CN116185786A - Alarm detection method, device, equipment and medium - Google Patents
Alarm detection method, device, equipment and medium Download PDFInfo
- Publication number
- CN116185786A CN116185786A CN202310127245.XA CN202310127245A CN116185786A CN 116185786 A CN116185786 A CN 116185786A CN 202310127245 A CN202310127245 A CN 202310127245A CN 116185786 A CN116185786 A CN 116185786A
- Authority
- CN
- China
- Prior art keywords
- time
- index
- time delay
- data corresponding
- delay data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/324—Display of status information
- G06F11/327—Alarm or error message display
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3065—Monitoring arrangements determined by the means or processing involved in reporting the monitored data
- G06F11/3072—Monitoring arrangements determined by the means or processing involved in reporting the monitored data where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Alarm Systems (AREA)
Abstract
The application relates to an alarm detection method, an alarm detection device, alarm detection equipment and an alarm detection medium, wherein the alarm detection method comprises the following steps: acquiring time delay data corresponding to each index in the process from the initiation of a request to the receipt of a response result of a processing party by a requesting party, and aggregating the time delay data corresponding to each index into time delay data of a preset time level; constructing a sliding time window with preset time length according to the time delay data corresponding to each aggregated index, and smoothing the time delay data corresponding to each aggregated index in the sliding time window based on a time sequence smoothing algorithm; calculating the variance ring ratio value of the delay data corresponding to each index after the smoothing treatment between adjacent time nodes; and comparing the time delay fluctuation value with a preset threshold, and triggering a time delay alarm if the time delay fluctuation value reaches the preset threshold. The method and the device can accurately identify the effective time delay alarm points and filter a large amount of invalid alarm information.
Description
Technical Field
The present disclosure relates to the field of data processing, and in particular, to an alarm detection method, a corresponding apparatus, an electronic device, and a computer readable storage medium.
Background
The time delay warning of the online service is warning information which is required to be processed by operation and maintenance personnel, and the warning information is a signal generated by online faults, which means that problems may occur to online tasks, particularly for some business scenes with high low time delay requirements, if effective time delay warning information cannot be timely checked for processing, user experience is greatly reduced, and business loss is caused.
At present, an operation and maintenance person monitors whether alarm information occurs by setting an alarm threshold, and according to the rule of the alarm threshold currently set, the alarm information includes a large number of invalid alarms, the operation and maintenance person needs to check and analyze each piece of alarm information in a large number of alarm information, so that the truly effective alarm information can be checked, when a real fault occurs, the processing speed of the operation and maintenance person is delayed, the effective alarm information can not be checked timely, the problem of large loss caused by small faults can possibly occur, and the operation and maintenance person can generate fatigue and reduce enthusiasm for the fussy alarm information along with the increase of time.
In the prior art, the alarm threshold value is required to be frequently modified according to different states of the service, otherwise, excessive invalid alarms are received or effective alarms are missed, the condition that a service is newly added with a service module or online flow is changed cannot be dealt with, the effective alarm information is mixed in a large amount of invalid alarm information, the alarm information is generated due to the fact that the alarm threshold value is reached, a large amount of invalid alarms are generated under the condition that the network jitter and the flow are suddenly increased in a short time, the effective alarm information is very low in proportion, so that operation and maintenance personnel cannot timely check out the effective alarm information from a large amount of alarm information, and the workload and the fault troubleshooting difficulty of the operation and maintenance personnel are increased.
Disclosure of Invention
An object of the present application is to solve the above-mentioned problems and provide an alarm detection method, a corresponding apparatus, an electronic device, and a computer-readable storage medium.
In order to meet the purposes of the application, the application adopts the following technical scheme:
an alarm detection method adapted to one of the purposes of the present application includes the following steps:
acquiring time delay data corresponding to each index in the process from the initiation of a request to the receipt of a response result of a processing party by a requesting party, and aggregating the time delay data corresponding to each index into time delay data of a preset time level;
constructing a sliding time window with preset time length according to the time delay data corresponding to each aggregated index, and smoothing the time delay data corresponding to each aggregated index in the sliding time window based on a time sequence smoothing algorithm;
calculating the variance ring ratio value of the delay data corresponding to each index after the smoothing treatment between adjacent time nodes;
and comparing the time delay fluctuation value with a preset threshold, and triggering a time delay alarm if the time delay fluctuation value reaches the preset threshold.
Optionally, before the step of comparing the delay fluctuation value with a preset threshold, the method further includes the following steps:
acquiring time delay data corresponding to each index in the effective time delay alarm in the history period;
calculating the variance mean value of the delay data corresponding to each index in the effective delay alarm;
and taking the maximum value of the variance mean value as a fluctuation threshold.
Optionally, before the step of comparing the delay fluctuation value with a preset threshold, the method further includes the following steps:
determining a frequency threshold value of delay data corresponding to each index;
constructing a maximum function expression according to the fluctuation threshold and the frequency threshold, wherein the maximum function expression is used for selecting a maximum value between the frequency threshold and the fluctuation threshold;
and taking the constructed maximum value function expression as a preset threshold value.
Optionally, the step of acquiring delay data corresponding to each index in the effective delay alarm in the history period includes the following steps:
performing data cleaning or value missing filling on the delay data corresponding to each index in the obtained effective delay alarm;
and carrying out normalization processing on the time delay data corresponding to each index after data cleaning or value deficiency filling.
Optionally, the step of aggregating the time delay data corresponding to each index into time delay data of a preset time level includes the following steps:
aggregating the time delay data corresponding to each index into time delay data of a minute level;
calculating the average value of time delay data corresponding to each index in the minute level;
taking the average value of the time delay data corresponding to each index as the time delay data corresponding to each index after aggregation.
