An operation management method, system and storage medium of an e-commerce platform

Abstract

The present invention relates to an operation and management method, system and storage medium of an e-commerce platform, and belongs to the technical field of operation and management of e-commerce platforms. The present invention obtains the information processing efficiency membership of the e-commerce platform at the current timestamp based on the information processing efficiency membership transfer probability value prediction model, and finally identifies the information processing efficiency membership of the e-commerce platform at the current timestamp to obtain the identification result, and performs flow limiting management on the e-commerce platform based on the abnormal identification result. The present invention evaluates the information processing efficiency membership of the e-commerce platform, thereby converting the data into fuzzy membership, so that the information processing efficiency of the e-commerce platform can be quickly identified, and then the e-commerce platform is flow limited according to the situation of the information processing efficiency membership of the current timestamp. It can effectively avoid the jamming phenomenon of the e-commerce platform, thereby avoiding the inability of the e-commerce platform to operate.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce platform management, and in particular to an operation and management method, system and storage medium of an e-commerce platform. Background Art

[0002] E-commerce platforms are business activity networks dominated by enterprises and carried out on the Internet. They are important places for coordinating and integrating the orderly and efficient flow of information, goods and funds. As a key means to promote the high-quality development of e-commerce, the marketing model of e-commerce platforms needs to change the traditional disorderly development mode and form a precise, personalized and differentiated marketing environment, so as to provide a service portal site for the high-quality development of e-commerce and enable the high-quality development of the e-commerce field. However, in the process of operation of e-commerce platforms, due to changes in factors such as network fluctuations, environment, and traffic, the e-commerce platform will cause the server to process data per unit time due to the need to receive and process data, which will cause the e-commerce platform to have a jamming phenomenon. If not processed, it may even cause the e-commerce platform to be unable to operate, which is not conducive to the maintenance of the e-commerce platform. Summary of the invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an operation and management method, system and storage medium for an e-commerce platform.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] A first aspect of the present invention provides an operation and management method of an e-commerce platform, comprising:

[0006] Obtaining the amount of information processed by the e-commerce platform within a preset time, and obtaining the degree of information processing efficiency of the e-commerce platform by evaluating the amount of information processed by the e-commerce platform within the preset time;

[0007] According to the information processing efficiency membership of the e-commerce platform, an information processing efficiency membership change matrix is ​​constructed, a Markov model is constructed based on the Markov chain, and the information processing efficiency membership change matrix is ​​input into the Markov model to obtain an information processing efficiency membership transfer probability value matrix;

[0008] Building an information processing efficiency membership transfer probability value prediction model based on the information processing efficiency membership transfer probability value matrix, and acquiring the information processing efficiency membership of the e-commerce platform at the current timestamp based on the information processing efficiency membership transfer probability value prediction model;

[0009] By identifying the information processing efficiency membership of the e-commerce platform at the current timestamp, an identification result is obtained, and flow limiting management is performed on the e-commerce platform based on the abnormal identification result.

[0010] Furthermore, in this method, by evaluating the information processing volume of the e-commerce platform within a preset time, the information processing efficiency membership of the e-commerce platform is obtained, specifically:

[0011] Introducing a decision tree algorithm, constructing a sample data set according to the amount of information processed by the e-commerce platform within a preset time, setting a splitting criterion, taking the sample data set as a root node, and performing initial splitting on the sample data set based on the splitting criterion to generate a number of leaf nodes;

[0012] Determine whether there is only one type of sample data in each leaf node. When there is only one type of sample data in the leaf node, output the leaf node and obtain the information processing efficiency membership of the e-commerce platform corresponding to each leaf node;

[0013] When more than one type of sample data exists in the leaf node, the leaf node is continuously split until only one type of sample data exists in the leaf node.

