Data processing method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a data processing method and device, electronic equipment, a storage medium and a program product. According to the specific implementation scheme, the method comprises the steps that firstly, a to-be-processed array is obtained, the to-be-processed array comprises multiple pieces of to-be-processed data arranged according to the time sequence, then a difference array corresponding to the to-be-processed array is determined, and the difference array comprises multiple pieces of difference measurement data; the difference measurement data indicates the difference degree between the to-be-processed data in the to-be-processed array, then processing the to-be-processed array and the data in the difference array so as to determine the trend change interval of the to-be-processed array, and finally performing reason analysis based on the change trend of the to-be-processed data in the trend change interval. By determining the trend change interval of the array, the data volume of the to-be-processed data for reason analysis is reduced, and the data processing efficiency is improved.

Description

Technical Field

[0001] This disclosure relates to computer technology, and more particularly to a data processing method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] Data processing is the process of extracting valuable information from data to support decision-making and problem-solving. For example, attributing application degradation requires processing the data generated during application operation. Application degradation refers to negative changes in application performance or functionality during operation. This degradation may affect the normal use of the application. Degradation attribution is the process of identifying and determining the causes of degradation.

[0003] Currently, when attributing application degradation, the entire amount of data generated during application operation is directly attributed to the cause. However, due to the massive amount of data, the processing efficiency is low. Summary of the Invention

[0004] This disclosure provides a data processing method, apparatus, electronic device, storage medium, and program product for analyzing the differences between data in an array to be processed.

[0005] In a first aspect, embodiments of this disclosure provide a data processing method, including:

[0006] Obtain a processing array, which includes multiple processing data arranged in chronological order, wherein the processing data is data associated with the application to be processed;

[0007] Determine the difference array corresponding to the array to be processed, the difference array including multiple difference measurement data, the difference measurement data indicating the degree of difference between the data to be processed in the array to be processed;

[0008] The data in the array to be processed and the difference array are processed to determine the trend change range of the array to be processed, and the change trend of the data to be processed within the trend change range is greater than a first significant threshold.

[0009] Analyze the reasons for the changes in the data to be processed within the aforementioned trend change range.

[0010] Secondly, embodiments of this disclosure also provide a data processing apparatus, including:

[0011] The acquisition module is used to acquire a processing array, which includes multiple processing data arranged in chronological order, and the processing data is data associated with the application to be processed.

[0012] The first determining module is used to determine the difference array corresponding to the array to be processed, the difference array including multiple difference measurement data, the difference measurement data indicating the degree of difference between the data to be processed in the array to be processed;

[0013] The second determining module is used to process the data in the array to be processed and the difference array, and determine the trend change range of the array to be processed, wherein the change trend of the data to be processed within the trend change range is greater than a first significant threshold.

[0014] The processing module is used to perform cause analysis based on the changing trend of the data to be processed within the trend change range.

[0015] Thirdly, embodiments of this disclosure also provide an electronic device, including:

[0016] One or more processing devices;

[0017] Storage device for storing one or more programs.

[0018] When the one or more programs are executed by the one or more processing devices, the one or more processing devices implement any of the data processing methods described in this disclosure.

[0019] Fourthly, embodiments of this disclosure also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform any of the data processing methods described in this disclosure.

[0020] Fifthly, embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements the data processing method described in any one of these disclosures.

[0021] The technical solution of this disclosure first obtains a processing array consisting of multiple data to be processed arranged in chronological order. Next, it determines a difference array corresponding to the processing array, which includes multiple difference measurement data indicating the degree of difference between the data to be processed in the processing array. Then, it processes the data within the processing array and the difference array to determine the trend change range of the processing array. Finally, it performs causal analysis based on the trend change trend of the data to be processed within the trend change range. The data processing method provided in this disclosure first determines the trend change range in the processing array, and then performs causal analysis on the trend change trend of the data to be processed within the trend change range, rather than directly performing causal analysis on all the data to be processed. By determining the trend change range of the array, the amount of data to be processed for causal analysis is reduced, improving the efficiency of data processing. Attached Figure Description

[0022] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0023] Figure 1 This is a schematic flowchart of a data processing method provided in an embodiment of this disclosure;

[0024] Figure 2 This is a schematic diagram of a data arrangement method provided in an embodiment of this disclosure;

[0025] Figure 3 This is a schematic flowchart of a method for determining a trend change range provided in an embodiment of this disclosure;

[0026] Figure 4 This is a schematic diagram of a data visualization provided in an embodiment of this disclosure;

[0027] Figure 5 This is a schematic diagram of an abnormal pending data provided in an embodiment of this disclosure;

[0028] Figure 6 This is a schematic diagram of data to be processed in an ascending range provided in an embodiment of this disclosure;

[0029] Figure 7 This is a schematic diagram of a descending interval of unprocessed data provided in an embodiment of this disclosure;

[0030] Figure 8 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this disclosure;

[0031] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0032] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0033] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0034] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0035] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0036] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0037] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0038] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0039] Figure 1This is a schematic flowchart of a data processing method provided in an embodiment of the present disclosure. The embodiments of the present disclosure are applicable to the situation of performing difference analysis on data in an array. The method can be executed by a data processing device, which can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, such as a mobile terminal, a PC, or a server.

[0040] like Figure 1 As shown, the method includes:

[0041] S110. Obtain a processing array, which includes multiple processing data arranged in chronological order, wherein the processing data is data associated with the application to be processed.

[0042] The data to be processed is organized into a processing array according to the time dimension, which can characterize the trend of the data. The trend of the data to be processed can be used to analyze the reasons for the degradation of the data.

[0043] In this embodiment, the array to be processed can be understood as a set of data waiting to be processed, which can be composed of multiple data to be processed arranged in chronological order, which can be the time when the data was collected.

[0044] The data to be processed can be understood as the individual data points in the array to be processed. This data can be of various types, such as integers and decimals, and can represent information related to the application being processed. The application can use this data to represent its own information, metrics, or characteristics.

[0045] This operation can either acquire the pending array transmitted by other electronic devices, or it can be that the electronic device determines the pending data to be processed and forms the pending array according to the time sequence of the determined pending data.

[0046] In one embodiment, multiple pending data sets of the application to be processed at each time point are obtained in chronological order. The pending data sets at each time point are then processed and used as the pending data sets for that time point. The pending data sets are then arranged in chronological order and placed into a pending data array to obtain the pending data array containing the pending data sets.

[0047] In this context, a time node can be considered a point in time within a defined time dimension. For example, if the dimension is days, the time node can be a date on a different day.

[0048] Taking the startup duration of the application to be processed as an example, for each time point, such as a certain day, the startup duration of each startup of the application to be processed within that day is determined. Then, the average of all startup durations for that day is determined as the startup duration of the application to be processed for that day, i.e., the data to be processed at that time point. As time progresses, data to be processed for different dates is acquired, and the data to be processed for each time point is added to the data to be processed in chronological order. Different data to be processed represent data at different time points, and the order of the data to be processed within the data to be processed is determined based on the time point corresponding to the data to be processed.

[0049] For example, Figure 2 This is a schematic diagram of a data arrangement method provided in an embodiment of this disclosure. For example... Figure 2 The original array is the array to be processed, and the data in the original array labeled 4-14 are the data to be processed. Each labeled data corresponds to a different time point in the array, and the time point represents the data to be processed increases sequentially as the label increases. The labels in the array to be processed can be considered as indices for the data to be processed, used to uniquely identify the data, such as identifying which position in the array the data to be processed belongs to.

[0050] S120. Determine the difference array corresponding to the array to be processed, wherein the difference array includes multiple difference measurement data, and the difference measurement data indicates the degree of difference between the data to be processed in the array to be processed.

