Gateway traffic prediction method and device, fusing method and device, equipment and storage medium

Abstract

The invention relates to the technical field of traffic prediction, and particularly provides a gateway traffic prediction method and device, a fusing method and device, equipment and a storage medium. The gateway traffic prediction method comprises the steps that a thermodynamic matrix graph is acquired, and the thermodynamic matrix graph takes a coding value of a service information index vector of a network element as a first coordinate axis, takes a time slice as a second coordinate axis, and takes a color of a pixel point to represent a traffic value of the corresponding network element under the corresponding time slice; and predicting the network element traffic based on the thermodynamic matrix graph. The invention discloses a micro-service fusing method. The method comprises the following steps: acquiring network element traffic predicted according to a gateway traffic prediction method; and executing the fusing strategy according to the network element flow. By implementing the technical scheme of the invention, the accuracy of network element traffic prediction can be improved, and the fusing misjudgment can be reduced.

Description

Technical Field

[0001] The present disclosure relates to the technical field of traffic prediction, and in particular to a gateway traffic prediction method, a fuse method, an apparatus, a device and a storage medium. Background Art

[0002] In the technical solutions of the existing microservice architecture, the gateway fuse technology is mainly based on the adaptive fuse technology of the amount of data accessed by the microservice. It dynamically adjusts the fuse strategy according to the real-time data volume accessed by the service. When the amount of data accessed by the service exceeds a certain threshold, the system may automatically trigger the fuse operation to prevent the service from overloading or crashing. Specific adaptive fuse strategies include: dynamically adjusting the fuse threshold, automatically switching the fuse state according to the change of data volume, etc.

[0003] However, since adaptive fusing is decided by the system based on real-time data, and network element traffic monitoring data has problems such as poor real-time performance and data detection errors, it is easy to cause misjudgment of fusing. Summary of the invention

[0004] In view of the above problems, the present disclosure is proposed. The present disclosure provides a gateway traffic prediction method, a fuse method, an apparatus, a device and a storage medium.

[0005] According to one aspect of the present disclosure, a gateway traffic prediction method is provided, the method comprising:

[0006] Obtain a heat matrix diagram, wherein the heat matrix diagram uses the encoding value of the service information index vector of the network element as the first coordinate axis, the time slice as the second coordinate axis, and the color of the pixel point represents the flow value of the corresponding network element in the corresponding time slice;

[0007] Based on the thermal matrix diagram, network element traffic is predicted.

[0008] In addition, according to a gateway traffic prediction method in one aspect of the present disclosure, obtaining a heat matrix diagram includes:

[0009] Obtain the service information index vectors of multiple network elements under the gateway and their traffic values ​​in the historical time slice sequence;

[0010] A heat matrix diagram is generated based on the service information index vectors of multiple network elements under the gateway and their flow values ​​in the historical time slice sequence.

[0011] In addition, according to a gateway traffic prediction method in one aspect of the present disclosure, the multiple network elements under the gateway are network elements with top M traffic counts under the gateway, where M is greater than or equal to 2.

[0012] In addition, according to a gateway traffic prediction method in one aspect of the present disclosure, the service information corresponding to the service information index vector includes multiple information of service type, technology type, capability provider, capability pool and geographic location;

[0013] and / or,

[0014] The business information index vector is a multi-dimensional index vector.

[0015] In addition, according to a gateway traffic prediction method in one aspect of the present disclosure, predicting network element traffic based on the thermal matrix diagram includes:

[0016] The network element traffic is predicted based on the thermal matrix diagram using a pre-trained traffic prediction network model, wherein the traffic prediction network model is obtained by training a neural network model using samples, and the samples include a sample thermal matrix diagram and corresponding network element traffic labels.

[0017] In addition, according to a gateway traffic prediction method in one aspect of the present disclosure, the neural network model includes a convolutional neural network and a long short-term memory network;

[0018] The convolutional neural network is used to extract the feature vector of the thermal matrix diagram;

[0019] The long short-term memory network is used to predict network element traffic based on a feature vector based on a time series.

