CN111831517A - Data processing method and device, electronic equipment and storage medium - Google Patents
Data processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111831517A CN111831517A CN202010044211.0A CN202010044211A CN111831517A CN 111831517 A CN111831517 A CN 111831517A CN 202010044211 A CN202010044211 A CN 202010044211A CN 111831517 A CN111831517 A CN 111831517A
- Authority
- CN
- China
- Prior art keywords
- dimension
- index
- index data
- detected
- 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
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/079—Root cause analysis, i.e. error or fault diagnosis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Alarm Systems (AREA)
Abstract
The application provides a data processing method, a data processing device, an electronic device and a storage medium, wherein the method comprises the following steps: acquiring index data to be detected and historical index data which are generated in historical time and correspond to the index data to be detected; determining an alarm threshold corresponding to the index data to be detected based on each historical index data; and determining whether the index data to be detected is abnormal or not based on a comparison result between the index data to be detected and the alarm threshold value. By adopting the scheme, the alarm threshold value is automatically determined by utilizing the historical index data, the problems of time and labor waste caused by manual setting are avoided, automatic abnormality detection can be further realized, and time and labor are saved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a data processing method and apparatus, an electronic device, and a storage medium.
Background
Currently, in order to ensure the normal operation of each service platform, each service platform needs to be monitored. When the service platform is monitored, some key indexes need to be extracted from service data, and the key indexes are subjected to anomaly detection through an anomaly detection method.
In the related art, an alarm threshold value is mainly set for the key index in a manual mode, and when the alarm threshold value is exceeded, an alarm prompt is sent out, so that maintenance personnel are reminded to maintain the platform.
However, the above manual detection method has a low automation degree, and especially when the number of key indexes requiring maintenance is large, time and labor are wasted, and efficiency is low.
Disclosure of Invention
In view of this, an object of the present application is to provide at least one data processing scheme, which can determine an alarm threshold based on historical data to achieve automatic detection of an abnormal condition, and is time-saving and labor-saving.
Mainly comprises the following aspects:
in a first aspect, the present application provides a data processing method, including:
acquiring index data to be detected and historical index data which are generated in historical time and correspond to the index data to be detected;
determining an alarm threshold corresponding to the index data to be detected based on each historical index data;
and determining whether the index data to be detected is abnormal or not based on a comparison result between the index data to be detected and the alarm threshold value.
In one embodiment, the method further comprises:
when the index data to be detected is determined to be abnormal, analyzing the index data to be detected in at least one layer of dimensionality until a preset analysis cut-off condition is reached, and determining the reason for enabling the index data to be detected to be abnormal.
In an embodiment, the analyzing the index data to be detected in at least one layer of dimensions until a preset analysis cutoff condition is reached, and determining a cause that the index data to be detected is abnormal includes:
determining each candidate dimension index corresponding to each layer dimension in the at least one layer dimension; determining the relative entropy of each candidate dimension index based on the data distribution of the index data to be detected on each candidate dimension index, and selecting the candidate dimension index with the maximum relative entropy as a target dimension index under the layer of dimension;
and when a preset analysis cut-off condition is reached, determining the reason for enabling the index data to be detected to have abnormity based on the information indicated by the target dimension index determined under the at least one layer of dimension.
In an embodiment, the determining the relative entropy of each candidate dimension index based on the data distribution of the index data to be detected on each candidate dimension index includes:
for each candidate dimension index corresponding to each layer of dimension, determining the current data distribution of each candidate dimension index data indicated by the candidate dimension index at the current moment and the historical data distribution of each candidate dimension index data indicated by the candidate dimension index at the historical moment; and determining the relative entropy of the candidate dimension index based on the historical data distribution and the distribution difference between the current data distribution and the historical data distribution.
In one embodiment, determining each candidate dimension indicator corresponding to the layer dimension includes:
when the layer dimension is a first layer dimension of the at least one layer dimension, determining each candidate dimension index included in a preset dimension list as a candidate dimension index corresponding to the layer dimension;
when the layer dimension is the other layer dimension in the at least one layer dimension, after the target dimension index determined by the dimension before the other layer dimension is screened out from each candidate dimension index included in the preset dimension list, each candidate dimension index which is not screened out in the preset dimension list is determined as a candidate dimension index corresponding to the layer dimension.
In one embodiment, the preset resolution cutoff condition comprises one of the following conditions:
the number of layers of dimension analysis reaches a preset number of layers;
the candidate dimension indexes which are not screened out in the preset dimension list are null;
and the relative entropy of the target dimension index determined by the current layer dimension analysis is smaller than the preset entropy.
In an embodiment, the determining, based on information indicated by the target dimension index determined in the at least one layer of dimensions, a cause of an abnormality in the index data to be detected includes:
and determining the reason for enabling the index data to be detected to have abnormity based on the information indicated by the target dimension index determined under the at least one layer of dimension and the data distribution of the index data to be detected on the target dimension index.
In an embodiment, the determining, based on information indicated by the target dimension indicator determined in the at least one layer of dimensions and data distribution of the to-be-detected indicator data on the target dimension indicator, a cause of an abnormality in the to-be-detected indicator data includes:
for each layer of dimensionality, determining the ring ratio contribution degree of each candidate dimensionality index data indicated by the target dimensionality index based on the data distribution of the index data to be detected on the target dimensionality index determined by the layer of dimensionality; selecting candidate dimension index data with the largest ring ratio contribution degree as target dimension index data and serving as an analysis node under the next layer of dimension;
and determining the reason for enabling the index data to be detected to have abnormity based on the target dimension index data determined under the at least one layer of dimension.
In one embodiment, the determining, based on each historical index data, an alarm threshold corresponding to the index data to be detected includes:
taking historical index data as an independent variable and cumulative distribution probability as a dependent variable to construct a cumulative distribution function;
and determining historical index data corresponding to a preset probability threshold value based on the preset probability threshold value and the constructed cumulative distribution function, and determining the historical index data as an alarm threshold value corresponding to the index data to be detected.
