Task processing method and device of equipment, equipment, medium and product

Abstract

The invention provides an equipment task processing method and device, equipment, a medium and a product, and the method comprises the steps: carrying out the prediction of real-time operation data based on a fault prediction model corresponding to a to-be-predicted fault type according to the operation data, inputted by a user, of to-be-processed equipment, and obtaining a fault prediction result; and diagnosing the fault operation data based on the fault diagnosis model to obtain a fault diagnosis result. According to the scheme, potential faults can be predicted in advance for different types of equipment under the infrastructure of the data center, fault reason analysis based on expert experience is provided for the fault equipment, and therefore the reliability of the infrastructure of the data center can be improved.

Description

Technical Field

[0001] This application relates to the field of data centers, and more particularly to a task processing method, apparatus, device, medium, and product for a device. Background Technology

[0002] Data centers are primarily responsible for storing, processing, and transmitting massive amounts of data. By providing powerful computing capabilities and reliable data management services, they have become the foundation for modern enterprise decision-making and business continuity. To ensure the efficient and reliable operation of data centers, their infrastructure needs to be maintained.

[0003] Current maintenance strategies for data center infrastructure typically combine scheduled maintenance with reactive maintenance. While scheduled maintenance can prevent equipment failures to some extent, it leads to wasted maintenance resources and increased downtime. Reactive maintenance, on the other hand, results in unplanned downtime and potentially higher production losses and repair costs. Therefore, the current challenge is to improve the reliability of data center infrastructure. Summary of the Invention

[0004] This application provides a task processing method, apparatus, device, medium, and product for improving the reliability of data center infrastructure.

[0005] On one hand, this application provides a task processing method for a device, comprising: receiving operational data of the device to be processed input by a user, wherein the data type of the operational data includes real-time operational data and fault operational data; if the operational data is real-time operational data, then inputting the operational data into a fault prediction model corresponding to the fault type according to the fault type to be predicted, and obtaining the fault prediction result output by the fault prediction model; wherein the fault prediction model corresponds one-to-one with the faults under the device type to which the device to be processed belongs; if the operational data is fault operational data, then inputting the fault operational data into a fault diagnosis model, and obtaining the fault diagnosis result output by the fault diagnosis model; wherein the fault diagnosis result includes the fault cause and maintenance suggestions, and the fault diagnosis model is constructed based on expert experience including fault diagnosis strategies for each device type.

[0006] The task processing method for the device provided in this application involves predicting real-time operational data based on a fault prediction model corresponding to the type of fault to be predicted, according to user-inputted operational data, to obtain fault prediction results; and then diagnosing fault operational data based on a fault diagnosis model to obtain fault diagnosis results. This method can predict potential faults in advance for different types of equipment within a data center infrastructure and provide fault cause analysis based on expert experience for faulty equipment, thereby improving the reliability of the data center infrastructure.

[0007] In one possible implementation, the fault prediction model includes a data prediction module and a fault determination module. The process involves inputting operational data into the fault prediction model corresponding to the fault type to obtain the fault prediction result output by the model. This includes: inputting real-time operational data into the data prediction module to obtain the relationship function between the operational data and time; wherein the data prediction module is constructed based on historical equipment data and machine learning algorithms, and the historical equipment data includes historical operational data before the fault and historical operational data at the time of the fault; and determining the time when the operational data changes to the data threshold based on the data threshold and the relationship function in the fault determination module, using this time as the fault prediction result.

[0008] In the task processing method of the device provided in this application, the data prediction module can effectively utilize historical data for training and provide accurate fault prediction based on the data threshold of the fault judgment module during real-time operation. At the same time, the modular design can improve the flexibility of the fault prediction model.

[0009] In one possible implementation, receiving user-inputted operational data of the device to be processed includes: receiving operational data of the device to be processed manually imported by the user, or receiving operational data of the device to be processed sent by the user through a data monitoring platform, or receiving operational data of the device to be processed sent by the user through an API call service on a third-party platform.

[0010] The task processing method of the device provided in this application obtains the data to be sent through multiple methods, which can improve the richness of the data source and thus optimize the subsequent operation data processing strategy.

[0011] In one possible implementation, the fault type to be predicted is all fault types under the device type to which the device to be processed belongs.

[0012] The task processing method for the equipment provided in this application achieves broader fault coverage and more accurate maintenance planning by treating all fault types under the equipment type to which the processing equipment belongs as the fault types to be predicted, thereby improving the overall reliability and availability of the equipment, reducing unexpected downtime, and optimizing resource allocation and maintenance costs.

[0013] In one possible implementation, the method further includes: obtaining the predicted demand of the device to be processed, the predicted demand including a first fault type, the first fault type being determined based on at least one of the following: the operating data of the device to be processed, the attribute information of the device to be processed, and the device type of the device to be processed; and updating the predicted fault type to the first fault type.

[0014] The task processing method for the device provided in this application can optimize the prediction of demand and improve the accuracy and effectiveness of fault prediction by determining a first fault type based on at least one of the operating data of the device to be processed, the attribute information of the device to be processed, and the device type of the device to be processed.

[0015] In one possible implementation, the real-time operating data includes the device health status of the device to be processed; the method further includes: if the operating data includes real-time operating data, then the device health status in the real-time operating data is weighted and calculated to obtain the health status of the device to be processed.

[0016] The task processing method for the equipment provided in this application achieves accurate equipment status monitoring and optimized maintenance strategies by evaluating and weighting the equipment health status, thereby improving the reliability of the equipment.