[0020] According to another aspect of the present disclosure, a microservice fusing method is provided, the method comprising:

[0021] Obtaining network element traffic predicted by any gateway traffic prediction method according to one aspect of the present disclosure;

[0022] A fuse strategy is executed according to the network element traffic.

[0023] In addition, according to another aspect of the present disclosure, a microservice fusing method includes:

[0024] Determine the traffic proportion of the microservice application according to the network element traffic;

[0025] According to the traffic proportion of the microservice application, the application weight of the microservice application is adjusted, wherein the increase ratio of the application weight of the microservice application is positively correlated with the traffic proportion of the microservice application.

[0026] According to another aspect of the present disclosure, a gateway traffic prediction device is provided, the device comprising:

[0027] An acquisition module is used to acquire a heat matrix diagram, wherein the heat matrix diagram uses the encoding value of the service information index vector of the network element as the first coordinate axis, the time slice as the second coordinate axis, and the color of the pixel point represents the flow value of the corresponding network element under the corresponding time slice;

[0028] The prediction module predicts the network element traffic based on the thermal matrix diagram.

[0029] According to another aspect of the present disclosure, a microservice fuse device is provided, the device comprising:

[0030] An acquisition module is used to acquire a heat matrix diagram, wherein the heat matrix diagram uses the encoding value of the service information index vector of the network element as the first coordinate axis, the time slice as the second coordinate axis, and the color of the pixel point represents the flow value of the corresponding network element under the corresponding time slice;

[0031] A prediction module, based on the thermal matrix diagram, predicts network element traffic;

[0032] The fusing module is used to execute a fusing strategy according to the network element traffic.

[0033] According to another aspect of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any of the above methods.

[0034] According to another aspect of the present disclosure, a computer-readable storage medium stores a computer program / instruction thereon, and the computer program / instruction implements the steps of any of the above-mentioned methods when executed by a processor.

[0035] According to another aspect of the present disclosure, a computer program product includes a computer program / instruction, and the computer program / instruction implements the steps of any of the above methods when executed by a processor.

[0036] As will be described in detail below, according to the gateway traffic prediction method, fuse method, device, equipment and storage medium of the embodiments of the present disclosure, a heat matrix diagram is obtained, and based on the heat matrix diagram, the network element traffic is predicted, wherein the heat matrix diagram uses the encoding value of the network element's business information index vector as the first coordinate axis, the time slice as the second coordinate axis, and the color of the pixel point represents the traffic value of the corresponding network element in the corresponding time slice, thereby improving the accuracy of network element traffic prediction and reducing fuse misjudgment.

[0037] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and other purposes, features and advantages of the present disclosure will become more apparent by describing the embodiments of the present disclosure in more detail in conjunction with the accompanying drawings. The accompanying drawings are used to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0039] Figure 1 is a flowchart illustrating a gateway traffic prediction method according to an embodiment of the present disclosure.

[0040] Figure 2 It is a flow chart further illustrating the generation of a thermal matrix diagram in the gateway traffic prediction method of an embodiment of the present disclosure.

[0041] Figure 3 It is a schematic diagram further illustrating a thermal matrix diagram in the gateway traffic prediction method of an embodiment of the present disclosure.

[0042] Figure 4 It is a flowchart further illustrating the microservice fusing method of an embodiment of the present disclosure.

[0043] Figure 5 is a block diagram illustrating a gateway traffic prediction device according to an embodiment of the present disclosure.

[0044] Figure 6 is a block diagram illustrating a microservice fuse device according to an embodiment of the present disclosure.

[0045] Figure 7 is a schematic diagram illustrating a computer program product according to an embodiment of the present disclosure.

[0046] Figure 8 is a hardware block diagram illustrating an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present disclosure more obvious, the exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described here.

[0048] See also Figure 1 , a gateway traffic prediction method, the method comprising:

[0049] S101, obtaining a heat matrix diagram, wherein the multi-dimensional index vector heat matrix diagram uses the encoding value of the network element's business information index vector as the first coordinate axis, the time slice as the second coordinate axis, and the color of the pixel point represents the flow value of the corresponding network element in the corresponding time slice.

[0050] The gateway traffic prediction method of the embodiment of the present disclosure can be applied to the traffic prediction of the gateway, for example, it can be applied to the traffic prediction of the apisix gateway.