Optionally, the step of constructing a sliding time window with a preset time length according to the time delay data corresponding to each aggregated index includes the following steps:
determining a size of the sliding time window;
taking the time delay data corresponding to each aggregated index as a sliding time window value;
and constructing a sliding time window with preset time length according to the size of the sliding time window and the sliding time window value.
Optionally, the step of smoothing the time delay data corresponding to each index after aggregation in the sliding time window based on a time sequence smoothing algorithm includes the following steps:
calculating the variation of time delay data corresponding to each aggregated index between adjacent time nodes in the sliding time window based on a first-order difference equation;
And smoothing the time delay data corresponding to each index after aggregation in the sliding time window according to the variable quantity.
An alarm detection device adapted for another object of the present application, comprising:
the data aggregation module is used for acquiring time delay data corresponding to each index in the process from the initiation of a request to the receipt of a response result of a processing party by a requesting party and aggregating the time delay data corresponding to each index into time delay data of a preset time level;
the data processing module is used for constructing a sliding time window with preset time length according to the time delay data corresponding to each aggregated index, and carrying out smoothing processing on the time delay data corresponding to each aggregated index in the sliding time window based on a time sequence smoothing algorithm;
the fluctuation value determining module is used for calculating the variance ring ratio value of the delay data corresponding to each index after the smoothing treatment between the adjacent time nodes;
and the alarm triggering module is used for comparing the time delay fluctuation value with a preset threshold value, and triggering a time delay alarm if the time delay fluctuation value reaches the preset threshold value.
An alarm detection device adapted for another object of the present application comprises a central processor and a memory, said central processor being adapted to invoke the execution of a computer program stored in said memory for performing the steps of the alarm detection method described herein.
A computer readable storage medium adapted to another object of the present application is provided, which stores a computer program implemented according to the alarm detection method in the form of computer readable instructions, which computer program, when being called by a computer for execution, performs the steps comprised by the corresponding method.
Compared with the prior art, the method and the device aim at the problems that the operation and maintenance personnel need to frequently modify the alarm threshold value, the effective alarm information is mixed in a large amount of invalid alarm information, the operation and maintenance personnel cannot timely check out the effective alarm information from the large amount of alarm information to process the effective alarm information, scattered and untimely original time delay data are aggregated into a minute level, so that the time delay data have operability, in a time window with a preset time length, effective time delay alarm points are accurately identified based on a dynamic variance algorithm and a time sequence smoothing algorithm, a large amount of invalid alarm information is filtered, the noise of the alarm information is obviously reduced, thereby valuable alarm information is provided for the operation and maintenance personnel to further process, the workload investment of the operation and maintenance personnel on the invalid alarm information is obviously reduced based on improvement of the identification of the effective alarm information, time and energy are focused on each effective alarm information, the operation of frequently modifying the alarm threshold value by the operation personnel is avoided, the on-line service fault checking efficiency and the processing efficiency are remarkably improved, the on-line service real-time performance and the low-time delay performance are ensured, and the service loss caused by the on-line service is avoided.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is an exemplary network architecture employed by the alarm detection method of the present application;
FIG. 2 is a schematic flow chart of an alarm detection method in an embodiment of the present application;
fig. 3 is a schematic flow chart of determining a fluctuation threshold of delay data in an embodiment of the present application;
fig. 4 is a schematic flow chart of determining a preset threshold value of delay data in the embodiment of the present application;
fig. 5 is a schematic flow chart of normalization processing for delay data corresponding to each index in an effective delay alarm in the embodiment of the present application;
fig. 6 is a flow chart of aggregating delay data corresponding to each index into delay data of a preset time level in the embodiment of the present application;
fig. 7 is a schematic flow chart of constructing a sliding time window with a preset time length according to the time delay data corresponding to each aggregated indicator in the embodiment of the present application;
fig. 8 is a schematic flow chart of smoothing processing on time delay data corresponding to each aggregated indicator in a sliding time window based on a time sequence smoothing algorithm in the embodiment of the present application;
FIG. 9 is a schematic block diagram of an alarm detection device in an embodiment of the present application;
fig. 10 is a schematic structural diagram of an alarm detection device in an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of illustrating the present application and are not to be construed as limiting the present application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As used herein, "client," "terminal device," and "terminal device" are understood by those skilled in the art to include both devices that include only wireless signal receivers without transmitting capabilities and devices that include receiving and transmitting hardware capable of two-way communication over a two-way communication link. Such a device may include: a cellular or other communication device such as a personal computer, tablet, or the like, having a single-line display or a multi-line display or a cellular or other communication device without a multi-line display; a PCS (Personal Communications Service, personal communication system) that may combine voice, data processing, facsimile and/or data communication capabilities; a PDA (Personal Digital Assistant ) that can include a radio frequency receiver, pager, internet/intranet access, web browser, notepad, calendar and/or GPS (Global Positioning System ) receiver; a conventional laptop and/or palmtop computer or other appliance that has and/or includes a radio frequency receiver. As used herein, "client," "terminal device" may be portable, transportable, installed in a vehicle (aeronautical, maritime, and/or land-based), or adapted and/or configured to operate locally and/or in a distributed fashion, at any other location(s) on earth and/or in space. As used herein, a "client," "terminal device," or "terminal device" may also be a communication terminal, an internet terminal, or a music/video playing terminal, for example, a PDA, a MID (Mobile Internet Device ), and/or a mobile phone with music/video playing function, or may also be a device such as a smart tv, a set top box, or the like.
