Service migration information determination method and device, electronic equipment, storage medium and product
Through automated correlation analysis and processing methods, the problem of low efficiency and accuracy of service migration information determination in the prior art is solved, and efficient and accurate service migration information detection is achieved.
Patent Information
- Application Number
- CN202411091010.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-08-09
AI Technical Summary
The determination process of service migration information in the prior art relies on manual intervention, resulting in inefficient efficiency and low accuracy, which extends the determination time.
By receiving service migration information determination instructions, searching for initial feature data and reference feature data based on the database, performing correlation analysis, determining the service migration information determination scheme, and using the scheme to process data to automatically detect service migration information.
It reduces the participation of managers, improves the detection efficiency and accuracy of service migration information, reduces the dependence on manuals, and improves the recognition accuracy.
Smart Images

Figure CN119011661A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, electronic device, storage medium and product for determining service migration information. Background Art
[0002] Service migration in a homogeneously deployed cluster in a distributed system refers to migrating some of the services or instances within the cluster. The migration of different content will cause the cluster to undergo different changes. Detailed service migration information is an important data support for intelligent operation and maintenance. Therefore, the recognition efficiency and accuracy of service migration information are one of the key issues in the data processing field.
[0003] Currently, the process of determining service migration information is semi-automated. For example, the deviation between new data in a distributed system and reference data is periodically determined and evaluated. When the deviation exceeds a reference threshold, management personnel are notified to further investigate whether a service migration has occurred in the distributed system. If a service migration has occurred, management personnel are required to further verify the service migration information, such as the migration type and relocation location. However, manual intervention to verify service migration actions and confirm service migration information not only prolongs the time required to determine service migration information, reduces the efficiency of identifying service migration information, but also leads to low recognition accuracy. Summary of the Invention
[0004] The present invention provides a method, device, electronic device, storage medium and product for determining service migration information, aiming to automatically detect service migration information of a distributed system and improve the detection efficiency and accuracy of service migration information.
[0005] According to one aspect of the present invention, a method for determining service migration information is provided, the method comprising:
[0006] Upon receiving a service migration information determination instruction of a distributed system, searching in a database based on the service migration information determination instruction to obtain initial feature data and reference feature data of the distributed system, wherein the initial feature data is business information of the distributed system in a current data acquisition cycle, and the reference feature data is business information of the distributed system in a preset data acquisition cycle, where the preset data acquisition cycle is earlier than the current data acquisition cycle;
[0007] Perform correlation analysis on the initial feature data and the reference feature data, and determine a service migration information determination plan for the distributed system based on the analysis results;
[0008] The service migration information is used to determine the solution, and the initial feature data and the reference feature data are processed to obtain the target service migration information of the distributed system.
[0009] According to another aspect of the present invention, a device for determining service migration information is provided. The device for determining service migration information is used to implement the method for determining service migration information in any embodiment of the present invention. The device includes:
[0010] An information acquisition module is configured to, upon receiving a service migration information determination instruction of a distributed system, search in a database based on the service migration information determination instruction to obtain initial feature data and reference feature data of the distributed system, wherein the initial feature data is business information of the distributed system within a current data acquisition period, and the reference feature data is business information of the distributed system within a preset data acquisition period, where the preset data acquisition period is earlier than the current data acquisition period;
[0011] A solution determination module is used to perform correlation analysis on the initial feature data and the reference feature data, and determine a service migration information determination solution for the distributed system based on the analysis results;
[0012] The information determination module is used to process the initial feature data and the reference feature data using the service migration information determination scheme to obtain the target service migration information of the distributed system.
[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0014] at least one processor; and a memory communicatively coupled to the at least one processor;
[0015] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the method for determining service migration information in any embodiment of the present invention.
[0016] According to another aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the method for determining service migration information in any embodiment of the present invention when executed.
[0017] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the method for determining service migration information according to any embodiment of the present invention is implemented.
[0018] The method for determining service migration information of the present invention includes: upon receiving a service migration information determination instruction of a distributed system, searching in a database based on the service migration information determination instruction to obtain initial feature data and reference feature data of the distributed system, wherein the initial feature data is business information of the distributed system within a current data acquisition cycle, and the reference feature data is business information of the distributed system within a preset data acquisition cycle, the preset data acquisition cycle being earlier than the current data acquisition cycle; performing correlation analysis on the initial feature data and the reference feature data, and determining a service migration information determination scheme for the distributed system based on the analysis results; and processing the initial feature data and the reference feature data using the service migration information determination scheme to obtain target service migration information of the distributed system. The method of the present invention calls the initial feature data and the reference feature data in the database according to the query requirements contained in the service migration information determination instruction upon receiving the service migration information determination instruction, performs correlation analysis on the two types of data, and determines a service migration information determination scheme in a targeted manner based on the correlation analysis results, and processes the initial feature data and the reference feature data using the determined scheme, thereby reducing the involvement of management personnel, reducing the reliance on manual labor in the determination of service migration information, and effectively improving the detection efficiency and quality of service migration information. The invention solves the problems that verifying service migration actions and confirming service migration information by management personnel will prolong the time of determining service migration information, reduce the efficiency of identifying service migration information, and make the identification accuracy of service migration information low.
[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0021] Figure 1 It is a flowchart of a method for determining service migration information provided by the present invention;
[0022] Figure 2 is a flow chart of another method for determining service migration information provided by the present invention;
[0023] Figure 3 This is a flow chart of a method for determining target service migration information provided by the present invention;
[0024] Figure 4 It is a flowchart of another method for determining target service migration information provided by the present invention;
[0025] Figure 5 It is a structural diagram of a device for determining service migration information provided by the present invention;
[0026] Figure 6 It is a structural schematic diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION
[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.
[0028] It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device. The acquisition, transmission, storage, use, and processing of data in the technical solutions of the present invention comply with the relevant provisions of national laws and regulations. It should be noted that in the embodiments of the present invention, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary and are intended solely to illustrate the feasibility of implementing the technical solutions of the present invention. This does not mean that the applicant has or will necessarily use such solutions.
[0029] Homogeneous deployment is a deployment strategy that integrates all components of a distributed system and deploys them to every instance of the system. This ensures that the applications running on each instance of the system are identical, simplifying the system's deployment and runtime complexity. The service migration information detected by the present invention is essentially the service migration information of the homogeneously deployed cluster in the distributed system.
[0030] Figure 1This is a flow chart of a method for determining service migration information provided by the present invention. This embodiment can be applied to determine whether service migration occurs in a distributed system, the migration type and migration time of the service migration that occurs, etc. The method can be executed by the device for determining service migration information provided by the present invention. The device can be implemented in the form of hardware and / or software. In a specific embodiment, the device can be integrated into an electronic device. The following embodiments will be described using the device integrated into an electronic device as an example. Figure 1 , the method specifically comprises the following steps:
[0031] S101 : When receiving a service migration information determination instruction of a distributed system, searching in a database based on the service migration information determination instruction is performed to obtain initial feature data and reference feature data of the distributed system.
[0032] The service migration information determination instruction can be understood as a detection indication of the service migration information of the homogeneously deployed cluster of the distributed system, which is used to instruct the processor to start the determination of the service migration information. The service migration information determination instruction can be triggered on a timer basis or determined based on the user's query requirements. The database can be understood as a component that stores the operating data or business information of the distributed system. The initial feature data is the operating data or business information of the distributed system during the current data acquisition cycle. The reference feature data is the operating data or business information of the distributed system during the preset data acquisition cycle. The preset data acquisition cycle is earlier than the current data acquisition cycle.
