Asset management method and device, equipment, storage medium and computer program product

Abstract

The invention discloses an asset management method and device, equipment, a storage medium and a computer program product, which are used for solving the problems that a maintenance decision depends on artificial experience, the asset utilization rate is low and fault response is lagged due to the fact that prediction logic cannot be optimized through autonomous learning when an existing asset management method is used for multi-type assets and multi-dimensional state data. The method comprises the steps of receiving asset information corresponding to a to-be-managed device; monitoring to-be-managed equipment according to the equipment basic information to obtain use data corresponding to the to-be-managed equipment; determining a use mode corresponding to the to-be-managed equipment according to the use data; according to the use mode and the asset information, based on a pre-trained asset prediction model, performing asset use prediction to obtain a use state prediction result corresponding to the to-be-managed device; and determining an asset management strategy corresponding to the to-be-managed equipment according to the use state prediction result.

Description

Technical Field

[0001] This application relates to the field of digital asset management technology, and in particular to an asset management method, apparatus, device, storage medium, and computer program product. Background Technology

[0002] As enterprises accelerate their digital transformation, the continuous expansion of asset scale and types places higher demands on the intelligence level of asset management systems. Currently, mainstream asset management systems on the market have evolved into comprehensive platforms integrating data entry, status monitoring, and basic reporting functions. However, such systems generally suffer from the following core defects: their AI technology applications are mostly superficial—although simple statistical models or rule engines are introduced, they do not deeply integrate deep learning algorithms to perform pattern mining on the full range of asset data; data flow between functional modules is fragmented, making it difficult to form a closed-loop optimization of "data collection-analysis-decision-execution"; especially when facing multi-type assets and multi-dimensional status data, they cannot optimize predictive logic through autonomous learning, leading to problems such as maintenance decisions relying on human experience, low asset utilization, and delayed fault response.

[0003] Specifically, the AI ​​analysis capabilities of existing systems can only support basic trend fitting and cannot extract implicit usage patterns from massive amounts of heterogeneous data to build adaptive predictive models. Furthermore, there is a lack of collaboration mechanisms between modules; for example, real-time location data acquired by the asset tracking module is not effectively input into the predictive maintenance module, leading to a disconnect between maintenance plans and the actual state of assets. These shortcomings make it difficult for enterprises to achieve their core goals of cost reduction and efficiency improvement through asset management systems.

[0004] Therefore, there is an urgent need for an asset information statistics and management system based on deep AI collaboration. By strengthening the data linkage and deep learning analysis capabilities between modules, this system can solve the core problems of "shallow AI application and fragmented module collaboration" in traditional systems, and achieve full-process optimization from data collection to intelligent decision-making. Summary of the Invention

[0005] This application provides an asset management method to address the problems of existing asset management methods being unable to optimize prediction logic through autonomous learning when faced with multi-type assets and multi-dimensional status data, resulting in maintenance decisions relying on human experience, low asset utilization, and delayed fault response.

[0006] This application also provides an asset management device to solve the problems of existing asset management methods being unable to optimize prediction logic through autonomous learning when faced with multi-type assets and multi-dimensional status data, resulting in maintenance decisions relying on human experience, low asset utilization, and delayed fault response.

[0007] This application also provides an asset management device to solve the problems of existing asset management methods being unable to optimize prediction logic through autonomous learning when faced with multi-type assets and multi-dimensional status data, resulting in maintenance decisions relying on human experience, low asset utilization, and delayed fault response.

[0008] This application also provides a computer-readable storage medium to address the problems of existing asset management methods being unable to optimize prediction logic through autonomous learning when faced with multi-type assets and multi-dimensional status data, resulting in maintenance decisions relying on human experience, low asset utilization, and delayed fault response.

[0009] A computer program product is designed to address the problems of existing asset management methods being unable to optimize predictive logic through autonomous learning when faced with multi-type assets and multi-dimensional status data. This results in maintenance decisions relying on human experience, low asset utilization, and delayed fault response.

[0010] The embodiments of this application adopt the following technical solutions: An asset management method includes: receiving asset information corresponding to a device to be managed, wherein the asset information includes basic device information, device status information, and historical maintenance data of the device; monitoring the device to be managed based on the basic device information to obtain usage data corresponding to the device to be managed; determining the usage mode corresponding to the device to be managed based on the usage data; predicting asset usage based on the usage mode and the asset information using a pre-trained asset prediction model to obtain a usage status prediction result corresponding to the device to be managed; and determining an asset management strategy corresponding to the device to be managed based on the usage status prediction result.

