A data sharing method and system based on artificial intelligence

Abstract

The present invention relates to a data sharing method and system based on artificial intelligence. The method comprises: the collection center acquires the multidimensional data features in the data source system, and calculates the sharing priority of the data according to the features; the control center calculates and selects the optimal data transmission path according to the sharing priority, determines the performance indicators of the transmission nodes and the transmission capacity of the intelligent sharing system; the control center selects the most suitable data transmission mode based on the calculated optimal transmission path and node performance, and adjusts the data flow direction; the control center monitors the data transmission process in real time, and if a bottleneck problem occurs, dynamically adjusts the data flow by optimizing the transmission path and transmission nodes; the control center issues optimization instructions to ensure performance improvement and transmission stability during data sharing. The present invention improves data transmission efficiency through machine learning and adaptive algorithms, and can adjust the sharing strategy according to real-time feedback in practical applications.

Description

Technical Field

[0001] The present invention relates to the field of data sharing, and in particular to an intelligent data sharing method and system based on artificial intelligence. Background Art

[0002] With the rapid development of information technology, especially the widespread application of big data, cloud computing and artificial intelligence, data sharing has become an important means for various industries to achieve efficient information flow, decision support and resource optimization. In the traditional data sharing process, data transmission efficiency, sharing mode and transmission path selection have always been the key factors to improve system performance. Existing technologies usually rely on static rules and preset paths for data transmission, which is difficult to dynamically adapt to complex and changing network environments, device status and data volume fluctuations, resulting in inefficiency and instability in data transmission. In particular, when facing large-scale data exchange, it is impossible to fully utilize intelligent algorithms for real-time adjustment and optimization.

[0003] In recent years, with the rapid progress of machine learning and artificial intelligence technologies, intelligent data sharing methods have gradually been applied to data transmission. However, existing intelligent data sharing methods often fail to fully combine multi-dimensional data characteristics, transmission node performance, and real-time environmental factors, resulting in the inability to effectively improve the overall system performance and data flow efficiency in complex application scenarios.

[0004] Therefore, there is an urgent need for a new AI-based data sharing method and system that can make full use of real-time data and intelligent algorithms, dynamically adjust data sharing strategies, optimize the data transmission process, and improve the efficiency and reliability of information flow. Summary of the invention

[0005] The present invention provides a data sharing method based on artificial intelligence, which includes: The collection center obtains the multidimensional data features in the data source system and calculates the data sharing priority based on the features; The control center calculates and selects the optimal data transmission path based on the sharing priority, and determines the performance indicators of the transmission nodes and the transmission capacity of the intelligent sharing system; The control center selects the most appropriate data transmission mode and adjusts the data flow based on the calculated optimal transmission path and node performance; The control center monitors the data transmission process in real time. If a bottleneck problem occurs, the data flow is dynamically adjusted by optimizing the transmission path and transmission nodes. Based on the real-time transmission status, the control center issues optimization instructions to ensure performance improvement and transmission stability during data sharing.

[0006] An artificial intelligence-based data sharing method as described above, wherein the method further includes dynamically adjusting the transmission priority according to real-time feedback during the data transmission process.

[0007] An artificial intelligence-based data sharing method as described above, wherein the method trains historical data transmission patterns through a machine learning algorithm to optimize data sharing decisions.

[0008] As described above, an artificial intelligence-based data sharing method adjusts the data transmission path to improve sharing efficiency according to the device status and environmental conditions of the data source system.

[0009] An artificial intelligence-based data sharing method as described above, wherein the method predicts data transmission bottlenecks through a data traffic prediction algorithm and takes proactive measures to avoid bottlenecks.

[0010] As described above, an artificial intelligence-based data sharing method adopts an adaptive algorithm to adjust the data transmission mode in real time to cope with network changes or data volume fluctuations.

[0011] An artificial intelligence-based data sharing method as described above, wherein the method shares data through a cloud platform and combines multi-node computing to optimize data transmission efficiency.

