Enterprise-level equipment as service (DaaS) system

Abstract

The invention relates to the technical field of equipment management service, in particular to an enterprise-level equipment as a service (DaaS) system which comprises a remote memory monitoring module, an equipment use identification module, a use cycle mapping module, an abnormal state identification module and a staged service label module. According to the invention, by collecting the memory usage data of the device in real time and calculating the memory utilization rate, the resource abnormity can be identified in time, and by analyzing the starting and ending time of the device session and combining the reference of the service level agreement for comparison, the refined classification of the device usage condition is realized; through deviation comparison with baseline data such as equipment use frequency and task throughput, abnormal behaviors are found in advance, abnormal behavior recognition is performed through multi-dimensional feature cross validation, the accuracy of abnormal detection can be greatly improved, the accuracy, response speed and early warning capability of equipment resource management are remarkably improved, the operation and maintenance cost is effectively reduced, and the method is suitable for popularization and application. And the service life cycle of equipment is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of device management services, and in particular, to an enterprise-level device as a service (DaaS) system. Background Art

[0002] The technical field of device management services includes an integrated management service for the unified procurement, deployment, management, maintenance, and recycling of computing devices during their usage cycle. The core content is to achieve the efficient management and dynamic allocation of internal device resources in an enterprise through the cooperation of software and hardware, thereby optimizing device utilization and life cycle management. It comprehensively covers aspects such as device configuration management, remote monitoring management, fault diagnosis and handling, software distribution, and upgrade maintenance, aiming to conduct orderly and standardized operation management of a large number of dispersed enterprise devices through centralized and automated means.

[0003] Among them, an enterprise-level device as a service (DaaS) system refers to a system that provides an enterprise with full life cycle management services such as hardware device leasing, configuration distribution, remote maintenance, and asset recycling through a centralized platform. It mainly addresses technical issues such as complex device procurement processes, high operation and maintenance costs, and difficulties in device update cycle management. It adopts a unified resource scheduling method, relies on a device management server to perform device initialization configuration and usage permission setting, combines a remote management instruction execution system to push device usage policies, conducts full-process management of devices through a life cycle asset tracking module, and implements recycling and data clearing according to preset recycling standards after the device usage ends.

[0004] In the existing device management process, the judgment of memory usage mainly relies on regular monitoring and fixed thresholds set manually, resulting in the failure to detect abnormal device resources in a timely manner, which is likely to cause resource waste or device overload; the existing technology fails to combine the refined requirements of different service levels in the identification of device usage status, and cannot provide personalized support for the allocation of device resources with different service requirements, resulting in low resource scheduling efficiency; in the analysis of the device usage cycle, traditional methods lack dynamic deviation comparison based on historical data and cannot accurately identify small changes in device usage behavior, resulting in slow identification of abnormal behavior; for the determination of abnormal device status, the existing technology usually judges based on a single monitoring index and lacks cross-verification of multi-dimensional features, resulting in low identification accuracy and increasing the workload of operation and maintenance personnel. For example, in the case where the device usage frequency suddenly increases but does not exceed the load range, it may still be misjudged as abnormal, leading to unnecessary manual intervention and operation and maintenance costs. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art and propose an enterprise-level device as a service (DaaS) system.

[0006] To achieve the above object, the present invention adopts the following technical solutions: An enterprise-level device as a service (DaaS) system includes: The remote memory monitoring module obtains the real-time operation data of the devices accessing the enterprise DaaS platform, collects the current memory usage and the total available capacity, calculates the memory utilization rate, combines the device numbers and time points of the devices exceeding the memory water level threshold, and generates DaaS device resource occupancy exception items; The device usage identification module collects the start and end timestamps in the same DaaS session of the device according to the DaaS device resource occupancy exception items, calculates the session duration and compares it with the SLA grading time benchmark, marks the corresponding service level, and generates a DaaS service level attribution mark; The usage cycle mapping module numerically compares the current usage duration with the device usage frequency baseline and the task throughput baseline based on the DaaS service level attribution mark, filters out the data deviating from the preset standard, and performs device usage characteristic trajectory mapping to generate a DaaS device usage offset trajectory; The abnormal state identification module performs synchronous mapping processing through time window alignment according to the DaaS device usage offset trajectory and the device information in the DaaS device resource occupancy exception items, determines whether the resource overrun condition and the behavior deviation condition are simultaneously met, extracts the qualified data items, and generates a DaaS remote device abnormal behavior cycle identifier.

[0007] As a further solution of the present invention, the DaaS device resource occupancy exception items include device numbers, abnormal occurrence time points, and memory utilization rate deviation amplitudes. The DaaS service level attribution mark includes service level types, session durations, and SLA benchmark corresponding relationships. The DaaS device usage offset trajectory includes device usage duration deviation, device usage frequency deviation, and device task throughput deviation. The DaaS remote device abnormal behavior cycle identifier includes resource overrun status marks, behavior deviation status marks, and time window matching results.

[0008] As a further solution of the present invention, the remote memory monitoring module includes: The memory data collection sub-module obtains the device numbers and current time points of the devices accessing the enterprise DaaS platform, detects the device operation status information, monitors the current memory usage and the total available capacity of the device system memory, makes a preliminary comparison between the current usage and the total available capacity, and generates memory usage collection data; The memory utilization rate calculation sub-module analyzes the memory utilization of each device at a fixed time point by calling the current memory usage and the total available capacity of the device based on the memory usage collection data, and calculates the memory utilization rate; The resource anomaly generation submodule performs interval judgment operation based on the memory utilization, the high watermark threshold and the low watermark threshold, combines the device number exceeding the threshold interval with the corresponding time point, filters the anomaly records, and obtains the DaaS device resource occupancy anomaly items.

[0009] As a further solution of the present invention, the device usage identification module includes: The session time collection submodule obtains the device number in the DaaS device resource usage anomaly item, collects the session start timestamp and session end timestamp within the same DaaS session corresponding to the device number, checks the integrity of the start timestamp and end timestamp, and organizes them into a time pair data set corresponding to the device number to generate a device session time pair; The session duration calculation submodule reads the start timestamp and the end timestamp data based on the device session time pair, calculates the session duration of each device, adjusts the abnormal negative value to zero, and obtains the device session duration; The service level marking submodule compares the duration of the device session with the platinum, gold, and silver SLA tiered time reference values set by the enterprise side, marks the devices that meet the service level standards, and establishes a DaaS service level attribution mark.

