Machine room moving ring fault detection method and device, electronic equipment and storage medium

Abstract

The invention discloses a machine room moving ring fault detection method and device, electronic equipment and a storage medium, and can be widely applied to the technical field of artificial intelligence. According to the method, after the machine room dynamic environment environmental element set and the corresponding environmental element historical data set are acquired and the machine room fault tag is acquired at the same time, the machine room fault occurrence rule is generated through the proportional boosting tree model according to the machine room dynamic environment environmental element set, the environmental element historical data set and the machine room fault tag; and after the real-time data of the environmental elements are obtained, the machine room dynamic environment fault detection is carried out in combination with the machine room fault occurrence rule, so that the machine room fault detection can be completed without setting an alarm threshold depending on artificial experience, and the accuracy of the dynamic environment fault detection result in the communication machine room is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method and device for detecting dynamic environmental faults in a computer room, an electronic device, and a storage medium. Background Art

[0002] In related technologies, with the rapid development of information technology, communication rooms carry the core functions of key information infrastructure such as data transmission, service hosting, voice communication, security monitoring and equipment operation and maintenance. The dynamic environment monitoring system is an indispensable and important component to ensure the normal operation of the communication room. The core function of the dynamic environment monitoring system is to integrate various sensors and monitoring equipment to achieve comprehensive and real-time monitoring and management of the communication room environment and equipment status, and to conduct dynamic environment fault diagnosis and alarm response in a timely manner to ensure the safe, stable and efficient operation of the room. The current dynamic environment fault detection method mainly relies on manual experience to set alarm thresholds to monitor room faults. However, the manually set thresholds are limited by the subjective judgment and experience accumulation of experts, and thus cannot fully cover the complex and changeable fault modes in the communication room, resulting in possible misjudgment or missed detection in the fault diagnosis results.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The main purpose of the embodiments of the present application is to propose a method and device for detecting dynamic environmental faults in a computer room, an electronic device, and a storage medium, which can effectively improve the accuracy of the detection results of dynamic environmental faults in a communication room.

[0005] To achieve the above objectives, an embodiment of the present application provides a method for detecting dynamic environmental faults in a computer room, the method comprising the following steps:

[0006] Get the set of dynamic and environmental elements of the computer room;

[0007] Obtaining a historical data set of environmental elements corresponding to the set of dynamic and environmental environmental elements of the computer room;

[0008] Get the fault tag of the computer room;

[0009] Generate computer room fault occurrence rules through a proportional boosting tree model based on the computer room dynamic and environmental environmental factor set, the environmental factor historical data set, and the computer room fault label;

[0010] Obtain real-time data on environmental factors;

[0011] The computer room dynamic environment fault detection is performed based on the real-time data of the environmental factors and the computer room fault occurrence rules.

[0012] In some embodiments, generating a computer room fault occurrence rule by using a proportional boosting tree model based on the computer room dynamic and environmental environmental factor set, the environmental factor historical data set, and the computer room fault label includes:

[0013] Calculate a tag statistic value based on the computer room fault tag;

[0014] Initialize the cause partitioning scheme;

[0015] The set of dynamic and environmental elements of the computer room is traversed, a proportional improvement function is calculated according to the tag statistics and the historical data set of the environmental elements, and the cause classification scheme is updated, and the updated cause classification scheme is obtained as the rule for the occurrence of the computer room fault.

[0016] In some embodiments, calculating the tag statistics based on the computer room fault tag includes:

[0017] Calculate a first positive sample ratio according to the computer room fault label as the label statistical value;

[0018] Alternatively, a likelihood ratio is calculated according to the computer room fault label as the label statistical value.

[0019] In some embodiments, traversing the set of dynamic and environmental factors of the computer room, calculating a proportional improvement function based on the tag statistics and the set of historical data of the environmental factors, and updating the cause classification scheme, to obtain the updated cause classification scheme as the computer room fault occurrence rule, includes:

[0020] Traversing each environmental element of the dynamic environment element set of the computer room;

[0021] Acquire an environmental element historical data subset corresponding to each environmental element from the environmental element historical data set;

[0022] Searching for a target tangent point set of the environmental element from the environmental element historical data subset;

[0023] Calculate the proportional improvement function of the field interval to which the target tangent point set belongs based on the tag statistics and the subset of the environmental factor historical data;

[0024] The cause division scheme is updated according to the proportional improvement function and the target tangent point set to obtain the computer room failure occurrence rule.

[0025] In some embodiments, searching the target tangent point set of the environmental element from the environmental element historical data subset includes:

[0026] preprocessing the historical data in the environmental factor historical data subset;

[0027] Sort the preprocessed historical data;

[0028] Calculate the middle value of two adjacent historical data after sorting as the cut point to be selected;

[0029] Based on a preset query rule, all lifting points are queried among the candidate tangent points to form the target tangent point set.