[0033] According to the detection logic of service migration information, feature data can be acquired hourly, daily or weekly. Taking weekly feature data acquisition as an example, the current data acquisition period can be understood as the week of the current moment or the week generated by extending 168 hours before the current moment. The preset data acquisition period can be understood as a pre-set week. The preset data acquisition period is earlier than the current data acquisition period, for example, a week before the current week, a preset number of weeks before the current week, etc. This embodiment does not limit this.
[0034] In one embodiment, assuming that the characteristic data is business transaction volume data in a homogeneous cluster, the preset data acquisition cycle can be understood as a data acquisition cycle before the current data acquisition cycle. When the processor receives the service migration information determination instruction, it will retrieve the business transaction volume data of the distributed system in the current data acquisition cycle and the previous data acquisition cycle stored in the database, and use the retrieved business transaction volume data in the current data acquisition cycle as the initial characteristic data, and use the retrieved business transaction volume data in the previous data acquisition cycle as the reference characteristic data.
[0035] The advantage of this setting is that the initial feature data and reference feature data can be quickly retrieved, thereby speeding up the efficiency of determining service migration information.
[0036] S102: Perform a correlation analysis on the initial feature data and the reference feature data, and determine a service migration information determination scheme for the distributed system based on the analysis results.
[0037] Among them, correlation analysis can be understood as analyzing the correlation or similarity between the initial feature data and the reference feature data, the analysis results can be understood as the analysis conclusion of the correlation or similarity between the initial feature data and the reference feature data, and the service migration information determination plan can be understood as the method of determining the service migration information.
[0038] The analysis results include high correlation between the initial feature data and the reference feature data and low correlation between the initial feature data and the reference feature data. The analysis results are used to indicate a method for determining the service migration information. Different analysis results correspond to different service migration information determination schemes.
[0039] Specifically, the analysis results with high correlation are set to correspond to the first service migration information determination scheme, and the first service migration information determination scheme is used to instruct the server to solve the service migration information according to the first data processing rule. The analysis results with low correlation are set to correspond to the second service migration information determination scheme, and the second service migration information determination scheme is used to instruct the server to solve the service migration information according to the second data processing rule.
[0040] In one embodiment, a correlation analysis is performed on the initial feature data and the reference feature data. If the analysis result indicates that the correlation between the initial feature data and the reference feature data is high, the service migration information determination scheme of the distributed system is determined to be the first service migration information determination scheme; if the analysis result indicates that the correlation between the initial feature data and the reference feature data is not high, the service migration information determination scheme of the distributed system is determined to be the second service migration information determination scheme.
[0041] The advantage of this setting is that it can quickly locate the service migration information of the distributed system and determine the solution, so as to process the initial feature data and reference feature data in a targeted manner and obtain the target service migration information faster and with higher quality.
[0042] S103: Determine a solution using the service migration information, process the initial feature data and the reference feature data, and obtain target service migration information of the distributed system.
[0043] The target service migration information may be understood as detailed migration information of a service migration action occurring in a homogeneous deployment cluster of a distributed system, including but not limited to the service migration relocation time.
[0044] In one embodiment, assuming that the service migration information determination scheme is to fit the initial feature data and the reference feature data according to pre-set weights in the scheme, and determine the fitting result as the service migration relocation time, the processor will fit the initial feature data and the reference feature data according to the weights in the service migration information determination scheme determined in S102, and use the fitted time as the service migration relocation time of the distributed system, i.e., the target service migration information of the distributed system.
[0045] The advantage of this setting is that it can automatically determine the target service migration information, reduce the involvement of managers in the target service migration information work, save human resources and improve the efficiency and accuracy of determining the target service migration information.
[0046] The technical solution of this embodiment, upon receiving a service migration information determination instruction, calls the initial feature data and reference feature data in the database according to the query requirements contained in the service migration information determination instruction, performs a correlation analysis on the two types of data, and determines a determination scheme for the service migration information in a targeted manner based on the correlation analysis results. Using the determined scheme, the initial feature data and reference feature data are processed, thereby reducing the involvement of management personnel, reducing the reliance on manual labor in determining service migration information, and effectively improving the efficiency and quality of service migration information detection. This solves the problem that verifying service migration actions and confirming service migration information by management personnel prolongs the determination time of service migration information, reduces the recognition efficiency of service migration information, and results in low recognition accuracy of service migration information.
[0047] Figure 2 This is a flow chart of another method for determining service migration information provided by the present invention. This embodiment can be applied to determine whether service migration occurs in a distributed system, the migration type and migration time of the service migration that occurs, and is used to determine the service migration information of a machine migration. This method can be performed by the service migration information determination device provided by the present invention. The device can be implemented in the form of hardware and / or software. In a specific embodiment, the device can be integrated into an electronic device. The following embodiments will be described using the device integrated into an electronic device as an example. Figure 2 , the method specifically comprises the following steps:
[0048] S201: When receiving a service migration information determination instruction of a distributed system, the service migration information determination instruction is parsed to obtain a data query duration and a first data query time of the distributed system.
[0049] The data query duration can be understood as the time period for retrieving the feature data contained in the service migration information determination instruction, for example, three days, five days, or one week. The first data query time can be understood as the time when the instruction contained in the service migration information determination instruction was generated or sent, indicating the time when the distributed system's detection requirements were generated. This setting has the advantage of quickly locating the acquisition range of the initial feature data and reference feature data.
[0050] S202: Determine a first query time period and a second data query time period according to the data query duration and the first data query time period, and search in the database based on the first query time period to obtain initial feature data.
[0051] Among them, the initial feature data is the business transaction volume data of the distributed system in the current data acquisition cycle. The first query time period can be understood as a data retrieval parameter generated according to the first data query moment and the data query duration, which is used to retrieve the initial feature data from the database. The present invention defines the first data query moment as the end time of the first query time period, and the moment corresponding to the data query duration before the first data query moment is the starting time of the first query time period. The transaction volume data within the first query time period is the initial feature data of the distributed system. Whether there is service migration in the initial feature data represents whether service migration occurs in the homogeneous deployment cluster of the distributed system. The second data query moment can be understood as a time node generated according to the first data query moment and the data query duration, which is used to retrieve reference feature data.
[0052] In a specific example, assume the data query duration is one week, the reference feature data acquisition cycle is one cycle before the initial feature data acquisition cycle, and the first data query time is time A. Time A is unique within a week and can be specified in minutes to a specific minute of a day of the week or in hours to a specific hour of a day of the week. Therefore, the first query time period is the period between time A of the previous week and time A of this week. The second data query time is time A of the previous week, and the initial feature data is the business transaction volume data of the distributed system between time A of the previous week and time A of this week.
[0053] S203: Determine a second query time period according to the data query duration and the second data query time, and search in the database based on the second query time period to obtain reference feature data.
[0054] The reference feature data is the business transaction volume data of the distributed system within a preset data acquisition period, which is earlier than the current data acquisition period. The second query time period can be understood as a data retrieval parameter generated based on the second data query time and the data query duration, used to retrieve the reference feature data from the database. The present invention defines the transaction volume data within the second query time period as the reference feature data of the distributed system. The reference feature data is used to assess whether there is migration in the initial feature data.
[0055] In a specific example, assuming that the data query duration is one week and the second data query time is time A of the previous week, the second query time period is the time period between time A of the previous week and time A of the previous week, and the reference feature data is the business transaction volume data of the distributed system in the time period between time A of the previous week and time A of the previous week.