[0010] As a further solution of the present invention, the usage cycle mapping module includes: The baseline data collection submodule obtains the device number corresponding to the DaaS service level attribution tag, collects the current usage time of the device, and simultaneously monitors the device usage frequency baseline and task throughput baseline. The device usage time, device usage frequency baseline, and task throughput baseline data are collated and merged to generate a device usage baseline data set. The numerical deviation screening submodule reads the device usage duration, the device usage frequency baseline, and the task throughput baseline based on the device usage baseline dataset, calculates the device numerical offset, compares it with a preset deviation range, screens out data items that exceed the standard, and obtains a screening offset dataset; The feature trajectory mapping submodule performs time sequence aggregation and feature trajectory reconstruction for each device number based on the filtered offset dataset, maps the filtered offset dataset into a usage trajectory trend, and establishes a DaaS device usage offset trajectory.

[0011] As a further solution of the present invention, the abnormal state identification module includes: The time window alignment submodule collects the device ID and timestamp data from the DaaS device usage offset trace and the DaaS device resource usage anomaly item, monitors the time series distribution of the two sets of data, uses a sliding time window mechanism to align the time bases of the two sets of data, adjusts the recording step size under different time sources, and establishes a synchronized time series dataset; The deviation condition determination submodule, based on the synchronized time series data set, calls the resource occupancy anomaly data item and the behavior deviation data item, extracts the resource usage value, resource baseline value, behavior actual usage value and behavior standard deviation value respectively, calculates the device synchronization offset, determines whether the resource limit condition and the behavior deviation condition are simultaneously met, filters the data items that meet the dual conditions, and generates a data set of qualified devices; The abnormal period extraction submodule collects the data points that continuously meet the conditions according to the device number and time stamp sequence based on the qualified device data set, extracts the start and end time of the continuous abnormal segment, and establishes the abnormal behavior period identification of the DaaS remote device.

[0012] As a further embodiment of the present invention, the system further comprises: The phased service tag module tracks the API call chain, IOPS indicators and resource allocation records of the device within the cycle according to the abnormal behavior cycle of the DaaS remote device, marks the service mode classification to which it belongs, binds the device number and phase type, and generates a DaaS service phase identification tag; The DaaS service stage identification tags include API call chain characteristics, IOPS change trends, and resource allocation patterns.

[0013] As a further solution of the present invention, the phased service label module includes: The periodic data tracking submodule obtains the device number and time period information in the abnormal behavior period identifier of the DaaS remote device, collects the API call chain data, IOPS indicator data and resource allocation record data of the device in the corresponding period, detects the timestamp sequence of each indicator, and organizes it into a complete indicator data chain corresponding to the device number to generate a device periodic indicator data set; The service mode classification submodule uses the device API call frequency, IOPS average, and resource allocation fluctuation data based on the device cycle indicator dataset to extract features from the three indicators of each device, summarize the device usage behavior patterns within the cycle, set service mode classification standards based on the feature extraction results, screen devices that meet each service mode range, and generate a device stage type dataset; The phase recognition label generation sub-module extracts the device number and the corresponding phase classification results based on the device phase type dataset, binds the device number with the phase type information, marks the service phase categories corresponding to each device within the cycle, and establishes the DaaS service phase recognition label.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In the present invention, by collecting the memory usage data of the device in real time and calculating the memory utilization rate, resource anomalies can be identified in a timely manner, significantly improving the real-time performance and accuracy of management; by analyzing the start and end times of device sessions and comparing them with the benchmarks of the service level agreement, refined classification of device usage can be achieved, effectively optimizing resource allocation; by comparing the deviations from baseline data such as device usage frequency and task throughput, the change trend of device usage patterns can be identified, and abnormal behaviors can be detected in advance; by performing abnormal behavior recognition through multi-dimensional feature cross-verification, the accuracy of abnormal detection can be greatly improved, reducing false alarms and missed detections; overall, the accuracy, response speed and early warning ability of device resource management are significantly improved, effectively reducing the operation and maintenance costs and extending the service life of the device. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is the system flow chart of the present invention; Figure 2 is the flow chart of the remote memory monitoring module of the present invention; Figure 3 is the flow chart of the device usage recognition module of the present invention; Figure 4 is the flow chart of the usage cycle mapping module of the present invention; Figure 5 is the flow chart of the abnormal state recognition module of the present invention; Figure 6 is the flow chart of the phase-based service label module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0017] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0018] Please refer to Figure 1 , an enterprise-level device as a service DaaS system includes: The remote memory monitoring module obtains the real-time operation data of the devices accessing the enterprise DaaS platform, collects the current usage amount and total available capacity of the system memory at fixed time points through polling, calculates the memory utilization rate, and performs an interval comparison operation with the memory water level threshold (the high water level and the low water level are predefined warning values in system resource management, set by the operation and maintenance team according to historical load data, the high water level is 80%, and the low water level is 10%). It combines the device numbers exceeding the memory water level threshold with the time points to generate DaaS device resource occupancy exception items; The device usage identification module collects the session start timestamp and session end timestamp of the device in the same DaaS session according to the device numbers in the DaaS device resource occupancy exception items. By calculating the session duration and comparing it with the SLA hierarchical time benchmark set by the enterprise side (referring to the minimum service duration standard corresponding to the platinum / gold / silver levels defined in the service level agreement), it marks the corresponding service level and generates a DaaS service level attribution mark; Based on the DaaS service level attribution mark, the usage cycle mapping module performs a numerical deviation comparison between the current usage duration and the device usage frequency baseline and the task throughput baseline (the usage frequency baseline refers to the historical average daily usage times of the device; the task throughput baseline refers to the statistical average value of the amount of tasks processed by the device per unit time), screens the data deviating from the preset standard, and performs device usage characteristic trajectory mapping to generate a DaaS device usage offset trajectory; The abnormal state recognition module performs synchronous mapping processing based on the device information in the DaaS device usage offset trajectory and the DaaS device resource occupancy anomaly items through time window alignment (the time window alignment uses a sliding time window mechanism to match time series data), and determines whether the resource overrun condition and the behavior deviation condition are both met (the behavior deviation condition means that the deviation between the actual usage pattern of the device and the historical baseline data exceeds 2 times the standard deviation of the device's historical usage pattern data (such as indicators like usage frequency, task throughput, etc.)), extracts the eligible data items, and generates a DaaS remote device abnormal behavior cycle identifier; The phased service label module tracks the API call chain, IOPS metrics, and resource allocation records of the device within the cycle according to the DaaS remote device abnormal behavior cycle identifier, marks the classified service mode (such as batch processing / real - time interaction), binds the device number and the phase type, and generates a DaaS service phase recognition label.

