Cloud-based e-commerce data analysis methods, systems, and electronic devices

Abstract

This invention discloses a cloud-based e-commerce data analysis method, system, and electronic device, relating to the field of e-commerce data analysis technology. It involves adjusting server and storage resources based on the current day's server and storage resource status, analyzing real-time data in conjunction with the initial adjustment result to determine if a secondary adjustment is needed, and then determining whether static adjustment is required after analyzing the current day's server and storage resource status. Finally, it combines real-time data acquired the following day with the server and storage resource status of that day to determine whether dynamic adjustment is needed. By using a cloud platform for traffic prediction, the platform's elastic scalability can dynamically adjust computing and storage resources according to business needs, avoiding system crashes during peak periods and reducing resource investment during low-traffic periods, thereby optimizing costs.

Description

Technical Field

[0001] This invention relates to the field of e-commerce data analysis technology, specifically to e-commerce data analysis methods, systems, and electronic devices based on cloud platforms. Background Technology

[0002] With the rapid development of the e-commerce industry, e-commerce platforms generate massive amounts of data every day, including user behavior data, transaction data, product information, inventory, and logistics information. This data is characterized by its large volume, diverse types, and rapid generation, requiring analysis and processing through analytical systems.

[0003] Existing e-commerce platforms typically pre-configure servers and storage resources, but this approach has the following drawbacks:

[0004] 1. E-commerce platforms typically configure server and storage resources based on estimated peak traffic, resulting in a large amount of computing resources being idle during off-peak periods, leading to resource waste and high operating costs.

[0005] 2. With limited server and storage resources, when faced with sudden traffic surges, the server load may be too high, leading to system crashes, lag, or slow response times, severely impacting the user experience.

[0006] 3. When real-time traffic increases, manual intervention is usually required, which may cause the system to be unable to respond quickly to sudden traffic, or even cause problems with untimely resource expansion. During low traffic periods, manually adjusting resources will slow down the response speed.

[0007] Based on this, the present invention proposes an e-commerce data analysis method, system and electronic device based on a cloud platform. After traffic prediction is performed through the cloud platform, the elastic expansion capability of the cloud platform can dynamically adjust computing and storage resources according to business needs, avoid system crashes during peak periods, and reduce resource investment during low traffic periods, thereby optimizing costs. Summary of the Invention

[0008] The purpose of this invention is to provide a cloud-based e-commerce data analysis method, system, and electronic device to address the shortcomings in the prior art.

[0009] To achieve the above objectives, the present invention provides the following technical solution: an e-commerce data analysis method based on a cloud platform, the analysis method comprising the following steps:

[0010] After the analysis system obtains the date of the next day, it analyzes whether the next day is a special date. If the analysis shows that the next day is a special date, it obtains multiple historical data of the special date based on the cloud platform, and then adjusts the server and storage resources based on the server and storage resource status of the day.

[0011] The analysis system acquires real-time data from the e-commerce platform the following day, and combines the real-time data with the results of the first adjustment to determine whether a second adjustment of server and storage resources is needed. On special dates, the e-commerce platform operates based on the server and storage resources after the first or second adjustment.

[0012] If the next day is not a special date, then analyze the status of the server and storage resources on that day to determine whether static adjustments to the server and storage resources are needed.

[0013] The real-time data acquired the following day is combined with the status of server and storage resources the following day to determine whether dynamic adjustment of server and storage resources is needed. On ordinary days, the e-commerce platform operates based on the initial state, static adjustment, or dynamic adjustment of server and storage resources.

[0014] In a preferred embodiment, adjusting the server and storage resources based on the server and storage resource status for the day includes the following steps:

[0015] Obtain multiple data points from several years prior to specific dates, including peak traffic variation factors and average page click-through rate;

[0016] Obtain the server's request timeout frequency and the memory's read / write latency frequency;

[0017] The first adjustment coefficient is obtained by comprehensively analyzing the traffic peak variation factor, average page click rate, request timeout frequency, and read / write latency frequency.

[0018] The initial number of servers and the initial number of storage devices are adjusted based on the first adjustment coefficient, and the expression is as follows: In the formula, fs c For the corrected number of servers, cs c fs is the corrected memory size. h For the initial number of servers, cs h tj is the initial memory size. one This is the first adjustment coefficient.