In one embodiment, the determining whether the index data to be detected is abnormal or not based on the comparison result between the index data to be detected and the alarm threshold value includes:
if the index data to be detected is forward index data, judging whether the index data to be detected is smaller than the alarm threshold value; if so, determining that the index data to be detected is abnormal;
if the index data to be detected is negative index data, judging whether the index data to be detected is larger than the alarm threshold value; and if so, determining that the index data to be detected is abnormal.
The present application also provides a data processing apparatus, the apparatus comprising:
the data acquisition module is used for acquiring index data to be detected and historical index data which are generated in historical duration and correspond to the index data to be detected;
the threshold value determining module is used for determining an alarm threshold value corresponding to the index data to be detected based on each historical index data;
and the abnormity determining module is used for determining whether the index data to be detected is abnormal or not based on the comparison result between the index data to be detected and the alarm threshold value.
In one embodiment, the apparatus further comprises:
and the reason determining module is used for analyzing the index data to be detected in at least one layer of dimensionality when the abnormality of the index data to be detected is determined, and determining the reason for enabling the abnormality of the index data to be detected when a preset analysis cut-off condition is reached.
In an embodiment, the cause determining module is configured to determine a cause that causes the to-be-detected index data to have an abnormality according to the following steps:
determining each candidate dimension index corresponding to each layer dimension in the at least one layer dimension; determining the relative entropy of each candidate dimension index based on the data distribution of the index data to be detected on each candidate dimension index, and selecting the candidate dimension index with the maximum relative entropy as a target dimension index under the layer of dimension;
and when a preset analysis cut-off condition is reached, determining the reason for enabling the index data to be detected to have abnormity based on the information indicated by the target dimension index determined under the at least one layer of dimension.
In one embodiment, the cause determination module is configured to determine the relative entropy of each candidate dimension indicator according to the following steps:
for each candidate dimension index corresponding to each layer of dimension, determining the current data distribution of each candidate dimension index data indicated by the candidate dimension index at the current moment and the historical data distribution of each candidate dimension index data indicated by the candidate dimension index at the historical moment; and determining the relative entropy of the candidate dimension index based on the historical data distribution and the distribution difference between the current data distribution and the historical data distribution.
In an embodiment, the reason determining module is configured to determine each candidate dimension index corresponding to the layer dimension according to the following steps:
when the layer dimension is a first layer dimension of the at least one layer dimension, determining each candidate dimension index included in a preset dimension list as a candidate dimension index corresponding to the layer dimension;
when the layer dimension is the other layer dimension in the at least one layer dimension, after the target dimension index determined by the dimension before the other layer dimension is screened out from each candidate dimension index included in the preset dimension list, each candidate dimension index which is not screened out in the preset dimension list is determined as a candidate dimension index corresponding to the layer dimension.
In one embodiment, the preset resolution cutoff condition comprises one of the following conditions:
the number of layers of dimension analysis reaches a preset number of layers;
the candidate dimension indexes which are not screened out in the preset dimension list are null;
and the relative entropy of the target dimension index determined by the current layer dimension analysis is smaller than the preset entropy.
In an embodiment, the cause determining module is configured to determine a cause that causes the to-be-detected index data to have an abnormality according to the following steps:
and determining the reason for enabling the index data to be detected to have abnormity based on the information indicated by the target dimension index determined under the at least one layer of dimension and the data distribution of the index data to be detected on the target dimension index.
In an embodiment, the cause determining module is configured to determine a cause that causes the to-be-detected index data to have an abnormality according to the following steps:
for each layer of dimensionality, determining the ring ratio contribution degree of each candidate dimensionality index data indicated by the target dimensionality index based on the data distribution of the index data to be detected on the target dimensionality index determined by the layer of dimensionality; selecting candidate dimension index data with the largest ring ratio contribution degree as target dimension index data and serving as an analysis node under the next layer of dimension;
and determining the reason for enabling the index data to be detected to have abnormity based on the target dimension index data determined under the at least one layer of dimension.
In an embodiment, the threshold determining module is configured to determine an alarm threshold corresponding to the index data to be detected according to the following steps:
taking historical index data as an independent variable and cumulative distribution probability as a dependent variable to construct a cumulative distribution function;
and determining historical index data corresponding to a preset probability threshold value based on the preset probability threshold value and the constructed cumulative distribution function, and determining the historical index data as an alarm threshold value corresponding to the index data to be detected.
In an embodiment, the anomaly determination module is configured to determine whether the index data to be detected is anomalous according to the following steps:
if the index data to be detected is forward index data, judging whether the index data to be detected is smaller than the alarm threshold value; if so, determining that the index data to be detected is abnormal;
if the index data to be detected is negative index data, judging whether the index data to be detected is larger than the alarm threshold value; and if so, determining that the index data to be detected is abnormal.
The present application further provides an electronic device, including: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, when the electronic device runs, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to perform the steps of the data processing method according to the first aspect and any one of the various implementation manners of the first aspect.
The present application further provides a computer-readable storage medium having stored thereon a computer program for performing the steps of the data processing method according to the first aspect and any of its various embodiments when executed by a processor.
By adopting the scheme, the alarm threshold corresponding to the index data to be detected can be determined based on the historical index data corresponding to the index data to be detected, which is generated in the acquired historical duration, and then whether the index data to be detected is abnormal or not can be determined based on the comparison result between the index data to be detected and the alarm threshold, namely, the alarm threshold is automatically determined by utilizing the historical index data, so that the problem of time and labor waste in a manual setting mode is avoided, the automatic abnormality detection can be further realized, and the time and the labor are saved.