[0019] The DaaS device resource occupancy anomaly items include the device number, the abnormal occurrence time point, and the memory utilization deviation range. The DaaS service level attribution mark includes the service level type, the session duration, and the SLA benchmark correspondence. The DaaS device usage offset trajectory includes the device usage duration deviation, the device usage frequency deviation, and the device task throughput deviation. The DaaS remote device abnormal behavior cycle identifier includes the resource overrun status mark, the behavior deviation status mark, and the time window matching result. The DaaS service phase recognition label includes the API call chain characteristics, the IOPS change trend, and the resource allocation mode.

[0020] Please refer to Figure 2 , the remote memory monitoring module includes a memory data collection sub - module, a memory utilization calculation sub - module, and a resource anomaly generation sub - module; The memory data collection sub - module obtains the device number and the current time point of the device accessing the enterprise DaaS platform, detects the device operation status information, monitors the current usage amount and the total available capacity of the device system memory, makes a preliminary comparison between the current usage amount and the total available capacity, and generates memory usage collection data; Obtain the device numbers and the current time points of the devices accessing the enterprise DaaS platform, record the numbers for each device, such as numbers D001, D002, D003, etc. The acquisition time is based on Beijing time, and the example time is 12:00 on April 28, 2025. When detecting the device running status information, it is necessary to call the real-time status signal output by the device sensing module. A status signal value of 0 indicates that the device is off, and a status signal value of 1 indicates that the device is on. Monitor the current usage and total available capacity of the device system memory, and record the current usage value and the total capacity value respectively. For example, the current usage of device D001 at 12:00 on April 28, 2025 is 3.2GB, and the total capacity is 8GB. Make a preliminary comparison between the current usage and the total available capacity. The comparison rule is that the current usage is less than the total capacity. If the current usage is higher than the total capacity, record the abnormal device. When collecting the memory usage data and the total capacity data, form an array for all devices, such as device D001: [3.2GB, 8GB], device D002: [5.5GB, 16GB], device D003: [7.0GB, 8GB]. The above data is summarized in a table form as follows: Table 1 Device Memory Usage Data Table: ; Referring to Table 1, the table clearly lists the memory usage and total capacity information of each device at the sampling time point. Based on the above data, through the logical judgment rule, when the current usage exceeds the total capacity, it is marked as abnormal. In this example, since 7.0GB of device D003 is less than 8GB, the abnormal mark is not triggered. After the above collection and preliminary judgment, the memory usage collection data is finally generated, that is, an array containing the usage and total capacity of all normal record devices and their corresponding time points.

[0021] The memory utilization rate calculation sub-module, based on the memory usage collection data, calls the current usage and total available capacity of the device memory, analyzes the memory utilization situation of each device at a fixed time point, and calculates the memory utilization rate; Based on the memory usage collection data, first call the current usage and total available capacity of each device's memory, extract and combine each group of data. For example, for device D001, extract the 3.2GB usage and 8GB total capacity. Regarding the data relationship between the memory usage and the total capacity, calculate the memory utilization situation of each device at a fixed time point in the way of dividing the usage by the total capacity. In the specific execution process, take out the data pairs of each device in turn and perform item-by-item operations. For example, the memory utilization rate calculation of device D001 is , that is, 40%. The memory utilization rate calculation of device D002 is , that is, 34.375%. The memory utilization rate calculation of device D003 is , that is, 87.5%. The above data is calculated to form an initial result array, which are D001: [40%], D002: [34.375%], and D003: [87.5%] respectively. To ensure the consistency and accuracy of the data, it is necessary to set the rule for retaining the number of decimal places. In this embodiment, the rule of retaining two decimal places is adopted, that is, D001: 40.00%, D002: 34.38%, D003: 87.50%. In addition, during the data processing, to avoid decimal point offset or rounding error, it is necessary to introduce the standardization check of memory capacity and usage. For example, use the standard unit GB for unified processing. If there are different units such as MB and TB, they need to be unified for conversion. In this embodiment, it is assumed that all data units are GB and no conversion is required, so the ratio operation can be directly performed. Further, during the data storage process, the device number, sampling time, and memory utilization rate are combined into a record. The record example is {device number: D001, time: April 28, 2025, 12:00, memory utilization rate: 40.00%}, forming a standardized device memory utilization record table as follows: Table 2 Device Memory Utilization Record Table: ; Referring to Table 2, it can be clearly seen the memory utilization rate of each device at the corresponding time point.

[0022] Based on the memory utilization rate, the resource exception generation sub-module performs an interval judgment operation according to the high water level threshold of 80% and the low water level threshold of 10%, combines the device numbers that exceed the threshold interval with the corresponding time points, filters the abnormal records, and obtains the abnormal items of DaaS device resource occupancy; Based on the obtained memory utilization rate, first extract the memory utilization rate data corresponding to each device. For example, the memory utilization rate of device D001 is 40.00%, that of device D002 is 34.38%, and that of device D003 is 87.50%. According to the set high water level threshold of 80% and low water level threshold of 10%, perform interval judgment operations. The specific implementation steps are as follows: sequentially take out the device memory utilization rate and judge whether it meets the condition of exceeding the threshold interval, that is, the memory utilization rate is less than 10% or greater than 80%. For each device, make judgments separately. The memory utilization rate of device D001 is 40.00%, which is within the range of 10% to 80%, and is determined to be normal. The memory utilization rate of device D002 is 34.38%, which is within the range of 10% to 80%, and is determined to be normal. The memory utilization rate of device D003 is 87.50%, which is higher than the 80% threshold, and is determined to be abnormal. According to the abnormal judgment result, combine the device number exceeding the threshold interval with the corresponding time point to form an abnormal record. An example is {device number: D003, time: April 28, 2025 12:00, memory utilization rate: 87.50%}. Further, for the convenience of subsequent query and statistics, sort the abnormal records in ascending order of device number. An abnormal record table can be formed within a single sampling period as follows: Table 3 Abnormal Record Table of DaaS Device Resources: ; As shown in Table 3, within this sampling period, only device D003 was recorded as abnormal because its memory utilization rate exceeded the high water level threshold. It should be noted that in actual applications, to prevent accidental errors, it can be set that an abnormality is officially marked only when the threshold is exceeded continuously for multiple times. In this embodiment, multi-cycle verification is not introduced for the time being, and only single-cycle data is used as the judgment basis. Therefore, finally, directly screen the abnormal devices in the current cycle to obtain the abnormal items of DaaS device resource occupancy. There is no new formula operation in the above screening process, and all are based on the existing memory utilization rate values for interval comparison and judgment, and combined with the time point and device number to generate the final record.

