A flow distribution method, device, terminal equipment and storage medium

Abstract

The present application provides a traffic distribution method, device, terminal equipment and storage medium, which are applicable to the field of data processing technology. The method includes: obtaining multiple communication module identification information and module traffic load information corresponding to each communication module identification information; the module traffic load information includes multiple initial business traffic load information and remaining traffic information; based on a preset projection transformation function, a preset weight matrix and a preset deviation matrix, predicting and analyzing the multiple initial business traffic load information, and calculating multiple target business traffic load information; according to the target business traffic load information and the remaining traffic information, calculating multiple business traffic allocation information corresponding to each communication module identification information; according to the business traffic allocation information, traffic is allocated to each communication module. The present application predicts and calculates each business traffic load based on communication module aggregation processing to achieve adaptive traffic allocation of communication modules.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular, relates to a flow distribution method, apparatus, terminal equipment and storage medium. Background Art

[0002] With the promotion and application of 5G technology, users' demands for data transmission rate and communication service quality of mobile terminals are increasing. Although 5G network has significantly improved the transmission rate and network capacity compared with traditional LTE network, in some high-density usage scenarios, the bandwidth and transmission capacity of a single 5G or LTE module are insufficient.

[0003] In the prior art, the real-time status of the network is monitored, the used traffic and remaining traffic in the communication network are counted, and the changes in traffic demand are updated in real time, so that the remaining traffic is allocated on demand.

[0004] However, in the existing technology, it is impossible to coordinate and allocate the traffic of multiple communication modules. The traffic allocation of multiple communication modules often lags and is uneven, resulting in services with traffic demands not being able to obtain traffic support in a timely manner and traffic being wasted, thereby extending the communication network delay and reducing network stability. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a traffic distribution method, device, terminal equipment and storage medium, which aim to solve the problem that the existing technology cannot coordinate the planning and distribution of the traffic of communication modules, and when sudden services with large traffic demands appear, lags are easily generated when traffic is distributed to multiple communication modules separately, resulting in low traffic utilization and inability to meet traffic demands in a timely manner, thereby extending communication delays and reducing the overall performance of the communication network.

[0006] A first aspect of an embodiment of the present application provides a flow distribution method, including:

[0007] Acquire multiple communication module identification information and module traffic load information corresponding to each communication module identification information; the module traffic load information includes multiple initial service traffic load information and remaining traffic information;

[0008] Based on a preset projection transformation function, a preset weight matrix, and a preset deviation matrix, a plurality of the initial service traffic load information are predicted and analyzed to calculate a plurality of target service traffic load information;

[0009] Calculate multiple service flow allocation information corresponding to each communication module identification information according to the target service flow load information and the remaining flow information;

[0010] According to the business traffic allocation information, traffic is allocated to each communication module.

[0011] A second aspect of an embodiment of the present application provides a flow distribution device, including:

[0012] An information acquisition module, used to acquire multiple communication module identification information and module traffic load information corresponding to each communication module identification information; the module traffic load information includes multiple initial service traffic load information and remaining traffic information;

[0013] A target service traffic load information calculation module, configured to perform prediction analysis on a plurality of the initial service traffic load information based on a preset projection transformation function, a preset weight matrix, and a preset deviation matrix, and calculate a plurality of target service traffic load information;

[0014] A service flow distribution information calculation module, used to calculate a plurality of service flow distribution information corresponding to each communication module identification information according to the target service flow load information and the remaining flow information;

[0015] The traffic allocation module is used to allocate traffic to each communication module according to the business traffic allocation information.

[0016] A third aspect of an embodiment of the present application provides a terminal device, which includes a memory and a processor, wherein the memory stores a computer program that can be executed on the processor, and when the processor executes the computer program, the steps of the traffic distribution method described in the first aspect above are implemented.

[0017] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, comprising: a computer program stored therein, wherein when the computer program is executed by a processor, the steps of the traffic distribution method described in the first aspect above are implemented.

[0018] Compared with the prior art, the embodiments of the present application have the following beneficial effects: based on the aggregation processing of communication modules, the traffic resources of multiple communication modules are comprehensively planned and allocated, the traffic utilization rate in the communication process is improved, and the multiple business traffic loads of each communication module are predicted and calculated according to the preset projection transformation function and the weight matrix and the deviation matrix. By projecting the multiple business traffic load data of each communication module into a multi-dimensional space for transformation processing, the nonlinear change characteristics of each business traffic load information are extracted and analyzed, and the accuracy of predicting the business traffic load situation is improved, so that traffic can be allocated to each communication module in advance before the outbreak of high-density business, and the communication delay can be reduced to ensure the timeliness and smoothness of business operation, realize adaptive traffic allocation of communication modules, and improve the working performance of the wireless communication network. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 This is a schematic diagram of the implementation flow of the flow distribution method provided in Example 1 of the present application;

[0021] Figure 2 This is a schematic diagram of the implementation flow of the flow distribution method provided in Example 2 of the present application;

[0022] Figure 3 This is a schematic diagram of the implementation flow of the flow distribution method provided in Example 3 of the present application;

[0023] Figure 4 This is a schematic diagram of the implementation flow of the flow distribution method provided in Example 4 of the present application;

[0024] Figure 5 This is a schematic diagram of the implementation flow of the flow distribution method provided in Example 5 of the present application;

[0025] Figure 6 This is a schematic diagram of the implementation flow of the flow distribution method provided in Example 6 of the present application;

[0026] Figure 7 This is a schematic diagram of the implementation flow of the flow distribution method provided in Example 7 of the present application;

[0027] Figure 8 is a schematic diagram of the structure of a flow distribution device provided in an embodiment of the present application;

[0028] Fig. 9 It is a schematic diagram of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0030] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0031] Figure 1The following is a flow chart showing the implementation of the flow distribution method provided in the first embodiment of the present application, which is described in detail as follows:

[0032] Step S101, obtaining multiple communication module identification information and module traffic load information corresponding to each communication module identification information; the module traffic load information includes multiple initial service traffic load information and remaining traffic information.

