Working equipment management method and device, equipment, medium and product
By obtaining and analyzing the operating information of equipment in the organization, using the target model to identify exceptions and sending prompts to users, the problem of the inability to dynamically manage equipment in the existing technology is solved and the efficiency of IT services is improved.
Patent Information
- Application Number
- CN202411801497.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-06
- Publication Date
- 2025-03-28
AI Technical Summary
The prior art is difficult to dynamically evaluate and manage the organization's equipment as a whole, and it is impossible to detect and handle equipment operation abnormalities in real time, affecting IT service efficiency.
By obtaining the operation information of multiple devices within the target organization or in the target network, sending it to the target model for analysis, determining the device that is running abnormally, and sending a prompt message to the relevant users to provide a solution.
It realizes dynamic equipment detection and management in the organizational dimension, improves IT service efficiency, promptly detects and handles equipment operation abnormalities, and reduces the impact of equipment failures on business.
Smart Images
Figure CN119718863A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a management method, device, electronic device, computer-readable storage medium, and computer program product for work equipment. Background Art
[0002] An organization is usually composed of multiple members. For example, an organization can be an enterprise, a company, etc. As the business of an organization develops, the performance of the work equipment used by members of the organization has an increasingly significant impact on office efficiency.
[0003] Usually, an IT department is set up within an organization to manage the equipment of its members. For example, the IT department can count the basic configuration and service life of the equipment used by members. When members report equipment failure, the IT department can also repair and replace the equipment.
[0004] However, the above methods often only focus on the static attribute information of the equipment and cannot dynamically evaluate and manage the organization's equipment as a whole. Summary of the invention
[0005] The present application provides a method for managing work equipment. The method can realize dynamic detection and management of equipment in the organizational dimension and improve the IT service efficiency within the organization. The present application also provides a device, an electronic device, a computer-readable storage medium, and a computer program product corresponding to the above method.
[0006] In a first aspect, the present application provides a method for managing work equipment, the method comprising:
[0007] Obtaining operation information of multiple devices in a target organization or a target network; wherein the operation information includes indicator values corresponding to multiple target performance indicators;
[0008] Sending the operation information of the multiple devices to the target model, and receiving the operation abnormality prediction probabilities corresponding to the multiple devices respectively returned by the target model;
[0009] Determining at least one target device with an abnormal operation among the multiple devices according to the predicted probability of abnormal operation;
[0010] A prompt message is sent to a target user associated with the at least one target device; wherein the prompt message is used to inform the target user that the target device is operating abnormally, or to inform the target user that the target device is operating abnormally and a corresponding solution.
[0011] In a second aspect, the present application provides a management device for work equipment, the device comprising:
[0012] An acquisition module, used to acquire operation information of multiple devices in a target organization or a target network; wherein the operation information includes indicator values corresponding to multiple target performance indicators;
[0013] A communication module, used to obtain operation information of multiple devices in a target organization or a target network; wherein the operation information includes indicator values corresponding to multiple target performance indicators;
[0014] A determination module, configured to determine at least one target device with an operation abnormality among the multiple devices according to the predicted probability of the operation abnormality;
[0015] A prompt module is used to send a prompt message to a target user associated with the at least one target device; wherein the prompt message is used to inform the target user that the target device is operating abnormally, or to inform the target user that the target device is operating abnormally and a corresponding solution.
[0016] In a third aspect, the present application provides an electronic device, the electronic device comprising a processor and a memory. The processor and the memory communicate with each other. The processor is used to execute instructions stored in the memory so that the electronic device executes the management method of the working device in the first aspect or any implementation of the first aspect.
[0017] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions are stored, and the instructions instruct an electronic device to execute the method for managing a work device as described in the first aspect or any one of the implementations of the first aspect.
[0018] In a fifth aspect, the present application provides a computer program product comprising instructions, which, when executed on an electronic device, enables the electronic device to execute the method for managing a work device as described in the first aspect or any one of the implementations of the first aspect.
[0019] Based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations.
[0020] It can be seen from the above technical solutions that this application has the following advantages:
[0021] The present application provides a method for managing work equipment. The method first obtains operating information of multiple devices in a target organization or a target network, wherein the operating information includes indicator values corresponding to multiple performance indicators, sends the operating information of the multiple devices to a target model, receives operation anomaly prediction probabilities corresponding to the multiple devices respectively returned by the target model, then, based on the operation anomaly prediction probability, determines at least one target device with an operation anomaly among the multiple devices, and sends a prompt message to a target user associated with the at least one target device, wherein the prompt message is used to inform the target user that the target device is operating abnormally, or to inform the target user that the target device is operating abnormally and a corresponding solution.
[0022] In this method, a unified detection is performed on multiple working devices within the organization. By obtaining the operation information of the devices, the operation status of the devices is determined from the dimensions of multiple performance indicators. If the device is determined to be operating abnormally, the user is informed in the form of a prompt message. In this way, dynamic detection and management of devices at the organizational level is achieved, and the efficiency of IT services within the organization is improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the technical method of the embodiments of the present application, the drawings required for use in the embodiments are briefly introduced below.
[0024] Figure 1 A flowchart of a method for managing work equipment provided in an embodiment of the present application;
[0025] Figure 2 A schematic diagram of the architecture of a data collection client provided in an embodiment of the present application;
[0026] Figure 3 A schematic diagram of the structure of a management device for work equipment provided in an embodiment of the present application;
[0027] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0028] The terms "first" and "second" in the embodiments of the present application are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.