[0056] The advantage of this setting is that it can obtain complete initial feature data and reference feature data to improve the accuracy of the correlation analysis conclusions.
[0057] It is worth noting that, on the one hand, the present invention divides the acquired initial and reference feature data into weekday and weekend time zones, performing service migration detection separately to achieve the goal of divide and conquer. On the other hand, the present invention performs a preliminary screening of the acquired initial and reference feature data, deleting transaction volume data containing abnormal services to ensure accurate service migration detection.
[0058] S204: Perform a correlation analysis on the initial feature data and the reference feature data, and determine the initial migration type of the distributed system based on the analysis result.
[0059] Correlation analysis can be understood as analyzing the relationship or similarity between the initial feature data and the reference feature data. The analysis results can be understood as the analysis conclusion of the relationship or similarity between the initial feature data and the reference feature data. The initial migration type can be understood as a preliminary conclusion of the migration type of the service migration action of the distributed system. Specifically, the migration types of service migration include machine migration and business migration. The machine migration type is used to indicate the presence of instance migration in the distributed system, and the business migration type is used to indicate the presence of business migration in the distributed system.
[0060] The analysis results indicate the initial migration type of the service migration, including whether the initial feature data has a high correlation with the reference feature data or a low correlation with the reference feature data. Different analysis results correspond to different initial migration types. For example, a low correlation between the initial feature data and the reference feature data corresponds to a business migration type, while a high correlation between the initial feature data and the reference feature data corresponds to a machine migration type. This setting allows for quick identification of the service migration type, specific determination of detailed service migration information, and increased efficiency in determining service migration information.
[0061] In one embodiment, S204 may specifically include: determining the first standard deviation of the initial feature data, the first covariance of the initial feature data, the second standard deviation of the reference feature data, and the second covariance of the reference feature data; processing the first standard deviation, the first covariance, the second standard deviation, and the second covariance to obtain an analysis result including a correlation value; comparing a preset correlation threshold and the correlation value, and obtaining the initial migration type based on the comparison result.
[0062] Among them, the correlation value can be understood as a data representing the degree of correlation between the initial feature data and the reference feature data, and the preset correlation threshold can be understood as the basis for judging the correlation between the initial feature data and the reference feature data according to the correlation value in the analysis result, for example, 0.75, 0.8, 0.85, etc. The specific numerical value is related to the detection logic of the service migration information, and this embodiment does not limit this. When the analysis result is greater than the preset correlation threshold, the initial migration type is determined to be a machine migration type, and it is preliminarily determined that there may be instance migration in the distributed system. When the analysis result is not greater than the preset correlation threshold, the initial migration type is determined to be a business migration type, and it is preliminarily determined that there may be business migration in the distributed system. The advantage of this setting is that the evaluation criteria for the service migration type can be quantified, thereby shortening the time for determining the service migration type.
[0063] In one embodiment, the correlation value Where x represents the product of the standard deviations of the initial feature data, that is, the product of multiple standard deviations within the first standard deviation, and y represents the product of the standard deviations of the reference feature data, that is, the product of multiple standard deviations within the second standard deviation. represents the covariance of the initial feature data, that is, the first covariance, represents the covariance of the reference feature data, that is, the second covariance, and n represents the total number of data.
[0064] Taking the preset correlation threshold of 0.8 as an example, when the correlation value is greater than 0.8, it is considered that the initial feature data and the reference feature data are extremely correlated, and the initial migration type is determined to be a machine migration type. Otherwise, the initial migration type is determined to be a business migration type.
[0065] S205: Determine the relocation point detection solution corresponding to the initial migration type as the service migration information determination solution.
[0066] The relocation point can be understood as the time when the service migration action occurs, and the service migration information determination scheme can be understood as a method for further verifying the service migration type and determining the time when the service migration action occurs. Specifically, the relocation point detection scheme includes a horizontal relocation detection scheme corresponding to the machine migration type and a trend mutation detection scheme corresponding to the business migration type. When the initial migration type is the business migration type, the service migration information determination scheme is determined to be the trend mutation detection scheme; when the initial migration type is the machine migration type, the service migration information determination scheme is determined to be the horizontal relocation detection scheme.
[0067] The advantage of this setting is that it can quickly locate service migration information and determine a solution so as to detect service migration information in a targeted manner.
[0068] S206: Determine a solution using the service migration information, process the initial feature data and the reference feature data, and obtain target service migration information of the distributed system.
[0069] The target service migration information may be understood as detailed migration information of a service migration action occurring in a homogeneous deployment cluster of a distributed system, including but not limited to the migration type and relocation point of the service migration.
[0070] In this step, the server processes the initial feature data and the reference feature data according to the service migration information determination scheme determined in step S205, and determines the target service migration information of the distributed system according to the processing result.
[0071] The technical solution of this embodiment parses the service migration information determination instruction upon receipt, and obtains the query requirements contained in the instruction, such as the directly contained data query duration and the first data query time of the distributed system, and the indirectly contained second data query time and the determination of the second query time period. The initial feature data and reference feature data in the database are called according to the query requirements contained in the service migration information determination instruction, and the two types of data are subjected to correlation analysis. The initial migration type of the distributed system and the determination scheme of the service migration information are determined in a targeted manner according to the correlation analysis results, and the initial feature data and reference feature data are processed using the determined scheme. This can reduce the involvement of management personnel, reduce the dependence on manual labor in the determination of service migration information, and effectively improve the detection efficiency and quality of service migration information. Service migration information can be detected in all directions, and while improving detection efficiency, manpower input can be reduced, achieving the purpose of reducing costs and increasing efficiency. This solves the problem that verifying service migration actions and confirming service migration information by management personnel prolongs the determination time of service migration information, reduces the recognition efficiency of service migration information, and results in low recognition accuracy of service migration information.
[0072] The present invention can adopt different service migration information detection methods to process different migration types, thereby achieving the goal of divide and conquer. Figure 3 This is a flow chart of a method for determining target service migration information provided by the present invention, which is used to determine service migration information of a machine migration type. Based on the above embodiment, when the service migration information determination scheme is a horizontal relocation detection scheme, S206 includes the following steps:
[0073] S301: Calculate an offset ratio between initial feature data and reference feature data to obtain at least one offset data.
[0074] The initial feature data includes trading volume data at multiple points in time, and the reference feature data also includes reference trading volume data at multiple points in time. The trading volume data in the initial feature data and the reference trading volume data in the reference feature data are in a one-to-one correspondence, defined by the data's position within the data acquisition cycle or the time of generation. The "offset ratio" can be understood as the degree of deviation between each trading volume data item in the initial feature data and its corresponding reference trading volume data item, and the "offset data" can be understood as a quantitative representation of the degree of deviation.
[0075] In one embodiment, S301 may specifically include: dividing the initial feature data and the reference feature data based on the machine migration clustering duration to obtain at least one sub-initial feature data and at least one sub-reference feature data, wherein the sub-initial feature data and the sub-reference feature data have a one-to-one correspondence; using preset data screening rules, processing the at least one sub-initial feature data and the at least one sub-reference feature data to obtain at least one initial feature data of an operator to be solved and at least one reference feature data of an operator to be solved, wherein the initial feature data of the operator to be solved and the reference feature data of the operator to be solved have a one-to-one correspondence; performing an offset ratio calculation on the at least one initial feature data of the operator to be solved and the at least one reference feature data of the operator to be solved to obtain at least one offset data; wherein the offset data has a one-to-one correspondence with the initial feature data of the operator to be solved and the reference feature data of the operator to be solved.