[0014] Furthermore, in this method, an information processing efficiency membership change matrix is ​​constructed according to the information processing efficiency membership of the e-commerce platform, a Markov model is constructed based on the Markov chain, and the information processing efficiency membership change matrix is ​​input into the Markov model to obtain the information processing efficiency membership transition probability value matrix, which specifically includes:

[0015] Constructing a timestamp, and obtaining the information processing efficiency membership of the e-commerce platform in each timestamp, constructing an information processing efficiency change membership matrix based on the information processing efficiency membership of the e-commerce platform in each timestamp, and constructing a Markov model based on the Markov chain;

[0016] Inputting the information processing efficiency membership degree change matrix into the Markov model, and calculating the transition probability value of the information processing efficiency membership degree in each time stamp in the information processing efficiency change matrix transferring to another information processing efficiency membership degree;

[0017] The transition probability value of the information processing efficiency membership at each time stamp in the information processing efficiency change matrix is ​​transferred to another information processing efficiency membership, and the information processing efficiency membership transition probability value matrix is ​​constructed.

[0018] Furthermore, in this method, an information processing efficiency membership transfer probability value prediction model is constructed based on the information processing efficiency membership transfer probability value matrix, and the information processing efficiency membership of the e-commerce platform at the current timestamp is obtained based on the information processing efficiency membership transfer probability value prediction model, specifically including:

[0019] Constructing an information processing efficiency membership transfer probability value prediction model based on a convolutional neural network, configuring training parameters of the information processing efficiency membership transfer probability value prediction model, and inputting the information processing efficiency membership transfer probability value matrix into the information processing efficiency membership transfer probability value prediction model;

[0020] The information processing efficiency membership transfer probability value prediction model is trained according to the training parameters, the trained information processing efficiency membership transfer probability value prediction model is obtained, and the information processing efficiency membership of the e-commerce platform at the current timestamp is obtained;

[0021] Inputting the information processing efficiency membership of the e-commerce platform at the current timestamp into the trained information processing efficiency membership transition probability value prediction model to predict the transition probability value of the information processing efficiency membership of the e-commerce platform at the current timestamp to another information processing efficiency membership;

[0022] When the transfer probability value is greater than the preset transfer probability value, another information processing efficiency membership is output as the information processing efficiency membership of the current timestamp; when the transfer probability value is not greater than the preset transfer probability value, the information processing efficiency membership of the e-commerce platform at the current timestamp is output.

[0023] Furthermore, in this method, by identifying the information processing efficiency membership of the e-commerce platform at the current timestamp, obtaining the identification result specifically includes:

[0024] Setting an information processing efficiency membership evaluation index, and determining whether the information processing efficiency membership of the e-commerce platform at the current timestamp is greater than the information processing efficiency membership evaluation index;

[0025] When the information processing efficiency membership of the e-commerce platform at the current timestamp is not greater than the information processing efficiency membership evaluation index, the information processing efficiency membership of the e-commerce platform at the current timestamp is output as an abnormality recognition result;

[0026] When the information processing efficiency membership of the e-commerce platform at the current timestamp is greater than the information processing efficiency membership evaluation index, the information processing efficiency membership of the e-commerce platform at the current timestamp is output as a normal recognition result.

[0027] Furthermore, in this method, based on the identification result, flow limiting management is performed on the e-commerce platform, specifically including:

[0028] If the recognition result is an abnormal recognition result, the amount of information accessed by a single user and the number of users' accesses within a preset time are obtained, and the total amount of information within the preset time is calculated based on the amount of information accessed by a single user and the number of users' accesses within the preset time;

[0029] Obtaining the amount of information processed by the e-commerce platform within a preset time, and determining whether the total amount of information within the preset time is greater than the amount of information processed by the e-commerce platform within the preset time;

[0030] When the total amount of information within the preset time is greater than the amount of information processed by the e-commerce platform within the preset time, reconfigure the access quantity information of the e-commerce platform within the preset time, generate adjusted access quantity information, and calculate the adjusted total amount of information based on the adjusted access quantity information;

[0031] When the adjusted total amount of information is no longer greater than the amount of information processed by the e-commerce platform within a preset time, the adjusted access quantity information is output, and access to the e-commerce platform is limited in flow management based on the adjusted access quantity information.

[0032] A second aspect of the present invention provides an operation and management system for an e-commerce platform, comprising a memory and a processor, wherein the memory includes an operation and management method program for the e-commerce platform, and when the operation and management method program for the e-commerce platform is executed by the processor, the steps of any one of the operation and management methods for the e-commerce platform are implemented.