[0051] In this embodiment, the difference array can be understood as an array generated from the array to be processed, used to represent the degree of difference between the data to be processed. The difference measure data can be understood as each data point in the difference array; the difference measure data can represent the degree of difference between the data to be processed, that is, the changes among the individual data points in the array to be processed. The greater the degree of difference between the data to be processed, the greater the trend of data change can be characterized.

[0052] This embodiment does not limit how the degree of difference between the data to be processed is determined. For example, the difference array can be obtained by performing a T-test on the array to be processed. Another method is to determine whether there is a significant difference between the means of two groups of samples in the array to be processed. The two groups of samples can be samples within two adjacent sliding windows of the array to be processed, with each sliding window having a step size of 1. Difference measures can characterize the degree of difference between the two groups of samples (i.e., the data to be processed). As the sliding window slides, multiple difference measures are determined, and these measures are added to the difference data in a predetermined order. Let the size of the sliding window be n, with adjacent sliding windows of equal size. The difference measures obtained after performing difference processing on the data to be processed within the two sliding windows can characterize the difference level of the first data point in the sliding window with the larger label.

[0053] For example, such as Figure 2 In order to ensure that the difference measurement data can also be determined at the beginning and end of the array to be processed, data compensation can be performed on the array to be processed, that is, data is added before the beginning and after the end of the array to be processed to form an updated array to be processed.

[0054] In one embodiment, the size of the data added before the first position can be determined based on the value of the first position, such as the size of the data added before the first position being the same as the size of the first position. Similarly, the size of the data added after the last position can be determined based on the size of the last position, such as the size of the data added after the last position being the same as the size of the last position.

[0055] In one embodiment, the size of the data added before the first position can be determined based on the value of the data to be processed, which is the length of the sliding window starting from the first position of the array to be processed, and the size of the data added after the last position can be determined based on the value of the data to be processed, which is the length of the sliding window starting from the last position of the array to be processed.

[0056] The compensation array is the array to be processed after data compensation; that is, the array formed by adding data to the array to be processed. The number of data added is determined by a specified length. The specified length can be the sliding window size, which can be an empirical value determined based on the number of data points to be processed in the array. This disclosure allows for the selection of an appropriate sliding window size based on the characteristics of the data to be processed, such as supporting a sliding window size based on the day dimension. The sliding window size can be 3-30, ensuring the use of at least 3 data points, which can reduce the probability of short-term data fluctuations being identified as data mutation problems. Considering the computational burden and the issue of data fluctuations at the monthly granularity, the maximum sliding window size can be 30. The size of the sliding window can be represented by the number of data points. A sliding window of 3 can be considered to contain 3 data points. When the statistical dimension of the data points is day, one data point can represent the data summarized within one day.

[0057] Assuming the sliding window size is 3, the data labeled 1, 2, and 3 in the compensation array are the data added before the first element of the array to be processed, and the data labeled 15, 16, and 17 are the data added after the last element of the array to be processed.

[0058] like Figure 2 In the compensation array, data labeled 1, 2, and 3 can be used as subarray 1, and data labeled 4, 5, and 6 as subarray 2. The significance difference between the two subarrays (i.e., the two samples) is calculated. The method for calculating the significance difference can be an independent samples t-test. Performing an independent samples t-test on the two subarrays yields a difference measure. This difference measure is then written to position 4 in the significance difference array, representing the difference level of the first data point to be processed in the sliding window corresponding to the larger label (i.e., the data point to be processed at label 4 in the compensation array).

[0059] Next, keeping the sliding window size constant and the step size 1, the next two selected subarrays are data labeled 2, 3, and 4, and data labeled 5, 6, and 7. The resulting difference measure data is written to position 5 of the significance difference array. This process is repeated, changing the position of the selected subarrays until the end of the entire compensation array, as shown below. Figure 2 The process is calculated sequentially along the direction of the sliding process to obtain multiple difference measurement data indicating the degree of difference between the data to be processed, which are then placed into the difference array.

[0060] S130. Process the data in the array to be processed and the difference array to determine the trend change range of the array to be processed, wherein the change trend of the data to be processed within the trend change range is greater than a first significant threshold.

[0061] In this embodiment, the trend change interval can be understood as the range used to describe the trend of data change over a period of time or within a certain range. It is a region determined by the increase or decrease of data. Within the trend change interval, the data changes; the data can be increasing or decreasing. The first significance threshold can be understood as a threshold used to determine whether the data to be processed has undergone a significant change. The data to be processed within the trend change interval can be considered as data with a significant trend of change.

[0062] In this operation, the data in the array to be processed and the difference array can be processed separately to obtain the determined trend change range for each.

[0063] In one embodiment, a trend change range can be determined by identifying abnormal data within the array to be processed. For example, a trend change range can be determined based on the location of the abnormal data in the array to be processed.

[0064] In one embodiment, the trend change range is determined by analyzing the degree of difference, distribution, and values ​​of the data within the difference array. For example, based on the difference measure data within the difference array obtained from the array to be processed, the locations of points in the difference measure data that indicate significant differences in the data to be processed can also be identified, thus determining a trend change range.

[0065] S140. Analyze the reasons for the changes in the data to be processed within the trend change range.

[0066] The trend of change can be increasing or decreasing. Within the multiple trend change intervals obtained, the trend of change of the data to be processed is different. Based on each trend, the cause of the change can be analyzed, and the application to be processed within the trend change interval can be analyzed, such as attributing the data degradation of the application to be processed.

[0067] For example, the data to be processed indicates changes in the metrics of the application being processed. If the data to be processed shows a significant increase or decrease within a trend change range, it means that the metrics of the application being processed have changed significantly. By analyzing the trend of the data to be processed within the trend change range, the reasons for the changes in the metrics of the application being processed can be determined.

[0068] The technical solution of this disclosure first obtains a processing array consisting of multiple data to be processed arranged in chronological order. Next, it determines a difference array corresponding to the processing array, which includes multiple difference measurement data indicating the degree of difference between the data to be processed in the processing array. Then, it processes the data within the processing array and the difference array to determine the trend change range of the processing array. Finally, it performs causal analysis based on the trend change trend of the data to be processed within the trend change range. The data processing method provided in this disclosure first determines the trend change range in the processing array, and then performs causal analysis on the trend change trend of the data to be processed within the trend change range, rather than directly performing causal analysis on all the data to be processed. By determining the trend change range of the array, the amount of data to be processed for causal analysis is reduced, improving the efficiency of data processing.

[0069] Based on the above embodiments, modified embodiments of the above embodiments are proposed. It should be noted that, in order to keep the description brief, only the differences from the above embodiments are described in the modified embodiments.

[0070] In one embodiment, the trend change range includes a first trend change range and a second trend change range, and the step of processing the data within the array to be processed and the difference array to determine the trend change range of the array to be processed includes:

[0071] The first trend change range is determined based on the location of the abnormal data to be processed in the array to be processed;

[0072] Based on the difference measurement data in the difference array and the second significance threshold, a second trend change range is determined, whereby the second significance threshold is a threshold for measuring whether the data difference is significant.

[0073] In this embodiment, the first trend change interval and the second trend change interval can be trend change intervals determined by different arrays. The first trend change interval can be a trend change interval determined by processing the array to be processed. The second trend change interval can be a trend change interval determined by processing the difference array.

[0074] The first trend change interval can be defined by considering outliers in the data to be processed within the array. The second trend change interval can be considered as the trend change interval defined by the degree of difference represented by the difference measurement data in the difference array. For example, the second trend change interval can be understood as the trend change interval determined by the difference measurement data, the position of the difference measurement data in the difference array, and a second significance threshold. The second significance threshold can be understood as a threshold used to determine whether the differences between data are significant. The first and second significance thresholds are used in different scenarios and are not necessarily related.

[0075] Since both the array to be processed and the difference array can determine the trend change range, the trend change range can include the first trend change range and the second trend change range.

[0076] In this embodiment, it can be determined whether there is abnormal data to be processed in the array to be processed. If so, its location is determined, and a segment of the array to be processed is selected as the first trend change segment with that location as the center.

