A data transmission method and system based on big data analysis

Abstract

This invention provides a data transmission method and system based on big data analysis. The invention relates to the field of data transmission technology based on big data analysis. The method acquires recorded videos from a user's original mobile phone; determines multiple recommended migration software and recommended migration data sizes based on the recorded videos; acquires data from the multiple recommended migration software; determines target migration data based on the data from the multiple recommended migration software and the recommended migration data sizes; and performs data transmission based on the target migration data using big data analysis. This method can quickly determine the optimal migration scheme.

Description

Technical Field

[0001] This invention relates to the field of data transmission technology based on big data analysis, and specifically to a data transmission method and system based on big data analysis. Background Technology

[0002] With the widespread adoption of mobile internet and smart devices, smartphones have become indispensable tools in people's daily lives. Users generate a large amount of data while using their phones, including application data, multimedia files, and communication logs. When users switch phones, efficiently and accurately migrating this data becomes a significant technical challenge. Traditional data migration methods typically rely on manual selection or full disk copying, which is not only inefficient but can also lead to unnecessary data migrations, wasting storage resources and network bandwidth.

[0003] Therefore, in situations involving multiple applications and large amounts of data, how to quickly determine the optimal migration solution is a pressing issue that needs to be addressed. Summary of the Invention

[0004] The main technical problem this invention addresses is how to quickly determine the optimal migration scheme.

[0005] According to a first aspect, the present invention provides a data transmission method based on big data analysis, comprising: acquiring recorded videos of a user's original mobile phone during use; determining multiple recommended migration software and recommended migration data size based on the recorded videos of the user's original mobile phone during use; acquiring data of the multiple recommended migration software; determining target migration data based on the data of the multiple recommended migration software and the size of the recommended migration data; and performing data transmission based on big data analysis based on the target migration data.

[0006] In one possible implementation, determining the target migration data based on the data from the plurality of recommended migration software and the size of the recommended migration data includes: Based on the data from the multiple recommended migration software programs and the size of the recommended migration data, a data migration model is used to determine the maximum and minimum values ​​of the migration data for each recommended migration software program. Based on the data from the multiple recommended migration software programs, the size of the recommended migration data, the maximum and minimum values ​​of the migration data for each recommended migration software program, multiple data transmission schemes based on big data analysis are generated, along with the similarity of each data transmission scheme. A data transmission graph based on big data analysis is constructed, comprising multiple nodes and multiple edges between nodes. Each node represents a data transmission scheme based on big data analysis, and the edge between two nodes represents the similarity between two data transmission schemes based on big data analysis. The data transmission graph based on big data analysis is processed using a graph neural network to determine the target migration data.

[0007] In one possible implementation, the data processing model is a long short-term neural network model.

[0008] In one possible implementation, the input to the graph neural network is the data transmission map based on big data analysis, and the output of the graph neural network is the target migration data.

[0009] According to a second aspect, the present invention provides a data transmission system based on big data analysis, comprising: The first acquisition module is used to acquire videos recorded when the user's original mobile phone was in use; The data processing module is used to determine multiple recommended migration software and the size of recommended migration data based on the video recorded when the user's original mobile phone was in use; The second acquisition module is used to acquire data from multiple recommended migration software programs; The determination module is used to determine the target migration data based on the data from the multiple recommended migration software and the size of the recommended migration data; The transmission module is used for data transmission based on big data analysis of the target migration data.

[0010] In one possible implementation, the determining module is further configured to: Based on the data from the multiple recommended migration software programs and the size of the recommended migration data, a data migration model is used to determine the maximum and minimum values ​​of the migration data for each recommended migration software program. Based on the data from the multiple recommended migration software, the size of the recommended migration data, the maximum value of the migration data for each recommended migration software, and the minimum value of the migration data for each recommended migration software, multiple data transmission schemes based on big data analysis are generated, along with the similarity of each data transmission scheme based on big data analysis. A data transmission graph based on big data analysis is constructed. The data transmission graph based on big data analysis includes multiple nodes and multiple edges between the nodes. Each node represents a data transmission scheme based on big data analysis, and the edge between two nodes represents the similarity between two data transmission schemes based on big data analysis. The target migration data is determined by processing the data transmission map based on big data analysis using a graph neural network.

