm event is triggered when the number of tasks exceeds the set threshold.

[0135] The methods disclosed in the above embodiments of the present invention can be applied to processor 401, or implemented by processor 401. Processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 401 or by instructions in the form of software. The processor 401 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software units in the decoding processor. The software units may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 402. Processor 401 reads the information in memory 402 and, in conjunction with its hardware, completes the steps of the above method.

[0136] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0137] For software implementation, the techniques described herein can be implemented by units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0138] The device provided in this embodiment can be as follows: Figure 4 The device shown can perform, for example Figure 1-2 All steps of the root cause treatment method for task backlog, thereby achieving Figure 1-2 For details on the technical effectiveness of the root cause treatment method for task backlog, please refer to [link / reference needed]. Figure 1-2 The relevant descriptions are presented concisely and will not be elaborated upon here.

[0139] This invention also provides a storage medium (computer-readable storage medium). This storage medium stores one or more programs. The storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; the memory may also include combinations of the above types of memory.

[0140] When one or more programs in the storage medium can be executed by one or more processors to implement the aforementioned root cause handling method for task backlog executed on the device side.

[0141] The processor is configured to execute a root cause processing program for task backlogs stored in memory to implement the following steps of a root cause processing method for task backlogs executed on the device side:

[0142] When the number of current tasks exceeds a set threshold, determine multiple information dimensions corresponding to all the tasks, and determine multiple information types corresponding to the multiple information dimensions. Each task corresponds to at least one information dimension, and each information dimension corresponds to at least one information type.

[0143] The target information dimension is determined from the plurality of information dimensions based on the surprise of each of the information dimensions.

[0144] Based on the interpretability of each of the information types, the target information type is determined from at least one information type corresponding to the target information dimension;

[0145] The task corresponding to the type of target information is identified as the root cause.

[0146] In one possible implementation, for any of the information dimensions, the sub-surprise degree of each of the information types is determined to obtain multiple sub-surprise degrees corresponding to any of the information dimensions;

[0147] The sum of the multiple sub-surprise values ​​is determined as the surprise value corresponding to any one of the information dimensions;

[0148] The information dimension whose surprise level is greater than the first threshold is determined as the target information dimension.

[0149] In one possible implementation, for any of the information dimensions, the number of CPU cores and the time occupied by each of the information types are determined.

[0150] The core hour for any of the aforementioned information types is determined based on the number of cores and the occupancy time.

[0151] Determine the total number of cores in the central processing unit;

[0152] For any of the aforementioned information types, the daily percentage of core hours is determined based on the core hours and the total number of cores;

[0153] Determine the initial surprise level for any of the aforementioned information types;

[0154] The initial surprise level is weighted and calculated based on the daily percentage of the nuclear hour to obtain the sub-surprise level.

[0155] In one possible implementation, the interpretability of each of the information categories corresponding to the target information dimension is determined;

[0156] The information types whose interpretability is greater than the second threshold are taken as the target information types.

[0157] In one possible implementation, the initial interpretability of any of the information types corresponding to the target information dimension is determined;

[0158] The initial explanatory power is calculated by weighting the initial explanatory power based on the daily percentage of nuclear hours, and the explanatory power is obtained.

[0159] In one possible implementation, the task initiator corresponding to the root cause is determined;

[0160] Reduce the number of tasks initiated by the task initiator, or reduce the number of tasks that meet preset conditions.

[0161] In one possible implementation, the current number of tasks is obtained at preset time intervals;

[0162] An alarm event is triggered when the number of tasks exceeds the set threshold.