[0033] A third aspect of the present invention provides a terminal device, including:

[0034] An acquisition module, used to acquire the information processing volume of the e-commerce platform within a preset time, and to acquire the information processing efficiency membership of the e-commerce platform by evaluating the information processing volume of the e-commerce platform within the preset time;

[0035] An analysis module, used to construct an information processing efficiency membership change matrix according to the information processing efficiency membership of the e-commerce platform, construct a Markov model based on the Markov chain, and input the information processing efficiency membership change matrix into the Markov model to obtain an information processing efficiency membership transition probability value matrix;

[0036] A prediction module, used to construct an information processing efficiency membership transfer probability value prediction model based on the information processing efficiency membership transfer probability value matrix, and obtain the information processing efficiency membership of the e-commerce platform at the current timestamp based on the information processing efficiency membership transfer probability value prediction model;

[0037] The management module is used to identify the information processing efficiency membership of the e-commerce platform at the current timestamp, obtain the identification result, and perform flow limiting management on the e-commerce platform based on the abnormal identification result.

[0038] The fourth aspect of the present invention provides a computer-readable storage medium, which includes an operation and management method program for an e-commerce platform. When the operation and management method program for the e-commerce platform is executed by a processor, the steps of any one of the operation and management methods for the e-commerce platform are implemented.

[0039] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0040] The present invention obtains the information processing efficiency membership of the e-commerce platform at the current timestamp based on the information processing efficiency membership transfer probability value prediction model, and finally identifies the information processing efficiency membership of the e-commerce platform at the current timestamp to obtain the identification result, and performs flow limiting management on the e-commerce platform based on the abnormal identification result. The present invention evaluates the information processing efficiency membership of the e-commerce platform, thereby converting the data into fuzzy membership, so that the information processing efficiency of the e-commerce platform can be quickly identified, and then the e-commerce platform is flow limited according to the situation of the information processing efficiency membership of the current timestamp. It can effectively avoid the jamming phenomenon of the e-commerce platform, thereby preventing the e-commerce platform from being unable to operate. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0042] Figure 1 The overall flow chart of the operation and management method of the e-commerce platform is shown;

[0043] Figure 2 A partial flow chart of the operation and management method of an e-commerce platform is shown.

[0044] Figure 3 A system block diagram of the operation management system of an e-commerce platform is shown;

[0045] Figure 4 A device schematic diagram of a terminal device is shown. DETAILED DESCRIPTION

[0046] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0048] like Figure 1 As shown, the first aspect of the present invention provides an operation and management method of an e-commerce platform, comprising:

[0049] S102: Obtaining the information processing volume of the e-commerce platform within a preset time, and obtaining the information processing efficiency membership of the e-commerce platform by evaluating the information processing volume of the e-commerce platform within the preset time;

[0050] It is worth mentioning that since the servers corresponding to the e-commerce platform are easily affected by factors such as network fluctuations, environment, and traffic, the data processing capabilities of the e-commerce platform will change, such as the amount of data that the e-commerce platform can process per unit time, the speed at which the e-commerce platform processes data, etc. In this process, the decision tree algorithm is integrated to batch process and identify data, including the following:

[0051] Introduce the decision tree algorithm, build a sample data set based on the amount of information processed by the e-commerce platform within a preset time, set a splitting standard, use the sample data set as the root node, initialize and split the sample data set based on the splitting standard, and generate several leaf nodes;

[0052] First, a splitting standard is set. For example, the data processing volume within a unit time is set between 0-20 megabytes as a low information processing efficiency membership, 20-100 megabytes as a medium information processing efficiency membership, 100-200 as a high information processing efficiency membership, etc. According to this standard, the collected sample data is continuously split as the root node. According to the principle of the decision tree algorithm, it can be known that several leaf nodes can be obtained to achieve the classification effect and realize batch processing of data.

[0053] Determine whether there is only one type of sample data in each leaf node. If there is only one type of sample data in the leaf node, output the leaf node and obtain the information processing efficiency membership of the e-commerce platform corresponding to each leaf node;

[0054] When there is more than one type of sample data in a leaf node, the leaf node is continuously split until there is only one type of sample data in the leaf node.

