Erp background management method and system based on multi-user shopping mall

Abstract

The invention discloses an erp background management method and system based on a multi-user shopping mall, and relates to the technical field of e-commerce, and the method comprises the steps: constructing an elastic extension mechanism based on a cloud architecture, and enabling the elastic extension mechanism to dynamically adjust server resources through monitoring the real-time load data of an erp background management system according to a server resource distribution strategy; a machine learning model is adopted to analyze merchant historical data and generate a behavior prediction result, and a server resource allocation strategy is optimized according to the behavior prediction result; developing an intelligent erp configuration recommendation system based on a deep reinforcement learning algorithm, wherein the intelligent erp configuration recommendation system automatically identifies a merchant business mode by using a behavior prediction result and generates a personalized erp management configuration suggestion; a multi-channel payment interface and a logistics API are integrated, payment and logistics strategies are automatically selected according to personalized erp management configuration suggestions, and a unified order management process is constructed. The performance, the resource utilization efficiency and the intelligent degree of the multi-user shopping mall ERP background management system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to an ERP background management method and system based on a multi-user mall. Background Art

[0002] With the rapid development of e-commerce, multi-user malls are becoming increasingly popular as a new business model. In order to effectively manage this complex business ecosystem, the enterprise resource planning (ERP) system plays a vital role in the backend management of multi-user malls. Traditional ERP systems mainly focus on resource integration and process optimization of a single enterprise, while in a multi-user mall environment, ERP systems face more complex challenges. These challenges include but are not limited to: dynamic allocation of multi-merchant resources, real-time synchronization of cross-platform data, personalized merchant management needs, and processing of large-scale concurrent transactions. Existing ERP backend management systems often seem to be unable to cope with these challenges, especially in terms of elastic resource expansion, intelligent configuration, and global order management.

[0003] The existing multi-user mall erp backend management system usually adopts a static resource allocation strategy, which is difficult to adapt to the dynamic changes of the mall business. At the same time, these systems lack the ability to deeply analyze and predict the merchant's historical data, and cannot provide merchants with personalized erp configuration suggestions. In addition, in terms of order management, the existing systems often separate functions such as payment and logistics, lack a unified management process, resulting in low order processing efficiency and poor user experience. These problems seriously restrict the operational efficiency and expansion capabilities of multi-user malls, and a new erp backend management solution is urgently needed. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: how to provide an ERP background management method based on a multi-user mall?

[0006] To solve the above technical problems, the present invention provides the following technical solutions: an ERP backend management method based on a multi-user mall, comprising: building an elastic expansion mechanism based on a cloud architecture, the elastic expansion mechanism dynamically adjusts server resources according to the server resource allocation strategy by monitoring the real-time load data of the ERP backend management system; using a machine learning model to analyze merchant historical data and generate behavior prediction results, and optimizing the server resource allocation strategy according to the behavior prediction results; developing an intelligent ERP configuration recommendation system based on a deep reinforcement learning algorithm, the intelligent ERP configuration recommendation system automatically identifies the merchant business model using the behavior prediction results and generates personalized ERP management configuration suggestions; integrating multi-channel payment interfaces and logistics APIs, and automatically selecting payment and logistics strategies according to the personalized ERP management configuration suggestions to build a unified order management process.

[0007] As a preferred solution of the ERP background management method based on the multi-user mall described in the present invention, wherein: an elastic expansion mechanism based on cloud architecture is constructed, and the elastic expansion mechanism dynamically adjusts server resources according to the server resource allocation strategy by monitoring the real-time load data of the ERP background management system, including the following steps: constructing a distributed load monitoring system based on cloud architecture, and collecting various real-time load data of the server cluster through the distributed load monitoring system; formulating a server resource allocation strategy; the server resource allocation strategy includes a resource utilization threshold and a resource adjustment rule; establishing a multi-dimensional resource scoring model; the multi-dimensional resource scoring model calculates the server resource utilization score according to the real-time load data; comparing the server resource utilization score with the resource utilization threshold, when the server resource utilization score exceeds the resource utilization threshold, triggering resource adjustment; after the resource adjustment is triggered, dynamically increasing or decreasing the number of server instances according to the resource adjustment rule, adjusting the computing resource allocation, and completing the elastic expansion mechanism of server resources.

[0008] As a preferred solution of the ERP background management method based on a multi-user mall described in the present invention, each of the real-time load data corresponds to a type of resource; the resource utilization threshold includes a dynamic high threshold and a dynamic low threshold; the resource adjustment rules include resource expansion rules, resource contraction rules, intelligent reservation rules, and elastic adjustment rules; wherein, the resource expansion rule is that when the resource utilization of a certain type of real-time load data exceeds its dynamic high threshold for T1 consecutive minutes, resource expansion is triggered, and the expansion amount is: the resource amount of the current real-time load data * (resource utilization of the current real-time load data - dynamic high threshold) / dynamic high threshold, rounded up, but not less than the minimum expansion unit; the resource contraction rule is that when the resource utilization of a certain type of real-time load data is lower than its dynamic low threshold for T2 consecutive minutes, resource contraction is triggered, and the contraction amount is: the current The resource volume of real-time load data * (dynamic low threshold - resource utilization of current real-time load data) / dynamic low threshold, rounded up, but not less than the minimum contraction unit; the intelligent reservation rule is that when the erp background management system predicts that the resource demand within the preset time will exceed the current capacity, that is, the total available resources, the reserved resource volume is: predicted peak usage * (1 + safety factor) + volatility coefficient * historical fluctuation range; the elastic adjustment rule is that if the number of resource adjustments in the last M hours is greater than the preset number, the new resource utilization threshold = original resource utilization threshold * (1 + X%); the multi-dimensional resource scoring model calculates the ratio of the current usage of each real-time load data to the maximum capacity, multiplies it by the weight of each real-time load data, adds the weighted resource utilization of all real-time load data, and obtains the score as the server resource utilization score.