[0011] An asset management device includes: an asset information acquisition unit for receiving asset information corresponding to a device to be managed, wherein the asset information includes basic device information, device status information, and historical maintenance data of the device; a monitoring unit for monitoring the device to be managed based on the basic device information to obtain usage data corresponding to the device to be managed; a usage mode determination unit for determining the usage mode corresponding to the device to be managed based on the usage data; a prediction unit for predicting asset usage based on the usage mode and the asset information, using a pre-trained asset prediction model, to obtain a usage status prediction result corresponding to the device to be managed; and a management strategy determination unit for determining an asset management strategy corresponding to the device to be managed based on the usage status prediction result.

[0012] An asset management device, comprising: A processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the following operations: receiving asset information corresponding to a device to be managed, wherein the asset information includes basic device information, device status information, and historical maintenance data of the device; monitoring the device to be managed based on the basic device information to obtain usage data corresponding to the device to be managed; determining the usage pattern corresponding to the device to be managed based on the usage data; predicting asset usage based on the usage pattern and the asset information using a pre-trained asset prediction model to obtain a usage status prediction result corresponding to the device to be managed; and determining an asset management strategy corresponding to the device to be managed based on the usage status prediction result.

[0013] A computer-readable storage medium stores one or more programs that, when executed by an electronic device including multiple applications, cause the electronic device to perform the following operations: receiving asset information corresponding to a device to be managed, wherein the asset information includes basic device information, device status information, and historical maintenance data of the device; monitoring the device to be managed based on the basic device information to obtain usage data corresponding to the device to be managed; determining a usage pattern corresponding to the device to be managed based on the usage data; predicting asset usage based on the usage pattern and the asset information using a pre-trained asset prediction model to obtain a usage status prediction result corresponding to the device to be managed; and determining an asset management strategy corresponding to the device to be managed based on the usage status prediction result.

[0014] A computer program product includes a computer program that, when executed by a processor, performs the following: receiving asset information corresponding to a device to be managed, wherein the asset information includes basic device information, device status information, and historical maintenance data of the device; monitoring the device to be managed based on the basic device information to obtain usage data corresponding to the device to be managed; determining the usage pattern corresponding to the device to be managed based on the usage data; predicting asset usage based on the usage pattern and the asset information using a pre-trained asset prediction model to obtain a usage status prediction result corresponding to the device to be managed; and determining an asset management strategy corresponding to the device to be managed based on the usage status prediction result.

[0015] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: Using the asset management method provided in this application embodiment, when asset planning is required, the method first receives asset information corresponding to the equipment to be managed, wherein the asset information includes basic equipment information, equipment status information, and historical maintenance data of the equipment; based on the basic equipment information, the equipment to be managed is monitored to obtain usage data corresponding to the equipment to be managed; based on the usage data, the usage mode corresponding to the equipment to be managed is determined; based on the usage mode and the asset information, asset usage prediction is performed based on a pre-trained asset prediction model to obtain the usage status prediction result corresponding to the equipment to be managed; based on the usage status prediction result, the asset management strategy corresponding to the equipment to be managed is determined. The asset management method provided in this application has several advantages. First, it allows for proactive monitoring of equipment based on basic equipment information. The system automatically and continuously collects multi-dimensional dynamic usage data, solving the problems of delayed data updates and coarse granularity caused by traditional reliance on manual data entry or periodic inspections. This also provides real-time and accurate data support for subsequent in-depth analysis. Second, by analyzing the collected usage data, this method determines the equipment's usage patterns and proactively uncovers inherent patterns and typical or abnormal modes in the equipment's operating cycle, load characteristics, and operating habits. This allows for accurate determination of asset usage and precise asset prediction based on the usage status. Finally, by combining the identified usage patterns with comprehensive historical asset information and using a pre-trained prediction model, the asset management method provided in this application can proactively warn of potential failure risks and predict remaining service life or performance degradation trends. This provides a scientific and quantitative basis for preventative maintenance and resource planning, effectively reducing the risk of unexpected downtime. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This application provides a schematic diagram of a specific process for an asset management method. Figure 2 A schematic diagram of the specific structure of an asset management device provided in this application embodiment; Figure 3 This is a schematic diagram of the specific structure of an asset management device provided in an embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] This application provides an asset management method to address the problems of existing asset management methods being unable to optimize prediction logic through autonomous learning when faced with multi-type assets and multi-dimensional status data, resulting in maintenance decisions relying on human experience, low asset utilization, and delayed fault response.