[0017] In one possible implementation, the method further includes: if the operating data includes real-time operating data, inputting the real-time operating data into the life prediction model corresponding to the equipment type to which the device to be processed belongs, and obtaining the life prediction result output by the life prediction model; wherein, the life prediction model is constructed based on historical operating data and equipment life.

[0018] The task processing method for the equipment provided in this application allows users to make accurate life predictions to optimize equipment maintenance plans, improve equipment utilization and safety, reduce maintenance costs, and extend equipment life.

[0019] On the other hand, this application provides a task processing apparatus for a device, comprising: a receiving module for receiving operating data of the device to be processed input by a user, wherein the data types of the operating data include real-time operating data and fault operating data; a prediction module for, if the operating data is real-time operating data, inputting the operating data into a fault prediction model corresponding to the fault type to be predicted, and obtaining a fault prediction result output by the fault prediction model; wherein the fault prediction model corresponds one-to-one with the faults under the device type to which the device to be processed belongs; and a diagnosis module for, if the operating data is fault operating data, inputting the fault operating data into a fault diagnosis model, and obtaining a fault diagnosis result output by the fault diagnosis model; wherein the fault diagnosis result includes the fault cause and maintenance suggestions, and the fault diagnosis model is constructed based on expert experience including fault diagnosis strategies for each device type.

[0020] The task processing device provided in this application, based on the user-input operating data of the device to be processed, predicts the real-time operating data using a fault prediction model corresponding to the type of fault to be predicted, and obtains the fault prediction result; it also diagnoses the fault operating data using a fault diagnosis model to obtain the fault diagnosis result. The method of this application can predict potential faults in advance for different types of equipment under the data center infrastructure and provide fault cause analysis based on expert experience for faulty equipment, thereby improving the reliability of the data center infrastructure.

[0021] On the other hand, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the above method.

[0022] On the other hand, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the above-described method.

[0023] On the other hand, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method described above.

[0024] The task processing method, apparatus, equipment, medium, and product provided in this application include: based on the operating data of the device to be processed input by the user, predicting the real-time operating data according to a fault prediction model corresponding to the type of fault to be predicted, and obtaining a fault prediction result; and diagnosing the fault operating data based on a fault diagnosis model to obtain a fault diagnosis result. The solution of this application can predict potential faults in advance for different types of equipment under the data center infrastructure and provide fault cause analysis based on expert experience for faulty equipment, thereby improving the reliability of the data center infrastructure. Attached Figure Description

[0025] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0026] Figure 1 The diagram above illustrates a flowchart of a task processing method for a device.

[0027] Figure 2 The diagram above illustrates a flowchart of a task processing method for a device.

[0028] Figure 3 The diagram above illustrates a flowchart of a task processing method for a device.

[0029] Figure 4 The diagram above illustrates a flowchart of a task processing method for a device.

[0030] Figure 5 The diagram above illustrates a flowchart of a task processing method for a device.

[0031] Figure 6 The diagram above exemplarily illustrates a structural schematic of a task processing device of a device;

[0032] Figure 7 The diagram above illustrates the structure of an electronic device.

[0033] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0034] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0035] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning. The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to be omnipresent but not exclusive. For example, a product or device that comprises a series of components is not necessarily limited to those components that are explicitly listed, but may include other components that are not explicitly listed or that are inherent to such products or devices. The term "module" as used in this application refers to any known or subsequently developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code capable of performing the functions associated with that element.

[0036] Data centers are primarily responsible for storing, processing, and transmitting massive amounts of data, becoming the foundation for modern enterprise decision-making and business continuity by providing powerful computing capabilities and reliable data management services. These data centers not only support daily operations but also drive innovation and global collaboration, enabling enterprises to maintain a leading position in highly competitive markets. To ensure the efficient and reliable operation of data centers, their infrastructure must be meticulously maintained and managed to guarantee the continuous delivery of high-performance and highly available services.

[0037] Currently, maintenance solutions for data center infrastructure typically employ a combination of scheduled maintenance and post-failure maintenance. Scheduled maintenance involves inspecting and servicing equipment at pre-set intervals, which can prevent equipment failures to some extent, but may also lead to wasted maintenance resources and unnecessary downtime. Post-failure maintenance, on the other hand, involves repairing equipment after a failure occurs. While this approach can save on routine maintenance costs, unplanned downtime can result in significant production losses and repair costs, impacting business continuity. Therefore, the key challenge is to improve the reliability of data center infrastructure and optimize maintenance strategies to achieve more efficient resource utilization and lower downtime risk.

[0038] The technical content provided in this application aims to solve the aforementioned technical problems in related technologies. The task processing method, apparatus, equipment, medium, and product provided in this application include: based on the operating data of the device to be processed input by the user, predicting the real-time operating data using a fault prediction model corresponding to the type of fault to be predicted, and obtaining a fault prediction result; and diagnosing the fault operating data based on a fault diagnosis model to obtain a fault diagnosis result. The solution of this application can predict potential faults in advance for different types of equipment under the data center infrastructure and provide fault cause analysis based on expert experience for faulty equipment, thereby improving the reliability of the data center infrastructure.

[0039] The technical solutions of this application will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. In the description of this application, unless otherwise expressly specified and limited, the terms should be broadly understood within the art. The embodiments of this application will now be described with reference to the accompanying drawings.

[0040] Example 1

[0041] Figure 1 The diagram illustrates a flowchart of a task processing method for a device. The executing entity in this example can be the task processing device of the device, such as... Figure 1 As shown, the method includes:

[0042] Step 101: Receive the operating data of the device to be processed input by the user. The data types of the operating data include real-time operating data and fault operating data.

