CN117891234A - Method and device for detecting running state of machine room, storage medium and electronic equipment - Google Patents

Abstract

The application discloses a method and a device for detecting the running state of a machine room, a storage medium and electronic equipment. Relates to the field of artificial intelligence. The method comprises the following steps: acquiring an operation parameter set of a machine room; grouping a plurality of operation parameters in an operation parameter set according to the equipment type of equipment to which each operation parameter belongs to obtain M groups of operation parameters, wherein M is a positive integer; determining a detection flow corresponding to each equipment type, and processing a group of related operation parameters by using the detection flow corresponding to each equipment to obtain a processing result; and determining the operation state of the machine room according to M processing results of the M groups of operation parameters. The application solves the problems that the timeliness of determining the abnormal state of the equipment is poor and the normal operation of the service is affected in the related technology.

Description

Method and device for detecting running state of machine room, storage medium and electronic equipment

Technical Field

The application relates to the field of artificial intelligence, in particular to a method and a device for detecting the running state of a machine room, a storage medium and electronic equipment.

Background

The machine room is an extremely important infrastructure, and the safe and stable operation of the machine room has great significance for the business development of banks. Power supplies, air conditioners, cabinets, physical servers, network devices, etc. are typically centrally located in a bank's machine room for management and maintenance. Currently, with the continuous development of bank electronization, common basic software such as an operating system, a database, middleware, virtual service and the like and application software are all run on a physical server, so that normal processing of daily business of the bank is supported.

An important means of the current bank for quickly identifying and distinguishing the states of all devices in a machine room is monitoring, and the current bank mainly comprises information such as a power supply running state, an air conditioner running state, a physical server hardware running state, software running states and the like. The current monitoring mode method has obvious defects: (1) The monitoring information of each operation device is scattered in different nodes, so that effective management is difficult to obtain; (2) The abnormal occurrence of each operation device can be monitored only under the abnormal condition, and at the moment, the device is operated abnormally, so that the operation business in the machine room is influenced.

Aiming at the problems that the timeliness of determining the abnormal state of the equipment is poor and the normal operation of the service is affected in the related technology, no effective solution is proposed at present.

Disclosure of Invention

The application provides a method and a device for detecting the running state of a machine room, a storage medium and electronic equipment, and aims to solve the problem that the timeliness of determining the abnormal state of the equipment in the related technology is poor, so that the normal running of a service is affected.

According to one aspect of the application, a method for detecting an operation state of a machine room is provided. The method comprises the following steps: acquiring an operation parameter set of a machine room; grouping a plurality of operation parameters in an operation parameter set according to the equipment type of equipment to which each operation parameter belongs to obtain M groups of operation parameters, wherein M is a positive integer; determining a detection flow corresponding to each equipment type, and processing a group of related operation parameters by using the detection flow corresponding to each equipment to obtain a processing result; and determining the operation state of the machine room according to M processing results of the M groups of operation parameters.

Optionally, in the case that the device type is a network device, processing the associated set of operation parameters by using a detection flow corresponding to each device, to obtain a processing result includes: inputting a first operation parameter of the network equipment into a prediction model to obtain a prediction result, wherein the prediction result comprises a plurality of prediction values, the prediction model is obtained by training sample data, and the sample data comprises operation parameters of the network equipment at a plurality of operation time points and operation state values of the network equipment at each operation time point; acquiring detection requirements corresponding to each predicted value, and judging whether each predicted value meets the corresponding detection requirements; under the condition that the target predicted value does not meet the corresponding target detection requirement, determining the processing result of the operation parameter of the network equipment as the parameter abnormality; and under the condition that all the predicted values meet the corresponding detection requirements, determining that the processing result of the operation parameters of the network equipment is that the parameters are not abnormal.

Optionally, before training the predictive model, the method further comprises: acquiring a plurality of operation characteristic information of the network equipment and operation parameters under each operation characteristic information; dividing each piece of operation characteristic information and the rest of operation characteristic information in a plurality of pieces of operation characteristic information into a group to obtain P groups of operation characteristic information, wherein each group of operation characteristic information comprises two pieces of operation characteristic information, and P is a positive integer; calculating correlation coefficients between two pieces of operation characteristic information in each set of operation characteristic information through operation parameters to obtain P correlation coefficients; judging whether a target coefficient larger than a preset value exists in the P correlation coefficients; under the condition that target coefficients exist in the P correlation coefficients, determining two pieces of target operation characteristic information corresponding to the target coefficients, deleting any one piece of target operation characteristic information in the two pieces of target operation characteristic information from a plurality of pieces of operation characteristic information, and obtaining updated Q pieces of operation characteristic information, wherein Q is a positive integer; and determining the operation parameter and the operation state value of each operation characteristic information in the updated Q operation characteristic information as sample data.