[0012] The present invention also provides a data annotation system based on big data management, wherein the system comprises: The collection center is used to obtain multi-dimensional data features in the data source system and calculate the sharing priority of the data; The control center is used to calculate and select the optimal data transmission path, monitor the data transmission process, adjust the transmission mode, and issue optimization instructions; The data exchange platform is used to share and transmit data according to the instructions of the control center.

[0013] The present invention also provides a computer storage medium, comprising: at least one memory and at least one processor; The memory is used to store one or more program instructions; A processor is used to run one or more program instructions to execute an artificial intelligence-based data sharing method.

[0014] The beneficial effects achieved by the present invention are as follows: the present invention can dynamically adjust the data transmission path and sharing mode through an intelligent optimization algorithm based on artificial intelligence, significantly improving the efficiency and stability of data sharing. Its adaptive adjustment mechanism can respond to changes in network environment, node performance and data flow in real time, optimize the data transmission process, avoid bottlenecks and delays, and reduce the operation and maintenance costs of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0016] Figure 1 This is a flow chart of a data sharing method based on artificial intelligence provided in Example 1 of the present application; Figure 2 This is a schematic diagram of a data annotation system based on big data management provided in Example 2 of the present application. DETAILED DESCRIPTION

[0017] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0018] Embodiment 1

[0019] like Figure 1 As shown, the first embodiment of the present application provides a data sharing method based on artificial intelligence, comprising the following steps: Step S10: The collection center obtains multidimensional data features in the data source system and calculates the data sharing priority according to the features; In this step, the collection center obtains real-time multi-dimensional data features from multiple data source systems. Data sources include various sensors, user devices, environmental monitoring platforms, and external data interfaces. These data cover different types of information such as temperature, humidity, device status, user behavior, and environmental parameters. The acquired data is first standardized to ensure that its numerical range is uniform and noise is removed to improve the quality and availability of the data. The characteristic values ​​of each data source are converted into a vector form suitable for calculation. ,in, Represents the i-th feature. Each feature may change over time, and there may be a certain correlation between each data point, so the time-varying and dynamic changes of the data need to be fully considered.

[0020] In order to achieve intelligent optimization during data transmission, the collection center calculates the sharing priority of each piece of data based on factors such as the time-varying, volatility, and historical variability of each feature. The priority calculation formula is as follows: , where P represents the sharing priority of each piece of data, which determines the order in which the data is processed in the subsequent transmission process. The data with higher priority will be transmitted first; n represents the total number of features in the data; Indicates feature weight. The importance of each data feature is different. The collection center assigns weights to the features according to their actual application scenarios in data sharing. The size of the weight reflects the importance of the feature to the final sharing decision. and is a regulating factor used to balance the effects of time variability and feature volatility on the calculation of shared priorities; Indicates the i-th feature in the time interval The rate of change within reflects the speed at which the feature changes over time. It is used to measure the time-varying nature of the feature. Features with a larger rate of change will have a greater weight in the priority calculation. represents the volatility of the ith feature, Representation characteristics The value at time k, is the mean of the feature, is the standard deviation, A constant introduced to prevent division by zero errors. This formula is used to measure the fluctuation of feature values. Features with larger fluctuations are more important in priority calculation, indicating that changes in this feature have a greater impact on system decisions. It is the real-time change rate of the i-th feature during the transmission process, reflecting the dynamic change of the feature. Features with a larger change rate will be transmitted first. Represents the sum of the squares of the change rates of all features, which is used to normalize the dynamic changes of each feature. Through this value, the dynamic changes of different features can be adjusted to the same scale; It is a regulating factor used to control the influence of the normalized weight of the change rate in the priority calculation.

[0021] Step S20: The control center calculates and selects the optimal data transmission path according to the sharing priority, and determines the performance indicators of the transmission nodes and the transmission capacity of the intelligent sharing system; In this step, the control center further decides how to optimize the data transmission process based on the data sharing priority P calculated by the collection center. The task of the control center is to select the optimal data transmission path and evaluate the performance of each transmission node to ensure the overall transmission efficiency and stability of the system.

[0022] The control center first sorts all the data to be transmitted according to the sharing priority. The data with higher sharing priority will be given priority for transmission. Therefore, the control center will allocate the data to different transmission paths according to the priority of the data to ensure that the critical data can be quickly transmitted to the target system.