[0077] In this embodiment, a second significance threshold is set. When the value of a difference measure data in the difference array is greater than the second threshold, a segment of the difference array is selected as the second trend change interval, starting from the position of the difference measure data. Alternatively, the selected difference measure data greater than the second threshold are distributed and processed to determine the second trend change interval.

[0078] Figure 3 This is a schematic flowchart of a method for determining a trend change interval provided by an embodiment of the present disclosure. This embodiment of the present disclosure is applicable to the situation where a second trend change interval is determined based on difference measurement data in a difference array and a second significance threshold.

[0079] like Figure 3 As shown, the method includes:

[0080] S210. For each difference measure data in the difference array, determine whether the absolute value of the difference measure data is greater than the absolute value of the second significance threshold.

[0081] For each difference measure in the difference array, calculate its absolute value and compare it with the absolute value of the second significance threshold to identify the difference measures whose absolute values ​​are greater than the second significance threshold.

[0082] For example, Figure 4 This is a schematic diagram illustrating a data visualization provided in an embodiment of this disclosure. For example... Figure 4 The horizontal axis represents the index, and the vertical axis represents the data size. The solid line represents the broken line formed by the data to be processed in the array to be processed, and the dashed line represents the broken line formed by the difference measure data in the difference array. For a difference measure data to be considered positive, its absolute value must be greater than the positive second significance threshold. For a difference measure data to be negative, its absolute value must be less than the negative second significance threshold.

[0083] The second significance threshold corresponds to two horizontal dotted lines, which can be used to determine two different trends: increasing and decreasing. For example... Figure 4 As shown, this identifies the difference measures where the absolute value is greater than the second significance threshold. The difference measures pointed to by horizontal axis 6 have absolute values ​​greater than the second significance threshold, as do the difference measures pointed to by horizontal axis 9. The difference measures outside the two dashed lines can be considered as those with absolute values ​​greater than the second significance threshold, indicating a significant trend in the corresponding data to be processed. The difference measures and the data to be processed can be correlated using array indices, also known as labels, such as... Figure 2 In the difference array, the difference measure data labeled 4 corresponds to the data to be processed in the original array labeled 4. Figure 4 The rectangular box can be considered as the trend change range, and the data to be processed theoretically has a relatively obvious trend within the trend change range.

[0084] S220. If the absolute value of the difference measurement data is greater than the absolute value of the second significant threshold, the first index of the difference measurement data is determined as the difference position. The difference position indicates that the change trend of the corresponding data to be processed is greater than the first significant threshold. The data to be processed corresponding to the difference position is the data to be processed at the first index position in the array to be processed.

[0085] In this embodiment, the first index can be understood as an identifier indicating the position of the difference measurement data in the difference array. Each difference measurement data in the difference array has its unique first index. The first index can also indicate the position of the data to be processed corresponding to the difference measurement data in the data to be processed array. The difference measurement data and the data to be processed can be associated through the first index. The difference position can be understood as the position of the difference measurement data in the difference array where a significant difference occurs. If the change trend of the data to be processed is greater than the first significance threshold, the change trend of the data to be processed can be considered significant.

[0086] The first index of the difference measurement data that is greater than the second significance threshold is taken as the difference position, and the data to be processed corresponding to the difference position is the data to be processed at the first index position in the data to be processed. At this time, the change trend of the data to be processed is greater than the first significance threshold.

[0087] For example, if the absolute value of the difference measure data pointed to by the horizontal axis 6 is greater than the second significance threshold, this position is used as the first index, and the first index is used as the difference position. The data to be processed corresponding to this position is the data to be processed at the horizontal axis 6 position (see...). Figure 4 The array to be processed and the difference array share a common x-axis, and the points on this x-axis can be indices (also called labels). Similarly, the absolute value of the difference measure data pointed to by x-axis 9 is also greater than the second significance threshold, and this position can also be used as another first index or another difference position.

[0088] S230. Determine the continuous interval formed by the difference positions determined from the difference array.

[0089] In this embodiment, the data within a continuous interval is continuous, meaning that the data within the continuous interval can be connected one after another without any jumps or missing parts. A continuous interval can be considered as an interval formed by at least one consecutive difference position. Whether a continuous interval is continuous can be determined by indexing; if the indices of the difference measurement data greater than the second significance threshold are continuous, a continuous interval can be formed.

[0090] After identifying the difference metrics that exceed the second significance threshold, a continuous interval can be formed by each difference metric exceeding the second significance threshold. This means forming continuous intervals from the difference metrics that are consecutively indexed. Each continuous interval can contain at least one difference metric.

[0091] This operation can determine the difference location within a continuous interval formed in the difference array, which includes the difference measurement data indicated by the difference location.

[0092] For example, a continuous interval formed by the difference positions is determined based on the difference positions. The number of data points within the continuous interval can be single or multiple, such as... Figure 4 In the data, the difference measurement data pointed to by the horizontal axes 6, 7, and 8 are all greater than the second significance threshold, and can be regarded as a continuous interval.

[0093] S240. Based on the length of the continuous interval and the target data associated with the length, determine a second trend change interval, wherein the target data includes the values ​​of the data within the continuous interval or the difference array.

[0094] Using the difference measure data within a continuous interval as the target data, a second trend change interval is determined based on the length of the continuous interval and the target data. Depending on the length of the continuous interval, it is determined whether the second trend change interval is determined based on the values ​​of the data at the difference locations, or based on the difference array to determine the location of the extreme values ​​near the difference locations.

[0095] The technical solution of this disclosure first determines whether the absolute value of each difference measure data in the difference array is greater than a second significance threshold. If the absolute value of the difference measure data is greater than the second significance threshold, the first index of the difference measure data is determined as the difference position. Then, a continuous interval formed by the difference positions determined from the difference array is determined. Finally, a second trend change interval is determined based on the length of the continuous interval and the target data associated with the length. By refining the method for determining the trend change interval by the magnitude of the absolute value of the difference measure data, the method of determining the trend change interval based on the difference array is realized.

[0096] In one embodiment, determining the second trend change interval based on the length of the continuous interval and the target data associated with the length includes:

[0097] When the length of the continuous interval is equal to the first value, in the difference array, starting from the difference position included in the continuous interval, extreme points are selected on both sides of the difference position;

[0098] The second trend change interval is determined based on the position of the selected extreme point within the difference array.

[0099] In this embodiment, the first value can be understood as a value used to determine the length of a continuous interval, and the first value can be a unit length.

[0100] When the length of the continuous interval equals the first value, the length of the continuous interval is the shortest. In this case, extreme points can be selected from both sides of the difference array, starting from the difference position, and the position of the selected extreme points in the difference array can be determined. Based on the obtained position, the second trend change interval is determined using this position as the midpoint of the interval.

[0101] For example, the first value can be 1. So when the length of the continuous interval is 1, extreme points need to be selected in the difference array from the difference position to both sides. The positions corresponding to the extreme points are the center of the second trend change interval.

[0102] In this embodiment, extreme points can also be selected based on the upward or downward trend of a continuous interval. When the continuous interval is an upward interval, extreme points can be selected along the direction of data increase. When the continuous interval is a downward interval, extreme points can be selected along the direction of data decrease.

[0103] When selecting extreme points in this disclosure, the size of a sliding window can be determined.

[0104] In one embodiment, determining the trend change range of the array to be processed based on the position of the selected extreme point within the array to be processed includes:

[0105] The extreme point is centered on the position of the extreme point in the difference array, and the first interval with a set length of interval length is determined as the second trend change interval.

[0106] In this embodiment, the first set length is the size of the candidate interval set during extreme value search to prevent the escape of the interval with significant data changes.

[0107] This embodiment can determine the position of the extreme point within the difference array, and form an interval with the position as the center and the first set length as the interval length. This interval is the second trend change interval.