[0043] Step 102: If the running data is real-time running data, then according to the type of fault to be predicted, the running data is input into the fault prediction model corresponding to the fault type, and the fault prediction result output by the fault prediction model is obtained; wherein the fault prediction model corresponds one-to-one with the faults under the equipment type of the equipment to be processed.

[0044] Step 103: If the running data is faulty running data, input the faulty running data into the fault diagnosis model to obtain the fault diagnosis results output by the fault diagnosis model; the fault diagnosis results include the fault cause and maintenance suggestions, and the fault diagnosis model is built based on expert experience including fault diagnosis strategies for each type of equipment.

[0045] It is understood that the fault prediction or fault diagnosis results can be communicated to the user. One possible implementation is to send the fault prediction or fault diagnosis results to the user terminal, and then display or broadcast these results through the user terminal. Other implementation methods are also possible, and this application does not limit these methods.

[0046] In practical applications, the execution subject of this method can be the task processing device of the equipment, and there are many ways to implement it. For example, it can be implemented through a computer program, such as application software; or it can be implemented as a medium storing the relevant computer program, such as a USB flash drive or cloud drive; or it can be implemented through a physical device that integrates or installs the relevant computer program, such as a chip.

[0047] In this example, the device to be processed refers to equipment within the data center infrastructure. Specifically, the infrastructure may include power supply infrastructure or HVAC infrastructure. In practical applications, equipment under the power supply infrastructure may be uninterruptible power supplies, high-voltage DC power supplies, air conditioners, battery devices, or generators, etc.

[0048] Optionally, after receiving data from the device to be processed, the data type of the device's operating data can be identified. This can be done by determining the range of the operating data. For example, if the DC voltage or resistance value of the circuit on the air conditioner control board is within a preset range, the data type of the operating data is determined to be fault operating data.

[0049] Optionally, the distinction can also be made based on the status value of a certain item in the operating data. For example, if the status value of the fan speed is "0" which represents an abnormality, then the data type of the operating data is determined to be fault operating data.

[0050] Optionally, the identification of faulty operating data can also be used for judgment. This scheme is mainly used to quickly determine the data type of operating data when the equipment has already triggered an alarm or crashed. It can be understood that the example above for judging faulty operating data can be used to deduce the same logic for judging real-time operating data. In practical applications, the variability of operating data can also be used for judgment; for example, data that is constantly updated is real-time operating data, while data that remains unchanged is faulty operating data.

[0051] On one hand, when the data type of the operating data is real-time data, the type of fault to be predicted is determined. Specifically, the type of fault to be predicted may be based on historical fault data of the device to be processed or the device type to which the device to be processed belongs, such as selecting the most frequently occurring fault type as the type of fault to be predicted. Optionally, fault types that have a significant impact on the core functions of the device or fault types with high maintenance costs can also be selected as the type of fault to be predicted. After determining the type of fault to be predicted, the operating data is input into the fault prediction model corresponding to the fault type, and the fault prediction result output by the fault prediction model is obtained. The fault prediction model can be designed according to different technologies and methods, and is not limited here. For example, it can be a statistical model based on regression analysis or time series analysis, or a machine learning model based on support vector machines, random forests, or neural networks, or a physical model based on the physical characteristics and behavior of the device.

[0052] In this embodiment, the fault prediction model corresponds one-to-one with the faults under the equipment type of the device to be processed. For example, the device to be processed is a certain model of air conditioner, and the equipment type is air conditioner. The fault prediction model corresponding to each fault may include a fault prediction model for AC power supply devices corresponding to capacitor faults or fan faults; a fault prediction model for DC power supply devices corresponding to module faults; a fault prediction model for air conditioning devices corresponding to compressor faults or fan faults; and a fault prediction model for battery devices corresponding to thermal runaway faults.

[0053] On the other hand, when the data type of the operational data is fault data, the fault operational data is input into the fault diagnosis model to obtain the fault diagnosis results output by the fault diagnosis model. For example, the fault diagnosis model can be a rule-based expert system. Specifically, by extracting "if-then" rules from expert experience based on fault diagnosis strategies for each equipment type, a large number of rules are integrated into a knowledge base. In actual use, the knowledge base is used to match the fault causes and maintenance suggestions corresponding to the input fault data using matching rules. Optionally, a fuzzy logic system based on expert experience can also be established to process inaccurate or incomplete fault operational data through fuzzy sets and fuzzy rules, and output the corresponding fault causes and maintenance suggestions.

[0054] Optionally, after obtaining the fault prediction or fault diagnosis results, these results can be sent to the user. Alternatively, a corresponding report can be generated and communicated to relevant maintenance personnel via a user interface or through telephone or SMS, so that the maintenance personnel can notify the manufacturer for repairs or provide a reference for future equipment maintenance planning.

[0055] The task processing method for the device provided in this application includes: predicting the real-time operating data based on a fault prediction model corresponding to the type of fault to be predicted, according to the operating data of the device to be processed input by the user, to obtain a fault prediction result; and diagnosing the fault operating data based on a fault diagnosis model to obtain a fault diagnosis result. The solution of this application can predict potential faults in advance for different types of devices under the data center infrastructure and provide fault cause analysis based on expert experience for faulty devices, thereby improving the reliability of the data center infrastructure.