[0051] In step S101 of the embodiment of the present disclosure, the first coordinate axis may be the ordinate, and correspondingly, the second coordinate axis is the abscissa; the first coordinate axis may be the abscissa, and correspondingly, the second coordinate axis is the ordinate.

[0052] In step S101 of the embodiment of the present disclosure, the encoding value of the business information index vector of the network element refers to the compilation value of the index vector of the business information of the network element. The index vector of the business information may be a multi-dimensional index vector, and the business information may include multiple information of business type, technology type, capability provider, capability pool and geographic location. Taking the network element's business information including business type, capability provider, geographic location, capability pool and technology type as an example, the index vector structure of the business information may be (business type, capability provider, geographic location, capability pool, technology type), and the index vector of the business information is encoded and combined to form an encoding value, which can be mapped to the index vector of the corresponding business information, and can be mapped to the corresponding business information. Coding methods such as Cartesian product or hash coding can be used to convert the encoding of each dimension into a coding value. The heat matrix diagram is intuitive enough to reflect the traffic conditions of different business combinations under different time slices.

[0053] In step S101 of the embodiment of the present disclosure, the time axis is divided into several time periods, each of which can be called a time slice. For example, the time slice can be divided into a granularity of 15 minutes, and the traffic value passing through the network element in the time slice is used as the traffic value of the network element in the time slice.

[0054] In step S101 of the embodiment of the present disclosure, the color of the pixel point represents the traffic value of the corresponding network element in the corresponding time slice. For example, the encoding value of the index vector of the service information of the network element W is G, the traffic in the first time slice is L, and the color corresponding to the traffic L is S. Then, in the thermal matrix diagram, the first time slice is used as the coordinate of the second coordinate axis, and the encoding value G is used as the coordinate of the first coordinate axis. The color of the pixel point corresponding to the coordinate of the second coordinate axis and the coordinate of the first coordinate axis is S.

[0055] See also Figure 2 In one embodiment, step S101 includes:

[0056] S201, obtaining service information index vectors of multiple network elements under the gateway and their traffic values ​​in a historical time slice sequence.

[0057] In step S201 of the embodiment of the present disclosure, the multiple network elements under the gateway refer to the multiple network elements under the gateway for the traffic to be predicted. The multiple network elements can be determined according to actual needs. For example, the multiple network elements under the gateway can be all network elements under the gateway. For example, the multiple network elements under the gateway can be the top M network elements in terms of traffic count, where M is greater than or equal to 2. Exemplarily, M is set to 50.

[0058] In step S201 of the embodiment of the present disclosure, the service information index vector of the network element refers to the index vector of the service information of the network element.

[0059] S202, generating a heat matrix diagram based on the service information index vectors of multiple network elements under the multi-dimensional index vector gateway and their traffic values ​​in the historical time slice sequence.

[0060] In step S202 of the embodiment of the present disclosure, a heat matrix diagram is generated using the service information index vectors of multiple network elements under the multidimensional index vector gateway and their flow values ​​in the historical time slice sequence. For example, the service information index vectors of multiple network elements under the multidimensional index vector gateway can be encoded to obtain the encoded values ​​of the service information index vectors of the multiple network elements under the gateway, and the heat matrix diagram is generated using the encoded values ​​of the service information index vectors of the multiple network elements under the multidimensional index vector gateway and their flow values ​​in the historical time slice sequence.

[0061] Take the case where the gateway is an apisix gateway, the time slice is a 15-minute granularity time slice, and multiple network elements under the gateway are the top 50 network elements in terms of traffic count as an example; the log information of the apisix gateway contains fields such as the log information timestamp, request type, response status code, and request source. The apisix gateway collects log information and uses the elasticsearch-logger plug-in to report the collected log information to the Elasticsearch engine. The system extracts log information from the Elasticsearch engine and extracts relevant information based on the gateway traffic monitoring. It can be known that the relevant information can be cleared, converted, and feature extracted as necessary. Specifically, with a 15-minute granularity as the time slice, the top 50 network elements in terms of traffic count are selected, and the encoded value of the index vector of each network element's business information is used as the vertical coordinate, and the traffic value passing every 15 minutes is used as the horizontal coordinate. There are 96 15 minutes in a day, and a 50*96 thermal matrix diagram is generated. See Figure 3 Each pixel of different colors in the heat matrix diagram 300 represents the traffic passing through a certain network element within the 15 minutes. A two-dimensional index vector (y, x) is used to represent the pixel in the image, where y is the ordinate and x is the abscissa.