[0023] Please refer to Figure 3 , the device usage identification module includes a session time acquisition sub-module, a session duration calculation sub-module, and a service level marking sub-module; The session time acquisition sub-module obtains the device number in the abnormal items of DaaS device resource occupancy, acquires the session start timestamp and session end timestamp within the same DaaS session corresponding to the device number, detects the integrity of the start timestamp and end timestamp, and organizes them into a time pair data set corresponding to the device number to generate a device session time pair; The session time collection sub-module, based on the device numbers in the abnormal items of DaaS device resource occupancy, first extracts the associated records of each device number, and collects the start timestamp and end timestamp data of each device in the DaaS session management system. For device number A1234, its session start time is 10:00:00 on April 15, 2024, and the end time is 14:15:00 on April 15, 2024. Record the start time Tsi = 10:00:00 and the end time Tei = 14:15:00. Detect whether there are missing or time-reversed problems in the start and end time data. If so, for example, if the start time of device number B5678 is later than the end time, correct the abnormal data or delete the record. At the same time, organize all normal timestamp data in a table structure. Each record corresponds to three fields: device number, start time, and end time. For the device numbers in the record set, if there are multiple session records, sort them in ascending order of the session start time to ensure that the session times of each device number do not overlap, and generate a standardized data set. The sorted result of the collected data is shown in the following table: Table 4 Device Session Time Pair Table: ; As shown in Table 4, device number A1234 starts a session at 10:00 on April 15, 2024, and ends at 14:15. Device number B5678 starts at 9:00 and ends at 12:30. Device number C9101 starts at 11:20 and ends at 13:00. Through the above collection process, the device session time pairs are standardized and organized.

[0024] The session duration calculation sub-module, based on the device session time pairs, reads the start timestamp and end timestamp data, calculates the session duration of each device, and adjusts abnormal negative values to zero values to obtain the device session duration; The session duration calculation sub-module, based on the device session time pairs generated by the session time collection sub-module, calls the start timestamp and end timestamp data of each device. First, it converts the timestamps into a unified standard time format such as seconds for calculation. For device number A1234, the start time 10:00:00 corresponds to 36000 seconds, the end time 14:15:00 corresponds to 51300 seconds, and the duration is 51300 - 36000 = 15300 seconds. Converted to hours, it is 4.25 hours. For the calculated duration, if a negative value appears, it is determined that the timestamp record is abnormal and the duration is set to 0 hours. Subsequently, the duration values of each device number are recorded. During this process, by dividing the time difference into intervals, sessions with a duration less than 1 hour are marked as short sessions, sessions with a duration between 1 and 3 hours are marked as medium sessions, and sessions with a duration greater than 3 hours are marked as long sessions. For example, the session time of device number C9101 is from 11:20 to 13:00. After conversion, the duration is 1 hour and 40 minutes, that is, 1.6667 hours, which is classified as a medium session, forming a duration data set, and finally obtaining the device session duration.

[0025] The service level marking sub-module, according to the device session duration, based on the platinum, gold, and silver SLA classification time benchmark values set by the enterprise side, performs an interval comparison between the duration value and the time benchmark values of each level, marks the devices that meet the service level standards, and establishes the DaaS service level attribution marking; The service level marking sub-module, based on the device session duration obtained by the session duration calculation sub-module, calls the SLA classification time benchmark values set by the enterprise side, compares the session duration of each device with the service duration standards corresponding to the platinum, gold, and silver levels, and sets the benchmark values as follows: the platinum standard is a duration greater than 4 hours, the gold standard is 2 to 4 hours, and the silver standard is 1 to 2 hours. Referring to these standards, for device number A1234, its duration is 4.25 hours, which exceeds 4 hours, so it belongs to the platinum level. The duration of device number C9101 is 1.6667 hours, which is between 1 and 2 hours, so it belongs to the silver level. The duration of device number B5678 is 3.5 hours, so it belongs to the gold level. During the differentiation process, if the duration is less than 1 hour, it is recorded as having no level attribution. Through the above judgment, the service level markings corresponding to each device are generated, and finally the DaaS service level attribution marking is established.

[0026] Please refer to Figure 4 , the usage cycle mapping module includes a baseline data collection sub-module, a numerical deviation screening sub-module, and a feature trajectory mapping sub-module; The baseline data collection sub-module obtains the device numbers corresponding to the DaaS service level attribution marks, collects the current usage duration of the devices, and simultaneously monitors the device usage frequency baseline and the task throughput baseline. It organizes and merges the device usage duration, device usage frequency baseline, and task throughput baseline data to generate a device usage baseline data set; Based on obtaining the device numbers corresponding to the DaaS service level attribution marks, collecting the current usage duration of the devices, and monitoring the device usage frequency baseline and the task throughput baseline, during the execution process of organizing and merging the device usage duration, device usage frequency baseline, and task throughput baseline data, it is first necessary to read the device list from the DaaS management system, such as device numbers A001, A002, A003, etc. For device A001, extract its most recent DaaS service level attribution information, assumed to be the gold level, and obtain the daily usage duration data within the most recent 30 days. For example, the daily usage durations of A001 are 5 hours, 6 hours, 4 hours, and 7 hours respectively. Through cumulative calculation, the total usage duration is 180 hours. Then, extract the usage frequency data of device A001 in the past 30 days. Assume that the number of times of starting a DaaS session per day for A001 is 5 times, 6 times, 4 times, and 5 times. The cumulative usage frequency baseline of device A001 is obtained as 5 times per day. Next, extract the task throughput data of A001. Assume that the number of tasks completed per day is 30 times, 28 times, 32 times, and 31 times respectively. Calculate its average task throughput in 30 days as 30.25 times. After collecting the above data, they are uniformly merged according to the device number, usage duration, usage frequency baseline, and task throughput baseline to form a device usage baseline data set. The example data is shown in Table 5.