[0056] As another example, the fault prediction model includes a data prediction module and a fault determination module. Figure 2 The diagram illustrates a flowchart of a task processing method for a device. Figure 2 As shown, the running data is input into the fault prediction model corresponding to the fault type, and the fault prediction results output by the fault prediction model are obtained, including:

[0057] Step 201: Input the real-time operating data into the data prediction module to obtain the relationship function between the operating data and time; the data prediction module is built based on historical equipment data and machine learning algorithms, and the historical equipment data includes historical operating data before the failure and historical operating data at the time of the failure;

[0058] Step 202: Based on the data threshold and relational function in the fault determination module, determine the time when the running data changes to the data threshold, and use this time as the fault prediction result.

[0059] In this example, historical device data refers to historical data from devices of the same type as the device to be processed. Optionally, historical device data can also be historical data from the device to be processed. After obtaining the historical device data, data preprocessing can be performed, such as handling missing data, outliers, and noise, and the preprocessed historical device data can be divided into training and testing sets. Further, a suitable machine learning algorithm, such as support vector machine, random forest, or neural network, is selected to build an initial model, which is then trained using the training set. In practical applications, during model training, features such as trends, periodicity, and volatility are extracted from the training set data to improve the model's ability to perceive changes in the training set data over time. After model training is complete, the historical device data in the testing set is used for model validation, and the validated model is integrated into the fault prediction model. In this example, real-time operating data is input into the data prediction module to obtain the relationship function between operating data and time. Based on the data threshold in the fault determination module, the time when the operating data changes to the data threshold is determined, and this time is used as the fault prediction result. Specifically, the data threshold in the fault determination module can be determined based on historical fault data or expert experience. In this example, the data prediction module can effectively utilize historical data for training and provide accurate fault prediction based on the data thresholds of the fault determination module during real-time operation. At the same time, the modular design can improve the flexibility of the fault prediction model.

[0060] As yet another example, receiving user-input operational data from the device to be processed includes:

[0061] It can receive operating data of devices to be processed that are manually imported by users, or receive operating data of devices to be processed that are sent by users through a data monitoring platform, or receive operating data of devices to be processed that are sent by users through API calls to services on a third-party platform.

[0062] In this example, the operational data manually imported by the user is typically fault operation data. In practical applications, fault operation data can also include equipment status descriptions and fault maintenance records. Alternatively, users can send operational data of the equipment to be processed through a data monitoring platform. In practice, the data monitoring platform can install environmental sensors around the equipment, such as temperature, humidity, and vibration sensors, to monitor the surrounding environmental conditions in real time. Alternatively, the data monitoring platform can obtain operational data from within the equipment, such as current, voltage, and operating status, to directly extract data from the equipment's control system. Furthermore, users can also send operational data of the equipment to be processed through API calls on third-party platforms. Optionally, operational data sent by the user in different ways can be used as historical operational data for training the model in any example to improve the model's generalization ability and robustness. This example's solution, by obtaining data for the sent data through multiple methods, enhances the richness of data sources, thereby optimizing subsequent operational data processing strategies.

[0063] As another example, the fault types to be predicted are all fault types under the device type to which the device to be processed belongs.

[0064] This example solution achieves broader fault coverage and more accurate maintenance planning by treating all fault types under the equipment type to which the processing equipment belongs as the fault types to be predicted. This improves the overall reliability and availability of the equipment, reduces unexpected downtime, and optimizes resource allocation and maintenance costs.

[0065] As yet another example, Figure 3 The diagram illustrates a flowchart of a task processing method for a device. Figure 3 As shown, the method also includes:

[0066] Step 301: Obtain the predicted demand of the device to be processed. The predicted demand includes a first fault type. The first fault type is determined based on at least one of the following: the operating data of the device to be processed, the attribute information of the device to be processed, and the device type of the device to be processed.

[0067] Step 302: Update the fault type to be predicted to the first fault type.

[0068] In this example, the requirement for predicting the first type of fault can be determined by the entity implementing this solution based on the execution strategy. Specific execution strategies include: the process of determining the fault type based on the operating data of the device to be processed can be: using data analysis techniques to extract features from the operating data, identifying abnormal patterns or trends, and then determining possible fault types; the process of determining the fault type based on the attribute information of the device to be processed can be: by analyzing the device's attribute information and combining it with historical fault data, identifying common fault types related to these attributes, for example, certain models or years of equipment may be more prone to specific faults; the process of determining the fault type based on the equipment type can be: referring to the fault history of the equipment type and industry experience, determining the typical fault types of that type of equipment.

[0069] Optionally, the prediction requirement can originate from the user's revised prediction requirement after reviewing the execution results of the above-mentioned execution strategy, or it can directly originate from the prediction requirement based on the operating data, attribute information, and device type of the device to be processed. In practical applications, a corresponding fault prediction scheme can be formulated by combining all fault types and the first fault type. For example, the fault prediction frequency based on all fault types is greater than the fault prediction frequency based on the first fault type. The scheme in this example, by determining the first fault type based on at least one of the operating data, attribute information, and device type of the device to be processed, can optimize the prediction requirement and improve the accuracy and effectiveness of fault prediction.

[0070] As yet another example, real-time operational data includes the device health status of the device being processed. Figure 4 The diagram illustrates a flowchart of a task processing method for a device. Figure 4 As shown, the method also includes:

[0071] Step 401: If the running data includes real-time running data, then the device health status in the real-time running data is weighted and calculated to obtain the health status of the device to be processed.