Optionally, before training the predictive model, the method further comprises: acquiring an operation state value and a plurality of operation characteristic information of the network equipment, and an operation parameter corresponding to each operation characteristic information; determining the correlation degree between each operation parameter and the operation state value to obtain N correlation degrees, wherein N is a positive integer; obtaining target correlation degrees smaller than preset correlation degrees from the N correlation degrees to obtain H target correlation degrees, wherein H is a positive integer; sequentially determining operation characteristic information of operation parameters corresponding to each target relevance to obtain H target operation characteristic information, deleting the H target operation characteristic information from the operation characteristic information to obtain updated operation characteristic information; and determining the operation parameter and the operation state value of each of the updated plurality of operation characteristic information as sample data.

Optionally, processing the associated set of operation parameters by using a detection flow corresponding to each device, and obtaining a processing result includes: acquiring the operation parameters of each non-network device, and acquiring the operation parameter interval of each non-network device; comparing each operation parameter with the corresponding operation parameter interval, and determining that the non-network equipment is abnormal under the condition that the target operation parameter is not located in the corresponding operation parameter interval.

Optionally, determining the operation state of the machine room according to the M processing results of the M sets of operation parameters includes: under the condition that the M processing results have abnormal processing results, determining that the running state of the machine room is an abnormal state, and determining equipment corresponding to the abnormal processing results to obtain abnormal equipment; acquiring preset flow information, and determining an operation and maintenance department of the abnormal equipment according to the preset flow information; and sending the abnormal equipment and the abnormal processing result to the operation and maintenance department.

Optionally, after acquiring the set of operating parameters of the machine room, the method further includes: determining the number of the operation parameters to be acquired to obtain a first number; determining the number of the operation parameters in the operation parameter set to obtain a second number; and under the condition that the first number is larger than the second number, determining the operation state of the machine room as an abnormal state, and determining the equipment to which the missing operation parameters belong as abnormal equipment.

According to another aspect of the application, a device for detecting an operation state of a machine room is provided. The device comprises: the first acquisition unit is used for acquiring an operation parameter set of the machine room; a first grouping unit, configured to group, according to a device type of a device to which each operating parameter belongs, a plurality of operating parameters in an operating parameter set to obtain M groups of operating parameters, where M is a positive integer; the first determining unit is used for determining a detection flow corresponding to each equipment type, and processing a group of related operation parameters by using the detection flow corresponding to each equipment to obtain a processing result; and the second determining unit is used for determining the operation state of the machine room according to M processing results of the M groups of operation parameters.

According to another aspect of the present invention, there is further provided a computer storage medium, where the computer storage medium is configured to store a program, and when the program runs, control a device in which the computer storage medium is located to execute a method for detecting an operation state of a machine room.

According to another aspect of the present invention, there is also provided an electronic device comprising one or more processors and a memory; the memory stores computer readable instructions, and the processor is configured to execute the computer readable instructions, where the computer readable instructions execute a method for detecting an operating state of the machine room when the computer readable instructions are executed.

According to the application, the following steps are adopted: acquiring an operation parameter set of a machine room; grouping a plurality of operation parameters in an operation parameter set according to the equipment type of equipment to which each operation parameter belongs to obtain M groups of operation parameters, wherein M is a positive integer; determining a detection flow corresponding to each equipment type, and processing a group of related operation parameters by using the detection flow corresponding to each equipment to obtain a processing result; and determining the operation state of the machine room according to M processing results of the M groups of operation parameters. The method solves the problems that the timeliness of determining the abnormal state of the equipment is poor and the normal operation of the service is affected in the related technology. The operation parameter set is obtained, the parameters are intensively processed according to the equipment type of the equipment to which the parameters belong, and the operation state of the equipment is predicted according to the processing result, so that the parameter processing efficiency is improved, the operation state of the equipment is predicted according to the parameter processing result, and the timeliness of determining the abnormal state of the equipment is enhanced.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

fig. 1 is a schematic view of an alternative central centralized control device for a machine room provided according to an embodiment of the present application;

fig. 2 is a flowchart of a method for detecting an operation state of a machine room according to an embodiment of the present application;

Fig. 3 is a flowchart of an alternative method for detecting an operation state of a machine room according to an embodiment of the present application;

fig. 4 is a schematic diagram of a device for detecting an operation state of a machine room according to an embodiment of the present application;

Fig. 5 is a schematic diagram of an electronic device according to an embodiment of the present application.

Detailed Description

It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be noted that the method, the device, the storage medium and the electronic device for detecting the operation state of the machine room, which are determined by the present disclosure, may be used in the field of artificial intelligence, and may also be used in any field other than the field of artificial intelligence, and the application fields of the method, the device, the storage medium and the electronic device for detecting the operation state of the machine room, which are determined by the present disclosure, are not limited.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the related regulations and standards, and are provided with corresponding operation entries for the user to select authorization or rejection. For example, an interface is provided between the system and the relevant user or institution, before acquiring the relevant information, the system needs to send an acquisition request to the user or institution through the interface, and acquire the relevant information after receiving the consent information fed back by the user or institution.

For convenience of description, the following will describe some terms or terminology involved in the embodiments of the present application:

The gradient-lifting regression tree (Gradient Boosting Regression Trees, GBRT) model consists of a plurality of decision trees, the purpose of which is to predict target values from inputs. Therefore, the server state can be predicted according to various indexes of the input influence server, but since GBRT uses training data with known target values to create a model, and then the model is applied to the observation with unknown targets, the generalization performance is poor, so that a migration model is introduced to enhance the training data through auxiliary data, and the model is optimized.