[0033] In this embodiment, based on the aggregation processing of the communication module, the communication module identification information set when each communication module is registered is collected by the server, and the module traffic load information uploaded by each communication module is summarized. Among them, the communication module identification information is used to identify each communication module, and the module traffic load information includes multiple initial business traffic load information and remaining traffic information. The initial business traffic load information can refer to the current business traffic load information and the historical business traffic load information, or it can only refer to the historical business traffic load information, which is used to predict and calculate the reference value of the allocated traffic for the next traffic allocation cycle. The reference value of the allocated traffic for the next traffic allocation cycle is the target business traffic load information, and the remaining traffic information is the current remaining traffic information of each communication module, that is, the unused traffic information in the currently running communication module. Communication module aggregation refers to integrating multiple communication modules to form a unified communication system or network. This aggregation method can improve communication efficiency, reduce costs, and support multiple communication standards and protocols. Specifically, the aggregation processing of the communication module can be realized based on the source address, domain name address, port, etc., so as to realize the coordination and sharing of traffic of multiple modules.

[0034] Step S102, based on a preset projection transformation function, a preset weight matrix and a preset deviation matrix, a plurality of the initial service flow load information are predicted and analyzed to calculate a plurality of target service flow load information.

[0035] In this embodiment, the preset projection transformation function can be manually set, and can be set based on an exponential function. The preset weight matrix and the preset deviation matrix can be manually set. The initial business traffic load information can be mapped to a high-dimensional space through a projection transformation function, and the initial business traffic load information can be transformed in the high-dimensional space through a weight matrix and a deviation matrix, thereby realizing the extraction and analytical calculation of the nonlinear characteristics of the initial business traffic load information, and the solution result is the target business traffic load information.

[0036] Step S103: Calculate multiple service flow allocation information corresponding to each communication module identification information according to the target service flow load information and the remaining flow information.

[0037] In this embodiment, traffic can be allocated to each communication module based on the target business traffic load information. When the target business traffic load information is less than or equal to the remaining traffic information, the business traffic allocation information corresponding to the identification information of each communication module is the sum of multiple target business traffic load information of a single communication module; but when the target business traffic load information exceeds the remaining traffic information, it can be scheduled from the remaining traffic of other communication modules, and the business traffic allocation information needs to be calculated based on the target business traffic load information and the remaining traffic of other communication modules.

[0038] Step S104: Allocate traffic to each communication module according to the service traffic allocation information.

[0039] In this embodiment, the service traffic allocation information is used as the traffic allocation value for each communication module in the next mobile communication cycle, and traffic is allocated to each communication module, so that each communication module can effectively cope with the situation of traffic burst.

[0040] The traffic distribution method provided in the embodiment of the present application is based on the aggregation processing of communication modules, and the traffic resources of multiple communication modules are comprehensively planned and allocated to improve the traffic utilization rate in the communication process. The multiple business traffic loads of each communication module are predicted and calculated according to the preset projection transformation function and the weight matrix and the deviation matrix. By projecting the multiple business traffic load data of each communication module into a multi-dimensional space for transformation processing, the nonlinear change characteristics of each business traffic load information are extracted and analyzed, and the accuracy of the prediction of the business traffic load situation is improved, so that the traffic is distributed to each communication module in advance before the outbreak of high-density business, and the communication delay is reduced to ensure the timeliness and smoothness of business operation, realize the adaptive traffic distribution of the communication modules, and improve the working performance of the wireless communication network.

[0041] Figure 2 The flow chart of the flow distribution method provided in the second embodiment of the present application is shown, which differs from the first embodiment in that:

[0042] The preset weight matrix includes a preset query weight matrix, a preset key weight matrix and a preset value variable weight matrix;

[0043] The initial service traffic load information includes first service initial traffic information and second service initial traffic information;

[0044] The step S102 specifically includes:

[0045] Step S201: Calculate the traffic change correlation between the first service initial traffic information and the second service initial traffic information.

[0046] In this embodiment, the flow change correlation can be the Spearman correlation coefficient. By calculating the flow change correlation between the initial flow information of the first service and the initial flow information of the second service, the correlation between the two services is quantified. It can be understood that when multiple service flows coexist, there is a mutual correlation between the multiple service flows, and another service flow increases or decreases accordingly. Therefore, the validity of the two service flow data can be determined by calculating the correlation between the two service flows. When the correlation between the two service flows is low, it means that the mutual correlation between the two service flows is weak, and the reference is weak in the long-range relationship prediction calculation.

[0047] Step S202, determine whether the flow change correlation is greater than a preset correlation threshold; if so, proceed to step S203; if not, discard the first service initial flow information and the second service initial flow information corresponding to the flow change correlation.

[0048] In this embodiment, the preset correlation threshold can be set manually. When the flow change correlation is greater than the correlation threshold, it means that the two types of business flows have a high correlation with each other, a large reference in a long-range relationship, and high accuracy and effectiveness. The two types of business flows corresponding to the flow change correlation are used as input data for prediction calculations, and are used to predict the communication module flow of the next communication cycle. When the flow correlation is less than or equal to the correlation threshold, it means that the two types of business flows have a low correlation with each other, a small reference in a long-range relationship, and low accuracy and effectiveness. The two types of business flows corresponding to the flow change correlation cannot be used as input data for prediction calculations. Forcibly using them for flow prediction calculations will interfere with highly effective flow data, so the flow information is discarded.

[0049] Step S203, according to the preset query weight matrix, the preset key weight matrix and the preset value variable weight matrix, the first business initial traffic information and the second business initial traffic information corresponding to the traffic change correlation are respectively encoded and processed to obtain the first business traffic weight information and the second business traffic weight information.

[0050] In this embodiment, the preset query weight matrix, the preset key weight matrix, and the preset value variable weight matrix can be manually set. The preset query weight matrix, the preset key weight matrix, and the preset value variable weight matrix can be respectively multiplied or convolved with the first service initial flow information and the second service initial flow information to extract the numerical features in the first service initial flow information and the second service initial flow information from different dimensions, and then the extracted multi-dimensional features are dimensionally transformed to complete the encoding process and obtain the first service flow weight information and the second service flow weight information.