[0019] In a preferred embodiment, a first adjustment coefficient is obtained by comprehensively analyzing the traffic peak variation factor, average page click-through rate, request timeout frequency, and read / write latency frequency, and its expression is:

[0020] In the formula, tj one δ is the first adjustment coefficient, ε is the peak traffic variation factor, ε is the average page click-through rate, and τ is the request timeout frequency. e represents the read / write latency frequency. (δ+ε) For historical data, The data represents the state data, and α and β are the proportion coefficients of historical data and state data, respectively, both of which are greater than 0.

[0021] In a preferred embodiment, the analysis system acquires real-time data from the e-commerce platform the following day, and combines this real-time data with the results of the first adjustment to determine whether a second adjustment of the server and storage resources is needed. This includes the following steps:

[0022] The analysis system acquires real-time data from the e-commerce platform the following day. The real-time data includes traffic growth rate and user online growth rate. A correction index is obtained based on the traffic growth rate and user online growth rate.

[0023] The second adjustment coefficient is obtained by correcting the first adjustment coefficient using a correction index. The expression is: tj two =tj one *XZ, where tj two The second adjustment coefficient, tj one X is the first adjustment coefficient, and XZ is the correction index;

[0024] The correction index is compared with an index threshold. The index threshold is used to determine whether the corrected number of servers and the corrected number of storage devices need to be adjusted using a second adjustment coefficient. If the correction index is less than or equal to the index threshold, it is determined that the corrected number of servers and the corrected number of storage devices do not need to be adjusted using the second adjustment coefficient. If the correction index is greater than the index threshold, it is determined that the corrected number of servers and the corrected number of storage devices need to be adjusted using the second adjustment coefficient. The expression is as follows: In the formula, fs c For the corrected number of servers, cs c fs is the corrected memory size. ct The number of servers after the second correction, cs ct The number of memory units after secondary correction, tj two This is the second adjustment coefficient.

[0025] In a preferred embodiment, obtaining a correction index based on traffic growth rate and user online growth rate includes the following steps:

[0026] The traffic growth rate and the user online growth rate are normalized so that their values ​​are mapped to the range [0,1]. The normalized values ​​of the traffic growth rate and the user online growth rate are obtained. The correction index is obtained by summing the normalized values ​​of the traffic growth rate and the user online growth rate.

[0027] In a preferred embodiment, if the analyzed next day is not a special day, then after analyzing the status of the server and storage resources on that day, it is determined whether static adjustments to the server and storage resources are needed, including the following steps:

[0028] When the following day is not a special date, obtain the server's request timeout frequency and the memory's read / write latency frequency for that day;

[0029] The request timeout frequency and read / write latency frequency are normalized to obtain normalized values. The normalized values ​​are then summed to obtain an anomaly coefficient. This coefficient is compared with a first anomaly threshold. If the coefficient is less than or equal to the threshold, static adjustment of server and storage resources is deemed unnecessary. If the coefficient is greater than the threshold, static adjustment of server and storage resources is deemed necessary, and this adjustment is performed according to the static adjustment table.

[0030] In a preferred embodiment, the determination of whether dynamic adjustment of server and storage resources is needed by combining real-time data acquired the following day with the server and storage resource status of the following day includes the following steps:

[0031] Get real-time data for the next day, including traffic growth rate and user online growth rate; get the server request timeout frequency and memory read / write latency frequency for the next day.

[0032] The dynamic adjustment coefficients are calculated using a linear regression analysis algorithm based on the traffic growth rate, user online growth rate, request timeout frequency, and read / write latency frequency. The expression is as follows: In the formula, tj dynamic θ1, θ2, θ3, and θ4 are the dynamic adjustment coefficients, R is the influencing factor with a value of 1.513, θ1, θ2, θ3, and θ4 are the traffic growth rate, user online growth rate, request timeout frequency, and read / write latency frequency, respectively, and γ1, γ2, γ3, and γ4 are the regression coefficients, and the regression coefficients are greater than 0.

[0033] The dynamic adjustment coefficient is compared with the dynamic adjustment threshold. The dynamic adjustment threshold is used to predict the overall load change trend of the e-commerce platform. If the dynamic adjustment coefficient is less than or equal to the dynamic adjustment threshold, the e-commerce platform is predicted to have a low load trend. If the dynamic adjustment coefficient is greater than the dynamic adjustment threshold, the e-commerce platform is predicted to have a high load trend.