[0030] In some embodiments, the calculation formula of the proportional improvement function is as follows:

[0031]

[0032] In the formula, Indicates the field interval; represents the target tangent point set; y represents the fault label of the computer room; α represents the environmental factor; X α represents the subset of environmental factor historical data corresponding to the environmental factor; π(·) represents the tag statistical value; Indicates maximizing the proportional improvement function in the field interval; |y| indicates taking the absolute value of y.

[0033] In some embodiments, performing computer room dynamic environment fault detection based on the real-time data of environmental factors and the computer room fault occurrence rules includes:

[0034] Obtaining a second positive sample ratio corresponding to the computer room failure occurrence rule;

[0035] Classifying the computer room fault occurrence rule into a target fault level according to the second positive sample ratio to obtain a target fault level;

[0036] The real-time data of the environmental factors is used to detect and analyze the dynamic environment faults in the computer room according to the target fault level and the fault occurrence rules of the computer room.

[0037] To achieve the above-mentioned purpose, another aspect of the present application provides a device for detecting dynamic environmental faults in a computer room, the device comprising:

[0038] The first module is used to obtain a set of dynamic and environmental elements of the computer room;

[0039] The second module is used to obtain a historical data set of environmental elements corresponding to the set of dynamic and environmental environmental elements of the computer room;

[0040] The third module is used to obtain the fault tag of the computer room;

[0041] A fourth module is configured to generate a computer room fault occurrence rule using a proportional boosting tree model based on the computer room dynamic and environmental environmental factor set, the environmental factor historical data set, and the computer room fault label;

[0042] The fifth module is used to obtain real-time data of environmental factors;

[0043] The sixth module is used to detect dynamic environment faults in the computer room based on the real-time data of the environmental factors and the rules for occurrence of computer room faults.

[0044] To achieve the above objectives, another aspect of the present application provides an electronic device, including:

[0045] at least one processor;

[0046] at least one memory for storing at least one program;

[0047] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0048] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above-mentioned method when executed by a processor.

[0049] The embodiments of the present application include at least the following beneficial effects: The present application provides a method and device for detecting dynamic and environmental faults in a computer room, an electronic device, and a storage medium. The solution obtains a set of dynamic and environmental environmental elements in the computer room and a corresponding set of historical data of environmental elements, and at the same time obtains the computer room fault label. Then, based on the set of dynamic and environmental environmental elements in the computer room, the set of historical data of environmental elements, and the computer room fault label, a computer room fault occurrence rule is generated through a proportional boosting tree model. Then, after obtaining real-time data of environmental elements, dynamic and environmental fault detection in the computer room is performed in combination with the computer room fault occurrence rule. Therefore, the computer room fault detection can be completed without relying on manual experience to set the alarm threshold, thereby effectively improving the accuracy of the dynamic and environmental fault detection results in the communication room. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flow chart of a method for detecting dynamic environmental faults in a computer room provided by an embodiment of the present application;

[0051] Figure 2 This is a flow chart for generating a computer room fault occurrence rule provided by an embodiment of the present application;

[0052] Figure 3 This is a sub-flowchart of step S230 provided in an embodiment of the present application;

[0053] Figure 4 This is a flow chart of searching for a target tangent point set of environmental elements from a subset of environmental element historical data provided by an embodiment of the present application;

[0054] Figure 5This is a flowchart of fault judgment based on computer room fault occurrence rules provided by an embodiment of the present application;

[0055] Figure 6 This is a schematic diagram of the training set corresponding to the environmental elements of computer room A provided in an embodiment of the present application;

[0056] Figure 7 This is a schematic diagram of a test set corresponding to the environmental elements of computer room A provided in an embodiment of the present application;

[0057] Figure 8 This is a flowchart of the environmental elements traversal in computer room A provided by an embodiment of the present application;

[0058] Figure 9 This is a schematic diagram of the structure of the device for detecting dynamic environmental faults in a computer room provided by an embodiment of the present application;

[0059] Figure 10 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are merely examples of devices and methods consistent with some aspects of the embodiments of the present application.

[0061] It will be understood that the terms "first", "second", etc. used in this application may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0062] The terms "at least one", "plurality", "each", "any", etc. used in this application include "at least one", "two" or more, "plurality" or "each", "any" or "any one", "each" or "any one" as used herein.

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0064] Before describing the embodiments of the present application in detail, some of the nouns and terms involved in the embodiments of the present application are first explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations:

[0065] Artificial Intelligence (AI) is a technology system that simulates human thinking and behavior patterns, allowing computer systems to perform tasks such as learning, reasoning, and decision-making. Its core lies in achieving autonomous perception, analysis, and action through algorithms and big data.