[0011] In one possible implementation, the data processing model is a long short-term neural network model.

[0012] In one possible implementation, the input to the graph neural network is the data transmission map based on big data analysis, and the output of the graph neural network is the target migration data.

[0013] According to a third aspect, embodiments of the present invention provide an electronic device, including: a processor; a memory; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above, the method including: acquiring a video recorded while the user's original mobile phone was in use; determining multiple recommended migration software and a recommended migration data size based on the video recorded while the user's original mobile phone was in use; acquiring data of the multiple recommended migration software; determining target migration data based on the data of the multiple recommended migration software and the size of the recommended migration data; and performing data transmission based on big data analysis based on the target migration data.

[0014] According to the fourth aspect, this embodiment provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements the aforementioned data transmission method based on big data analysis. The method includes: acquiring recorded videos of a user's original mobile phone during use; determining multiple recommended migration software and recommended migration data sizes based on the recorded videos of the user's original mobile phone during use; acquiring data of the multiple recommended migration software; determining target migration data based on the data of the multiple recommended migration software and the recommended migration data sizes; and performing data transmission based on big data analysis based on the target migration data.

[0015] This invention provides a data transmission method and system based on big data analysis. The method includes acquiring recorded videos of a user's original mobile phone; determining multiple recommended migration software and recommended migration data sizes based on the recorded videos; acquiring data from the multiple recommended migration software; determining target migration data based on the data from the multiple recommended migration software and the recommended migration data sizes; and performing data transmission based on the target migration data using big data analysis. This method can quickly determine the optimal migration scheme. Attached Figure Description

[0016] Figure 1 A schematic diagram illustrating an application scenario of a data transmission method based on big data analysis provided in an embodiment of the present invention; Figure 2 A flowchart illustrating a data transmission method based on big data analysis provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a process for determining target migration data provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of a data transmission system based on big data analysis provided in an embodiment of the present invention. Detailed Implementation

[0017] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of the invention. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to the present invention are not shown or described in the specification. This is to avoid obscuring the core parts of the invention with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0018] Figure 1 This is a schematic diagram illustrating an application scenario of a data transmission method based on big data analysis, provided in an embodiment of the present invention. Figure 1 Application scenarios for data transmission methods based on big data analysis can include servers 11, networks 12, terminals 13, and storage devices 14.

[0019] In some embodiments, server 11 may be a single server or a group of servers. Server 11 can access information and / or data stored in terminal 13 or storage device 14 via network 12. In some embodiments, server 11 may be used to perform... Figure 2 The data transmission method based on big data analytics is shown in the figure.

[0020] Network 12 can facilitate the exchange of information and / or data. In some embodiments, network 12 can be any form of wired or wireless network, or any combination thereof.

[0021] Terminal 13 may refer to one or more terminal devices used by a user. In some embodiments, terminal 13 may include one or more combinations of mobile devices, tablet computers, laptop computers, etc.

[0022] Storage device 14 can store data and / or instructions, for example, storage device 14 can store data instructions based on big data analytics data transfer methods.

[0023] In this embodiment of the invention, the following are provided: Figure 2 The above describes a data transmission method based on big data analytics, comprising steps S1 to S5: Step S1: Obtain the video recorded when the user's original mobile phone was in use.

[0024] Videos recorded while the user was using their original phone refer to videos recorded by the user during their use of their original phone before they changed phones. These videos include records of application usage, file operations, system settings, and other behaviors.

[0025] Step S2: Determine multiple recommended migration software and recommended migration data size based on the recorded video of the user's original mobile phone.

[0026] In some embodiments, determining multiple recommended migration software and the recommended migration data size based on the recorded video from the user's original mobile phone usage includes: determining multiple recommended migration software and the recommended migration data size based on the recorded video from the user's original mobile phone usage using a data processing model.

[0027] The data processing model is a long short-term neural network model. The input of the data processing model is the video recorded when the user's original mobile phone was in use. The output of the data processing model is multiple recommended migration software and the recommended migration data size.

[0028] Long Short-Term Memory (LSTM) neural network models can process video recordings made by the user's original mobile phone over continuous time periods. They can better capture the relationships within the time series of these recordings and output features that comprehensively consider the characteristics of the video recordings at various points in time, making the output features more accurate and comprehensive.