[0076] The machine migration clustering duration can be understood as the time unit for dividing the initial feature data during horizontal relocation detection. In the present invention, the machine migration clustering duration is one hour, that is, one week is used as a data acquisition cycle. The initial feature data and the reference feature data are divided based on the machine migration clustering duration to obtain at least one sub-initial feature data and at least one sub-reference feature data. It can be understood that the initial feature data is divided into 168 sub-initial feature data and the reference feature data is divided into 168 sub-reference feature data based on one hour. The weekly data is 120 and the weekend data is 48. The weekly data and the weekend data are processed separately.
[0077] The preset data filtering rule can be understood as a data filtering rule. For example, data between the 10th and 90th digits, data between the 20th and 80th digits, etc., are selected to eliminate the maximum and minimum data and reduce the impact of discrete data on the detection conclusion. The initial feature data of the operator to be solved can be understood as the sub-initial feature data after filtering, and the reference feature data of the operator to be solved can be understood as the sub-reference feature data after filtering.
[0078] An offset ratio calculation is performed on at least one initial feature data of an operator to be solved and at least one reference feature data of an operator to be solved to obtain at least one offset data. This can be understood as respectively calculating the offset degree of each initial feature data of an operator to be solved and its corresponding reference feature data of an operator to be solved, and obtaining a deviation value between the two, so as to quantify the deviation degree of each initial feature data of an operator to be solved.
[0079] Specifically, for any initial feature data of the operator to be solved, an offset ratio calculation is performed on the initial feature data of the operator to be solved and the reference feature data of the operator to be solved corresponding to the initial feature data of the operator to be solved to obtain the offset data corresponding to the initial feature data of the operator to be solved, including: determining the offset data based on the aggregate mean of the initial feature data of the operator to be solved, the aggregate mean of the reference feature data of the operator to be solved and the data minimum.
[0080] Among them, the aggregate mean of the initial feature data of the operator to be solved can be understood as the average value of multiple transaction volume data in the initial feature data of the operator to be solved, the aggregate mean of the reference feature data of the operator to be solved can be understood as the average value of multiple transaction volume data in the reference feature data of the operator to be solved, and the data minimum value can be understood as the weight parameter used to calculate the offset data.
[0081] Specifically, offset data Among them, c represents the aggregate mean of the initial feature data of the operator to be solved, m represents the aggregate mean of the reference feature data of the operator to be solved, and l represents the minimum value of the data.
[0082] The at least one offset data of the present invention is an offset data sequence including 120 offset data or 48 offset data.
[0083] S302: Cluster at least one offset data to obtain at least one data cluster.
[0084] The data cluster can be understood as a cluster of offset data, for example, a data cluster formed by dividing relatively close offset data according to distance values.
[0085] In one embodiment, S302 may specifically include: sorting at least one offset data in ascending order of data value; determining the distance value between each offset data and adjacent offset data, and clustering the offset data whose distance value is less than a preset neighborhood radius to obtain at least one data cluster.
[0086] Among them, the preset neighborhood radius can be understood as the basis for evaluating the distance between two offset data and whether they can be clustered into a data cluster. Only two offset data with a distance value less than the preset neighborhood radius can be clustered.
[0087] Specifically, the preset neighborhood radius s = α * (1 / w), where w represents the size of the homogeneous deployment cluster and α represents the decay coefficient, which defaults to 0.8. The minimum number of neighbors is 1, indicating that a single data point can also be grouped.
[0088] S303: Determine target service migration information based on a preset data threshold, a data value of at least one data cluster, and a data time identifier.
[0089] Among them, the data value of the data cluster can be understood as the value of each transaction volume data in the data cluster, and the data time identifier of the data cluster can be understood as the generation time of each transaction volume data in the data cluster, which is similar to an index and is used to locate the relocation point of service migration.
[0090] The preset data threshold can be understood as a basis for determining whether a data cluster needs further detection. The data cluster that needs further detection is the data cluster that may have service migration. The advantage of this setting is that the data cluster is preliminarily screened and only the data clusters that may have service migration are detected, thereby reducing the workload of detecting service migration information.
[0091] Specifically, the preset data threshold is -α*(1 / w), where w represents the size of the homogeneous deployment cluster and α represents the attenuation coefficient, which defaults to 0.8.
[0092] In one embodiment, S303 may specifically include: determining that a data cluster whose data value is less than a preset data threshold is a candidate data cluster; determining whether there is a data cluster with an offset higher than a preset offset in the candidate data cluster; if there is no data cluster with an offset higher than the preset offset, determining the first target migration type as a no migration type, and determining the first target migration type as the target service migration information; if there is a data cluster with an offset higher than the preset offset, determining the second target migration type as a machine migration type, determining the target migration point based on the data time identifier of the data cluster with an offset higher than the preset offset, and determining the second target migration type and the target migration point as the target service migration information.
[0093] The candidate data cluster can be understood as a data cluster requiring further service migration information detection. The preset offset can be understood as the basis for evaluating whether each transaction volume data in the candidate data cluster is migration data, and the offset degree can be understood as the degree of offset of each transaction volume data in the candidate data cluster. The "no migration" type indicates that no service migration occurs in the distributed system. The "machine migration" type indicates that a machine migration occurs in the distributed system, meaning that some instances in the distributed system have migrated. The target migration point is the time when the machine migration occurs.
[0094] Specifically, assuming a preset offset of 0.9, this embodiment determines the offset of each transaction volume data point in the candidate data cluster, sequentially following the time stamps of each transaction volume data point from earliest to latest. If the offset of a transaction volume data point exceeds 0.9, the calculation is stopped and the corresponding time stamp of that data point is determined as the target relocation point. It is worth noting that the transaction volume data in the candidate data cluster is the processed initial feature data of the operator to be solved.
[0095] Offset Among them, p represents the size of the candidate data cluster, that is, the number of transaction volume data in the candidate data cluster, q represents the length of the initial feature data of the operator to be solved, that is, the number of initial feature data of the operator to be solved, which is 120 or 48 in this embodiment, and j represents the data time identifier.
[0096] Specifically, the process of determining the target relocation point based on the data time stamp includes: 1) calculating the relocation day, relocation day = j / / 24 + 1; 2) calculating the relocation time, relocation time hour = j% 24, where j represents the data time stamp.
[0097] The advantage of this setting is that it takes advantage of the fact that machine migration changes the overall transaction volume characteristics to quickly and accurately determine the service migration information of the distributed system.
[0098] Figure 4 This is a flow chart of another method for determining target service migration information provided by the present invention, which is used to determine service migration information of a business migration type. Based on the above embodiment, when the service migration information determination scheme is a trend mutation detection scheme, S206 includes the following steps:
[0099] S401: Process initial feature data and reference feature data to obtain at least one trend mutation factor.
[0100] The initial feature data includes trading volume data at multiple points in time, and the reference feature data also includes reference trading volume data at multiple points in time. The trading volume data in the initial feature data and the reference trading volume data in the reference feature data are in a one-to-one correspondence, determined by the data's position within the data acquisition cycle or the time of generation. The trend mutation factor can be understood as a quantitative measure of the degree of mutation between each trading volume data point in the initial feature data and its corresponding reference trading volume data point.