[0066] Dynamic Environmental Monitoring (DEM) refers to a system that monitors and manages dynamic changes in natural or industrial environments through real-time, continuous data collection and analysis. Its core goal is to leverage technologies such as sensors, the Internet of Things (IoT), big data, and artificial intelligence to enable real-time tracking, early warning, and control of environmental parameters such as temperature, humidity, air quality, noise, and vibration.

[0067] In dynamic environment monitoring, the dynamic environment refers to the dynamically changing physical environment. Specifically, it refers to the comprehensive status of power, environmental, and security systems in scenarios such as computer rooms, industrial facilities, and public spaces that require real-time monitoring and management. Changes in the physical environment can be reflected through real-time variations in environmental parameters such as temperature, humidity, voltage, and device status. These parameters must be continuously tracked through sensors and automated systems.

[0068] The proportional boosting tree refers to a set of element series rules for generating dynamic environment faults in the computer room by maximizing the proportional boosting function strategy.

[0069] A flood detector is a sensor designed specifically to detect flooding. It is commonly used in warehouses, machine rooms, cable trenches, and other locations requiring waterproofing. Once a leak is detected, the sensor immediately sounds an alarm to prevent damage caused by the leak.

[0070] Smoke detectors are primarily used to detect smoke and are often used in fire warning systems. When the smoke sensor detects smoke, the smoke detector will sound an alarm to alert people to the risk of fire.

[0071] The temperature and humidity sensor is used to detect temperature and humidity and convert the detected temperature and humidity into a usable output signal.

[0072] Switching power supply status monitoring is a technology that monitors and detects the operating status of switching power supply equipment.

[0073] In related technologies, communications rooms typically host core functions of critical information infrastructure, including data transmission, service hosting, voice communications, security monitoring, and equipment operation and maintenance. The dynamic environment monitoring system is an essential component for ensuring the normal operation of the room, and its stability is particularly critical. The core function of the dynamic environment monitoring system is to integrate various sensors and monitoring equipment to achieve comprehensive, real-time monitoring and management of the communications room environment and equipment status, conduct timely fault diagnosis and alarm response, and ensure the safe, stable, and efficient operation of the room. Therefore, improving the accuracy of fault monitoring in the dynamic environment monitoring system is crucial to ensuring the safe operation of the room's communication equipment.

[0074] Current dynamic environment monitoring methods in dynamic environment monitoring systems primarily rely on manual experience to set alarm thresholds to monitor computer room failures. This manually set threshold method is limited by the subjective judgment and accumulated experience of experts and may not fully cover the complex and changing failure modes within the computer room, resulting in potential problems being missed or misjudged. For example, when a computer room failure occurs, if the alarm threshold is set too high or too low, the risk of missed or false alarms in the dynamic environment monitoring system increases, thereby affecting the operational reliability of the dynamic environment monitoring system and the speed of its response to computer room failures. Therefore, it can be seen that the accuracy of existing dynamic environment monitoring methods in detecting the dynamic environment in the computer room is not high.

[0075] In view of this, an embodiment of the present application provides a method and device for detecting dynamic and environmental faults in a computer room, an electronic device, and a storage medium. The embodiment of the present application generates computer room fault occurrence rules through a proportional boosting tree model based on a set of computer room dynamic and environmental environmental elements, a set of historical data of environmental elements, and computer room fault labels. Then, based on the relationship between the generated computer room fault occurrence rules and the real-time data of environmental elements, it is judged whether a fault will occur in the computer room. Therefore, the computer room fault detection can be completed without relying on manual experience to set the alarm threshold, thereby effectively improving the accuracy of the dynamic and environmental fault detection results in the communication room.

[0076] The method for detecting dynamic environmental faults in a computer room provided in the embodiment of the present application relates to the field of artificial intelligence technology. The method for detecting dynamic environmental faults in a computer room provided in the embodiment of the present application can be applied to a terminal, can be applied to a server, or can be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements the method for detecting dynamic environmental faults in a computer room, etc., but is not limited to the above forms.

[0077] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0078] The following is a detailed description of the embodiments of the present application with reference to the accompanying drawings:

[0079] Figure 1 This is an optional flowchart of the method for detecting dynamic environment faults in a computer room provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S110 to S160:

[0080] Step S110: Obtain a set of dynamic and environmental elements of the computer room;

[0081] Step S120: Obtain a historical data set of environmental elements corresponding to the dynamic and environmental environmental element set of the computer room;

[0082] Step S130: Obtain the equipment room fault tag;

[0083] Step S140: Generate computer room fault occurrence rules using a proportional boosting tree model based on the computer room dynamic and environmental environmental factor set, the environmental factor historical data set, and the computer room fault label;

[0084] Step S150: Acquire real-time data of environmental factors;

[0085] Step S160: Perform computer room dynamic environment fault detection based on real-time environmental factor data and computer room fault occurrence rules.