[0062] Business (label) information can be extracted from the apisix gateway configuration, and ordinate encoding is performed using a multidimensional index vector. For example, network elements can be classified according to business scenarios, capability pools, capability providers and other information, such as business types: network services, cloud computing, big data analysis, etc. Capability providers: headquarters, provincial companies, other manufacturers, etc. Geographical location: network elements are distributed in different geographical locations, such as data centers, edge computing nodes, etc. Technology type: such as 5G, 4G, IoT, etc. Capability pool: such as planning domain, construction domain, optimization domain, maintenance domain, etc. Based on the above classification dimensions, a multidimensional index vector can be defined to represent each network element information. This multidimensional index vector can contain multiple elements, each element corresponding to a classification dimension. The multidimensional index vector structure can be (business type, capability provider, geographic location, capability pool, technology type).

[0063] S102, predicting network element traffic based on a multi-dimensional index vector heat matrix diagram.

[0064] In step S102 of the embodiment of the present disclosure, the network element traffic is predicted based on the heat matrix diagram. It should be understood that the network element traffic is the traffic of the network element under the gateway, which can be implemented by using a neural network model or other related technical solutions for predicting network element traffic using images. For example, a pre-trained traffic prediction network model can be used to predict network element traffic based on a multi-dimensional index vector heat matrix diagram, wherein the multi-dimensional index vector traffic prediction network model is obtained by training a neural network model using samples, and the multi-dimensional index vector sample includes a sample heat matrix diagram and a corresponding network element traffic label. In order to improve the training effect, recent data (for example, the past three months) can be used as sample training. Specifically, a series of matrix heat maps with time information can be collected as samples, and features can be extracted by methods such as multi-modal input, multi-task learning or attention mechanism, and the extracted features or flattened image data are arranged in chronological order to form a feature sequence arranged in chronological order. These feature sequences are used as inputs to the LSTM model, and a fixed-length subsequence is constructed using a sliding window or other technology. The long short-term memory network LSTM model is trained using a time-ordered picture sequence and corresponding labels, and the weights of the model are updated by a back-propagation algorithm and an optimizer. In the embodiments of the present disclosure, other neural network models may also be used for implementation, such as other temporal convolutional networks and other temporal neural network models.

[0065] The traffic prediction network model of the disclosed embodiment can adopt a lightweight prediction model based on the LSTM attention mechanism, and use lightweight plug-in embedding technology to embed the traffic prediction network model into the APISIX gateway, so that it can update the gateway weight information in real time, ensuring that the gateway can quickly respond to traffic changes. The pluggable lightweight prediction model makes the gateway easy to expand and maintain to meet ever-changing business needs.

[0066] In one embodiment, the multidimensional index vector neural network model includes a convolutional neural network and a long short-term memory network LSTM; the multidimensional index vector convolutional neural network is used to extract the feature vector of the multidimensional index vector heat matrix diagram; the multidimensional index vector long short-term memory network is used to predict the network element traffic based on the feature vector based on the time series. The embodiment of the present disclosure considers the server performance requirements and selects the LSTM attention mechanism.

[0067] The gateway traffic prediction method of the disclosed embodiment uses a heat matrix diagram to express the traffic distribution of multiple network elements in a time-sliced ​​sequence, which can better associate the topological structures between multiple network elements and facilitate capturing the spatial and temporal correlation of network elements. At the same time, combined with the business information index vector, it helps to capture the correlation between gateway traffic and business characteristics, so that the network element traffic predicted based on the heat matrix diagram is more accurate, thereby improving the accuracy of traffic prediction.

[0068] The gateway traffic prediction method of the disclosed embodiment adds a business index vector, so that the traffic prediction network model trained using the sample heat matrix diagram and the corresponding network element traffic labels can better understand the business logic behind the traffic, improve the model's prediction ability for the same type of gateway traffic, and thus make more accurate traffic predictions.