[0163] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0164] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0165] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for addressing the root cause of task backlog, characterized in that, include: When the number of current tasks exceeds a set threshold, determine multiple information dimensions corresponding to all the tasks, and determine multiple information types corresponding to the multiple information dimensions. Each task corresponds to at least one information dimension, and each information dimension corresponds to at least one information type. The target information dimension is determined from the plurality of information dimensions based on the surprise of each of the information dimensions. Based on the interpretability of each of the information types, the target information type is determined from at least one information type corresponding to the target information dimension; The task corresponding to the type of target information is identified as the root cause; The surprise factor and the interpretability are determined based on the daily percentage of core hours for each information type; wherein the daily percentage of core hours is calculated in the following manner: For any of the aforementioned information dimensions, determine the number of CPU cores and the time required for each of the aforementioned information types; The core hour for any of the aforementioned information types is determined based on the number of cores and the occupancy time. Determine the total number of cores in the central processing unit; For any of the aforementioned information types, the daily percentage of core hours is determined based on the core hours and the total number of cores; The degree of surprise is calculated in the following way: For any of the aforementioned information dimensions, determine the sub-surprise degree for each of the aforementioned information types to obtain multiple sub-surprise degrees corresponding to any of the aforementioned information dimensions; The sum of the multiple sub-surprise values ​​is determined as the surprise value corresponding to any one of the information dimensions; The explanatory power was calculated in the following manner: Determine the initial interpretability of any of the information types corresponding to the target information dimension; The initial explanatory power is calculated by weighting the initial explanatory power based on the daily percentage of nuclear hours, and the explanatory power is obtained.

2. The method according to claim 1, characterized in that, The step of determining the target information dimension from multiple information dimensions based on the surprise of each of the information dimensions includes: The information dimension whose surprise level is greater than the first threshold is determined as the target information dimension.

3. The method according to claim 2, characterized in that, Determining the sub-surprise degree for each of the information categories corresponding to any of the aforementioned information dimensions includes: Determine the initial surprise level for any of the aforementioned information types; The initial surprise level is weighted and calculated based on the daily percentage of the nuclear hour to obtain the sub-surprise level.

4. The method according to claim 3, characterized in that, The step of determining the target information category from multiple information categories corresponding to the target information dimension based on the interpretability of each information category includes: Determine the interpretability of each information category corresponding to the target information dimension; The information types whose interpretability is greater than the second threshold are taken as the target information types.

5. The method according to claim 1, characterized in that, After determining that the task corresponding to the target information type is the root cause, the method further includes: Identify the task initiator corresponding to the root cause; Reduce the number of tasks initiated by the task initiator, or reduce the number of tasks that meet preset conditions.

6. The method according to claim 1, characterized in that, Before determining the multiple information dimensions corresponding to the task, the method further includes: Get the current number of tasks at preset time intervals; An alarm event is triggered when the number of tasks exceeds the set threshold.

7. A root cause treatment device for task backlog, characterized in that, include: The determination module is used to determine multiple information dimensions corresponding to all the tasks when the number of current tasks is greater than a set threshold, and to determine multiple information types corresponding to the multiple information dimensions, wherein each task corresponds to at least one information dimension and each information dimension corresponds to at least one information type. The determining module is further configured to determine a target information dimension from multiple information dimensions based on the surprise of each information dimension. The determining module is further configured to determine the target information type from at least one information type corresponding to the target information dimension based on the interpretability of each information type. The determining module is further configured to determine that the task corresponding to the target information type is the root cause; The surprise factor and the interpretability are determined based on the daily percentage of core hours for each information type; wherein the daily percentage of core hours is calculated in the following manner: For any of the aforementioned information dimensions, determine the number of CPU cores and the time required for each of the aforementioned information types; The core hour for any of the aforementioned information types is determined based on the number of cores and the occupancy time. Determine the total number of cores in the central processing unit; For any of the aforementioned information types, the daily percentage of core hours is determined based on the core hours and the total number of cores; The degree of surprise is calculated in the following way: For any of the aforementioned information dimensions, determine the sub-surprise degree for each of the aforementioned information types to obtain multiple sub-surprise degrees corresponding to any of the aforementioned information dimensions; The sum of the multiple sub-surprise values ​​is determined as the surprise value corresponding to any one of the information dimensions; The explanatory power was calculated in the following manner: Determine the initial interpretability of any of the information types corresponding to the target information dimension; The initial explanatory power is calculated by weighting the initial explanatory power based on the daily percentage of nuclear hours, and the explanatory power is obtained.

8. A device, characterized in that, include: A processor and a memory, the processor being configured to execute a root cause processing program for a task backlog stored in the memory to implement the root cause processing method for a task backlog as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores one or more programs, which can be executed by one or more processors to implement the root cause treatment method for task backlog as described in any one of claims 1 to 6.

Images