[0034] When the e-commerce platform is predicted to experience a high load trend, and no static adjustments are made to the initial number of servers and initial storage, the expression for adjusting using dynamic adjustment coefficients is as follows: In the formula, fs c For the corrected number of servers, cs c fs is the corrected memory size. h For the initial number of servers, cs h tj is the initial memory size. dynamic This is a dynamic adjustment coefficient;

[0035] When the overall e-commerce platform is predicted to experience a high load trend, and the initial number of servers and initial storage are statically adjusted, the expression for adjustment using dynamic adjustment coefficients is as follows: In the formula, fs c For the corrected number of servers, cs c fs is the corrected memory size. jh The number of servers after static adjustment, cs jh tj represents the number of memory units after static adjustment. dynamic This is the dynamic adjustment coefficient.

[0036] In a preferred embodiment, after the analysis system obtains the date of the following day, it analyzes whether the following day is a special date, including the following steps:

[0037] The analysis system obtains the date of the next day and retrieves all special dates from the e-commerce platform's special date library;

[0038] The obtained next day date is matched with the dates in the special date database. The determination of whether a date is a special date is made by directly comparing the dates.

[0039] If the next day's date matches a date or date range in a special date database, the analysis system marks the type of that date.

[0040] Based on the date matching results, the system outputs a judgment to determine whether the next day is a special date and its type. If it is a special date, the system returns information about the special date; otherwise, the system returns the corresponding status.

[0041] The cloud-based e-commerce data analysis system includes a date analysis module, a special date adjustment module, and a regular date adjustment module.

[0042] Date Analysis Module: After obtaining the date of the following day, analyze whether the following day is a special date;

[0043] Special Date Adjustment Module: When the analysis shows that the next day is a special date, after obtaining multiple historical data of the special date based on the cloud platform, the server and storage resources are adjusted once in combination with the server and storage resource status on that day. On the next day, the real-time data of the e-commerce platform is obtained, and the real-time data is analyzed together with the adjustment result to determine whether a second adjustment of the server and storage resources is needed.

[0044] Normal date adjustment module: When the next day's date is not a special date, it analyzes the status of the server and storage resources on that day to determine whether static adjustment of the server and storage resources is needed. It combines the real-time data obtained on the next day with the status of the server and storage resources on the next day to determine whether dynamic adjustment of the server and storage resources is needed.

[0045] An e-commerce data analysis electronic device based on a cloud platform includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of an e-commerce data analysis method based on a cloud platform.

[0046] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0047] This invention analyzes whether the following day is a special date. If the following day is a special date, it adjusts the server and storage resources based on the current day's server and storage resource status. Real-time data is then combined with the initial adjustment result to determine if a secondary adjustment is needed. If the following day is not a special date, the analysis of the current day's server and storage resource status determines if static adjustment is needed. Real-time data from the following day is then combined with the following day's server and storage resource status to determine if dynamic adjustment is needed. By using a cloud platform for traffic prediction, the platform's elastic scaling capabilities can dynamically adjust computing and storage resources according to business needs, preventing system crashes during peak periods and reducing resource investment during low-traffic periods, thereby optimizing costs. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0049] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] Example 1: Please refer to Figure 1 As shown in this embodiment, the e-commerce data analysis method based on a cloud platform includes the following steps:

[0052] After obtaining the date of the following day, the analysis system analyzes whether the following day is a special date. If the following day is a special date, it obtains historical data on special dates from the cloud platform and adjusts the server and storage resources based on the server and storage resource status of that day. The analysis system then obtains real-time data from the e-commerce platform on the following day and combines this real-time data with the adjustment result to determine whether a second adjustment of the server and storage resources is needed. On special dates, the e-commerce platform operates based on the server and storage resources adjusted in the first or second adjustment. If the following day is not a special date, the system analyzes the server and storage resource status of that day to determine whether static adjustment of the server and storage resources is needed. It then combines the real-time data obtained on the following day with the server and storage resource status of the following day to determine whether dynamic adjustment of the server and storage resources is needed. On ordinary dates, the e-commerce platform operates based on the initial state, the server and storage resources adjusted statically, or the server and storage resources adjusted dynamically.