In addition, after the index data to be detected is determined to be abnormal, analysis under at least one layer of dimensionality can be carried out on the index data to be detected to determine the reason for the abnormal index data to be detected, namely, the abnormal reason can be automatically found out through the dimensionality analysis, so that the maintenance work of the service platform can be guided.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart illustrating a data processing method according to an embodiment of the present application;
fig. 2 is a flowchart illustrating a specific method for determining a threshold in a data processing method according to an embodiment of the present application;
fig. 3 is a flowchart illustrating a specific method for determining an abnormality cause in a data processing method according to an embodiment of the present application;
fig. 4 is a flowchart illustrating a specific method for determining an abnormality cause in a data processing method according to an embodiment of the present application;
fig. 5 is a schematic application diagram illustrating a data processing method according to an embodiment of the present application;
fig. 6 is a schematic structural diagram illustrating a data processing apparatus according to a second embodiment of the present application;
fig. 7 shows a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.
In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
In order to enable those skilled in the art to use the present disclosure, the following embodiments are given in conjunction with a specific application scenario "index data processing in a car travel service platform for a car appointment". It will be apparent to those skilled in the art that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the application. Although the present application is described primarily in the context of index data processing in a net appointment travel platform, it should be understood that this is merely one exemplary embodiment.
It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.
It is worth mentioning that, before the application is provided, the related art mainly adopts a manual mode to set an alarm threshold value for the key index, and when the alarm threshold value is exceeded, an alarm prompt is sent out, so that a maintainer is reminded to maintain the platform. However, the above manual detection method has a low automation degree, and especially when the number of key indexes requiring maintenance is large, time and labor are wasted, and efficiency is low. In view of this, the present application provides at least one data processing scheme, which can determine an alarm threshold based on historical data to realize automatic detection of an abnormal condition, and is time-saving and labor-saving. The following examples are provided for the purpose of illustration.
Example one
As shown in fig. 1, a flowchart of a data processing method provided in an embodiment of the present application is shown, an execution subject of the method may be a server, a terminal device, or other electronic devices with computing capability, and a specific description may be given below by taking the server as an example of the execution subject. The data processing method comprises the following steps:
s101, acquiring index data to be detected and historical index data which are generated in historical duration and correspond to the index data to be detected;
s102, determining an alarm threshold corresponding to the index data to be detected based on each historical index data;
s103, determining whether the index data to be detected is abnormal or not based on a comparison result between the index data to be detected and the alarm threshold value.
Here, after the server obtains the index data to be detected and the historical index data corresponding to the index data to be detected generated in the historical duration, an alarm threshold corresponding to the index data to be detected may be determined based on the historical index data, and then whether the index data to be detected is abnormal may be determined based on a comparison result between the alarm threshold and the index data to be detected, that is, the alarm threshold is automatically determined through the historical index data, so that the automatic detection of the abnormal condition is realized, and time and labor are saved.
And aiming at different service platforms, the corresponding index data to be detected can be different. For the network car booking and traveling service platform, the service order quantity (that is, once the passenger needs to use the network car booking and traveling service platform to travel, when the passenger starts the issuing button to issue the service request, the background server of the network car booking platform can generate the quantity of the corresponding service order based on the car taking information of the passenger), and the service order cancellation quantity (the quantity of the unfinished service order) can be used as the index data to be detected.
After the index data to be detected is determined, each historical index data corresponding to the index data to be detected in the historical duration may be determined, for example, when the service order quantity is used as the index data to be detected, the corresponding historical index data may be the service order quantity in the historical one-month time. It should be noted that the index data to be detected may further include other dimension information, for example, the number of service orders in the AA market may be included, which is not specifically limited in the embodiment of the present application.
In view of the fact that the historical index data of the index data to be detected can reflect fluctuation information of the index data to be detected to a certain extent, in the embodiment of the application, the alarm threshold corresponding to the index data to be detected can be determined based on the historical index data, and thus, after the size relationship between the index data to be detected and the alarm threshold is determined, whether the index data to be detected is abnormal or not can be determined.
As shown in fig. 2, the alarm threshold may be determined according to the following steps:
s201, constructing a cumulative distribution function by taking historical index data as an independent variable and cumulative distribution probability as a dependent variable;
s202, based on a preset probability threshold and the constructed cumulative distribution function, determining historical index data corresponding to the preset probability threshold, and determining the historical index data as an alarm threshold corresponding to the index data to be detected.
Here, a cumulative distribution function for representing the probability distribution of the historical index data may be first constructed with the historical index data as an independent variable and the cumulative distribution probability as a dependent variable. After the cumulative distribution function is determined, historical index data corresponding to a preset probability threshold can be determined, and the historical index data can be used as an alarm threshold.
The selection of the relevant preset probability threshold is related to the polarity of the index data, and for the forward index data, a smaller probability threshold, for example, 0.1, may be set in the embodiment of the present application, and at this time, if it is determined that the index data to be detected is smaller than the historical index data pointed to at 0.1, it may be determined that the detected index data is abnormal. Here, the lower the probability threshold is set, the more severe the requirement for index change alarm is. For example, when the number of service orders is determined to be 100 based on a plurality of historical order numbers as a kind of forward direction index data, it is possible to confirm that there is an abnormality in the number of service orders; similarly, for negative indicator data, a larger probability threshold, for example, 0.9, may be set in the embodiment of the present application, and at this time, if it is determined that the indicator data to be detected is greater than the historical indicator data pointed to by 0.9, it may be determined that the detected indicator data is abnormal. Here, the higher the probability threshold is set, the more strict the requirement for the index transaction alarm is.
In consideration of different value ranges and variation trends of different index data, for example, some indexes fluctuate continuously, some indexes gradually rise, and some indexes gradually fall, so that the indexes can be preprocessed first to reduce the indexes to the same numerical space, and then threshold comparison is performed. In the embodiment of the present application, a mean shift transformation method may be adopted to perform normalization processing, as shown in the following formula:
where r denotes index data after transformation, x denotes index data before transformation, w denotes a time window, and if w is 7, the physical meaning of r after transformation is the cyclic ratio.