[0029] Recording videos captures user actions on their phones, such as which applications are opened, their frequency of use, duration of operations, and file access. This behavioral information directly reflects the user's dependence on specific applications and data. For example, if a user frequently uses WeChat and the Photos app in a video, it indicates that these applications are very important to the user, so migrating WeChat and the Photos app could be recommended. Videos can also record the frequency and methods of users accessing specific data, such as viewing photos and downloading files. This information can help determine the amount of data that needs to be migrated. For another example, if a user repeatedly views photos in the Photos app in a video, and there are a large number of photos, migrating the Photos app could be recommended, and the amount of data to be migrated could be estimated.

[0030] In some embodiments, the data processing model includes an application identification layer, a data access pattern extraction layer, and a migration data size calculation layer. The input to the application identification layer is a video recording of the user's original phone usage, and the output is a list of identified applications and a segmented video of each application's usage. The input to the data access pattern extraction layer is the segmented video of each application's usage, and the output is the data access pattern, usage frequency, and priority level of each application. The input to the migration data size calculation layer is the data access pattern, usage frequency, and priority level of each application, and the output is multiple recommended migration software and a recommended migration data size.

[0031] The application identification layer, usage frequency analysis layer, data access pattern extraction layer, migration priority evaluation layer, and migration data size calculation layer all include long short-term neural networks.

[0032] Data access patterns refer to the ways and frequencies with which users access different types of data within an application. Data access patterns reflect a user's dependence on and usage habits regarding the data within the application. For example, in WeChat, users primarily access chat history (text, images, videos), Moments, and payment records. Similarly, in the Photos app, users primarily access photos, videos, and screenshots.

[0033] Usage frequency refers to the number of times and duration a user uses an application within a certain period of time (e.g., a day or a week).

[0034] Priority refers to assessing the importance of the application in the data migration process.

[0035] Step S3: Obtain data on multiple recommended migration software.

[0036] In some embodiments, data from multiple recommended migration software programs can be obtained via a USB interface.

[0037] The data for recommended migration software refers to all data related to the recommended migration software.

[0038] Step S4: Determine the target migration data based on the data from the multiple recommended migration software and the size of the recommended migration data.

[0039] In some embodiments, Figure 3 This is a schematic diagram of a process for determining target migration data according to an embodiment of the present invention. The determination of target migration data includes steps S21 to S24: Step S21: Based on the data of the multiple recommended migration software and the size of the recommended migration data, a data migration model is used to determine the maximum value and minimum value of the migration data for each recommended migration software.

[0040] In some embodiments, the data transfer model is a deep neural network model. A deep neural network model includes deep neural networks (DNNs). A deep neural network may include multiple processing layers, each consisting of multiple neurons, and each neuron performs matrix transformations on the data.

[0041] The maximum value of migration data for each recommended migration software is the upper limit of the amount of data that needs to be migrated in each recommended migration software.

[0042] The minimum value of migration data for each recommended migration software is the lower limit of the amount of data that needs to be migrated in each recommended migration software.

[0043] Deep neural network models possess powerful data processing capabilities, nonlinear modeling capabilities, hierarchical feature extraction capabilities, and learning and optimization capabilities. Through deep neural network models, the scope of migrated data can be determined more accurately, migration plans can be optimized, and migration efficiency and user satisfaction can be improved.

[0044] In some embodiments, determining the maximum and minimum values ​​of migration data for each recommended migration software using a data migration model based on the data of the plurality of recommended migration software and the size of the recommended migration data includes steps S211 to S213: Step S211: Based on the data of the multiple recommended migration software and the size of the recommended migration data, determine the high-frequency data access ratio, core function data retention weight, and redundant data accumulation rate of each recommended migration software.

[0045] In some embodiments, deep neural networks can be used to determine the proportion of high-frequency data access, the weight of core function data retention, and the rate of redundant data accumulation for each recommended migration software.

[0046] The high-frequency data access ratio for each recommended migration software is the percentage of data in each recommended migration software that has been frequently accessed, read, and modified by users recently, out of the total data volume of that software.

[0047] The core functional data retention weight for each recommended migration software is the ratio between the data that must be migrated to maintain basic business operations and the expired cached data that can be discarded.