[0053] This application analyzes whether the following day is a special date. If the following day is a special date, it adjusts the server and storage resources based on the server and storage resource status of that day. Real-time data is then combined with the adjustment result to determine if a secondary adjustment is needed. If the following day is not a special date, the application analyzes the server and storage resource status of that day to determine if static adjustment is needed. Real-time data from the following day is then combined with the server and storage resource status of that day to determine if dynamic adjustment is needed. By using a cloud platform for traffic prediction, the platform's elastic scaling capabilities can dynamically adjust computing and storage resources according to business needs, preventing system crashes during peak periods and reducing resource investment during low-traffic periods, thereby optimizing costs.

[0054] An e-commerce data analysis electronic device based on a cloud platform includes a memory, a processor, and a computer program stored on the memory and executable on the processor: the steps of implementing an e-commerce data analysis method based on a cloud platform when the processor executes the computer program.

[0055] Example 2: After the analysis system obtains the date of the following day, it analyzes whether the following day is a special date, including the following steps:

[0056] The analysis system obtains the date of the following day and retrieves all special dates that may affect business from the e-commerce platform's special date database. These special dates are typically categorized as follows:

[0057] Fixed holidays, shopping festivals, platform-customized promotional days, and seasonal events

[0058] By matching the obtained next day's date with dates in the special date database, it is possible to determine whether a date is a special date by directly comparing the dates.

[0059] Once the next day's date matches a date or date range in a special date library, the system needs to label the type of that date;

[0060] If the next day's date matches multiple specific dates, the system needs to determine the priority of these dates, using historical user traffic as the priority.

[0061] Based on the date matching results, determine whether the following day is a special date and its type. If it is a special date, return the specific information about that date; otherwise, the system should return the appropriate status, such as "normal date".

[0062] When the analysis indicates that the following day is a special date, after obtaining historical data on this special date from the cloud platform, adjustments are made to the server and storage resources based on the server and storage resource status on that day. This includes the following steps:

[0063] Obtain multiple data points from several years prior to specific dates, including peak traffic variation factors and average page click-through rate;

[0064] Obtain the server's request timeout frequency and the memory's read / write latency frequency;

[0065] The first adjustment coefficient is obtained by comprehensively analyzing the traffic peak variation factor, average page click-through rate, request timeout frequency, and read / write latency frequency. The expression is:

[0066] In the formula, tj one δ is the first adjustment coefficient, ε is the peak traffic variation factor, ε is the average page click-through rate, and τ is the request timeout frequency. e represents the read / write latency frequency. (δ+ε) For historical data, For state data, α and β are the proportion coefficients of historical data and state data, respectively, and both are greater than 0;

[0067] The larger the first adjustment coefficient, the greater the historical traffic peak change factor and average page click-through rate on special dates under comprehensive analysis. The higher the server request timeout frequency and storage read / write latency frequency the day before the special date, the more necessary it is to increase the number of servers and storage. The initial number of servers and storage is adjusted based on the first adjustment coefficient, expressed as: In the formula, fs c For the corrected number of servers, cs c fs is the corrected memory size. h For the initial number of servers, cs h tj is the initial memory size. one This is the first adjustment coefficient;

[0068] It should be noted that since the calculated corrected number of servers and corrected number of storage devices may contain decimals, in this application, when the corrected number of servers or corrected number of storage devices contains decimals, the decimals are rounded up to one place. For example, if the corrected number of servers is 2.12, then the corrected number of servers is rounded up to 3, and so on.

[0069] The analysis system acquires real-time data from the e-commerce platform the following day, and combines this real-time data with the results of the initial adjustment to determine whether a second adjustment to the server and storage resources is needed. This includes the following steps:

[0070] The analysis system acquires real-time data from the e-commerce platform the following day, including traffic growth rate and user online growth rate.

[0071] The traffic growth rate and the online user growth rate are normalized so that their values ​​are mapped to [0,1]. The normalized values ​​of the traffic growth rate and the online user growth rate are obtained. The normalized values ​​of the traffic growth rate and the online user growth rate are summed to obtain the correction index. The larger the correction index, the greater the increase in traffic and users of the e-commerce platform in a short period of time.