[0055] It is worth mentioning that if there is no other type of sample data in the leaf node, the splitting of the leaf node ends. This embodiment may also include:

[0056] The Jaccard distance measurement algorithm and the genetic algorithm are integrated, and the Jaccard similarity coefficient between the leaf nodes is calculated. The Jaccard distance between the leaf nodes is calculated according to the Jaccard similarity coefficient, a plurality of Jaccard distances are obtained, and a Jaccard distance threshold is set; the genetic algebra is set based on the genetic algorithm, and it is determined whether the Jaccard distances between all leaf nodes are greater than the Jaccard distance threshold; when the Jaccard distances between all leaf nodes are greater than the Jaccard distance threshold, all leaf nodes are output and the splitting ends; when the Jaccard distances between all leaf nodes are not greater than the Jaccard distance threshold, the leaf nodes are continuously split based on the genetic algebra until the Jaccard distances between all leaf nodes are greater than the Jaccard distance threshold.

[0057] It should be noted that when there is a large amount of data, the decision tree algorithm is prone to classification anomalies during classification. By integrating the genetic algorithm and the Jaccard distance measurement algorithm, the classification accuracy can be improved, thereby improving the recognition accuracy of the information processing efficiency membership.

[0058] Among them, obtaining the information processing volume of the e-commerce platform within a preset time is specifically as follows: obtaining the information processing volume of the e-commerce platform under various influencing factors through big data, and introducing a graph neural network, taking the influencing factors as the first graph nodes, and taking the information processing volume of the e-commerce platform as the second graph nodes; constructing a topological structure graph according to the first graph node and the second graph node, obtaining a related adjacency matrix based on the topological structure graph, constructing an information processing volume prediction model based on deep neural networks, and inputting the related adjacency matrix into the information processing volume prediction model for training; obtaining the trained information processing volume prediction model, obtaining real-time influencing factor data of the operation of the e-commerce platform, and inputting the real-time influencing factor data of the operation of the e-commerce platform into the trained information processing volume prediction model for prediction; obtaining the information processing volume of the e-commerce platform within the preset time through prediction, and outputting the information processing volume of the e-commerce platform within the preset time.

[0059] It should be noted that the influencing factor data include network fluctuations, environment, etc. Through this method, it is possible to obtain more accurate information processing volume of the e-commerce platform within a preset time, thereby improving the management rationality of the e-commerce platform.

[0060] S104: constructing an information processing efficiency membership change matrix according to the information processing efficiency membership of the e-commerce platform, constructing a Markov model based on the Markov chain, and inputting the information processing efficiency membership change matrix into the Markov model to obtain an information processing efficiency membership transfer probability value matrix;

[0061] It is worth mentioning that the Markov Chain describes a state sequence, each state value of which depends on the previous finite state. The Markov Chain is a sequence of random variables X1, X2, X3... with Markov properties. The range of these variables, that is, the set of all their possible values, is called the "state space", and the value of Xn is the state at time n. In the present invention, the information processing efficiency membership in each timestamp (time point) can be regarded as a state value, wherein the Markov chain can calculate the transition probability value of the information processing efficiency membership in each timestamp in the information processing efficiency change matrix to another information processing efficiency membership, which specifically includes the following steps:

[0062] Construct timestamps and obtain the information processing efficiency membership of the e-commerce platform in each timestamp, construct the information processing efficiency change membership matrix based on the information processing efficiency membership of the e-commerce platform in each timestamp, and construct a Markov model based on the Markov chain;

[0063] Inputting the information processing efficiency membership degree change matrix into the Markov model, calculating the transition probability value of the information processing efficiency membership degree at each time stamp in the information processing efficiency change matrix transferring to another information processing efficiency membership degree;

[0064] It is worth mentioning that in a state sequence, the state will undergo certain transitions, such as from low processing efficiency membership to high processing efficiency membership, from medium processing efficiency membership to high processing efficiency membership, from high processing efficiency membership to low processing efficiency membership, etc. When the state transitions, it indicates that the information processing ability of the e-commerce platform has declined. The transition probability value of the information processing efficiency membership to another information processing efficiency membership can be obtained through the calculation of the Markov chain.