[0108] In one embodiment, determining the second trend change interval based on the length of the continuous interval and the target data associated with the length includes:

[0109] If the length of the continuous interval is greater than a first value and less than a second value, determine the maximum value of the absolute value of the data within the continuous interval.

[0110] If the maximum value is greater than the third significant threshold, the continuous interval is determined as the second trend change interval, and the first significant threshold is less than the third significant threshold.

[0111] In this embodiment, the second value can be understood as a value used to determine the length of a continuous interval. The second value is related to the sliding window size; for example, if the second value is equal to the sliding window size, the first value must be less than the second value. The third significance threshold is used to determine the magnitude of the absolute values ​​of data within the difference array. There is no necessary relationship between the first, second, and third significance thresholds. The second and third significance thresholds can be confidence values ​​selected based on the sliding window size and with reference to the T-test standard.

[0112] When the length of the continuous interval is greater than the first value and less than the second value, the length of the continuous interval is relatively short. It is necessary to determine the maximum value of the absolute value of the data within the continuous interval. When the maximum value is greater than the third significance threshold (i.e., greater than the relatively larger threshold between the second and third significance thresholds), it indicates that the data significance changes significantly within the continuous interval. Therefore, this continuous interval is taken as the second trend change interval.

[0113] For example, suppose the second value is the size of the sliding window, which is 3. That is, when the length of the continuous interval is greater than 1 and 3, the maximum value of the absolute value of the data in the continuous interval is determined. When the maximum value is greater than the third significance threshold, it indicates that the data has changed significantly in the continuous interval. Therefore, the continuous interval is taken as the second trend change interval.

[0114] In one embodiment, determining the second trend change interval based on the length of the continuous interval and the target data associated with the length includes:

[0115] If the length of the continuous interval is greater than the second value, determine the maximum value of the absolute value of the data within the continuous interval;

[0116] If the maximum value is greater than the second significant threshold, the continuous interval is determined as the second trend change interval.

[0117] When the length of the continuous interval is greater than the second value, the length of the continuous interval is relatively long, indicating that the significance of the data changes within the continuous interval is relatively reliable. Therefore, the maximum value of the absolute value of the data within the continuous interval can be determined. As long as this maximum value is greater than the second significance threshold (i.e., greater than the relatively smaller threshold between the second and third significance thresholds), it can be said that the significance of the data changes within the continuous interval is obvious. Therefore, this continuous interval is regarded as the second trend change interval.

[0118] For example, suppose the second value can be the size of the sliding window, 3. When the length of the continuous interval is greater than 3, the length of the continuous interval is already relatively long, indicating that the data changes significantly within the continuous interval. Then, it is only necessary to determine the maximum value of the absolute value of the data within the continuous interval. As long as the maximum value is greater than the second significance threshold, the continuous interval can be regarded as the second trend change interval.

[0119] In one embodiment, determining the first trend change range based on the location of the abnormal data to be processed in the array to be processed includes:

[0120] Starting from the position of the abnormal data to be processed in the array to be processed, select an interval of a second predetermined length on both sides of the position of the abnormal data to be processed as the first trend change interval.

[0121] In this embodiment, the second set length can be understood as a value used to determine the size of the first trend change range, and there is no necessary relationship between the first set length and the second set length.

[0122] If abnormal data is found in the array to be processed, determine the location of the abnormal data, and take that location as the starting point. Select a second set length on both sides of the array to be processed, and take the resulting interval as the first trend change interval.

[0123] For example, Figure 5 This is a schematic diagram of abnormal pending data provided in an embodiment of this disclosure. Assuming the second preset length is 1 data point, when abnormal pending data occurs, the position of the abnormal pending data is determined as Xi. Starting from Xi, 1 is selected on both sides of the pending data array. That is, the interval with a length of 1 to the left of the abnormal point is defined as the ascending interval, and the interval with a length of 1 to the right is defined as the descending interval, such as... Figure 5 The interval corresponding to the part inside the middle frame, i.e., the first trend change interval, is set to [X]. i-1 ,X i ),[X i ,X i+1 When identifying abnormal pending data, consecutive abnormal pending data are not identified. For example, in the array [1,1,1,1,1,1,1,30,1,1,1,1], the data 30 in [30,1,1,1,1,1,1,30,1,1,1,1] is identified as abnormal pending data, while the data 30 in the array [1,1,1,1,1,1,1,30,30,1,1,1] and [30,301,1,1,1,1,1,1,1,1,1,1] is not identified as abnormal pending data.

[0124] In one embodiment, the indices of the two boundary points of the trend change interval are a second index, and before performing causal analysis based on the trend of the data to be processed within the trend change interval, the method further includes:

[0125] In the array to be processed, for each of the two second indices, starting from the second index, along the outside of the trend change interval, the first data to be processed is selected, and the relationship between the value of the selected data to be processed and the value of the data to be processed corresponding to the second index position is determined.

[0126] If the size relationship satisfies the upward and downward characteristic information constraint of the trend change interval, the index of the selected data to be processed is determined as the updated second index, and the process continues to determine the size relationship of the second index until the size relationship no longer satisfies the upward and downward characteristic information constraint. The upward and downward characteristic information indicates that the data in the trend change interval is trending upward or downward.

[0127] The interval formed by the updated second index is determined as the updated trend change interval.

[0128] In this embodiment, the second index can be understood as an identifier used to indicate the positions of the two boundary points of the trend change interval, and the second index indicates the position of the trend change interval. The outer part of the trend change interval can be understood as the portion outside the trend change interval, including the left and right portions of the trend change interval. When the boundary point is a left boundary point, the outer part of the trend change interval can be to the left of the left boundary point. When the boundary point is a right boundary point, the outer part of the trend change interval can be to the right of the right boundary point.

[0129] Rising / falling characteristic information constraints can be used to define restrictions and specifications for data with rising or falling characteristics. Separate constraints can be set for data with rising and falling characteristics to determine the update trend change range based on the different characteristics of the data. For data with rising characteristics, the condition for the rising / falling characteristic information constraint is that the value of the data to the right of the coordinate axis is greater than the value of the data to the left. For data with falling characteristics, the condition for the rising / falling characteristic information constraint is that the value of the data to the right of the coordinate axis is less than the value of the data to the left.

[0130] In the array to be processed, a trend change interval has two second indices. For one of the left second indices, starting from the second index, select the first data point to be processed along the left side of the trend change interval. Compare the value of the data point to be processed with the value of the data point to be processed at the corresponding position of the left second index. If the relationship of the rise and fall characteristic information constraint is satisfied, the index of the selected data point to be processed is determined as the updated second index, and the comparison of the numerical magnitudes continues until the magnitude relationship no longer satisfies the rise and fall characteristic information constraint. Similarly, for the other right second index, starting from the second index, select the first data point to be processed along the right side of the trend change interval, and use the same method to determine the updated second index. The new interval formed by the updated second indices is taken as the updated trend change interval.

[0131] For example, Figure 6 This is a schematic diagram of data to be processed in an ascending range, provided in an embodiment of this disclosure. For example... Figure 6 The area indicated by the white arrow represents the trend change range. For the second index on the left, the first data to be processed is selected, and its value is compared with the value of the data to be processed at the corresponding position of the second index on the left. If the relationship of the upward characteristic constraint is satisfied, that is, the value of the first data to be processed is less than the value of the data to be processed at the corresponding position of the second index, then the index of the selected data to be processed is determined as the updated second index. For the second index on the right, the first data to be processed is selected, and its value is compared with the value of the data to be processed at the corresponding position of the second index on the right. If the relationship of the upward characteristic constraint is satisfied, that is, the value of the first data to be processed is greater than the value of the data to be processed at the corresponding position of the second index, then the index of the selected data to be processed is determined as the updated second index. Figure 6 The area indicated by the black arrow in the middle represents the updated trend change range, which is... Figure 6 The area enclosed by the dashed box in the text.