[0009] As a preferred solution of the ERP backend management method based on a multi-user mall described in the present invention, wherein: a machine learning model is used to analyze merchant historical data and generate behavior prediction results, and the server resource allocation strategy is optimized according to the behavior prediction results, including the following steps: collecting merchant historical data and preprocessing; the merchant historical data includes order volume, transaction amount, access traffic, inventory changes and seasonal fluctuations; a time series prediction model is constructed based on the long short-term memory network algorithm LSTM and the attention mechanism, and the preprocessed merchant historical data is trained by the time series prediction model; the merchant behavior prediction results are generated by the time series prediction model; the merchant behavior prediction results include expected order volume, transaction amount and access traffic; according to the merchant behavior prediction results, the server resource allocation strategy is adjusted; wherein adjusting the server resource allocation strategy includes updating resource utilization thresholds, optimizing resource adjustment rules and formulating resource reservation plans.

[0010] As a preferred solution of the ERP background management method based on a multi-user mall described in the present invention, wherein: the intelligent ERP configuration recommendation system is developed based on the deep reinforcement learning algorithm, and the intelligent ERP configuration recommendation system uses the behavior prediction results to automatically identify the merchant business model and generate personalized ERP management configuration suggestions, including the following steps: constructing a merchant business model feature matrix containing the merchant behavior prediction results, historical ERP usage data and commodity category information; constructing a multi-task deep neural network model, which includes a shared layer and multiple task-specific layers, wherein the shared layer is used to extract the common features of the merchant business, and the multiple task-specific layers are used for merchant business model recognition and EPR configuration respectively. Parameter prediction; using the transfer learning method, using the pre-trained e-commerce knowledge graph to initialize the multi-task deep neural network model parameters; training the initialized multi-task deep neural network model based on the merchant business model feature matrix to obtain a trained multi-task deep neural network model for merchant business model recognition and erp configuration parameter prediction; using the merchant business model feature matrix as input, passing it into the trained multi-task deep neural network model, extracting the common features of the merchant business through the shared layer, and then using the task-specific layer for merchant business model recognition to perform merchant business model recognition, and using the task-specific layer for erp configuration parameter prediction to generate corresponding personalized erp management configuration suggestions.

[0011] As a preferred solution of the ERP background management method based on a multi-user mall described in the present invention, wherein: the integrated multi-channel payment interface and logistics API, and the automatic selection of payment and logistics strategies according to the personalized ERP management configuration suggestions, to build a unified order management process, includes the following steps: integrating multiple third-party payment platform APIs and logistics service provider APIs; establishing a payment and logistics strategy database, and storing the payment and logistics parameters in the personalized ERP management configuration suggestions into the logistics strategy database; building an order processing module; building an order status tracking system, and the order status tracking system obtains the payment status and logistics information of the order in real time; and building a unified order management interface.

[0012] As a preferred solution of the ERP background management method based on a multi-user mall described in the present invention, the real-time load data includes CPU, memory, network bandwidth, and disk I / O.

[0013] To further solve the above technical problems, the present invention provides the following technical solutions: an ERP backend management system based on a multi-user mall, comprising: an elastic resource management module, used to build an elastic expansion mechanism based on a cloud architecture, the elastic expansion mechanism dynamically adjusts server resources according to the server resource allocation strategy by monitoring the real-time load data of the ERP backend management system; a prediction optimization module, used to use a machine learning model to analyze merchant historical data and generate behavior prediction results, and optimize the server resource allocation strategy according to the behavior prediction results; an intelligent ERP configuration recommendation module, used to develop an intelligent ERP configuration recommendation system based on a deep reinforcement learning algorithm, the intelligent ERP configuration recommendation system uses the behavior prediction results to automatically identify the merchant business model and generate personalized ERP management configuration suggestions; a unified order management module, used to integrate multi-channel payment interfaces and logistics APIs, and automatically select payment and logistics strategies according to the personalized ERP management configuration suggestions to build a unified order management process.

[0014] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the ERP background management method based on a multi-user mall as described above are implemented.

[0015] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the ERP background management method based on a multi-user mall as described above are implemented.

[0016] Beneficial effects of the present invention: The present invention provides a multi-user mall ERP background management method based on cloud architecture, which realizes intelligent and dynamic server resource allocation by building an elastic expansion mechanism, and effectively copes with load fluctuations. The method uses a machine learning model to analyze merchant historical data, generate behavior prediction results, optimize resource allocation strategies, and improve the foresight and adaptability of the system. At the same time, the intelligent ERP configuration recommendation system developed based on the deep reinforcement learning algorithm can automatically identify the merchant business model and generate personalized management configuration suggestions, greatly improving the intelligence level of the system. In addition, by integrating multi-channel payment interfaces and logistics APIs, a unified order management process is constructed, which realizes the automatic selection of payment and logistics strategies, as well as efficient management of the entire life cycle of orders. This comprehensive solution not only significantly improves resource utilization efficiency and system performance, but also better meets the personalized needs of different merchants, provides strong technical support for the operation and management of multi-user malls, and effectively improves user experience and operational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 The present invention provides an overall flow chart of an ERP backend management method based on a multi-user mall according to an embodiment of the present invention.

[0019] Figure 2 This is a computer equipment diagram of the ERP background management method based on a multi-user mall of the present invention. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides an ERP background management method based on a multi-user mall.