In this embodiment, fig. 1 is a schematic diagram of an optional central control device for a machine room according to an embodiment of the present application, as shown in fig. 1, an optional central control device for a machine room is used as an execution body to centrally obtain an operation parameter set of the machine room, where the operation parameter set includes:

and a display device module: the display device is composed of a display screen for displaying and touching, a touch and keyboard module and the like.

And the induction module is used for: sensing, detecting temperature, humidity, illumination brightness and other data.

Power supply, air conditioner, illumination state information collection module: and acquiring the operation parameters of the infrastructure such as a machine room power supply, an air conditioner, illumination and the like.

Server and network hardware equipment state collection module: the method is used for collecting the operation information of hardware devices such as a server, network devices and the like.

System and application state collection module: to collect operational information and status of the system, software applications.

The information early warning processing module: and processing the collected operation information, and analyzing and predicting the information by using an algorithm model.

An information sending module: and the information processed by the information processing platform module transmits the early warning or alarming information to the corresponding contact person through the information transmitting module.

According to the embodiment of the application, a method for detecting the running state of a machine room is provided.

Fig. 2 is a flowchart of a method for detecting an operation state of a machine room according to an embodiment of the present application. As shown in fig. 2, the method comprises the steps of:

Step S201, acquiring an operation parameter set of the machine room.

Specifically, the operation parameter set of the machine room may include physical devices, operation and maintenance devices, server devices, and the like, for example, operation parameters of the machine room on devices such as a power supply, an air conditioner, a cabinet, a physical server, a network device, and the like, where the operation parameters may include: temperature, humidity, illumination brightness and other data of the machine room, and various index data of the server, such as: CPU utilization rate, memory utilization rate, network flow, voltage, current and the like, and after the operation parameters are obtained, whether the current operation state of the machine room is normal or not can be determined according to the operation parameters.

Step S202, grouping a plurality of operation parameters in the operation parameter set according to the equipment type of the equipment to which each operation parameter belongs to obtain M groups of operation parameters, wherein M is a positive integer.

Specifically, after the operation parameters are obtained, the operation judgment standards and judgment modes of different devices are different, so that the parameters of different devices are required to be grouped and are respectively processed according to different processing methods after being grouped, and the operation condition of each device can be analyzed according to the parameter condition of the device, so that the operation state of the whole machine room is further determined.

Step S203, determining a detection flow corresponding to each device type, and processing an associated set of operation parameters by using the detection flow corresponding to each device to obtain a processing result.

Specifically, after the operation parameters are grouped according to the device types, the corresponding operation parameters can be processed according to the detection flow corresponding to each device type, so that the operation state of the device to which each device type belongs in the current state is predicted according to the processing result, and the operation state of the machine room is determined according to the operation state of each device.

For example, in the case where the device type is a power supply device, the operation parameters may include a voltage, a current, and the like, and the method for processing the operation parameters of the power supply device may be to determine whether the voltage value and the current value are within a preset threshold, determine that the voltage value and the current value are correct if they are within the preset threshold, and determine that the voltage value and the current value are abnormal if they are not within the preset threshold, thereby determining an operation state of the power supply device in the machine room.

Step S204, determining the operation state of the machine room according to M processing results of the M groups of operation parameters.

Specifically, after the processing results corresponding to each set of operation parameters are obtained, the operation state of the machine room can be determined according to the operation state, for example, when the processing results of all the operation parameters are normal, no abnormality of the machine room can be determined, when an abnormality exists in a certain processing result, the influence program of the abnormality on the operation of the machine room and the duration of the abnormality can be determined, when the influence program is low or the duration is short, no abnormality of the machine room is determined, when the influence program is high or the duration is long and the machine room cannot be restored by itself, the abnormality of the machine room is determined, and at this time, information needs to be sent to corresponding operation staff or departments, and then the abnormality of the machine room is processed as soon as possible.

According to the method for detecting the running state of the machine room, the running parameter set of the machine room is obtained; grouping a plurality of operation parameters in an operation parameter set according to the equipment type of equipment to which each operation parameter belongs to obtain M groups of operation parameters, wherein M is a positive integer; determining a detection flow corresponding to each equipment type, and processing a group of related operation parameters by using the detection flow corresponding to each equipment to obtain a processing result; and determining the operation state of the machine room according to M processing results of the M groups of operation parameters. The method solves the problems that the timeliness of determining the abnormal state of the equipment is poor and the normal operation of the service is affected in the related technology. The operation parameter set is obtained, the parameters are intensively processed according to the equipment type of the equipment to which the parameters belong, and the operation state of the equipment is predicted according to the processing result, so that the parameter processing efficiency is improved, the operation state of the equipment is predicted according to the parameter processing result, and the timeliness of determining the abnormal state of the equipment is enhanced.