The hardware referred to by the names "server", "client", "service node", etc. in the present application is essentially an electronic device having the performance of a personal computer, etc., and is a hardware device having a central processing unit (including an arithmetic unit and a controller), a memory, an input device, and an output device, etc. Feng Reyi man-machine principle disclosed as necessary components, a computer program is stored in the memory, and the central processing unit calls the program stored in the external memory into the memory to run, executes instructions in the program, and interacts with the input/output device, thereby completing a specific function.
Referring to fig. 1, an exemplary network architecture used in the application scenario includes a terminal device 80, a media server 81 and an application server 82. The application server 82 may be used to deploy a live webcast service. The media server 81 or the terminal device 80 may run a computer program product programmed according to the alarm detection method of the present application, and implement each step of the method by running the product, so as to realize detection of effective alarm information in online live webcasting, and provide effective alarm information to operation and maintenance personnel, so as to avoid invalid alarm information from being mixed in the effective alarm information. The terminal device 80 may be used by a host user or a viewer user to log into a webcast room supported by the webcast service. The anchor user can acquire video through a camera unit in the terminal device 80 and submit the video as a live video stream to the media server, and the audience user can receive the live video stream pushed by the media server through the terminal device 80 and play and display the live video stream.
It should be noted that the concept of "server" as referred to in this application is equally applicable to the case of a server farm. The servers should be logically partitioned, physically separate from each other but interface-callable, or integrated into a physical computer or group of computers, according to network deployment principles understood by those skilled in the art. Those skilled in the art will appreciate this variation and should not be construed as limiting the implementation of the network deployment approach of the present application.
With reference to the above exemplary scenario and referring to fig. 2, in one embodiment, the alarm detection method of the present application includes the following steps:
step S1100, acquiring time delay data corresponding to each index in the process from the initiation of a request to the receipt of a response result of a processing party by a requesting party, and aggregating the time delay data corresponding to each index into time delay data of a preset time level;
the data which needs to be subjected to alarm detection through the technical scheme of the application can be regarded as the time delay data of the application. The type and the source of the delay data can be determined according to the actual application scene, in the scene of the network live broadcast, the network live broadcast is different from the general audio-video call application scene, the real-time performance and low-delay performance requirements on the service are higher, the perception of the delay by a live broadcast user is more obvious, a large amount of invalid alarm information can be generated under the condition of network jitter or short-time sudden increase of the flow, the effective alarm information is often low in proportion, the effective alarm information can be mixed in the large amount of invalid alarm information, the fault point is very difficult to locate, the operation and maintenance personnel cannot timely find out the effective alarm information from the large amount of alarm information to process, the workload and the fault troubleshooting difficulty of the operation and maintenance personnel are greatly increased, and if the effective alarm information cannot be timely detected to process, the user experience is greatly reduced, and the service loss is caused.
The delay data in this embodiment may be delay generated in network live broadcast, where the delay data may be delay from capturing a corresponding live video stream by a camera unit of a terminal device to pushing to a corresponding response delay of a client, network transmission delay, server processing delay or client display delay, or may be delay from a client initiating a service request to receiving a response result in network live broadcast, network transmission delay, server processing delay or client display delay, where sources and types of delay data are wide and are not limited herein. In the network live broadcast scenario, because the corresponding delay data generated by each index is untimely and scattered in the process from the initiation of the service request to the receipt of the response result by the client, it is easy to understand that the corresponding live video stream is collected by the camera unit of the terminal device, and the response delay from pushing to the client, the network transmission delay, the server processing delay or the client display delay, and the response delay from the initiation of the service request to the receipt of the response result by the client in the network live broadcast process are untimely and scattered, the delay data corresponding to each index needs to be aggregated into the delay data of a preset time level based on the time aggregation module, and the preset time level may be a minute level, and the minute level may be one minute, two minutes or three minutes, and is not limited herein. Because the corresponding alarm information generated by each index needs to consider the time delay data generated in the preset time level instead of the time delay data generated by a single point, the average value of the time delay data generated by each index in the preset time level is used as the time delay data corresponding to each aggregated index.
In some embodiments, after a host user in a network living room starts network living, living activities such as dance, singing, body building and the like can be implemented, a camera unit of a terminal device collects corresponding living video streams and submits the corresponding living video streams to a corresponding server for encoding, and then the encoded living video streams are submitted to a media server. And after the media server obtains the encoded live video stream, decoding the encoded live video stream, and pushing the decoded live video stream to a client for display. It is to be understood that the delay data may be response delay, network transmission delay, etc. corresponding to the response time from the capturing unit of the terminal device capturing the corresponding live video stream to pushing to the client, or may be corresponding server processing delay generated by encoding the live video stream by the corresponding server or decoding the encoded live video stream by the media server, client display delay generated by displaying the decoded video stream by the client, etc., or may be response delay, network transmission delay, server processing delay, or client display delay from the client initiating a service request to receiving a response result in the network live broadcast process, for example: the time delay data can be response time delay, network transmission time delay and client display time delay from the time of the user's crazy praise, bullet screen, gift brushing and the like to the time of receiving corresponding response results, or server processing time delay generated by a server processing the service data corresponding to the user crazy praise, bullet screen, gift brushing and the like, and because the generation of the response time delay, network transmission time delay, client display time delay or server processing time delay data is untimely and scattered, the response time delay, network transmission time delay, client display time delay or server processing time delay data needs to be aggregated into time delay data of a minute level.