[0048] The redundant data accumulation rate of each recommended migration software is a quantitative indicator of the proportion of useless data that has not been accessed for a long time, does not contribute substantially to the operation of the software, and can be cleaned up within each recommended migration software.

[0049] Deep neural networks, through their multi-layered perceptual structure, can perform deep, non-linear feature extraction on data from multiple recommendation migration software programs. By cross-analyzing file access frequency, file type attributes, and business logic relationships within the software, deep neural networks can identify which data belongs to the active parts of frequent user interaction, thereby determining the proportion of high-frequency data access for each recommendation migration software program. Simultaneously, deep neural networks can accurately locate silent files residing at the storage layer with no long-term interaction records, and, combined with global constraints on the size of recommendation migration data, calculate the redundant data accumulation rate for each recommendation migration software program.

[0050] Step S212: Based on the size of the recommended migration data, the data of the multiple recommended migration software, the proportion of high-frequency data access for each recommended migration software, the core function data retention weight, and the redundant data accumulation rate, determine the migration priority ranking of the multiple recommended migration software, the migration space requirement of each recommended migration software, and the additional migration experience benefit sequence.

[0051] In some embodiments, deep neural networks can be used to determine the migration priority ranking of multiple recommended migration software, the migration space requirement of each recommended migration software, and the sequence of additional migration experience benefits.

[0052] The migration priority ranking of multiple recommended migration software is generated by a deep neural network based on the user's dependence on each software and the data value, from high to low, to determine the order in which each software receives migration quotas. A higher migration priority ranking means that the recommended migration software has a greater privilege in terms of the number of storage bytes it can occupy in the storage resource pool.

[0053] The migration space requirement for each recommended software is calculated using a deep neural network, representing the urgency coefficient of the storage space required to ensure the software's basic operability and core business loop. A higher urgency coefficient indicates a larger minimum data volume required for the software to achieve its basic business loop.

[0054] The additional migration experience benefit sequence for each recommended software refers to the discrete set of values ​​that, after completing the migration that ensures the basic operation of the software and the integrity of the core data, increases with a certain amount of storage space, such as every 500MB or 1GB increase, and the corresponding increase in user experience.

[0055] Deep neural networks can analyze the competitive relationships among different migration software programs under limited recommended migration data sizes. By learning the space sensitivity of each migration software program, deep neural networks can deduce which software data should be prioritized for migration when resources are insufficient, thus generating a migration priority ranking of multiple recommended migration software programs. Furthermore, deep neural networks can calculate the minimum physical space required for each migration software program to avoid errors or functional deficiencies, thereby determining the migration space requirements of each recommended migration software program. Through further mining of the value of high-frequency user data, deep neural networks can identify the experience benefits brought by allocating additional space, ultimately determining the sequence of additional migration experience benefits for each recommended migration software program.

[0056] Step S213: Based on the migration priority ranking of the multiple recommended migration software, the migration space requirement of each recommended migration software, and the additional migration experience benefit sequence, determine the maximum value and minimum value of the migration data for each recommended migration software.

[0057] In some embodiments, a deep neural network can be used to determine the maximum and minimum values ​​of migration data for each recommended migration software.

[0058] Deep neural networks (DNNs) map abstract policy coefficients to physical byte values ​​by comprehensively processing the migration priority ranking of multiple recommended migration software, the migration space requirements of each recommended migration software, and the sequence of additional migration experience benefits. Through complex non-linear weighted calculations, DNNs directly map the requirement level representing the survival baseline to the minimum migration data for each recommended migration software. Simultaneously, using migration priority ranking as the allocation basis, DNNs dynamically accumulate and stress-test the migration space requirements and the sequence of additional migration experience benefits to ensure that the maximum migration data for each recommended migration software is determined for each application without exceeding the total recommended migration data size.

[0059] Step S22: Based on the data of the multiple recommended migration software, the size of the recommended migration data, the maximum value of the migration data of each recommended migration software, and the minimum value of the migration data of each recommended migration software, generate multiple data transmission schemes based on big data analysis and the similarity of each data transmission scheme based on big data analysis.