[0029] First, some technical terms and application scenarios involved in the embodiments of this application are introduced.
[0030] An organization is usually composed of multiple members. For example, an organization can be an enterprise, a company, etc. As the business of an organization develops, the performance of the work equipment used by members of the organization has an increasingly significant impact on office efficiency.
[0031] Usually, an IT department is set up within an organization to manage the equipment of its members. For example, the IT department can count the basic configuration and service life of the equipment used by members. When members report equipment failure, the IT department can also repair and replace the equipment.
[0032] However, the above methods can only focus on the static attribute information of the device, and cannot dynamically evaluate and manage the organization's equipment as a whole. For example, it is difficult for the IT department to accurately know whether the central processing unit (CPU) of the organization's employees' work equipment has degraded due to long-term high-load operation, whether the memory has bottlenecks due to multi-tasking, and whether the hard disk read and write speed affects the software startup and running speed. When using devices with poor performance, the organization's employees need to experience frequent freezes, unresponsive software, and rapid battery depletion, which affects office efficiency and is not convenient for the IT department to evaluate and manage the equipment.
[0033] In view of this, the present application provides a method for managing work equipment, which first obtains operating information of multiple devices within a target organization or a target network, wherein the operating information includes indicator values corresponding to multiple performance indicators, sends the operating information of the multiple devices to a target model, receives operation anomaly prediction probabilities corresponding to the multiple devices returned by the target model, and then, based on the operation anomaly prediction probability, determines at least one target device with an operation anomaly among the multiple devices, and sends a prompt message to a target user associated with the at least one target device, wherein the prompt message is used to inform the target user that the target device is operating abnormally, or to inform the target user that the target device is operating abnormally and a corresponding solution.
[0034] In this method, a unified detection is performed on multiple working devices within the organization. By obtaining the operation information of the devices, the operation status of the devices is determined from the dimensions of multiple performance indicators. If the device is determined to be operating abnormally, the user is informed in the form of a prompt message. In this way, dynamic detection and management of devices at the organizational level is achieved, and the efficiency of IT services within the organization is improved.
[0035] To facilitate understanding of the technical solution provided by the embodiments of the present application, the following will be described in conjunction with the accompanying drawings. Figure 1 The flowchart of a method for managing working equipment shown in FIG. 1 is a flowchart of a method for managing working equipment, which can be applied to an equipment management system. The method specifically includes:
[0036] S101: Obtain operation information of multiple devices in a target organization or a target network.
[0037] In the embodiment of the present application, the target organization can be understood as an organization that has a need for work equipment management, for example, the target organization can be a company, an enterprise, a school, etc. The target network can be understood as a network used by the target organization, for example, the target network can be an office network used by a company, an office network used by an enterprise, a campus network used by a school, etc.
[0038] The multiple devices in the target organization or target network can be understood as IT devices used by users of the target organization (e.g., members of the organization) at work. For example, when the target organization is a company, the multiple devices in the target organization can be office equipment used by company employees. For another example, when the target network is a campus network used by a school, the multiple devices in the target network can be devices connected to the target network (e.g., devices used by teachers or students connected to the target network).
[0039] Generally, the devices in the target organization are provided by the target organization. For example, when the target organization is a company, the multiple devices in the target organization may be office devices provided by the company to its employees.
[0040] In the embodiments of the present application, the devices may be of different types. For example, the devices may be computer devices (such as desktop computers, etc.), mobile devices (such as smart phones, tablet computers, smart wearable devices, etc.).
[0041] Operation information can be understood as information used to characterize the operation status of a device. In an embodiment of the present application, the operation information includes index values corresponding to multiple target performance indicators. In other words, the operation information is presented in the form of index values of multiple target performance indicators. One target performance indicator can measure the operation status of a device from one dimension.
[0042] In some possible implementations, the operating information may include at least one of the following: an indicator value corresponding to a target performance indicator related to the device's CPU, an indicator value corresponding to a target performance indicator related to the device's memory, an indicator value corresponding to a target performance indicator related to the device's hard disk, and an indicator value corresponding to a target performance indicator related to the device's battery.
[0043] That is to say, in the embodiment of the present application, target performance indicators related to different components of the device are set, and multi-dimensional detection is performed on the different components of the device in the form of multiple target performance indicators, so as to perform a multi-dimensional and comprehensive analysis of the operating status of the device.
[0044] For example, the target performance indicator related to the device's CPU may be the average CPU usage, the average daily maximum CPU usage, etc.; the target performance indicator related to the device's memory may be the average memory margin, the average daily minimum memory margin, etc.; the target performance indicator related to the device's hard disk may be the disk usage, etc.; the target performance indicator related to the device's battery may be the remaining power change rate, etc.
[0045] In specific implementation, data collection clients can be deployed in multiple devices, and the data collection clients can be used to collect performance data of the devices. In this case, the performance data of multiple devices in the target organization or target network sent by multiple data collection clients are received, and the performance data of the multiple devices are statistically calculated to generate the operation information of the multiple devices.
[0046] That is to say, in the embodiment of the present application, by deploying the data collection client on multiple devices within the target organization or in the target network, the data collection client can interact deeply with the devices, collect the performance data of the devices through system-level sensors and driver interfaces, and ensure the accuracy and real-time nature of data collection.