[0023] In view of the problems of inflexible resource allocation, lack of intelligent configuration, and decentralized order management process in the existing multi-user mall erp background management technology, the present invention proposes an erp background management method and system based on a multi-user mall. The method aims to solve the above problems by constructing an elastic expansion mechanism based on cloud architecture, using machine learning models to predict merchant behavior, developing an intelligent erp configuration recommendation system, and integrating multi-channel payment and logistics API. The present invention belongs to the field of e-commerce technology and enterprise resource planning system, and provides new technical support for the efficient operation and intelligent management of multi-user malls.

[0024] S1: Build an elastic expansion mechanism based on cloud architecture. The elastic expansion mechanism dynamically adjusts server resources according to the server resource allocation strategy by monitoring the real-time load data of the ERP background management system.

[0025] S1.1: Build a distributed load monitoring system based on cloud architecture, and collect real-time load data such as CPU utilization, memory occupancy, network throughput, and disk I / O of the server cluster through the distributed load monitoring system.

[0026] Specifically, in the present invention, the distributed load monitoring system based on cloud architecture is the basis of the entire elastic expansion mechanism. It adopts a distributed architecture and deploys multiple monitoring nodes in a cloud environment to achieve real-time and efficient monitoring of large-scale server clusters. Each monitoring node is responsible for collecting real-time load data such as CPU utilization, memory occupancy, network throughput and disk I / O of servers under its jurisdiction. These real-time load data are transmitted to the central data processing unit through a secure network channel, where they are summarized, cleaned and preliminarily analyzed. The distributed load monitoring system adopts a lightweight data acquisition agent to minimize the impact on the performance of the monitored server. At the same time, in order to cope with the challenges of large-scale data processing, the distributed load monitoring system integrates stream processing technology and can process massive monitoring data in real time. In addition, the system also has an adaptive sampling rate adjustment function, which can dynamically adjust the data acquisition frequency according to the load situation, and optimize the use of system resources while ensuring monitoring accuracy. In order to improve reliability, the distributed load monitoring system adopts a multi-copy data storage and fault automatic switching mechanism to ensure that accurate monitoring data can be continuously provided when some nodes fail. The distributed load monitoring system provided by the present invention provides a reliable data basis for subsequent resource evaluation and dynamic adjustment, and is a key component for realizing intelligent resource management.

[0027] S1.2: Formulate a server resource allocation strategy. The server resource allocation strategy includes resource utilization thresholds and resource adjustment rules.

[0028] Specifically, the server resource allocation strategy is a method for dynamically adjusting cloud server resources, aiming to optimize resource utilization efficiency and system performance. In the ERP backend management system of the multi-user mall provided by the present invention, the server resource allocation strategy needs to cope with load changes in different time periods, such as traffic surges during promotions or load fluctuations in daily operations, so the server resource allocation strategy plays an important role.

[0029] In this embodiment, the resource utilization threshold is set dynamically, and the resource utilization threshold includes a dynamic high threshold and a dynamic low threshold. Before setting the resource utilization threshold, it is necessary to determine the baseline threshold, which also includes a baseline high threshold and a baseline low threshold. The baseline threshold is usually determined based on the experience of the system administrator or historical data analysis. By setting different baseline thresholds for different types of resources (i.e., real-time load data: CPU, memory, network bandwidth, disk I / O), resource allocation can be controlled more finely. In one embodiment, the setting rules of the baseline threshold can be: a) CPU utilization is set lower to retain sufficient processing power to cope with burst requests. b) Memory utilization is slightly higher because memory resources are generally easier to expand quickly. c) The network bandwidth threshold is moderate to ensure a good response speed. d) The disk I / O threshold is lower because I / O operations are generally performance bottlenecks.

[0030] Exemplarily, based on setting rules, the baseline high thresholds of these resource types may be: CPU utilization threshold: 75%, memory utilization threshold: 80%, network bandwidth utilization threshold: 70%, and disk I / O utilization threshold: 60%.

[0031] Specifically, the calculation formula of the dynamic high threshold is:

[0032] Dynamic high threshold = benchmark high threshold + α*standard deviation + β*trend factor;

[0033] The calculation formula for the dynamic low threshold is:

[0034] Dynamic low threshold = benchmark low threshold - α*standard deviation - β*trend factor;

[0035] It should be noted that the trend factor refers to an indicator that reflects the trend of resource utilization changes. This embodiment uses the resource utilization data of a certain type of real-time load data at the latest N time points, and obtains the slope through linear regression as the trend factor. α and β represent the weight of the standard deviation and the weight of the trend factor, respectively. The standard deviation refers to the standard deviation of the resource utilization of a certain type of real-time load data.

[0036] Furthermore, resource adjustment rules include resource expansion rules, resource contraction rules, intelligent reservation rules, and elastic adjustment rules.

[0037] Resource expansion rules: When the resource utilization of a certain type of real-time load data exceeds its dynamic high threshold for T1 consecutive minutes, resource expansion is triggered. The expansion amount is: the resource amount of the current real-time load data * (resource utilization of the current real-time load data - dynamic high threshold) / dynamic high threshold, rounded up, but not less than the minimum expansion unit.

[0038] Resource shrinkage rule: When the resource utilization of a certain type of real-time load data is lower than its dynamic low threshold for T2 consecutive minutes, resource shrinkage is triggered, and the shrinkage amount is:

[0039] Resource amount of current real-time load data * (dynamic low threshold - resource utilization of current real-time load data) / dynamic low threshold, rounded up but not less than the minimum contraction unit.

[0040] Smart reservation rule: When the resource demand within the preset time of the ERP background management system (for example, predicting the next N hours) will exceed the total available resources, the reserved resource amount is: predicted peak usage * (1 + safety factor) + volatility coefficient * historical fluctuation range; among them, the safety factor is a value greater than 0, which is used to add a certain proportion of additional resources based on the prediction to deal with potential prediction errors; the volatility coefficient is a weight factor used to adjust the impact of historical fluctuations on reserved resources; the historical fluctuation range refers to the range of changes in resource usage over a period of time in the past.