Specifically, in a network live broadcast scene, a camera unit of a terminal device collects a corresponding live video stream to be pushed to a whole service of a client, the network transmission delay can be RTT delay (Round Trip Time), the server processing delay can be average encoding Time of the server to the live video stream, the method comprises format conversion, memory copy, video encoding and the like, the client display delay can be rendering Time, decoding Time, delay Time in jitter buffer and the like, and the response delay can be the sum of the network transmission delay, the server processing delay and the delay Time of the client display delay.
for some service scenarios with higher requirements on real-time performance and low time delay performance, time delay data corresponding to each index in a short time window are required to be paid attention to at all times, so that a sliding time window with preset time length is constructed by the time delay data corresponding to each index after aggregation, alarm information corresponding to each index is conveniently detected in time and is delivered to related personnel for processing in a short time, so that real-time performance and low time ductility of network live broadcasting and related services are guaranteed, the time delay data corresponding to each index after aggregation in the sliding time window is subjected to smoothing processing based on a time sequence smoothing algorithm, the time sequence smoothing algorithm can be a first-order differential equation or the like, the influence of time delay data extreme values corresponding to each index in the sliding time window is reduced, the accuracy of the time delay data corresponding to each index in the sliding time window is guaranteed, and accordingly the alarm accuracy and effectiveness are improved, and the preset time length can be 5 min, 10 min or 15 min and the like.
In some embodiments, in order to accurately and effectively respond to the delay alarms corresponding to the indexes and timely process the delay alarms, the anchor needs to collect corresponding live video streams from the camera unit of the terminal device aggregated to the minute level to the response delay, the network transmission delay, the server processing delay or the client display delay corresponding to the response delay from the client to the receiving of the response result, the network transmission delay, the server processing delay or the client display delay corresponding to the indexes in the network live broadcast process, to construct a sliding time window of 5mi n, frame the time sequence of the delay data corresponding to the indexes according to the time unit length of 5mi n, and smooth the delay data corresponding to the indexes aggregated in the sliding time window based on the first-order differential equation so as to reduce the influence of the delay data extremum corresponding to the indexes in the sliding time window, thereby calculating the fluctuation condition of the delay data corresponding to the indexes in the frame.
Step S1300, calculating a variance-ring ratio value of delay data corresponding to each index after the smoothing treatment between adjacent time nodes;
In a sliding time window with a preset time length, the effective delay alarm corresponding to each index is usually low in duty ratio, the effective delay alarm can be detected based on delay data fluctuation corresponding to each index in the sliding time window with the preset time length, the delay data fluctuation detection can be based on a dynamic variance algorithm, a variance-loop ratio value of delay data corresponding to each index after smoothing processing between adjacent time nodes is calculated to obtain a delay fluctuation value of each index, and fluctuation conditions of delay data corresponding to each index are judged based on the delay fluctuation values.
In some embodiments, in a live network broadcast scenario, the camera unit of the terminal device after smoothing processing collects corresponding response delay, network transmission delay, server processing delay or client display delay from the client initiating a service request to receiving response results in a live network broadcast process, delay data corresponding to various indexes such as network transmission delay, server processing delay or client display delay are added to a corresponding time sequence in real time, firstly, variance values of delay data corresponding to various indexes of a last time node of a current time node in the corresponding time sequence are calculated, variance values of delay data corresponding to various indexes of the current time node in the corresponding time sequence are calculated based on variance values of various indexes in the corresponding time sequence between the current time node and the last time node, so that variance ring ratio of delay data corresponding to various indexes after smoothing processing between the current time node and the last time node is calculated, the variance ring ratio is used as a delay fluctuation value of various indexes, and according to the delay fluctuation value of various indexes, a certain range of delay data corresponding to various indexes in a network can be judged, and when a certain range of delay of the delay data corresponding to be triggered reaches a certain alarm threshold value.
Specifically, the time node t= { T1, T2,...
The variance formula of the current time node and the last time node is:
wherein X represents the average number of the time delay data values corresponding to each index, mu represents the time delay data values corresponding to each index, and N represents the number of the time delay data values corresponding to each index.
Variance ring ratio formula: variance ring ratio = [ (variance value of current time node-variance value of last time node)/variance value of last time node) ] ×100%
And step 1400, comparing the time delay fluctuation value with a preset threshold, and triggering a time delay alarm if the time delay fluctuation value reaches the preset threshold.
After the time delay fluctuation value of the time delay data corresponding to each index is calculated, the time delay fluctuation value needs to be compared with a preset threshold value to accurately detect effective time delay alarm points, a large amount of invalid alarm information is filtered, time delay alarms are accurately triggered, service loss caused by incapability of timely checking and processing the effective alarm information is avoided, when the time delay fluctuation value of each index reaches the corresponding preset threshold value, the on-line time delay index of the current time node is considered to develop in a worse direction, time delay alarms need to be timely performed and related personnel are informed to process, so that on-line service faults are prevented from being generated and spread, and the preset threshold value can be determined according to the historical alarm data of each index, so that the effectiveness and the accuracy of the alarms are enhanced.
In some embodiments, in a live network broadcast scenario, calculating a delay fluctuation value of delay data corresponding to each index, such as response delay, network transmission delay, server processing delay or client display delay from a service request initiated by a client to a receiving response result in a live network broadcast process, where a camera unit of the terminal device between a current time node and a last time node acquires a corresponding live video stream to a corresponding response delay pushed to a client, and the delay fluctuation value of delay data corresponding to each index, such as the response delay, the network transmission delay, the server processing delay or the client display delay, is compared with a corresponding preset threshold value based on the delay fluctuation value of each index, and if the delay fluctuation value reaches the corresponding preset threshold value, a delay alarm of the corresponding index of the current time node is triggered.
