Equipment accessory management method and device of data center, equipment and storage medium

Abstract

The invention discloses an equipment accessory management method and device for a data center, equipment and a storage medium, and the method comprises the steps: extracting equipment features from the equipment operation data of the data center, and inputting the equipment features to a preset equipment health score prediction model, so that the equipment health score prediction model obtains an equipment health score according to the equipment features; estimating the health score of the equipment, and outputting the current health score of the equipment; according to the health score, adjusting a preset initial accessory inventory threshold value of the equipment to obtain a current accessory inventory threshold value of the equipment; and monitoring the inventory of the equipment accessories in real time, and when the inventory of the accessories is monitored to be lower than the accessory inventory threshold value, generating a corresponding alarm notification, so that a corresponding worker adjusts the inventory of the accessories according to the accessory inventory threshold value. According to the invention, the inventory required by the fittings can be adjusted in real time according to the health condition of the equipment, and the normal operation and maintenance activity of the data center is ensured on the premise of controlling the cost.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment parts management, and in particular to an equipment parts management method, device, equipment and storage medium for a data center. Background Art

[0002] The current data center equipment parts management is rather chaotic. It is not possible to estimate the required parts reserve inventory based on the current situation of the equipment, which easily leads to the situation that some equipment parts are over-purchased, while some equipment parts are insufficient, resulting in no parts to replace when the data center equipment fails, affecting the operation safety of the data center, or causing waste and increasing its operating costs. For example, for some important parts, their prices are relatively high. In order to control costs, general enterprises will not reserve a lot of such parts, which easily leads to the situation that there are no parts to replace when key equipment in the data center has problems. In addition, since parts are also a considerable cost for the data center, too many parts will cause waste and increase operating costs.

[0003] Equipment parts management in data centers is an important guarantee for their safe operation and maintenance, and appropriate parts inventory is also an important part of cost control for data centers. Therefore, it is necessary to adjust the reserve inventory of parts according to the actual situation of the equipment, and to carry out refined and intelligent management of the equipment parts inventory. Summary of the invention

[0004] The present invention provides a method, device, equipment and storage medium for managing equipment accessories in a data center to solve the technical problem that the prior art cannot estimate the required accessories reserve inventory according to the current situation of the equipment, which easily leads to over-purchase or shortage of equipment accessories.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a method for managing equipment accessories in a data center, including:

[0006] Obtaining equipment operation data of the data center; wherein the equipment operation data includes: the current temperature, voltage, current, operation time and error log of the equipment;

[0007] Extracting device features from the device operation data, and inputting the extracted device features into a preset device health score estimation model, so that the device health score estimation model estimates the health score of the device according to the device features, and outputs the current health score of the device;

[0008] According to the health score, an initial parts inventory threshold preset for the device is adjusted to obtain a current parts inventory threshold for the device;

[0009] Monitor the inventory of equipment accessories in real time, and when it is monitored that the inventory of accessories is lower than the accessories inventory threshold, generate a corresponding alarm notification so that the corresponding staff can adjust the inventory of accessories according to the accessories inventory threshold;

[0010] The equipment health score estimation model is obtained by training a preset machine learning model with the historical equipment operation data of the data center as input and the health score corresponding to the equipment as output.

[0011] As a preferred solution, before extracting the device features from the device operation data, the method further includes:

[0012] The equipment operation data is preprocessed; wherein the preprocessing includes: data cleaning, missing value processing, outlier processing, data smoothing and data normalization.

[0013] As a preferred solution, it also includes:

[0014] Obtaining historical health scores corresponding to the device at several historical moments, and constructing a health score curve for the device based on the historical health scores;

[0015] According to the health score curve, the health score corresponding to the device at a future moment is predicted to obtain the health score of the device at the future moment.

[0016] As a preferred solution, the setting of the initial parts inventory threshold includes:

[0017] Obtain the accessory type and accessory importance corresponding to the equipment accessories, as well as the total consumption of the equipment accessories in a preset historical time period;

[0018] According to the total consumption of the equipment accessories in a preset historical time period, the historical consumption rate of the equipment accessories is calculated, and then the initial accessories inventory threshold of the equipment accessories is generated according to the historical consumption rate, the accessory type and the importance of the accessory.

[0019] As a preferred solution, it also includes:

[0020] Acquire the accessory operation data of the equipment accessory; wherein the accessory operation data includes: the historical replacement record, operation time and number of failures of the equipment accessory;

[0021] Inputting the accessory operation data into a preset accessory life prediction model, so that the accessory life prediction model predicts the remaining service life of the equipment accessory according to the accessory operation data, and outputs the current remaining service life of the equipment accessory;

[0022] The health score of the equipment is adjusted according to the remaining service life of the equipment accessories, and then the equipment accessories inventory threshold is adjusted according to the adjusted health score;

[0023] Among them, the accessory life prediction model is obtained by training a preset machine learning model with the historical accessory operation data of the data center as input and the remaining service life corresponding to the equipment accessories as output.

[0024] As a preferred solution, it also includes:

[0025] Determine the parts inventory cycle for each equipment part based on the historical consumption rate, part type and part importance of each equipment part;

[0026] Generate a parts inventory list corresponding to each device part according to the parts inventory cycle; wherein the parts inventory list includes: the name, quantity, storage location and last inventory date of the parts to be inventoried;

[0027] The parts inventory list corresponding to each equipment part is sent to the corresponding staff, so that the corresponding staff can conduct a parts inventory of the corresponding equipment parts according to the parts inventory list.

[0028] As a preferred solution, it also includes:

[0029] Obtain the parts inventory list obtained after the parts inventory, compare the parts inventory list before and after the parts inventory, and obtain the inventory results corresponding to the equipment parts;

[0030] The accessories inventory threshold of the equipment accessories is adjusted according to the inventory result.

[0031] Based on the above embodiment, another embodiment of the present invention provides a device for managing equipment parts in a data center, including: a data acquisition module, a health score estimation module, a parts inventory threshold adjustment module, and a parts inventory monitoring module;

[0032] The data acquisition module is used to acquire the equipment operation data of the data center; wherein the equipment operation data includes: the current temperature, voltage, current, operation time and error log of the equipment;

[0033] The health score estimation module is used to extract equipment features from the equipment operation data, and input the extracted equipment features into a preset equipment health score estimation model, so that the equipment health score estimation model estimates the health score of the equipment according to the equipment features, and outputs the current health score of the equipment; wherein the equipment health score estimation model is obtained by training a preset machine learning model using the historical equipment operation data of the data center as input and the health score corresponding to the equipment as output;

[0034] The accessory inventory threshold adjustment module is used to adjust the initial accessory inventory threshold preset for the device according to the health score to obtain the current accessory inventory threshold of the device;

[0035] The accessories inventory monitoring module is used to monitor the inventory of equipment accessories in real time. When it is monitored that the inventory of accessories is lower than the accessories inventory threshold, a corresponding alarm notification is generated to enable the corresponding staff to adjust the inventory of accessories according to the accessories inventory threshold.

[0036] Based on the above embodiments, another embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the device accessories management method of the data center described in the above invention embodiments.

[0037] Based on the above embodiments, another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the device accessories management method of the data center described in the above invention embodiment.

[0038] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0039] The present invention provides a method for managing equipment accessories of a data center, which includes acquiring equipment operation data of the data center; extracting equipment features from the equipment operation data, and inputting the extracted equipment features into a preset equipment health score estimation model, so that the equipment health score estimation model estimates the health score of the equipment according to the equipment features, and outputs the current health score of the equipment; adjusting the preset initial accessories inventory threshold of the equipment according to the health score, and obtaining the current accessories inventory threshold of the equipment; monitoring the inventory of equipment accessories in real time, and generating a corresponding alarm notification when it is monitored that the inventory of accessories is lower than the accessories inventory threshold, so that the corresponding staff can adjust the inventory of accessories according to the accessories inventory threshold.