[0041] Elastic adjustment rules: If the number of resource adjustments in the last M hours is greater than the preset number, the new resource utilization threshold = the original resource utilization threshold * (1 + X%) to reduce frequent adjustments.

[0042] S1.3: Establish a multi-dimensional resource scoring model. The multi-dimensional resource scoring model calculates the server resource utilization score based on the real-time load data collected in S1.1.

[0043] Specifically, the multi-dimensional resource scoring model calculates the ratio of the current usage of each real-time load data to the maximum capacity, then multiplies it by the weight of each real-time load data, and finally adds up the weighted resource utilization of all real-time load data to obtain the score as the server resource utilization score. This server resource utilization score reflects the overall resource usage of the server. The formula is:

[0044]

[0045] Where S is the server resource utilization score; n is the number of resource types considered (such as CPU, memory, network, disk I / O, etc.); w i is the weight of the ith resource, and R i is the current usage of the i-th resource; R i,max is the maximum capacity of the ith resource.

[0046] It should be noted that, in this embodiment, the application layer response time can also be regarded as the n+1th “resource”, that is, as an additional item in the formula:

[0047]

[0048] Among them, w app is the weight of the application layer indicator; T current is the current response time; T target is the target response time.

[0049] By extending the calculation of server resource utilization scores by treating application layer response time as the n+1th "resource", a more comprehensive and intelligent resource allocation strategy can be implemented in the ERP backend management system of the multi-user mall. Because the response speed of the system directly affects the user experience and transaction completion rate in the e-commerce environment, it is crucial to include it in the resource allocation decision. With this extension, the ERP backend management system not only considers the traditional hardware resource utilization (such as CPU, memory, storage and network), but also takes into account the performance indicators at the software level. This means that even if the hardware resources are not under high load, if the application layer response time slows down, the ERP backend management system can detect and make adjustments in time. For example, during a promotion, there may be a large number of concurrent requests that cause the response time to increase, but the CPU and memory utilization have not reached the threshold. In this case, the traditional resource allocation strategy may not be able to respond in time, and the extended multi-dimensional resource scoring model can trigger resource expansion more quickly to ensure user experience. In addition, the addition of this additional item also provides the ERP backend management system with more refined tuning capabilities. Administrators can balance the relationship between hardware resource utilization and software performance by adjusting the weights of application layer indicators to better meet the needs of specific business scenarios. For example, for modules that process high-value transactions, a higher weight can be given to response time to ensure that these critical operations receive more resource guarantees.

[0050] This method of comprehensively considering hardware and software performance makes the resource allocation strategy closer to actual business needs, can better cope with the dynamic load characteristics of the e-commerce platform, and improve the overall efficiency of the system and user satisfaction. At the same time, it also provides an extensible framework for the introduction of more application layer indicators (such as transaction processing speed, query response time, etc.) in the future, so that the resource allocation strategy can be continuously evolved and optimized to adapt to changing business needs.

[0051] S1.4: Compare the server resource utilization score calculated in S1.3 with the resource utilization threshold in S1.2. When the server resource utilization score exceeds the resource utilization threshold, trigger resource adjustment.

[0052] S1.5: After the resource adjustment is triggered, the number of server instances is dynamically increased or decreased according to the resource adjustment rules in S1.2, and the computing resource allocation is adjusted to achieve elastic expansion of server resources.

[0053] Preferably, S1 implements an intelligent and dynamic server resource allocation strategy by building an elastic expansion mechanism based on cloud architecture. First, the distributed load monitoring system is used to collect multi-dimensional resource usage data in real time, providing a comprehensive and accurate basis for decision-making. Secondly, by introducing a dynamic threshold system and a multi-dimensional resource scoring model, the erp backend management system can flexibly adjust the resource allocation strategy according to the real-time load situation and historical trends, and effectively respond to load fluctuations. In particular, the application layer response time is incorporated into the scoring model, so that resource allocation is more in line with actual business needs and can respond to changes in user experience in a timely manner. In addition, the intelligent reservation rules and elastic adjustment rules further enhance the forward-looking and stability of the system, and can effectively prevent the problem of insufficient or over-allocation of resources. This method of comprehensively considering hardware resource utilization and software performance indicators not only improves resource utilization efficiency, but also significantly improves the system's adaptability in the face of complex and changeable load conditions, especially for application scenarios with high concurrency and large load fluctuations such as e-commerce platforms. In general, this solution can achieve economical and efficient use of resources while ensuring system performance and user experience, and provides strong technical support for the erp backend management system of multi-user malls.

[0054] S2: Use machine learning models to analyze merchant historical data and generate behavior prediction results, and optimize server resource allocation strategies based on the behavior prediction results.

[0055] S2.1: Collect merchant historical data. Merchant historical data consists of multi-dimensional information, including order volume, transaction amount, visit traffic, inventory changes and seasonal fluctuations.

[0056] Collect historical merchant data, including order volume O(t), transaction amount V(t), access traffic F(t), inventory change I(t), and seasonal fluctuation index S(t), where t represents the time point.

[0057] S2.2: Preprocess the merchant historical data collected in S2.1, including data cleaning, outlier processing and feature standardization.

[0058] S2.3: A time series prediction model is constructed based on the long short-term memory network algorithm LSTM and the attention mechanism, and the merchant historical data preprocessed in S2.2 is trained through the time series prediction model.