[0051] Step S204, calculating a plurality of service flow coding variables according to the first service flow weight information, the second service flow weight information, the first service initial flow information and the second service initial flow information.

[0052] In this embodiment, the first service flow weight information and the first service initial flow information may be multiplied, and the second service flow weight information and the second service initial flow information may be multiplied, respectively, to obtain a plurality of service flow coding variables. It can be understood that the first service flow weight information, the second service flow weight information, the first service initial flow information, and the second service initial flow information are all calculated in the form of a matrix.

[0053] Step S205, performing dimensionality reduction processing on the business traffic coding variable to obtain multiple business traffic coding intermediate variables.

[0054] In this embodiment, the business traffic coding variable is presented in the form of a multi-dimensional matrix. The multi-dimensional matrix can be flattened to obtain multiple one-dimensional matrices. The obtained one-dimensional matrix is ​​the business traffic coding intermediate variable, which is used to reduce the amount of calculation and computational complexity and improve the solution efficiency of the prediction calculation process.

[0055] Step S206, performing projection transformation calculation on the service flow coding intermediate variable according to a preset projection transformation function and a preset deviation matrix to obtain a plurality of service flow decoding variables.

[0056] In this embodiment, the preset projection transformation function and the preset deviation matrix can be manually set, wherein the preset projection transformation function can be set based on an exponential function. It can be that an iteration number is first set, the service flow coding intermediate variable is used as the independent variable of the projection transformation function, the function value obtained by calculation is used as the first decoding intermediate variable, and then the first decoding intermediate variable is summed with the preset deviation matrix to obtain the second decoding intermediate variable, and then the second decoding intermediate variable is used as the independent variable of the projection transformation function again, and the second decoding intermediate variable is summed with the preset deviation matrix to obtain the fourth decoding intermediate variable, and so on, when the number of cycles is equal to the number of iterations, the variable value output at the end is used as the service flow decoding variable, so as to realize the projection transformation calculation of the service flow coding intermediate variable, fully understand the nonlinear components in the service flow coding intermediate variable, and fully analyze the nonlinear components to realize the prediction calculation of the service flow.

[0057] Step S207: Calculate multiple target service traffic load information according to the multiple service traffic decoding variables.

[0058] In this embodiment, the service traffic decoding variable is presented in the form of a matrix, so the matrix needs to be formatted and converted into numerical information before it can be output as multiple target service traffic load information. Specifically, the service traffic decoding variable in the form of a matrix can be firstly subjected to string extraction, and then the extracted string can be converted into a numerical format for output.

[0059] The traffic allocation method provided in the embodiment of the present application first calculates the correlation of multiple business traffic information, and puts two groups of business traffic with high mutual correlation into prediction calculation to ensure the validity and reliability of the business traffic data for prediction calculation, avoids the interference of low-validity business traffic data on the prediction calculation process, and improves the validity and accuracy of the prediction results of the business traffic. Multi-dimensional calculation is performed with multiple preset weight matrices and business traffic information to ensure that the autocorrelation characteristics, mutual correlation characteristics and long-term correlation characteristics of the business traffic information are fully extracted to ensure that important features are not missed in the encoding and decoding process. The extracted feature variables are projected into a multi-dimensional space for decoding processing, so that the nonlinear characteristics in the autocorrelation characteristics, mutual correlation characteristics and long-term correlation characteristics can be fully analyzed, thereby improving the accuracy and robustness of the prediction of the business traffic information, facilitating the subsequent effective allocation of traffic according to the prediction results, so as to improve the operating performance of the wireless communication network.

[0060] Figure 3 The flow chart of the implementation of the flow distribution method provided in the third embodiment of the present application is shown. The difference between the third embodiment and the second embodiment is that the step S203 specifically includes:

[0061] Step S301, calculate the first business traffic query weight matrix, the first business traffic key weight matrix, the first business traffic value variable weight matrix, the second business traffic query weight matrix, the second business traffic key weight matrix and the second business traffic value variable weight matrix according to the preset query weight matrix, the preset key weight matrix, the preset value variable weight matrix and the first business initial traffic information and the second business initial traffic information.

[0062] In this embodiment, the preset query weight matrix, the preset key weight matrix, and the preset value variable weight matrix can be manually set. It can be that the first service initial flow information is firstly inner-producted with the query weight matrix, the key weight matrix, and the value variable weight matrix to obtain the first service flow query weight matrix, the first service flow key weight matrix, and the first service flow value variable weight matrix; and then the second service initial flow information is inner-producted with the query weight matrix, the key weight matrix, and the value variable weight matrix to obtain the second service flow query weight matrix, the second service flow key weight matrix, and the second service flow value variable weight matrix.

[0063] Step S302, calculate the first business traffic weight intermediate variable matrix and the second business traffic weight intermediate variable matrix according to the first business traffic query weight matrix, the first business traffic key weight matrix, the second business traffic query weight matrix and the second business traffic key weight matrix.

[0064] In this embodiment, the first business traffic query weight matrix can be multiplied with the transposed first business traffic key weight matrix to obtain the first business traffic weight intermediate variable matrix, and the second business traffic query weight matrix can be multiplied with the transposed second business traffic key weight matrix to obtain the second business traffic weight intermediate variable matrix.

[0065] Step S303: Scaling and exponential transformation are performed on the first service flow weight intermediate variable matrix and the second service flow weight intermediate variable matrix to obtain a first service flow coding weight matrix and a second service flow coding weight matrix.