[0047] Among them, performance data can be understood as data that can be directly collected from the device. In an embodiment of the present application, performance data may include data related to different components such as CPU, memory, hard disk, battery, etc. For example, the data collection client can collect performance data such as CPU usage, CPU usage frequency, CPU temperature, etc. from the device, so as to subsequently evaluate the performance of the CPU under different workloads. For another example, the data collection client can collect performance data such as the total capacity of the memory, the available capacity of the memory, the read and write speed of the memory, etc. from the device, so as to fully understand the operating status of the memory. For another example, the data collection client can collect performance data such as the storage space of the hard disk, the read and write speed of the hard disk (including sequential read and write speed and random read and write speed), health status (such as bad track detection) from the device. For another example, the data collection client can collect performance data such as the remaining power of the battery, the number of charge and discharge times, the estimated battery life, and the degree of battery loss from the device.
[0048] In this way, the data collection client collects performance data in real time, integrates the collected performance data, encapsulates it into a standardized data format, and transmits it to the device management system through a secure and encrypted network transmission channel. In some embodiments, during the transmission process between the data collection client and the device management system, data compression technology is used to reduce network bandwidth usage, and at the same time, a data verification and retransmission mechanism is used to ensure the integrity and accuracy of the performance data.
[0049] After the device management system receives the performance data of multiple devices, it can perform statistical calculations on the performance data of the multiple devices to obtain the operation information of the multiple devices.
[0050] It is understandable that, since the operation information includes the index values corresponding to multiple target performance indicators, and the data collection client collects the original performance data, the device management system calculates the index value corresponding to the target performance indicator from the performance data. For example, when the target performance indicator is the average CPU usage, the device management system can calculate the average value of the CPU usage of each device collected by the data collection client to obtain the average CPU usage.
[0051] S102: Sending operation information of the plurality of devices to the target model, and receiving operation abnormality prediction probabilities corresponding to the plurality of devices respectively returned by the target model.
[0052] In an embodiment of the present application, a target model is used to perform a logistic regression analysis on the operating information of multiple devices to determine whether the multiple devices have any operating abnormalities.
[0053] The target model can be understood as a trained logistic regression model for classifying devices. The target model can output the predicted probability of abnormal operation of each device, which can characterize the possibility of abnormal operation of the device. In other words, the target model can determine the possibility of abnormal operation of the device based on the operation information of the device.
[0054] In the embodiment of the present application, considering the correlation between the target model and the target organization, the target model can be trained using data related to the devices in the target organization. Specifically, multiple first-category devices and multiple second-category devices in the target organization or target network are determined, and historical performance data of the multiple first-category devices and multiple second-category devices in a preset historical time period are obtained. The historical performance data is used to train a logistic regression model to obtain the target model.
[0055] Among them, the first type of equipment is equipment with abnormal operation, and the second type of equipment is equipment with normal operation. In other words, based on the feedback from the target organization on the use of work equipment, the equipment in the target organization is divided into the first type of equipment with performance problems and abnormal operation and the second type of equipment without performance problems and normal operation.
[0056] Next, obtain the historical performance data of the two types of equipment in the same historical time period, such as the historical performance data of the first type of equipment in the N days before the performance problem, and use the historical performance data of the two types of equipment to train the model and obtain the target model. In this way, combined with the actual situation of the target organization, such as the performance requirements of the target organization's business for the equipment, the historical performance data of the target organization's actual equipment is used to train the target model for managing the equipment in the target organization, improve the matching degree between the target organization and the target model, and improve the judgment accuracy of the target model for the equipment in the target organization.
[0057] In some possible implementations, the number of first-category devices in the target organization may be much larger than the number of second-category devices. In this case, in order to solve the problem of unbalanced data sets, the number of first-category devices can be reduced to make the category distribution of the data set more balanced. By under-sampling the first-category devices, the data set can be quickly balanced and the model training effect can be improved.
[0058] The following is an introduction to the specific training process of the target logistic regression model. In the specific implementation, first, statistical calculations are performed on the historical performance data to generate historical operation information of multiple first-category devices and multiple second-category devices. The historical operation information includes indicator values corresponding to multiple candidate performance indicators.
[0059] Candidate performance indicators can be understood as candidate performance indicators for the target model. That is, the target model can select one or more performance indicators from the candidate performance indicators as the final target performance indicators. During the reasoning process, the target model will use one or more target performance indicators selected from the candidate performance indicators as a basis to determine the predicted probability of abnormal operation of the equipment.
[0060] In some embodiments, the candidate performance indicators and the indicator definitions of the candidate performance indicators may be as shown in Table 1:
[0061] Table 1
[0062]
[0063] In this way, the historical performance data of each device is calculated to generate indicator values corresponding to multiple candidate performance indicators of each device, and the historical operation information is obtained.
[0064] Next, the historical operation information is divided into a training set and a validation set, and the multiple candidate performance indicators are divided into multiple performance indicator combinations.
[0065] The training set is used to train the logistic regression model, and the validation set is used to verify the inference effect of the trained logistic regression model. In some embodiments, the ratio of the training set to the validation set can be 8:2, that is, the historical operation information of 80% of the first and second category devices is used as the training set, and the historical operation information of the remaining 20% of the first and second category devices is used as the validation set.