In the embodiment of the application, whether the index data to be detected is abnormal or not can be determined based on the threshold value determination method, the index data to be detected can be analyzed in at least one layer of dimensionality when the abnormality is determined to exist, and the reason why the index data to be detected is abnormal is determined until a preset analysis cut-off condition is reached, so that the subsequent service quality of a service platform can be improved conveniently.
The at least one layer of dimension may be a layer of dimension or a multilayer of dimension, and specifically, whether to perform one-layer dimension or multilayer dimension analysis may be determined based on a preset analysis cutoff condition. For the analysis of each layer of dimension, the reason why the index data to be detected is abnormal in the layer of dimension can be determined based on the information indicated by the target dimension index in the layer of dimension. As shown in fig. 3, the abnormality cause may be determined as follows:
s301, aiming at each layer of dimensionality, determining each candidate dimensionality index corresponding to the layer of dimensionality; determining the relative entropy of each candidate dimension index based on the data distribution of the index data to be detected on each candidate dimension index, and selecting the candidate dimension index with the maximum relative entropy as a target dimension index under the layer dimension;
s302, when a preset analysis cut-off condition is reached, determining the reason for enabling the index data to be detected to have abnormity based on the information indicated by the target dimension index determined under the at least one layer of dimension.
Here, in the embodiment of the application, first, each candidate dimension index corresponding to each layer of dimension may be determined, then, based on data distribution of the to-be-detected index data on each candidate dimension index, the relative entropy of each candidate dimension index may be determined, and finally, the candidate dimension index with the largest relative entropy is selected as the target dimension index in the layer of dimension, so that the reason why the to-be-detected index data is abnormal may be determined based on information indicated by the target dimension index determined in at least one layer of dimension.
The candidate dimension index corresponding to each layer of dimension may be determined based on each candidate dimension index included in the preset dimension list. In the embodiment of the application, when analyzing each layer of dimension for the index data, the most suitable analysis dimension needs to be selected. Here, for a first layer of dimensions in the at least one layer of dimensions, each candidate dimension index included in the preset dimension list may be determined as a candidate dimension index corresponding to the layer of dimensions, that is, as a dimension analysis of the first layer, and a most suitable analysis dimension may be selected from all candidate dimension indexes included in the preset dimension list as a target dimension index in the first layer of dimensions; for a second-layer dimension in at least one-layer dimension, a target dimension index under the first-layer dimension can be screened from a preset dimension list, and then the most appropriate analysis dimension is selected from the remaining candidate dimension indexes to serve as the target dimension index under the second-layer dimension; similarly, for the third dimension of the at least one dimension, the target dimension index in the first dimension and the target dimension index in the second dimension may be first screened, and then selected again, and so on, and no further description is given.
Here, taking the number of service orders as the index data to be detected as an example, the preset dimension list may include candidate dimension indexes including indexes such as a city, a user group, an order channel, and an order duration, when performing dimension analysis on the index data to be detected, the first layer may select the dimension index of the city, the second layer may select the dimension index of the order channel, and the third layer may select the dimension index of the user group.
In the embodiment of the present application, in order to select the most suitable analysis dimension (i.e., target dimension index) for each layer of dimension, the corresponding target dimension index may be selected based on the relative entropy of each candidate dimension index corresponding to each layer of dimension.
For each candidate dimension index corresponding to each layer of dimension, the current data distribution of each candidate dimension index data indicated by the candidate dimension index at the current time and the historical data distribution of each candidate dimension index data indicated by the candidate dimension index at the historical time may be determined first, and then the relative entropy of the candidate dimension index may be determined based on the historical data distribution and the distribution difference between the current data distribution and the historical data distribution.
In order to facilitate understanding of the above-described determination process of the relative entropy, the following formula may be incorporated for explanation.
Wherein D isKLRelative entropy (i.e., KL divergence value) for any candidate dimension index; p (x.) is the historical data distribution of each candidate dimension index data indicated by the candidate dimension index at the historical moment, q (x.) is the current data distribution of each candidate dimension index data indicated by the candidate dimension index at the current moment, and N is the total number of the candidate dimension index data.
When the KL divergence value of a candidate dimension index is larger, the difference between the current distribution and the historical distribution of the dimension index is too large, and the dimension is more likely to be the cause of index abnormality. Therefore, in the embodiment of the present application, for the analysis of each layer of dimensionality, the dimension index with the largest KL divergence value may be selected as the analysis dimensionality of the current layer of the drill-down tree by comparing the KL divergence values of each selectable dimensionality. After dimension analysis is performed on each layer of the drill-down tree, the reason for finally causing the index abnormality can be determined.
In the embodiment of the application, the number of the analyzed dimension layers is not too large, and is not too small, the too large number of the dimension layers may bring a large calculation amount, and the too small number of the dimension layers may cause insufficient depth of analysis, which is not enough to find out a final abnormal reason. In order to consider both the amount of calculation and the analysis depth, in the embodiment of the present application, when the number of layers of dimension analysis reaches a preset number of layers (e.g., 3 layers), it may be determined that an analysis cutoff condition is reached, or when candidate dimension indexes that are not screened out in a preset dimension list are empty (i.e., all candidate dimension indexes in the preset dimension list are polled), it may be determined that the analysis cutoff condition is reached, or when the relative entropy of a target dimension index determined by current layer dimension analysis is smaller than a preset entropy, it may be determined that the analysis cutoff condition is reached. It should be noted that, in the embodiments of the present application, the analysis cutoff condition may be combined as a final analysis cutoff condition, and the final analysis cutoff condition is not particularly limited.