[0066] In this embodiment, the dimension of the key weight matrix may be determined first, and the square root of the dimension is taken as the scaling factor, and the scaling factor is multiplied with the first service flow weight intermediate variable matrix and the second service flow weight intermediate variable matrix respectively, so as to realize the scaling processing of the first service flow weight intermediate variable matrix and the second service flow weight intermediate variable matrix. The scaled variable may be subjected to exponential transformation processing. Specifically, the exponential transformation processing may be to use the scaled variable as the independent variable of the exponential function, and then calculate the function value of the exponential function, and then use the function value obtained after the exponential transformation of a single scaled variable as the numerator, and the sum of the function values ​​obtained after the exponential transformation of all scaled variables as the denominator, so as to realize the encoding operation, and calculate the first service flow encoding weight matrix and the second service flow encoding weight matrix.

[0067] Step S304: multiply the first service traffic coding weight matrix by the first service traffic value variable weight matrix to obtain first service traffic weight information.

[0068] In this embodiment, an inner product operation may be performed on the first service flow coding weight matrix and the first service flow value variable weight matrix, and the calculation result is the first service flow weight information.

[0069] Step S305: multiply the second service flow coding weight matrix by the second service flow value variable weight matrix to obtain second service flow weight information.

[0070] In this embodiment, the inner product operation may be performed on the second service flow coding weight matrix and the second service flow value variable weight matrix, and the calculation result is the second service flow weight information.

[0071] The traffic distribution method provided in the embodiment of the present application is used to perform feature extraction on the business traffic information by calculating the overall sequence composed of a preset query weight matrix, a key weight matrix, and a value variable weight matrix respectively with the business traffic information, so as to ensure that the nonlinear features of each dimension of the business traffic information are fully extracted, so that the extracted feature information is richer, and the feature expression capability of the computing network is enhanced. By encoding the extracted feature information, the weight value of each feature information is calculated to quantify the importance of each feature information in the multidimensional space, so that the features with high importance can be fully extracted and utilized in the process of prediction and calculation, thereby improving the accuracy and robustness of the prediction of business traffic, so as to enhance the effectiveness and reliability of subsequent traffic distribution.

[0072] Figure 4 The flowchart of the flow distribution method provided in the fourth embodiment of the present application is shown. The difference between the fourth embodiment and the second embodiment is that the step S203 specifically includes:

[0073] Step S401, calculate the first business traffic query weight matrix, the first business traffic key weight matrix, the second business traffic query weight matrix and the second business traffic key weight matrix according to the preset query weight matrix, the preset key weight matrix and the first business initial traffic information and the second business initial traffic information.

[0074] In this embodiment, the preset query weight matrix can be multiplied with the first business initial traffic information and the second business initial traffic information respectively to obtain the first business traffic query weight matrix and the second business traffic query weight matrix; the preset key weight matrix can be multiplied with the first business initial traffic information and the second business initial traffic information respectively to obtain the first business traffic key weight matrix and the second business traffic key weight matrix.

[0075] Step S402: Calculate the similarity between the first service flow query weight matrix and the first service flow key weight matrix to obtain a first service flow query weight correlation matrix.

[0076] In this embodiment, the first service flow query weight matrix and the first service flow key weight matrix may be subjected to a dot product operation, and the operation result, namely the first service flow query weight correlation matrix, is used to quantify the correlation of the nonlinear characteristics of the two dimensions of the first service flow information. It can be understood that the service flow has autocorrelation, which needs to be considered when performing prediction calculations.

[0077] Step S403: Calculate the similarity between the second service flow query weight matrix and the second service flow key weight matrix to obtain a second service flow query weight correlation matrix.

[0078] In this embodiment, the second business traffic query weight matrix and the second business traffic key weight matrix may be subjected to a dot product operation, and the operation result, i.e., the correlation of the second business traffic query weight matrix, is used to quantify the correlation of the nonlinear characteristics of the two dimensions of the first business traffic information, so that in the subsequent calculation process, the autocorrelation characteristics of the business traffic can be fully considered.

[0079] Step S404: normalize the first business traffic query weight relevance matrix and the second business traffic query weight relevance matrix to obtain a first business traffic query weight contribution matrix and a second business traffic query weight contribution matrix.

[0080] In this embodiment, the first business traffic query weight correlation matrix and the second business traffic query weight correlation matrix can be normalized by a softmax function. Specifically, the first business traffic query weight correlation matrix and the second business traffic query weight correlation matrix can be used as independent variables of the softmax function respectively, and the calculated function values, namely the first business traffic query weight contribution matrix and the second business traffic query weight contribution matrix, are used to quantify the importance of the weights of each nonlinear feature in the business traffic, and are used to subsequently calculate the weights of each nonlinear feature.

[0081] Step S405: Perform weighted summation on the first business traffic query weight contribution matrix and the preset value variable weight matrix to obtain first business traffic weight information.

[0082] In this embodiment, the first business traffic query weight contribution matrix is ​​weighted and summed according to the preset value variable weight matrix. The summation result is the first business traffic weight information, which is used to quantify the importance of each nonlinear feature in the first business traffic information, increase the logical distance between each feature, and ensure that features with high importance are not ignored.

[0083] Step S406: Perform weighted summation on the second business traffic query weight contribution matrix and the preset value variable weight matrix to obtain second business traffic weight information.

[0084] In this embodiment, the second business traffic query weight contribution matrix is ​​weighted and summed according to the preset value variable weight matrix. The summation result is the second business traffic weight information, which is used to quantify the importance of each nonlinear feature in the second business traffic information, increase the logical distance between each nonlinear feature, and ensure that nonlinear features with high importance are not omitted.

[0085] The traffic distribution method provided in the embodiment of the present application uses a preset query weight matrix and a key weight matrix to respectively extract features of sequence segments at different positions in a sequence composed of business traffic information, so as to perform single-dimensional extraction of the business traffic information, thereby reducing the computational complexity and being able to fully extract the long-correlation features of the business traffic information. Feature weights are calculated for different sequence segments based on the long-correlation features, so that the long-correlation of the business traffic is considered in the process of traffic prediction calculation, and the matrix is ​​normalized in time during the calculation process to avoid the generation of invalid values ​​due to the numerical values ​​exceeding the dimension during the calculation process, thereby ensuring the validity of each numerical value during the calculation process, thereby improving the prediction accuracy of the business traffic information, thereby improving the accuracy and reliability of subsequent traffic distribution, and ensuring the working stability of the wireless communication network.