[0072] Therefore, the second adjustment coefficient is obtained by correcting the first adjustment coefficient using the correction index, and the expression is: tj two =tj one *XZ, where tj two The second adjustment coefficient, tj oneX is the first adjustment coefficient, and XZ is the correction index;

[0073] It should be noted that after obtaining the second adjustment coefficient, the corrected number of servers and the corrected number of storage devices cannot be directly adjusted using the second adjustment coefficient.

[0074] The correction index is compared with an index threshold. The index threshold is used to determine whether the corrected number of servers and the corrected number of storage devices need to be adjusted using a second adjustment coefficient. If the correction index is less than or equal to the index threshold, it is determined that the corrected number of servers and the corrected number of storage devices do not need to be adjusted using the second adjustment coefficient. If the correction index is greater than the index threshold, it is determined that the corrected number of servers and the corrected number of storage devices need to be adjusted using the second adjustment coefficient. The expression is as follows: In the formula, fs c For the corrected number of servers, cs c fs is the corrected memory size. ct The number of servers after the second correction, cs ct The number of memory units after secondary correction, tj two This is the second adjustment coefficient.

[0075] If the following day is not a special date, then analyze the server and storage resource status for that day to determine whether static adjustments to the server and storage resources are needed, including the following steps:

[0076] When the following day is not a special date, obtain the server's request timeout frequency and the memory's read / write latency frequency for that day;

[0077] The request timeout frequency and read / write latency frequency are normalized to obtain normalized values. These values ​​are then summed to obtain an anomaly coefficient. A larger anomaly coefficient indicates a worse state of the server and storage on that day. The anomaly coefficient is compared to a first anomaly threshold. If the anomaly coefficient is less than or equal to the first anomaly threshold, it is determined that no static adjustment of the server and storage resources is needed. If the anomaly coefficient is greater than the first anomaly threshold, it is determined that static adjustment of the server and storage resources is needed, and static adjustment is performed on the server and storage resources according to the static adjustment table, as shown in Table 1.

[0078] Table 1 Static Adjustment Table

[0079]

[0080] In Table 1, yc is the anomaly coefficient, yz1 is the first anomaly threshold, yz2 is the second anomaly threshold, yz3 is the third anomaly threshold, yz4 is the fourth anomaly threshold, yz5 is the fifth anomaly threshold, and yz... n-1 For the (n-1)th abnormal threshold, yz n The nth abnormal threshold;

[0081] As shown in Table 1, the increase in the number of initial servers and the number of initial storage devices varies at different gradients. The larger the anomaly coefficient, the greater the increase in the number of initial servers and the number of initial storage devices.

[0082] The process involves combining real-time data acquired the following day with the server and storage resource status of the following day to determine whether dynamic adjustments to the server and storage resources are necessary. This includes the following steps:

[0083] Get real-time data for the next day, including traffic growth rate and user online growth rate. Get the server request timeout frequency and memory read / write latency frequency for the next day (get in real time).

[0084] The dynamic adjustment coefficients are calculated using a linear regression analysis algorithm based on the traffic growth rate, user online growth rate, request timeout frequency, and read / write latency frequency. The expression is as follows: In the formula, ij dynamic θ1, θ2, θ3, and θ4 are the dynamic adjustment coefficients, R is the influencing factor with a value of 1.513, θ1, θ2, θ3, and θ4 are the traffic growth rate, user online growth rate, request timeout frequency, and read / write latency frequency, respectively, and γ1, γ2, γ3, and γ4 are the regression coefficients, and the regression coefficients are greater than 0.

[0085] In this application, since the dynamic adjustment coefficient is obtained in real time, the overall load change trend of the e-commerce platform is predicted by the dynamic adjustment coefficient.

[0086] The dynamic adjustment coefficient is compared with the dynamic adjustment threshold. The dynamic adjustment threshold is used to predict the overall load change trend of the e-commerce platform. If the dynamic adjustment coefficient is less than or equal to the dynamic adjustment threshold, the e-commerce platform is predicted to have a low load trend. If the dynamic adjustment coefficient is greater than the dynamic adjustment threshold, the e-commerce platform is predicted to have a high load trend.