[0086] It is understandable that the environmental factors in the dynamic environment factor set of the computer room in this embodiment may include but are not limited to temperature, humidity, current, voltage, water immersion, door magnetism and smoke detection. The data in the environmental factor historical data set include but are not limited to the measured data corresponding to each environmental factor. For example, for the environmental factor (temperature), the corresponding environmental factor historical data may include but are not limited to 35.5℃, 38℃, 45℃, etc.; for the environmental factor (humidity), the corresponding environmental factor historical data may include but are not limited to 41.3%RH, 50%RH, 39.6%RH, etc. Specifically, the data in the environmental factor historical data set of this embodiment may be the data collected by the corresponding sensor before the current time node. It is understandable that when the dynamic environment fault detection is performed at 11:50 on January 1, 2025, the data in the corresponding environmental factor historical data set of this embodiment is the data collected in real time by the corresponding sensor before 11:50 on January 1, 2025. After a test is completed at 11:55 on January 1, 2025, the historical data of environmental factors collected at 11:55 on January 1, 2025 will also be saved in the data set to update the data in the data set and ensure the real-time nature of the data in the data set.

[0087] It will be appreciated that the computer room fault tag in this embodiment is used to indicate whether a fault has occurred in the computer room at a certain point in time. A "yes" can indicate a fault has occurred, while a "no" can indicate no fault has occurred. This embodiment can generate computer room fault occurrence rules by obtaining all computer room fault tags within a corresponding time period from a set of historical environmental factor data, thereby effectively improving the accuracy of the generated computer room fault occurrence rules.

[0088] In the embodiment of the present application, after obtaining the computer room dynamic environment element set, the environmental element historical data set and the computer room fault label, the computer room fault occurrence rule is generated by the proportional boosting tree model based on the computer room dynamic environment element set, the environmental element historical data set and the computer room fault label. Specifically, Figure 2 As shown, the process of generating the computer room fault occurrence rule includes but is not limited to steps S210 to S230:

[0089] Step S210: Calculate the tag statistics based on the computer room fault tag;

[0090] Step S220: Initialize the cause classification scheme;

[0091] Step S230: traverse the set of dynamic and environmental elements of the computer room, calculate the proportional improvement function according to the tag statistics and the historical data set of environmental elements, and update the cause classification scheme, and obtain the updated cause classification scheme as the computer room fault occurrence rule.

[0092] Specifically, the label statistics are used to characterize the content of various labels in the computer room fault labels used in the current normal process of generating computer room fault occurrence rules. Characterization can be performed using the ratio between the label positive sample content and the label negative sample content, or using the ratio between the label positive sample content and the label total sample content, or using the ratio between the label negative sample content and the label total sample content. At the same time, other characterization methods that can characterize the relationship between label sample content can also be used for characterization. The specific characterization method can be selected according to actual conditions.

[0093] In the embodiment of the present application, taking the ratio between the positive sample content of the label and the total sample content of the label as an example, the process of calculating the first positive sample ratio as the label statistical value based on the computer room fault label in this embodiment is shown in Formula 1:

[0094]

[0095] In formula 1, π(·) represents the proportion of the first positive sample; Indicates the number of positive label samples after division; Indicates the number of labeled negative samples after division.

[0096] Since the total computer room fault label contains only positive label samples and negative label samples, the proportion of negative label samples can be obtained by calculating the proportion of positive label samples in the total computer room fault label. This embodiment can provide effective data support for the subsequent process of generating computer room fault occurrence rules by calculating the proportion of positive label samples or negative label samples.

[0097] In the embodiment of the present application, the likelihood ratio can also be used to characterize the content of various tags in the machine room fault tag. Specifically, the likelihood ratio is a statistical indicator used to measure the probability of an event occurring, which can be calculated using Formula 2:

[0098]

[0099] In formula 2, π(·) represents the likelihood; Indicates the number of positive label samples after division; m -Indicates the number of negative label samples before division; m + Indicates the number of positive label samples before division; Indicates the number of labeled negative samples after division.

[0100] It can be understood that this embodiment obtains the likelihood of the computer room fault label by calculation, and then the probability of the occurrence of events corresponding to the positive and negative label samples in all computer room fault labels can be determined by the likelihood, thereby providing effective data support for the subsequent generation process of computer room fault occurrence rules.

[0101] Specifically, when the computer room failure rule needs to be regenerated at the current time point, the cause planning scheme will be initialized first, that is, the cause planning scheme will be set. Represents an empty set, so that the currently generated computer room fault occurrence rules are all generated based on the analysis of the latest data, thereby making the currently generated computer room fault occurrence rules consistent with the current actual situation.