[0019] The execution subject of the asset management method provided in this application embodiment may be, but is not limited to, at least one of an asset management server, a business server, and an asset server; in addition, the execution subject of the method may also be the system or application (APP) itself running on these servers.

[0020] For ease of description, the following description uses an asset management system as an example to illustrate the implementation of this method. It should be understood that using an asset management system as the implementing entity is merely an illustrative example and should not be construed as a limitation on the method.

[0021] The schematic diagram illustrating the specific implementation process of the asset management method provided in this application is as follows: Figure 1 As shown, the main steps include the following: Step 11: Receive asset information corresponding to the equipment to be managed, wherein the asset information includes basic equipment information, equipment status information and historical maintenance data of the equipment; In this embodiment, the asset management system can receive full asset information of the managed devices through a user interface, such as a web interface or API interface, or by synchronizing from other business systems. This asset information constitutes the device's knowledge graph and full lifecycle record. In one implementation, the asset information obtained by the asset management system may include, but is not limited to, the following: 1. Basic equipment information: including but not limited to static attributes such as equipment unique identifier (ID), name, model, serial number, supplier, purchase date, original value, department, and installation location.

[0022] 2. Equipment status information: refers to the latest status of the equipment, such as whether it is running, shut down, under maintenance, the current user department or responsible person, and the latest health score.

[0023] 3. Equipment historical maintenance data: This refers to a complete record of past maintenance, repair, inspection, calibration, and other activities performed on the equipment. Each record should include at least the maintenance time, maintenance type, maintenance content, replaced parts, time spent, cost, and post-maintenance status.

[0024] The asset management system can store the acquired asset information in a structured asset database, serving as the data foundation for all subsequent analyses.

[0025] Step 12: Monitor the device to be managed based on the basic device information to obtain the usage data corresponding to the device to be managed; In one implementation, the asset management system can activate or configure corresponding monitoring methods based on basic equipment information (such as equipment ID, type, and location) to continuously collect its runtime data.

[0026] In this embodiment of the application, the usage data obtained by the asset management system is real-time or near real-time dynamic information, which may include, but is not limited to, the following: 1. Operating parameter data: collected through the device's sensors or monitoring agents, such as CPU / memory usage, temperature, pressure, flow rate, energy consumption, and operating time.

[0027] 2. Geographic location and movement trajectory data: For movable assets, by integrating GPS modules or indoor positioning technologies such as radio frequency identification (RFID) and ultra-wideband (UWB), the geographic coordinates of the equipment or its specific location within the factory area can be obtained in real time, and its movement trajectory can be recorded.

[0028] 3. Usage frequency and duration data: By recording the device's power on / off events, operation logs, or the number of interface calls, we can statistically analyze its daily / weekly / monthly usage frequency, single continuous working duration, and cumulative working time.

[0029] 4. External environment data: Specifically, the asset management system can use data about the environment in which the equipment is located, such as temperature, humidity, and air quality, as auxiliary factors for equipment status analysis.

[0030] In this embodiment of the application, the asset management system can transmit the collected usage data to the system's data entry and management module in real time through an Internet of Things (IoT) gateway or data bus, and store it according to the time sequence.

[0031] Step 13: Determine the usage mode corresponding to the device to be managed based on the usage data obtained by performing Step 12; In one implementation, the asset management system may determine the usage mode corresponding to the equipment to be managed by following the sub-steps: Sub-step 1301: Preprocess the usage data obtained by executing step 12 to obtain the first usage data; In this embodiment of the application, the asset management system can preprocess the collected usage data in the following ways, including: 1. Data cleaning: Remove obviously erroneous outliers and process missing values ​​using interpolation methods (such as linear interpolation or imputation based on the average value of similar devices).

[0032] 2. Data standardization / normalization: Transform data of different dimensions (e.g., temperature, pressure, energy consumption) to the same scale, such as by using Z-score standardization or Min-Max normalization, to provide good input for subsequent machine learning algorithms.