[0087] When the e-commerce platform is predicted to experience a high load trend, and no static adjustments are made to the initial number of servers and initial storage, the expression for adjusting using dynamic adjustment coefficients is as follows: In the formula, fs c For the corrected number of servers, cs c fs is the corrected memory size. h For the initial number of servers, csh tj is the initial memory size. dynamic This is a dynamic adjustment coefficient;

[0088] When the overall e-commerce platform is predicted to experience a high load trend, and the initial number of servers and initial storage are statically adjusted, the expression for adjustment using dynamic adjustment coefficients is as follows: In the formula, fs c For the corrected number of servers, cs c fs is the corrected memory size. jh The number of servers after static adjustment, cs jh tj represents the number of memory units after static adjustment. dynamic This is the dynamic adjustment coefficient.

[0089] In this application,

[0090] The calculation logic of the peak traffic variation factor is as follows: obtain the peak traffic on special dates in the previous few years (e.g., the previous five years), establish a dataset of the peak traffic on special dates in the previous few years, calculate the average peak traffic and the standard deviation of the peak traffic in the dataset (the calculation method is existing technology and will not be described in detail in this application), and obtain the peak traffic variation factor by dividing the average peak traffic by the standard deviation of the peak traffic. The larger the peak traffic variation factor, the larger the peak traffic on special dates in the previous few years and the smaller the fluctuation, that is, the larger and more stable the overall peak traffic on special dates in the previous few years.

[0091] The calculation logic for average page click-through rate (CTR) is as follows: After obtaining the page CTR for specific dates in previous years (e.g., the previous five years), the average CTR is calculated. The higher the average CTR, the higher the overall historical page CTR for specific dates. The calculation logic for page CTR is as follows: After obtaining the number of pages in the e-commerce platform and the number of clicks for each page, the number of clicks for all pages is summed to obtain the total number of clicks. After obtaining the number of impressions for each page, the number of impressions for all pages is summed to obtain the total number of impressions. The page CTR is obtained by dividing the total number of clicks by the total number of impressions.

[0092] The calculation logic for request timeout frequency is as follows: obtain the number of request timeouts and the total number of requests within a certain time period, and divide the number of request timeouts by the total number of requests to obtain the request timeout frequency. The higher the request timeout frequency, the worse the server's response capability.

[0093] The calculation logic for read / write latency frequency is as follows: obtain the total number of read / write operations and the number of read / write latency operations in a certain time period, and obtain the read / write latency frequency by dividing the number of read / write latency operations by the total number of read / write operations. The read / write latency frequency indicates the proportion of memory latency.

[0094] The calculation logic for the traffic growth rate is as follows: subtract the traffic from the previous time period to obtain the traffic difference, subtract the previous time period to obtain the monitoring duration, and then divide the traffic difference by the monitoring duration to obtain the traffic growth rate.

[0095] The calculation logic for the user online growth rate is as follows: subtract the number of online users in the previous time period from the number of online users in the current time period to obtain the user difference, subtract the previous time period from the current time period to obtain the monitoring duration, and obtain the user online growth rate by dividing the user difference by the monitoring duration.

[0096] Example 3: The e-commerce data analysis system based on the cloud platform described in this example includes a date analysis module, a special date adjustment module, and a normal date adjustment module;

[0097] Date Analysis Module: After obtaining the date of the next day, analyze whether the next day is a special date, and send the analysis results to the special date adjustment module and the ordinary date adjustment module;

[0098] Special Date Adjustment Module: When the analysis shows that the next day is a special date, the module obtains historical data on the special date from the cloud platform and adjusts the server and storage resources based on the server and storage resource status on that day. On the next day, the module obtains real-time data from the e-commerce platform and analyzes it together with the results of the first adjustment to determine whether a second adjustment of the server and storage resources is needed. On the special date, the e-commerce platform operates based on the server and storage resources after the first or second adjustment.

[0099] Normal Date Adjustment Module: When the following day is not a special date, the module analyzes the status of the server and storage resources on that day to determine whether static adjustment of the server and storage resources is required. It combines the real-time data obtained on the following day with the status of the server and storage resources on the following day to determine whether dynamic adjustment of the server and storage resources is required. On normal dates, the e-commerce platform operates based on the initial state, static adjustment, or dynamic adjustment of the server and storage resources.