Optionally, in the method for detecting an operation state of a machine room provided by the embodiment of the present application, when a device type is a network device, processing an associated set of operation parameters by using a detection flow corresponding to each device, where obtaining a processing result includes: inputting a first operation parameter of the network equipment into a prediction model to obtain a prediction result, wherein the prediction result comprises a plurality of prediction values, the prediction model is obtained by training sample data, and the sample data comprises operation parameters of the network equipment at a plurality of operation time points and operation state values of the network equipment at each operation time point; acquiring detection requirements corresponding to each predicted value, and judging whether each predicted value meets the corresponding detection requirements; under the condition that the target predicted value does not meet the corresponding target detection requirement, determining the processing result of the operation parameter of the network equipment as the parameter abnormality; and under the condition that all the predicted values meet the corresponding detection requirements, determining that the processing result of the operation parameters of the network equipment is that the parameters are not abnormal.

Specifically, in the case that the device type is network device, since whether the network device is normal or not directly affects service operation in the machine room, it is necessary to predict the operation state (such as high load, breakdown, etc.) of the device according to the current operation parameters, that is, determine whether the network device is abnormal at a certain moment in the future, so as to ensure that the network device can be processed before the network device is abnormal.

Further, when the operation state of the network device is predicted, a prediction model may be used, where the preset model may be GBRT models, and the operation parameters of the network device are input into the prediction model, that is, the operation state value of the network device may be generated by the prediction model, for example, the operation parameters may include; the CPU utilization rate, the memory utilization rate, the network flow and the like, and the running state value can be information transmission delay, and the information transmission quantity is equal to the running state value which is related to data processing and transmission and has a close relation with the service.

When the model is trained, the operating parameters of the network device at a plurality of operating time points and the operating state value at each operating time point can be used as sample data to train the model. During training, sample data at a plurality of moments can be obtained to obtain a plurality of groups of sample data, and the model is trained by using the plurality of groups of sample data. .

It should be noted that, when sample data is collected, the missing and obviously erroneous data in the collected data are removed and filled, and these operations can improve the performance of the model. The processed characteristic values are used as input to a GBRT model, parameters of the GBRT model, such as a loss function, the number of weak learners, namely regression trees, the maximum depth of each regression tree, the minimum leaf nodes, splitting conditions and the like, are adjusted through a grid search method, a prediction model is obtained through training, and the prediction model based on the GBRT algorithm is used for predicting the running condition of network equipment in a machine room.

It should be noted that there are two important parameters in GBRT algorithm: one is the learning rate, i.e. the weight reduction coefficient of the weak learner, also called step size. If the learning rate is too small, which means that more weak learners are needed for iteration, the iteration times are greatly increased, and the learning time is also increased; the other is the tree depth, i.e. the number of iterations, which is generally too small, the more under-fitted and too large the over-fitted. And the learning rate and the iteration times interact, so that the learning rate and the tree depth are combined to be considered in the parameter adjustment process. When the value of the learning rate is smaller, a higher number of tree depths are required to enable the training error to converge, that is, the learning rate and the iteration number are required to be set within a preset range, so that the convergence of the training error is ensured, and the model accuracy is improved.

Further, after the prediction results are obtained according to the model, the running state values in the prediction results need to be processed according to the detection requirements, and when the target prediction values do not meet the corresponding target detection requirements, the processing results of the running parameters of the network equipment are determined to be abnormal parameters, namely, abnormal running state values in the plurality of prediction results are determined to be abnormal, and when all the prediction values meet the corresponding detection requirements, the network equipment is characterized that the parameters in the network equipment in the current state are not abnormal, namely, the network equipment is not abnormal.

In order to improve the training efficiency of the model, optionally, in the method for detecting the running state of the machine room provided by the embodiment of the application, before training the prediction model, the method further includes: acquiring a plurality of operation characteristic information of the network equipment and operation parameters under each operation characteristic information; dividing each piece of operation characteristic information and the rest of operation characteristic information in a plurality of pieces of operation characteristic information into a group to obtain P groups of operation characteristic information, wherein each group of operation characteristic information comprises two pieces of operation characteristic information, and P is a positive integer; calculating correlation coefficients between two pieces of operation characteristic information in each set of operation characteristic information through operation parameters to obtain P correlation coefficients; judging whether a target coefficient larger than a preset value exists in the P correlation coefficients; under the condition that target coefficients exist in the P correlation coefficients, determining two pieces of target operation characteristic information corresponding to the target coefficients, deleting any one piece of target operation characteristic information in the two pieces of target operation characteristic information from a plurality of pieces of operation characteristic information, and obtaining updated Q pieces of operation characteristic information, wherein Q is a positive integer; and determining the operation parameter and the operation state value of each operation characteristic information in the updated Q operation characteristic information as sample data.

It should be noted that, because each operation parameter corresponds to one kind of operation characteristic information, and the operation characteristic information in the sample data is more, the correlation between partial operation characteristic information is higher, therefore, there is serious multiple collinearity between the operation characteristic information, and it is difficult to generate a satisfactory model to directly use the operation characteristic information after preprocessing to perform the construction of the model. Therefore, before modeling, a plurality of operation characteristic information is required to be screened, and operation characteristic information with higher correlation is screened and deleted, so that the number of operation parameters input into a model is reduced, and the model training efficiency and the model accuracy are improved.