[0101] In one embodiment, S401 may specifically include: dividing the initial feature data and the reference feature data based on the service migration clustering duration to obtain at least one sub-initial feature data and at least one sub-reference feature data, wherein the sub-initial feature data and the sub-reference feature data have a one-to-one correspondence; using preset data screening rules, processing the at least one sub-initial feature data and the at least one sub-reference feature data to obtain at least one initial feature data of an operator to be solved and at least one reference feature data of an operator to be solved, wherein the initial feature data of the operator to be solved and the reference feature data of the operator to be solved have a one-to-one correspondence; performing sum and difference calculation on the at least one initial feature data of the operator to be solved and the at least one reference feature data of the operator to be solved to obtain at least one trend mutation factor; wherein the trend mutation factor has a one-to-one correspondence with the initial feature data of the operator to be solved and the reference feature data of the operator to be solved.
[0102] The business migration clustering duration can be understood as the time unit for dividing the initial feature data during mutation trend detection. In the present invention, the business migration clustering duration is two hours, that is, one week is used as a data acquisition cycle. The initial feature data and the reference feature data are divided based on the business migration clustering duration to obtain at least one sub-initial feature data and at least one sub-reference feature data. It can be understood that the initial feature data is divided into 84 sub-initial feature data and the reference feature data is divided into 84 sub-reference feature data based on two hours. There are 60 data within the week and 24 data on the weekend. The data within the week and the weekend data are processed separately.
[0103] Similarly, the preset data filtering rules are data filtering rules. For example, data between the 10th and 90th digits, data between the 20th and 80th digits, etc. are selected. The purpose of this is to filter out the maximum and minimum data and reduce the impact of discrete data on the detection conclusion. The initial feature data of the operator to be solved can be understood as the sub-initial feature data after filtering, and the reference feature data of the operator to be solved can be understood as the sub-reference feature data after filtering.
[0104] Sum and difference calculations are performed on at least one initial characteristic data of an operator to be solved and at least one reference characteristic data of an operator to be solved to obtain at least one trend mutation factor. This can be understood as respectively calculating the trend mutation factors of each initial characteristic data of an operator to be solved and its corresponding reference characteristic data of an operator to be solved, so as to quantify the mutation situation of each initial characteristic data of an operator to be solved.
[0105] For any initial feature data of the operator to be solved, a sum and difference calculation is performed on the initial feature data of the operator to be solved and the reference feature data of the operator to be solved corresponding to the initial feature data of the operator to be solved to obtain a trend mutation factor corresponding to the initial feature data of the operator to be solved, including: determining the trend mutation factor based on the aggregate mean of the initial feature data of the operator to be solved and the aggregate mean of the reference feature data of the operator to be solved.
[0106] The aggregate mean of the initial feature data of the operator to be solved can be understood as the average of multiple transaction volume data in the initial feature data of the operator to be solved, and the aggregate mean of the reference feature data of the operator to be solved can be understood as the average of multiple transaction volume data in the reference feature data of the operator to be solved. c represents the aggregate mean of the initial characteristic data of the operator to be solved, and m represents the aggregate mean of the reference characteristic data of the operator to be solved. At least one trend mutation factor of the present invention is a trend mutation factor sequence including 60 offset data or 24 offset data.
[0107] S402: Process at least one trend mutation factor to obtain a first business statistic and a second business statistic.
[0108] The first service statistic can be understood as a sequence of at least one trend mutation factor in ascending order, and the second service statistic can be understood as a sequence of at least one trend mutation factor in descending order. Specifically, the first service statistic and the second service statistic are used to determine whether a mutation has occurred in each trend mutation factor. If a mutation has occurred in a trend mutation factor, further testing of the mutation time is required to determine the relocation point for service migration.
[0109] In one embodiment, S402 may specifically include: sorting at least one trend mutation factor based on the order of generation time from early to late to obtain a first sorting result; processing at least one trend mutation factor according to the first sorting result to obtain a first-order series factor, and determining a first business statistic based on the variance and expectation of the first-order series factor, wherein the first-order series factor includes at least one sub-first-order series factor, the first business statistic includes at least one sub-first-business statistic, and the sub-first-business statistic corresponds one-to-one to the sub-first-order series factor; sorting at least one trend mutation factor based on the order of generation time from late to early to obtain a second sorting result; processing at least one trend mutation factor according to the second sorting result to obtain a second-order series factor, and determining a second business statistic based on the variance and expectation of the second-order series factor, wherein the second-order series factor includes at least one sub-second-order series factor, the second business statistic includes at least one sub-second-business statistic, and the sub-second-business statistic corresponds one-to-one to the sub-second-order series factor.
[0110] Among them, the first-order series factor can be understood as the sum of the sequences constructed based on the trend mutation factors in the forward order, and the second-order series factor can be understood as the sum of the sequences constructed based on the trend mutation factors in the reverse order.
[0111] Specifically, the first business statistics Among them, k represents the number of trend mutation factors, E(s k ) represents the expectation of the first-order series factor, Var(s k ) represents the variance of the first-order series factor, s k represents the first sequence factor.
[0112] Variance of the first-order series factor Expectation of the first-order series of factors n represents the total number of trend mutation factors, the first order series factors r i represents the i-th order sequence parameter, 1≤j≤i≤n. The second service statistic UB kThe method for determining the second service statistic is the same as that for the first service statistic, and the present invention will not elaborate on this. Generally, the value of the second service statistic is the negative value of the first service statistic.
[0113] S403: Determine target service migration information based on intersection information of the first service statistic and the second service statistic.
[0114] Among them, the intersection information can be understood as the intersection point information of the curves represented by the first business statistic and the second business statistic, for example, the confidence level of the intersection of the curve of the first business statistic and the curve of the second business statistic, the data time mark of the intersection, etc., which is used to locate the relocation point of service migration.
[0115] In one embodiment, S403 may specifically include: determining whether the intersection information of the first business statistic and the second business statistic meets the business migration condition, wherein the business migration condition is that the intersection information of the first business statistic and the second business statistic is within the confidence level interval; if the intersection information of the first business statistic and the second business statistic does not meet the business migration condition, determining the first target migration type as the no migration type, and determining the first target migration type as the target service migration information; if the intersection information of the first business statistic and the second business statistic meets the business migration condition, determining the second target migration type as the business migration type, determining the target relocation point based on the first business statistic and the second business statistics, and determining the second target migration type and the target relocation point as the target service migration information.
[0116] The confidence level interval determines whether the intersection information represents a trend mutation point. Only intersection information within the confidence level interval indicates that a service migration has occurred in the distributed system. The confidence level interval is generally [-1.96, 1.96]. Specifically, when the first and second service statistics curves do not intersect, or their intersection information is not within the confidence level interval [-1.96, 1.96], the sequence is determined to have no trend mutation, the distributed system has no service migration, and the target migration type is no migration. When the intersection information of the first and second service statistics curves is within the confidence level interval [-1.96, 1.96], the sequence is determined to have a trend mutation, the distributed system has service migration, and the intersection corresponds to the location where the mutation begins.
[0117] Optionally, determining the target relocation point based on the first business statistic and the second business statistic includes: performing differential processing on the first business statistic and the second business statistic to obtain at least one differential data, wherein the differential data corresponds one-to-one to the sub-first business statistic and the sub-second business statistic; if there is differential data whose differential result satisfies the preset business migration condition, determining the target relocation point based on the data time identifier corresponding to the differential data that satisfies the preset business migration condition; if there is differential data whose differential result satisfies the preset business migration condition, reversing at least one differential data, constructing a target business function based on the reversed result, the first business statistic, and the second business statistic, solving the target business function, and determining the target relocation point based on the function solution result within the confidence level interval.