[0040] The present invention can adjust the device's accessory inventory threshold according to the device's health score. For example, when the device's health score is low, the device's accessory inventory threshold is increased, and when the device's health score is high, the device's accessory inventory threshold is reduced. That is, the required inventory of accessories can be adjusted in real time according to the device's health status, realizing refined and intelligent management of the device's accessory inventory, ensuring that there is a matching supply of device accessories when the device fails or changes, and ensuring the normal operation and maintenance activities of the data center under the premise of controlling costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flowchart of a method for managing equipment accessories in a data center provided by an embodiment of the present invention;

[0042] Figure 2 It is a structural diagram of an equipment parts management device for a data center provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0045] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0046] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0047] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0048] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0049] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0050] Embodiment 1

[0051] Please refer to Figure 1 , is a flow chart of a method for managing equipment accessories in a data center provided by an embodiment of the present invention, comprising the following specific steps:

[0052] S1. Obtaining equipment operation data of the data center; wherein the equipment operation data includes: current temperature, voltage, current, operation time and error log of the equipment;

[0053] Specifically, the existing data center equipment accessories management is relatively chaotic and has the following defects:

[0054] 1. Failure to estimate spare parts inventory based on equipment health, especially some important spare parts, which are very expensive. In order to control costs, most companies will not reserve a lot of such spare parts, which may easily lead to problems with key equipment in the data center and no spare parts available for replacement;

[0055] 2. The inventory of accessories only follows a static inventory threshold, without dynamic threshold management;

[0056] 3. The entire life cycle of accessories is not recorded and evaluated. An accessory also has a service life, and its service life will also affect the health of the equipment. Therefore, there needs to be a statistics and estimate of the service life of important accessories.

[0057] In view of the above defects, the present invention proposes a data center equipment accessories management method, which can ensure that there is a matching supply of equipment accessories when equipment fails or changes, so as to ensure the normal operation and maintenance activities of the data center, which specifically includes the following parts:

[0058] 1. Equipment health assessment and inventory threshold setting

[0059] 1. Equipment health assessment:

[0060] (1) Collect equipment operation data from the data center, including but not limited to the current temperature, voltage, current, operating time, and error logs of the equipment.

[0061] S2. Extracting device features from the device operation data, and inputting the extracted device features into a preset device health score estimation model, so that the device health score estimation model estimates the health score of the device according to the device features, and outputs the current health score of the device; wherein the device health score estimation model is obtained by training a preset machine learning model using the historical device operation data of the data center as input and the health score corresponding to the device as output;

[0062] Preferably, before extracting device features from the device operation data, it also includes: preprocessing the device operation data; wherein the preprocessing includes: data cleaning, missing value processing, outlier processing, data smoothing and data normalization.

[0063] Then, the equipment operation data is preprocessed, and the preprocessing includes but is not limited to: data cleaning, missing value processing, outlier processing, data smoothing, and data normalization. Then, the equipment features of the preprocessed equipment operation data are extracted, and the extracted equipment features are input into the pre-trained equipment health score estimation model, so that the equipment health score estimation model estimates the health score of the equipment according to the equipment features and outputs the current health score of the equipment.

[0064] The model training process of the equipment health score estimation model is as follows:

[0065] A. Data collection: Collect historical equipment operation data from data center equipment, such as temperature, voltage, current, operation time, and error logs.

[0066] B. Data preprocessing: data cleaning, missing value processing, outlier processing, data smoothing and data normalization, etc.

[0067] C. Feature engineering: Extract meaningful device features from raw data, such as mean, standard deviation, peak, trend, etc.

[0068] D. Model training: Use the extracted device features to train a machine learning model, such as a random forest, gradient boosting machine, or deep learning model, to estimate the health score of the device.

[0069] E. Health score calculation: Apply the trained equipment health score estimation model to the real-time equipment operation data to estimate the equipment health score.

[0070] S3. According to the health score, adjust the initial parts inventory threshold preset for the device to obtain the current parts inventory threshold for the device;

[0071] Preferably, the setting of the initial accessories inventory threshold includes: obtaining the accessory type and accessory importance corresponding to the equipment accessories, and the total consumption of the equipment accessories in a preset historical time period; calculating the historical consumption rate of the equipment accessories based on the total consumption of the equipment accessories in a preset historical time period, and then generating the initial accessories inventory threshold for the equipment accessories based on the historical consumption rate, accessory type and accessory importance.