[0086] Figure 5 The flowchart of the flow distribution method provided in the fifth embodiment of the present application is shown. The difference between the fifth embodiment and the first embodiment is that the step S103 specifically includes:

[0087] Step S501, determine whether the target service traffic load information is less than the remaining traffic information; if so, proceed to step S502; if not, proceed to step S503.

[0088] In this embodiment, when the target service traffic load information is less than the remaining traffic information, it means that the current remaining traffic is sufficient for the normal operation of the service in the next communication cycle, and there is no need to schedule the remaining traffic of other communication modules; when the target service traffic load information is greater than or equal to the remaining traffic information, it means that the current remaining traffic is insufficient for the normal operation of the service in the next communication cycle, and some services will not be able to obtain sufficient traffic support, so the remaining traffic of other communication modules needs to be scheduled for service support.

[0089] Step S502: Calculate multiple service flow distribution information corresponding to each communication module identification information according to the target service flow load information.

[0090] In this embodiment, when the target service traffic load information is less than the remaining traffic information, it means that the current remaining traffic is sufficient for the normal operation of the service in the next communication cycle, and there is no need to schedule the remaining traffic of other communication modules. Therefore, the target service traffic load information can be used as multiple service traffic allocation information corresponding to the identification information of each communication module, or it can be incrementally calculated on the basis of the target service traffic load information within the scope permitted by the remaining traffic information to obtain multiple service traffic allocation information corresponding to the identification information of each communication module. It can be understood that when the remaining traffic is large, more traffic can be allocated to the communication module to ensure smooth operation of the communication service and avoid sudden communication services from squeezing out the traffic of the communication service that is already in operation.

[0091] Step S503: extract the communication module identification information corresponding to the target service traffic load information, and mark it as traffic overload module identification information.

[0092] In this embodiment, when the target service traffic load information is greater than or equal to the remaining traffic information, it means that the current remaining traffic is insufficient for the normal operation of the service in the next communication cycle, and some services will not be able to obtain sufficient traffic support. Therefore, it is necessary to determine the communication module identification information corresponding to the target service traffic load information, and then mark the communication module identification information as traffic overload module identification information, which is used for subsequent scheduling of the remaining traffic of other communication modules to provide service support for the communication module corresponding to the traffic overload module identification information.

[0093] Step S504: determine the adjacent module of the communication module corresponding to the traffic overload module identification information.

[0094] In this embodiment, the adjacent modules can be determined based on the source address, domain name address, port, etc. For example, based on the source address or domain name address of the registration data of the communication module, the routing table information where the source address or domain name address appears is found, and the communication path of the registration data is tracked through the routing table information to obtain multiple adjacent modules.

[0095] Step S505: Calculate multiple service flow allocation information corresponding to each communication module identification information according to the target service flow load information and the remaining flow information of the adjacent modules.

[0096] In this embodiment, it can be determined whether the residual flow information of the adjacent module is sufficient. When the residual flow information of the adjacent module is sufficient, the difference between the target business flow load information of the communication module itself and the residual flow is filled by the residual flow of the adjacent module. When the residual flow information of the adjacent module is sufficient to fill the difference between the target business flow load information and the residual flow, the calculated business flow allocation information is the target business flow load information. When the residual flow information of the adjacent module is not sufficient to fill the difference between the target business flow load information and the residual flow, the calculated business flow allocation information is the sum of the residual flow value of the communication module itself and the residual flow value that the adjacent module can provide. It can be understood that a communication module can have multiple adjacent modules.

[0097] The traffic allocation method provided in the embodiment of the present application determines whether the current remaining traffic of the communication module is sufficient to support the normal and immediate operation of the communication service by judging the size relationship between the target service traffic load information and the remaining traffic information. If the current remaining traffic of the communication module is not sufficient to support the normal operation of the communication service, the adjacent modules of the communication module are determined, and traffic scheduling is performed from the adjacent modules to fill the traffic gap in the communication module, thereby ensuring the normal operation of various services in the wireless communication network, and effectively reducing the probability of communication user complaints during service bursts.

[0098] Figure 6 The flowchart of the flow distribution method provided in the sixth embodiment of the present application is shown. The difference between the sixth embodiment and the first embodiment is that after the step S104, the method further includes:

[0099] Step S601, obtaining protection time slot information and traffic usage information of each communication module.

[0100] In this embodiment, the protection time slot information of each communication module that has been aggregated and the traffic usage information after traffic allocation can be collected by the server. The protection time slot information and traffic usage information can also be reported to the server by each communication module after aggregation. In the field of wireless communications, the main function of the protection time slot is to prevent inter-code interference. By separating two types of communication information transmitted in the same channel in a certain time domain resource, interference between the two types of communication information is avoided. It can be understood that the protection time slot occupies a certain traffic space during the communication process. The protection time slot information can also be the protection time slot configuration information set during the factory or debugging process of the communication module, which can be used to characterize the duration of the protection time slot and the number of occurrences during the communication process.

[0101] Step S602, determine whether the traffic usage information is greater than or equal to a preset traffic usage threshold; if so, determine the communication module identification information corresponding to the traffic usage information as excessive traffic usage module identification information; if not, determine the communication module identification information corresponding to the traffic usage information as normal traffic usage module identification information.

[0102] In this embodiment, the preset traffic usage threshold can be set manually. It can be understood that each communication module is provided with a traffic usage threshold to prevent the communication module from being overloaded and causing irreparable damage to hardware resources, and to avoid frequent server crashes or restarts, while avoiding slow access speeds or even inability to connect, and to prevent the communication module from being vulnerable to hacker attacks in an overloaded state. When the traffic usage information is greater than or equal to the preset traffic usage threshold, it means that the communication module corresponding to the traffic usage information is already overloaded and can no longer be allocated more traffic resources. The communication module identification information is determined as traffic overuse module identification information, which is used to adjust the protection time slot in the subsequent process, so that the increased traffic resources after adjusting the protection time slot can be used to support the normal operation of the business. When the traffic usage information is less than the preset traffic usage threshold, it means that the communication module corresponding to the traffic usage information is not overloaded, and there is no need to stop the additional traffic allocation to it, and there is no need to control and adjust its protection time slot, so the communication module identification information corresponding to the communication module is determined as traffic normal use module identification information.