[0072] Optionally, after obtaining the health status of the device to be processed, the health status can be sent to the user. Optionally, a corresponding report can also be generated and the relevant maintenance personnel can be contacted through the user interface or via telephone or SMS.

[0073] It should be noted that the health calculation of the device to be processed in this example can be based on a corresponding algorithm, or real-time operating data can be input into a health calculation model to obtain the health score of the device to be processed from the model output. When calculating based on a health calculation model, this health model can be a different model under an integrated model, or it can be an independent model. In this example, the devices used for health score calculation are the core devices of the device to be processed. For example, when the device to be processed is an air conditioner, the corresponding health scores could be: compressor health, fan health, filter health, etc.; when the device to be processed is an AC-powered device, the corresponding device health scores could be: battery health, capacitor health, fan health, etc.; when the device to be processed is a DC-powered device, the corresponding device health scores could be: battery health, load module health, etc. Optionally, the current environmental conditions of the device, such as humidity or temperature, can also be considered when calculating the device health score; abnormal environmental conditions can reduce the device health score. In practical applications, the correlation coefficients between each device and the core function in the device to be processed can be determined as weights when calculating the health score of the device to be processed. Optionally, this weighting can be determined by the user according to their needs. This example solution, by evaluating and weighting the calculation of device health, achieves accurate device status monitoring and optimized maintenance strategies, thereby improving device reliability.

[0074] As yet another example, Figure 5 The diagram illustrates a flowchart of a task processing method for a device. Figure 5 As shown, the method also includes:

[0075] Step 501: If the operating data includes real-time operating data, input the real-time operating data into the life prediction model corresponding to the equipment type of the device to be processed, and obtain the life prediction result output by the life prediction model; wherein the life prediction model is constructed based on historical operating data and equipment life.

[0076] Optionally, after obtaining the lifespan prediction results for the equipment to be processed, the prediction results can be sent to the user. Optionally, a corresponding report can also be generated, and relevant maintenance personnel can be contacted through a user interface or via telephone or SMS to arrange procurement and repair matters.

[0077] For example, historical operating data used to build the lifespan prediction model and real-time operating data input to the model may include equipment operating parameters, equipment maintenance records, and physical environmental conditions such as temperature, humidity, and air pollution levels. Specifically, the lifespan prediction model construction process may include: collecting historical operating data and equipment lifespan data; preprocessing the collected data, such as cleaning, denoising, and normalizing, to improve data quality and model accuracy; extracting key features related to equipment lifespan from the preprocessed data using statistical analysis, signal processing, or machine learning techniques; selecting an appropriate model, such as a regression model (e.g., linear regression, logistic regression) or a machine learning model (e.g., random forest, support vector machine), to establish an initial lifespan prediction; and training the model using historical operating data and corresponding lifespan data, adjusting model parameters during training to minimize prediction errors, and completing the lifespan prediction model construction after successful model validation. This example solution provides users with accurate lifespan predictions to optimize equipment maintenance plans, improve equipment utilization and safety, reduce maintenance costs, and extend equipment lifespan.

[0078] The device task processing method provided in this embodiment includes: predicting real-time operating data based on a fault prediction model corresponding to the type of fault to be predicted, according to user-inputted operating data of the device to be processed, to obtain a fault prediction result; and diagnosing fault operating data based on a fault diagnosis model to obtain a fault diagnosis result. The solution of this application can predict potential faults in advance for different types of devices under the data center infrastructure and provide fault cause analysis based on expert experience for faulty devices, thereby improving the reliability of the data center infrastructure.

[0079] Example 2

[0080] Figure 6 The diagram above exemplifies the structure of the task processing apparatus of the device provided in the embodiments of this application, such as... Figure 6 As shown, the device includes:

[0081] The receiving module 71 is used to receive the operating data of the device to be processed input by the user. The data types of the operating data include real-time operating data and fault operating data.

[0082] The prediction module 72 is used to input the running data into the fault prediction model corresponding to the fault type according to the fault type to be predicted if the running data is real-time running data, and obtain the fault prediction result output by the fault prediction model; wherein the fault prediction model corresponds one-to-one with the faults under the equipment type of the equipment to be processed.

[0083] The diagnostic module 73 is used to input the faulty running data into the fault diagnosis model if the running data is faulty running data, and obtain the fault diagnosis results output by the fault diagnosis model; wherein the fault diagnosis results include the fault cause and maintenance suggestions, and the fault diagnosis model is built based on expert experience including fault diagnosis strategies for each type of equipment;

[0084] Optionally, the device further includes a sending module 74 for sending fault prediction results or fault diagnosis results to the user. It is understood that the fault prediction results or fault diagnosis results can be communicated to the user. In possible implementations, the fault prediction results or fault diagnosis results can be sent to a user terminal, and displayed or broadcast through the user terminal. Other implementations are also possible, and this application embodiment does not limit these.

[0085] In practical applications, there are various ways to implement the task processing device of a device. For example, it can be implemented through computer programs, such as application software; or it can be implemented as a medium storing relevant computer programs, such as USB flash drives or cloud drives; or it can be implemented through a physical device that integrates or installs relevant computer programs, such as chips.