[0059] Specifically, the time series prediction model is expressed as:

[0060] 1. Calculation of LSTM unit:

[0061] f t =σ(W f ·[h t-1 ,x t ]+bf );

[0062] i t =σ(W i ·[h t-1 ,x t ]+b i );

[0063]

[0064] o t =σ(W o ·[h t-1 ,x t ]+b o );

[0065] h t =o t *tanh(C t );

[0066] Among them, f t is the forget gate; i t is the input gate; o t is the output gate; C t It is the cell state, storing long-term memory; is the candidate unit state; h t is the hidden state, which is the output of the current time step; x t is the input of the current time step; W f is the weight matrix of the forget gate; W i is the weight matrix of the input gate; W C is the weight matrix of the unit state; W o is the weight matrix of the output gate; b f 、b i 、b C 、b o are the corresponding bias terms; σ is the activation function; tanh is the hyperbolic tangent activation function.

[0067] 2. Attention Mechanism:

[0068]

[0069] Among them, e ij is the attention score of the jth encoding hidden state at the i-th decoding time step; α ij is the normalized attention weight; c i is the context vector, representing the weighted encoder hidden state; V a , W a and U a is a learnable parameter of the attention mechanism; s i-1is the decoder state at the previous time step; h j is the jth encoder hidden state; The T in represents transpose; T in it represents the length of the input sequence, and k is an index from 1 to T.

[0070] 3. Introducing time-aware attention mechanism:

[0071]

[0072] Among them, τ ij is the time decay factor; θ is an adjustable time scale parameter; is the attention weight after adding time perception.

[0073] 4. Final prediction:

[0074]

[0075] in, is the predicted output; W y and b y are the weights and biases of the output layer.

[0076] S2.4: Generate merchant behavior prediction results using the time series prediction model in S2.3. The merchant behavior prediction results include the expected order volume, transaction amount and visit traffic in a certain period of time in the future.

[0077] Specifically, use the trained model to make predictions:

[0078]

[0079] in, is the predicted future order volume; is the predicted future transaction amount; is the predicted future access traffic; f LSTM Represents the trained LSTM model; represents the historical data of merchant i; Δt is the predicted time span.

[0080] S2.5: According to the merchant behavior prediction results in S2.4, adjust the server resource allocation strategy in S1.2, including updating the resource utilization threshold, optimizing the resource adjustment rules and formulating the resource reservation plan.

[0081] Specifically, the resource utilization threshold is updated, specifically by dynamically adjusting the dynamic high threshold and the dynamic low threshold in S1.2 according to the prediction result:

[0082]

[0083] in, are the updated dynamic high and low thresholds; are the original dynamic high and low thresholds; δ high , δ low is the adjustment factor for the high and low thresholds; is the predicted future access traffic; F i (t) is the current access traffic.

[0084] Preferably, the change of access traffic is mainly considered when updating the threshold, because it is usually the factor that most directly affects the server load.

[0085] Furthermore, the resource expansion and contraction rules in S1.2 are adjusted according to the prediction results.

[0086] Resource expansion rules:

[0087]

[0088] Resource shrinking rules:

[0089]

[0090] Among them, E is the expansion amount; P is the contraction amount; R current is the current resource amount; E min is the smallest expansion unit; P min It is the smallest unit of contraction.

[0091] Preferably, access traffic is used as the main reference indicator in resource adjustment rules, but in actual applications, the impact of order volume and transaction amount can be considered based on specific circumstances.

[0092] Develop a resource reservation plan:

[0093]

[0094] Among them, R reserve is the amount of resources reserved; is the safety factor, corresponding to the safety factor in S1.2; ω is the volatility coefficient, corresponding to the volatility coefficient in S1.2; V hist is the historical volatility, corresponding to the historical volatility in S1.2.

[0095] Preferably, the predicted access traffic and order volume are comprehensively considered in the resource reservation plan, and the maximum value is taken as the benchmark, so as to better cope with possible peak loads.

[0096] S3: Develop an intelligent ERP configuration recommendation system based on deep reinforcement learning algorithm. The intelligent ERP configuration recommendation system uses behavior prediction results to automatically identify merchant business models and generate personalized ERP management configuration recommendations.

[0097] S3.1: Construct a merchant business model feature matrix that includes the merchant behavior prediction results in S2.4, historical ERP usage data, and product category information.

[0098] Specifically, for merchant i at time t, the merchant business model feature matrix X i (t), expressed as:

[0099] X i (t) = [P i (t), H i (t), C i ];

[0100]

[0101] Among them, P i (t) is the merchant behavior prediction result vector from S2.4; H i (t) is the historical erp usage data vector; C i is the product category information vector.

[0102] S3.2: Construct a multi-task deep neural network model, which includes a shared layer and multiple task-specific layers. The shared layer is used to extract common features of merchant business, and the multiple task-specific layers are used for merchant business pattern recognition and EPR configuration parameter prediction respectively.

[0103] Multi-task learning objective function:

[0104] L total =αL business +βL config +γL shared +λΩ(W);

[0105] Among them, L business is the loss function of merchant business model recognition; L config is the loss function of erp configuration parameter prediction; L shared is the loss function of the shared layer; Ω(W) is the regularization term; α, β, γ, λ are the weight coefficients.

[0106] S3.3: Use the transfer learning method to initialize the multi-task deep neural network model parameters in S3.2 using the pre-trained e-commerce domain knowledge graph.

[0107] Specifically, the knowledge graph is embedded into the model:

[0108] W init =W pretrained +∈;

[0109] Among them, Winit is the initialized model weight; W pretrained are the pre-trained weights learned from the knowledge graph; ∈ is a small random perturbation used to break the symmetry.

[0110] S3.4: Based on the merchant business model feature matrix in S3.1, the multi-task deep neural network model initialized in S3.3 is trained to obtain a trained multi-task deep neural network model for merchant business model recognition and ERP configuration parameter prediction.

[0111] Specifically, the model training process is expressed as:

[0112]

[0113] in, is the optimized model parameter; X is the input feature; Y is the true label; are model parameters.