When determining the correlation, a correlation calculation mode such as a pearson correlation coefficient may be used to determine the correlation between the operation feature information, and the algorithm for performing the correlation calculation is not limited herein.

When calculating the correlation, it is necessary to perform correlation calculation for each feature operation information with each of the remaining feature operation information, thereby determining the correlation between any two feature operation information. Under the condition that the correlation between any two pieces of characteristic operation information is determined to be larger than a preset value, any one piece of characteristic operation information in the two pieces of characteristic operation information can be deleted, so that the collinearity of operation parameters in sample data is reduced.

For example, a variable for which multiple collinearity may exist is first selected to calculate a correlation coefficient matrix, and then a thermodynamic diagram is made from the correlation coefficient matrix. And drawing thermodynamic diagrams for multiple times, finding out variables with high correlation in each thermodynamic diagram, and removing the variables from the variables. It is known from the Pearson correlation coefficient principle that the larger the absolute value of the correlation coefficient, the stronger the correlation. For example: by comparing the thermodynamic diagrams, the severe multiple collinearity exists between the temperature of the machine room and the temperature distribution of the air conditioner, namely, the temperature of the machine room is only required to be brought into a model, and the characteristic operation information with larger influence on the state of the server is finally selected.

In order to improve the training efficiency of the model, optionally, in the method for detecting the running state of the machine room provided by the embodiment of the application, before training the prediction model, the method further includes: acquiring an operation state value and a plurality of operation characteristic information of the network equipment, and an operation parameter corresponding to each operation characteristic information; determining the correlation degree between each operation parameter and the operation state value to obtain N correlation degrees, wherein N is a positive integer; obtaining target correlation degrees smaller than preset correlation degrees from the N correlation degrees to obtain H target correlation degrees, wherein H is a positive integer; sequentially determining operation characteristic information of operation parameters corresponding to each target relevance to obtain H target operation characteristic information, deleting the H target operation characteristic information from the operation characteristic information to obtain updated operation characteristic information; and determining the operation parameter and the operation state value of each of the updated plurality of operation characteristic information as sample data.

Specifically, when training the model, because the influence of different feature operation information on the operation state value is different, the correlation degree between each feature operation information and the operation state value can be calculated, and the feature operation information with the correlation degree smaller than the preset correlation degree is deleted according to the correlation degree, so that the training of the model and the state prediction operation of the network equipment are performed by using the operation parameters corresponding to the rest feature operation information.

For example, the feature operation information with great influence on the server state is analyzed separately so as to facilitate the construction of a later model. For example, the most intuitive observation of the influence of CPU utilization on the operation state of the network device is to make a scatter diagram of the processed data and observe the relationship between the two. The two or more characteristic operating information affects the operating state of the network device. For example: at different temperatures, different CPU usage may not affect the server state. We can make different classifications for different temperature divisions, make a scatter diagram to observe the influence of the two on the running state of the network equipment, and the like, observe the influence of various variables on the state of the server.

Optionally, in the method for detecting an operation state of a machine room provided by the embodiment of the present application, when the device type is a non-network device, processing an associated set of operation parameters by using a detection flow corresponding to each device, where obtaining a processing result includes: acquiring the operation parameters of each non-network device, and acquiring the operation parameter interval of each non-network device; comparing each operation parameter with the corresponding operation parameter interval, and determining that the non-network equipment is abnormal under the condition that the target operation parameter is not located in the corresponding operation parameter interval.

Specifically, in the case that the device is a non-network device, the operation parameters and the corresponding parameter intervals of the non-network device may be directly obtained, and the parameters and the parameter intervals are compared, so as to determine whether the non-network device has an abnormality.

For example, the power supply, the air conditioner and the illumination state collection processing module judge the running state of the equipment by analyzing the data transmitted by the sensing module. For the running state of the air conditioner of the machine room, if the room temperature and the humidity are detected to be larger than the preset threshold value, the running state of the air conditioner can be judged to be abnormal; the machine room power supply running state, the machine room meets the requirement that an AB double-circuit power supply is connected and is provided with UPS power generation equipment, and if the UPS battery is detected to be discharging, faults exist in the double-circuit power supply; if any power supply voltage in the A/B path is detected to be lower than the load voltage, judging that the running state of the independent power supply is abnormal; and for illumination of the machine room, if the current brightness is detected to be smaller than the preset threshold value, judging that the illumination equipment of the machine room is abnormal. If the running information is normal, the running information is transmitted to the display device module for displaying; if the information is abnormal, the information is transmitted to a maintainer through an early warning module while the information is transmitted to a display device module, so that the information can be processed in time.

Optionally, in the method for detecting an operation state of a machine room provided by the embodiment of the present application, determining the operation state of the machine room according to M processing results of M sets of operation parameters includes: under the condition that the M processing results have abnormal processing results, determining that the running state of the machine room is an abnormal state, and determining equipment corresponding to the abnormal processing results to obtain abnormal equipment; acquiring preset flow information, and determining an operation and maintenance department of the abnormal equipment according to the preset flow information; and sending the abnormal equipment and the abnormal processing result to the operation and maintenance department.