[0086] In this example, the device to be processed refers to equipment within the data center infrastructure. Specifically, the infrastructure may include power supply infrastructure or HVAC infrastructure. In practical applications, equipment under the power supply infrastructure can be uninterruptible power supplies, high-voltage DC power supplies, air conditioners, battery devices, or generators, etc. Optionally, after receiving data from the device to be processed, the data type of the device's operating data can be identified. This can be done by determining the range of the operating data; for example, if the DC voltage or resistance value of the circuit on the air conditioner control board is within a preset range, the data type is determined to be fault operating data. Optionally, it can also be distinguished based on the status value of a specific item in the operating data; for example, if the fan speed status value is "0," representing an abnormality, the data type is determined to be fault operating data. Optionally, it can also be determined based on the identifier of the fault operating data. This scheme is mainly used for rapid determination of the data type when the device has already triggered an alarm or crashed. It can be understood that the above examples for determining fault operating data can be used to reverse-engineer the data for determining real-time operating data. In practical applications, it can also be determined based on the variability of the operating data; for example, data that is continuously updated is real-time operating data, while data that remains unchanged is fault operating data.

[0087] On one hand, when the data type of the operating data is real-time data, the type of fault to be predicted is determined. Specifically, the type of fault to be predicted may be based on historical fault data of the device to be processed or the device type to which the device to be processed belongs, such as selecting the most frequently occurring fault type as the type of fault to be predicted. Optionally, fault types that have a significant impact on the core functions of the device or fault types with high maintenance costs can also be selected as the type of fault to be predicted. After determining the type of fault to be predicted, the operating data is input into the fault prediction model corresponding to the fault type, and the fault prediction result output by the fault prediction model is obtained. The fault prediction model can be designed according to different technologies and methods, and is not limited here. For example, it can be a statistical model based on regression analysis or time series analysis, or a machine learning model based on support vector machines, random forests, or neural networks, or a physical model based on the physical characteristics and behavior of the device.

[0088] In this embodiment, the fault prediction model corresponds one-to-one with the faults under the equipment type of the device to be processed. For example, the device to be processed is a certain model of air conditioner, and the equipment type is air conditioner. The fault prediction model corresponding to each fault may include a fault prediction model for AC power supply devices corresponding to capacitor faults or fan faults; a fault prediction model for DC power supply devices corresponding to module faults; a fault prediction model for air conditioning devices corresponding to compressor faults or fan faults; and a fault prediction model for battery devices corresponding to thermal runaway faults.

[0089] On the other hand, when the data type of the operational data is fault data, the fault operational data is input into the fault diagnosis model to obtain the fault diagnosis results output by the fault diagnosis model. For example, the fault diagnosis model can be a rule-based expert system. Specifically, by extracting "if-then" rules from expert experience based on fault diagnosis strategies for each equipment type, a large number of rules are integrated into a knowledge base. In actual use, the knowledge base is used to match the fault causes and maintenance suggestions corresponding to the input fault data using matching rules. Optionally, a fuzzy logic system based on expert experience can also be established to process inaccurate or incomplete fault operational data through fuzzy sets and fuzzy rules, and output the corresponding fault causes and maintenance suggestions.

[0090] Optionally, after obtaining the fault prediction or fault diagnosis results, these results can be sent to the user. Alternatively, a corresponding report can be generated and communicated to relevant maintenance personnel via a user interface or through telephone or SMS, so that the maintenance personnel can notify the manufacturer for repairs or provide a reference for future equipment maintenance planning.

[0091] The task processing device provided in this application, based on the user-input operating data of the device to be processed, predicts the real-time operating data using a fault prediction model corresponding to the type of fault to be predicted, and obtains the fault prediction result; it also diagnoses the fault operating data using a fault diagnosis model to obtain the fault diagnosis result. The solution of this application can predict potential faults in advance for different types of equipment under the data center infrastructure and provide fault cause analysis based on expert experience for faulty equipment, thereby improving the reliability of the data center infrastructure.

[0092] In one example, the fault prediction model includes: a data prediction module and a fault determination module; the prediction module 72 is specifically used for:

[0093] Real-time operational data is input into the data prediction module to obtain the relationship function between operational data and time. The data prediction module is built based on historical equipment data and machine learning algorithms. The historical equipment data includes historical operational data before the failure and historical operational data at the time of the failure.

[0094] Based on the data threshold and relational function in the fault determination module, the time when the running data changes to the data threshold is determined, and this time is used as the fault prediction result.

[0095] In this example, historical device data refers to historical data from devices of the same type as the device to be processed. Optionally, historical device data can also be historical data from the device to be processed. After obtaining the historical device data, data preprocessing can be performed, such as handling missing data, outliers, and noise, and the preprocessed historical device data can be divided into training and testing sets. Further, a suitable machine learning algorithm, such as support vector machine, random forest, or neural network, is selected to build an initial model, which is then trained using the training set. In practical applications, during model training, features such as trends, periodicity, and volatility are extracted from the training set data to improve the model's ability to perceive changes in the training set data over time. After model training is complete, the historical device data in the testing set is used for model validation, and the validated model is integrated into the fault prediction model. In this example, real-time operating data is input into the data prediction module to obtain the relationship function between operating data and time. Based on the data threshold in the fault determination module, the time when the operating data changes to the data threshold is determined, and this time is used as the fault prediction result. Specifically, the data threshold in the fault determination module can be determined based on historical fault data or expert experience. In this example, the data prediction module can effectively utilize historical data for training and provide accurate fault prediction based on the data thresholds of the fault determination module during real-time operation. At the same time, the modular design can improve the flexibility of the fault prediction model.

[0096] In one example, receiving module 71 is specifically used for:

[0097] It can receive operating data of devices to be processed that are manually imported by users, or receive operating data of devices to be processed that are sent by users through a data monitoring platform, or receive operating data of devices to be processed that are sent by users through API calls to services on a third-party platform.