[0027] Table 5 Device Usage Baseline Data Table: ; As shown in Table 5, the device numbers and the baseline data set are collected and organized. Among them, the usage duration of device A001 is 180 hours, the usage frequency baseline is 5 times per day, and the task throughput baseline is 30.25 times per hour. Through the above data merging, a device usage baseline data set is obtained.

[0028] Based on the device usage baseline data set, the numerical deviation screening sub-module reads the device usage duration, device usage frequency baseline, and task throughput baseline, calculates the numerical deviation between the usage duration and the baseline data, using the formula: ; Calculate the device numerical offset , compare it with the preset deviation range, screen out the data items that exceed the standard, and obtain the screened offset data set. Among them, represents the device current usage duration, represents the device The usage frequency baseline, represents the device 's task throughput baseline; Based on the device usage baseline dataset, during the numerical deviation calculation by invoking the device usage duration, the device usage frequency baseline, and the task throughput baseline, first extract the data of device A001. It is known that the device usage duration of A001 is 180 hours, the usage frequency baseline is 5 times per day, and the task throughput baseline is 30.25 times / h. Substitute them into the formula in sequence, and substitute , , into it. First, calculate the first part: ; Then calculate the second part: ; Take the absolute value and add the two terms: ; Thus, the numerical offset of device A001 is obtained as 31.96. Calculate the numerical offsets of devices A002 and A003 in the same way, and obtain 28.23 and 33.50 respectively. See Table 6.

[0029] Table 6 Numerical offset calculation table: ; As shown in Table 6, compare the device numerical offset with the offset standard set by the enterprise side. Assume the offset standard is within 30 (the offset standard value within 30 is determined based on the floating range of the single-day maximum task volume of the device in the past 30 days. Specifically, it is set according to the change range between the maximum and minimum values of the daily task throughput. In the calculation, a fluctuation range not exceeding 25% is selected as a reasonable limit. By statistically analyzing the maximum values of the single-day usage frequency and the task throughput of each device, after standardizing the fluctuations of the two, most of the device offsets are screened out to be within the normal range of 25 to 30. Therefore, the offset standard is set within 30, and this value fluctuates with the number of daily task completions and the daily usage duration of the device. When the device usage duration increases or the single-day task volume surges, the offset tends to rise, and vice versa. The set standard can effectively reflect the impact of device load changes on the overall stability), and screen out the devices exceeding 30, that is, screen out A001 and A003, and obtain the screened offset dataset.

[0030] The device numerical offset is a numerical indicator used to quantify the degree of change in the device's current usage status compared to its historical baseline characteristics. This value comprehensively considers the deviation relationship between the device's current usage time and its usage frequency baseline, as well as the deviation relationship between the usage frequency baseline and the task throughput baseline. It is obtained by standardizing and accumulating the two sets of deviations after absolute value processing. It is used to comprehensively reflect the degree of consistency between the device's current operating load mode, operating intensity and processing capacity and the historical stable state. Among them, the larger the device numerical offset value, the more obvious the deviation of the device's current usage behavior from the previous baseline. There may be phenomena such as sudden increase in usage frequency, abnormal extension of usage cycle, and increased task load fluctuation. The smaller the value, the closer the device usage status is to the historical pattern and remains within the normal fluctuation range. Therefore, in practical applications, the device numerical offset value is mainly used as an important reference for judging device status stability, monitoring load anomalies, and adjusting operation and maintenance strategies.

[0031] The overall operational logic of the formula is to comprehensively measure the numerical deviations between the device usage duration, usage frequency baseline, and task throughput baseline. First, the difference between the current usage duration and the usage frequency baseline is calculated and normalized by the square root of the task throughput baseline. The square root operation is used to reduce the direct amplification effect of the deviation results when the task throughput baseline value is large, ensuring a relatively stable deviation magnitude. Next, the direct difference between the device usage frequency baseline and the task throughput baseline is calculated and normalized using the current usage duration as the denominator. The current duration is used in the denominator because the device usage duration directly affects the task processing capacity per unit time. Therefore, a normalized method is used to measure the relative proportion of the deviation. Then, the deviation results of the two items after absolute value processing are accumulated. The absolute value operation ensures that the direction of the deviation (increase or decrease) has no effect on the final result. The accumulation operation reflects the combined effect of the usage duration deviation and the frequency and throughput deviations, thus comprehensively reflecting the overall numerical deviation between the current device usage characteristics and the historical baseline. Finally, the overall quantified numerical deviation is used as an important indicator of the change in device usage characteristics.

[0032] The feature trajectory mapping submodule performs chronological aggregation and feature trajectory reconstruction for each device number based on the filtered offset dataset, maps the filtered offset dataset into usage trajectory trends, and establishes the DaaS device usage offset trajectory; Based on the filtered offset dataset, feature trajectory mapping is performed for device numbers A001 and A003. First, the daily usage duration trends for A001 and A003 over the past 30 days are summarized chronologically, and trajectory lines are plotted. For example, the usage duration for device A001 over the past 30 days is 5 hours, 6 hours, 4 hours, and 7 hours, respectively. This data is aggregated to form a trajectory array [5, 6, 4, 7, ...]. The same process is performed for device A003, resulting in trajectory arrays. Subsequently, by combining the filtered offset dataset with the trajectory array, dates with deviations exceeding the standard are marked as outliers. For example, on the 10th day, the usage duration for A001 drops to 3 hours, and the numerical deviation is greater than the deviation standard of 30. Therefore, the 10th day is marked as an outlier. Ultimately, the offset trajectory data corresponding to the device number is generated, and the DaaS device usage deviation trajectory is established.