[0066] The performance indicator combination is composed of at least one candidate performance indicator. That is, from multiple candidate performance indicators, possible performance indicator combinations are enumerated (for example, a performance indicator combination composed of any one candidate performance indicator, a performance indicator combination composed of any two candidate performance indicators, a performance indicator combination composed of any three candidate performance indicators, etc.).
[0067] In the embodiment of the present application, a performance indicator combination corresponds to a logistic regression model, and the logistic regression model uses the candidate performance indicators in the corresponding performance indicator combination to output the prediction probability of abnormal operation of the device. For example, the performance indicator combination A includes candidate performance indicator a and candidate performance indicator b. During the reasoning process, the logistic regression model corresponding to the performance indicator combination A performs a logistic regression analysis on the indicator value corresponding to the candidate performance indicator a of the device and the indicator value corresponding to the candidate performance indicator b, and outputs the prediction probability of abnormal operation of the device.
[0068] Specifically, for each performance indicator combination in the multiple performance indicator combinations, the following steps are performed: using the training set as training data, training the logistic regression model corresponding to the performance indicator combination, and using the validation set to determine the accuracy of the logistic regression model corresponding to the performance indicator combination.
[0069] In this way, the same training set is used to train logistic regression models corresponding to different performance indicator combinations, and the trained logistic regression models are applied to the same validation set respectively. Combined with the trained logistic regression model for the predicted probability of operational abnormality output by the equipment in the validation set and the label of the equipment in the validation set (i.e., first-category equipment or second-category equipment), it is determined whether the trained logistic regression model can accurately classify the equipment in the validation set into the corresponding label, and the accuracy of the logistic regression model is determined.
[0070] The candidate performance indicators included in the performance indicator combination with the highest degree of accuracy are determined as a plurality of target performance indicators, and the logistic regression model corresponding to the performance indicator combination with the highest degree of accuracy is determined as the target model.
[0071] For example, the accuracy of the logistic regression model corresponding to performance indicator combination A is 0.6, the accuracy of the logistic regression model corresponding to performance indicator combination B is 0.5, and the accuracy of the logistic regression model corresponding to performance indicator combination C is 0.8. The target model is the logistic regression model corresponding to performance indicator combination C, and the multiple target performance indicators are candidate performance indicators included in performance indicator combination C.
[0072] In this way, by training the logistic regression models corresponding to different performance indicator combinations respectively, the performance indicator combination with the highest reasoning accuracy is determined, and this performance indicator combination is used as the final multiple target performance indicators. The logistic regression model corresponding to this performance indicator combination is used to determine the target model with the best reasoning performance.
[0073] In some possible implementations, considering that the operating conditions of different types of devices can be characterized by different performance indicators, for example, the operating conditions of devices using different operating systems can be characterized by different performance indicators, therefore, the embodiment of the present application can also distinguish the first type of devices from the second type of devices according to the device type, and perform model training for devices of different types of devices respectively to obtain target models of devices of different types of devices. In this way, in the actual application process, the operating information of devices of different types of devices is input into the target model corresponding to the device type, so as to achieve more accurate classification of the device operating conditions.
[0074] Furthermore, after a set time period, a plurality of first-category devices and a plurality of second-category devices in the target organization or the target network are re-determined, and historical performance data are re-acquired, and the target model is updated using the re-acquired historical performance data.
[0075] That is to say, in the embodiment of the present application, the data set is updated regularly, the model parameters of the target model are optimized regularly, and the target model is dynamically adjusted according to the actual situation of the target organization to ensure the accuracy and adaptability of the equipment management.
[0076] S103: Determine at least one target device with an operation abnormality among the multiple devices according to the predicted probability of the operation abnormality.
[0077] In actual application, the operation information of multiple devices is respectively input into the target model, and the operation abnormality prediction probability of each device output by the target model is received. Based on the operation abnormality prediction probability of each device, the target device with operation abnormality is determined.
[0078] In a specific implementation, at least one device whose predicted probability of operation abnormality is greater than a probability threshold is determined as a target device of operation abnormality.
[0079] The probability threshold is determined in the following manner: respectively obtaining the operation anomaly prediction probability of the validation set of the target model under the target model, sorting the operation anomaly prediction probability of the validation set under the target model from low to high, determining the operation anomaly prediction probability corresponding to the set quantile, and determining the operation anomaly prediction probability corresponding to the set quantile as the probability threshold.
[0080] That is to say, since the target model outputs the possibility of characterizing device abnormal operation, it is necessary to set a probability threshold (also called a baseline) to identify devices whose possibility of characterizing device abnormal operation is greater than the probability threshold as target devices with abnormal operation.
[0081] In an embodiment of the present application, a probability threshold is determined based on a data quantile. By excluding a portion of the validation set with a low probability of prediction of anomaly output when the validation set is applied to the target model, the probability threshold is set to the probability of prediction of anomaly corresponding to a higher quantile.
[0082] For example, the quantile is set to 75%, and after the prediction probability of abnormal operation of the validation set under the target model is sorted from low to high, the devices in the validation set that are in the 75% are determined, and the prediction probability of abnormal operation of the devices in the validation set that are in the 75% are determined as the probability threshold (for example, 0.6). In this way, in actual applications, after the operation information of multiple devices is input into the target model, the device whose prediction probability of abnormal operation output by the target model is greater than 0.6 is determined as the target device.
[0083] S104: Send a prompt message to a target user associated with at least one target device.