[0100] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0101] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0102] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A cloud-based e-commerce data analysis method, characterized by: The analytical method includes the following steps: After the analysis system obtains the date of the next day, it analyzes whether the next day is a special date. If the analysis shows that the next day is a special date, it obtains multiple historical data of the special date based on the cloud platform, and then adjusts the server and storage resources based on the server and storage resource status of the day. The analysis system acquires real-time data from the e-commerce platform the following day, and combines the real-time data with the results of the first adjustment to determine whether a second adjustment of server and storage resources is needed. On special dates, the e-commerce platform operates based on the server and storage resources after the first or second adjustment. If the next day is not a special date, then analyze the status of the server and storage resources on that day to determine whether static adjustments to the server and storage resources are needed. The real-time data acquired the following day is combined with the status of the server and storage resources the following day to determine whether dynamic adjustment of the server and storage resources is needed. On ordinary days, the e-commerce platform operates based on the initial state, static adjustment, or dynamic adjustment of the server and storage resources. Adjust the server and storage resources based on the status of the server and storage resources on that day, including the following steps: Obtain multiple data points from several years prior to specific dates, including traffic peak variation factors and average page click-through rate; Obtain the server's request timeout frequency and the memory's read / write latency frequency; The first adjustment coefficient is obtained by comprehensively analyzing the traffic peak variation factor, average page click rate, request timeout frequency, and read / write latency frequency. The initial number of servers and the initial number of storage devices are adjusted based on the first adjustment coefficient, and the expression is as follows: In the formula, fs c For the corrected number of servers, cs c fs is the corrected memory size. h For the initial number of servers, cs h tj is the initial memory size. one The first adjustment coefficient is expressed as: In the formula, tj one δ is the first adjustment coefficient, ε is the peak traffic variation factor, ε is the average page click-through rate, and τ is the request timeout frequency. e represents the read / write latency frequency. (δ+ε) For historical data, The data represents the state data, and α and β are the proportion coefficients of historical data and state data, respectively, both of which are greater than 0.

2. The e-commerce data analysis method based on a cloud platform according to claim 1, characterized in that: The analysis system acquires real-time data from the e-commerce platform the following day, and combines this real-time data with the results of the initial adjustment to determine whether a second adjustment to the server and storage resources is needed. This includes the following steps: The analysis system acquires real-time data from the e-commerce platform the following day. The real-time data includes traffic growth rate and user online growth rate. A correction index is obtained based on the traffic growth rate and user online growth rate. The second adjustment coefficient is obtained by correcting the first adjustment coefficient using a correction index. The expression is: tj two =tj one *XZ, where tj two tj is the second adjustment coefficient. one X is the first adjustment coefficient, and XZ is the correction index; The correction index is compared with an index threshold. The index threshold is used to determine whether the corrected number of servers and the corrected number of storage devices need to be adjusted using a second adjustment coefficient. If the correction index is less than or equal to the index threshold, it is determined that the corrected number of servers and the corrected number of storage devices do not need to be adjusted using the second adjustment coefficient. If the correction index is greater than the index threshold, it is determined that the corrected number of servers and the corrected number of storage devices need to be adjusted using the second adjustment coefficient. The expression is as follows: In the formula, fs c For the corrected number of servers, cs c fs is the corrected memory size. ct The number of servers after the second correction, cs ct The number of memory units after secondary correction, tj two This is the second adjustment coefficient.

3. The e-commerce data analysis method based on a cloud platform according to claim 2, characterized in that: The correction index is obtained based on the traffic growth rate and the user online growth rate, including the following steps: The traffic growth rate and the user online growth rate are normalized so that their values ​​are mapped to the range [0,1]. The normalized values ​​of the traffic growth rate and the user online growth rate are obtained. The correction index is obtained by summing the normalized values ​​of the traffic growth rate and the user online growth rate.

4. The e-commerce data analysis method based on a cloud platform according to claim 1, characterized in that: If the following day is not a special date, then analyze the server and storage resource status for that day to determine whether static adjustments to the server and storage resources are needed, including the following steps: When the following day is not a special date, obtain the server's request timeout frequency and the memory's read / write latency frequency for that day; The request timeout frequency and read / write latency frequency are normalized to obtain normalized values. The normalized values ​​are then summed to obtain an anomaly coefficient. This coefficient is compared with a first anomaly threshold. If the coefficient is less than or equal to the threshold, static adjustment of server and storage resources is deemed unnecessary. If the coefficient is greater than the threshold, static adjustment of server and storage resources is deemed necessary, and this adjustment is performed according to the static adjustment table.