[0072] (2) Parts inventory threshold setting:

[0073] Setting the initial inventory threshold for accessories: Based on the total consumption of equipment accessories within a preset historical time period, equipment type, equipment importance and other factors, calculate the historical consumption rate of equipment accessories, and then set an initial inventory threshold for each equipment accessory based on the historical consumption rate of the equipment, accessory type and accessory importance.

[0074] Dynamic adjustment: Dynamically adjust the accessory inventory threshold based on the health score of the device. For example, when the health score decreases, the inventory threshold increases accordingly; when the health score increases, the inventory threshold can be appropriately reduced.

[0075] Threshold algorithm: Rule-based methods (such as ifelse logic) or machine learning models (such as linear regression, neural network, etc.) can be used to predict and adjust inventory thresholds.

[0076] In a specific embodiment, the steps for implementing the inventory threshold dynamic adjustment algorithm are as follows:

[0077] A. Initial parts inventory threshold: Set the initial inventory threshold based on factors such as historical consumption rate, part type, and part importance.

[0078] B. Threshold adjustment rules: Define rules, such as when the health score drops by more than a certain percentage, the inventory threshold increases by a certain amount or percentage.

[0079] C. Real-time adjustment: Dynamically adjust inventory thresholds based on the real-time health score of the device and defined rules.

[0080] The historical consumption rates are described in detail below:

[0081] Historical consumption rate: refers to the frequency and quantity of equipment parts used or consumed in the past period of time. This is an important parameter that can help inventory managers understand the consumption rate of each part, so as to better plan inventory and predict future demand. The historical consumption rate is usually obtained by analyzing the data in the inventory management system. The following is a detailed calculation method:

[0082] Step 1: Data Collection

[0083] Collect inventory records: Collect all parts inbound and outbound records from the inventory management system.

[0084] Collect usage records: If possible, equipment usage records should also be collected to understand the consumption of accessories in actual operation.

[0085] Step 2: Data Processing

[0086] Data cleaning: Ensure that the collected data is accurate and delete any abnormal or duplicate records.

[0087] Data collation: Organize the data format to ensure that each record has key information such as timestamp, part number, quantity in and out of the warehouse, etc.

[0088] Step 3: Calculate the consumption rate

[0089] Statistics by time period: Statistics on the total consumption of each accessory are compiled based on the required time granularity (such as monthly, quarterly, or annual).

[0090] Calculate the average consumption rate: Divide the total consumption by the length of the time period to get the average consumption rate.

[0091] Step 4: Analyze and apply

[0092] Trend analysis: Analyze the changing trend of consumption rate and identify parts with increasing or decreasing consumption.

[0093] Inventory adjustment: Adjust inventory strategies based on consumption rates, such as increasing inventory for high-consumption-rate parts and reducing inventory for low-consumption-rate parts.

[0094] S4. Monitor the inventory of equipment accessories in real time. When it is monitored that the inventory of accessories is lower than the accessories inventory threshold, generate a corresponding alarm notification so that the corresponding staff can adjust the inventory of accessories according to the accessories inventory threshold.

[0095] Preferably, it also includes: obtaining historical health scores corresponding to the device at several historical moments, and constructing a health score curve for the device based on the historical health scores; and predicting the health score corresponding to the device at future moments based on the health score curve to obtain the health score of the device at future moments.

[0096] (3) Inventory alarm: Real-time monitoring of the inventory of equipment accessories. When the inventory is lower than the dynamically adjusted accessories inventory threshold, the system triggers an alarm notification and generates a corresponding alarm notification. The alarm notification can be sent to relevant management personnel via email, SMS, mobile application push, etc., so that the corresponding staff can adjust the inventory of accessories according to the accessories inventory threshold.

[0097] In a specific embodiment, these health score data are also used to construct a health score curve for the device, and the health trend of the device can be predicted using time series analysis and machine learning models (such as random forests, gradient boosting machines, etc.) based on the health score curve. According to the health curve, a health score is calculated for each device, which reflects the current state of the device and its possible performance in the future.