[0118] In this case, performing differential processing on the first business statistic and the second business statistic to obtain at least one differential data can be understood as performing differential processing on each transaction volume data in the first business statistic and its corresponding transaction volume data in the second business statistic to obtain differential data corresponding to the transaction volume data. The preset business migration condition is the basis for assessing whether each transaction volume data is a trend mutation point. In the present invention, the preset business migration condition is that the sequence values (sub-first business statistics and sub-second business statistics) corresponding to the transaction volume data with a differential result of 0 in the first business statistic and the second business statistic are both within the confidence level interval [-1.96, 1.96]. If there is differential data whose differential result meets the preset business migration condition, the data time identifier corresponding to the differential data meeting the preset business migration condition is determined as the mutation time, and the data time identifier is parsed to obtain the target relocation point. The target relocation point parsing process is the same as in the above embodiment and is not elaborated on in this embodiment.
[0119] The target business function can be understood as a solution algorithm for a mutation point. Specifically, when there is no differential data in the differential result that meets the preset business migration conditions, it is necessary to construct a target business function to solve the service migration information. The solution process specifically includes: 1) solving the positive and negative transformation positions n and n+1 of the first business statistic and the second business statistic; 2) reversing at least one differential data to obtain at least one intermediate differential data; 3) using (n, UFn), (n+1, UFn+1) to construct the function f(x), and using (n, UBn), (n+1, UBn+1) to construct the function g(x); 4) setting f(x)-g(x)=0, and determining whether rk in the solution result (k, rk) is within the confidence level interval [-1.96, 1.96]. If it is within the confidence level interval, then determining the time when k is rounded up and restored as the target relocation point, that is, the time when the service migration action occurs; if rk is not within the confidence level interval [-1.96, 1.96], then updating the positive and negative transformation position, and returning to execute step 3).
[0120] The advantage of this setting is that it utilizes the characteristics of business migration that change the overall transaction volume characteristics to detect trend mutation points, and then quickly and accurately determine the service migration information of the distributed system's business migration. The trend mutation point in the present invention is the relocation point where the business migration occurs.
[0121] Figure 5 This is a schematic diagram of the structure of a device for determining service migration information provided by the present invention. Figure 5 As shown, the device includes: an information acquisition module 501, a solution determination module 502 and an information determination module 503.
[0122] The information acquisition module 501 is used to search in the database based on the service migration information determination instruction when receiving the service migration information determination instruction of the distributed system, and obtain the initial feature data and reference feature data of the distributed system, wherein the initial feature data is the business information of the distributed system in the current data acquisition cycle, and the reference feature data is the business information of the distributed system in the preset data acquisition cycle, and the preset data acquisition cycle is earlier than the current data acquisition cycle.
[0123] The solution determination module 502 is configured to perform a correlation analysis on the initial feature data and the reference feature data, and determine a service migration information determination solution for the distributed system based on the analysis result.
[0124] The information determination module 503 is configured to process the initial feature data and the reference feature data using a service migration information determination solution to obtain target service migration information of the distributed system.
[0125] Optionally, the information acquisition module 501 is specifically used to parse the service migration information to determine the instruction, and obtain the data query duration and the first data query time of the distributed system; determine the first query time period and the second data query time based on the data query duration and the first data query time, and search in the database based on the first query time period to obtain initial feature data; determine the second query time period based on the data query duration and the second data query time, and search in the database based on the second query time period to obtain reference feature data.
[0126] Optionally, the solution determination module 502 is specifically used to perform correlation analysis on the initial feature data and the reference feature data, and determine the initial migration type of the distributed system based on the analysis results; and determine the relocation point detection solution corresponding to the initial migration type as the service migration information determination solution.
[0127] Optionally, the scheme determination module 502 is specifically used to determine the first standard deviation of the initial feature data, the first covariance of the initial feature data, the second standard deviation of the reference feature data, and the second covariance of the reference feature data; process the first standard deviation, the first covariance, the second standard deviation, and the second covariance to obtain an analysis result including a correlation value; compare the preset correlation threshold and the correlation value, and obtain the initial migration type according to the comparison result.
[0128] Optionally, the solution determination module 502 is specifically used to determine that the initial migration type is a machine migration type when the analysis result is greater than a preset correlation threshold, wherein the machine migration type is used to indicate that there is instance migration in the distributed system; when the analysis result is not greater than the preset correlation threshold, determine that the initial migration type is a business migration type, wherein the business migration type is used to indicate that there is business migration in the distributed system.
[0129] Optionally, the relocation point detection scheme includes a horizontal relocation detection scheme corresponding to the machine migration type and a trend mutation detection scheme corresponding to the business migration type.
[0130] Optionally, the solution determination module 502 is specifically used to determine that the service migration information determination solution is a trend mutation detection solution when the initial migration type is a business migration type; when the initial migration type is a machine migration type, determine that the service migration information determination solution is a horizontal relocation detection solution.
[0131] Optionally, when the service migration information determination scheme is a horizontal relocation detection scheme, the information determination module 503 is specifically used to calculate the offset ratio of the initial feature data and the reference feature data to obtain at least one offset data; cluster the at least one offset data to obtain at least one data cluster; and determine the target service migration information based on a preset data threshold, the data value of at least one data cluster, and the data time identifier.
[0132] Optionally, the information determination module 503 is specifically used to divide the initial feature data and the reference feature data based on the machine migration clustering duration to obtain at least one sub-initial feature data and at least one sub-reference feature data, wherein the sub-initial feature data and the sub-reference feature data have a one-to-one correspondence; use preset data screening rules to process the at least one sub-initial feature data and the at least one sub-reference feature data respectively to obtain at least one initial feature data of the operator to be solved and at least one reference feature data of the operator to be solved, wherein the initial feature data of the operator to be solved and the reference feature data of the operator to be solved have a one-to-one correspondence; perform offset ratio calculation on the at least one initial feature data of the operator to be solved and the at least one reference feature data of the operator to be solved to obtain at least one offset data; wherein the offset data has a one-to-one correspondence with the initial feature data of the operator to be solved and the reference feature data of the operator to be solved.
[0133] Optionally, for any initial feature data of the operator to be solved, the information determination module 503 is specifically configured to calculate an offset ratio between the initial feature data of the operator to be solved and the reference feature data of the operator to be solved corresponding to the initial feature data of the operator to be solved, to obtain offset data corresponding to the initial feature data of the operator to be solved. For example, the offset data may be determined based on the aggregate mean of the initial feature data of the operator to be solved, the aggregate mean of the reference feature data of the operator to be solved, and a data minimum.
[0134] Optionally, the information determination module 503 is specifically used to sort at least one offset data in ascending order of data value; determine the distance value between each offset data and the adjacent offset data, and cluster the offset data whose distance value is less than a preset neighborhood radius to obtain at least one data cluster.
[0135] Optionally, the information determination module 503 is specifically used to determine that a data cluster whose data value is less than a preset data threshold is a candidate data cluster; determine whether there is a data cluster with an offset higher than a preset offset in the candidate data cluster; if there is no data cluster with an offset higher than the preset offset, determine the first target migration type as a no migration type, and determine the first target migration type as the target service migration information; if there is a data cluster with an offset higher than the preset offset, determine the second target migration type as a machine migration type, determine the target migration point based on the data time identifier of the data cluster with an offset higher than the preset offset, and determine the second target migration type and the target migration point as the target service migration information.
[0136] Optionally, when the service migration information determination scheme is a trend mutation detection scheme, the information determination module 503 is specifically used to process the initial feature data and the reference feature data to obtain at least one trend mutation factor; process at least one trend mutation factor to obtain a first business statistic and a second business statistic; and determine the target service migration information based on the intersection information of the first business statistic and the second business statistic.