[0102] It is understandable that after completing the initialization operation of the cause planning scheme, this embodiment generates the rules for the occurrence of computer room failures by traversing the environmental factors in the computer room dynamic environment factor set and combining the tag statistics and the historical data set of environmental factors. Specifically, Figure 3 As shown, the process of generating a computer room fault occurrence rule by traversing the environmental factors in the computer room dynamic environment factor set includes but is not limited to steps S310 to S350:

[0103] Step S310: traverse each environmental element of the computer room dynamic environment element set;

[0104] Step S320: Obtain an environmental element historical data subset corresponding to each environmental element from the environmental element historical data set;

[0105] Step S330: Searching for a target tangent point set of environmental elements from the environmental element historical data subset;

[0106] Step S340: Calculate the proportional improvement function of the field interval to which the target tangent point set belongs based on the tag statistics and the subset of environmental factor historical data;

[0107] Step S350: Update the cause classification scheme according to the proportional improvement function and the target tangent point set to obtain the rules for the occurrence of computer room failures.

[0108] Specifically, this embodiment can traverse the set of dynamic and environmental elements of the computer room in sequence Each environmental factor in the room is used to iteratively generate the rules for the occurrence of computer room failures; or the computer room dynamic and environmental factor set can be After all environmental factors in the computer room are classified into categories to obtain the corresponding subset of computer room dynamic environment factors for each category, the environmental factors in each computer room dynamic environment factor subset are traversed in turn, and the computer room fault occurrence rules are iteratively generated. For example, assuming that the computer room dynamic environment factor set includes environmental factors such as temperature, humidity, current, voltage, water immersion, door magnet and smoke detector, this embodiment can iteratively generate computer room fault occurrence rules by traversing the historical data subsets of environmental factors under these environmental factors such as temperature, humidity, current, voltage, water immersion, door magnet and smoke detector in turn; this embodiment can also divide temperature and humidity into computer room environmental factor subsets; divide current and voltage into computer room equipment factor subsets; divide water immersion, door magnet and smoke detector into computer room safety factor subsets, and then iteratively generate computer room fault occurrence rules based on the historical data subsets of environmental factors under the environmental factors in each subset after traversing the computer room environmental factor subsets, computer room equipment factor subsets and computer room safety factor subsets in turn.

[0109] It is understandable that if Figure 4 As shown, the process of searching for a target tangent point set of environmental elements from a subset of environmental element historical data in this embodiment includes, but is not limited to, steps S410 to S440:

[0110] Step S410: pre-processing the historical data in the environmental factor historical data subset;

[0111] Step S420: sorting the pre-processed historical data;

[0112] Step S430: Calculate the middle value of two adjacent historical data after sorting as the cutting point to be selected;

[0113] Step S440: Based on the preset query rules, all lifting points in the candidate tangent points are searched to form a target tangent point set.

[0114] Specifically, the preprocessing process of this embodiment can be to normalize all historical data in the training set, round them according to the number of floating-point digits, and then take the rounded unique value as the representative value of the historical data. Then, after sorting all the representative values, take the middle value between two adjacent representative values ​​as the candidate cut-off point, and then query all the improvement points in the candidate cut-off points based on the preset query rules to form a target cut-off point set. It can be understood that the process of querying the target cut-off point set based on the preset query rules can be to find an improvement point under the candidate cut-off point, which can ensure that there is an improvement in one ratio and a certain decrease in the other ratio after the cut-off interval, and then find an improvement point in the sub-interval after the cut-off until there is no improvement point or the maximum number of sub-intervals M is reached or the number of samples in the cut-off interval is less than the sample threshold γ after the cut-off. In addition, the query process of this embodiment allows environmental factor data and factor cut-off point data to be located in different fields under the same subset (i.e., heterogeneous cut-off points).

[0115] For example, for searching for a target tangent point set under a certain environmental factor α Assuming that the environmental factor α is temperature, all temperature values ​​in the training set corresponding to the temperature are sorted from small to large, and then the middle value between the two adjacent temperature values ​​after sorting is found as the target cut point. After completing the middle value query process of all adjacent temperature values, all the middle values ​​are combined into the target cut point set

[0116] It is understandable that the field interval of this embodiment can be a data segment of the data corresponding to an environmental factor. For example, assuming that the minimum value of the temperature data is 10°C and the maximum value is 60°C, then 30°C-40°C can be a field interval. This embodiment calculates the proportional improvement function of the field interval to which the target tangent point set belongs using Formula 3:

[0117]

[0118] In formula 3, Indicates the field interval; represents the target tangent point set; y represents the fault label of the computer room; α represents the environmental factor; X α represents the subset of historical data of environmental factors corresponding to the environmental factors; π(·) represents the label statistics; Indicates maximizing the proportional improvement function in the field interval; |y| means taking the absolute value of y.

[0119] This embodiment maximizes the proportional improvement function within the field interval, thereby obtaining the optimal target tangent point set.