[0098] Among them, the health score is only static, and different time nodes correspond to different health scores. For example, if the device is evaluated once every month, the score on the 1st of each month represents the device health score during the period before the next score. By stringing together the time, a health score curve is formed, and each device has its own health curve.

[0099] Preferably, it also includes: obtaining accessory operation data of equipment accessories; wherein the accessory operation data includes: historical replacement records, operating hours and number of failures of equipment accessories; inputting the accessory operation data into a preset accessory life prediction model, so that the accessory life prediction model predicts the remaining service life of the equipment accessories according to the accessory operation data, and outputs the current remaining service life of the equipment accessories; according to the current remaining service life of the equipment accessories, the health score of the equipment is adjusted, and then according to the adjusted health score, the accessory inventory threshold of the equipment is adjusted; wherein the accessory life prediction model is obtained by training a preset machine learning model with the historical accessory operation data of the data center as input and the corresponding remaining service life of the equipment accessories as output.

[0100] 2. Evaluation of accessories’ service life and impact on health value

[0101] 1. Service life assessment:

[0102] The accessory operation data of each accessory is recorded; wherein the accessory operation data includes: historical replacement records of equipment accessories, operation time and number of failures, etc.

[0103] Predict the remaining service life of equipment accessories using a pre-trained accessory life prediction model (such as Weibull distribution, normal distribution, or machine learning model, such as survival analysis model). Input the accessory operation data into the accessory life prediction model, and output the current remaining service life of the equipment accessories.

[0104] 2. Impact of health value:

[0105] The health score of the device is adjusted according to the remaining service life of the device accessories. When the service life of the accessories is approaching the end, the system will issue a prompt and automatically adjust the health score of the device.

[0106] The adjustment algorithm may be a simple subtraction (eg, subtracting a fixed value from the health score) or a more complex function (eg, reducing the health score based on a percentage of remaining useful life).

[0107] 3. Threshold increase:

[0108] Recalculate the spare parts inventory threshold based on the adjusted health score to ensure that there is sufficient spare parts inventory to deal with possible equipment failures.

[0109] The training steps of the accessory life prediction model are as follows:

[0110] A. Data collection: Collect historical replacement records of equipment accessories, operating hours, number of failures, etc.

[0111] B. Model selection: Select an appropriate statistical model or machine learning model, such as the Weibull distribution model in survival analysis or a prediction model based on time series.

[0112] C. Model training: Use historical data of equipment accessories to train the model to predict the remaining service life of the accessories.

[0113] D. Real-time prediction: Apply the trained model to real-time data to predict the remaining service life of the accessories, and issue reminders or adjust the health score accordingly.

[0114] Preferably, it also includes: determining the accessories inventory cycle of each equipment accessory based on the historical consumption rate, accessory type and accessory importance of each equipment accessory; generating an accessories inventory list corresponding to each equipment accessory based on the accessories inventory cycle; wherein the accessories inventory list includes: the name, quantity, storage location and last inventory date of the accessories to be inventoried; and sending the accessories inventory list corresponding to each equipment accessory to the corresponding staff, so that the corresponding staff can conduct accessories inventory for the corresponding equipment accessories according to the accessories inventory list.

[0115] Preferably, it also includes: obtaining an inventory list of accessories obtained after the accessories inventory, comparing the inventory list of accessories before and after the accessories inventory to obtain inventory results corresponding to the equipment accessories; and adjusting the accessories inventory threshold of the equipment accessories according to the inventory results.

[0116] 3. Intelligent Inventory and Task Allocation

[0117] 1. Identification of important accessories: Identify key and important accessories based on the importance of the equipment, the frequency of replacement of accessories, and the cost.

[0118] The importance of the equipment is described in detail below:

[0119] Equipment importance: Key parts can be identified according to the importance of the equipment. Key parts are used frequently and have a great impact on equipment changes. Without key parts, some important equipment maintenance and changes cannot be carried out. Therefore, it is necessary to ensure that key and important parts are in place before equipment changes or important maintenance, which can improve efficiency and ensure the work results of staff.