[0132] Figure 7 This is a schematic diagram of the data to be processed in a decreasing interval, provided in an embodiment of this disclosure. For example... Figure 7The area indicated by the white arrow represents the trend change range. For the second index on the left, the first data to be processed is selected, and its value is compared with the value of the data to be processed at the corresponding position of the second index on the left. If the relationship of the descent characteristic constraint is satisfied, that is, the value of the first data to be processed is greater than the value of the data to be processed at the corresponding position of the second index, then the index of the selected data to be processed is determined as the updated second index. For the second index on the right, the first data to be processed is selected, and its value is compared with the value of the data to be processed at the corresponding position of the second index on the right. If the relationship of the descent characteristic constraint is satisfied, that is, the value of the first data to be processed is less than the value of the data to be processed at the corresponding position of the second index, then the index of the selected data to be processed is determined as the updated second index. Figure 7 The area indicated by the black arrow in the middle represents the updated trend change range, which is... Figure 7 The area enclosed by the dashed box in the text.

[0133] In one embodiment, the number of trend change intervals is multiple, and before performing causal analysis based on the trend change trend of the data to be processed within the trend change intervals, the method further includes:

[0134] Determine whether adjacent trend change intervals within the trend change interval meet the merging conditions;

[0135] If the conditions are met, the adjacent trend change intervals are merged;

[0136] The merging conditions include:

[0137] Adjacent trend change intervals have the same trend direction; and,

[0138] The distance between adjacent trend change intervals is less than the size of any one of the adjacent trend change intervals; and,

[0139] The amount of data after merging adjacent trend change intervals is less than or equal to the data amount threshold, and the trend direction formed by the mean of adjacent trend change intervals is consistent with the trend direction of the adjacent trend change intervals.

[0140] Alternatively, the merging conditions include:

[0141] Adjacent trend change intervals have the same trend direction; and,

[0142] The distance between adjacent trend change intervals is less than the size of any one of the adjacent trend change intervals; and,

[0143] The amount of data after merging adjacent trend change intervals is greater than the data volume threshold, and the merged intervals are monotonic.

[0144] In this embodiment, the merging condition is a rule or a combination of rules used to determine whether to merge two adjacent trend change intervals. Adjacent trend change intervals can be understood as two intervals that are immediately adjacent to each other on a number line or in an ordered range division, with no other intervals of the same type between them. For example, consider the interval set {[1,3],[4,6],[7,9]}, where [1,3] and [4,6] are adjacent intervals, and [4,6] and [7,9] are also adjacent intervals. Although the overall intervals are discretely distributed, they are adjacent to each other on the number line.

[0145] The data volume threshold can be understood as a set threshold used to determine whether adjacent trend change intervals can be merged.

[0146] This embodiment obtains multiple trend change intervals, and then determines whether adjacent trend change intervals meet the merging conditions according to the merging conditions. If they do, the adjacent trend change intervals are merged until there are no adjacent trend change intervals that meet the merging conditions.

[0147] Among them, to meet the merging conditions, adjacent trend change intervals must satisfy either condition 1 or condition 2:

[0148] Case 1: The amount of data after merging adjacent trend change intervals is greater than the data volume threshold and the merged interval is monotonic. That is, merge two trend change intervals, determine whether the amount of data after merging is greater than the data volume threshold, and whether the merged interval of adjacent trend change intervals is monotonic.

[0149] Adjacent trend change intervals have the same trend direction, that is, both are either upward or both are downward.

[0150] The distance between adjacent trend change intervals is less than the size of any one of the adjacent trend change intervals; that is, the distance between two trend change intervals must be less than the length of any one of the two trend change intervals.

[0151] Case 2. The amount of data after merging adjacent trend change intervals is less than or equal to the data amount threshold, and the trend direction formed by the mean of adjacent trend change intervals is consistent with the trend direction of adjacent trend change intervals. That is, for each trend change interval in adjacent trend change intervals, the mean of the data in the interval is determined, and the trend direction of the two means must be consistent with the trend direction of the trend change interval.

[0152] Adjacent trend change intervals have the same trend direction, that is, both are either upward or both are downward.

[0153] The distance between adjacent trend change intervals is less than the size of any one of the adjacent trend change intervals; that is, the distance between two trend change intervals must be less than the length of any one of the two trend change intervals.

[0154] For example, the data volume threshold can be set to 5. If adjacent trend change intervals meet either condition 1 or condition 2, then the adjacent trend change intervals are merged. Condition 1: The trend directions of adjacent trend change intervals are consistent, and the distance between adjacent trend change intervals is less than the size of any interval (left or right). When the sum of the data volume of the merged adjacent trend change intervals is > 5, a trend determination algorithm is used for verification. When the merged trend change interval has significant monotonicity, the adjacent trend change intervals can be merged into one trend change interval. Condition 2: The trend directions of adjacent trend change intervals are consistent, and the distance between adjacent trend change intervals is less than the size of any interval (left or right). When the sum of the data volume of the merged adjacent trend change intervals is ≤ 5, if the trend of the average value of the adjacent trend change intervals is consistent with the trend direction of the interval, the adjacent trend change intervals can be merged into one trend change interval. For example, two adjacent trend change intervals [X] i-5 ,X i-2 ),[X i ,X i+5 If the conditions for merging are met, then merging can proceed.

[0155] The merger conditions in this disclosure include:

[0156] Adjacent trend change intervals have the same trend direction; and,

[0157] The distance between adjacent trend change intervals is less than the size of any one of the adjacent trend change intervals;

[0158] Furthermore, when the amount of data after merging adjacent trend change intervals is less than or equal to a data volume threshold, the merging condition also includes that the trend direction formed by the mean of the adjacent trend change intervals is consistent with the trend direction of the adjacent trend change intervals; when the amount of data after merging adjacent trend change intervals is greater than a data volume threshold, the merging condition also includes that the merged intervals are monotonic. The following is an exemplary description of this disclosure. The data processing method provided by this disclosure can be considered as a method for identifying data change trend intervals in an array to be processed. By processing the input time series array to be processed, it is identified whether there is a significant trend in the data, and if so, the intervals of significant trend changes are given. Significant change intervals include two types: increasing intervals and decreasing intervals.

[0159] The process for identifying trend change intervals can be as follows: determine the sliding window size, generate a significance array, identify individual outliers, generate trend change intervals, and optimize the trend change intervals.

[0160] The sliding window size can be a preset size or determined based on the number of data to be processed in the array to be processed.

[0161] When generating the significant difference array, two subarrays of the sliding window size are selected within the array to be processed for T-test to determine the significance level of the difference between the two subarrays and record this significance level at the split position of the two subarrays; the sliding window is moved from left to right until the significance of the entire array to be processed is calculated.

[0162] When comparing arrays to determine differences, you can first compensate the array by adding data of the size of a sliding window to both the left and right sides of the array to ensure that the significance of the differences can be calculated at the beginning and end positions of the array. The compensation data before the first element is based on the value of the first element of the array, and the compensation data after the first element is based on the value of the last element of the array.

[0163] When generating trend change intervals, the positions of significant differences in the significance array, i.e., the difference positions and the left and right positions of the data to be processed in the data to be processed that have anomalies, are determined as trend change intervals.

[0164] When the absolute value of a difference measure in the significance array exceeds the second significance threshold, it can be determined that there may be a significant trend change in the data to be processed at that position. This position can be the index of the difference measure data with an absolute value greater than the second significance threshold.

[0165] Select all difference measures whose absolute values ​​are greater than the second significance threshold. The position of this difference measure in the difference array can be called the difference position.

[0166] Form continuous intervals from all consecutive difference locations. The length of each continuous interval is H, the sliding window size is L, and the maximum absolute value of the data within each continuous significant interval is V, where p0 < 0.<p1&&L> 1; When the data meets the following conditions, the following interval selection logic will be executed respectively:

[0167] 1. If H>L&&V>p0, then the continuous interval is determined as the trend change interval. That is, if the length of the continuous interval is greater than the second value, the maximum value of the absolute value of the data in the continuous interval is determined; if the maximum value is greater than the second significance threshold, the continuous interval is determined as the second trend change interval.