[0023] In order to select the optimal transmission path, the control center needs to evaluate the adaptability and transmission delay of different paths. The selection of the transmission path is based on multiple factors, including network bandwidth, distance between nodes, network topology, and current network load. The transmission delay of each path can be expressed as the following formula: ,in, is the total delay of path k; n represents the total number of optional paths; is the transmission distance of the i-th data packet on path k; is the bandwidth of path k; is the network load factor on path k, reflecting the current network congestion level. The control center calculates the delays of different paths and selects the path with the smallest delay to transmit high-priority data.

[0024] During data transmission, the performance of the node is crucial. The control center evaluates the performance of each transmission node, mainly by calculating the processing power, response time and reliability of the node. The performance index of each transmission node can be calculated by the following formula: ,in, is the comprehensive performance evaluation index of node n; m is the number of nodes; is the computational cost of node n when processing the i-th data; is the computing power of node n; is the error rate of node n when processing the i-th data; Score the reliability of node n; and It is the adjustment coefficient used to adjust the weight of computing consumption and error rate in performance evaluation. The control center selects the node with the best performance for data transmission based on the performance evaluation results of the node to ensure the efficiency and reliability of the data transmission process.

[0025] The transmission capacity of the intelligent sharing system determines the efficiency of the entire data sharing process. The control center calculates the overall transmission capacity of the system based on factors such as the current network status, the performance of each transmission node, and the total bandwidth of the system. The system's transmission capacity calculation formula is: ,in, is the total transmission capacity of the system, which indicates the data flow that the system can handle under the current network status, bandwidth, and node load, and determines whether the system can transmit data stably; n represents the number of transmission paths or nodes; is the bandwidth of path k, which represents the maximum data flow that the path can provide when transmitting data. The larger the bandwidth, the stronger the transmission capacity of the path; is the network load factor of path k, which is used to indicate the congestion level or load of the current path. A path with a higher load will reduce the transmission capacity of the system. is the path k adjustment factor, which is used to balance the computing power and network load of each path; is the load of the ith node on path k, indicating the resource consumption of the node; is the computing power of the i-th node on path k, indicating the ability of the node to process data. The stronger the computing power, the higher the processing efficiency of the node; is the transmission delay on path j, which indicates the time consumption when data is transmitted on this path; is the delay adjustment factor of path j, which is used to adjust the impact of delay on the system transmission capacity; It is a global adjustment factor used to adjust the combined impact of each path delay and node load and balance different factors in the system.

[0026] Based on a comprehensive evaluation of transmission paths, node performance, and system capabilities, the control center dynamically selects the optimal data transmission path and adjusts the transmission strategy in real time. In particular, during the transmission process, the control center will adjust the path selection and node allocation based on real-time feedback to ensure that data can still be transmitted efficiently and stably when the system load changes or the network condition is unstable.

[0027] Step S30: The control center selects the most appropriate data transmission mode based on the calculated optimal transmission path and node performance, and adjusts the data flow direction; In this step, the control center further optimizes the data transmission process based on the optimal transmission path calculated in the previous step, node performance evaluation, and system transmission capacity. The main task is to select the most appropriate data transmission mode and adjust the data flow direction when necessary to ensure that data can be transmitted efficiently and stably from the source node to the target node.

[0028] The control center first selects the most appropriate data transmission mode based on factors such as network topology, transmission delay, bandwidth requirements, node performance, and real-time network load. During the selection process, the control center comprehensively considers the delay, bandwidth, node performance, and stability of each path. In order to accurately calculate the transmission efficiency of each path, the following calculation formula is used: ,in, is the total transmission benefit of path k, representing the comprehensive transmission capacity of the path; n represents the number of paths or nodes; is the bandwidth of the i-th node on path k; is the performance evaluation value of the i-th node on path k; is the transmission delay of the i-th node on path k; is the network load factor of path k, indicating the current network congestion; is the transmission load adjustment factor of path k; is the real-time change rate of the i-th data on path k; is the computing processing capacity of the i-th node on path k. This formula comprehensively considers the path bandwidth, delay, node performance, load conditions, and the dynamics of real-time data changes to determine the transmission efficiency of each path. The control center selects the path with the greatest transmission efficiency to ensure that high-priority data can be transmitted through the optimal path.