Specifically, after the processing results corresponding to each set of operation parameters are obtained, the operation state of the machine room can be determined according to the operation state, for example, when the processing results of all the operation parameters are normal, no abnormality of the machine room can be determined, when an abnormality exists in a certain processing result, the influence program of the abnormality on the operation of the machine room and the duration of the abnormality can be determined, when the influence program is low or the duration is short, no abnormality of the machine room is determined, when the influence program is high or the duration is long and the machine room cannot be restored by itself, the abnormality of the machine room is determined, and at this time, information needs to be sent to corresponding operation staff or departments, and then the abnormality of the machine room is processed as soon as possible.

In order to improve the judging speed of the machine room state, optionally, in the method for detecting the machine room operation state provided by the embodiment of the application, after the operation parameter set of the machine room is obtained, the method further includes: determining the number of the operation parameters to be acquired to obtain a first number; determining the number of the operation parameters in the operation parameter set to obtain a second number; and under the condition that the first number is larger than the second number, determining the operation state of the machine room as an abnormal state, and determining the equipment to which the missing operation parameters belong as abnormal equipment.

Specifically, after the operation parameter set of the machine room is acquired, whether the operation parameter is acquired completely needs to be determined first, and if the operation parameter set is not acquired, the abnormal operation of some devices is represented, so that the operation parameter set cannot be acquired successfully from the devices.

Fig. 3 is a flowchart of an optional method for detecting an operation state of a machine room, as shown in fig. 3, where a plurality of operation parameters are first acquired and grouped to obtain a plurality of groups of operation parameters, for operation parameters of non-network devices, operation parameters of non-network devices and corresponding parameter intervals may be acquired, the parameters and the parameter intervals are compared to obtain a first result, for operation parameters of network devices, the operation parameters of network devices are input into a prediction model to obtain a prediction result, and a second result is determined according to the prediction result and a detection requirement to determine that the operation state of the machine room is normal under the condition that both the first result and the second result represent that the device is normal, otherwise, the operation state of the machine room is abnormal, so as to achieve the effect of detecting the operation state of the machine room.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.

The embodiment of the application also provides a device for detecting the running state of the machine room, and the device for detecting the running state of the machine room can be used for executing the method for detecting the running state of the machine room. The following describes a device for detecting the running state of a machine room provided by the embodiment of the application.

Fig. 4 is a schematic diagram of a device for detecting an operation state of a machine room according to an embodiment of the present application. As shown in fig. 4, the apparatus includes: a first acquisition unit 41, a first grouping unit 42, a first determination unit 43, a second determination unit 44.

The first obtaining unit 41 is configured to obtain an operation parameter set of the machine room.

A first grouping unit 42, configured to group, according to a device type of a device to which each operating parameter belongs, a plurality of operating parameters in the operating parameter set to obtain M groups of operating parameters, where M is a positive integer.

The first determining unit 43 is configured to determine a detection flow corresponding to each device type, and process the associated set of operation parameters by using the detection flow corresponding to each device to obtain a processing result.

And a second determining unit 44, configured to determine an operation state of the machine room according to M processing results of the M sets of operation parameters.

According to the detection device for the running state of the machine room, the first acquisition unit 41 acquires the running parameter set of the machine room; the first grouping unit 42 groups a plurality of operation parameters in the operation parameter set according to the device type of the device to which each operation parameter belongs, so as to obtain M groups of operation parameters, where M is a positive integer; the first determining unit 43 determines a detection flow corresponding to each device type, and processes the associated set of operation parameters by using the detection flow corresponding to each device to obtain a processing result; the second determining unit 44 determines the operation state of the machine room according to the M processing results of the M sets of operation parameters. The problem that the timeliness of determining the abnormal state of the equipment is poor in the related technology and further the normal operation of the service is affected is solved, the operation state of the equipment is predicted according to the processing result by acquiring the operation parameter set, carrying out centralized processing on the parameters according to the equipment type of the equipment to which the parameters belong, further the parameter processing efficiency is improved, the operation state of the equipment is predicted according to the parameter processing result, and the timeliness of determining the abnormal state of the equipment is enhanced.

Optionally, in the apparatus for detecting an operation state of a machine room provided in the embodiment of the present application, in a case where a device type is a network device, the first determining unit 43 includes: the input module is used for inputting a first operation parameter of the network equipment into the prediction model to obtain a prediction result, wherein the prediction result comprises a plurality of prediction values, the prediction model is obtained by training sample data, and the sample data comprises operation parameters of the network equipment at a plurality of operation time points and operation state values of the network equipment at each operation time point; the judging module is used for acquiring the detection requirement corresponding to each predicted value and judging whether each predicted value accords with the corresponding detection requirement; the first determining module is used for determining that the processing result of the operation parameter of the network equipment is abnormal parameter under the condition that the target predicted value does not meet the corresponding target detection requirement; and the second determining module is used for determining that the processing result of the operation parameters of the network equipment is that the parameters are not abnormal under the condition that all the predicted values meet the corresponding detection requirements.