[0084] The prompt message is used to inform the target user that the target device is operating abnormally, or the prompt message user informs the target user that the target device is operating abnormally and the corresponding solution. For example, the target user may be a member of an organization that uses the target device. In this way, for the target device that is operating abnormally, the target user is informed of the operating status of the target device in a timely manner.
[0085] In some possible implementations, the device management system can be integrated with an office platform. The office platform usually includes multiple different functional modules, such as an instant messaging module, a schedule module, a video conferencing module, etc. In the embodiment of the present application, by integrating the device management system with the office platform, prompt messages are sent in the office platform (for example, the instant messaging module in the office platform) to achieve convenient message reminders and interactive functions.
[0086] In an embodiment of the present application, the prompt message sent to the target user may include rich content. Specifically, a prompt message including at least one of the following items is sent to the target user associated with at least one target device: information for characterizing an abnormal performance indicator that generates an abnormality, information for optimizing an indicator value corresponding to the abnormal performance indicator, process information for replacing the target device, guidance information for interacting with an offline IT site, and information related to IT operation and maintenance.
[0087] The information of the abnormal performance indicator used to characterize the abnormality can be understood as detailed information of the abnormal performance indicator, for example, including the indicator value corresponding to the abnormal performance indicator and the impact that the abnormal performance indicator may have on the device.
[0088] The information used to optimize the indicator value corresponding to the abnormal performance indicator can be understood as a solution to the abnormal operation of the target device. In some embodiments, the device management system can filter out solutions related to the abnormal performance indicator from a pre-established solution library, and the solutions can be provided in the form of operation guides. For example, the solutions may include operation guides such as optimizing the system settings of the device (such as closing unnecessary background programs, adjusting virtual memory settings, etc.), cleaning up system junk files, and updating drivers, so that the target members can implement them by themselves.
[0089] The process information for replacing the target device can be understood as the guidance information of the device replacement process. In some embodiments, the prompt message can also provide an entry for device replacement. The target user can trigger the entry for device replacement in the prompt message to enter the device replacement application page of the target organization and make a quick device replacement application. In addition, the device management system can also recommend a suitable device model for the replacement device to the target user.
[0090] The guidance information for interacting with offline IT sites can be understood as guidance information for offline IT operation and maintenance. Typically, the target organization sets up an offline IT operation and maintenance service desk, which is equipped with IT operation and maintenance personnel to provide offline IT operation and maintenance services to members of the organization. In an embodiment of the present application, the prompt message may include guidance information for offline IT operation and maintenance, such as the geographical location, service hours, and estimated service duration of the offline IT operation and maintenance service desk. In addition, the prompt message may also include a reservation control for making an appointment for offline IT operation and maintenance services. The target members can quickly make an appointment for offline IT operation and maintenance services by triggering the reservation control in the prompt message, thereby improving service efficiency.
[0091] Information related to IT operation and maintenance can be understood as interactive information for interacting with IT operation and maintenance personnel. In some embodiments, the prompt message includes an IT operation and maintenance control, and the target user can establish an instant messaging dialogue with the IT operation and maintenance member by triggering the IT operation and maintenance control in the prompt message to conduct online consultation on the target IT equipment.
[0092] Furthermore, the prompt message can also provide a feedback entry, and the target user can also provide feedback on the prompt message, such as whether the device is operating abnormally, the richness of the content of the prompt message, etc., so as to optimize the target model and the content contained in the prompt message.
[0093] In some embodiments, the device management system can also perform visual management on the operating conditions of multiple devices. Specifically, based on the operating information of multiple devices in the target organization or target network, the operating statistics of multiple devices are generated and presented in the form of charts.
[0094] By presenting the operation statistics in the form of charts, equipment managers can fully and intuitively understand the overall performance status of the equipment in the target organization or target network. Specifically, presenting the operation statistics in the form of charts can include at least one of the following: presenting the distribution of indicator values corresponding to multiple target performance indicators in the form of charts, presenting the change trend of indicator values corresponding to multiple target performance indicators in the form of charts, and presenting the operation statistics related to the target equipment in the form of charts. In this way, the distribution of equipment in the target organization under different target performance indicators, historical change trends, and the number and proportion of abnormally operating equipment can be intuitively counted.
[0095] Furthermore, a filtering operation for the running statistical results may be received, and the running statistical results may be filtered according to the filtering operation, and the filtered running statistical results may be presented in the form of a chart.
[0096] The filtering operation is used to filter from at least one of the following dimensions: the department of the user associated with the device, the office area of the user associated with the device, and the device type. In this way, the equipment manager can also filter the operation statistics results according to the organizational department, office area, device type and other dimensions of the target organization, so as to formulate targeted equipment management strategies and resource allocation plans, which will help the target organization to plan equipment updates or maintenance in advance, arrange equipment resources reasonably, extend the service life of equipment, and reduce equipment management costs.
[0097] In addition, the equipment manager can also configure and adjust the model parameters of the target model in the equipment management system, for example, setting the weights of different performance indicators in combination with the business needs of the target organization. At the same time, the equipment manager can also manage the solution library, add, delete or modify the solutions in the solution library to ensure the effectiveness and timeliness of the prompt messages sent to the target users. In addition, the equipment manager can also set the prompt message push rules in the equipment management system, such as setting the prompt message sending frequency, etc., to meet the diverse equipment management needs of the target organization.