[0120] It is understandable that, after obtaining the set of dynamic and environmental environmental factors of the computer room, the tag statistics, and the set of historical data of environmental factors, this embodiment generates the computer room fault occurrence rule through the following process:

[0121] Step 1: Traverse all environmental element sets and search for the target tangent point set under a certain environmental element α in the environmental element set So that the corresponding field interval can maximize the proportional improvement function;

[0122] Step 2: Update the cause planning plan

[0123] Step 3: Record environmental factors α and target tangent point set Proportion improvement area Proportion reduction area

[0124] Step 4: Immediately test the proportion improvement area in the test set If the label positive sample ratio can also be improved during the test, the ratio improvement area is retained; otherwise, the ratio improvement area is deleted;

[0125] Step 5: For the proportion improvement area Traverse with exploration probability ε and the environment factor α does not belong to the same subset The environmental factors belong to the same subset as the environmental factor α with a probability of 1-ε For environmental factors, perform steps 1 to 4; for areas with reduced proportions The traversal and the environment element α do not belong to the same subset If the environmental factors are correct, perform steps 1 to 4;

[0126] Step 6: Repeat step 6 until the proportional improvement function is 0 when searching for tangent points in all areas or all environmental elements are traversed, then the algorithm stops.

[0127] Step 7: Use the latest updated cause planning scheme as the rule for the occurrence of the computer room failure.

[0128] In the embodiment of the present application, the ratio in the ratio increasing area and the ratio decreasing area can be the ratio of the positive label samples to the total label samples, or the ratio between the positive label samples and the negative label samples. By determining the ratio increasing area and the ratio decreasing area, this embodiment can use different methods to perform the tangent point search to improve the accuracy of the tangent point search results.

[0129] It is understandable that this embodiment involves Indicates the element set to which the environmental element α belongs; Indicates is the complement operator of the whole set; Indicates is the complement operator of the whole set; Represents a collection of dynamic and environmental elements of a computer room.

[0130] Specifically, after obtaining the computer room fault occurrence rules, this embodiment can judge the real-time data of environmental factors based on the computer room fault occurrence rules to determine whether a dynamic environment fault occurs in the computer room. It is understandable that if Figure 5 As shown, the process of fault diagnosis based on the computer room fault occurrence rule includes but is not limited to steps S510 to S530:

[0131] Step S510: Obtain a second positive sample ratio corresponding to the computer room failure occurrence rule;

[0132] Step S520: Classify the computer room fault occurrence rules into target fault levels according to the second positive sample ratio to obtain a target fault level;

[0133] Step S530: Perform computer room dynamic environment fault detection and analysis on the real-time data of environmental factors according to the target fault level and computer room fault occurrence rules.

[0134] Specifically, each machine room fault occurrence rule in this embodiment has a label positive sample ratio between 0 and 1. Different label positive sample ratios correspond to different fault levels. Since positive label samples indicate a fault has occurred, and negative label samples indicate a fault has not occurred, a larger second positive sample ratio within a machine room fault occurrence rule indicates a higher corresponding fault level; a smaller second positive sample ratio within a machine room fault occurrence rule indicates a lower corresponding fault level.

[0135] It can be understood that after obtaining the target fault level and the computer room fault occurrence rules, this embodiment can visualize the target fault level and the computer room fault occurrence rules, so that when the staff obtains real-time data of environmental factors, they can refer to the visualized target fault level and computer room fault occurrence rules to quickly locate whether a fault has occurred and the cause of the fault.

[0136] In some embodiments, taking computer room A in a real-world scenario as an example, assume that a data collector is located within computer room A and is equipped with various monitoring devices, including temperature and humidity sensors, smoke detectors, flood detectors, and power supply status monitoring. These devices collect various parameters of the computer room environment and equipment, such as temperature, humidity, current, voltage, power status, flooding, smoke detection, and access control status. The sensors transmit the monitoring data to the collector, and once the data reaches a preset alarm condition, an alarm signal is triggered.

[0137] In the simulation environment, it is assumed that all the equipment in the A computer room environment is connected and operating normally. The monitoring device can monitor the environmental parameter signals, power equipment signals and safety monitoring signals, providing effective data support for subsequent fault warning and diagnosis. Based on the actual needs and data characteristics of the computer room operation and maintenance, this embodiment classifies and combines the monitored environmental parameters, power equipment signals and safety monitoring signals, which are environmental factors. Specifically, this embodiment classifies temperature and humidity into one category as key indicators of computer room environmental comfort, collectively referred to as the computer room environmental factor set; water immersion, door magnets, and smoke detectors are classified into one category as important monitoring objects for computer room safety, collectively referred to as the computer room safety factor set; current and voltage are classified into one category directly related to the operating status of the power equipment, collectively referred to as the computer room equipment factor set. This embodiment can simplify the iteration complexity through classification, and can also improve the correlation between features, thereby improving the accuracy of the computer room fault occurrence rules.