Optionally, in the apparatus for detecting a machine room running state provided by the embodiment of the present application, before training the prediction model, the apparatus further includes: the second acquisition unit is used for acquiring a plurality of operation characteristic information of the network equipment and operation parameters under each operation characteristic information; the second grouping unit is used for sequentially dividing each piece of operation characteristic information and the rest of operation characteristic information in the plurality of pieces of operation characteristic information into one group to obtain P groups of operation characteristic information, wherein each group of operation characteristic information comprises two pieces of operation characteristic information, and P is a positive integer; the calculating unit is used for calculating the correlation coefficient between the two pieces of operation characteristic information in each set of operation characteristic information through the operation parameters to obtain P correlation coefficients; the judging unit is used for judging whether target coefficients larger than a preset value exist in the P related coefficients; the third determining unit is used for determining two pieces of target operation characteristic information corresponding to the target coefficients under the condition that the target coefficients exist in the P correlation coefficients, deleting any one piece of the two pieces of target operation characteristic information from the plurality of pieces of operation characteristic information, and obtaining updated Q pieces of operation characteristic information, wherein Q is a positive integer; and a fourth determining unit configured to determine an operation parameter and an operation state value of each of the updated Q pieces of operation feature information as sample data.

Optionally, in the apparatus for detecting a machine room running state provided by the embodiment of the present application, before training the prediction model, the apparatus further includes: the third acquisition unit is used for acquiring the operation state value and a plurality of operation characteristic information of the network equipment and the operation parameter corresponding to each operation characteristic information; a fifth determining unit, configured to determine a correlation between each operation parameter and an operation state value, to obtain N correlations, where N is a positive integer; a fourth obtaining unit, configured to obtain target correlations smaller than a preset correlation from the N correlations, to obtain H target correlations, where H is a positive integer; the deleting unit is used for sequentially determining the operation characteristic information of the operation parameters corresponding to each target relativity to obtain H target operation characteristic information, deleting the H target operation characteristic information from the operation characteristic information to obtain updated operation characteristic information; and a sixth determining unit configured to determine an operation parameter and an operation state value of each of the plurality of operation feature information after updating as sample data.

Optionally, in the apparatus for detecting an operation state of a machine room provided in the embodiment of the present application, the first determining unit 43 includes: the acquisition module is used for acquiring the operation parameters of each non-network device and acquiring the operation parameter interval of each non-network device; the comparison module is used for comparing each operation parameter with the corresponding operation parameter interval and determining that the non-network equipment is abnormal under the condition that the target operation parameter is not located in the corresponding operation parameter interval.

Optionally, in the apparatus for detecting an operation state of a machine room provided by the embodiment of the present application, the second determining unit 44 includes: the third determining module is used for determining that the running state of the machine room is an abnormal state and determining equipment corresponding to the abnormal processing results to obtain abnormal equipment when the abnormal processing results exist in the M processing results; the fourth determining module is used for acquiring preset flow information and determining operation departments of the abnormal equipment according to the preset flow information; and the sending module is used for sending the abnormal equipment and the abnormal processing result to the operation and maintenance department.

Optionally, in the apparatus for detecting an operation state of a machine room provided by the embodiment of the present application, after acquiring an operation parameter set of the machine room, the apparatus further includes: a seventh determining unit, configured to determine the number of operating parameters to be acquired, to obtain a first number; an eighth determining unit, configured to determine the number of operating parameters in the operating parameter set, to obtain a second number; and the ninth determining unit is used for determining that the operation state of the machine room is an abnormal state and determining that the equipment to which the missing operation parameters belong is abnormal equipment under the condition that the first number is larger than the second number.

The apparatus for detecting the operation state of the machine room includes a processor and a memory, where the first acquiring unit 41, the first grouping unit 42, the first determining unit 43, the second determining unit 44, etc. are stored as program units in the memory, and the processor executes the program units stored in the memory to implement corresponding functions.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one kernel, and the problem that the timeliness of determining the abnormal state of the equipment is poor in the related technology and the normal operation of the service is affected is solved by adjusting the kernel parameters.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the invention provides a computer readable storage medium, wherein a program is stored on the computer readable storage medium, and the program is executed by a processor to realize the method for detecting the running state of a machine room.

The embodiment of the invention provides a processor which is used for running a program, wherein the program runs to execute a method for detecting the running state of a machine room.

Fig. 5 is a schematic diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 5, an embodiment of the present application provides an electronic device, where an electronic device 50 includes a processor, a memory, and a program stored in the memory and capable of running on the processor, and the processor implements steps of the method for detecting an operating state of a machine room when executing the program. The device herein may be a server, PC, PAD, cell phone, etc.

The application also provides a computer program product adapted to perform a program of steps of a method of detecting an operating state of a machine room as described above when executed on a data processing apparatus.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

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

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

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

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims (10)

1. The method for detecting the running state of the machine room is characterized by comprising the following steps of:

Acquiring an operation parameter set of a machine room;

Grouping a plurality of operation parameters in the operation parameter set according to the equipment type of the equipment to which each operation parameter belongs to obtain M groups of operation parameters, wherein M is a positive integer;

Determining a detection flow corresponding to each equipment type, and processing a group of related operation parameters by using the detection flow corresponding to each equipment to obtain a processing result;

And determining the operation state of the machine room according to M processing results of the M groups of operation parameters.