[0098] In this method, a unified detection is performed on multiple working devices within the organization. By obtaining the operation information of the devices, the operation status of the devices is determined from the dimensions of multiple performance indicators. If the device is determined to be operating abnormally, the user is informed in the form of a prompt message. In this way, dynamic detection and management of devices at the organizational level is achieved, and the efficiency of IT services within the organization is improved.
[0099] In an embodiment of the present application, the performance data of the devices is collected by deploying a data collection client on multiple devices in a target organization or a target network. The specific implementation of the data collection client is described below.
[0100] In the data collection client, you can set up scheduled data collection tasks, for example, automatically triggering data collection tasks every 30 minutes to collect performance data from the device. In the process of executing data collection tasks, the data collection client collects performance data (also called facts) on the device through the system application programming interface (API) and command line, organizes, formats and compresses the performance data, and transmits the performance data to the device management system through the mutual TLS (mTLS) protocol to improve transmission efficiency and save bandwidth.
[0101] The equipment management system may include a data center, which parses the performance data, converts it into a processable standard format, and stores the parsed performance data in a database. Equipment management is achieved by obtaining performance data from the data center, generating operation information, and using the target model to identify target equipment with abnormal operation.
[0102] See also Figure 2 The schematic diagram of the architecture of a data acquisition client shown in the figure is divided into an application layer and a service layer. The application layer includes a user notification module and a user interaction model. The user notification module is used to send notifications to the device, and the user interaction module is used to update prompts and operations, pull configurations, etc. The service layer includes a network communication module, a data storage module, a data acquisition module, a configuration application module, a resource provision module, a remote script module and a peripheral control module. The network communication module is used to communicate with the device management system to ensure data synchronization, heartbeat maintenance and command response. The data storage module is used to locally persist and update the operation data during the data acquisition exchangeable operation process. The data acquisition module is used to transmit the collected performance data to the device management system to realize the configuration generation of the current node. The configuration application module is used to configure the application according to the generated node configuration. The resource provision module is used to parse each resource in the configuration application, obtain the attributes or behaviors of the resource, and realize resource alignment. The remote script module is used to run remote command lines and remote scripts. The peripheral control module is used to provide peripheral control capabilities through the system API.
[0103] Combination of the above Figure 1 and Figure 2 The management method of the work equipment provided in the embodiment of the present application is introduced in detail. The following will introduce the device and equipment provided in the embodiment of the present application in conjunction with the accompanying drawings.
[0104] See also Figure 3 The schematic diagram of the structure of the management device of the working equipment shown in FIG. 30 includes:
[0105] The acquisition module 301 is used to acquire the operation information of multiple devices in the target organization or the target network; wherein the operation information includes the indicator values corresponding to the multiple target performance indicators;
[0106] The communication module 302 is used to obtain the operation information of multiple devices in the target organization or the target network; wherein the operation information includes the indicator values corresponding to the multiple target performance indicators;
[0107] A determination module 303 is used to determine at least one target device with an operation abnormality among the multiple devices according to the operation abnormality prediction probability;
[0108] The prompt module 304 is used to send a prompt message to a target user associated with the at least one target device; wherein the prompt message is used to inform the target user that the target device is operating abnormally, or to inform the target user that the target device is operating abnormally and a corresponding solution.
[0109] In some possible implementations, the target model is a logistic regression model, and the apparatus 30 further includes a training module, wherein the training module is used to:
[0110] Determine a plurality of first-category devices and a plurality of second-category devices in the target organization or the target network; wherein the first-category devices are devices that operate abnormally, and the second-category devices are devices that operate normally;
[0111] Acquire historical performance data of a plurality of the first-category devices and a plurality of the second-category devices within a preset historical time period;
[0112] The historical performance data is used to train a logistic regression model to obtain the target model.
[0113] In some possible implementations, the training module is specifically used to:
[0114] Performing statistical calculations on the historical performance data to generate historical operation information of a plurality of the first-category IT devices and a plurality of the second-category IT devices; wherein the historical operation information includes indicator values corresponding to a plurality of candidate performance indicators;
[0115] Dividing the historical operation information into a training set and a validation set, and dividing the multiple candidate performance indicators into multiple performance indicator combinations; wherein the performance indicator combination is composed of at least one candidate performance indicator;
[0116] For each performance indicator combination in the multiple performance indicator combinations, the following steps are performed: using the training set as training data to train a logistic regression model corresponding to the performance indicator combination; using the validation set to determine the accuracy of the logistic regression model corresponding to the performance indicator combination;
[0117] The candidate performance indicators included in the performance indicator combination with the highest degree of accuracy are determined as the multiple target performance indicators, and the logistic regression model corresponding to the performance indicator combination with the highest degree of accuracy is determined as the target model.
[0118] In some possible implementations, the training module is further used to:
[0119] After a set time period, re-determine a plurality of first-category devices and a plurality of second-category devices in the target organization or the target network, and re-acquire the historical performance data;
[0120] The target model is updated using the retrieved historical performance data.
[0121] In some possible implementations, the determining module 303 is specifically configured to:
[0122] Determine at least one device whose predicted probability of operation abnormality is greater than a probability threshold as a target device with operation abnormality;
[0123] The probability threshold is determined in the following way:
[0124] Respectively obtain the prediction probability of operation anomaly of the validation set of the target model under the target model;
[0125] Sorting the operation abnormality prediction probability of the validation set under the target model from low to high, and determining the operation abnormality prediction probability corresponding to the set quantile;
[0126] The predicted probability of operational abnormality corresponding to the set quantile is determined as a probability threshold.