[0069] See also Figure 4 The embodiment of the present disclosure also provides a microservice fusing method, and the multi-dimensional index vector method includes:

[0070] S401, obtaining network element traffic predicted by any gateway traffic prediction method according to the embodiments of the present disclosure.

[0071] S402, executing a fuse strategy according to the multi-dimensional index vector network element traffic.

[0072] The circuit breaker strategy of the embodiment of the present disclosure may be any circuit breaker strategy based on network element traffic, and the embodiment of the present disclosure is not limited thereto.

[0073] In one embodiment, a microservice fuse method also includes: determining the traffic proportion of the microservice application based on the multidimensional index vector network element traffic; adjusting the application weight of the microservice application based on the traffic proportion of the multidimensional index vector microservice application, wherein the increase ratio of the application weight of the microservice application is positively correlated with the traffic proportion of the microservice application.

[0074] Based on the predicted network element traffic, the traffic proportion consumed by each microservice application in the next cycle can be predicted. Based on the traffic proportion consumed by each microservice application in the next cycle, the application weight of the microservice application can be adjusted. After adjusting the application weight of each microservice application, it can be sent to the gateway, and the gateway configures the upstream component to allocate the weight ratio of the microservice application. For example, the initial weight ratio of the microservice application is 1, the application weight ratio of the microservice application with the top 20% of traffic proportion is increased by 100%, the application weight ratio of the microservice application with the top 20%-50% of traffic proportion is increased by 50%, and the application weight ratio of the microservice application with the last 20% of traffic proportion is reduced by 50%, and the minimum value is 1 to ensure its dynamic balance. The prediction information can be fed back to the permission system, and restrictions such as account recovery will be taken for users who have been accessing maliciously for a long time.

[0075] In some cases, the malicious access of a user to a microservice in the next cycle can be predicted based on the predicted network element traffic. If it is predicted that a user may maliciously access a microservice in the next cycle, an alarm message can be sent to the authorized system administrator to indicate the risk level and recommend appropriate measures.

[0076] See also Figure 5 The exemplary embodiment of the present disclosure further provides a gateway traffic prediction device, wherein the multi-dimensional index vector device comprises:

[0077] Acquisition module 501 obtains a heat matrix diagram, wherein the multi-dimensional index vector heat matrix diagram uses the encoding value of the network element's business information index vector as the first coordinate axis, the time slice as the second coordinate axis, and the color of the pixel point represents the flow value of the corresponding network element in the corresponding time slice.

[0078] The prediction module 502 predicts the network element traffic based on the multi-dimensional index vector heat matrix diagram.

[0079] In one embodiment, the acquisition module 501 is used to obtain a heat matrix diagram, specifically for: obtaining the business information index vectors of multiple network elements under the gateway and their traffic values ​​in the historical time slice sequence; based on the multi-dimensional index vector, the business information index vectors of multiple network elements under the gateway and their traffic values ​​in the historical time slice sequence, generate a heat matrix diagram.

[0080] In one embodiment, the multiple network elements under the multi-dimensional index vector gateway are the network elements ranked in the top M in terms of traffic times under the multi-dimensional index vector gateway, where M is greater than or equal to 2.

[0081] In one embodiment, the business information corresponding to the multi-dimensional index vector business information index vector includes multiple information of business type, technology type, capability provider, capability pool and geographic location.

[0082] In one embodiment, the prediction module 502 is used for predicting network element traffic based on a multidimensional index vector heat matrix diagram using a multidimensional index vector. Specifically, it is used for: predicting network element traffic based on a multidimensional index vector heat matrix diagram using a pre-trained traffic prediction network model, wherein the multidimensional index vector traffic prediction network model is obtained by training a neural network model using a sample, and the multidimensional index vector sample includes a sample heat matrix diagram and a corresponding network element traffic label.

[0083] In one embodiment, the multidimensional index vector neural network model includes a convolutional neural network and a long short-term memory network; the multidimensional index vector convolutional neural network is used to extract the feature vectors of the multidimensional index vector heat matrix diagram; the multidimensional index vector long short-term memory network is used to predict the network element traffic based on the feature vectors based on the time series.

[0084] See also Figure 6 The exemplary embodiment of the present disclosure further provides a microservice fuse device, wherein the multi-dimensional index vector device comprises:

[0085] Acquisition module 601 obtains a heat matrix diagram, wherein the multi-dimensional index vector heat matrix diagram uses the encoding value of the network element's business information index vector as the first coordinate axis, the time slice as the second coordinate axis, and the color of the pixel point represents the flow value of the corresponding network element in the corresponding time slice.

[0086] The prediction module 602 predicts the network element traffic based on the multi-dimensional index vector heat matrix diagram.

[0087] The fusing module 603 is used to execute a fusing strategy according to the multi-dimensional index vector network element traffic.

[0088] In one embodiment, the acquisition module 601 is used to obtain a heat matrix diagram, specifically for: obtaining the business information index vectors of multiple network elements under the gateway and their traffic values ​​in the historical time slice sequence; based on the multi-dimensional index vector, the business information index vectors of multiple network elements under the gateway and their traffic values ​​in the historical time slice sequence, generate a heat matrix diagram.

[0089] In one embodiment, the multiple network elements under the multi-dimensional index vector gateway are the network elements ranked in the top M in terms of traffic times under the multi-dimensional index vector gateway, where M is greater than or equal to 2.

[0090] In one embodiment, the business information corresponding to the multi-dimensional index vector business information index vector includes multiple information of business type, technology type, capability provider, capability pool and geographic location.

[0091] In one embodiment, the prediction module 602 is used for predicting network element traffic based on a multidimensional index vector heat matrix diagram using a multidimensional index vector. Specifically, it is used for: predicting network element traffic based on a multidimensional index vector heat matrix diagram using a pre-trained traffic prediction network model, wherein the multidimensional index vector traffic prediction network model is obtained by training a neural network model using a sample, and the multidimensional index vector sample includes a sample heat matrix diagram and a corresponding network element traffic label.

[0092] In one embodiment, the multidimensional index vector neural network model includes a convolutional neural network and a long short-term memory network; the multidimensional index vector convolutional neural network is used to extract the feature vectors of the multidimensional index vector heat matrix diagram; the multidimensional index vector long short-term memory network is used to predict the network element traffic based on the feature vectors based on the time series.

[0093] In one embodiment, the device also includes an adjustment module for determining the traffic proportion of the microservice application based on the multidimensional index vector network element traffic; and adjusting the application weight of the microservice application based on the traffic proportion of the multidimensional index vector microservice application, wherein the increase ratio of the application weight of the microservice application is positively correlated with the traffic proportion of the microservice application.

[0094] The exemplary embodiment of the present disclosure also provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication. The multidimensional index vector memory stores a computer program that can be executed by the at least one processor of the multidimensional index vector, and the multidimensional index vector computer program is used to enable the multidimensional index vector electronic device to perform the method according to the embodiment of the present disclosure when it is executed by the at least one processor of the multidimensional index vector.

[0095] The exemplary embodiments of the present disclosure also provide a non-transitory computer-readable storage medium storing a computer program, wherein the multidimensional index vector computer program, when executed by a processor of a computer, is used to cause a multidimensional index vector computer to execute a method according to an embodiment of the present disclosure.

[0096] refer to Figure 7 The exemplary embodiment of the present disclosure also provides a computer program product 700, including a computer program 701, wherein the multi-dimensional index vector computer program is used to enable the multi-dimensional index vector computer to perform the method according to the embodiment of the present disclosure when executed by the processor of the computer.

[0097] refer to Figure 8, a block diagram of an electronic device 800 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0098] The electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0099] A plurality of components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, an output unit 807, a storage unit 808, and a communication unit 809. The input unit 806 may be any type of device capable of inputting information to the electronic device 800, and the input unit 806 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 807 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 808 may include, but is not limited to, a disk, an optical disk. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0100] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above. For example, in some embodiments, the method of the embodiment of the present disclosure may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. In some embodiments, the computing unit 801 may be configured to perform the method of the embodiment of the present disclosure in any other appropriate manner (e.g., by means of firmware).

[0101] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0102] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0103] Additionally, as used herein, "or" used in a list of items beginning with "at least one" indicates a separate list, so that, for example, a list of "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not mean that the example described is preferred or better than other examples.

[0104] It should also be noted that in the system and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0105] Various changes, substitutions, and modifications to the techniques of the multidimensional index vectors herein may be made without departing from the techniques of the teachings defined by the appended claims. Furthermore, the scope of the claims of the present disclosure is not limited to the specific aspects of the processes, machines, manufactures, compositions of events, means, methods, and actions of the multidimensional index vectors above. Currently existing or later to be developed processes, machines, manufactures, compositions of events, means, methods, or actions that perform substantially the same functions or achieve substantially the same results as the corresponding aspects of the multidimensional index vectors herein may be utilized. Thus, the appended claims include such processes, machines, manufactures, compositions of events, means, methods, or actions within their scope.

[0106] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0107] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A gateway traffic prediction method, characterized in that: The method comprises: Obtain a heat matrix diagram, wherein the heat matrix diagram uses the encoding value of the service information index vector of the network element as the first coordinate axis, the time slice as the second coordinate axis, and the color of the pixel point represents the flow value of the corresponding network element in the corresponding time slice; Based on the thermal matrix diagram, network element traffic is predicted.

2. The method according to claim 1, characterized in that The step of obtaining a thermal matrix diagram comprises: Obtain the service information index vectors of multiple network elements under the gateway and their traffic values ​​in the historical time slice sequence; A heat matrix diagram is generated based on the service information index vectors of multiple network elements under the gateway and their flow values ​​in the historical time slice sequence.

3. The method according to claim 2, characterized in that The multiple network elements under the gateway are network elements ranked in top M in terms of traffic times under the gateway, where M is greater than or equal to 2.

4. The method according to claim 1, characterized in that: The business information corresponding to the business information index vector includes multiple information of business type, technology type, capability provider, capability pool and geographical location; and / or, The business information index vector is a multi-dimensional index vector.

5. The method according to claim 1, characterized in that The predicting of network element traffic based on the thermal matrix diagram includes: The network element traffic is predicted based on the thermal matrix diagram using a pre-trained traffic prediction network model, wherein the traffic prediction network model is obtained by training a neural network model using samples, and the samples include a sample thermal matrix diagram and corresponding network element traffic labels.

6. The method according to claim 5, characterized in that The neural network model includes a convolutional neural network and a long short-term memory network; The convolutional neural network is used to extract the feature vector of the thermal matrix diagram; The long short-term memory network is used to predict network element traffic based on a feature vector based on a time series.

7. A microservice fuse method, characterized in that: The method comprises: Obtaining the network element traffic predicted by the gateway traffic prediction method according to any one of claims 1 to 6; A fuse strategy is executed according to the network element traffic.

8. The method according to claim 7, characterized in that The method further comprises: Determine the traffic proportion of the microservice application according to the network element traffic; According to the traffic proportion of the microservice application, the application weight of the microservice application is adjusted, wherein the increase ratio of the application weight of the microservice application is positively correlated with the traffic proportion of the microservice application.

9. A gateway traffic prediction device, characterized in that: The device comprises: An acquisition module is used to acquire a heat matrix diagram, wherein the heat matrix diagram uses the encoding value of the service information index vector of the network element as the first coordinate axis, the time slice as the second coordinate axis, and the color of the pixel point represents the flow value of the corresponding network element in the corresponding time slice; The prediction module predicts the network element traffic based on the thermal matrix diagram.

10. A microservice fuse device, characterized in that: The device comprises: An acquisition module is used to acquire a heat matrix diagram, wherein the heat matrix diagram uses the encoding value of the service information index vector of the network element as the first coordinate axis, the time slice as the second coordinate axis, and the color of the pixel point represents the flow value of the corresponding network element in the corresponding time slice; A prediction module, based on the thermal matrix diagram, predicts network element traffic; The fusing module is used to execute a fusing strategy according to the network element traffic.

11. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of any one of claims 1 to 8.

12. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the steps of any method described in claims 1 to 8 are implemented.

13. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of any method described in claims 1 to 8 are implemented.

Images