[0098] In this example, the operational data manually imported by the user is typically fault operation data. In practical applications, fault operation data can also include equipment status descriptions and fault maintenance records. Alternatively, users can send operational data of the equipment to be processed through a data monitoring platform. In practice, the data monitoring platform can install environmental sensors around the equipment, such as temperature, humidity, and vibration sensors, to monitor the surrounding environmental conditions in real time. Alternatively, the data monitoring platform can obtain operational data from within the equipment, such as current, voltage, and operating status, to directly extract data from the equipment's control system. Furthermore, users can also send operational data of the equipment to be processed through API calls on third-party platforms. Optionally, operational data sent by the user in different ways can be used as historical operational data for training the model in any example to improve the model's generalization ability and robustness. This example's solution, by obtaining data for the sent data through multiple methods, enhances the richness of data sources, thereby optimizing subsequent operational data processing strategies.

[0099] In one example, the fault types to be predicted are all fault types under the device type to which the device to be processed belongs.

[0100] This example solution achieves broader fault coverage and more accurate maintenance planning by treating all fault types under the equipment type to which the processing equipment belongs as the fault types to be predicted. This improves the overall reliability and availability of the equipment, reduces unexpected downtime, and optimizes resource allocation and maintenance costs.

[0101] In one example, receiving module 71 is also used for:

[0102] Obtain the predicted demand of the device to be processed. The predicted demand includes a first fault type, which is determined based on at least one of the following: the operating data of the device to be processed, the attribute information of the device to be processed, and the device type of the device to be processed.

[0103] Update the fault type to be predicted to the first fault type.

[0104] In this example, the requirement for predicting the first type of fault can be determined by the entity implementing this solution based on the execution strategy. Specific execution strategies include: the process of determining the fault type based on the operating data of the device to be processed can be: using data analysis techniques to extract features from the operating data, identifying abnormal patterns or trends, and then determining possible fault types; the process of determining the fault type based on the attribute information of the device to be processed can be: by analyzing the device's attribute information and combining it with historical fault data, identifying common fault types related to these attributes, for example, certain models or years of equipment may be more prone to specific faults; the process of determining the fault type based on the equipment type can be: referring to the fault history of the equipment type and industry experience, determining the typical fault types of that type of equipment.

[0105] Optionally, the prediction requirement can originate from the user's revised prediction requirement after reviewing the execution results of the above-mentioned execution strategy, or it can directly originate from the prediction requirement based on the operating data, attribute information, and device type of the device to be processed. In practical applications, a corresponding fault prediction scheme can be formulated by combining all fault types and the first fault type. For example, the fault prediction frequency based on all fault types is greater than the fault prediction frequency based on the first fault type. The scheme in this example, by determining the first fault type based on at least one of the operating data, attribute information, and device type of the device to be processed, can optimize the prediction requirement and improve the accuracy and effectiveness of fault prediction.

[0106] In one example, the device's task processing unit further includes: an optimization module 75; real-time operating data includes: the device health status of the device to be processed. The optimization module 75 is specifically used for:

[0107] If the operational data includes real-time operational data, the device health status in the real-time operational data is weighted and calculated to obtain the health status of the device to be processed.

[0108] Optionally, after obtaining the health status of the device to be processed, the optimization module 75 can also send the health status to the user. Optionally, a corresponding report can also be generated and the relevant maintenance personnel can be contacted through the user interface or via telephone or SMS.

[0109] It should be noted that the health calculation of the device to be processed in this example can be based on a corresponding algorithm, or real-time operating data can be input into a health calculation model to obtain the health status of the device to be processed from the model output. When calculating based on a health calculation model, this health model can be a different model under an integrated model, or it can be an independent model. For example, when the device to be processed is an air conditioner, the corresponding health status could be: compressor health, fan health, filter health, etc.; when the device to be processed is an AC-powered device, the corresponding component health status could be: battery health, capacitor health, fan health, etc.; when the device to be processed is a DC-powered device, the corresponding component health status could be: battery health, load module health, etc. Optionally, the current environmental conditions of the device, such as humidity or temperature, can also be considered when calculating the device health status; abnormal environmental conditions can reduce the device health status. In practical applications, the correlation coefficients between each component and the core function of the device to be processed can be determined as the weights when calculating the health status of the device to be processed. Optionally, these weights can also be determined by the user according to their needs. The solution presented in this example improves equipment reliability by assessing and weighting the calculation of equipment health, thereby enabling precise monitoring of equipment status and optimizing maintenance strategies.

[0110] In one example, optimization module 75 is also used for:

[0111] If the operational data includes real-time operational data, the real-time operational data is input into the life prediction model corresponding to the equipment type to which the device to be processed belongs, and the life prediction result output by the life prediction model is obtained; wherein, the life prediction model is constructed based on historical operational data and equipment life.

[0112] Optionally, after obtaining the lifespan prediction results of the equipment to be processed, the optimization module 75 can also send the lifespan prediction results to the user. Optionally, a corresponding report can also be generated, and relevant maintenance personnel can be contacted through a user interface or via telephone or SMS to arrange procurement and maintenance matters.