[0114] S3.5: The merchant business model feature matrix in S3.1 is taken as input and passed into the multi-task deep neural network model trained in S3.4. The common features of the merchant business are extracted through the shared layer, and then the merchant business model is identified using the task-specific layer for merchant business model identification, and the corresponding personalized ERP management configuration recommendations are generated using the task-specific layer for ERP configuration parameter prediction.

[0115] Specifically, merchant business model identification:

[0116]

[0117] Among them, p(y i |X i ) is the input feature matrix X for a given merchant i i When y is used, the probability distribution of merchant i belonging to each business model is predicted; i is the business model category of merchant i; W b is the weight matrix of the business pattern recognition task; h is the output feature vector of the shared layer; b b is the bias vector of the business pattern recognition task; softmax is the activation function used to convert the output into a probability distribution;

[0118] erp configuration parameter prediction:

[0119]

[0120] Among them, h is the output feature vector of the shared layer; W b , b b are the weights and biases of the business pattern recognition task; W c , bc are the weights and biases of the configuration parameter prediction task; f c is the activation function (such as ReLU). is the predicted erp configuration parameter vector;

[0121] It should be noted that in order to further improve the accuracy of erp configuration parameter prediction, an attention mechanism can be introduced.

[0122] It should be noted that the attention mechanism is used in both S2.3 and S3.5, but they have some important differences in application scenarios and specific implementations:

[0123] 1. Differences in application scenarios:

[0124] S2.3 (time series prediction model): used to process time series data with the aim of predicting future order volume, transaction amount and access traffic. The attention mechanism is mainly used to capture the importance of different time points.

[0125] S3.5 (erp configuration parameter prediction): used to process multi-dimensional merchant feature data, with the aim of generating personalized erp configuration recommendations. The attention mechanism is mainly used to capture the importance of different erp configuration parameters.

[0126] 2. Differences in specific implementation: The attention mechanism of S2.3 is on the time dimension, while the attention mechanism of S3.5 is between different erp configuration parameters.

[0127] 3. The difference between input and output: S2.3: The input is time series data, and the output is the predicted value at a future time point; S3.5: The input is a feature matrix containing prediction results, historical data, and product information, and the output is the predicted value of the erp configuration parameters.

[0128] 4. Difference in computational complexity: The attention mechanism of S2.3 has a higher computational complexity because it needs to calculate the attention weight at each time step. The attention mechanism of S3.5 is relatively simple and only needs to calculate the attention weight once for a fixed number of erp configuration parameters.

[0129] 5. Difference in objectives: The attention mechanism of S2.3 aims to improve the accuracy of time series prediction. The attention mechanism of S3.5 aims to improve the personalization and accuracy of ERP configuration recommendations.

[0130] In general, although both use the attention mechanism technology, they have obvious differences in specific implementation and function due to different application scenarios, input and output, calculation methods and final goals. The attention mechanism of S2.3 focuses more on capturing long-term dependencies in time series, while the attention mechanism of S3.5 focuses more on finding the most relevant parts among multiple configuration parameters. The combination of these two attention mechanisms enables the entire system to accurately predict future trends and provide accurate personalized erp configuration recommendations.

[0131] S4: Integrate multi-channel payment interfaces and logistics APIs, and automatically select payment and logistics strategies based on personalized ERP management configuration suggestions to build a unified order management process.

[0132] S4.1: Integrate payment interface and logistics API.

[0133] Integrate multiple third-party payment platform APIs and logistics service provider APIs.

[0134] Establish a payment and logistics strategy database, and store the payment and logistics related parameters in the personalized ERP management configuration suggestions generated in S3.5 into the database.

[0135] S4.2: Build order processing module and order status tracking system.

[0136] Build an order processing module that automatically selects the most suitable payment method and logistics solution for each order based on the payment and logistics strategy database in S4.1.

[0137] Build an order status tracking system that obtains the payment status and logistics information of the order in real time through the multi-channel payment interface and logistics API integrated in S4.1.

[0138] S4.3: Build a unified order management interface.

[0139] Build a unified order management interface that integrates S4.2's order processing module and order status tracking system.

[0140] The order management interface implements the management functions of the entire order life cycle, including order creation, payment, shipment, logistics tracking and completion.

[0141] In summary, the present invention realizes intelligent and dynamic server resource allocation by constructing an elastic expansion mechanism, and effectively copes with load fluctuations. The method uses a machine learning model to analyze merchant historical data, generate behavior prediction results, optimize resource allocation strategies, and improve the foresight and adaptability of the system. At the same time, the intelligent erp configuration recommendation system developed based on the deep reinforcement learning algorithm can automatically identify merchant business models and generate personalized management configuration suggestions, greatly improving the intelligence level of the system. In addition, by integrating multi-channel payment interfaces and logistics APIs, a unified order management process is constructed, which realizes the automatic selection of payment and logistics strategies, as well as efficient management of the entire life cycle of orders. This comprehensive solution not only significantly improves resource utilization efficiency and system performance, but also better meets the personalized needs of different merchants, provides strong technical support for the operation and management of multi-user malls, and effectively improves user experience and operational efficiency.

[0142] Embodiment 2 is an embodiment of the present invention, which provides an ERP backend management system based on a multi-user mall, including: an elastic resource management module, which is used to build an elastic expansion mechanism based on cloud architecture. The elastic expansion mechanism dynamically adjusts server resources according to the server resource allocation strategy by monitoring the real-time load data of the ERP backend management system; a prediction optimization module, which is used to use a machine learning model to analyze merchant historical data and generate behavior prediction results, and optimize the server resource allocation strategy according to the behavior prediction results; an intelligent ERP configuration recommendation module, which is used to develop an intelligent ERP configuration recommendation system based on a deep reinforcement learning algorithm. The intelligent ERP configuration recommendation system uses the behavior prediction results to automatically identify the merchant business model and generate personalized ERP management configuration suggestions; a unified order management module, which is used to integrate multi-channel payment interfaces and logistics APIs, and automatically select payment and logistics strategies according to personalized ERP management configuration suggestions to build a unified order management process.