[0033] It should be noted that the embodiments of this application do not specifically limit the method used to preprocess the collected usage data.

[0034] Sub-step 1302: Based on the first usage data obtained after preprocessing by executing sub-step 1301, a machine learning algorithm is used to identify usage patterns in order to determine the usage patterns of the device to be managed.

[0035] It should be noted that, in this embodiment of the application, the asset management system can identify usage patterns using the following two machine learning algorithms: Type 1, usage pattern recognition based on supervised learning: Specifically, the asset management system can train an SVM classifier using historical labeled data, finding an optimal hyperplane that maximizes the margin between the two classes of data points. The objective function follows the maximum margin principle, with parameters including a penalty parameter C to control the weights of misclassification and the kernel function parameter σ of the radial basis function. The trained model can then be used to automatically classify real-time data into predefined patterns.

[0036] Type 2, usage pattern recognition based on unsupervised learning: Specifically, unsupervised learning algorithms can automatically aggregate data points into K clusters, maximizing the similarity of data points within the same cluster. The algorithm objective is to minimize the sum of squared distances from all data points to the center of their respective clusters. The main parameter is the number of clusters, K, which can be determined using the elbow rule or silhouette coefficient. Several clusters are obtained through clustering, each representing a potential usage pattern, such as a high-frequency, light-load usage pattern, a low-frequency, heavy-load usage pattern, or a periodic, intermittent operation usage pattern.

[0037] In this embodiment, to ensure the accuracy of the model, the asset management system can use cross-validation to evaluate the accuracy of the recognition model. For example, the dataset can be divided into 10 parts, with 9 parts used for training and 1 part for testing in turn, and the average accuracy can be calculated. Based on the feedback from the recognition results, the algorithm parameters can be adjusted to optimize the model.

[0038] Step 14: Based on the usage pattern obtained by performing the above steps and the asset information, perform asset usage prediction based on the pre-trained asset prediction model to obtain the usage status prediction result corresponding to the equipment to be managed. In this application embodiment, the asset prediction model can be a linear regression model. In one implementation, the asset prediction model can be constructed according to the following process: Step 1: Obtain characteristic factors based on asset information and usage patterns; Specifically, characteristic factors may include: the equipment's years of use, recent average usage frequency, time since the last maintenance, average ambient temperature, and identified usage pattern codes, etc.

[0039] Step 2: Construct the initial multiple linear regression model; In this embodiment of the application, an initial multiple linear regression model can be constructed as shown in the following formula [1]: y = β0 + β1*x1 + β2*x2 + ... + βn*xn [1] Where y is the dependent variable, representing the asset status to be predicted, such as remaining useful life in months, probability of next failure, maintenance cost next month, etc.; β0 is the intercept, and β1, β2, ..., βn are the regression coefficients of the corresponding feature factors.

[0040] Step 3, parameter estimation; Specifically, in this embodiment of the application, the asset management system can use historical data, such as historical feature factors and corresponding actual observed states yi, to train the initial multiple linear regression model constructed in the above process, and estimate the optimal parameter β by minimizing the residual sum of squares (RSS) based on the following formula [2]: RSS = Σ(yi - (β0 + β1*x1i + β2*x2i + ... + βn*xni))^2 [2] To find the β value that minimizes RSS, the least squares method is usually used, and its parameter estimation formula is as follows [3]: β0 = (Σ(xi * yi) - Σxi * Σyi) / (Σxi^2 - (Σxi)^2 / n) [3] Then β1 = (Σ(xi^2 * yi) - Σxi * Σxi * yi) / (Σxi^2 - (Σxi)^2 / n),..., the same is true for βn.

[0041] Where Σ represents summation, xi is the value of the independent variable, yi is the value of the dependent variable, and n is the number of data points.

[0042] After training the asset prediction model through the above process, the asset management system can perform asset usage prediction in the following way: inputting the usage pattern and the asset information as feature factors into a pre-built initial linear regression model; calculating the linear combination of the feature factors through the linear regression model to determine the predicted usage status of the managed equipment in a specific future period.