[0120] 2. Periodic inventory: The system automatically generates an inventory list of accessories according to the preset period (such as monthly or quarterly). The list includes the name, quantity, storage location, and last inventory date of the accessories.

[0121] 3. Task allocation and execution: The system allocates the inventory task to the relevant staff, which can be achieved through the workflow management system or task allocation algorithm. After receiving the task, the staff will confirm the offline list and feedback the confirmation result to the system.

[0122] 4. Inventory result processing: The system compares the differences between the inventory before and after the inventory. If there are any differences, the exception handling process is triggered (such as re-inventory, investigation of the cause, etc.). The inventory result is used to update the inventory data and provide a reference for the inventory management and procurement plan of the next cycle.

[0123] The following is a detailed description of the above intelligent inventory algorithm:

[0124] A. Identification of important parts: Based on factors such as cost, replacement frequency, and equipment importance, use clustering algorithms (such as K-means) or sorting algorithms (such as TOP-N) to identify important parts.

[0125] Among them, using clustering algorithms to identify important parts in data centers is an effective method, especially when there is no clear standard for the importance of parts. Clustering can help us discover patterns and natural groupings in the data, and automatically classify parts based on factors such as cost, replacement frequency, and equipment importance. The following are detailed steps for using clustering algorithms, such as K-means, to identify important parts:

[0126] Step 1. Data preparation: First, collect and prepare the required data. For accessories, the following types of data are required:

[0127] Cost: the cost of each accessory;

[0128] Replacement frequency: replacement frequency or replacement record of accessories;

[0129] Equipment Importance: The importance of the equipment to which the accessory belongs. This can be based on the functional importance of the equipment, the impact of failure on the business, etc.

[0130] Step 2: Data preprocessing: Data usually needs to be preprocessed to be suitable for clustering algorithms:

[0131] Missing value processing: fill in or delete missing data;

[0132] Standardization: Since the scales of indicators such as cost and replacement frequency may be different, they need to be standardized to ensure that each feature contributes equally to the results;

[0133] Step 3: Clustering algorithm application: Use K-means clustering algorithm to identify different accessory groups. The selection of the appropriate number of clusters (k value) usually needs to be determined based on business needs or through methods such as the elbow rule.

[0134] Step 4: Analyze clustering results: Analyze the clustering results to identify which groups represent "important parts". This may be based on the characteristics of the parts in the cluster being high in cost, frequently replaced, and very important in the equipment they belong to.

[0135] B. Determination of inventory cycle: Determine the inventory cycle for each accessory based on its importance and historical consumption rate.

[0136] C. Automatically generate inventory: The system automatically generates an inventory list based on the inventory cycle and the list of important accessories.

[0137] D. Task allocation: Use task allocation algorithms (such as polling, load balancing, etc.) to assign inventory tasks to staff members.

[0138] E. Result comparison and processing: The system compares the lists before and after the inventory, uses difference detection algorithms (such as hash comparison, quantity difference, etc.) to identify differences, and triggers the corresponding processing flow.

[0139] Among them, in the intelligent inventory process, the difference detection algorithm plays a key role to ensure the accuracy of inventory data and identify any anomalies. After the inventory is completed, the system needs to compare the data before and after the inventory to confirm whether the actual inventory is consistent with the system records and whether there are any inconsistencies. The following is the specific implementation method of the difference detection process:

[0140] 1. Data preparation: Ensure that inventory data before and after the inventory count has been accurately recorded and in a consistent format. This usually includes the identifier of the accessory (such as SKU, barcode, etc.), quantity and location information.

[0141] 2. Data cleaning: Before making a comparison, clean the data to ensure that there are no invalid or erroneous records, such as deleting unrecognizable barcodes and correcting obvious input errors.

[0142] 3. Hash comparison: For each accessory item, a hash value of its unique identifier and quantity can be generated. By comparing the hash values ​​before and after the inventory, it is possible to quickly determine which accessory items have changed.

[0143] Hash algorithms such as MD5 or SHA-256 can be used to generate a unique fingerprint of data, quickly identifying if the data has been altered.