[0168] 2. If H>1 (the confidence level can be considered low) && V>p1 (a higher threshold is required), then the continuous interval is determined as the trend change interval. That is, if the length of the continuous interval is greater than the first value and less than the second value, the maximum value of the absolute value of the data in the continuous interval is determined; if the maximum value is greater than the third significance threshold, the continuous interval is determined as the second trend change interval, and the first significance threshold is less than the third significance threshold.

[0169] 3. With H set to 1, perform an extreme value search.

[0170] In a significance index, locations with significant differences theoretically indicate a trend change in their vicinity. For cases where continuous significance is insufficient, such as when H is 1, extreme values ​​within the interval are processed to prevent significant data fluctuations from escaping the range. Candidate intervals are extracted from the left and right sides of each extreme point.

[0171] Extreme value search method: Find extreme points from the data at most one sliding window length to the left and right of the significant point, i.e., the difference position. That is, when the length of the continuous interval is equal to the first value, in the difference array, take the difference position included in the continuous interval as the starting point and select extreme points on both sides of the difference position; based on the position of the selected extreme points in the difference array, determine the second trend change interval.

[0172] This disclosure describes an outlier detection method for an array to be processed. It uses the standard deviation method to identify individual outliers in the array, omitting the detection of multiple consecutive outliers. Initially, the interval of length 1 to the left of each outlier is defined as an ascending interval, and the interval of length 1 to the right of each outlier is defined as a descending interval. The intervals to the left and right of the abrupt change point are the determined trend abrupt change intervals.

[0173] This publication uses the rise and fall characteristics of the reference range, combined with data near the trend change range, to correct, merge, and filter the trend change range.

[0174] If the trend change interval is an upward interval, and there is a lower point to the left or a higher point to the right, the interval range is updated. If the trend change interval is a downward interval, and there is a higher point to the left or a lower point to the right, the interval range is updated. That is, starting from the second index, along the outer edge of the trend change interval, the first data to be processed is selected. The value of the selected data to be processed is determined to be in relation to the value of the data to be processed corresponding to the second index position. If the magnitude relationship satisfies the upward / downward characteristic information constraint of the trend change interval, the index of the selected data to be processed is determined as the updated second index, and the process returns to continue determining the magnitude relationship of the second index until the magnitude relationship no longer satisfies the upward / downward characteristic information constraint.

[0175] In this disclosure, adjacent trend change intervals are merged. If two adjacent intervals meet the merging conditions, the intervals are merged.

[0176] This disclosure performs interval filtering. If the increase / decrease of the merged trend change interval is less than one standard deviation of the overall data in the array to be processed, then this interval is removed.

[0177] Figure 8 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this disclosure, as shown below. Figure 8 As shown, the device includes: an acquisition module 310, a first determination module 320, a second determination module 330, and a processing module 340.

[0178] The acquisition module 310 is used to acquire a processing array, which includes multiple processing data arranged in chronological order, and the processing data is data associated with the application to be processed.

[0179] The first determining module 320 is used to determine the difference array corresponding to the array to be processed, the difference array including multiple difference measurement data, the difference measurement data indicating the degree of difference between the data to be processed in the array to be processed;

[0180] The second determining module 330 is used to process the data in the array to be processed and the difference array, and determine the trend change range of the array to be processed, wherein the change trend of the data to be processed within the trend change range is greater than a first significant threshold.

[0181] The processing module 340 is used to perform cause analysis based on the changing trend of the data to be processed within the trend change range.

[0182] The technical solution of this disclosure involves an acquisition module first acquiring a processing array composed of multiple data items arranged in chronological order. Then, a first determination module determines a difference array corresponding to the processing array. This difference array includes multiple difference measurement data, indicating the degree of difference between the data items in the processing array. Next, a second determination module processes the data in both the processing array and the difference array to determine the trend change range of the processing array. Finally, a processing module performs causal analysis based on the trend of the processing data within this trend change range. Through the cooperation of these modules, the trend change range of the array is determined, reducing the amount of data to be processed for causal analysis and improving data processing efficiency.

[0183] In one embodiment, the trend change range includes a first trend change range and a second trend change range, and the second determining module 330 includes:

[0184] The first determining unit is used to determine the first trend change range based on the position of the abnormal data to be processed in the array to be processed;

[0185] The second determining unit is used to determine a second trend change range based on the difference measurement data in the difference array and a second significance threshold, wherein the second significance threshold is a threshold for measuring whether the data difference is significant.

[0186] In one embodiment, the second determining unit includes:

[0187] The third determining unit is used to determine, for each difference measure data in the difference array, whether the absolute value of the difference measure data is greater than the absolute value of the second significant threshold.

[0188] The fourth determining unit is used to determine the first index of the difference measurement data as the difference position when the absolute value of the difference measurement data is greater than the absolute value of the second significant threshold. The difference position indicates that the change trend of the corresponding data to be processed is greater than the first significant threshold. The data to be processed corresponding to the difference position is the data to be processed at the first index position in the array to be processed.

[0189] The fifth determining unit is used to determine the continuous interval formed by the difference positions determined from the difference array;

[0190] The sixth determining unit is used to determine a second trend change interval based on the length of the continuous interval and the target data associated with the length, wherein the target data includes the values ​​of the data within the continuous interval or the difference array.

[0191] In one embodiment, the sixth determining unit includes:

[0192] The selection unit is used to select extreme points on both sides of the difference position in the difference array, starting from the difference position included in the continuous interval, when the length of the continuous interval is equal to the first value.

[0193] The seventh determining unit is used to determine the second trend change range based on the position of the selected extreme point within the difference array.

[0194] In one embodiment, the seventh determining unit is specifically used for:

[0195] The extreme point is centered on the position of the extreme point in the difference array, and the first interval with a set length of interval length is determined as the second trend change interval.

[0196] In one embodiment, the sixth determining unit is specifically used for:

[0197] If the length of the continuous interval is greater than a first value and less than a second value, determine the maximum value of the absolute value of the data within the continuous interval.

[0198] If the maximum value is greater than the third significant threshold, the continuous interval is determined as the second trend change interval, and the first significant threshold is less than the third significant threshold.

[0199] In one embodiment, the sixth determining unit is specifically used for:

[0200] If the length of the continuous interval is greater than the second value, determine the maximum value of the absolute value of the data within the continuous interval;

[0201] If the maximum value is greater than the second significant threshold, the continuous interval is determined as the second trend change interval.

[0202] In one embodiment, the first determining unit is specifically used for:

[0203] Starting from the position of the abnormal data to be processed in the array to be processed, select an interval of a second predetermined length on both sides of the position of the abnormal data to be processed as the first trend change interval.

[0204] In one embodiment, the indices of the two boundary points of the trend change interval are a second index. The data processing device further includes an update module, specifically used for:

[0205] In the array to be processed, for each of the two second indices, starting from the second index, along the outside of the trend change interval, the first data to be processed is selected, and the relationship between the value of the selected data to be processed and the value of the data to be processed corresponding to the second index position is determined.

[0206] If the size relationship satisfies the upward and downward characteristic information constraint of the trend change interval, the index of the selected data to be processed is determined as the updated second index, and the process continues to determine the size relationship of the second index until the size relationship no longer satisfies the upward and downward characteristic information constraint. The upward and downward characteristic information indicates that the data in the trend change interval is trending upward or downward.

[0207] The interval formed by the updated second index is determined as the updated trend change interval.