In the embodiment of the application, when determining the dimension index adopted by each layer of the drilling number, one leaf node needs to be selected as a final transaction root, and here, the reason for causing the index data to be detected to have abnormality can be determined based on information indicated by the target dimension index determined under at least one layer of dimension and data distribution of the index data to be detected on the target dimension index. As shown in fig. 4, the process of determining the cause of the abnormality specifically includes the following steps:
s401, aiming at each layer of dimensionality, determining the ring ratio contribution degree of each candidate dimensionality index data indicated by the target dimensionality index based on the data distribution of the index data to be detected on the target dimensionality index determined by the layer of dimensionality; selecting candidate dimension index data with the largest ring ratio contribution degree as target dimension index data and serving as an analysis node under the next layer of dimension;
s402, determining the reason for enabling the index data to be detected to have abnormity based on the target dimension index data determined under the at least one layer of dimension.
Here, for each layer of dimensionality, the ring ratio contribution degree of each candidate dimensionality index data indicated by the target dimensionality index may be determined based on the data distribution of the index data to be detected on the target dimensionality index determined by the layer of dimensionality, then the candidate dimensionality index data with the largest ring ratio contribution degree may be selected as the target dimensionality index data and used as an analytic node of the next layer of dimensionality, and so on, the reason that the index data to be detected is abnormal is determined through the target dimensionality index data corresponding to each layer of dimensionality.
The determination process of the ring ratio contribution degree is similar to the determination process of the KL divergence value, namely, dimension index data which has the largest influence on the current distribution difference value is searched for in each layer, and the dimension index data is represented by the reduction degree of the data proportion of each dimension index data in the historical data distribution and the data proportion of the dimension index data in the current data distribution.
To facilitate understanding of the above determination process of the transaction root, the following description may be made with reference to fig. 5 and a specific example.
As shown in fig. 5, the number of service orders is used as index data to be detected, when it is determined that candidate dimension indexes in the preset dimension list are dimension indexes such as a city, a service mode, an order channel, and the like, if it is determined that the KL dispersion value of the city is 0.001259 (maximum), the KL dispersion value of the service mode is 0.001011, and the KL dispersion value of the order channel is 0.000154, the dimension index of the city can be used as a result of first-layer dimension analysis, and the maximum ring-to-ring ratio contribution degree corresponding to wuhan city is considered, at this time, next-layer dimension analysis can be performed based on the leaf node. For the second-layer dimension, when it is determined that the KL variance value of the service mode corresponding to the leaf node is 0.00063 (maximum) and the KL variance value of the order channel is 0.00044, the dimension index of the service mode may be used as a result of second-layer dimension analysis, and considering that the ring ratio contribution degree corresponding to the direct connection mode is maximum, at this time, the next-layer dimension analysis may be performed based on the leaf node. For the third-level dimension, when it is determined that the KL divergence value of the order channel corresponding to the leaf node is 0.000014, the dimension index of the order channel may be used as a result of the third-level dimension analysis, and it is considered that the ring ratio contribution degree corresponding to the driver end is the largest, at this time, it may be determined that the driver end channel in the direct connection mode in wuhan city causes an abnormal service order quantity when it is determined that the analysis cutoff condition is reached.
Based on the same inventive concept, a data processing apparatus corresponding to the data processing method is also provided in the embodiments of the present application, and because the principle of the apparatus in the embodiments of the present application for solving the problem is similar to the data processing method described above in the embodiments of the present application, the implementation of the apparatus may refer to the implementation of the method, and repeated details are not described again.
Referring to fig. 6, which is a schematic diagram of a data processing apparatus according to a second embodiment of the present application, the apparatus includes:
the data acquisition module 601 is configured to acquire index data to be detected and historical index data corresponding to the index data to be detected, which are generated within a historical duration;
a threshold determining module 602, configured to determine, based on each historical index data, an alarm threshold corresponding to the index data to be detected;
an anomaly determination module 603, configured to determine whether the index data to be detected is abnormal based on a comparison result between the index data to be detected and the alarm threshold.
In one embodiment, the apparatus further comprises:
the reason determining module 604 is configured to, when it is determined that the to-be-detected index data is abnormal, perform analysis in at least one layer of dimensionality on the to-be-detected index data until a preset analysis cutoff condition is reached, determine a reason why the to-be-detected index data is abnormal.
In an embodiment, the cause determining module 604 is configured to determine a cause that causes the to-be-detected index data to have an abnormality according to the following steps:
determining each candidate dimension index corresponding to each layer dimension in the at least one layer dimension; determining the relative entropy of each candidate dimension index based on the data distribution of the index data to be detected on each candidate dimension index, and selecting the candidate dimension index with the maximum relative entropy as a target dimension index under the layer of dimension;
and when a preset analysis cut-off condition is reached, determining the reason for enabling the index data to be detected to have abnormity based on the information indicated by the target dimension index determined under the at least one layer of dimension.
In one embodiment, the cause determination module 604 is configured to determine the relative entropy of each candidate dimension indicator according to the following steps:
for each candidate dimension index corresponding to each layer of dimension, determining the current data distribution of each candidate dimension index data indicated by the candidate dimension index at the current moment and the historical data distribution of each candidate dimension index data indicated by the candidate dimension index at the historical moment; and determining the relative entropy of the candidate dimension index based on the historical data distribution and the distribution difference between the current data distribution and the historical data distribution.
In an embodiment, the reason determining module 604 is configured to determine each candidate dimension index corresponding to the layer dimension according to the following steps:
when the layer dimension is a first layer dimension of the at least one layer dimension, determining each candidate dimension index included in a preset dimension list as a candidate dimension index corresponding to the layer dimension;
when the layer dimension is the other layer dimension in the at least one layer dimension, after the target dimension index determined by the dimension before the other layer dimension is screened out from each candidate dimension index included in the preset dimension list, each candidate dimension index which is not screened out in the preset dimension list is determined as a candidate dimension index corresponding to the layer dimension.