5. The e-commerce data analysis method based on a cloud platform according to claim 4, characterized in that: The process involves combining real-time data acquired the following day with the server and storage resource status of the following day to determine whether dynamic adjustments to the server and storage resources are necessary. This includes the following steps: Get real-time data for the next day, including traffic growth rate and user online growth rate; get the server request timeout frequency and memory read / write latency frequency for the next day. The dynamic adjustment coefficients are calculated using a linear regression analysis algorithm based on the traffic growth rate, user online growth rate, request timeout frequency, and read / write latency frequency. The expression is as follows: In the formula, tj dynamic θ1, θ2, θ3, and θ4 are the dynamic adjustment coefficients, R is the influencing factor with a value of 1.513, θ1, θ2, θ3, and θ4 are the traffic growth rate, user online growth rate, request timeout frequency, and read / write latency frequency, respectively, and γ1, γ2, γ3, and γ4 are the regression coefficients, and the regression coefficients are greater than 0. The dynamic adjustment coefficient is compared with the dynamic adjustment threshold. The dynamic adjustment threshold is used to predict the overall load change trend of the e-commerce platform. If the dynamic adjustment coefficient is less than or equal to the dynamic adjustment threshold, the e-commerce platform is predicted to have a low load trend. If the dynamic adjustment coefficient is greater than the dynamic adjustment threshold, the e-commerce platform is predicted to have a high load trend. When the e-commerce platform is predicted to experience a high load trend, and no static adjustments are made to the initial number of servers and initial storage, the expression for adjusting using dynamic adjustment coefficients is as follows: In the formula, fs c For the corrected number of servers, cs c fs is the corrected memory size. h For the initial number of servers, cs h tj is the initial memory size. dynamic This is a dynamic adjustment coefficient; When the overall e-commerce platform is predicted to experience a high load trend, and the initial number of servers and initial storage are statically adjusted, the expression for adjustment using dynamic adjustment coefficients is as follows: In the formula, fs c For the corrected number of servers, cs c fs is the corrected memory size. jh The number of servers after static adjustment, cs jh tj represents the number of memory units after static adjustment. dynamic This is the dynamic adjustment coefficient.

6. The e-commerce data analysis method based on a cloud platform according to claim 5, characterized in that: After the analysis system obtains the date of the following day, it analyzes whether the following day is a special date, including the following steps: The analysis system obtains the date of the next day and retrieves all special dates from the e-commerce platform's special date library; The obtained next day date is matched with the dates in the special date database. The determination of whether a date is a special date is made by directly comparing the dates. If the next day's date matches a date or date range in a special date database, the analysis system marks the type of that date. Based on the date matching results, the system outputs a judgment to determine whether the next day is a special date and its type. If it is a special date, the system returns information about the special date; otherwise, the system returns the corresponding status.

7. A cloud-based e-commerce data analysis system, used to implement the cloud-based e-commerce data analysis method according to any one of claims 1-6, characterized in that: Includes a date analysis module, a special date adjustment module, and a regular date adjustment module; Date Analysis Module: After obtaining the date of the following day, analyze whether the following day is a special date; Special Date Adjustment Module: When the analysis shows that the next day is a special date, after obtaining multiple historical data of the special date based on the cloud platform, the server and storage resources are adjusted once in combination with the server and storage resource status on that day. On the next day, the real-time data of the e-commerce platform is obtained, and the real-time data is analyzed together with the adjustment result to determine whether a second adjustment of the server and storage resources is needed. Normal date adjustment module: When the next day's date is not a special date, it analyzes the status of the server and storage resources on that day to determine whether static adjustment of the server and storage resources is needed. It combines the real-time data obtained on the next day with the status of the server and storage resources on the next day to determine whether dynamic adjustment of the server and storage resources is needed.

8. An e-commerce data analysis electronic device based on a cloud platform, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the steps of the cloud-based e-commerce data analysis method as described in any one of claims 1-6.

Images