[0143] Example 3, reference Figure 2, is an embodiment of the present invention, which is different from the previous embodiment in that: if the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0144] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0145] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0146] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0147] Example 4 is an embodiment of the present invention, which provides an ERP background management method based on a multi-user mall. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0148] First, this embodiment builds a simulated multi-user mall environment, including 100 merchants of different sizes and types, and about 500,000 users. The experiment is divided into two phases, each lasting 30 days. The first phase is managed using the traditional ERP system, and the second phase is managed by switching to this solution. Throughout the experiment, various scenarios such as daily operations, promotional activities, and sudden traffic are simulated to fully test the performance and adaptability of the system.

[0149] During the experiment, various indicators were continuously monitored and recorded. For system performance, stress testing tools were used to simulate different levels of concurrent access to test the system's response time and processing capabilities. For resource management efficiency, monitoring agents were deployed to collect resource usage of the server cluster in real time. In terms of intelligent evaluation, a certain proportion of merchant samples were randomly selected to manually review the personalized configuration recommendations, resource demand forecasts, and abnormal situation detection results generated by the system, and their accuracy was calculated. Through these comprehensive tests and data collection, the above experimental results were obtained, which strongly proved the superiority of this solution in all aspects.

[0150] Table 1 System performance evaluation

[0151]

[0152]

[0153] As shown in Table 1, the system performance evaluation results show that the present invention has achieved significant improvements in various key indicators. The average response time was reduced from 320ms to 95ms, an increase of 70.3%, which greatly improved the user experience. The number of concurrent users increased from 5000 to 15000, an increase of 200%, indicating that the load capacity of the system has been greatly improved. The transaction volume per second (TPS) increased from 3500 to 9800, an increase of 180%, which means that the system can process more business requests in the same time. These data fully demonstrate the excellent performance of the present invention in processing high-concurrency and large-scale transactions, and provide strong technical support for the efficient operation of multi-user malls.

[0154] Table 2 Resource management efficiency evaluation

[0155] index Traditional ERP system The present invention Improvement CPU utilization (%) 40 75 87.5％ Memory usage efficiency (%) 55 82 49.1％ Storage space utilization (%) 60 85 41.7％

[0156] As shown in Table 2, the resource management efficiency evaluation results show that the present invention has made significant progress in server resource utilization. CPU utilization increased from 40% to 75%, an increase of 87.5%; memory utilization efficiency increased from 55% to 82%, an increase of 49.1%; storage space utilization increased from 60% to 85%, an increase of 41.7%. These data reflect that the present invention has greatly improved the utilization efficiency of system resources through intelligent resource scheduling and elastic expansion mechanisms. Efficient resource management not only reduces operating costs, but also provides greater flexibility for the business growth of the mall, enabling the system to better cope with business peaks and sudden traffic.

[0157] Table 3: Evaluation of intelligence level

[0158] index Traditional ERP system The present invention Improvement Personalized configuration accuracy (%) 65 94 44.6％ Resource prediction accuracy (%) 70 92 31.4％ Anomaly detection accuracy (%) 75 96 28.0％

[0159] As shown in Table 3, the results of the intelligence evaluation highlight the advantages of the present invention in intelligent decision-making and prediction. The accuracy of personalized configuration increased from 65% to 94%, an increase of 44.6%, which means that the system can provide merchants with customized ERP configuration suggestions more accurately. The resource prediction accuracy increased from 70% to 92%, an increase of 31.4%, showing the excellent performance of the system in resource demand forecasting. The accuracy of anomaly detection increased from 75% to 96%, an increase of 28%, which greatly improved the system's ability to identify and handle abnormal situations. These data fully demonstrate the effectiveness of the machine learning and deep reinforcement learning algorithms used in the present invention, and provide strong technical support for the intelligent management of multi-user malls.

[0160] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An ERP background management method based on a multi-user mall, characterized in that: include: Build an elastic expansion mechanism based on cloud architecture, which dynamically adjusts server resources according to server resource allocation strategy by monitoring real-time load data of ERP backend management system; Using a machine learning model to analyze merchant historical data and generate behavior prediction results, and optimizing the server resource allocation strategy based on the behavior prediction results; Develop an intelligent erp configuration recommendation system based on a deep reinforcement learning algorithm, which uses the behavior prediction results to automatically identify the merchant's business model and generate personalized erp management configuration suggestions; Integrate multi-channel payment interfaces and logistics APIs, and automatically select payment and logistics strategies based on the personalized ERP management configuration suggestions to build a unified order management process.

2. The ERP background management method based on a multi-user mall as claimed in claim 1, characterized in that: Construct an elastic expansion mechanism based on cloud architecture. The elastic expansion mechanism dynamically adjusts server resources according to the server resource allocation strategy by monitoring the real-time load data of the ERP background management system, including the following steps: Building a distributed load monitoring system based on cloud architecture, and collecting various real-time load data of the server cluster through the distributed load monitoring system; Formulate a server resource allocation strategy; the server resource allocation strategy includes a resource utilization threshold and a resource adjustment rule; Establishing a multi-dimensional resource scoring model; the multi-dimensional resource scoring model calculates the server resource utilization score according to the real-time load data; comparing the server resource utilization score with the resource utilization threshold, and triggering resource adjustment when the server resource utilization score exceeds the resource utilization threshold; After the resource adjustment is triggered, the number of server instances is dynamically increased or decreased according to the resource adjustment rules, and the computing resource allocation is adjusted to complete the elastic expansion mechanism of server resources.