[0138] To ensure the accuracy and reliability of the data, this embodiment can preprocess the massive amount of data collected in the recent period to ensure the data quality of the input proportional boosting tree model. Based on the historical fault records, each data item is labeled as a fault (positive sample) or no fault (negative sample). Finally, the data is input into the proportional boosting tree model to generate multiple computer room fault occurrence rules. Specifically, each computer room fault occurrence rule has a positive sample ratio between 0 and 1. According to the ratio, they are sorted and divided into three levels: high, medium, and low, each corresponding to a target fault level.

[0139] After obtaining the rules for the occurrence of computer room faults, this embodiment collects new data once a second and visualizes the rules for the occurrence of computer room faults and the corresponding target fault levels as a reference for professional maintenance personnel. At the same time, relevant field intervals and target intersection points can also be visualized in the interactive interface, making it convenient for professional maintenance personnel to quickly locate whether a fault has occurred and the cause of the fault based on specific rules.

[0140] Specifically, Figure 6 The data of the environmental factors of computer room A during a certain period of time is used as the training set. Figure 7 The data of the environmental factors of the A computer room during a certain period of time is used as a training set to generate the rules for the occurrence of computer room failures. Figure 6 and Figure 7 The temperature and humidity are defined as the computer room environment factor R1; the current and voltage are defined as the computer room equipment factor R2; and the water immersion, door magnetic, and smoke detector are defined as the computer room safety factor R3. The occurrence of a fault is considered a positive sample, and the sample positive-negative ratio statistical function is selected, and the sample fault ratio is calculated to be 0.3. The initialization scheme is And set the exploration rate to 0.5.

[0141] After the above division and setting, the present embodiment Figure 8 As shown in Figure 1, in the computer room environment factor R1 of computer room A, all the intersection points of the two environmental factors are traversed, and it is found that when the temperature is greater than or equal to 39.5, the maximum value of the proportional improvement function is 0.175. Therefore, the temperature greater than or equal to 39.5 is selected as the proportional improvement area, and the temperature less than 39.5 is selected as the proportional reduction area. In the test data set, it is verified that the positive sample ratio also increases when the temperature is greater than or equal to 39.5. Therefore, the cause division scheme is added Then, when the temperature is greater than or equal to 39.5, we traverse R1 in the computer room environment element with an exploration rate of 0.5. Assuming that exploration is required, but no ratio improvement interval is found in the remaining set, no further exploration is done. For the temperature reduction area <39.5, we traverse the tangent points in all element sets in the computer room equipment element R2 and find that when the voltage is greater than or equal to 60.5, the ratio improvement function is as large as 0.047. In the test data set, it is verified that the positive sample ratio also increases when the voltage is greater than or equal to 60.5. Therefore, the cause partitioning scheme is added At this point, all faulty samples are within the proportional improvement range, so the algorithm ends and outputs the data center fault occurrence rule. The final data center fault occurrence rule is determined to be a high-alert fault when the temperature is greater than or equal to 39.5 or when the temperature is less than 39.5 and the voltage is greater than or equal to 60.5.

[0142] It can be seen from the above experiments that the method of the embodiment of the present application has higher interpretability. Compared with the empirical threshold of the traditional method, the method of the embodiment of the present application can provide a more accurate estimation interval, and increase the accuracy of fault alarm from the original 72.8% to 98.4%, effectively improving the accuracy of dynamic environment fault detection results in the communication room.

[0143] Reference Figure 9 The embodiment of the present application provides a device for detecting faults in a computer room, the device comprising:

[0144] The first module 910 is used to obtain a set of dynamic and environmental factors of the computer room;

[0145] The second module 920 is used to obtain a historical data set of environmental factors corresponding to a set of dynamic and environmental factors of the computer room;

[0146] The third module 930 is used to obtain a fault tag of the computer room;

[0147] The fourth module 940 is configured to generate a computer room fault occurrence rule using a proportional boosting tree model based on the computer room dynamic and environmental environmental factor set, the environmental factor historical data set, and the computer room fault label;

[0148] The fifth module 950 is used to obtain real-time data of environmental factors;

[0149] The sixth module 960 is used to detect dynamic environment faults in the computer room based on real-time data of environmental factors and computer room fault occurrence rules.

[0150] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0151] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the above method when executing the computer program. The electronic device can be any smart terminal including a tablet computer, an in-vehicle computer, or the like.

[0152] It can be understood that the contents of the above method embodiments are applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0153] See also Figure 10 , Figure 10 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0154] The processor 1010 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0155] The memory 1020 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1020 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1020 and is called by the processor 1010 to execute the above-mentioned methods of the embodiments of this application.