[0043] Specifically, the asset management system can convert the acquired usage patterns and other relevant asset information into a feature factor vector, and input this vector into a pre-trained asset prediction model. The asset prediction model calculates a linear weighted combination of the feature factors and outputs a specific predicted value, namely the usage status prediction result. For example, the prediction result may be "the probability of the equipment failing within the next 30 days is 25%" or "the estimated remaining useful life is 180 days".

[0044] Step 15: Based on the usage status prediction results obtained by executing Step 14, determine the asset management strategy corresponding to the equipment to be managed.

[0045] In this embodiment of the application, the asset management system can determine the asset management strategy corresponding to the equipment to be managed through the following sub-steps, which may specifically include: Sub-step 1501: Determine the failure risk probability of the equipment to be managed based on the usage status prediction results obtained by executing step 14. Specifically, the asset management system can trigger corresponding strategy formulation processes based on the forecast results and a pre-set decision rule base. For example, the rule could be: "If the probability of failure P in the next 30 days is greater than 20%, then trigger the preventive maintenance strategy generation process."

[0046] In one implementation, the asset management system can use a logistic regression model to perform a refined assessment of failure risk. Specifically, the logistic regression model can calculate the failure probability according to the following formula [5]: P = 1 / (1 + e^-(β0+ β1*x1+ β2*x2+ ... + β k *x k )) [5] Where x1, x2, ..., x kThese are characteristics strongly correlated with faults, such as the number of consecutive fault-free days and the number of recent vibration exceedances, with β being the corresponding coefficient.

[0047] Sub-step 1502: Based on the failure risk probability obtained by executing sub-step 1501, determine the asset management strategy for the equipment to be managed.

[0048] Specifically, the asset management system can automatically generate the following types of management strategies based on the prediction results and rules, for example: 1. Preventive maintenance strategy: If the prediction shows a high risk of failure, a work order will be automatically generated, which includes the recommended maintenance time, maintenance content (based on historical maintenance data), a list of required spare parts, and estimated cost.

[0049] 2. Resource allocation strategy: If it is predicted that the efficiency of a certain device will decrease, it is recommended to transfer part of its load to the backup device.

[0050] 3. Inventory optimization strategy: Optimize the safety stock level of key spare parts based on the forecast results of multiple similar equipment.

[0051] The asset management system dispatches generated work orders to the maintenance management system or issues early warning notifications. Simultaneously, cost thresholds are set, such as "if the estimated cost of an automatically generated maintenance work order exceeds 5000 yuan, it must be submitted to a secondary administrator for approval," thus achieving a closed-loop decision-making process through human-machine collaboration.

[0052] Using the asset management method provided in this application embodiment, when asset planning is required, the method first receives asset information corresponding to the equipment to be managed, wherein the asset information includes basic equipment information, equipment status information, and historical maintenance data of the equipment; based on the basic equipment information, the equipment to be managed is monitored to obtain usage data corresponding to the equipment to be managed; based on the usage data, the usage mode corresponding to the equipment to be managed is determined; based on the usage mode and the asset information, asset usage prediction is performed based on a pre-trained asset prediction model to obtain the usage status prediction result corresponding to the equipment to be managed; based on the usage status prediction result, the asset management strategy corresponding to the equipment to be managed is determined. The asset management method provided in this application has several advantages. First, it allows for proactive monitoring of equipment based on basic equipment information. The system automatically and continuously collects multi-dimensional dynamic usage data, solving the problems of delayed data updates and coarse granularity caused by traditional reliance on manual data entry or periodic inspections. This also provides real-time and accurate data support for subsequent in-depth analysis. Second, by analyzing the collected usage data, this method determines the equipment's usage patterns and proactively uncovers inherent patterns and typical or abnormal modes in the equipment's operating cycle, load characteristics, and operating habits. This allows for accurate determination of asset usage and precise asset prediction based on the usage status. Finally, by combining the identified usage patterns with comprehensive historical asset information and using a pre-trained prediction model, the asset management method provided in this application can proactively warn of potential failure risks and predict remaining service life or performance degradation trends. This provides a scientific and quantitative basis for preventative maintenance and resource planning, effectively reducing the risk of unexpected downtime.