[0029] The adjustment of data flow is to cope with unforeseen factors such as network congestion, node failure or transmission delay. The control center monitors the status of each transmission path and node in real time and dynamically adjusts the data flow based on real-time feedback. Specifically, the control center adjusts the data flow based on the following conditions: If the load on a path or node is too high, the control center will calculate an alternative path and transfer part of the data flow to the path with lower load. At this time, the control center adjusts the data flow according to the load of the path and the network status. Specifically, the adjustment of data flow depends on the network load, bandwidth, delay and node processing capacity. The following formula is used to dynamically adjust the data flow: ,in, is the adjusted data flow; is the raw data traffic of the current path; is the load of the current path; is the maximum load of the path; is the bandwidth of the path; is the transmission delay of the path; is the processing capacity of the path node; and is a regulation factor that controls the impact of network load and bandwidth / delay on traffic adjustment. This formula combines network load and bandwidth / delay ratio to dynamically adjust traffic. By introducing the regulation factor, the control center can reduce traffic when the load is high and increase traffic when bandwidth is sufficient and latency is low.

[0030] When the network status is poor, the control center will choose another path to optimize data transmission. The decision basis for path switching takes into account the path bandwidth, delay, node load and network congestion. The path selection formula is as follows: ,in, is the comprehensive performance of the new path; n represents the number of all possible paths considered in the system; is the bandwidth on path i; is the performance evaluation value on path i; is the transmission delay on path i; is the network load factor of path i, reflecting the congestion level of the path; is the load of the node on path i; is the computing power of the node on path i; It is an adjustment factor used to adjust the impact of load and computing power on path selection.

[0031] The control center will continuously adjust and optimize the data flow based on real-time transmission data feedback. By real-time detection of the delay, bandwidth utilization, node load and network status of each path, the control center can dynamically adjust the data flow to avoid system bottlenecks or transmission interruptions. The control center not only considers the immediate efficiency of data transmission, but also conducts long-term evaluation of the stability of each transmission mode. If a mode performs well in the long term, the control center will give priority to this mode in subsequent transmissions; if the mode is at risk of overload or delay at a certain stage, the control center will adjust the strategy in advance to ensure the continued stability of the data flow.

[0032] Step S40: The control center monitors the data transmission process in real time. If a bottleneck problem occurs, the data flow is dynamically adjusted by optimizing the transmission path and transmission nodes. In this step, the control center continuously monitors various indicators during data transmission, such as transmission delay, bandwidth utilization, node load, network congestion, etc., to ensure smooth data transmission. When a network bottleneck or excessive transmission delay is detected, the control center will intervene in time to ensure the stability and efficiency of data transmission by optimizing the transmission path, adjusting node allocation, or dynamically adjusting data flow.

[0033] The control center monitors the status of each data transmission path in real time through an integrated monitoring system. The monitoring content includes but is not limited to: transmission delay. The control center will track the transmission delay on each path in real time to ensure the timeliness of the data transmission process; bandwidth utilization. The bandwidth utilization of each transmission path is tracked to ensure that the transmission path is not overly congested; node load. The control center monitors the performance of the node through the real-time load of the node to prevent node overload; network health status. The network status is globally monitored, including the packet loss rate and retransmission rate of each path, to ensure the stability of data transmission.

[0034] The monitoring system will continuously collect this data and compare it with the preset threshold. When the system finds that a certain indicator exceeds the preset threshold, it will automatically trigger the bottleneck detection mechanism. The control center uses the set bottleneck identification algorithm to detect in real time whether there is a network bottleneck or performance bottleneck. The key indicators of bottleneck detection include: delay exceeding the threshold. If the transmission delay of a path exceeds the set maximum delay threshold, it is considered that the path has a bottleneck; bandwidth saturation. If the bandwidth utilization of a path reaches or exceeds 100% and lasts for a period of time, the path is considered to have a bottleneck; node load is too high. If the load of a node exceeds the set maximum load threshold, it means that the node may have a performance bottleneck, affecting the data transmission efficiency; data packet loss rate. When the packet loss rate exceeds the set threshold, it indicates path congestion or node failure, which may lead to a decrease in data transmission quality.