[0127] In some possible implementations, a data collection client is deployed in the multiple devices, and the data collection client is used to collect performance data of the devices; the acquisition module 301 is specifically used to:
[0128] Receiving performance data of a plurality of devices in a target organization or a target network sent by a plurality of the data collection clients;
[0129] Statistical calculation is performed on the performance data of the multiple devices to generate operation information of the multiple devices.
[0130] In some possible implementations, the operation information includes at least one of the following:
[0131] An indicator value corresponding to a performance indicator related to a central processing unit (CPU) of the device;
[0132] an indicator value corresponding to a performance indicator related to the memory of the device;
[0133] an indicator value corresponding to a performance indicator related to a hard disk of the device;
[0134] An indicator value corresponding to a performance indicator related to the battery of the device.
[0135] In some possible implementations, the prompt module 304 is specifically used to:
[0136] A prompt message including at least one of the following is sent to a target user associated with the at least one target device: information for characterizing an abnormal performance indicator that generates an abnormality; information for optimizing an indicator value corresponding to the abnormal performance indicator; process information for replacing the target device; guidance information for interacting with an offline IT site; and information related to IT operation and maintenance.
[0137] In some possible implementations, the apparatus 30 further includes a presentation module, and the presentation module is configured to:
[0138] Generate operation statistics of the plurality of devices according to the operation information of the plurality of devices in the target organization or the target network;
[0139] The running statistical results are presented in the form of charts.
[0140] In some possible implementations, the presentation module is specifically used to:
[0141] Presenting the distribution of the indicator values corresponding to the multiple target performance indicators in the form of a chart;
[0142] Presenting the changing trends of the indicator values corresponding to the multiple target performance indicators in the form of a chart;
[0143] The operation statistics related to the target device are presented in the form of a chart.
[0144] In some possible implementations, the presentation module is further configured to:
[0145] receiving a filtering operation for the running statistical result, wherein the filtering operation is used to filter from at least one of the following dimensions: a department where a user associated with a device is located, an office area where the user associated with the device is located, and a device type;
[0146] According to the screening operation, the running statistical results are screened;
[0147] The operation statistical results after screening are presented in the form of charts.
[0148] The management device 30 of the working equipment according to the embodiment of the present application may correspond to the method described in the embodiment of the present application, and the above and other operations and / or functions of each module / unit of the management device 30 of the working equipment are respectively to achieve Figure 1 For the sake of brevity, the corresponding processes of each method in the illustrated embodiment are not described in detail here.
[0149] The present application also provides an electronic device. The electronic device is specifically used to implement Figure 3 The functions of the management device 30 for working equipment in the embodiment shown.
[0150] Figure 4 A schematic diagram of the structure of an electronic device 400 is provided. Figure 4 As shown, the electronic device 400 includes a bus 401, a processor 402, a communication interface 403 and a memory 404. The processor 402, the memory 404 and the communication interface 403 communicate with each other via the bus 401.
[0151] The bus 401 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0152] The processor 402 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).
[0153] The communication interface 403 is used for communicating with the outside. For example, the communication interface 403 can be used for communicating with a terminal.
[0154] The memory 404 may include a volatile memory, such as a random access memory (RAM). The memory 404 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).
[0155] The memory 404 stores executable codes, and the processor 402 executes the executable codes to perform the aforementioned method for managing work equipment.
[0156] Specifically, in implementing Figure 3 In the case of the embodiment shown, and Figure 3 When each module or unit of the management device 30 for working equipment described in the embodiment is implemented by software, Figure 3 The software or program code required for the functions of each module / unit in the system may be partially or completely stored in the memory 404. The processor 402 executes the program code corresponding to each unit stored in the memory 404 to execute the aforementioned management method for working equipment.
[0157] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by the computing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute the management method for work equipment of the management device 30 applied to the work equipment.
[0158] The embodiment of the present application further provides a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the process or function described in the embodiment of the present application is generated in whole or in part.
[0159] The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer or data center to another website, computer or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means.
[0160] When the computer program product is executed by a computer, the computer executes any of the aforementioned methods for managing work equipment. The computer program product may be a software installation package, and when any of the aforementioned methods for managing work equipment is needed, the computer program product may be downloaded and executed on a computer.
[0161] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to each embodiment of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0162] The units involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the unit / module does not, in some cases, constitute a limitation on the unit itself.
[0163] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0164] In the context of the present application embodiment, machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable medium can include but is not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the above. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.
[0165] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the system or device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0166] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0167] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0168] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
[0169] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for managing work equipment, characterized in that: The method comprises: Obtaining operation information of multiple devices in a target organization or a target network; wherein the operation information includes indicator values corresponding to multiple target performance indicators; Sending the operation information of the multiple devices to the target model, and receiving the operation abnormality prediction probabilities corresponding to the multiple devices respectively returned by the target model; Determining at least one target device with an abnormal operation among the multiple devices according to the predicted probability of abnormal operation; A prompt message is sent to a target user associated with the at least one target device; wherein the prompt message is used to inform the target user that the target device is operating abnormally, or to inform the target user that the target device is operating abnormally and a corresponding solution.