2. The method of claim 1, wherein, in the case where the device type is a network device, processing the associated set of operation parameters using the detection flow corresponding to each device, to obtain a processing result includes:

Inputting a first operation parameter of the network equipment into a prediction model to obtain a prediction result, wherein the prediction result comprises a plurality of prediction values, the prediction model is obtained by training sample data, and the sample data comprises operation parameters of the network equipment at a plurality of operation time moments and operation state values of the network equipment at each operation time moment;

acquiring detection requirements corresponding to each predicted value, and judging whether each predicted value meets the corresponding detection requirements;

under the condition that the target predicted value does not meet the corresponding target detection requirement, determining the processing result of the operation parameter of the network equipment as the parameter abnormality;

And under the condition that all predicted values meet the corresponding detection requirements, determining that the processing result of the operation parameters of the network equipment is that the parameters are not abnormal.

3. The method of claim 2, wherein prior to training the predictive model, the method further comprises:

acquiring a plurality of operation characteristic information of the network equipment and operation parameters under each operation characteristic information;

Dividing each piece of operation characteristic information and the rest of operation characteristic information in the plurality of pieces of operation characteristic information into a group to obtain P groups of operation characteristic information, wherein each group of operation characteristic information comprises two pieces of operation characteristic information, and P is a positive integer;

calculating correlation coefficients between two pieces of operation characteristic information in each set of operation characteristic information through the operation parameters to obtain P correlation coefficients;

judging whether target coefficients larger than a preset value exist in the P correlation coefficients or not;

Under the condition that the target coefficients exist in the P correlation coefficients, two pieces of target operation characteristic information corresponding to the target coefficients are determined, any one piece of target operation characteristic information in the two pieces of target operation characteristic information is deleted from the plurality of pieces of operation characteristic information, and updated Q pieces of operation characteristic information are obtained, wherein Q is a positive integer;

and determining the operation parameter and the operation state value of each operation characteristic information in the updated Q operation characteristic information as the sample data.

4. The method of claim 2, wherein prior to training the predictive model, the method further comprises:

Acquiring an operation state value and a plurality of operation characteristic information of the network equipment, and an operation parameter corresponding to each operation characteristic information;

determining the correlation between each operation parameter and the operation state value to obtain N correlations, wherein,

N is a positive integer;

obtaining target correlation degrees smaller than preset correlation degrees from the N correlation degrees to obtain H target correlation degrees, wherein H is a positive integer;

Sequentially determining operation characteristic information of operation parameters corresponding to each target relevance to obtain H target operation characteristic information, deleting the H target operation characteristic information from the plurality of operation characteristic information to obtain a plurality of updated operation characteristic information;

And determining the operation parameter and the operation state value of each operation characteristic information in the updated plurality of operation characteristic information as the sample data.

5. The method of claim 1, wherein, in the case where the device type is a non-network device, processing the associated set of operating parameters using the detection flow corresponding to each device, to obtain a processing result includes:

Acquiring the operation parameters of each non-network device, and acquiring the operation parameter interval of each non-network device;

comparing each operation parameter with a corresponding operation parameter interval, and determining that the non-network equipment is abnormal under the condition that the target operation parameter is not located in the corresponding operation parameter interval.

6. The method of claim 1, wherein determining the operating state of the machine room based on the M processing results for the M sets of operating parameters comprises:

Under the condition that an abnormal processing result exists in the M processing results, determining that the running state of the machine room is an abnormal state, and determining equipment corresponding to the abnormal processing result to obtain abnormal equipment;

Acquiring preset flow information, and determining an operation and maintenance department of the abnormal equipment according to the preset flow information;

And sending the abnormal equipment and the abnormal processing result to the operation and maintenance department.

7. The method of claim 1, wherein after obtaining the set of operating parameters of the machine room, the method further comprises:

Determining the number of the operation parameters to be acquired to obtain a first number;

determining the number of the operation parameters in the operation parameter set to obtain a second number;

and under the condition that the first number is larger than the second number, determining the running state of the machine room as an abnormal state, and determining the equipment to which the missing running parameters belong as abnormal equipment.

8. The utility model provides a detection device of computer lab running state which characterized in that includes:

the first acquisition unit is used for acquiring an operation parameter set of the machine room;

A first grouping unit, configured to group, according to a device type of a device to which each operating parameter belongs, a plurality of operating parameters in the operating parameter set to obtain M groups of operating parameters, where M is a positive integer;

The first determining unit is used for determining a detection flow corresponding to each equipment type, and processing a group of related operation parameters by using the detection flow corresponding to each equipment to obtain a processing result;

and the second determining unit is used for determining the operation state of the machine room according to M processing results of the M groups of operation parameters.

9. A computer storage medium for storing a program, wherein the program when run controls a device in which the computer storage medium is located to execute the method for detecting an operation state of a machine room according to any one of claims 1 to 7.

10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of detecting a machine room operating state of any of claims 1-7.