[0053] In one embodiment, this application also provides an asset management device to address the problems of existing asset management methods failing to optimize predictive logic through autonomous learning when faced with multi-type assets and multi-dimensional status data. This results in maintenance decisions relying on human experience, low asset utilization, and delayed fault response. A schematic diagram of the specific structure of this asset management device is shown below. Figure 2 As shown, it includes: asset information acquisition unit 21, monitoring unit 22, usage mode determination unit 23, prediction unit 24, and management strategy determination unit 25.

[0054] The asset information acquisition unit 21 is used to receive asset information corresponding to the equipment to be managed, wherein the asset information includes basic equipment information, equipment status information and historical maintenance data of the equipment. The monitoring unit 22 is used to monitor the device to be managed based on the basic information of the device, so as to obtain the usage data corresponding to the device to be managed; The usage mode determination unit 23 is used to determine the usage mode corresponding to the device to be managed based on the usage data. Prediction unit 24 is used to predict asset usage based on the usage pattern and the asset information, using a pre-trained asset prediction model, to obtain the usage status prediction result corresponding to the device to be managed. The management strategy determination unit 25 is used to determine the asset management strategy corresponding to the equipment to be managed based on the usage status prediction results.

[0055] In one embodiment, the usage pattern determination unit 23 is specifically used for: preprocessing the usage data to obtain first usage data; and using a machine learning algorithm to identify usage patterns based on the first usage data, so as to determine the usage pattern of the device to be managed, wherein the machine learning algorithm includes a supervised learning algorithm or an unsupervised learning algorithm.

[0056] In one implementation, the supervised learning algorithm includes the support vector machine algorithm, and the unsupervised learning algorithm includes the K-means clustering algorithm.

[0057] In one implementation, if the asset prediction model is a linear regression model, then the prediction unit 24 is specifically used to: input the usage pattern and the asset information as feature factors into a pre-constructed initial linear regression model; calculate the linear combination of the feature factors through the linear regression model to determine the predicted usage status of the managed equipment in a specific future period.

[0058] In one implementation, the parameters of the linear regression model are estimated by minimizing the sum of squared errors between the predicted and actual observed values.

[0059] In one implementation, the management strategy determination unit 25 is specifically used to: determine the failure risk probability of the device to be managed based on the usage status prediction result; and determine an asset management strategy for the device to be managed based on the failure risk probability.

[0060] Using the asset management device provided in this application embodiment, when asset planning is required, it first receives asset information corresponding to the equipment to be managed, wherein the asset information includes basic equipment information, equipment status information, and historical maintenance data of the equipment; based on the basic equipment information, it monitors the equipment to be managed to obtain usage data corresponding to the equipment to be managed; based on the usage data, it determines the usage mode corresponding to the equipment to be managed; based on the usage mode and the asset information, it performs asset usage prediction based on a pre-trained asset prediction model to obtain the usage status prediction result corresponding to the equipment to be managed; based on the usage status prediction result, it determines the asset management strategy corresponding to the equipment to be managed. The asset management device provided in this application has several advantages. First, it allows for proactive monitoring of equipment based on basic equipment information. The system automatically and continuously collects multi-dimensional dynamic usage data, solving the problems of delayed data updates and coarse granularity caused by traditional reliance on manual data entry or periodic inspections. This also provides real-time and accurate data support for subsequent in-depth analysis. Second, by analyzing the collected usage data, this solution determines the equipment's usage patterns. It proactively uncovers the inherent patterns and typical or abnormal modes of equipment in terms of operating cycles, load characteristics, and operating habits, thereby accurately determining the asset's usage status and making precise asset predictions based on this status. Finally, by combining the identified usage patterns with comprehensive historical asset information and making predictions based on a pre-trained prediction model, the asset management method provided in this application can proactively warn of potential failure risks and predict remaining service life or performance degradation trends. This provides a scientific and quantitative basis for preventative maintenance and resource planning, effectively reducing the risk of unexpected downtime.

[0061] Figure 3 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 3 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0062] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0063] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0064] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming an asset management device at the logical level. The processor executes the program stored in memory and specifically performs the following operations: The system receives asset information corresponding to the device to be managed, wherein the asset information includes basic device information, device status information, and historical maintenance data; monitors the device to be managed based on the basic device information to obtain usage data corresponding to the device; determines the usage mode corresponding to the device to be managed based on the usage data; predicts asset usage based on the usage mode and the asset information using a pre-trained asset prediction model to obtain a usage status prediction result for the device to be managed; and determines the asset management strategy corresponding to the device to be managed based on the usage status prediction result.