[0144] 4. Quantity difference detection: Directly compare the quantity before and after the inventory count for each accessory item. Record any mismatch in quantity, such as the quantity recorded by the system and the actual inventory count. This can be achieved by simply calculating the difference between the two quantities, with a positive difference indicating a shortage and a negative difference indicating an excess.

[0145] 5. Results summary and analysis: Summarize all detected discrepancies and analyze possible causes, such as recording errors, theft, data entry errors, etc. Depending on the nature and severity of the discrepancies, trigger corresponding processing procedures, such as re-inventory, updating inventory records, investigating potential theft, etc.

[0146] 4. System Integration and Automation

[0147] 1. System integration: Integrate the above algorithms and processes into the data center management system to ensure data sharing and communication between various modules.

[0148] 2. Automation: Through API interface, automation scripts or workflow management tools, the process can be automated and human intervention can be reduced.

[0149] 3. Monitoring and logging: Establish a monitoring system and logging mechanism to track the system's operating status and abnormal conditions in real time to ensure the reliability and stability of the process.

[0150] 4. Continuous optimization: Regularly evaluate the effectiveness and performance of the process, collect feedback and suggestions, and continuously optimize and improve algorithms and processes.

[0151] It can be seen that the present invention provides a data center equipment accessories management method. Through the present invention, the management of dynamic thresholds of data center equipment accessories can be solved, making accessory management more flexible while saving costs. It can also solve the management problem of the entire life cycle of data center equipment accessories, evaluate the service life of equipment accessories, and help better manage the inventory of accessories.

[0152] Embodiment 2

[0153] Please refer to Figure 2, is a schematic diagram of the structure of a device for managing equipment parts in a data center provided by an embodiment of the present invention, the device comprising: a data acquisition module, a health score estimation module, a parts inventory threshold adjustment module and a parts inventory monitoring module;

[0154] The data acquisition module is used to acquire the equipment operation data of the data center; wherein the equipment operation data includes: the current temperature, voltage, current, operation time and error log of the equipment;

[0155] The health score estimation module is used to extract equipment features from the equipment operation data, and input the extracted equipment features into a preset equipment health score estimation model, so that the equipment health score estimation model estimates the health score of the equipment according to the equipment features, and outputs the current health score of the equipment; wherein the equipment health score estimation model is obtained by training a preset machine learning model using the historical equipment operation data of the data center as input and the health score corresponding to the equipment as output;

[0156] The accessory inventory threshold adjustment module is used to adjust the initial accessory inventory threshold preset for the device according to the health score to obtain the current accessory inventory threshold of the device;

[0157] The accessories inventory monitoring module is used to monitor the inventory of equipment accessories in real time. When it is monitored that the inventory of accessories is lower than the accessories inventory threshold, a corresponding alarm notification is generated to enable the corresponding staff to adjust the inventory of accessories according to the accessories inventory threshold.

[0158] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0159] Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0160] Embodiment 3

[0161] Accordingly, an embodiment of the present invention provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the device implements the device accessories management method for the data center described in the above-mentioned embodiment of the invention.

[0162] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, a cloud server, etc. The device may include, but is not limited to, a processor and a memory.

[0163] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the device, and various interfaces and lines are used to connect various parts of the entire device.

[0164] Embodiment 4

[0165] Accordingly, an embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the device accessories management method for the data center described in the above-mentioned embodiment of the invention.

[0166] The memory can be used to store the computer program, and the processor realizes various functions of the device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0167] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each method embodiment described above can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-On l yMemory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0168] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A data center equipment accessories management method, characterized in that: include: Obtaining equipment operation data of the data center; wherein the equipment operation data includes: the current temperature, voltage, current, operation time and error log of the equipment; Extracting device features from the device operation data, and inputting the extracted device features into a preset device health score estimation model, so that the device health score estimation model estimates the health score of the device according to the device features, and outputs the current health score of the device; According to the health score, an initial parts inventory threshold preset for the device is adjusted to obtain a current parts inventory threshold for the device; Monitor the inventory of equipment accessories in real time, and when it is monitored that the inventory of accessories is lower than the accessories inventory threshold, generate a corresponding alarm notification so that the corresponding staff can adjust the inventory of accessories according to the accessories inventory threshold; The equipment health score estimation model is obtained by training a preset machine learning model with the historical equipment operation data of the data center as input and the health score corresponding to the equipment as output.