In one embodiment, the preset resolution cutoff condition comprises one of the following conditions:
the number of layers of dimension analysis reaches a preset number of layers;
the candidate dimension indexes which are not screened out in the preset dimension list are null;
and the relative entropy of the target dimension index determined by the current layer dimension analysis is smaller than the preset entropy.
In an embodiment, the cause determining module 604 is configured to determine a cause that causes the to-be-detected index data to have an abnormality according to the following steps:
and determining the reason for enabling the index data to be detected to have abnormity based on the information indicated by the target dimension index determined under the at least one layer of dimension and the data distribution of the index data to be detected on the target dimension index.
In an embodiment, the cause determining module 604 is configured to determine a cause that causes the to-be-detected index data to have an abnormality according to the following steps:
for each layer of dimensionality, determining the ring ratio contribution degree of each candidate dimensionality index data indicated by the target dimensionality index based on the data distribution of the index data to be detected on the target dimensionality index determined by the layer of dimensionality; selecting candidate dimension index data with the largest ring ratio contribution degree as target dimension index data and serving as an analysis node under the next layer of dimension;
and determining the reason for enabling the index data to be detected to have abnormity based on the target dimension index data determined under the at least one layer of dimension.
In an embodiment, the threshold determining module 602 is configured to determine an alarm threshold corresponding to the index data to be detected according to the following steps:
taking historical index data as an independent variable and cumulative distribution probability as a dependent variable to construct a cumulative distribution function;
and determining historical index data corresponding to a preset probability threshold value based on the preset probability threshold value and the constructed cumulative distribution function, and determining the historical index data as an alarm threshold value corresponding to the index data to be detected.
In an embodiment, the anomaly determining module 603 is configured to determine whether the index data to be detected is anomalous according to the following steps:
if the index data to be detected is forward index data, judging whether the index data to be detected is smaller than the alarm threshold value; if so, determining that the index data to be detected is abnormal;
if the index data to be detected is negative index data, judging whether the index data to be detected is larger than the alarm threshold value; and if so, determining that the index data to be detected is abnormal.
EXAMPLE III
An embodiment of the present application provides an electronic device, as shown in fig. 7, the electronic device includes: a processor 701, a storage medium 702 and a bus 703, where the storage medium 702 stores machine-readable instructions executable by the processor 701 (such as execution instructions corresponding to the data obtaining module 601, the threshold determining module 602, and the exception determining module 603 in the data processing apparatus in fig. 6, and the like), when the electronic device runs, the storage medium 702 of the processor 701 communicates with each other through the bus 703, and the machine-readable instructions, when executed by the processor 701, perform the following processes:
acquiring index data to be detected and historical index data which are generated in historical time and correspond to the index data to be detected;
determining an alarm threshold corresponding to the index data to be detected based on each historical index data;
and determining whether the index data to be detected is abnormal or not based on a comparison result between the index data to be detected and the alarm threshold value.
In one embodiment, the instructions executed by the processor 701 further include:
when the index data to be detected is determined to be abnormal, analyzing the index data to be detected in at least one layer of dimensionality until a preset analysis cut-off condition is reached, and determining the reason for enabling the index data to be detected to be abnormal.
In an embodiment, in the instruction executed by the processor 701, the analyzing the to-be-detected index data in at least one layer of dimensionality until a preset analysis cutoff condition is reached, and determining a cause that the to-be-detected index data is abnormal includes:
determining each candidate dimension index corresponding to each layer dimension in the at least one layer dimension; determining the relative entropy of each candidate dimension index based on the data distribution of the index data to be detected on each candidate dimension index, and selecting the candidate dimension index with the maximum relative entropy as a target dimension index under the layer of dimension;
and when a preset analysis cut-off condition is reached, determining the reason for enabling the index data to be detected to have abnormity based on the information indicated by the target dimension index determined under the at least one layer of dimension.
In an embodiment, in the instruction executed by the processor 701, the determining the relative entropy of each candidate dimension index based on the data distribution of the index data to be detected on each candidate dimension index includes:
for each candidate dimension index corresponding to each layer of dimension, determining the current data distribution of each candidate dimension index data indicated by the candidate dimension index at the current moment and the historical data distribution of each candidate dimension index data indicated by the candidate dimension index at the historical moment; and determining the relative entropy of the candidate dimension index based on the historical data distribution and the distribution difference between the current data distribution and the historical data distribution.
In an embodiment, the determining, in the instruction executed by the processor 701, each candidate dimension index corresponding to the layer dimension includes:
when the layer dimension is a first layer dimension of the at least one layer dimension, determining each candidate dimension index included in a preset dimension list as a candidate dimension index corresponding to the layer dimension;
when the layer dimension is the other layer dimension in the at least one layer dimension, after the target dimension index determined by the dimension before the other layer dimension is screened out from each candidate dimension index included in the preset dimension list, each candidate dimension index which is not screened out in the preset dimension list is determined as a candidate dimension index corresponding to the layer dimension.
In one embodiment, in the instructions executed by the processor 701, the preset parsing cutoff condition includes one of the following conditions:
the number of layers of dimension analysis reaches a preset number of layers;
the candidate dimension indexes which are not screened out in the preset dimension list are null;
and the relative entropy of the target dimension index determined by the current layer dimension analysis is smaller than the preset entropy.
In an embodiment, in the instruction executed by the processor 701, the determining, based on information indicated by the target dimension index determined in the at least one layer of dimensions, a reason for causing the data of the index to be detected to have an abnormality includes:
and determining the reason for enabling the index data to be detected to have abnormity based on the information indicated by the target dimension index determined under the at least one layer of dimension and the data distribution of the index data to be detected on the target dimension index.