[0065] The transition probability value of the information processing efficiency membership at each time stamp in the information processing efficiency change matrix is ​​transferred to another information processing efficiency membership, and the information processing efficiency membership transition probability value matrix is ​​constructed.

[0066] S106: constructing an information processing efficiency membership transfer probability value prediction model based on the information processing efficiency membership transfer probability value matrix, and obtaining the information processing efficiency membership of the e-commerce platform at the current timestamp based on the information processing efficiency membership transfer probability value prediction model;

[0067] like Figure 2 As shown, the next step is to predict a state, which is achieved through a convolutional neural network. The model parameters such as the parameters of the convolution layer, the size of the convolution kernel, and the number of maps in each layer are set to predict the probability value of the information processing efficiency membership of the e-commerce platform at the current timestamp transferring to another information processing efficiency membership. The specific steps include:

[0068] S202: constructing an information processing efficiency membership transfer probability value prediction model based on a convolutional neural network, configuring training parameters of the information processing efficiency membership transfer probability value prediction model, and inputting the information processing efficiency membership transfer probability value matrix into the information processing efficiency membership transfer probability value prediction model;

[0069] S204: training the information processing efficiency membership transfer probability value prediction model according to the training parameters, obtaining the trained information processing efficiency membership transfer probability value prediction model, and obtaining the information processing efficiency membership of the e-commerce platform at the current timestamp;

[0070] S206: inputting the information processing efficiency membership of the e-commerce platform at the current timestamp into the trained information processing efficiency membership transition probability value prediction model to predict the transition probability value of the information processing efficiency membership of the e-commerce platform at the current timestamp to another information processing efficiency membership;

[0071] S208: When the transfer probability value is greater than the preset transfer probability value, another information processing efficiency membership is output as the information processing efficiency membership of the current timestamp; when the transfer probability value is not greater than the preset transfer probability value, the information processing efficiency membership of the e-commerce platform in the current timestamp is output.

[0072] It is worth mentioning that this method can more accurately estimate the information processing efficiency membership of the e-commerce platform at the current timestamp.

[0073] S108: Identify the information processing efficiency membership of the e-commerce platform at the current timestamp, obtain the identification result, and perform flow limiting management on the e-commerce platform based on the abnormal identification result.

[0074] It is worth mentioning that an information processing efficiency membership evaluation index is set (such as setting the information processing efficiency membership as the evaluation index), and judging whether the information processing efficiency membership of the e-commerce platform at the current timestamp is greater than the information processing efficiency membership evaluation index; when the information processing efficiency membership of the e-commerce platform at the current timestamp is not greater than the information processing efficiency membership evaluation index, the information processing efficiency membership of the e-commerce platform at the current timestamp is output as the abnormal recognition result; when the information processing efficiency membership of the e-commerce platform at the current timestamp is greater than the information processing efficiency membership evaluation index, the information processing efficiency membership of the e-commerce platform at the current timestamp is output as the normal recognition result.

[0075] Furthermore, in this method, the e-commerce platform is subjected to flow control management based on the identification result, specifically including:

[0076] If the recognition result is an abnormal recognition result, the amount of information accessed by a single user and the number of users' accesses within a preset time are obtained, and the total amount of information within the preset time is calculated based on the amount of information accessed by a single user and the number of users' accesses within the preset time;

[0077] Obtaining the amount of information processed by the e-commerce platform within a preset time, and determining whether the total amount of information within the preset time is greater than the amount of information processed by the e-commerce platform within the preset time;

[0078] When the total amount of information within the preset time is greater than the amount of information processed by the e-commerce platform within the preset time, reconfigure the access quantity information of the e-commerce platform within the preset time, generate adjusted access quantity information, and calculate the adjusted total amount of information based on the adjusted access quantity information;

[0079] When the adjusted total amount of information is no longer greater than the amount of information processed by the e-commerce platform within a preset time, the adjusted access quantity information is output, and access to the e-commerce platform is limited based on the adjusted access quantity information.