2. The data center equipment accessories management method according to claim 1, characterized in that: Before extracting the device features from the device operation data, the method further includes: The equipment operation data is preprocessed; wherein the preprocessing includes: data cleaning, missing value processing, outlier processing, data smoothing and data normalization.

3. The data center equipment parts management method according to claim 1, characterized in that: Also includes: Obtaining historical health scores corresponding to the device at several historical moments, and constructing a health score curve for the device based on the historical health scores; According to the health score curve, the health score corresponding to the device at a future moment is predicted to obtain the health score of the device at the future moment.

4. The data center equipment accessories management method according to claim 1, characterized in that: The setting of the initial parts inventory threshold includes: Obtain the accessory type and accessory importance corresponding to the equipment accessories, as well as the total consumption of the equipment accessories in a preset historical time period; According to the total consumption of the equipment accessories in a preset historical time period, the historical consumption rate of the equipment accessories is calculated, and then the initial accessories inventory threshold of the equipment accessories is generated according to the historical consumption rate, the accessory type and the importance of the accessory.

5. The data center equipment parts management method according to claim 4, characterized in that: Also includes: Acquire the accessory operation data of the equipment accessory; wherein the accessory operation data includes: the historical replacement record, operation time and number of failures of the equipment accessory; Inputting the accessory operation data into a preset accessory life prediction model, so that the accessory life prediction model predicts the remaining service life of the equipment accessory according to the accessory operation data, and outputs the current remaining service life of the equipment accessory; The health score of the equipment is adjusted according to the remaining service life of the equipment accessories, and then the equipment accessories inventory threshold is adjusted according to the adjusted health score; Among them, the accessory life prediction model is obtained by training a preset machine learning model with the historical accessory operation data of the data center as input and the remaining service life corresponding to the equipment accessories as output.

6. The data center equipment parts management method according to claim 5, characterized in that: Also includes: Determine the parts inventory cycle for each equipment part based on the historical consumption rate, part type and part importance of each equipment part; Generate a parts inventory list corresponding to each device part according to the parts inventory cycle; wherein the parts inventory list includes: the name, quantity, storage location and last inventory date of the parts to be inventoried; The parts inventory list corresponding to each equipment part is sent to the corresponding staff, so that the corresponding staff can conduct a parts inventory of the corresponding equipment parts according to the parts inventory list.

7. The data center equipment parts management method according to claim 6, characterized in that: Also includes: Obtain the parts inventory list obtained after the parts inventory, compare the parts inventory list before and after the parts inventory, and obtain the inventory results corresponding to the equipment parts; The accessories inventory threshold of the equipment accessories is adjusted according to the inventory result.

8. A device for managing equipment accessories in a data center, characterized in that: include: Data acquisition module, health score estimation module, spare parts inventory threshold adjustment module and spare parts inventory monitoring module; The data acquisition module is used to acquire the equipment operation data of the data center; wherein the equipment operation data includes: the current temperature, voltage, current, operation time and error log of the equipment; The health score estimation module is used to extract equipment features from the equipment operation data, and input the extracted equipment features into a preset equipment health score estimation model, so that the equipment health score estimation model estimates the health score of the equipment according to the equipment features, and outputs the current health score of the equipment; wherein the equipment health score estimation model is obtained by training a preset machine learning model using the historical equipment operation data of the data center as input and the health score corresponding to the equipment as output; The accessory inventory threshold adjustment module is used to adjust the initial accessory inventory threshold preset for the device according to the health score to obtain the current accessory inventory threshold of the device; The accessories inventory monitoring module is used to monitor the inventory of equipment accessories in real time. When it is monitored that the inventory of accessories is lower than the accessories inventory threshold, a corresponding alarm notification is generated to enable the corresponding staff to adjust the inventory of accessories according to the accessories inventory threshold.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for managing equipment accessories of a data center as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute the device accessories management method for a data center as described in any one of claims 1 to 7.

Images