In an embodiment, in the instruction executed by the processor 701, the determining, based on information indicated by the target dimension index determined in the at least one layer of dimensions and data distribution of the index data to be detected on the target dimension index, a reason for causing the index data to be detected to have an abnormality includes:
for each layer of dimensionality, determining the ring ratio contribution degree of each candidate dimensionality index data indicated by the target dimensionality index based on the data distribution of the index data to be detected on the target dimensionality index determined by the layer of dimensionality; selecting candidate dimension index data with the largest ring ratio contribution degree as target dimension index data and serving as an analysis node under the next layer of dimension;
and determining the reason for enabling the index data to be detected to have abnormity based on the target dimension index data determined under the at least one layer of dimension.
In an embodiment, in the instructions executed by the processor 701, the determining, based on each historical index data, an alarm threshold corresponding to the index data to be detected includes:
taking historical index data as an independent variable and cumulative distribution probability as a dependent variable to construct a cumulative distribution function;
and determining historical index data corresponding to a preset probability threshold value based on the preset probability threshold value and the constructed cumulative distribution function, and determining the historical index data as an alarm threshold value corresponding to the index data to be detected.
In an embodiment, in the instruction executed by the processor 701, the determining whether the index data to be detected is abnormal based on the comparison result between the index data to be detected and the alarm threshold includes:
if the index data to be detected is forward index data, judging whether the index data to be detected is smaller than the alarm threshold value; if so, determining that the index data to be detected is abnormal;
if the index data to be detected is negative index data, judging whether the index data to be detected is larger than the alarm threshold value; and if so, determining that the index data to be detected is abnormal.
An embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor 701, the steps of the data processing method are performed.
Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, and the like, and when a computer program on the storage medium is run, the data processing method can be executed, so that the problems that the automation degree of a manual detection mode in the related art is low, and particularly, when key indexes needing to be maintained are more, time and labor are wasted, and the efficiency is low are solved, and further, the effects that an alarm threshold value can be determined based on historical data to realize automatic detection of abnormal conditions, and time and labor are saved are achieved.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (14)
1. A method of data processing, the method comprising:
acquiring index data to be detected and historical index data which are generated in historical time and correspond to the index data to be detected;
determining an alarm threshold corresponding to the index data to be detected based on each historical index data;
and determining whether the index data to be detected is abnormal or not based on a comparison result between the index data to be detected and the alarm threshold value.
2. The method of claim 1, further comprising:
when the index data to be detected is determined to be abnormal, analyzing the index data to be detected in at least one layer of dimensionality until a preset analysis cut-off condition is reached, and determining the reason for enabling the index data to be detected to be abnormal.
3. The method according to claim 2, wherein the analyzing the index data to be detected in at least one layer of dimensionality until a preset analysis cutoff condition is reached, and determining the reason for the abnormality of the index data to be detected comprises:
determining each candidate dimension index corresponding to each layer dimension in the at least one layer dimension; determining the relative entropy of each candidate dimension index based on the data distribution of the index data to be detected on each candidate dimension index, and selecting the candidate dimension index with the maximum relative entropy as a target dimension index under the layer of dimension;
and when a preset analysis cut-off condition is reached, determining the reason for enabling the index data to be detected to have abnormity based on the information indicated by the target dimension index determined under the at least one layer of dimension.
4. The method according to claim 3, wherein the determining the relative entropy of each candidate dimension index based on the data distribution of the index data to be detected on each candidate dimension index comprises:
for each candidate dimension index corresponding to each layer of dimension, determining the current data distribution of each candidate dimension index data indicated by the candidate dimension index at the current moment and the historical data distribution of each candidate dimension index data indicated by the candidate dimension index at the historical moment; and determining the relative entropy of the candidate dimension index based on the historical data distribution and the distribution difference between the current data distribution and the historical data distribution.
5. The method of claim 3, wherein determining each candidate dimension indicator corresponding to the layer dimension comprises:
when the layer dimension is a first layer dimension of the at least one layer dimension, determining each candidate dimension index included in a preset dimension list as a candidate dimension index corresponding to the layer dimension;
when the layer dimension is the other layer dimension in the at least one layer dimension, after the target dimension index determined by the dimension before the other layer dimension is screened out from each candidate dimension index included in the preset dimension list, each candidate dimension index which is not screened out in the preset dimension list is determined as a candidate dimension index corresponding to the layer dimension.
6. The method of claim 5, wherein the preset resolution cutoff condition comprises one of:
the number of layers of dimension analysis reaches a preset number of layers;
the candidate dimension indexes which are not screened out in the preset dimension list are null;
and the relative entropy of the target dimension index determined by the current layer dimension analysis is smaller than the preset entropy.
7. The method according to claim 3, wherein the determining, based on the information indicated by the target dimension indicator determined in the at least one layer of dimension, the cause of the abnormality of the indicator data to be detected comprises:
and determining the reason for enabling the index data to be detected to have abnormity based on the information indicated by the target dimension index determined under the at least one layer of dimension and the data distribution of the index data to be detected on the target dimension index.
8. The method according to claim 7, wherein the determining, based on information indicated by the target dimension indicator determined in the at least one layer of dimension and data distribution of the indicator data to be detected on the target dimension indicator, a cause of abnormality in the indicator data to be detected includes:
for each layer of dimensionality, determining the ring ratio contribution degree of each candidate dimensionality index data indicated by the target dimensionality index based on the data distribution of the index data to be detected on the target dimensionality index determined by the layer of dimensionality; selecting candidate dimension index data with the largest ring ratio contribution degree as target dimension index data and serving as an analysis node under the next layer of dimension;
and determining the reason for enabling the index data to be detected to have abnormity based on the target dimension index data determined under the at least one layer of dimension.