[0080] It is worth mentioning that the method can limit the number of users accessing the e-commerce platform according to the amount of information processed by the e-commerce platform within a preset time and the total amount of information within a preset time, that is, limit the number of accessing users, thereby effectively avoiding the lag of the e-commerce platform, thereby preventing the e-commerce platform from being unable to operate and improving the user experience.

[0081] like Figure 3 As shown, the second aspect of the present invention provides an operation management system 4 of an e-commerce platform, including a memory 41 and a processor 42. The memory 41 includes an operation management method program of the e-commerce platform. When the operation management method program of the e-commerce platform is executed by the processor 42, any step of the operation management method of the e-commerce platform is implemented.

[0082] like Figure 4 As shown, the third aspect of the present invention provides a terminal device, including:

[0083] The acquisition module 10 is used to acquire the information processing volume of the e-commerce platform within a preset time, and to acquire the information processing efficiency membership of the e-commerce platform by evaluating the information processing volume of the e-commerce platform within the preset time;

[0084] The analysis module 20 is used to construct an information processing efficiency membership change matrix according to the information processing efficiency membership of the e-commerce platform, construct a Markov model based on the Markov chain, and input the information processing efficiency membership change matrix into the Markov model to obtain the information processing efficiency membership transition probability value matrix;

[0085] A prediction module 30, for constructing an information processing efficiency membership transfer probability value prediction model based on the information processing efficiency membership transfer probability value matrix, and obtaining the information processing efficiency membership of the e-commerce platform at the current timestamp based on the information processing efficiency membership transfer probability value prediction model;

[0086] The management module 40 is used to identify the information processing efficiency membership of the e-commerce platform at the current timestamp, obtain the identification result, and perform flow limiting management on the e-commerce platform based on the abnormal identification result.

[0087] The fourth aspect of the present invention provides a computer-readable storage medium, which includes an operation and management method program for an e-commerce platform. When the operation and management method program for the e-commerce platform is executed by a processor, any step of the operation and management method for the e-commerce platform is implemented.

[0088] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0089] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0090] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0091] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0092] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0093] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An operation and management method for an e-commerce platform, It is characterized in that include: Obtaining the amount of information processed by the e-commerce platform within a preset time, and obtaining the degree of information processing efficiency of the e-commerce platform by evaluating the amount of information processed by the e-commerce platform within the preset time; According to the information processing efficiency membership of the e-commerce platform, an information processing efficiency membership change matrix is ​​constructed, a Markov model is constructed based on the Markov chain, and the information processing efficiency membership change matrix is ​​input into the Markov model to obtain an information processing efficiency membership transfer probability value matrix; Building an information processing efficiency membership transfer probability value prediction model based on the information processing efficiency membership transfer probability value matrix, and acquiring the information processing efficiency membership of the e-commerce platform at the current timestamp based on the information processing efficiency membership transfer probability value prediction model; By identifying the information processing efficiency membership of the e-commerce platform at the current timestamp, obtaining an identification result, and performing flow limiting management on the e-commerce platform based on the identification result; Among them, the amount of information processed by the e-commerce platform within a preset time is obtained, specifically: The information processing volume of the e-commerce platform under each influencing factor is obtained through big data, and a graph neural network is introduced, with the influencing factor as the first graph node and the information processing volume of the e-commerce platform as the second graph node; Constructing a topological structure graph according to the first graph nodes and the second graph nodes, acquiring a related adjacency matrix based on the topological structure graph, constructing an information processing amount prediction model based on deep neural networks, and inputting the related adjacency matrix into the information processing amount prediction model for training; Obtaining a trained information processing volume prediction model, obtaining real-time influencing factor data of the operation of the e-commerce platform, and inputting the real-time influencing factor data of the operation of the e-commerce platform into the trained information processing volume prediction model for prediction; Obtaining the information processing volume of the e-commerce platform within a preset time through prediction, and outputting the information processing volume of the e-commerce platform within the preset time; Based on the identification result, the e-commerce platform is subjected to flow limiting management, which specifically includes: If the recognition result is an abnormal recognition result, the amount of information accessed by a single user and the number of users' accesses within a preset time are obtained, and the total amount of information within the preset time is calculated based on the amount of information accessed by a single user and the number of users' accesses within the preset time; Obtaining the amount of information processed by the e-commerce platform within a preset time, and determining whether the total amount of information within the preset time is greater than the amount of information processed by the e-commerce platform within the preset time; When the total amount of information within the preset time is greater than the amount of information processed by the e-commerce platform within the preset time, reconfigure the access quantity information of the e-commerce platform within the preset time, generate adjusted access quantity information, and calculate the adjusted total amount of information based on the adjusted access quantity information; When the adjusted total amount of information is no longer greater than the amount of information processed by the e-commerce platform within a preset time, the adjusted access quantity information is output, and access to the e-commerce platform is limited in flow management based on the adjusted access quantity information.