[0208] In one embodiment, the number of trend change intervals is multiple, and the data processing device further includes a merging module, specifically used for:

[0209] Determine whether adjacent trend change intervals within the trend change interval meet the merging conditions;

[0210] If the conditions are met, the adjacent trend change intervals are merged;

[0211] The merging conditions include:

[0212] Adjacent trend change intervals have the same trend direction; and,

[0213] The distance between adjacent trend change intervals is less than the size of any one of the adjacent trend change intervals; and,

[0214] The trend direction formed by the average of adjacent trend change intervals is consistent with the trend direction of the adjacent trend change intervals; and,

[0215] The amount of data after merging adjacent trend change intervals is greater than the data volume threshold, and the merged intervals are monotonic.

[0216] The data processing apparatus provided in this disclosure can execute the data processing method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects for executing the method.

[0217] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0218] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Refer to the following... Figure 9 It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 9 A structural diagram of the terminal device or server in the 500.

[0219] Electronic equipment 500, including:

[0220] One or more processing devices 501;

[0221] Storage device 508, for storing one or more programs,

[0222] When the one or more programs are executed by the one or more processing devices 501, the one or more processing devices 501 implement any of the methods provided in this disclosure.

[0223] The terminal devices in this disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0224] like Figure 9 As shown, electronic device 500 may include a processing unit (e.g., central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. An edit / output (I / O) interface 505 is also connected to bus 504.

[0225] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0226] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0227] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0228] The electronic device provided in this embodiment and the data processing method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0229] This disclosure provides a computer storage medium storing a computer program that, when executed by a processor, implements the data processing method provided in the above embodiments.

[0230] It should be noted that the computer-readable medium described above in this disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination thereof.

[0231] The computer storage medium may be a storage medium for computer-executable instructions, which, when executed by a computer processor, are used to perform the methods provided in this disclosure.

[0232] Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0233] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0234] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0235] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: acquire at least two Internet Protocol (IP) addresses; send a node evaluation request including the at least two IP addresses to a node evaluation device, wherein the node evaluation device selects an IP address from the at least two IP addresses and returns it; and receive the IP address returned by the node evaluation device; wherein the acquired IP address indicates an edge node in a content delivery network.

[0236] Alternatively, the aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: receive a node evaluation request including at least two Internet Protocol (IP) addresses; select an IP address from the at least two IP addresses; and return the selected IP address; wherein the received IP address indicates an edge node in the content delivery network.

[0237] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0238] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0239] The modules or units described in the embodiments of this disclosure can be implemented in software or hardware. The names of modules or units do not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0240] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0241] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0242] A computer program product includes a computer program that, when executed by a processor, implements the data processing method provided in this disclosure.

[0243] According to one or more embodiments of this disclosure, [Example 1] provides a data processing method, including: obtaining a to-be-processed array, the to-be-processed array including a plurality of to-be-processed data arranged in chronological order, the to-be-processed data being data associated with an application to be processed; determining a difference array corresponding to the to-be-processed array, the difference array including a plurality of difference measurement data, the difference measurement data indicating the degree of difference between the to-be-processed data in the to-be-processed array;

[0244] The data in the array to be processed and the difference array are processed to determine the trend change range of the array to be processed. The change trend of the data to be processed within the trend change range is greater than a first significant threshold. The cause analysis is performed based on the change trend of the data to be processed within the trend change range.

[0245] According to one or more embodiments of this disclosure, [Example 2] provides the method of Example 1, wherein the trend change interval includes a first trend change interval and a second trend change interval, and the step of processing the data in the array to be processed and the difference array to determine the trend change interval of the array to be processed includes:

[0246] The first trend change range is determined based on the location of the abnormal data to be processed in the array to be processed;

[0247] Based on the difference measurement data in the difference array and the second significance threshold, a second trend change interval is determined, whereby the second significance threshold is a threshold for measuring whether the data difference is significant.

[0248] According to one or more embodiments of this disclosure, [Example 3] provides the method of Example 2, wherein determining the second trend change interval based on the difference measure data in the difference array and a second significance threshold includes:

[0249] For each difference measure data in the difference array, determine whether the absolute value of the difference measure data is greater than the absolute value of the second significance threshold;

[0250] If the absolute value of the difference measurement data is greater than the absolute value of the second significance threshold, the first index of the difference measurement data is determined as the difference position. The difference position indicates that the change trend of the corresponding data to be processed is greater than the first significance threshold. The data to be processed corresponding to the difference position is the data to be processed at the first index position in the array to be processed.

[0251] Determine the continuous interval formed by the difference positions determined from the difference array;

[0252] Based on the length of the continuous interval and the target data associated with the length, a second trend change interval is determined, wherein the target data includes the values ​​of the data within the continuous interval or the difference array.

[0253] According to one or more embodiments of this disclosure, [Example 4] provides the method of Example 3, wherein determining a second trend change interval based on the length of the continuous interval and target data associated with the length includes:

[0254] When the length of the continuous interval is equal to the first value, in the difference array, starting from the difference position included in the continuous interval, extreme points are selected on both sides of the difference position;

[0255] The second trend change interval is determined based on the position of the selected extreme point within the difference array.

[0256] According to one or more embodiments of this disclosure, [Example 5] provides the method of Example 4, wherein determining the trend change range of the array to be processed based on the position of the selected extreme point within the array to be processed includes:

[0257] The extreme point is centered on the position of the extreme point in the difference array, and the first interval with a set length of interval length is determined as the second trend change interval.

[0258] According to one or more embodiments of this disclosure, [Example 6] provides the method of Example 3, wherein determining a second trend change interval based on the length of the continuous interval and target data associated with the length includes:

[0259] If the length of the continuous interval is greater than a first value and less than a second value, determine the maximum value of the absolute value of the data within the continuous interval.

[0260] If the maximum value is greater than the third significant threshold, the continuous interval is determined as the second trend change interval, and the first significant threshold is less than the third significant threshold.

[0261] According to one or more embodiments of this disclosure, [Example 7] provides the method of Example 3, wherein determining a second trend change interval based on the length of the continuous interval and target data associated with the length includes:

[0262] If the length of the continuous interval is greater than the second value, determine the maximum value of the absolute value of the data within the continuous interval;

[0263] If the maximum value is greater than the second significant threshold, the continuous interval is determined as the second trend change interval.

[0264] According to one or more embodiments of this disclosure, [Example 8] provides the method of Example 2, wherein determining the first trend change range based on the position of abnormal data to be processed in the array to be processed includes:

[0265] Starting from the position of the abnormal data to be processed in the array to be processed, select an interval of a second predetermined length on both sides of the position of the abnormal data to be processed as the first trend change interval.

[0266] According to one or more embodiments of this disclosure, [Example 9] provides the method of Example 1, wherein the indices of the two boundary points of the trend change interval are second indices, and before performing causal analysis based on the trend of the data to be processed within the trend change interval, the method further includes:

[0267] In the array to be processed, for each of the two second indices, starting from the second index, along the outside of the trend change interval, the first data to be processed is selected, and the relationship between the value of the selected data to be processed and the value of the data to be processed corresponding to the second index position is determined.

[0268] If the size relationship satisfies the upward and downward characteristic information constraint of the trend change interval, the index of the selected data to be processed is determined as the updated second index, and the process continues to determine the size relationship of the second index until the size relationship no longer satisfies the upward and downward characteristic information constraint. The upward and downward characteristic information indicates that the data in the trend change interval is trending upward or downward.

[0269] The interval formed by the updated second index is determined as the updated trend change interval.

[0270] According to one or more embodiments of this disclosure, [Example 10] provides the method of Example 1, wherein the number of trend change intervals is multiple, and before performing causal analysis based on the change trend of the data to be processed within the trend change intervals, the method further includes:

[0271] Determine whether adjacent trend change intervals within the trend change interval meet the merging conditions;

[0272] If the conditions are met, the adjacent trend change intervals are merged;

[0273] The merging conditions include:

[0274] Adjacent trend change intervals have the same trend direction; and,

[0275] The distance between adjacent trend change intervals is less than the size of any one of the adjacent trend change intervals; and,

[0276] The trend direction formed by the average of adjacent trend change intervals is consistent with the trend direction of the adjacent trend change intervals; and,

[0277] The amount of data after merging adjacent trend change intervals is greater than the data volume threshold, and the merged intervals are monotonic.