[0103] Step S603: determining the protection time slot information corresponding to the traffic overuse module identification information as the protection time slot information to be adjusted.

[0104] In this embodiment, when the traffic usage information is greater than or equal to the preset traffic usage threshold, it means that the communication module corresponding to the traffic usage information is already overloaded and can no longer be allocated more traffic resources. Then the communication module identification information is determined as traffic overuse module identification information, which is used to adjust the protection time slot in the subsequent process, so that the increased traffic resources after the protection time slot is adjusted can be used to support the normal operation of the service. Therefore, it is necessary to determine the protection time slot information of the communication module and determine it as the protection time slot information to be adjusted, so as to facilitate subsequent adjustment.

[0105] Step S604: adjusting the protection time slot information to be adjusted according to a preset protection time slot adjustment range to obtain adjusted protection time slot information.

[0106] In this embodiment, the preset guard time slot adjustment range can be manually set, and can be set with reference to the communication protocol standard in the field of wireless communication. The guard time slot information to be adjusted can be adjusted in duration and quantity based on the preset guard time slot adjustment range, thereby obtaining the adjusted guard time slot information.

[0107] The traffic allocation method provided in the embodiment of the present application, when the traffic usage of a communication module is determined to be excessive traffic usage, traffic allocation for the communication module can no longer be continued. In this way, the protection time slot of the communication module is adjusted to reduce the traffic occupancy of the protection time slot during the communication process, so as to provide more traffic for burst services, reduce network latency, ensure the timeliness of the operation of communication services, and improve the service operation quality of each communication module in the communication network, thereby reducing the probability of complaints from users of the wireless communication network in the event of a service emergency.

[0108] Figure 7 The flowchart of the flow distribution method provided in the seventh embodiment of the present application is shown, which differs from the sixth embodiment in that:

[0109] The to-be-adjusted protection time slot information includes to-be-adjusted protection time slot quantity information and to-be-adjusted protection time slot length information;

[0110] The preset guard time slot adjustment range includes a preset guard time slot quantity adjustment range and a preset guard time slot length adjustment range;

[0111] The step S604 specifically includes:

[0112] Step S701, calculating the reduction amount of the number of protection time slots according to the preset adjustment range of the number of protection time slots and the information of the number of protection time slots to be adjusted.

[0113] In this embodiment, the preset adjustment range of the number of protection time slots can be set manually, can be set with reference to the corresponding protocol standard in the communication field, or can be set during the factory or debugging of the communication module. According to the preset adjustment range of the number of protection time slots, the information on the number of protection time slots to be adjusted in the current communication module is adjusted, and the reduction in the number of protection time slots is calculated, thereby reducing the number of protection time slots generated in the next communication cycle. For example, when transmitting three different business traffic flows, the number of protection time slots required to be used may be 5. When these three business data packets are transmitted using the same communication protocol, it can be reduced to 2, and the reduction in the number of protection time slots is 3.

[0114] Step S702: Calculate the reduction amount of the guard time slot length according to the preset guard time slot length adjustment range and the guard time slot length information to be adjusted.

[0115] In this embodiment, the preset protection time slot length adjustment range can be set manually, can be set with reference to the corresponding protocol standard in the communication field, or can be set during the factory or debugging of the communication module. According to the preset protection time slot length adjustment range, the protection time slot length information to be adjusted in the current communication module is adjusted, and the reduction amount of the protection time slot length is calculated, thereby reducing the length of the protection time slot in the next communication cycle. For example, the original protection time slot between the uplink signaling and the downlink signaling can be, the length of a protection time slot can be 0.3 milliseconds, which can be reduced by 0.1 milliseconds to 0.2 milliseconds, then 0.1 milliseconds is the reduction amount of the protection time slot length.

[0116] Step S703, obtaining the adjusted protection time slot information according to the to-be-adjusted protection time slot information, the reduction amount of the number of protection time slots, and the reduction amount of the protection time slot length.

[0117] In this embodiment, the number of guard time slot information to be adjusted is adjusted by the reduction amount of the guard time slot number, and the length of the guard time slot information to be adjusted is adjusted by the reduction amount of the guard time slot length, so as to obtain the adjusted guard time slot information.

[0118] The traffic distribution method provided in the embodiment of the present application adjusts the protection time slot information to be adjusted according to the preset protection time slot quantity adjustment range and the protection time slot length adjustment range, while ensuring that the inter-code interference in the communication process is not sufficient to affect the communication quality, saving the bandwidth occupied by the protection time slot, so that when the business volume is high, there can be more traffic for the normal operation of the business, improving the operating efficiency and quality of the communication business, ensuring network performance during the time period of intensive business volume, and reducing the complaint rate of communication users.

[0119] Corresponding to the method of the above embodiment, Figure 8 A structural block diagram of a flow distribution device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown. Figure 8 The exemplary flow distribution device may be an execution subject of the flow distribution method provided in the aforementioned first embodiment.

[0120] Reference Figure 8 , the flow distribution device comprises:

[0121] The information acquisition module 810 is used to acquire multiple communication module identification information and module traffic load information corresponding to each communication module identification information; the module traffic load information includes multiple initial service traffic load information and remaining traffic information;

[0122] The target service traffic load information calculation module 820 is used to perform prediction analysis on the multiple initial service traffic load information based on a preset projection transformation function, a preset weight matrix and a preset deviation matrix, and calculate multiple target service traffic load information;

[0123] The service flow distribution information calculation module 830 is used to calculate a plurality of service flow distribution information corresponding to each communication module identification information according to the target service flow load information and the remaining flow information;

[0124] The traffic allocation module 840 is used to allocate traffic to each communication module according to the business traffic allocation information.