[0033] See also Figure 5 ,The abnormal state recognition module includes a time window alignment submodule, a deviation ,condition determination submodule, and an abnormal period extraction submodule; The time window alignment submodule collects device ID and timestamp data from DaaS device usage offset trajectories and DaaS device resource usage anomaly items, monitors the time series distribution of the two sets of data, and uses a sliding time window mechanism to align the time bases of the two sets of data. It adjusts the recording step size under different time sources to establish a synchronized time series dataset. Obtain the device number and timestamp data from the DaaS device usage offset trajectory and the DaaS device resource usage anomaly item, collect the device number and corresponding timestamp data from the device usage offset trajectory, synchronously collect the device number and recording time for the device resource usage anomaly item, monitor the arrangement and time accuracy of the two sets of data time axes, set the sliding time window width to 5 minutes, and the sliding step to 1 minute. Taking device A as an example, if the offset trajectory recording time is 10:00, 10:01, and 10:03 on April 1, 2024, and the resource anomaly recording time is 10:02, 10:03, and 10:04 on April 1, 2024, then compare them in a sliding window every minute and calculate and The difference is 2 minutes, 2 minutes, and 1 minute respectively, which are all less than the 5-minute window width. They are recorded as synchronous alignment data. During the synchronous matching process, the starting time of the sliding window is first detected. , then advance the time window in steps, and update the comparison offset trajectory and resource anomaly time in real time. If the difference meets the condition of being less than or equal to 5 minutes, the synchronization mark is completed. Assume that the offset trajectory recording time of device B is 11:00 on April 1, 2024, and the resource anomaly time is 11:10 on April 1, 2024. Then the difference between the two is 10 minutes, exceeding the window width, and no synchronization processing is performed. When establishing the synchronization time series data set, the successfully matched device numbers and timestamps are collected item by item, sorted in chronological order, and a preliminary synchronization mapping table is generated, as shown in Table 7: Table 7 Sample Table of Synchronization Time Series: ; As shown in Table 7, the offset trajectory of device A at 0 minutes matches the resource anomaly at 2 minutes, the offset trajectory at 1 minute matches the resource anomaly at 3 minutes, and the offset trajectory at 3 minutes matches the resource anomaly at 4 minutes, all meeting the synchronization conditions. Finally, a synchronization time series data set is established.

[0034] Based on the synchronization time series data set, the resource occupancy anomaly data item and the behavior offset data item are called, and the resource usage value, resource baseline value, actual behavior usage value, and behavior standard deviation value are extracted respectively. The combined difference and product accumulation method is used for joint calculation, using the formula: ; Calculate the device synchronization offset , and determine whether both the resource overlimit condition and the behavior deviation condition are met at the same time. Filter out the data items that meet the dual conditions to generate a data set of devices that meet the conditions. Among them, represents the resource occupancy of device , represents the resource baseline value of device , represents the actual usage value of device , represents the historical standard deviation value of device ; Based on the synchronization time series data set, the resource occupancy anomaly data item and the behavior offset data item are called, and the resource usage value, resource baseline value, actual behavior usage value, and behavior standard deviation value are extracted respectively for resource and behavior joint deviation analysis. First, calculate the resource occupancy deviation. Assume that the resource occupancy of device A is 60%, the resource baseline value is 45%, the behavior usage frequency is 8 times, and the historical standard deviation is 2 times. Perform the difference offset calculation. The calculation steps are as follows. First, calculate , and then take the square root to get , then calculate , take the absolute value to get , and add the two parts together to get , that is, the synchronization offset value of device A is 43.49. Referring to the synchronization offset threshold setting standard, a synchronization offset exceeding 30 is considered a serious offset. In this example, the offset of device A is 43.49, exceeding 30, so it is marked as abnormal. The specific data is shown in Table 8: Table 8 Synchronization Offset Calculation Table: ; Referring to Table 8, the synchronization offset calculated for device A is 43.49, which meets the offset condition and is extracted into the dataset of devices meeting the conditions.

[0035] The device synchronization offset represents a comprehensive quantitative index of the simultaneous occurrence of resource usage anomalies and behavior pattern deviations in a single DaaS device within the same time window. Specifically, this value quantifies the anomaly levels in the resource and behavior dimensions by combining the difference between the resource occupancy and the resource baseline value, and the deviation degree between the actual behavior usage frequency and the historical standard deviation, respectively, in the form of taking the square root of the product and the absolute value of the fraction. Then, the two parts of the anomaly amounts are superimposed into a unified value, thereby reflecting the overall comprehensive offset intensity of the device's resource load pressure and behavior change amplitude within the current time period. The larger the device synchronization offset value, the higher the overall deviation degree of the device's current state from its historical normal usage pattern, and the deviation phenomenon is simultaneously reflected in the dual characteristics of increased resource consumption anomalies and amplified operation behavior anomalies. This value can be used to screen out those devices with synchronous anomalies in resource and behavior within a certain time window, providing a direct quantitative basis for subsequent cycle anomaly identification, fault prediction, or maintenance priority division.

[0036] The operation logic of the formula is as follows: First, The part calculates the difference between the resource usage amount and the resource baseline value , and the difference between the actual behavior usage value and the behavior standard deviation , and multiplies these two deviation amounts to quantify the combined degree of resource anomaly and behavior offset. The product result can reflect the superimposed effect of the two deviation degrees. Subsequently, the absolute value of this product is taken and square-rooted, intending to reduce the amplification effect of extreme anomaly values on the overall offset amount, and at the same time ensuring that the final quantification result is positive regardless of whether the deviation direction is positive or negative. Then, The part divides the sum of the resource usage amount and the behavior usage value by the historical standard deviation to quantify the anomaly degree of the total deviation of resource and behavior relative to the normal fluctuation range. This fractional form can intuitively reflect the proportional relationship between the overall anomaly magnitude and the historical stability of the device. Then, the absolute value of this fraction is taken , ensuring that both exceeding the standard and decreasing fluctuations can be handled uniformly, and finally adding the two parts of the results, By superimposing the independent contributions of resource deviation and behavior deviation, the overall deviation degree of the device in the current time window is comprehensively evaluated to form a unified device synchronization offset value. ,This design can not only reflect the severity of a single abnormality, but also comprehensively ,consider the deviation conditions in all aspects, thus enhancing the ,overall recognition capability of double deviation abnormalities.