According to the embodiment, aiming at the problems that the operation and maintenance personnel need to frequently modify the alarm threshold value, the effective alarm information is mixed in a large amount of invalid alarm information, the operation and maintenance personnel cannot timely check out the effective alarm information from the large amount of alarm information to process the effective alarm information, scattered and untimely original time delay data are aggregated into a minute level, so that the time delay data have operability, the effective time delay alarm points are accurately identified based on a dynamic variance algorithm and a time sequence smoothing algorithm in a time window with a preset time length, a large amount of invalid alarm information is filtered, the noise of the alarm information is obviously reduced, and therefore valuable alarm information is provided for the operation and maintenance personnel to further process, the workload investment of the operation and maintenance personnel on the invalid alarm information is obviously reduced based on the improvement of the accuracy of identifying the effective alarm information, the time and energy are focused on each effective alarm information, the operation and maintenance personnel are prevented from frequently modifying the alarm threshold value, the on-line service fault checking efficiency and the processing efficiency are remarkably improved, the on-line service real-time and the low-time delay and service loss caused by the fact that the operation and the service efficiency are not processed is avoided.
On the basis of any embodiment of the present application, referring to fig. 3, before the step of comparing the delay fluctuation value with a preset threshold, the method further includes the following steps:
step S1301, obtaining delay data corresponding to each index in the effective delay alarm in the history period;
the method comprises the steps that corresponding response time delay, network transmission time delay, server processing time delay or client display time delay of a corresponding live video stream to be pushed to a client and corresponding time delay data of various indexes such as response time delay, network transmission time delay, server processing time delay or client display time delay of a service request initiated by the client to a response result received in a network live process are acquired by a camera unit of the terminal equipment in an effective time delay alarm in a history period, wherein the history period can be 3 months or 6 months, and the like, and is not limited herein.
Step S1303, calculating a variance mean value of delay data corresponding to each index in the effective delay alarm;
in order to fully consider the change condition of corresponding time delay data in the effective time delay alarm of each index so as to accurately detect the effective time delay alarm points, the variance average value of the time delay data corresponding to each effective time delay alarm point in the history period needs to be calculated, and the variance average value of the time delay data corresponding to each effective time delay alarm point is compared to determine the fluctuation threshold value corresponding to each index.
Specifically, in a network live broadcast scene, taking an example that a camera unit of the terminal equipment collects corresponding live video streams and pushes the live video streams to an effective response delay alarm generated within 3 months of a client, constructing a time sequence of response delay data corresponding to the obtained effective response delay alarm, calculating a variance average value of the response delay data corresponding to each effective delay alarm point within 3 months, and comparing the variance average value to determine the fluctuation threshold.
Step S1305, taking the maximum value of the variance mean value as a fluctuation threshold.
Based on comprehensive consideration of online service, the triggering of invalid alarm information is avoided, meanwhile, the frequent modification of alarm thresholds by operation and maintenance personnel is avoided, and the workload of the operation and maintenance personnel is reduced, so that the maximum value of the variance mean value of the delay data corresponding to the effective delay alarm point in the history period is used as the fluctuation threshold of the corresponding index.
On the basis of any embodiment of the present application, referring to fig. 4, before the step of comparing the delay fluctuation value with a preset threshold, the method further includes the following steps:
step S1302, determining a frequency threshold of delay data corresponding to each index;
The frequency threshold needs to consider the difference between different services, and the frequency threshold of the time delay data corresponding to each index can be set according to the actual service condition as required, and the frequency threshold can be 15%, 20% or 25% and the like.
Step S1304, constructing a maximum value function expression according to the fluctuation threshold value and the frequency threshold value, wherein the maximum value function expression is used for selecting a maximum value between the frequency threshold value and the fluctuation threshold value;
in order to further avoid triggering invalid alarm information, reduce workload investment of operation and maintenance personnel on the invalid alarm information, focus time and energy on each valid alarm information, improve failure troubleshooting efficiency of the operation and maintenance personnel, collect corresponding live video stream to corresponding response time delay pushed to a client by a camera unit of the terminal equipment, network transmission time delay, server processing time delay or client display time delay, response time delay from a client to receiving a response result in the network live broadcast process, network transmission time delay, server processing time delay or client display time delay and other corresponding indexes are related to the frequency threshold, and construct a maximum value function expression according to the corresponding fluctuation threshold and the frequency threshold of each index, wherein the maximum value function expression is used for selecting a maximum value between the frequency threshold and the fluctuation threshold, and avoiding invalid alarm information with excessive mashup in the alarm information.
Step S1306, taking the constructed maximum value function expression as a preset threshold value.
And a maximum function expression constructed based on the fluctuation threshold and the frequency threshold corresponding to each index is used as a preset threshold, so that a large amount of invalid alarm information can be filtered out, the accuracy of triggering delay alarms is improved, and the operation and maintenance personnel can conveniently and timely process faults generated by online service.
On the basis of any embodiment of the present application, referring to fig. 5, the step of obtaining delay data corresponding to each index in the effective delay alarm in the history period includes the following steps:
step S13011, carrying out data cleaning or value missing filling on the time delay data corresponding to each index in the obtained effective time delay alarm;
for the obtained delay data corresponding to each index, such as response delay, network transmission delay, server processing delay or client display delay of a response result initiated by a client in a live video streaming to a client in a live video streaming manner, in a history period, of the terminal equipment, because the delay data corresponding to each index in the effective delay alarm may contain a large number of missing values and a large number of noises, or because abnormal data exists due to manual entry errors, the accuracy and the precision of the fluctuation threshold corresponding to each index are greatly affected, if a plurality of factors, such as the accuracy and the reliability of the fluctuation threshold corresponding to each index, are not involved, the obtained delay data corresponding to each index in the effective delay alarm are subjected to data cleaning or value filling, so that the accuracy and the precision of the corresponding delay data in the effective delay alarm are ensured, and the accuracy of the corresponding delay threshold of each index are ensured.