9. The method according to claim 1, wherein the determining an alarm threshold corresponding to the index data to be detected based on each historical index data comprises:
taking historical index data as an independent variable and cumulative distribution probability as a dependent variable to construct a cumulative distribution function;
and determining historical index data corresponding to a preset probability threshold value based on the preset probability threshold value and the constructed cumulative distribution function, and determining the historical index data as an alarm threshold value corresponding to the index data to be detected.
10. The method according to claim 9, wherein the determining whether the index data to be detected is abnormal or not based on the comparison result between the index data to be detected and the alarm threshold value comprises:
if the index data to be detected is forward index data, judging whether the index data to be detected is smaller than the alarm threshold value; if so, determining that the index data to be detected is abnormal;
if the index data to be detected is negative index data, judging whether the index data to be detected is larger than the alarm threshold value; and if so, determining that the index data to be detected is abnormal.
11. A data processing apparatus, characterized in that the apparatus comprises:
the data acquisition module is used for acquiring index data to be detected and historical index data which are generated in historical duration and correspond to the index data to be detected;
the threshold value determining module is used for determining an alarm threshold value corresponding to the index data to be detected based on each historical index data;
and the abnormity determining module is used for determining whether the index data to be detected is abnormal or not based on the comparison result between the index data to be detected and the alarm threshold value.
12. The apparatus of claim 11, further comprising:
and the reason determining module is used for analyzing the index data to be detected in at least one layer of dimensionality when the abnormality of the index data to be detected is determined, and determining the reason for enabling the abnormality of the index data to be detected when a preset analysis cut-off condition is reached.
13. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the steps of the data processing method according to any one of claims 1 to 10.
14. A computer-readable storage medium, having stored thereon a computer program for performing, when executed by a processor, the steps of the data processing method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010044211.0A CN111831517A (en) | 2020-01-15 | 2020-01-15 | Data processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010044211.0A CN111831517A (en) | 2020-01-15 | 2020-01-15 | Data processing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111831517A true CN111831517A (en) | 2020-10-27 |
Family
ID=72913379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010044211.0A Pending CN111831517A (en) | 2020-01-15 | 2020-01-15 | Data processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111831517A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113342616A (en) * | 2021-06-30 | 2021-09-03 | 北京奇艺世纪科技有限公司 | Abnormal index information positioning method and device, electronic equipment and storage medium |
| CN113525332A (en) * | 2021-09-17 | 2021-10-22 | 中车戚墅堰机车车辆工艺研究所有限公司 | Brake monitoring method, brake monitoring device, electronic equipment and computer readable storage medium |
| CN113836204A (en) * | 2021-09-28 | 2021-12-24 | 安徽听见科技有限公司 | Interface abnormity detection method and device, electronic equipment and storage medium |
-
2020
- 2020-01-15 CN CN202010044211.0A patent/CN111831517A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113342616A (en) * | 2021-06-30 | 2021-09-03 | 北京奇艺世纪科技有限公司 | Abnormal index information positioning method and device, electronic equipment and storage medium |
| CN113342616B (en) * | 2021-06-30 | 2023-10-27 | 北京奇艺世纪科技有限公司 | Positioning method and device of abnormal index information, electronic equipment and storage medium |
| CN113525332A (en) * | 2021-09-17 | 2021-10-22 | 中车戚墅堰机车车辆工艺研究所有限公司 | Brake monitoring method, brake monitoring device, electronic equipment and computer readable storage medium |
| CN113525332B (en) * | 2021-09-17 | 2022-01-28 | 中车戚墅堰机车车辆工艺研究所有限公司 | Brake monitoring method, brake monitoring device, electronic equipment and computer readable storage medium |
| CN113836204A (en) * | 2021-09-28 | 2021-12-24 | 安徽听见科技有限公司 | Interface abnormity detection method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111831517A (en) | Data processing method and device, electronic equipment and storage medium | |
| EP3722901B1 (en) | Vehicle trouble diagnosis method and vehicle trouble diagnosis apparatus | |
| CN111064614B (en) | Fault root cause positioning method, device, equipment and storage medium | |
| CN111143102B (en) | Abnormal data detection method and device, storage medium and electronic equipment | |
| CN108696368B (en) | Network element health state detection method and equipment | |
| CN112231181B (en) | Data abnormal update detection method and device, computer equipment and storage medium | |
| CN110008247B (en) | Method, device and equipment for determining abnormal source and computer readable storage medium | |
| CN110995524B (en) | Flow data monitoring method and device, electronic equipment and computer readable medium | |
| US11507674B2 (en) | Quantifying privacy impact | |
| CN109976971B (en) | Hard disk state monitoring method and device | |
| KR101776350B1 (en) | Method and system for diagnosing compressors | |
| CN110399903B (en) | Abnormal data detection method and device and computer readable storage medium | |
| CN113988723A (en) | User behavior locking method and system based on power consumption data anomaly analysis | |
| EP3335185A1 (en) | Diabetes management system with alert status interface and patient prioritization | |
| CN110673973A (en) | Application programming interface API (application programming interface) abnormity determining method and device | |
| US20160042141A1 (en) | Integrated assessment of needs in care management | |
| CN110991241B (en) | Abnormality recognition method, apparatus, and computer-readable medium | |
| CN111555895B (en) | Method, device, storage medium and computer equipment for analyzing website faults | |
| CN111506455A (en) | Checking method and device for service release result | |
| CN113535458B (en) | Abnormal false alarm processing method and device, storage medium and terminal | |
| CN114490829A (en) | Fault identification method, device, equipment and storage medium | |
| CN115358336A (en) | Power utilization abnormity detection method and device and electronic equipment | |
| CN116302774A (en) | Scheduling task monitoring method and device, electronic equipment and readable storage medium | |
| CN112949951A (en) | Data prediction method, data prediction device, electronic equipment and storage medium | |
| WO2016163008A1 (en) | Fault diagnostic device and fault diagnostic method |
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 |