3. The ERP background management method based on a multi-user mall as claimed in claim 2 is characterized in that: Each type of real-time load data corresponds to a type of resource; the resource utilization threshold includes a dynamic high threshold and a dynamic low threshold; The resource adjustment rules include resource expansion rules, resource contraction rules, intelligent reservation rules, and elastic adjustment rules; The resource expansion rule is that when the resource utilization rate of a certain type of real-time load data exceeds its dynamic high threshold for T1 consecutive minutes, resource expansion is triggered, and the expansion amount is: The resource amount of the current real-time load data*(resource utilization of the current real-time load data-dynamic high threshold) / dynamic high threshold, rounded up but not less than the minimum expansion unit; The resource shrinkage rule is that when the resource utilization rate of a certain type of real-time load data is lower than its dynamic low threshold for T2 consecutive minutes, resource shrinkage is triggered, and the shrinkage amount is: The resource amount of the current real-time load data * (dynamic low threshold - resource utilization of the current real-time load data) / dynamic low threshold, rounded up but not less than the minimum contraction unit; The intelligent reservation rule is that when the ERP backend management system predicts that the resource demand will exceed the current capacity within the preset time, that is, the total available resources, the reserved resources are: predicted peak usage * (1 + safety factor + volatility coefficient * historical volatility range; The elastic adjustment rule is that if the number of resource adjustments in the last M hours is greater than the preset number, the new resource utilization threshold = the original resource utilization threshold * (1 + X%); The multi-dimensional resource scoring model calculates the ratio of the current usage of each real-time load data to the maximum capacity, multiplies it by the weight of each real-time load data, adds up the weighted resource utilization of all real-time load data, and obtains the score as the server resource utilization score.

4. The ERP background management method based on a multi-user mall as claimed in claim 3 is characterized in that: Using a machine learning model to analyze merchant historical data and generate behavior prediction results, and optimizing the server resource allocation strategy according to the behavior prediction results, includes the following steps: Collect and pre-process merchant historical data; the merchant historical data includes order volume, transaction amount, visit traffic, inventory changes and seasonal fluctuations; Building a time series prediction model based on the long short-term memory network algorithm LSTM and the attention mechanism, and training the preprocessed merchant historical data through the time series prediction model; Generate merchant behavior prediction results using the time series prediction model; the merchant behavior prediction results include expected order volume, transaction amount and access traffic; Adjusting the server resource allocation strategy according to the merchant behavior prediction result; Wherein, adjusting the server resource allocation strategy includes updating resource utilization thresholds, optimizing resource adjustment rules, and formulating resource reservation plans.

5. The ERP background management method based on the multi-user mall as claimed in claim 4 is characterized by: The intelligent erp configuration recommendation system is developed based on the deep reinforcement learning algorithm. The intelligent erp configuration recommendation system uses the behavior prediction results to automatically identify the merchant business model and generate personalized erp management configuration suggestions, including the following steps: Constructing a merchant business model feature matrix including the merchant behavior prediction results, historical ERP usage data and commodity category information; Construct a multi-task deep neural network model, which includes a shared layer and multiple task-specific layers. The shared layer is used to extract the common features of the merchant's business, and the multiple task-specific layers are used for merchant business pattern recognition and EPR configuration parameter prediction respectively. Using transfer learning methods, we use pre-trained e-commerce knowledge graphs to initialize the parameters of multi-task deep neural network models. Based on the merchant business model feature matrix, the initialized multi-task deep neural network model is trained to obtain a trained multi-task deep neural network model for merchant business model recognition and ERP configuration parameter prediction; The merchant business model feature matrix is ​​taken as input and passed into the trained multi-task deep neural network model. The common features of the merchant business are extracted through the shared layer, and then the merchant business model is recognized by the task-specific layer used for merchant business model recognition, and the task-specific layer used for ERP configuration parameter prediction is used to generate corresponding personalized ERP management configuration recommendations.

6. The ERP background management method based on a multi-user mall as claimed in claim 5 is characterized in that: The integrated multi-channel payment interface and logistics API, and the automatic selection of payment and logistics strategies based on personalized ERP management configuration suggestions, build a unified order management process, including the following steps: Integrate multiple third-party payment platform APIs and logistics service provider APIs; Establishing a payment and logistics strategy database, and storing the payment and logistics parameters in the personalized ERP management configuration suggestion into the logistics strategy database; Build order processing module; Build an order status tracking system, which obtains the payment status and logistics information of the order in real time; Build a unified order management interface.

7. The ERP background management method based on a multi-user mall as claimed in claim 6 is characterized in that: The real-time load data includes CPU, memory, network bandwidth, and disk I / O.

8. A system using the ERP background management method based on a multi-user mall as claimed in any one of claims 1 to 7, characterized in that: include: The elastic resource management module is used to build an elastic expansion mechanism based on the cloud architecture. The elastic expansion mechanism dynamically adjusts server resources according to the server resource allocation strategy by monitoring the system load data in real time; A prediction optimization module, used to analyze merchant historical data using a machine learning model and generate behavior prediction results, and optimize the server resource allocation strategy according to the behavior prediction results; An intelligent erp configuration recommendation module is used to develop an intelligent erp configuration recommendation system based on a deep reinforcement learning algorithm. The intelligent erp configuration recommendation system automatically identifies the merchant's business model using the behavior prediction results and generates personalized erp management configuration suggestions; The unified order management module is used to integrate multi-channel payment interfaces and logistics APIs, and automatically select payment and logistics strategies based on the personalized ERP management configuration suggestions to build a unified order management process.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the ERP background management method based on a multi-user mall described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the ERP background management method based on the multi-user mall described in any one of claims 1 to 7 are implemented.

Images