[0137] Optionally, the information determination module 503 is specifically used to divide the initial feature data and the reference feature data based on the service migration clustering duration to obtain at least one sub-initial feature data and at least one sub-reference feature data, wherein the sub-initial feature data and the sub-reference feature data have a one-to-one correspondence; use preset data screening rules to process the at least one sub-initial feature data and the at least one sub-reference feature data respectively to obtain at least one initial feature data of the operator to be solved and at least one reference feature data of the operator to be solved, wherein the initial feature data of the operator to be solved and the reference feature data of the operator to be solved have a one-to-one correspondence; perform sum and difference calculation on the at least one initial feature data of the operator to be solved and the at least one reference feature data of the operator to be solved to obtain at least one trend mutation factor; wherein the trend mutation factor has a one-to-one correspondence with the initial feature data of the operator to be solved and the reference feature data of the operator to be solved.
[0138] Optionally, the information determination module 503 is specifically used to sort at least one trend mutation factor based on the order of generation time from early to late to obtain a first sorting result; process at least one trend mutation factor according to the first sorting result to obtain a first order series factor, and determine a first business statistic based on the variance and expectation of the first order series factor, wherein the first order series factor includes at least one sub-first order series factor, the first business statistic includes at least one sub-first business statistic, and the sub-first business statistic corresponds one-to-one to the sub-first order series factor; sort at least one trend mutation factor based on the order of generation time from late to early to obtain a second sorting result; process at least one trend mutation factor according to the second sorting result to obtain a second order series factor, and determine a second business statistic based on the variance and expectation of the second order series factor, wherein the second order series factor includes at least one sub-second order series factor, the second business statistic includes at least one sub-second business statistic, and the sub-second business statistic corresponds one-to-one to the sub-second order series factor.
[0139] Optionally, the information determination module 503 is specifically used to determine whether the intersection information of the first business statistic and the second business statistic meets the business migration condition, wherein the business migration condition is that the intersection information of the first business statistic and the second business statistic is within the confidence level interval; if the intersection information of the first business statistic and the second business statistic does not meet the business migration condition, the first target migration type is determined to be a no-migration type, and the first target migration type is determined to be the target service migration information; if the intersection information of the first business statistic and the second business statistic meets the business migration condition, the second target migration type is determined to be a business migration type, the target relocation point is determined based on the first business statistic and the second business statistics, and the second target migration type and the target relocation point are determined to be the target service migration information.
[0140] Optionally, the information determination module 503 is specifically used to perform differential processing on the first business statistic and the second business statistic to obtain at least one differential data, wherein the differential data corresponds one-to-one to the sub-first business statistic and the sub-second business statistic; if there is differential data whose differential result meets the preset business migration condition, then the target relocation point is determined based on the data time identifier corresponding to the differential data that meets the preset business migration condition; if there is differential data whose differential result meets the preset business migration condition, then at least one differential data is reversed, and a target business function is constructed based on the reversed result, the first business statistic, and the second business statistic, the target business function is solved, and the target relocation point is determined based on the function solution result within the confidence level interval.
[0141] The device for determining service migration information provided in this embodiment can execute the method for determining service migration information provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0142] Figure 6 : is a structural diagram of an electronic device provided by the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.
[0143] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (also known as random access memory, RAM) 13, etc., wherein the memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12 and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0144] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.
[0145] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for determining service migration information.
[0146] In some embodiments, the method for determining service migration information may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for determining service migration information described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method for determining service migration information in any other appropriate manner (for example, by means of firmware).
[0147] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0148] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.
[0149] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device or any suitable combination of the foregoing.
[0150] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0151] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0152] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.
[0153] In one embodiment, the present invention further includes a computer program product. The computer program product includes a computer program. When the computer program is executed by a processor, the method for determining service migration information of any embodiment of the present invention is implemented.
[0154] The computer program product may be implemented by writing computer program code for performing the operations of the present invention in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone 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 a remote computer, the remote computer may 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 may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0155] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.
[0156] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.
Claims
1. A method for determining service migration information, characterized in that: include: When receiving a service migration information determination instruction of a distributed system, searching in a database based on the service migration information determination instruction to obtain initial feature data and reference feature data of the distributed system, wherein the initial feature data is the business information of the distributed system in a current data acquisition cycle, and the reference feature data is the business information of the distributed system in a preset data acquisition cycle, and the preset data acquisition cycle is earlier than the current data acquisition cycle; Performing a correlation analysis on the initial feature data and the reference feature data, and determining a service migration information determination scheme for the distributed system according to the analysis result; The service migration information determination scheme is used to process the initial feature data and the reference feature data to obtain target service migration information of the distributed system.
2. The method according to claim 1, characterized in that The determining instruction based on the service migration information searches in a database to obtain initial feature data and reference feature data of the distributed system, including: Parsing the service migration information determination instruction to obtain the data query duration and the first data query time of the distributed system; Determine a first query time period and a second data query time period according to the data query duration and the first data query time period, and search the database based on the first query time period to obtain the initial feature data; A second query time period is determined according to the data query duration and the second data query time, and a search is performed in the database based on the second query time period to obtain the reference feature data.
3. The method according to claim 1, characterized in that The performing correlation analysis on the initial feature data and the reference feature data, and determining a service migration information determination scheme of the distributed system according to the analysis result, includes: Performing a correlation analysis on the initial feature data and the reference feature data, and determining an initial migration type of the distributed system according to the analysis result; Determine the relocation point detection scheme corresponding to the initial migration type as the service migration information determination scheme.
4. The method according to claim 3, characterized in that The performing correlation analysis on the initial feature data and the reference feature data, and determining the initial migration type of the distributed system according to the analysis result, includes: Determining a first standard deviation of the initial feature data, a first covariance of the initial feature data, a second standard deviation of the reference feature data, and a second covariance of the reference feature data; Processing the first standard deviation, the first covariance, the second standard deviation, and the second covariance to obtain the analysis result including the correlation value; The preset correlation threshold and the correlation value are compared, and the initial migration type is obtained according to the comparison result.
5. The method according to claim 4, characterized in that The comparing the preset correlation threshold and the analysis result to obtain the initial migration type includes: When the analysis result is greater than the preset correlation threshold, determining that the initial migration type is a machine migration type, wherein the machine migration type is used to indicate that there is instance migration in the distributed system; When the analysis result is not greater than the preset correlation threshold, it is determined that the initial migration type is a service migration type, wherein the service migration type is used to indicate that service migration exists in the distributed system.
6. The method according to claim 5, characterized in that The relocation point detection scheme includes a horizontal relocation detection scheme corresponding to the machine migration type and a trend mutation detection scheme corresponding to the business migration type; The relocation point detection scheme for determining the initial migration type corresponding to the service migration information determination scheme includes: When the initial migration type is the business migration type, determining the service migration information determination scheme as the trend mutation detection scheme; When the initial migration type is the machine migration type, the service migration information determination scheme is determined to be the horizontal relocation detection scheme.
7. The method according to claim 6, characterized in that Using the horizontal relocation detection scheme, the initial feature data and the reference feature data are processed to obtain target service migration information of the distributed system, including: Calculating an offset ratio between the initial feature data and the reference feature data to obtain at least one offset data; Clustering the at least one offset data to obtain at least one data cluster; The target service migration information is determined based on a preset data threshold, a data value of the at least one data cluster, and a data time identifier.