2. According to the operation and management method of an e-commerce platform according to claim 1, It is characterized in that By evaluating the information processing volume of the e-commerce platform within a preset time, the information processing efficiency membership of the e-commerce platform is obtained, specifically: Introducing a decision tree algorithm, constructing a sample data set according to the amount of information processed by the e-commerce platform within a preset time, setting a splitting criterion, taking the sample data set as a root node, and performing initial splitting on the sample data set based on the splitting criterion to generate a number of leaf nodes; Determine whether there is only one type of sample data in each leaf node. When there is only one type of sample data in the leaf node, output the leaf node and obtain the information processing efficiency membership of the e-commerce platform corresponding to each leaf node; When more than one type of sample data exists in the leaf node, the leaf node is continuously split until only one type of sample data exists in the leaf node.

3. According to the operation and management method of an e-commerce platform according to claim 1, It is characterized in that According to the information processing efficiency membership of the e-commerce platform, an information processing efficiency membership change matrix is ​​constructed, a Markov model is constructed based on the Markov chain, and the information processing efficiency membership change matrix is ​​input into the Markov model to obtain the information processing efficiency membership transition probability value matrix, which specifically includes: Constructing a timestamp, and obtaining the information processing efficiency membership of the e-commerce platform in each timestamp, constructing an information processing efficiency change membership matrix based on the information processing efficiency membership of the e-commerce platform in each timestamp, and constructing a Markov model based on the Markov chain; Inputting the information processing efficiency membership degree change matrix into the Markov model, and calculating the transition probability value of the information processing efficiency membership degree in each time stamp in the information processing efficiency change matrix transferring to another information processing efficiency membership degree; The transition probability value of the information processing efficiency membership at each time stamp in the information processing efficiency change matrix is ​​transferred to another information processing efficiency membership, and the information processing efficiency membership transition probability value matrix is ​​constructed.

4. According to the operation and management method of an e-commerce platform according to claim 1, It is characterized in that Based on the information processing efficiency membership transfer probability value matrix, an information processing efficiency membership transfer probability value prediction model is constructed, and based on the information processing efficiency membership transfer probability value prediction model, the information processing efficiency membership of the e-commerce platform at the current timestamp is obtained, specifically including: Constructing an information processing efficiency membership transfer probability value prediction model based on a convolutional neural network, configuring training parameters of the information processing efficiency membership transfer probability value prediction model, and inputting the information processing efficiency membership transfer probability value matrix into the information processing efficiency membership transfer probability value prediction model; The information processing efficiency membership transfer probability value prediction model is trained according to the training parameters, the trained information processing efficiency membership transfer probability value prediction model is obtained, and the information processing efficiency membership of the e-commerce platform at the current timestamp is obtained; Inputting the information processing efficiency membership of the e-commerce platform at the current timestamp into the trained information processing efficiency membership transition probability value prediction model to predict the transition probability value of the information processing efficiency membership of the e-commerce platform at the current timestamp to another information processing efficiency membership; When the transfer probability value is greater than the preset transfer probability value, another information processing efficiency membership is output as the information processing efficiency membership of the current timestamp; when the transfer probability value is not greater than the preset transfer probability value, the information processing efficiency membership of the e-commerce platform at the current timestamp is output.