[0278] According to one or more embodiments of this disclosure, [Example 11] provides a data processing apparatus, including:

[0279] The acquisition module is used to acquire a processing array, which includes multiple processing data arranged in chronological order, and the processing data is data associated with the application to be processed.

[0280] The first determining module is used to determine the difference array corresponding to the array to be processed, the difference array including multiple difference measurement data, the difference measurement data indicating the degree of difference between the data to be processed in the array to be processed;

[0281] The second determining module is used to process the data in the array to be processed and the difference array, and determine the trend change range of the array to be processed, wherein the change trend of the data to be processed within the trend change range is greater than a first significant threshold.

[0282] The processing module is used to perform cause analysis based on the changing trend of the data to be processed within the trend change range.

[0283] According to one or more embodiments of this disclosure, [Example 12] an electronic device is provided, the electronic device comprising:

[0284] One or more processing devices;

[0285] Storage device for storing one or more programs.

[0286] When the one or more programs are executed by the one or more processing devices, the one or more processing devices implement the data processing method as described in any of Examples 1-10.

[0287] According to one or more embodiments of this disclosure, [Example 13] provides a storage medium containing computer-executable instructions that, when executed by a computer processor, are used to perform a data processing method as described in any of Examples 1-10.

[0288] According to one or more embodiments of this disclosure, [Example 14] provides a computer program product including a computer program that, when executed by a processor, implements the data processing method according to any one of Examples 1-10.

[0289] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0290] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0291] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A data processing method, characterized in that, include: Obtain a processing array, which includes multiple processing data arranged in chronological order, wherein the processing data is data associated with the application to be processed; Determine the difference array corresponding to the array to be processed, the difference array including multiple difference measurement data, the difference measurement data indicating the degree of difference between the data to be processed in the array to be processed; Based on the data in the array to be processed and the difference array, the trend change range of the array to be processed is determined, and the change trend of the data to be processed within the trend change range is greater than a first significant threshold. Analyze the reasons for the changes in the data to be processed within the aforementioned trend change range.

2. The method according to claim 1, characterized in that, The trend change range includes a first trend change range and a second trend change range. The process of processing the data within the array to be processed and the difference array to determine the trend change range of the array to be processed includes: The first trend change range is determined based on the location of the abnormal data to be processed in the array to be processed; Based on the difference measurement data in the difference array and the second significance threshold, a second trend change range is determined, whereby the second significance threshold is a threshold for measuring whether the data difference is significant.

3. The method according to claim 2, characterized in that, The step of determining the second trend change interval based on the difference measurement data and the second significance threshold in the difference array includes: For each difference measure data in the difference array, determine whether the absolute value of the difference measure data is greater than the absolute value of the second significance threshold; If the absolute value of the difference measurement data is greater than the absolute value of the second significance threshold, the first index of the difference measurement data is determined as the difference position. The difference position indicates that the change trend of the corresponding data to be processed is greater than the first significance threshold. The data to be processed corresponding to the difference position is the data to be processed at the first index position in the array to be processed. Determine the continuous interval formed by the difference positions determined from the difference array; Based on the length of the continuous interval and the target data associated with the length, a second trend change interval is determined, wherein the target data includes the values ​​of the data within the continuous interval or the difference array.

4. The method according to claim 3, characterized in that, The determination of the second trend change interval based on the length of the continuous interval and the target data associated with the length includes: When the length of the continuous interval is equal to the first value, in the difference array, starting from the difference position included in the continuous interval, extreme points are selected on both sides of the difference position; The second trend change interval is determined based on the position of the selected extreme point within the difference array.

5. The method according to claim 4, characterized in that, The step of determining the trend change range of the array to be processed based on the position of the selected extreme point within the array to be processed includes: The extreme point is centered on the position of the extreme point within the difference array, and a first interval with a set length equal to the interval length is determined as the second trend change interval.

6. The method according to claim 3, characterized in that, The determination of the second trend change interval based on the length of the continuous interval and the target data associated with the length includes: If the length of the continuous interval is greater than a first value and less than a second value, determine the maximum value of the absolute value of the data within the continuous interval. If the maximum value is greater than the third significant threshold, the continuous interval is determined as the second trend change interval, and the first significant threshold is less than the third significant threshold.

7. The method according to claim 3, characterized in that, The determination of the second trend change interval based on the length of the continuous interval and the target data associated with the length includes: If the length of the continuous interval is greater than the second value, determine the maximum value of the absolute value of the data within the continuous interval; If the maximum value is greater than the second significant threshold, the continuous interval is determined as the second trend change interval.

8. The method according to claim 2, characterized in that, The step of determining the first trend change range based on the position of the abnormal data to be processed in the array to be processed includes: Starting from the position of the abnormal data to be processed in the array to be processed, select an interval of a second predetermined length on both sides of the position of the abnormal data to be processed as the first trend change interval.

9. The method according to claim 1, characterized in that, The indices of the two boundary points of the trend change interval are the second index. Before performing causal analysis based on the trend of the data to be processed within the trend change interval, the following steps are also included: In the array to be processed, for each of the two second indices, starting from the second index, along the outside of the trend change interval, the first data to be processed is selected, and the relationship between the value of the selected data to be processed and the value of the data to be processed corresponding to the second index position is determined. If the size relationship satisfies the upward and downward characteristic information constraint of the trend change interval, the index of the selected data to be processed is determined as the updated second index, and the process continues to determine the size relationship of the second index until the size relationship no longer satisfies the upward and downward characteristic information constraint. The upward and downward characteristic information indicates that the data in the trend change interval is trending upward or downward. The interval formed by the updated second index is determined as the updated trend change interval.

10. The method according to claim 1, characterized in that, The number of trend change intervals is multiple. Before performing causal analysis based on the trend of the data to be processed within the trend change intervals, the following steps are also included: Determine whether adjacent trend change intervals within the trend change interval meet the merging conditions; If the conditions are met, the adjacent trend change intervals are merged; The merging conditions include: Adjacent trend change intervals have the same trend direction; and, The distance between adjacent trend change intervals is less than the size of any one of the adjacent trend change intervals; and, The amount of data after merging adjacent trend change intervals is less than or equal to the data amount threshold, and the trend direction formed by the mean of adjacent trend change intervals is consistent with the trend direction of the adjacent trend change intervals. Alternatively, the merging conditions include: Adjacent trend change intervals have the same trend direction; and, The distance between adjacent trend change intervals is less than the size of any one of the adjacent trend change intervals; and, The amount of data after merging adjacent trend change intervals is greater than the data volume threshold, and the merged intervals are monotonic.

11. A data processing apparatus, characterized in that, include: The acquisition module is used to acquire a processing array, which includes multiple processing data arranged in chronological order, and the processing data is data associated with the application to be processed. The first determining module is used to determine the difference array corresponding to the array to be processed, the difference array including multiple difference measurement data, the difference measurement data indicating the degree of difference between the data to be processed in the array to be processed; The second determining module is used to process the data in the array to be processed and the difference array, and determine the trend change range of the array to be processed, wherein the change trend of the data to be processed within the trend change range is greater than a first significant threshold. The processing module is used to perform cause analysis based on the changing trend of the data to be processed within the trend change range.

12. An electronic device, characterized in that, The electronic device includes: One or more processing devices; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processing devices, the one or more processing devices implement the data processing method as described in any one of claims 1-10.

13. A storage medium comprising computer-executable instructions, which, when executed by a computer processor, are used to perform the data processing method as described in any one of claims 1-10.

14. A computer program product comprising a computer program that, when executed by a processor, implements the data processing method according to any one of claims 1-10.

Images