2. The method according to claim 1, characterized in that The target model is a logistic regression model, which is trained in the following way: Determine a plurality of first-category devices and a plurality of second-category devices in the target organization or the target network; wherein the first-category devices are devices that operate abnormally, and the second-category devices are devices that operate normally; Obtaining historical performance data of a plurality of the first-category devices and a plurality of the second-category devices within a preset historical time period; The historical performance data is used to train a logistic regression model to obtain the target model.
3. The method according to claim 2, characterized in that The using the historical performance data to train a logistic regression model to obtain the target model includes: Performing statistical calculations on the historical performance data to generate historical operation information of a plurality of the first-category IT devices and a plurality of the second-category IT devices; wherein the historical operation information includes indicator values corresponding to a plurality of candidate performance indicators; Dividing the historical operation information into a training set and a validation set, and dividing the multiple candidate performance indicators into multiple performance indicator combinations; wherein the performance indicator combination is composed of at least one candidate performance indicator; For each performance indicator combination in the multiple performance indicator combinations, the following steps are performed: using the training set as training data to train a logistic regression model corresponding to the performance indicator combination; using the validation set to determine the accuracy of the logistic regression model corresponding to the performance indicator combination; The candidate performance indicators included in the performance indicator combination with the highest degree of accuracy are determined as the multiple target performance indicators, and the logistic regression model corresponding to the performance indicator combination with the highest degree of accuracy is determined as the target model.
4. The method according to claim 2, characterized in that: The method further comprises: After a set time period, re-determine a plurality of first-category devices and a plurality of second-category devices in the target organization or the target network, and re-acquire the historical performance data; The target model is updated using the reacquired historical performance data.
5. The method according to claim 1, characterized in that The step of determining at least one target device with an operation abnormality among the multiple devices according to the operation abnormality prediction probability includes: Determine at least one device whose predicted probability of operation abnormality is greater than a probability threshold as a target device with operation abnormality; The probability threshold is determined in the following way: Respectively obtain the prediction probability of operation anomaly of the validation set of the target model under the target model; Sorting the operation abnormality prediction probability of the validation set under the target model from low to high, and determining the operation abnormality prediction probability corresponding to the set quantile; The predicted probability of operational abnormality corresponding to the set quantile is determined as a probability threshold.
6. The method according to claim 1, characterized in that A data collection client is deployed in the multiple devices, and the data collection client is used to collect performance data of the devices; The obtaining of operation information of multiple devices in a target organization or a target network includes: Receiving performance data of a plurality of devices in a target organization or a target network sent by a plurality of the data collection clients; Statistical calculation is performed on the performance data of the multiple devices to generate operation information of the multiple devices.
7. The method according to claim 1, characterized in that The operation information includes at least one of the following: An indicator value corresponding to a performance indicator related to a central processing unit (CPU) of the device; an indicator value corresponding to a performance indicator related to the memory of the device; an indicator value corresponding to a performance indicator related to a hard disk of the device; An indicator value corresponding to a performance indicator related to the battery of the device.
8. The method according to claim 1, characterized in that The sending a prompt message to a target user associated with the at least one target device includes: A prompt message including at least one of the following is sent to a target user associated with the at least one target device: information for characterizing an abnormal performance indicator that generates an abnormality; information for optimizing an indicator value corresponding to the abnormal performance indicator; process information for replacing the target device; guidance information for interacting with an offline IT site; and information related to IT operation and maintenance.
9. The method according to any one of claims 1 to 8, characterized in that: The method further comprises: Generate operation statistics of the plurality of devices according to the operation information of the plurality of devices in the target organization or the target network; The running statistical results are presented in the form of charts.
10. The method according to claim 9, characterized in that The presenting of the operation statistical results in the form of a chart includes at least one of the following: Presenting the distribution of the indicator values corresponding to the multiple target performance indicators in the form of a chart; Presenting the changing trends of the indicator values corresponding to the multiple target performance indicators in the form of a chart; The operation statistics related to the target device are presented in the form of a chart.
11. The method according to claim 9, characterized in that The method further comprises: receiving a filtering operation for the running statistical result, wherein the filtering operation is used to filter from at least one of the following dimensions: a department where a user associated with a device is located, an office area where the user associated with the device is located, and a device type; According to the screening operation, the running statistical results are screened; The operation statistical results after screening are presented in the form of charts.
12. A management device for working equipment, characterized in that: The device comprises: An acquisition module, used to acquire operation information of multiple devices in a target organization or a target network; wherein the operation information includes indicator values corresponding to multiple target performance indicators; A communication module, used to obtain operation information of multiple devices in a target organization or a target network; wherein the operation information includes indicator values corresponding to multiple target performance indicators; A determination module, configured to determine at least one target device with an operation abnormality among the multiple devices according to the predicted probability of the operation abnormality; A prompt module is used to send a prompt message to a target user associated with the at least one target device; wherein the prompt message is used to inform the target user that the target device is operating abnormally, or to inform the target user that the target device is operating abnormally and a corresponding solution.
13. An electronic device, characterized in that: The electronic device comprises a processor and a memory; The processor is configured to execute instructions stored in the memory, so that the electronic device performs the method according to any one of claims 1 to 11.
14. A computer-readable storage medium, characterized in that: The method comprises instructions, wherein the instructions instruct an electronic device to execute the method according to any one of claims 1 to 11.
15. A computer program product, characterized in that The computer program product comprises computer readable instructions for implementing the method according to any one of claims 1 to 11.