[0065] The above is as stated in this application. Figure 3The method executed by the asset management electronic device disclosed in the illustrated embodiments can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0066] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0067] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by a portable electronic device including multiple applications, enable the portable electronic device to perform... Figure 1 The asset management method shown in the embodiment is specifically used to perform the following operations: The system receives asset information corresponding to the device to be managed, wherein the asset information includes basic device information, device status information, and historical maintenance data; monitors the device to be managed based on the basic device information to obtain usage data corresponding to the device; determines the usage mode corresponding to the device to be managed based on the usage data; predicts asset usage based on the usage mode and the asset information using a pre-trained asset prediction model to obtain a usage status prediction result for the device to be managed; and determines the asset management strategy corresponding to the device to be managed based on the usage status prediction result.

[0068] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0069] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0070] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0071] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0072] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0073] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0074] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0075] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0076] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. An asset management method, characterized in that, include: Receive asset information corresponding to the equipment to be managed, wherein the asset information includes basic equipment information, equipment status information and historical maintenance data of the equipment; Based on the basic information of the device, the device to be managed is monitored to obtain the usage data corresponding to the device to be managed; Based on the usage data, determine the usage mode corresponding to the device to be managed; Based on the usage pattern and the asset information, asset usage prediction is performed using a pre-trained asset prediction model to obtain the usage status prediction result corresponding to the device to be managed. Based on the usage status prediction results, the asset management strategy corresponding to the equipment to be managed is determined.

2. The method according to claim 1, characterized in that, The step of determining the usage mode corresponding to the device to be managed based on the usage data specifically includes: The usage data is preprocessed to obtain the first usage data; Based on the first usage data, a machine learning algorithm is used to identify usage patterns in order to determine the usage patterns of the device to be managed, wherein the machine learning algorithm includes a supervised learning algorithm or an unsupervised learning algorithm.

3. The method according to claim 2, characterized in that, The supervised learning algorithm includes the support vector machine algorithm, and the unsupervised learning algorithm includes the K-means clustering algorithm.

4. The method according to claim 1, characterized in that, The asset prediction model is a linear regression model; The step of predicting asset usage based on the usage pattern and the asset information, using a pre-trained asset prediction model, specifically includes: The usage pattern and asset information are used as feature factors and input into a pre-built initial linear regression model; The linear regression model is used to calculate the linear combination of the feature factors to determine the predicted usage status of the equipment to be managed in a specific future period.

5. The method according to claim 4, characterized in that, The parameters of the linear regression model are estimated by minimizing the sum of squared errors between the predicted and actual observed values.

6. The method according to claim 1, characterized in that, The step of determining the asset management strategy corresponding to the equipment to be managed based on the usage status prediction result includes: Based on the usage status prediction results, determine the failure risk probability of the managed equipment; Based on the probability of failure risk, an asset management strategy is determined for the equipment to be managed.

7. An asset management device, characterized in that, include: The asset information acquisition unit is used to receive asset information corresponding to the equipment to be managed, wherein the asset information includes basic equipment information, equipment status information and historical maintenance data of the equipment; The monitoring unit is used to monitor the device to be managed based on the basic information of the device, so as to obtain the usage data corresponding to the device to be managed; The usage mode determination unit is used to determine the usage mode corresponding to the device to be managed based on the usage data. The prediction unit is used to predict asset usage based on the usage pattern and the asset information, using a pre-trained asset prediction model, to obtain the predicted usage status of the device to be managed. The management strategy determination unit is used to determine the asset management strategy corresponding to the device to be managed based on the usage status prediction results.

8. An asset management device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the following operations: Receive asset information corresponding to the equipment to be managed, wherein the asset information includes basic equipment information, equipment status information and historical maintenance data of the equipment; Based on the basic information of the device, the device to be managed is monitored to obtain the usage data corresponding to the device to be managed; Based on the usage data, determine the usage mode corresponding to the device to be managed; Based on the usage pattern and the asset information, asset usage prediction is performed using a pre-trained asset prediction model to obtain the usage status prediction result corresponding to the device to be managed. Based on the usage status prediction results, the asset management strategy corresponding to the equipment to be managed is determined.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the asset management method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the asset management method as described in any one of claims 1-6.

Images