Step S13013, normalize the time delay data corresponding to each index after the data cleaning or the deficiency filling.
Because the dimension and magnitude of the delay data corresponding to each index in the effective delay alarm in the history period may be inconsistent, in order to eliminate the influence of the dimension and magnitude, normalization processing needs to be performed on the delay data corresponding to each index after data cleaning or value deficiency filling.
On the basis of any embodiment of the present application, referring to fig. 6, the step of aggregating the delay data corresponding to each index into delay data of a preset time level includes the following steps:
step 1101, aggregating the time delay data corresponding to each index into time delay data of a minute level;
the camera unit of the terminal equipment acquires corresponding response time delay, network transmission time delay, server processing time delay or client display time delay from pushing corresponding live video streams to the client, and delay data corresponding to various indexes such as response time delay, network transmission time delay, server processing time delay or client display time delay from sending service requests to receiving response results in the network live broadcast process are generated irregularly and sporadically, and the delay data corresponding to various indexes are required to be aggregated into minute-level delay data based on a time aggregation module.
Step S1103, calculating the average value of the time delay data corresponding to each index in the minute level;
and acquiring corresponding time delay data generated by each index at each single point, calculating the average value of the corresponding time delay data generated by each index at each single point in the minute level, and taking the average value of the corresponding time delay data generated by each index at each single point in the minute level as the time delay data corresponding to each aggregated index.
Step S1105, taking the average value of the delay data corresponding to each index as the aggregated delay data corresponding to each index.
Because the corresponding alarm information generated by each index needs to consider the time delay data generated in the minute level instead of the time delay data generated by a single point, the average value of the time delay data generated by each index in the minute level is used as the aggregated time delay data corresponding to each index.
On the basis of any embodiment of the present application, referring to fig. 7, the step of constructing a sliding time window with a preset time length according to the time delay data corresponding to each aggregated index includes the following steps:
step S1201, determining the size of the sliding time window;
In a live network scene, the real-time performance and low-time delay performance requirements are high, and the time delay data corresponding to each index in a short time window are required to be paid attention to at any time, so that the time length of the sliding time window is 5mi < n >, the alarm information corresponding to each index can be conveniently detected in time in a short time and is delivered to related personnel for processing, and the real-time performance and low-time ductility of the live network and related services are ensured.
Step S1203, using the time delay data corresponding to each aggregated index as a sliding time window value;
and acquiring corresponding response time delay, network transmission time delay, server processing time delay or client display time delay of corresponding live video streams from the camera shooting units of the terminal equipment after aggregation to the client, and taking time delay data values corresponding to various indexes such as response time delay, network transmission time delay, server processing time delay or client display time delay of a response result from a client to a service request in a network live broadcast process as sliding time window values.
And step S1205, constructing a sliding time window with preset time length according to the size of the sliding time window and the sliding time window value.
In order to accurately and effectively respond to the corresponding time delay alarms of each index and timely process the time delay alarms, service loss caused by incapability of timely checking and processing effective alarm information is avoided, and a sliding time window with preset time length is constructed according to the determined size of the sliding time window and the sliding time window value.
On the basis of any embodiment of the present application, referring to fig. 8, a step of performing smoothing processing on delay data corresponding to each index aggregated in the sliding time window based on a time sequence smoothing algorithm includes the following steps:
step S1207, calculating the variation of the time delay data corresponding to each aggregated index between adjacent time nodes in the sliding time window based on the first-order differential equation;
specifically, based on a first-order differential equation, the camera unit of the terminal device after aggregation between adjacent time nodes in the sliding time window acquires corresponding response time delay, network transmission time delay, server processing time delay or client display time delay from pushing corresponding live video streams to clients, and change amounts of time delay data corresponding to various indexes such as response time delay, network transmission time delay, server processing time delay or client display time delay from a client initiating a service request to receiving a response result in a network live broadcast process, wherein the first-order differential equation is as follows:
Δy x ＝y x+1 -y x (x＝0，1，2，...)
Wherein y is x+1 For the time delay data value, y corresponding to each index in the current time node x Delay data value delta y corresponding to each index in adjacent time nodes of current time node x Is the variation of time delay data corresponding to each index between adjacent time nodes.
Step S1209, performing smoothing processing on the time delay data corresponding to each index after aggregation in the sliding time window according to the variation.
In order to reduce the influence of the extreme value of the time delay data corresponding to each index in the sliding time window, the time delay fluctuation value of the time delay data corresponding to each index in the frame is accurately calculated, and the time delay data corresponding to each index after aggregation in the sliding time window is subjected to smoothing processing according to the variation.
Referring to fig. 9, an alarm detection apparatus provided for adapting to one of the purposes of the present application includes a data aggregation module 1100, a data processing module 1200, a fluctuation value determination module 1300, and an alarm triggering module 1400. The data aggregation module 1100 is configured to obtain delay data corresponding to each index in a process from initiating a request to receiving a response result of a processor, and aggregate the delay data corresponding to each index into delay data of a preset time level; the data processing module 1200 is configured to construct a sliding time window with a preset time length according to the time delay data corresponding to each aggregated index, and perform smoothing processing on the time delay data corresponding to each aggregated index in the sliding time window based on a time sequence smoothing algorithm; the fluctuation value determining module 1300 is configured to calculate a variance-ring ratio value of the delay data corresponding to each index after the smoothing process between the adjacent time nodes; the alarm triggering module 1400 is configured to compare the delay fluctuation value with a preset threshold, and if the delay fluctuation value reaches the preset threshold, trigger a delay alarm.