[0037] The abnormal cycle extraction submodule collects data points that continuously meet the conditions based on the device data set and the device number and timestamp sequence, extracts the start and end times of the continuous abnormal segments, and establishes the abnormal behavior cycle identification of the DaaS remote device; Based on the dataset of eligible devices, time series aggregation is performed for each device ID. Data records that continuously meet the offset condition are merged into a continuous segment. The segment start and end times are extracted to form an abnormal period identifier. For example, if device A meets the offset condition at 10:00, 10:01, and 10:03 on April 1, 2024, they are merged into an abnormal period starting at 10:00 on April 1, 2024, and ending at 10:03 on April 1, 2024. If device B meets the offset condition at 11:00 on April 1, 2024, but the next abnormality occurs at 11:10, the two are divided into different abnormal periods. During the period extraction process, the interval between consecutive offset records that does not exceed 5 minutes is considered the same period. If it exceeds 5 minutes, it is divided into a new period. When setting the standard interval value, refer to the regular usage interval standard of DaaS devices. The interval between continuous access operations between regular devices is less than 3 minutes, so 5 minutes is used as a reasonable upper limit. In this way, the abnormal behavior data of all devices are merged to generate a period table, as shown in Table 9: Table 9 Abnormal cycle extraction table: ; As shown in Table 9, device A is merged to form a complete abnormal cycle, and device B is divided into a separate cycle because the interval exceeds 5 minutes. Finally, the DaaS remote device abnormal behavior cycle identification is established.

[0038] See also Figure 6 ,The phased service label module includes a period data tracking submodule, a service mode classification submodule, and a phase identification label generation submodule; The periodic data tracking submodule obtains the device number and time period information in the abnormal behavior cycle identifier of the DaaS remote device, collects the API call chain data, IOPS indicator data and resource allocation record data of the device in the corresponding period, detects the timestamp sequence of each indicator, and organizes it into a complete indicator data chain corresponding to the device number to generate the device periodic indicator data set; When collecting the device number and time period information in the abnormal behavior cycle identifier of the DaaS remote device, it is first necessary to retrieve the unique number of the corresponding device and the start and end times of the recorded abnormal cycle from the background database. For example, select device number D001, start time 00:00:00 on May 1, 2024, and end time 00:00:00 on May 2, 2024. For this time range, extract all API call records of the device within the DaaS platform one by one. The record fields include API name, call start time, and call end time. Assume that the number of calls extracted is 250 times per day. Subsequently, collect the IOPS metrics of the device during the corresponding time period. IOPS refers to the number of input / output operations per second. Assume that through log reading, the average IOPS of this device is 600, and the peak reaches 900. Finally, collect the resource allocation records of the device. The resource allocation records involve the number of CPU cores allocated, the amount of memory allocated, and the amount of disk allocated. For example, the average number of CPU cores allocated to this device is 2 cores, the amount of memory allocated is 8GB, and the amount of disk allocated is 200GB. By aligning the unified time stamps for each type of data and processing in a way that takes every 5 minutes as a data synchronization node, merge each data field into a synchronization table, as shown in Table 1. Table 1 lists the synchronization data of device D001 at a sampling point.

[0039] Table 10 Synchronization Data Table of Device D001's Periodic Metrics: ; As shown in Table 10, the collection results show the API call times and IOPS fluctuations at different time points during the cycle. Through the above method, the collection and timeline synchronization integration of the metric data are completed, and a device cycle metric dataset is generated.

[0040] Based on the device cycle metric dataset, the service mode classification sub-module calls the data of the device API call frequency, IOPS mean, and resource allocation fluctuation range, extracts features for the three metrics of each device, summarizes the usage behavior patterns of the device during the cycle, compares the set service mode classification criteria according to the feature extraction results, filters the devices that meet the intervals of each service mode, and generates a device stage type dataset; Based on the device cycle metric dataset generated by the cycle data tracking sub-module, first call the device API call frequency metric. For the API call count data within the sampling cycle, calculate the average number of calls per hour and aggregate it in hours. For example, if the total number of calls for device D001 from 00:00 to 01:00 on May 01 is 280 times, then the hourly call frequency is 280 times / 1 hour = 280 times / hour. Subsequently, process the average IOPS. Extract the IOPS data at each 5-minute point and calculate the average value. Assume that a total of 12 data points are obtained from 00:00 to 01:00 on May 01, which are 600, 620, 590, 610, 580, 600, 610, 590, 600, 610, 580, 600 respectively. Then the average IOPS is (600 + 620 + 590 +......+ 610 + 580 + 600) / 12 = 599.17. After that, process the resource allocation fluctuation range, and obtain the fluctuation degree by calculating the standard deviation. Assume that the memory allocation amount remains stable at 8GB during the cycle, then the standard deviation is 0. If there is fluctuation, calculate according to the standard deviation formula based on the sampling data. Set the fluctuation threshold to 1GB. When the standard deviation is greater than 1GB, it is considered that there is significant fluctuation. Subsequently, summarize the API call frequency, average IOPS, and resource fluctuation standard deviation, and compare with the set service mode classification criteria. For example, devices with an API call frequency higher than 200 times / hour, an average IOPS higher than 500, and a resource fluctuation less than 1GB are classified as the "real-time interaction mode", otherwise they are classified as the "batch processing mode". Taking device D001 as an example, it meets the real-time interaction mode standard and is classified into the real-time interaction category. Organize the results to generate the device phase type dataset.

[0041] Based on the device phase type dataset generated by the phase identification label generation sub-module, extract the device number and the corresponding phase classification result, bind the device number and the phase type information, mark the corresponding service phase category of each device within the cycle, and establish the DaaS service phase identification label; Based on the device phase type dataset generated by the service mode classification sub-module, extract the device number and the corresponding phase classification result, bind the device number D001 with the attributed phase type "real-time interaction", and record the service mode identifier for each cycle. Assume that the device phase type changes in the subsequent time period, such as after 00:00 on May 2, the phase changes to "batch processing", then add the binding information of the timestamp and the phase type to the record, and store it in a three-field structure of device number + time period + phase type. At the same time, verify whether there is a time intersection for each record. If there is an overlap, split it according to the time priority. Finally, generate the phase label table shown in Table 2 in a standardized format. Table 2 lists the phase identification information of device D001 during the monitoring cycle.

[0042] Table 11 D001 Device Stage Identification Label Table: ; As shown in Table 11, the service stage status of device D001 in different time periods is marked to establish DaaS service stage identification labels.