[0060] In some embodiments, generating multiple data transmission schemes based on big data analysis and the similarity of each data transmission scheme based on the data of the multiple recommended migration software, the size of the recommended migration data, the maximum value of the migration data of each recommended migration software, and the minimum value of the migration data of each recommended migration software includes: using a generative adversarial network to generate multiple data transmission schemes based on big data analysis and the similarity of each data transmission scheme based on the data of the multiple recommended migration software, the size of the recommended migration data, the maximum value of the migration data of each recommended migration software, and the minimum value of the migration data of each recommended migration software.

[0061] Generative Adversarial Networks (GANs) consist of a generator and a discriminator. The inputs to the GAN are the data from the multiple recommended migration software programs, the size of the recommended migration data, the maximum value of the migration data for each recommended migration software program, and the minimum value of the migration data for each recommended migration software program. The outputs of the GAN are multiple data transmission schemes based on big data analytics and the similarity score of each data transmission scheme based on big data analytics.

[0062] The data transfer scheme based on big data analytics is a specific plan for which data needs to be transferred for each recommended migration software.

[0063] For example, Option A involves migrating 500MB of WeChat chat history, 1GB of photos, and 300MB of music files. Option B involves migrating 300MB of WeChat chat history, 2GB of photos, and 200MB of music files. Option C involves migrating 700MB of WeChat chat history, 1.5GB of photos, and 500MB of music files.

[0064] Traditional data migration methods typically offer only a single migration scheme, failing to meet the needs of diverse users. Generative Adversarial Networks (GANs), however, can generate multiple data transmission schemes based on big data analysis, allowing subsequent graph neural networks to consider them comprehensively.

[0065] Generative Adversarial Networks (GANs) can generate multiple data transmission schemes based on big data analytics, considering data from various recommendation migration software programs, the size of the recommended migration data, and the maximum and minimum values ​​of the migration data, while also calculating their similarity. GANs are based on a unique generator-discriminator architecture, powerful data generation capabilities, the ability to model complex relationships, and optimization capabilities. By using GANs, various data transmission schemes based on big data analytics can be generated, ensuring the diversity and rationality of the schemes, thereby improving migration efficiency and user satisfaction.

[0066] Step S23: Construct a data transmission graph based on big data analysis. The data transmission graph based on big data analysis includes multiple nodes and multiple edges between the nodes. Each node represents a data transmission scheme based on big data analysis, and the edge between two nodes represents the similarity between two data transmission schemes based on big data analysis.

[0067] A data transmission graph based on big data analysis can be constructed. The data transmission graph based on big data analysis includes multiple nodes and multiple edges between the nodes. Each node represents a data transmission scheme based on big data analysis, and the edge between two nodes represents the similarity between two data transmission schemes based on big data analysis.

[0068] Step S24: Process the data transmission map based on big data analysis using a graph neural network to determine the target migration data.

[0069] The input to the graph neural network is the data transmission map based on big data analysis, and the output of the graph neural network is the target migration data.

[0070] The target migration data is the data that needs to be migrated, determined by comprehensively considering multiple data transmission schemes based on big data analysis and their similarity within a data transmission graph based on big data analysis using a graph neural network. For example, the graph neural network can aggregate the features and similarity relationships of schemes A, B, and C to select the optimal scheme A as the target migration data.

[0071] The data transmission graph based on big data analytics uses nodes and edges to represent data transmission schemes based on big data analytics and their similarity, which can intuitively show the relationships between the schemes. For example, nodes A, B, and C represent three data transmission schemes based on big data analytics, edge AB indicates that the similarity between scheme A and scheme B is 0.8, and edge AC indicates that the similarity between scheme A and scheme C is 0.6.

[0072] Graph neural networks are specifically designed for processing data transmission graph data based on big data analytics, and are able to extract features from nodes and edges.

[0073] Graph neural networks optimize migration schemes and determine target migration data by aggregating information from nodes and edges.

[0074] Constructing a data transmission graph based on big data analytics can represent multiple data transmission schemes and their similarity relationships in a structured way, facilitating graph neural network (Graph Neural Network) analysis and optimization of migration schemes. Graph Neural Networks can process data transmission graphs based on big data analytics and determine target migration data because they can process the data transmission graph data, extract node features, and thus determine the target migration data, improving migration efficiency and accuracy.

[0075] Step S5: Perform data transmission based on big data analysis based on the target migration data.