On the basis of any embodiment of the present application, the alarm detection device of the present application further includes: the acquisition module is used for acquiring delay data corresponding to each index in the effective delay alarm in the history period; the calculating module is used for calculating the variance mean value of the time delay data corresponding to each index in the effective time delay alarm; and the fluctuation threshold determining module is used for setting the maximum value of the variance mean value as a fluctuation threshold.
On the basis of any embodiment of the present application, the alarm detection device of the present application further includes: the frequency threshold determining module is used for determining the frequency threshold of the time delay data corresponding to each index; a function construction module configured to construct a maximum function expression according to the fluctuation threshold and the frequency threshold, the maximum function expression being used for selecting a maximum between the frequency threshold and the fluctuation threshold; the preset threshold determining module is used for setting the constructed maximum function expression as a preset threshold.
On the basis of any embodiment of the present application, the obtaining module includes: the preprocessing unit is used for cleaning data or filling missing values of the delay data corresponding to each index in the obtained effective delay alarm;
The normalization processing unit is used for performing normalization processing on the time delay data corresponding to each index after the data cleaning or the deficiency filling.
On the basis of any embodiment of the present application, the data aggregation module 1100 includes: the aggregation unit is used for aggregating the time delay data corresponding to each index into time delay data of a minute level; the average value calculating unit is used for calculating the average value of the time delay data corresponding to each index in the minute level; the data determining unit is used for setting the average value of the time delay data corresponding to each index as the time delay data corresponding to each index after aggregation.
On the basis of any embodiment of the present application, the data processing module 1200 includes: a window size determining unit configured to determine a size of the sliding time window; the window value determining unit is used for taking the time delay data corresponding to each aggregated index as a sliding time window value; and the window construction unit is used for constructing a sliding time window with preset time length according to the size of the sliding time window and the sliding time window value.
On the basis of any embodiment of the present application, the data processing module 1200 includes: the variation determining unit is used for calculating the variation of the time delay data corresponding to each aggregated index between adjacent time nodes in the sliding time window based on a first-order difference equation; and the smoothing processing unit is used for carrying out smoothing processing on the time delay data corresponding to each index after aggregation in the sliding time window according to the variable quantity.
On the basis of any embodiment of the present application, please refer to fig. 10, another embodiment of the present application further provides an alarm detection device, where the alarm detection device may be implemented by a computer device, and as shown in fig. 10, an internal structure diagram of the computer device is shown. The computer device includes a processor, a computer readable storage medium, a memory, and a network interface connected by a system bus. The computer readable storage medium of the computer device stores an operating system, a database and computer readable instructions, the database can store a control information sequence, and the computer readable instructions can enable the processor to realize an alarm detection method when the computer readable instructions are executed by the processor. The processor of the computer device is used to provide computing and control capabilities, supporting the operation of the entire computer device. The memory of the computer device may have stored therein computer readable instructions that, when executed by the processor, may cause the processor to perform the alert detection method of the present application. The network interface of the computer device is for communicating with a terminal connection. It will be appreciated by those skilled in the art that the structure shown in fig. 10 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
The processor in this embodiment is configured to execute specific functions of each module and its sub-modules in fig. 9, and the memory stores program codes and various types of data required for executing the above modules or sub-modules. The network interface is used for data transmission between the user terminal or the server. The memory in this embodiment stores program codes and data required for executing all modules/sub-modules in the alarm detection device of the present application, and the server can call the program codes and data of the server to execute the functions of all sub-modules.
The present application also provides a storage medium storing computer readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the alert detection method described in any of the embodiments of the present application.
The present application also provides a computer program product comprising computer programs/instructions which when executed by one or more processors implement the steps of the alert detection method of any of the embodiments of the present application.
Those skilled in the art will appreciate that implementing all or part of the above-described methods of embodiments of the present application may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed, may comprise the steps of embodiments of the methods described above. The storage medium may be a computer readable storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).
The foregoing is only a partial embodiment of the present application, and it should be noted that, for a person skilled in the art, several improvements and modifications can be made without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
In summary, the method and the device aggregate scattered and untimely original time delay data into minute levels, so that the time delay data has operability, effective time delay alarm points are accurately identified based on a dynamic variance algorithm and a time sequence smoothing algorithm in a time window with preset time length, a large amount of invalid alarm information is filtered, noise of the alarm information is remarkably reduced, and accordingly valuable alarm information is provided for operation and maintenance personnel to further process.
Claims (10)
1. An alarm detection method is characterized by comprising the following steps:
acquiring time delay data corresponding to each index in the process from the initiation of a request to the receipt of a response result of a processing party by a requesting party, and aggregating the time delay data corresponding to each index into time delay data of a preset time level;
constructing a sliding time window with preset time length according to the time delay data corresponding to each aggregated index, and smoothing the time delay data corresponding to each aggregated index in the sliding time window based on a time sequence smoothing algorithm;
calculating the variance ring ratio value of the delay data corresponding to each index after the smoothing treatment between adjacent time nodes;
and comparing the time delay fluctuation value with a preset threshold, and triggering a time delay alarm if the time delay fluctuation value reaches the preset threshold.
2. The alarm detection method according to claim 1, further comprising, before the step of comparing the delay variation value with a preset threshold value, the steps of:
acquiring time delay data corresponding to each index in the effective time delay alarm in the history period;
calculating the variance mean value of the delay data corresponding to each index in the effective delay alarm;
And taking the maximum value of the variance mean value as a fluctuation threshold.
3. The alarm detection method according to claim 2, further comprising, before the step of comparing the delay variation value with a preset threshold value, the steps of:
determining a frequency threshold value of delay data corresponding to each index;
constructing a maximum function expression according to the fluctuation threshold and the frequency threshold, wherein the maximum function expression is used for selecting a maximum value between the frequency threshold and the fluctuation threshold;
and taking the constructed maximum value function expression as a preset threshold value.