[0113] For example, historical operating data used to build the lifespan prediction model and real-time operating data input to the model may include equipment operating parameters, equipment maintenance records, and physical environmental conditions such as temperature, humidity, and air pollution levels. Specifically, the lifespan prediction model construction process may include: collecting historical operating data and equipment lifespan data; preprocessing the collected data, such as cleaning, denoising, and normalizing, to improve data quality and model accuracy; extracting key features related to equipment lifespan from the preprocessed data using statistical analysis, signal processing, or machine learning techniques; selecting an appropriate model, such as a regression model (e.g., linear regression, logistic regression) or a machine learning model (e.g., random forest, support vector machine), to establish an initial lifespan prediction; and training the model using historical operating data and corresponding lifespan data, adjusting model parameters during training to minimize prediction errors, and completing the lifespan prediction model construction after successful model validation. This example solution optimizes equipment maintenance plans through accurate lifespan prediction, improving equipment utilization and safety, reducing maintenance costs, and extending equipment lifespan.

[0114] The task processing device provided in this application, based on the user-input operating data of the device to be processed, predicts the real-time operating data using a fault prediction model corresponding to the type of fault to be predicted, and obtains the fault prediction result; it also diagnoses the fault operating data using a fault diagnosis model to obtain the fault diagnosis result. The solution of this application can predict potential faults in advance for different types of equipment under the data center infrastructure and provide fault cause analysis based on expert experience for faulty equipment, thereby improving the reliability of the data center infrastructure.

[0115] Example 3

[0116] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device includes:

[0117] The electronic device includes a processor 291 and a memory 292; it may also include a communication interface 293 and a bus 294. The processor 291, memory 292, and communication interface 293 can communicate with each other via the bus 294. The communication interface 293 can be used for information transmission. The processor 291 can invoke logical instructions stored in the memory 292 to execute the methods described in the example above.

[0118] Furthermore, the logic instructions in the aforementioned memory 292 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0119] The memory 292, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this application. The processor 291 executes functional applications and data processing by running the software programs, instructions, and modules stored in the memory 292, that is, it implements the methods in the above method examples.

[0120] The memory 292 may include a program storage area and a data storage area. The program storage area may store the operating system and application programs required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 292 may include high-speed random access memory and may also include non-volatile memory.

[0121] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method in any of the embodiments.

[0122] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the method in any of the embodiments.

[0123] Following the disclosure of the invention herein, other embodiments of this application will readily occur. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0124] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A task processing method for a device, characterized in that, include: Receive user-inputted operational data of the device to be processed, wherein the data types of the operational data include real-time operational data and fault operational data; If the operating data is real-time operating data, then according to the type of fault to be predicted, the operating data is input into the fault prediction model corresponding to the fault type to obtain the fault prediction result output by the fault prediction model; wherein the fault prediction model corresponds one-to-one with the faults under the equipment type to which the device to be processed belongs; If the operating data is faulty operating data, then the faulty operating data is input into the fault diagnosis model to obtain the fault diagnosis result output by the fault diagnosis model; wherein the fault diagnosis result includes the fault cause and maintenance suggestions, and the fault diagnosis model is built based on expert experience including fault diagnosis strategies for each type of equipment.

2. The method according to claim 1, characterized in that, The fault prediction model includes a data prediction module and a fault determination module; the step of inputting the operating data into the fault prediction model corresponding to the fault type and obtaining the fault prediction result output by the fault prediction model includes: The real-time operating data is input into the data prediction module to obtain the relationship function between the operating data and time; wherein, the data prediction module is constructed based on historical equipment data and machine learning algorithms, and the historical equipment data includes historical operating data before the failure and historical operating data at the time of the failure; Based on the data threshold in the fault determination module and the relationship function, the time when the running data changes to the data threshold is determined, and this time is used as the fault prediction result.

3. The method according to claim 1, characterized in that, The process of receiving user-inputted operational data of the device to be processed includes: The system can receive the operating data of the device to be processed manually imported by the user, or receive the operating data of the device to be processed sent by the user through the data monitoring platform, or receive the operating data of the device to be processed sent by the user through API call service on a third-party platform.

4. The method according to claim 1, characterized in that, The fault types to be predicted are all fault types under the equipment type to which the device to be processed belongs.

5. The method according to claim 4, characterized in that, The method further includes: Obtain the predicted demand of the device to be processed, the predicted demand including a first fault type, the first fault type being determined based on at least one of the following: the operating data of the device to be processed, the attribute information of the device to be processed, and the device type of the device to be processed; Update the fault type to be predicted to the first fault type.

6. The method according to claim 1, characterized in that, The real-time operational data includes: the device health status of the device to be processed; the method further includes: If the operating data includes real-time operating data, then the health status of the device in the real-time operating data is weighted and calculated to obtain the health status of the device to be processed.

7. The method according to claim 1, characterized in that, The method further includes: If the operating data includes real-time operating data, the real-time operating data is input into the life prediction model corresponding to the equipment type to which the device to be processed belongs, and the life prediction result output by the life prediction model is obtained; wherein, the life prediction model is constructed based on historical operating data and equipment life.

8. A task processing device for an equipment, characterized in that, include: The receiving module is used to receive the operating data of the device to be processed input by the user. The data types of the operating data include real-time operating data and fault operating data. The prediction module is used to input the operating data into the fault prediction model corresponding to the fault type according to the fault type to be predicted, if the operating data is real-time operating data, and obtain the fault prediction result output by the fault prediction model; wherein the fault prediction model corresponds one-to-one with the faults under the equipment type to which the device to be processed belongs; The diagnostic module is used to input the faulty operating data into the fault diagnosis model if the operating data is faulty operating data, and obtain the fault diagnosis result output by the fault diagnosis model; wherein the fault diagnosis result includes the fault cause and maintenance suggestions, and the fault diagnosis model is built based on expert experience including fault diagnosis strategies for each type of equipment.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 7.

11. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images