[0125] The process of each module in the flow distribution device provided in the embodiment of the present application realizing its own function can be specifically referred to the aforementioned Figure 1 The description of the first embodiment is not repeated here.

[0126] The method implemented by the traffic distribution device provided in the embodiment of the present application is based on the aggregation processing of communication modules, and the traffic resources of multiple communication modules are comprehensively planned and allocated to improve the traffic utilization rate during the communication process. The multiple business traffic loads of each communication module are predicted and calculated according to the preset projection transformation function and the weight matrix and the deviation matrix. By projecting the multiple business traffic load data of each communication module into a multi-dimensional space for transformation processing, the nonlinear change characteristics of each business traffic load information are extracted and analyzed, and the accuracy of the prediction of the business traffic load situation is improved, so that the traffic is distributed to each communication module in advance before the outbreak of high-density business, and the communication delay is reduced to ensure the timeliness and smoothness of business operation, realize the adaptive traffic distribution of the communication modules, and improve the working performance of the wireless communication network.

[0127] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0128] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0129] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0130] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0131] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish descriptions, and cannot be understood as indicating or suggesting relative importance. It should also be understood that although the terms "first", "second", etc. are used to describe various elements in some embodiments of the present application in the text, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, the first table can be named as the second table, and similarly, the second table can be named as the first table without departing from the scope of the various described embodiments. The first table and the second table are both tables, but they are not the same table.

[0132] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0133] The traffic distribution method provided in the embodiment of the present application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc. The embodiment of the present application does not impose any restrictions on the specific type of terminal devices.

[0134] For example, the terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a TV set top box (STB), a customer premises equipment (CPE) and / or other devices for communicating on a wireless system and a next-generation communication system, such as a mobile terminal in a 5G network or a mobile terminal in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0135] As an example but not limitation, when the terminal device is a wearable device, the wearable device can also be a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not just hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0136] Fig. 9 Schematic diagram of the structure of a terminal device provided by an embodiment of the present application. Fig. 9 As shown, the terminal device 9 of this embodiment includes: at least one processor 90 ( Fig. 9 Only one is shown in the figure), a memory 91, wherein the memory 91 stores a computer program 92 that can be run on the processor 90. When the processor 90 executes the computer program 92, the steps in the above-mentioned various flow distribution method embodiments are implemented, such as Figure 1 Alternatively, when the processor 90 executes the computer program 92, the functions of each module / unit in the above-mentioned device embodiments are realized, for example Figure 8Functions of modules 810 to 840 are shown.

[0137] The terminal device 9 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device may include, but is not limited to, a processor 90 and a memory 91. Those skilled in the art will appreciate that Fig. 9 It is only an example of the terminal device 9 and does not constitute a limitation on the terminal device 9. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include an input sending device, a network access device, a bus, etc.

[0138] The processor 90 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0139] In some embodiments, the memory 91 may be an internal storage unit of the terminal device 9, such as a hard disk or memory of the terminal device 9. The memory 91 may also be an external storage device of the terminal device 9, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 9. Further, the memory 91 may also include both an internal storage unit of the terminal device 9 and an external storage device. The memory 91 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 91 may also be used to temporarily store data that has been sent or is to be sent.

[0140] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0141] An embodiment of the present application also provides a terminal device, which includes at least one memory, at least one processor, and a computer program stored in the at least one memory and executable on the at least one processor, wherein when the processor executes the computer program, the terminal device implements the steps in any of the above-mentioned method embodiments.

[0142] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0143] An embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0144] If the integrated module / unit 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 present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0145] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0146] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0147] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, 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 solution of this embodiment.

[0148] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A flow distribution method, characterized in that: include: Obtain multiple communication module identification information and module traffic load information corresponding to each communication module identification information; The module traffic load information includes a plurality of initial service traffic load information and remaining traffic information; Based on a preset projection transformation function, a preset weight matrix, and a preset deviation matrix, a plurality of the initial service traffic load information are predicted and analyzed to calculate a plurality of target service traffic load information; Calculate multiple service flow allocation information corresponding to each communication module identification information according to the target service flow load information and the remaining flow information; Allocate traffic to each communication module according to the service traffic allocation information; The preset weight matrix includes a preset query weight matrix, a preset key weight matrix and a preset value variable weight matrix; The initial service traffic load information includes first service initial traffic information and second service initial traffic information; The step of performing prediction analysis on the multiple initial service traffic load information based on the preset projection transformation function, the preset weight matrix and the preset deviation matrix to calculate the multiple target service traffic load information specifically includes: Calculating the flow change correlation between the initial flow information of the first service and the initial flow information of the second service; When the traffic change correlation is greater than a preset correlation threshold, encoding the first service initial traffic information and the second service initial traffic information corresponding to the traffic change correlation are respectively processed according to a preset query weight matrix, a preset key weight matrix, and a preset value variable weight matrix to obtain first service traffic weight information and second service traffic weight information; Calculate multiple service flow coding variables according to the first service flow weight information, the second service flow weight information, the first service initial flow information and the second service initial flow information; Performing dimensionality reduction processing on the business flow coding variable to obtain multiple business flow coding intermediate variables; According to a preset projection transformation function and a preset deviation matrix, a projection transformation calculation is performed on the service flow coding intermediate variable to obtain a plurality of service flow decoding variables; Based on the multiple business traffic decoding variables, multiple target business traffic load information is calculated.