[0156] Input / output interface 1030, used to implement information input and output;

[0157] Communication interface 1040, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0158] bus 1050 , which transmits information between various components of the device (e.g., processor 1010 , memory 1020 , input / output interface 1030 , and communication interface 1040 );

[0159] The processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 are connected to each other in communication within the device via a bus 1050 .

[0160] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and the computer program implements the above method when executed by a processor.

[0161] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiment, the functions specifically implemented by the present storage medium embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0162] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0163] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0164] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0165] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0166] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0167] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0168] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0169] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0170] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0171] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0172] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0173] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A method for detecting dynamic environment faults in a machine room, characterized in that: The method comprises the following steps: Get the set of dynamic and environmental elements of the computer room; Obtaining a historical data set of environmental elements corresponding to the set of dynamic and environmental environmental elements of the computer room; Get the fault tag of the computer room; Generate computer room fault occurrence rules through a proportional boosting tree model based on the computer room dynamic and environmental environmental factor set, the environmental factor historical data set, and the computer room fault label; Obtain real-time data on environmental factors; The computer room dynamic environment fault detection is performed based on the real-time data of the environmental factors and the computer room fault occurrence rules.

2. The method according to claim 1, characterized in that The generating of a computer room fault occurrence rule by a proportional boosting tree model based on the computer room dynamic and environmental environmental factor set, the environmental factor historical data set, and the computer room fault label includes: Calculate a tag statistic value based on the computer room fault tag; Initialize the cause partitioning scheme; The set of dynamic and environmental elements of the computer room is traversed, a proportional improvement function is calculated according to the tag statistics and the historical data set of the environmental elements, and the cause classification scheme is updated, and the updated cause classification scheme is obtained as the rule for the occurrence of the computer room fault.

3. The method according to claim 2, characterized in that The calculating of the label statistics according to the computer room fault label includes: Calculate a first positive sample ratio according to the computer room fault label as the label statistical value; Alternatively, a likelihood ratio is calculated according to the computer room fault label as the label statistical value.

4. The method according to claim 2, characterized in that The step of traversing the set of dynamic and environmental elements of the computer room, calculating a proportional improvement function based on the tag statistics and the set of historical data of the environmental elements, and updating the cause classification scheme, to obtain the updated cause classification scheme as the computer room fault occurrence rule, includes: Traversing each environmental element of the dynamic environment element set of the computer room; Acquire an environmental element historical data subset corresponding to each environmental element from the environmental element historical data set; Searching for a target tangent point set of the environmental element from the environmental element historical data subset; Calculate the proportional improvement function of the field interval to which the target tangent point set belongs based on the tag statistics and the subset of the environmental factor historical data; The cause division scheme is updated according to the proportional improvement function and the target tangent point set to obtain the computer room failure occurrence rule.

5. The method according to claim 4, characterized in that The step of searching for a target tangent point set of the environmental element from the environmental element historical data subset includes: preprocessing the historical data in the environmental factor historical data subset; Sort the preprocessed historical data; Calculate the middle value of two adjacent historical data after sorting as the cut point to be selected; Based on a preset query rule, all lifting points are queried among the candidate tangent points to form the target tangent point set.

6. The method according to claim 4, characterized in that The calculation formula of the proportional improvement function is as follows: In the formula, Indicates the field interval; represents the target tangent point set; y represents the fault label of the computer room; α represents the environmental factor; X α represents the subset of environmental factor historical data corresponding to the environmental factor; π(·) represents the tag statistical value; L represents maximizing the proportional improvement function in the field interval; |y| represents taking the absolute value of y.

7. The method according to claim 1, characterized in that Performing computer room dynamic environment fault detection based on the real-time data of environmental factors and the computer room fault occurrence rules includes: Obtaining a second positive sample ratio corresponding to the computer room failure occurrence rule; Classifying the computer room fault occurrence rule into a target fault level according to the second positive sample ratio to obtain a target fault level; The real-time data of the environmental factors is used to detect and analyze the dynamic environment faults in the computer room according to the target fault level and the fault occurrence rules of the computer room.

8. A device for detecting faults in a machine room's dynamic environment, characterized in that: The device comprises: The first module is used to obtain a set of dynamic and environmental elements of the computer room; The second module is used to obtain a historical data set of environmental elements corresponding to the set of dynamic and environmental environmental elements of the computer room; The third module is used to obtain the fault tag of the computer room; A fourth module is configured to generate a computer room fault occurrence rule using a proportional boosting tree model based on the computer room dynamic and environmental environmental factor set, the environmental factor historical data set, and the computer room fault label; The fifth module is used to obtain real-time data of environmental factors; The sixth module is used to detect dynamic environment faults in the computer room based on the real-time data of the environmental factors and the rules for occurrence of computer room faults.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images