8. The method according to claim 7, characterized in that The calculating the offset ratio between the initial feature data and the reference feature data to obtain at least one offset data includes: The initial feature data and the reference feature data are divided based on the machine migration clustering duration to obtain at least one sub-initial feature data and at least one sub-reference feature data, wherein the sub-initial feature data and the sub-reference feature data correspond to each other one by one; Using a preset data screening rule, the at least one sub-initial feature data and the at least one sub-reference feature data are processed respectively to obtain at least one to-be-solved operator initial feature data and at least one to-be-solved operator reference feature data, wherein the to-be-solved operator initial feature data and the to-be-solved operator reference feature data are in one-to-one correspondence; An offset ratio calculation is performed on the at least one initial feature data of the operator to be solved and the at least one reference feature data of the operator to be solved to obtain the at least one offset data; wherein the offset data corresponds one-to-one to the initial feature data of the operator to be solved and the reference feature data of the operator to be solved.
9. The method according to claim 8, characterized in that For any initial feature data of an operator to be solved, an offset ratio calculation is performed on the initial feature data of the operator to be solved and the reference feature data of the operator to be solved corresponding to the initial feature data of the operator to be solved to obtain offset data corresponding to the initial feature data of the operator to be solved, including: The offset data is determined based on the aggregate mean value of the initial feature data of the operator to be solved, the aggregate mean value of the reference feature data of the operator to be solved, and a data minimum value.
10. The method according to claim 7, characterized in that The step of clustering the at least one offset data to obtain at least one data cluster comprises: Sort the at least one offset data according to the order of data value from small to large; The distance value between each offset data and adjacent offset data is determined, and the offset data with a distance value smaller than a preset neighborhood radius is clustered to obtain the at least one data cluster.
11. The method according to claim 7, characterized in that The determining the target service migration information based on a preset data threshold, a data value of the at least one data cluster, and a data time identifier includes: Determine a data cluster whose data value is less than the preset data threshold as a candidate data cluster; Determine whether there is a data cluster with a deviation greater than a preset deviation in the candidate data clusters; If there is no data cluster with an offset greater than the preset offset, determining the first target migration type as a non-migration type, and determining the first target migration type as the target service migration information; If there is a data cluster with an offset higher than the preset offset, the second target migration type is determined to be a machine migration type, the target migration point is determined based on the data time identifier of the data cluster with an offset higher than the preset offset, and the second target migration type and the target migration point are determined as the target service migration information.
12. The method according to claim 6, characterized in that Using the trend mutation detection scheme, the initial feature data and the reference feature data are processed to obtain target service migration information of the distributed system, including: Processing the initial characteristic data and the reference characteristic data to obtain at least one trend mutation factor; Processing the at least one trend mutation factor to obtain a first business statistic and a second business statistic; The target service migration information is determined based on intersection information of the first service statistic and the second service statistic.
13. The method according to claim 12, characterized in that The processing of the initial feature data and the reference feature data to obtain at least one trend mutation factor includes: The initial feature data and the reference feature data are divided based on the service migration clustering duration to obtain at least one sub-initial feature data and at least one sub-reference feature data, wherein the sub-initial feature data and the sub-reference feature data correspond to each other one by one; Using a preset data screening rule, the at least one sub-initial feature data and the at least one sub-reference feature data are processed respectively to obtain at least one to-be-solved operator initial feature data and at least one to-be-solved operator reference feature data, wherein the to-be-solved operator initial feature data and the to-be-solved operator reference feature data are in one-to-one correspondence; The at least one initial characteristic data of the operator to be solved and the at least one reference characteristic data of the operator to be solved are calculated by sum and difference to obtain the at least one trend mutation factor; wherein the trend mutation factor corresponds one-to-one to the initial characteristic data of the operator to be solved and the reference characteristic data of the operator to be solved.
14. The method according to claim 12, characterized in that The processing of the at least one trend mutation factor to obtain a first business statistic and a second business statistic includes: Sorting the at least one trend mutation factor based on the order of generation time from early to late to obtain a first sorting result; According to the first sorting result, the at least one trend mutation factor is processed to obtain a first order series factor, and the first business statistic is determined based on the variance and expectation of the first order series factor, wherein the first order series factor includes at least one sub-first order series factor, the first business statistic includes at least one sub-first business statistic, and the sub-first business statistic corresponds to the sub-first order series factor one by one; Sorting the at least one trend mutation factor based on the order of generation time from late to early to obtain a second sorting result; According to the second sorting result, the at least one trend mutation factor is processed to obtain a second order series factor, and the second business statistic is determined based on the variance and expectation of the second order series factor, wherein the second order series factor includes at least one sub-second order series factor, and the second business statistic includes at least one sub-second business statistic, and the sub-second business statistic corresponds one-to-one to the sub-second order series factor.
15. The method according to claim 12, characterized in that The determining the target service migration information based on the intersection information of the first service statistic and the second service statistic includes: Determine whether the intersection information of the first service statistic and the second service statistic meets a service migration condition, wherein the service migration condition is that the intersection information of the first service statistic and the second service statistic is within a confidence level interval; If the intersection information of the first service statistic and the second service statistic does not meet the service migration condition, determining the first target migration type as a non-migration type, and determining the first target migration type as the target service migration information; If the intersection information of the first business statistics and the second business statistics meets the business migration condition, the second target migration type is determined to be the business migration type, the target migration point is determined based on the first business statistics and the second business statistics, and the second target migration type and the target migration point are determined as the target service migration information.
16. The method according to claim 15, characterized in that The determining of the target relocation point based on the first business statistics and the second business statistics includes: Performing differential processing on the first service statistic and the second service statistic to obtain at least one differential data, wherein the differential data corresponds one-to-one to the sub-first service statistic and the sub-second service statistic; If there is differential data whose differential result meets the preset business migration condition, the target relocation point is determined based on the data time identifier corresponding to the differential data that meets the preset business migration condition; If there is no differential data whose differential result meets the preset business migration conditions, then the at least one differential data is reversed, and a target business function is constructed based on the reversed result, the first business statistic and the second business statistic, and the target business function is solved, and the target relocation point is determined according to the function solution result within the confidence level interval.
17. A device for determining service migration information, characterized in that: include: An information acquisition module, configured to, upon receiving a service migration information determination instruction of a distributed system, search in a database based on the service migration information determination instruction to obtain initial feature data and reference feature data of the distributed system, wherein the initial feature data is the business information of the distributed system in a current data acquisition cycle, and the reference feature data is the business information of the distributed system in a preset data acquisition cycle, and the preset data acquisition cycle is earlier than the current data acquisition cycle; A scheme determination module, used to perform a correlation analysis on the initial feature data and the reference feature data, and determine a service migration information determination scheme for the distributed system according to the analysis result; The information determination module is used to process the initial feature data and the reference feature data using the service migration information determination scheme to obtain the target service migration information of the distributed system.
18. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for determining service migration information as described in any one of claims 1 to 16 when executing the computer program.
19. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for determining service migration information as described in any one of claims 1 to 16 is implemented.
20. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the method for determining service migration information according to any one of claims 1 to 16.
Citation Information
Patent Citations
Vehicle terminal service migration method and system
CN113377743A
Database migration method and device, electronic equipment and storage medium
CN115033551A
Data security control method and device, electronic equipment and storage medium
CN115238292A
Target object prediction method and device, equipment and medium
CN115545248A
Migration estimation with partial data
US20160092813A1
Cited By
System upgrading method and device and storage medium
CN119225770A
Cloud service automatic migration platform and migration method
CN120658796A