[0076] In some embodiments, the target migration data can be transmitted via a Wi-Fi network based on big data analytics.

[0077] Based on the same inventive concept Figure 4 This invention provides a schematic diagram of a data transmission system based on big data analytics, which includes: The first acquisition module 41 is used to acquire the recorded video when the user's original mobile phone was in use; Data processing module 42 is used to determine multiple recommended migration software and the size of recommended migration data based on the video recorded when the user's original mobile phone was in use; The second acquisition module 43 is used to acquire data from multiple recommended migration software programs; The determination module 44 is used to determine the target migration data based on the data of the multiple recommended migration software and the size of the recommended migration data; The transmission module 45 is used for data transmission based on big data analysis based on the target migration data.

[0078] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments of this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0079] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A data transmission method based on big data analysis, characterized in that, include: Obtain videos recorded on the user's original mobile phone; Based on the recorded videos of the user's original mobile phone, multiple recommended migration software and recommended migration data size are determined. Obtain data from multiple recommended migration software programs; The target migration data is determined based on the data from the multiple recommended migration software and the size of the recommended migration data. Data transmission based on big data analytics is performed on the target migration data.

2. The data transmission method based on big data analysis as described in claim 1, characterized in that, The determination of target migration data based on the data from the multiple recommended migration software and the size of the recommended migration data includes: Based on the data from the multiple recommended migration software programs and the size of the recommended migration data, a data migration model is used to determine the maximum and minimum values ​​of the migration data for each recommended migration software program. Based on the data from the multiple recommended migration software, the size of the recommended migration data, the maximum value of the migration data for each recommended migration software, and the minimum value of the migration data for each recommended migration software, multiple data transmission schemes based on big data analysis are generated, along with the similarity of each data transmission scheme based on big data analysis. A data transmission graph based on big data analysis is constructed. The data transmission graph based on big data analysis includes multiple nodes and multiple edges between the nodes. Each node represents a data transmission scheme based on big data analysis, and the edge between two nodes represents the similarity between two data transmission schemes based on big data analysis. The target migration data is determined by processing the data transmission map based on big data analysis using a graph neural network.

3. The data transmission method based on big data analysis as described in claim 1, characterized in that, The data migration model is a deep neural network model.

4. The data transmission method based on big data analysis as described in claim 2, characterized in that, The input to the graph neural network is the data transmission map based on big data analysis, and the output of the graph neural network is the target migration data.

5. A data transmission system based on big data analytics, characterized in that, include: The first acquisition module is used to acquire videos recorded when the user's original mobile phone was in use; The data processing module is used to determine multiple recommended migration software and the size of recommended migration data based on the video recorded when the user's original mobile phone was in use; The second acquisition module is used to acquire data from multiple recommended migration software programs; The determination module is used to determine the target migration data based on the data from the multiple recommended migration software and the size of the recommended migration data; The transmission module is used for data transmission based on big data analysis of the target migration data.

6. The data transmission system based on big data analysis as described in claim 5, characterized in that, The determining module is also used for: Based on the data from the multiple recommended migration software programs and the size of the recommended migration data, a data migration model is used to determine the maximum and minimum values ​​of the migration data for each recommended migration software program. Based on the data from the multiple recommended migration software, the size of the recommended migration data, the maximum value of the migration data for each recommended migration software, and the minimum value of the migration data for each recommended migration software, multiple data transmission schemes based on big data analysis are generated, along with the similarity of each data transmission scheme based on big data analysis. A data transmission graph based on big data analysis is constructed. The data transmission graph based on big data analysis includes multiple nodes and multiple edges between the nodes. Each node represents a data transmission scheme based on big data analysis, and the edge between two nodes represents the similarity between two data transmission schemes based on big data analysis. The target migration data is determined by processing the data transmission map based on big data analysis using a graph neural network.

7. The data transmission system based on big data analysis as described in claim 5, characterized in that, The data processing model is a long short-term neural network model.

8. The data transmission system based on big data analysis as described in claim 6, characterized in that, The input to the graph neural network is the data transmission map based on big data analysis, and the output of the graph neural network is the target migration data.

9. An electronic device, characterized in that, include: processor; Memory; And a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the data transmission method based on big data analysis as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the data transmission method based on big data analysis as described in any one of claims 1 to 4.

Images