4. The alert detection method of claim 2, wherein the step of obtaining delay data corresponding to each index in the effective delay alert during the history period comprises the steps of:
performing data cleaning or value missing filling on the delay data corresponding to each index in the obtained effective delay alarm;
and carrying out normalization processing on the time delay data corresponding to each index after data cleaning or value deficiency filling.
5. The alarm detection method according to claim 1, wherein the step of aggregating the delay data corresponding to the respective indicators into delay data of a preset time level comprises the steps of:
Aggregating the time delay data corresponding to each index into time delay data of a minute level;
calculating the average value of time delay data corresponding to each index in the minute level;
taking the average value of the time delay data corresponding to each index as the time delay data corresponding to each index after aggregation.
6. The alarm detection method according to claim 1, wherein the step of constructing a sliding time window of a preset time length according to the time delay data corresponding to the aggregated respective indexes comprises the steps of:
determining a size of the sliding time window;
taking the time delay data corresponding to each aggregated index as a sliding time window value;
and constructing a sliding time window with preset time length according to the size of the sliding time window and the sliding time window value.
7. The alarm detection method according to claim 1, wherein the step of smoothing the time delay data corresponding to the aggregated indicators in the sliding time window based on a time series smoothing algorithm includes the steps of:
calculating the variation of time delay data corresponding to each aggregated index between adjacent time nodes in the sliding time window based on a first-order difference equation;
And smoothing the time delay data corresponding to each index after aggregation in the sliding time window according to the variable quantity.
8. An alarm detection apparatus, comprising:
the data aggregation module is used for acquiring time delay data corresponding to each index in the process from the initiation of a request to the receipt of a response result of a processing party by a requesting party and aggregating the time delay data corresponding to each index into time delay data of a preset time level;
the data processing module is used for constructing a sliding time window with preset time length according to the time delay data corresponding to each aggregated index, and carrying out smoothing processing on the time delay data corresponding to each aggregated index in the sliding time window based on a time sequence smoothing algorithm;
the fluctuation value determining module is used for calculating the variance ring ratio value of the delay data corresponding to each index after the smoothing treatment between the adjacent time nodes;
and the alarm triggering module is used for comparing the time delay fluctuation value with a preset threshold value, and triggering a time delay alarm if the time delay fluctuation value reaches the preset threshold value.
9. An alarm detection device comprising a central processor and a memory, characterized in that the central processor is arranged to invoke a computer program stored in the memory for performing the steps of the method according to any of claims 1 to 7.
10. A computer-readable storage medium, characterized in that it stores in the form of computer-readable instructions a computer program implemented according to the method of any one of claims 1 to 7, which, when invoked by a computer, performs the steps comprised by the corresponding method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310127245.XA CN116185786A (en) | 2023-02-15 | 2023-02-15 | Alarm detection method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310127245.XA CN116185786A (en) | 2023-02-15 | 2023-02-15 | Alarm detection method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116185786A true CN116185786A (en) | 2023-05-30 |
Family
ID=86434089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310127245.XA Pending CN116185786A (en) | 2023-02-15 | 2023-02-15 | Alarm detection method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116185786A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118158117A (en) * | 2024-05-10 | 2024-06-07 | 山东首瀚信息科技有限公司 | Data processing method and system based on industrial Internet of things gateway |
-
2023
- 2023-02-15 CN CN202310127245.XA patent/CN116185786A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118158117A (en) * | 2024-05-10 | 2024-06-07 | 山东首瀚信息科技有限公司 | Data processing method and system based on industrial Internet of things gateway |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10884844B2 (en) | Data stream processor and method to counteract anomalies in data streams transiting a distributed computing system | |
| CN107426022B (en) | Security event monitoring method and device, electronic equipment and storage medium | |
| US10282246B2 (en) | Application error detection method for cloud streaming service, and apparatus and system therefor | |
| US10581886B1 (en) | Computer system anomaly detection | |
| US10120746B1 (en) | Throttling system and method | |
| US10171335B2 (en) | Analysis of site speed performance anomalies caused by server-side issues | |
| US20130055145A1 (en) | Event management apparatus, systems, and methods | |
| CA2969131A1 (en) | Data stream processing language for analyzing instrumented software | |
| CN112333556B (en) | Control method for monitoring video transmission bandwidth, terminal equipment and readable storage medium | |
| CN116185786A (en) | Alarm detection method, device, equipment and medium | |
| US9992379B2 (en) | Partial snapshots for creating generalized snapshots | |
| US10504026B2 (en) | Statistical detection of site speed performance anomalies | |
| US20160094392A1 (en) | Evaluating Configuration Changes Based on Aggregate Activity Level | |
| US20090315886A1 (en) | Method to prevent resource exhaustion while performing video rendering | |
| US7711518B2 (en) | Methods, systems and computer program products for providing system operational status information | |
| CN104506940B (en) | A kind of information processing method and television set | |
| CN116781568A (en) | Data monitoring alarm method, device, equipment and storage medium | |
| CN106453504A (en) | Monitoring system and method based on NGINX server cluster | |
| US20170139803A1 (en) | Obtaining and analyzing a reduced metric data set | |
| US20170171307A1 (en) | Method and electronic apparatus for processing picture | |
| US20240086272A1 (en) | System, method and computer-readable medium for anomaly detection | |
| CN116578911A (en) | Data processing method, device, electronic equipment and computer storage medium | |
| US11929869B2 (en) | Scalable and real-time anomaly detection | |
| CN110351014B (en) | Data processing method, data processing device, computer readable storage medium and computer equipment | |
| CN112672405A (en) | Power consumption calculation method and device, storage medium, electronic device and server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |