Edge data processing method and apparatus, electronic device, and readable storage medium

Abstract

The application provides an edge data processing method and device, electronic equipment and a readable storage medium, and relates to the field of edge computing in the technical field of computers. The edge data processing method comprises the following steps: acquiring a state parameter of a terminal device; predicting a target edge node according to the state parameter of the terminal device; and synchronizing target data to the target edge node before the terminal device and the target edge node establish a connection, wherein the target data is edge data corresponding to the terminal device in a current edge node, and the current edge node is an edge node currently connected with the terminal device. The application improves the continuity of business processing when the edge node is switched, and reduces the business processing delay caused by data transmission.

Description

Technical Field

[0001] The present invention relates to the field of edge computing in the field of computer technology, and more particularly to an edge data processing method, apparatus, electronic device and readable storage medium. Background Technology

[0002] Edge computing refers to the technology of using distributed edge nodes for data processing. Because edge nodes are closer to the terminals that need to provide services, the load on the edge nodes can be allocated more efficiently, while reducing data transmission time and improving data processing efficiency. However, terminals may move at high speeds during use. As the terminal's location changes, when it leaves the coverage area of ​​an edge node, it needs to switch to a different edge node. However, since the newly switched edge node does not contain the terminal's relevant data, data transmission is required, which introduces a certain delay in the service processing provided to the terminal. Summary of the Invention

[0003] This invention provides an edge data processing method, apparatus, electronic device, and readable storage medium to solve the problem of service processing latency when the edge node corresponding to the terminal switches.

[0004] To solve the above problems, the present invention is implemented as follows:

[0005] In a first aspect, embodiments of the present invention provide an edge data processing method, comprising the following steps:

[0006] Obtain the status parameters of the terminal device;

[0007] The target edge node is predicted based on the state parameters of the terminal device, wherein the target edge node is a first edge node that meets the preset probability conditions. The first edge node is an edge node that has not yet established a connection with the terminal device. The preset probability conditions include that the probability parameter of establishing a connection with the terminal device within a preset time period is greater than the preset probability parameter threshold or that the probability parameter value of establishing a connection with the terminal device within the preset time period is the largest.

[0008] Before the terminal device establishes a connection with the target edge node, the target data is synchronized to the target edge node, wherein the target data is the edge data corresponding to the terminal device in the current edge node, and the current edge node is the edge node currently connected to the terminal device.

[0009] In some embodiments, synchronizing the target data to the target edge node includes:

[0010] Receive a data synchronization request, wherein the data synchronization request is sent by the current edge node when it detects the existence of the target data;

[0011] According to the data synchronization request, a data synchronization strategy is sent to the target edge node and the current edge node, and the target edge node obtains the target data from the current edge node based on the data synchronization strategy.

[0012] In some embodiments, the data synchronization request includes one or more of a first data request for cached data and a second data request for database data.

[0013] In some embodiments, synchronizing the target data to the target edge node includes:

[0014] Based on the type of the data synchronization request, the cached data in the current edge node is synchronized to the cache of the target edge node, and / or

[0015] Synchronize the database data in the current edge node to the database of the target edge node.

[0016] In some embodiments, the status parameters include one or more of the following: the identity identifier of the terminal device, the identity identifier of the current edge node, the connection record between the terminal device and the edge node, the location information of the terminal device, and time information.

[0017] In some embodiments, before predicting the target edge node based on the state parameters of the terminal device, the method further includes:

[0018] Obtain the historical status parameters of the terminal device;

[0019] The handover probability and the rate of change of the handover probability between the terminal device and each edge node in different time periods are evaluated based on the historical state parameters.

[0020] In some embodiments, after synchronizing the target data to the target edge node, the method further includes:

[0021] When the terminal device switches to establish a connection with the target edge node, the target data in the target edge node is invoked to provide services to the terminal device.

[0022] In a second aspect, embodiments of the present invention provide an edge data processing apparatus, comprising:

[0023] The status parameter acquisition module is used to acquire the status parameters of the terminal device;

[0024] The target edge node prediction module is used to predict target edge nodes based on the status parameters of the terminal device. The target edge node is a first edge node that meets a preset probability condition. The first edge node is an edge node that has not yet established a connection with the terminal device. The preset probability condition includes that the probability parameter of establishing a connection with the terminal device within a preset time period is greater than a preset probability parameter threshold or that the probability parameter value of establishing a connection with the terminal device within a preset time period is the largest.

[0025] The data synchronization module is used to synchronize target data to the target edge node before the terminal device establishes a connection with the target edge node, wherein the target data is the edge data corresponding to the terminal device in the current edge node, and the current edge node is the edge node currently connected to the terminal device.

[0026] Thirdly, embodiments of the present invention also provide an electronic device, including: a transceiver, a memory, a processor, and a program stored in the memory and executable on the processor; the processor is configured to read the program in the memory to implement the steps in the method described in the first aspect above.

[0027] Fourthly, embodiments of the present invention also provide a readable storage medium for storing a program, which, when executed by a processor, implements the steps of the method described in the first aspect above.

[0028] In this embodiment of the invention, the edge data processing method includes the following steps: obtaining state parameters of a terminal device; predicting a target edge node based on the state parameters of the terminal device, wherein the target edge node is a first edge node that meets a preset probability condition, the first edge node being an edge node that has not yet established a connection with the terminal device, the preset probability condition including a probability parameter that establishes a connection with the terminal device within a preset time period being greater than a preset probability parameter threshold or a probability parameter value that establishes a connection with the terminal device within a preset time period being the maximum; synchronizing target data to the target edge node before the terminal device establishes a connection with the target edge node, wherein the target data is edge data corresponding to the terminal device in the current edge node, and the current edge node is the edge node currently connected to the terminal device. Thus, this embodiment of the invention predicts a target edge node and synchronizes relevant target data to the target edge node before the terminal device connects to the target edge node. If the terminal device connects to the target edge node, the target edge node can directly call the target data therein to provide services to the terminal device, improving the continuity of business processing during edge node switching and reducing business processing delays caused by data transmission. Attached Figure Description

[0029] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic diagram illustrating the switching of edge nodes connected to the terminal device in an embodiment of the present invention;

[0031] Figure 2 This is a schematic diagram of a scenario according to an embodiment of the present invention;

[0032] Figure 3 This is a flowchart illustrating the edge data processing method provided in an embodiment of the present invention;

[0033] Figure 4 This is a schematic diagram of the data synchronization process in an embodiment of the present invention;

[0034] Figure 5 This is a schematic diagram of the edge node architecture according to an embodiment of the present invention;

[0035] Figure 6 This is a schematic diagram of the edge data processing device provided in an embodiment of the present invention;

[0036] Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention. Detailed Implementation

[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] In the embodiments of this invention, the terms "first," "second," etc., are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or devices. Additionally, the use of "and / or" in this application indicates at least one of the connected objects, such as A and / or B and / or C, representing seven possibilities: including A alone, B alone, C alone, and the presence of both A and B, both B and C, both A and C, and the presence of A, B, and C.

[0039] like Figure 1 As shown, edge computing refers to providing business support to corresponding areas by utilizing edge nodes covering different regions under the control and scheduling of servers. Each edge node can be understood as an independent data center.

[0040] The edge nodes that provide service support to terminal devices may change, for example, such as Figure 1 As shown, as a vehicle travels at high speed, when it moves from the service area covered by the base station corresponding to one edge node to the service area covered by the base station corresponding to another edge node, it needs to switch to the edge node that provides services to the vehicle.

[0041] The service environment that provides business support at edge nodes is usually based on container instances or virtual machine instances. However, when providing service support to a single user, due to the limitation of computing resources, it is difficult to start or create a container instance or virtual machine instance separately for the user's service request. Even if a container instance or virtual machine instance is created separately, some data depends on middleware or database operation, and this data cannot be synchronized by replicating the container instance or virtual machine instance. Even if synchronization is performed, due to the large amount of data transmission, it will consume a lot of network resources, resulting in a large delay in the service.

[0042] The technical solution of this embodiment is applied to edge services. In this embodiment, the required business components run on a container environment, specifically involving the processing of edge data involved in edge services. Figure 2 As shown, in the technical solution of this embodiment, the terminal device (UE) can refer to devices such as vehicles, cameras, traffic lights, mobile terminals, routers, and intelligent robots. Under the scheduling of the server (or central cloud), the edge nodes can provide business support for these terminal devices based on edge applications, thus forming a distributed architecture in which cloud-edge (central cloud-edge node) and edge-edge (edge ​​node-edge node) cooperate with each other.

[0043] The central cloud is equipped with a data synchronization management module, which is responsible for orchestrating and scheduling edge data migration strategies between edge nodes. Edge applications execute central cloud strategies to achieve application and data migration between edge nodes, as well as data synchronization between the edge and the central cloud.

[0044] Before the edge node switch occurs on the terminal device, the edge-to-edge data synchronization strategy is run through the central cloud edge data synchronization management framework, and the data is synchronized to the target node, thus ensuring data continuity during the switch.

[0045] Specifically, such as Figure 3 As shown, in some embodiments, the method includes the following steps:

[0046] Step 301: Obtain the status parameters of the terminal device;

[0047] In this embodiment, the status parameters of the terminal device are first obtained. In some embodiments, the status parameters include one or more of the following: the identity identifier of the terminal device, the identity identifier of the current edge node, the connection record between the terminal device and the edge node, the location information of the terminal device, and the time information.

[0048] Here, the identity identifiers of terminal devices and edge nodes can both use their unique device identifiers or serial numbers, etc.

[0049] It is understandable that once the current edge node corresponding to the terminal device is determined, the edge nodes adjacent to the current edge node can also be determined based on the distribution of edge nodes. It is also understandable that when the terminal device is used and moved continuously, it can only move from the area corresponding to the current edge node to the area corresponding to an adjacent edge node. Therefore, in this embodiment, based on the current edge node, the edge nodes corresponding to the areas the terminal device may move to can be determined.

[0050] For example, the current edge node is numbered X1, and the edge nodes adjacent to the current edge node are X2, X3, ..., Xn.

[0051] Connection records refer to the connection or disconnection status between the terminal device and the edge node. Location information can be used to analyze the location change trend of the terminal device, thereby analyzing and determining the edge node that the terminal device may connect to due to location changes. Time information can refer to the timestamps corresponding to the above actions. For example, it can be the timestamps corresponding to the connection or disconnection operations between the terminal device and the edge node, or it can be the timestamps corresponding to the location information, etc.

[0052] Terminal devices can report these status parameters to the server; for example, this can be done by... Figure 2The data synchronization management module shown collects and analyzes these status parameters.

[0053] In some embodiments, the method further includes:

[0054] Obtain the historical status parameters of the terminal device;

[0055] The handover probability and the rate of change of the handover probability between the terminal device and each edge node in different time periods are evaluated based on the historical state parameters.

[0056] Here, historical state parameters refer to the historical data of the aforementioned state parameters. Based on the analysis of historical data, the usage habits of the terminal device can be inferred, thereby predicting the edge node switching needs of the terminal device. For example, it can be derived from... Figure 2 The data synchronization management module shown analyzes historical status parameters.

[0057] Based on the analysis of historical state parameters, the handover probability of the terminal device switching to each edge node in different time periods and the rate of change of the handover probability can be obtained.

[0058] For example, the switching probability [P1,P2,P3,P4] of the edge node switching from X1 to X2 in different time periods is calculated based on historical state parameters.

[0059] In one specific implementation, for the morning peak (7:00 < timestamp < 9:00), let s1 = the number of times X1 successfully switches to X2 during this time period; n1 = the total number of times node X1 switches during this time period; then the estimated switching probability of the edge node of the morning peak switching from X1 to X2 is: P1 = s1 / n1.

[0060] In another specific implementation, for the evening peak (17:00 < timestamp < 20:00), let s2 = the number of times X1 successfully switches to X2 during this time period; n2 = the total number of times node X1 switches during this time period; then the estimated switching probability of the edge node of the evening peak switching from X1 to X2 is: P2 = s2 / n2.

[0061] In another specific implementation, for the historical state parameters of holidays, let s3 = the number of times X1 successfully switches to X2 during the time period; n3 = the total number of times node X1 switches during the time period; then the estimated switching probability of the edge node switching from X1 to X2 during holidays is: P3 = s3 / n3.

[0062] In another specific implementation, for other time periods, let s4 = the number of times X1 successfully switches to X2 in that time period; n4 = the total number of times node X1 switches in that time period; then the estimated switching probability of edge nodes switching from X1 to X2 in other time periods is: P4 = s4 / n4.

[0063] Obviously, the time period can be further divided according to different conditions during implementation, but no further restrictions are made here.

[0064] Thus, by collecting a sufficient number of historical state parameters, the sample means of si and ni both exhibit linear trends. To improve the accuracy of the overall characteristic estimation, a uniform design table Ux(qm) of the relevant influencing indicators can be designed based on the uniform distribution matrix, where x represents the number of samples, q represents the number of strata in the overall indicator population, and m represents the number of indicators with core influence. The sample estimate S of si is then calculated based on the uniform design table. i The mean of the k-th space of the sampled population qm is denoted as but:

[0065]

[0066] Similarly, the sample mean N of ni can be calculated. i Then, based on the probability data P for each time period of the day... i =S i / N i The probability change rate for each time period is calculated. The probability change rate can be calculated by calculating the derivative or by interpolation. No further restrictions are placed on the specific calculation method here.

[0067] For example, the probability change rate corresponding to the above switching probabilities [P1,P2,P3,P4] is denoted as [P1',P2',P3',P4'].

[0068] Using the above method, based on the historical state parameters corresponding to each edge node, the switching probability and the rate of change of the probability of the terminal device switching from one edge node to each of the adjacent edge nodes in different time periods can be calculated.

[0069] Step 302: Predict the target edge node based on the state parameters of the terminal device.

[0070] In this embodiment, the target edge node is a first edge node that meets the preset probability conditions. The first edge node is an edge node that has not yet established a connection with the terminal device. The preset probability conditions include the probability parameter of establishing a connection with the terminal device within a preset time period being greater than the preset probability parameter threshold or the probability parameter value of establishing a connection with the terminal device within a preset time period being the maximum.

[0071] The probability parameter refers to one or more of the above-mentioned handover probability and the change in handover probability. It can be understood that the greater the handover probability and the rate of change of handover probability, the greater the probability that the terminal device will move to the corresponding edge node.

[0072] In this embodiment, the number of target edge nodes can be one or more, and obviously, it can also be zero, that is, after analysis, there are no corresponding target edge nodes.

[0073] Step 303: Before the terminal device establishes a connection with the target edge node, synchronize the target data to the target edge node.

[0074] The target data is the edge data corresponding to the terminal device in the current edge node, and the current edge node is the edge node currently connected to the terminal device.

[0075] In some embodiments, after step 303, the method further includes:

[0076] When the terminal device switches to establish a connection with the target edge node, the target data in the target edge node is invoked to provide services to the terminal device.

[0077] After the target edge node is determined, the target data in the current edge node is pulled to the target edge node. In this way, if the terminal device moves to the area corresponding to the target edge node and connects to the target edge node, the target edge node can be directly used to provide service support to the terminal device based on the pulled target data, reducing the time required for output transmission.

[0078] It is understandable that if the target edge node is not determined, edge node switching may occur. In this case, the previously connected edge node is accessed through the backhaul network to obtain the required edge data.

[0079] In this way, by predicting the target edge node and synchronizing the relevant target data to the target edge node before the terminal device accesses the target edge node, if the terminal device accesses the target edge node, the target edge node can directly call the target data therein to provide services to the terminal device, thereby improving the continuity of business processing when the edge node is switched and reducing the business processing delay caused by data transmission.

[0080] It is understandable that some edge data may not support data migration. For edge data that cannot be migrated, when the terminal device connects to the target edge node, the terminal device's request can be routed back to the previous edge node for processing through the backhaul network.

[0081] In some embodiments, step 303 above includes:

[0082] Receive a data synchronization request, wherein the data synchronization request is sent by the current edge node when it detects the existence of the target data;

[0083] According to the data synchronization request, a data synchronization strategy is sent to the target edge node and the current edge node, and the target edge node obtains the target data from the current edge node based on the data synchronization strategy.

[0084] like Figure 4 As shown, the data synchronization process in this embodiment can be summarized as follows: First, the edge node listens for the writing of edge data. Here, edge data can refer to various data involved in the operation of edge applications.

[0085] Upon detecting edge data writing, the edge node notifies the server to synchronize data. For example, this can be achieved through... Figure 2 The data synchronization management module of the central cloud, as shown, performs data synchronization control.

[0086] The server issues a data synchronization strategy. Specifically, the server may determine the target edge nodes for data synchronization based on historical state data.

[0087] According to this data synchronization strategy, the target edge node may request data synchronization from the current edge node, or the current edge node may send a data synchronization notification to the target edge node.

[0088] Finally, data is transmitted between the current edge node and the target edge node to complete data synchronization.

[0089] In some embodiments, the data synchronization request includes one or more of a first data request for cached data and a second data request for database data.

[0090] In some embodiments, synchronizing the target data to the target edge node includes:

[0091] Based on the type of the data synchronization request, the cached data in the current edge node is synchronized to the cache of the target edge node, and / or

[0092] Synchronize the database data in the current edge node to the database of the target edge node.

[0093] In this embodiment, the edge data involved is divided into three categories: stateful data, stateless data, and global state data.

[0094] Stateful data refers to data that needs to be synchronized between the central cloud and edge nodes, and between edge nodes. Stateful data applies to multiple edge nodes and the central cloud. For example, it can be business database data, cached middleware data, function input parameters, execution status, and execution results.

[0095] Stateless data refers to data that is processed locally on a single edge node. Stateless data operates on a single edge node; for example, it could be data generated during function execution.

[0096] Global status data refers to data that needs to be uploaded to the central cloud. Data that needs to be uploaded to the central cloud affects the central cloud and controls all edge nodes. For example, it can be anonymized geographic location data, edge cloud operation status information, application traffic information, etc.

[0097] These three data types encapsulate existing basic data types and object types. During implementation, the appropriate data type can be selected to define the involved edge data based on specific scenarios and requirements. Different data synchronization strategies are then executed for different edge data types.

[0098] Edge data may be stored in data blocks or in a cache.

[0099] like Figure 5 As shown in this embodiment, each edge node includes a cache for temporarily storing data and a database for long-term data storage. The cache and database provide the edge data required by edge applications in the business layer.

[0100] Each edge node is equipped with a data synchronization module, which monitors data update status. Specifically, a cache listener and a database listener are embedded in the application data storage layer to receive call requests from the business layer.

[0101] like Figure 5 As shown in number 1, when a call request exists, corresponding edge data will be generated. When the listener hears the data write request, it will write the listened data to the data table to be synchronized. As shown in number 2, the listener will also send a request to the central cloud data synchronization management module to obtain the synchronization instruction.

[0102] As shown in number 3, based on this synchronization instruction, the edge application in the current edge node (edge ​​node A) obtains the instruction from the central cloud. As shown in number 4, the edge application in the current edge node (edge ​​node A) then notifies the edge applications of the target edge nodes (edge ​​node B and edge node X).

[0103] As shown in number 5, the edge application of the target edge node (edge ​​node B and edge node X) obtains the data records of the data table to be synchronized from the current edge node (edge ​​node A).

[0104] After obtaining the data records, data processing operations can be performed on the database or cache according to the data type and data operation instructions. These operations can include adding, deleting, or modifying data. Once the data processing operations are completed, the data synchronization status is updated.

[0105] In the above process, the fields transmitted may include the identity identifier of the terminal device (e.g., the unique identifier of the user terminal), the identity identifier of the edge node (e.g., the edge node number), the identifier of the edge application (e.g., the application identifier), the data type (e.g., database data or cached data), data operation instructions (e.g., add, modify, delete), data objects (e.g., files in JSON / XML / TXT format), synchronization status (e.g., data synchronization status with different edge nodes is pending synchronization, synchronizing, synchronization completed, error occurred, etc.), and timestamps.

[0106] The technical solution of this embodiment does not require copying and transferring edge application container instances or edge application virtual machines, making it easy to implement and requiring fewer computing and network transmission resources. It also effectively solves the problem of data existing in the edge server middleware and database, which edge applications rely on, in addition to synchronizing the edge application runtime environment. Furthermore, in this embodiment, edge application data is pre-synchronized to the target edge node before the edge computing node switches, resulting in lower latency and a better user experience.

[0107] The present invention also provides an edge data processing device.

[0108] like Figure 6 As shown, in some embodiments, the edge data processing device 600 includes:

[0109] The status parameter acquisition module 601 is used to acquire the status parameters of the terminal device;

[0110] The target edge node prediction module 602 is used to predict the target edge node based on the state parameters of the terminal device. The target edge node is a first edge node that meets a preset probability condition. The first edge node is an edge node that has not yet established a connection with the terminal device. The preset probability condition includes that the probability parameter of establishing a connection with the terminal device within a preset time period is greater than a preset probability parameter threshold or that the probability parameter value of establishing a connection with the terminal device within a preset time period is the largest.

[0111] The data synchronization module 603 is used to synchronize target data to the target edge node before the terminal device establishes a connection with the target edge node, wherein the target data is the edge data corresponding to the terminal device in the current edge node, and the current edge node is the edge node currently connected to the terminal device.

[0112] In some embodiments, the data synchronization module 603 includes:

[0113] The synchronization request receiving submodule is used to receive data synchronization requests, wherein the data synchronization request is sent by the current edge node when it detects the existence of the target data;

[0114] The strategy sending submodule is used to send a data synchronization strategy to the target edge node and the current edge node according to the data synchronization request, and the target edge node obtains the target data from the current edge node based on the data synchronization strategy.

[0115] In some embodiments, the data synchronization request includes one or more of a first data request for cached data and a second data request for database data.

[0116] In some embodiments, the data synchronization module 603 is specifically used for:

[0117] Based on the type of the data synchronization request, the cached data in the current edge node is synchronized to the cache of the target edge node, and / or

[0118] Synchronize the database data in the current edge node to the database of the target edge node.

[0119] In some embodiments, the status parameters include one or more of the following: the identity identifier of the terminal device, the identity identifier of the current edge node, the connection record between the terminal device and the edge node, the location information of the terminal device, and time information.

[0120] In some embodiments, it also includes:

[0121] The historical status parameter acquisition module is used to acquire the historical status parameters of the terminal device;

[0122] The probability calculation module is used to evaluate the handover probability and the rate of change of the handover probability between the terminal device and each edge node in different time periods based on the historical state parameters.

[0123] In some embodiments, it also includes:

[0124] The module is used to call target data in the target edge node to provide services to the terminal device when the terminal device switches to establish a connection with the target edge node.

[0125] The edge data processing device 600 of this embodiment can implement the various steps of the above-described edge data processing method embodiment and achieve essentially the same technical effects, which will not be repeated here.

[0126] This invention also provides an electronic device. Please refer to [link to relevant documentation]. Figure 7The electronic device may include a processor 701, a memory 702, and a program 7021 stored in the memory 702 and capable of running on the processor 701.

[0127] When the electronic device is a terminal, program 7021 can be executed by processor 701 to achieve the following: Figure 1 Any steps in the corresponding method embodiments and the achievement of the same beneficial effects will not be repeated here.

[0128] When the electronic device is a network-side device, program 7021 can be executed by processor 701 to achieve the following: Figure 7 Any steps in the corresponding method embodiments and the achievement of the same beneficial effects will not be repeated here.

[0129] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by hardware related to program instructions, and the program can be stored in a readable medium.

[0130] This invention also provides a readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described functions. Figure 1 Any step in the corresponding method embodiment can achieve the same technical effect, and will not be repeated here to avoid repetition.

[0131] The storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0132] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. An edge data processing method, characterized by, The method comprises the following steps: obtaining a state parameter of a terminal device; predicting a target edge node according to the state parameter of the terminal device, wherein the target edge node is a first edge node that meets a preset probability condition, the first edge node is an edge node that has not established a connection with the terminal device, and the preset probability condition comprises that a probability parameter of establishing a connection with the terminal device within a preset time length is greater than a preset probability parameter threshold or the probability parameter value is maximum within the preset time length; synchronizing target data to the target edge node before the terminal device establishes a connection with the target edge node, wherein the target data is edge data corresponding to the terminal device in a current edge node, and the current edge node is an edge node currently connected with the terminal device; the step of synchronizing the target data to the target edge node comprises: receiving a data synchronization request, wherein the data synchronization request is sent by the current edge node when it is detected that the target data exists; sending a data synchronization strategy to the target edge node and the current edge node according to the data synchronization request, and the target edge node acquires the target data from the current edge node based on the data synchronization strategy; the data synchronization request comprises one or more of a first data request for cache data and a second data request for database data; the step of synchronizing the target data to the target edge node comprises: synchronizing cache data in the current edge node to a cache of the target edge node according to the type of the data synchronization request, and / or synchronizing database data in the current edge node to a database of the target edge node.

2. The method of claim 1, wherein, The state parameter comprises one or more of an identity of the terminal device, an identity of the current edge node, a connection record of the terminal device and the edge node, location information of the terminal device, and time information.

3. The method of claim 1, wherein, Before the step of predicting the target edge node according to the state parameter of the terminal device, the method further comprises: obtaining a historical state parameter of the terminal device; evaluating a switching probability and a change rate of the switching probability of the terminal device corresponding to each edge node in different time periods according to the historical state parameter.

4. The method according to any one of claims 1 to 3, characterized in that, After the step of synchronizing the target data to the target edge node, the method further comprises: in a case where the terminal device switches to establish a connection with the target edge node, calling the target data in the target edge node to provide services for the terminal device.

5. An edge data processing device, comprising: comprise: a state parameter obtaining module configured to obtain a state parameter of a terminal device; The target edge node prediction module is configured to predict a target edge node according to a state parameter of the terminal device, wherein the target edge node is a first edge node satisfying a preset probability condition, the first edge node is an edge node that has not established a connection with the terminal device, and the preset probability condition includes that a probability parameter of establishing a connection with the terminal device within a preset time length is greater than a preset probability parameter threshold or a probability parameter value of establishing a connection with the terminal device within a preset time length is maximum. The data synchronization module is configured to synchronize target data to the target edge node before the terminal device establishes a connection with the target edge node, wherein the target data is edge data corresponding to the terminal device in a current edge node, and the current edge node is an edge node currently connected with the terminal device. The data synchronization module includes: The synchronization request receiving submodule is configured to receive a data synchronization request, wherein the data synchronization request is sent by the current edge node when it is detected that the target data exists. The policy sending submodule is configured to send a data synchronization policy to the target edge node and the current edge node according to the data synchronization request, and the target edge node acquires the target data from the current edge node based on the data synchronization policy. The data synchronization request includes one or more of a first data request for cache data and a second data request for database data. The data synchronization module is specifically configured to: synchronize cache data in the current edge node to a cache of the target edge node according to a type of the data synchronization request, and / or synchronize database data in the current edge node to a database of the target edge node.

6. An electronic device comprising: The memory, the processor, and a program stored in the memory and capable of running on the processor; and the processor is configured to read the program in the memory to implement the steps in the edge data processing method according to any one of claims 1 to 4.

7. A readable storage medium for storing a program, characterized by The program is executed by the processor to implement the steps in the edge data processing method according to any one of claims 1 to 4.

Images