2. The flow distribution method according to claim 1, characterized in that: The step of encoding the first service initial flow information and the second service initial flow information corresponding to the flow change correlation according to the preset query weight matrix, the preset key weight matrix and the preset value variable weight matrix to obtain the first service flow weight information and the second service flow weight information specifically includes: According to the preset query weight matrix, the preset key weight matrix, the preset value variable weight matrix, and the first business initial traffic information and the second business initial traffic information, calculate the first business traffic query weight matrix, the first business traffic key weight matrix, the first business traffic value variable weight matrix, the second business traffic query weight matrix, the second business traffic key weight matrix, and the second business traffic value variable weight matrix; Calculate a first business traffic weight intermediate variable matrix and a second business traffic weight intermediate variable matrix according to the first business traffic query weight matrix, the first business traffic key weight matrix, the second business traffic query weight matrix and the second business traffic key weight matrix; Scaling and exponentially transforming the first service flow weight intermediate variable matrix and the second service flow weight intermediate variable matrix to obtain a first service flow coding weight matrix and a second service flow coding weight matrix; Multiplying the first service flow coding weight matrix by the first service flow value variable weight matrix to obtain first service flow weight information; The second service flow coding weight matrix is ​​multiplied by the second service flow value variable weight matrix to obtain second service flow weight information.

3. The flow distribution method according to claim 1, characterized in that: The step of encoding the first service initial flow information and the second service initial flow information corresponding to the flow change correlation according to the preset query weight matrix, the preset key weight matrix and the preset value variable weight matrix to obtain the first service flow weight information and the second service flow weight information specifically includes: Calculate the first service traffic query weight matrix, the first service traffic key weight matrix, the second service traffic query weight matrix, and the second service traffic key weight matrix according to the preset query weight matrix, the preset key weight matrix, and the first service initial traffic information and the second service initial traffic information; Calculate the similarity between the first service flow query weight matrix and the first service flow key weight matrix to obtain a first service flow query weight correlation matrix; Calculate the similarity of the second service flow query weight matrix and the second service flow key weight matrix to obtain a second service flow query weight correlation matrix; Normalizing the first service flow query weight correlation matrix and the second service flow query weight correlation matrix to obtain a first service flow query weight contribution matrix and a second service flow query weight contribution matrix; Performing weighted summation on the first service flow query weight contribution matrix and the preset value variable weight matrix to obtain first service flow weight information; The second business traffic query weight contribution matrix and the preset value variable weight matrix are weighted and summed to obtain the second business traffic weight information.

4. The flow distribution method according to claim 1, characterized in that: The step of calculating the multiple service flow allocation information corresponding to each communication module identification information according to the target service flow load information and the remaining flow information specifically includes: Determining whether the target service traffic load information is less than the remaining traffic information; If yes, then calculating multiple service flow allocation information corresponding to each communication module identification information according to the target service flow load information; If not, extracting the communication module identification information corresponding to the target service traffic load information and marking it as traffic overload module identification information; Determine an adjacent module of the communication module corresponding to the traffic overload module identification information; According to the target service flow load information and the remaining flow information of the adjacent modules, multiple service flow allocation information corresponding to the identification information of each communication module is calculated.

5. The flow distribution method according to claim 1, characterized in that: After the step of distributing traffic to each communication module according to the service traffic distribution information, the method further includes: Obtain protection time slot information and traffic usage information of each communication module; When the traffic usage information is greater than or equal to a preset traffic usage threshold, determining the communication module identification information corresponding to the traffic usage information as traffic overuse module identification information; Determining the protection time slot information corresponding to the traffic overuse module identification information as the protection time slot information to be adjusted; According to the preset protection time slot adjustment range, the protection time slot information to be adjusted is adjusted to obtain the adjusted protection time slot information.

6. The flow distribution method according to claim 5, characterized in that: The to-be-adjusted protection time slot information includes to-be-adjusted protection time slot quantity information and to-be-adjusted protection time slot length information; The preset guard time slot adjustment range includes a preset guard time slot quantity adjustment range and a preset guard time slot length adjustment range; The step of adjusting the to-be-adjusted protection time slot information according to the preset protection time slot adjustment range to obtain the adjusted protection time slot information specifically includes: Calculate the reduction amount of the number of protection time slots according to the preset adjustment range of the number of protection time slots and the information of the number of protection time slots to be adjusted; Calculate the reduction amount of the protection time slot length according to the preset protection time slot length adjustment range and the protection time slot length information to be adjusted; The adjusted protection time slot information is obtained according to the to-be-adjusted protection time slot information, the reduction amount of the number of protection time slots, and the reduction amount of the protection time slot length.

7. A flow distribution device, characterized in that: include: An information acquisition module, used to acquire identification information of multiple communication modules and module traffic load information corresponding to the identification information of each communication module; The module traffic load information includes a plurality of initial service traffic load information and remaining traffic information; A target service traffic load information calculation module, configured to perform prediction analysis on a plurality of the initial service traffic load information based on a preset projection transformation function, a preset weight matrix, and a preset deviation matrix, and calculate a plurality of target service traffic load information; A service flow distribution information calculation module, used to calculate a plurality of service flow distribution information corresponding to each communication module identification information according to the target service flow load information and the remaining flow information; A traffic distribution module, used to distribute traffic to each communication module according to the service traffic distribution information; The preset weight matrix includes a preset query weight matrix, a preset key weight matrix and a preset value variable weight matrix; The initial service traffic load information includes first service initial traffic information and second service initial traffic information; The step of performing prediction analysis on the multiple initial service traffic load information based on the preset projection transformation function, the preset weight matrix and the preset deviation matrix to calculate the multiple target service traffic load information specifically includes: Calculating the flow change correlation between the initial flow information of the first service and the initial flow information of the second service; When the traffic change correlation is greater than a preset correlation threshold, encoding the first service initial traffic information and the second service initial traffic information corresponding to the traffic change correlation are respectively processed according to a preset query weight matrix, a preset key weight matrix, and a preset value variable weight matrix to obtain first service traffic weight information and second service traffic weight information; Calculate multiple service flow coding variables according to the first service flow weight information, the second service flow weight information, the first service initial flow information and the second service initial flow information; Performing dimensionality reduction processing on the business flow coding variable to obtain multiple business flow coding intermediate variables; According to a preset projection transformation function and a preset deviation matrix, a projection transformation calculation is performed on the service flow coding intermediate variable to obtain a plurality of service flow decoding variables; Based on the multiple business traffic decoding variables, multiple target business traffic load information is calculated.

8. A terminal device, characterized in that: The terminal device includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images