[0043] The above is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical content of the technical solution of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An enterprise-level device as a service (DaaS) system, characterized in that, The system comprises: The remote memory monitoring module obtains real-time operating data from devices connected to the enterprise's DaaS platform, collects current memory usage and total available capacity, calculates memory utilization, and combines the device number and time point that exceeded the memory watermark threshold to generate DaaS device resource usage anomaly items; The device usage identification module collects the start and end timestamps of the same DaaS session of the device based on the abnormal DaaS device resource usage, calculates the session duration and compares it with the SLA tiered time benchmark, marks the corresponding service level, and generates a DaaS service level attribution tag; The usage cycle mapping module compares the current usage duration with the device usage frequency baseline and the task throughput baseline based on the DaaS service level attribution tag, filters out data that deviates from the preset standard, maps the device usage feature trajectory, and generates a DaaS device usage deviation trajectory; The abnormal state identification module performs synchronous mapping processing based on the DaaS device usage offset trajectory and the device information in the DaaS device resource occupancy abnormal item through time window alignment, determines whether the resource excess condition and the behavior deviation condition are met at the same time, extracts the data items that meet the conditions, and generates a DaaS remote device abnormal behavior cycle identifier.

2. The enterprise-level device as a service DaaS system according to claim 1, characterized in that, The DaaS device resource usage anomaly items include the device number, the time point of the anomaly occurrence, and the memory utilization deviation amplitude. The DaaS service level attribution mark includes the service level type, session duration, and SLA benchmark correspondence. The DaaS device usage deviation trajectory includes the device usage time deviation, the device usage frequency deviation, and the device task throughput deviation. The DaaS remote device abnormal behavior cycle identifier includes the resource excess status mark, the behavior deviation status mark, and the time window matching result.

3. The enterprise-level device as a service DaaS system according to claim 1, characterized in that The remote memory monitoring module includes: The memory data collection submodule obtains the device number and current time point connected to the enterprise DaaS platform, detects the device's operating status information, monitors the current usage and total available capacity of the device system memory, performs a preliminary comparison between the current usage and the total available capacity, and generates memory usage collection data; The memory utilization calculation submodule calculates the memory utilization of each device based on the memory usage collection data, calls the current memory usage and the total available capacity of the device, analyzes the memory utilization of each device at a fixed time point, and calculates the memory utilization; The resource anomaly generation submodule performs interval judgment operation based on the memory utilization, the high watermark threshold and the low watermark threshold, combines the device number exceeding the threshold interval with the corresponding time point, filters the anomaly records, and obtains the DaaS device resource occupancy anomaly items.

4. The enterprise-level device as a service DaaS system according to claim 1, wherein The device usage identification module includes: The session time collection submodule obtains the device number in the DaaS device resource usage anomaly item, collects the session start timestamp and session end timestamp within the same DaaS session corresponding to the device number, checks the integrity of the start timestamp and end timestamp, and organizes them into a time pair data set corresponding to the device number to generate a device session time pair; The session duration calculation submodule reads the start timestamp and the end timestamp data based on the device session time pair, calculates the session duration of each device, adjusts the abnormal negative value to zero, and obtains the device session duration; The service level marking submodule compares the duration of the device session with the platinum, gold, and silver SLA tiered time reference values set by the enterprise side, marks the devices that meet the service level standards, and establishes a DaaS service level attribution mark.

5. The enterprise-level device as a service DaaS system according to claim 1, characterized in that, The usage cycle mapping module includes: The baseline data collection submodule obtains the device number corresponding to the DaaS service level attribution tag, collects the current usage time of the device, and simultaneously monitors the device usage frequency baseline and task throughput baseline. The device usage time, device usage frequency baseline, and task throughput baseline data are collated and merged to generate a device usage baseline data set. The numerical deviation screening submodule reads the device usage duration, the device usage frequency baseline, and the task throughput baseline based on the device usage baseline dataset, calculates the device numerical offset, compares it with a preset deviation range, screens out data items that exceed the standard, and obtains a screening offset dataset; The feature trajectory mapping submodule performs time sequence aggregation and feature trajectory reconstruction for each device number based on the filtered offset dataset, maps the filtered offset dataset into a usage trajectory trend, and establishes a DaaS device usage offset trajectory.

6. The enterprise-level device as a service DaaS system according to claim 1, wherein The abnormal state recognition module includes: The time window alignment submodule collects the device ID and timestamp data from the DaaS device usage offset trace and the DaaS device resource usage anomaly item, monitors the time series distribution of the two sets of data, uses a sliding time window mechanism to align the time bases of the two sets of data, adjusts the recording step size under different time sources, and establishes a synchronized time series dataset; The deviation condition determination submodule, based on the synchronized time series data set, calls the resource occupancy anomaly data item and the behavior deviation data item, extracts the resource usage value, resource baseline value, behavior actual usage value and behavior standard deviation value respectively, calculates the device synchronization offset, determines whether the resource limit condition and the behavior deviation condition are simultaneously met, filters the data items that meet the dual conditions, and generates a data set of qualified devices; The abnormal period extraction submodule collects the data points that continuously meet the conditions according to the device number and time stamp sequence based on the qualified device data set, extracts the start and end time of the continuous abnormal segment, and establishes the abnormal behavior period identification of the DaaS remote device.

7. The enterprise-level device as a service DaaS system according to claim 1, characterized in that, The system further comprises: The phased service tag module tracks the API call chain, IOPS indicators and resource allocation records of the device within the cycle according to the abnormal behavior cycle of the DaaS remote device, marks the service mode classification to which it belongs, binds the device number and phase type, and generates a DaaS service phase identification tag; The DaaS service stage identification tags include API call chain characteristics, IOPS change trends, and resource allocation patterns.

8. The enterprise-level device as a service DaaS system according to claim 7, characterized in that, The phased service label module includes: The periodic data tracking submodule obtains the device number and time period information in the abnormal behavior period identifier of the DaaS remote device, collects the API call chain data, IOPS indicator data and resource allocation record data of the device in the corresponding period, detects the timestamp sequence of each indicator, and organizes it into a complete indicator data chain corresponding to the device number to generate a device periodic indicator data set; The service mode classification submodule uses the device API call frequency, IOPS average, and resource allocation fluctuation data based on the device cycle indicator dataset to extract features from the three indicators of each device, summarize the device usage behavior patterns within the cycle, set service mode classification standards based on the feature extraction results, screen devices that meet each service mode range, and generate a device stage type dataset; The stage identification label generation submodule extracts the device number and the corresponding stage classification result based on the device stage type dataset, binds the device number and stage type information, marks the service stage category corresponding to each device in the cycle, and establishes a DaaS service stage identification label.

Images