5. According to the operation and management method of an e-commerce platform according to claim 1, It is characterized in that By identifying the information processing efficiency membership of the e-commerce platform at the current timestamp, an identification result is obtained, specifically including: Setting an information processing efficiency membership evaluation index, and determining whether the information processing efficiency membership of the e-commerce platform at the current timestamp is greater than the information processing efficiency membership evaluation index; When the information processing efficiency membership of the e-commerce platform at the current timestamp is not greater than the information processing efficiency membership evaluation index, the information processing efficiency membership of the e-commerce platform at the current timestamp is output as an abnormality recognition result; When the information processing efficiency membership of the e-commerce platform at the current timestamp is greater than the information processing efficiency membership evaluation index, the information processing efficiency membership of the e-commerce platform at the current timestamp is output as a normal recognition result.

6. An operation management system for an e-commerce platform, It is characterized in that It includes a memory and a processor, the memory includes an operation and management method program of an e-commerce platform, and when the operation and management method program of the e-commerce platform is executed by the processor, the steps of the operation and management method of the e-commerce platform as described in any one of claims 1-5 are implemented.

7. A terminal device, It is characterized in that include: An acquisition module, used to acquire the information processing volume of the e-commerce platform within a preset time, and to acquire the information processing efficiency membership of the e-commerce platform by evaluating the information processing volume of the e-commerce platform within the preset time; An analysis module, used to construct an information processing efficiency membership change matrix according to the information processing efficiency membership of the e-commerce platform, construct a Markov model based on the Markov chain, and input the information processing efficiency membership change matrix into the Markov model to obtain an information processing efficiency membership transition probability value matrix; A prediction module, used to construct an information processing efficiency membership transfer probability value prediction model based on the information processing efficiency membership transfer probability value matrix, and obtain the information processing efficiency membership of the e-commerce platform at the current timestamp based on the information processing efficiency membership transfer probability value prediction model; A management module, used to identify the information processing efficiency membership of the e-commerce platform at the current timestamp, obtain an identification result, and perform flow limiting management on the e-commerce platform based on the identification result; Among them, the amount of information processed by the e-commerce platform within a preset time is obtained, specifically: The information processing volume of the e-commerce platform under each influencing factor is obtained through big data, and a graph neural network is introduced, with the influencing factor as the first graph node and the information processing volume of the e-commerce platform as the second graph node; Constructing a topological structure graph according to the first graph nodes and the second graph nodes, acquiring a related adjacency matrix based on the topological structure graph, constructing an information processing amount prediction model based on deep neural networks, and inputting the related adjacency matrix into the information processing amount prediction model for training; Obtaining a trained information processing volume prediction model, obtaining real-time influencing factor data of the operation of the e-commerce platform, and inputting the real-time influencing factor data of the operation of the e-commerce platform into the trained information processing volume prediction model for prediction; Obtaining the information processing volume of the e-commerce platform within a preset time through prediction, and outputting the information processing volume of the e-commerce platform within the preset time; Based on the identification result, the e-commerce platform is subjected to flow limiting management, which specifically includes: If the recognition result is an abnormal recognition result, the amount of information accessed by a single user and the number of users' accesses within a preset time are obtained, and the total amount of information within the preset time is calculated based on the amount of information accessed by a single user and the number of users' accesses within the preset time; Obtaining the amount of information processed by the e-commerce platform within a preset time, and determining whether the total amount of information within the preset time is greater than the amount of information processed by the e-commerce platform within the preset time; When the total amount of information within the preset time is greater than the amount of information processed by the e-commerce platform within the preset time, reconfigure the access quantity information of the e-commerce platform within the preset time, generate adjusted access quantity information, and calculate the adjusted total amount of information based on the adjusted access quantity information; When the adjusted total amount of information is no longer greater than the amount of information processed by the e-commerce platform within a preset time, the adjusted access quantity information is output, and access to the e-commerce platform is limited in flow management based on the adjusted access quantity information.

8. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes an operation and management method program of an e-commerce platform. When the operation and management method program of the e-commerce platform is executed by a processor, the steps of the operation and management method of the e-commerce platform as described in any one of claims 1 to 5 are implemented.

Images