[0035] Once the monitoring system detects a bottleneck, the control center will solve the problem by optimizing the transmission path. The goal of path optimization is to guide the data flow to a path with sufficient bandwidth and low latency. The optimization formula is as follows: ,in, is the expected performance gain of path k after optimization; n is the total number of paths involved in the transmission; is the bandwidth of the i-th node on path k; is the performance evaluation value of the i-th node on path k; is the transmission delay of the i-th node on path k; is the load of path k; is the network load factor of path k; is the real-time change rate of the i-th node on path k; is the computing processing capacity of the i-th node on path k; and It is an adjustment factor used to control the weight of delay and load in path optimization. The control center adjusts the path selection to minimize the delay of the transmission path, maximize the bandwidth, and balance the node load, thereby optimizing data flow and reducing the probability of bottlenecks.

[0036] In addition to optimizing the path, the control center will also adjust the data transmission nodes according to the real-time load and performance status of the nodes. By analyzing the node load and computing power, the control center selects nodes with higher performance and lower load for data processing. The node adjustment formula is: ,in, Select the index for the adjusted node; m represents the number of all nodes participating in the transmission; is the bandwidth of node n; is the performance evaluation value of node n; is the load of node n; is the maximum load of node n; is the load factor of node n; is the adjustment factor, which controls the intensity of node adjustment; is the real-time change rate of node n; is the computing processing capacity of node n. The control center reduces transmission bottlenecks and ensures smooth data transmission by selecting nodes with strong processing capacity and low load.

[0037] After optimizing the paths and nodes, the control center will adjust the data flow according to the real-time monitoring data. The control center uses the flow adjustment algorithm to dynamically adjust the data flow distribution to ensure the efficiency and stability of the transmission process. The formula for data flow adjustment is: ,in, is the data flow of path k at time t; is the data flow of path k at time t−1; is the load of path k at time t; is the maximum load of path k; It is an adjustment factor used to control the intensity of data flow adjustment. The control center adjusts the data flow in real time to avoid overload of paths and nodes and ensure the stability of the entire data transmission process.

[0038] Through the above steps, the control center can monitor the data transmission process in real time, discover bottleneck problems in time, and optimize the transmission path, adjust node allocation, and dynamically adjust data flow.

[0039] Step S50: According to the real-time transmission status, the control center issues optimization instructions to ensure performance improvement and transmission stability during data sharing.

[0040] In this step, the control center evaluates the overall performance of the system based on the real-time transmission status, especially indicators such as network load, data transmission delay, node status and bandwidth utilization. When the monitoring system detects any problems that may affect the stability and performance of data sharing, the control center will issue corresponding optimization instructions according to the predetermined optimization strategy to ensure that the entire system can operate efficiently and stably.

[0041] The control center continuously tracks the status of each transmission path, node, and data flow through an integrated monitoring system. Key parameters monitored include: transmission delay, bandwidth utilization, node load, packet loss rate, and retransmission rate. Real-time monitoring data is transmitted to the control center through a feedback mechanism for further analysis and decision-making.

[0042] The control center evaluates the overall performance based on real-time monitoring data and determines whether optimization is needed. The control center evaluates the stability and performance of the transmission status through the following formula: , where Q is the overall performance evaluation index of the system, representing the comprehensive stability of the current transmission state; m represents the number of transmission paths; is the real-time bandwidth utilization of path k; is the bandwidth of path k; is the transmission delay of path k; is the maximum allowed delay of path k; is the real-time load of path k; is the maximum load of path k; is the packet loss rate of path k; is the maximum allowed packet loss rate; It is the adjustment coefficient used to control the impact of various factors on the optimization instructions. If Q exceeds the predetermined performance threshold, the control center believes that there are bottlenecks or unstable factors in some parts of the transmission process, and optimization measures must be taken.

[0043] Once the performance evaluation results show that the transmission status is unstable, the control center will issue optimization instructions based on the location and type of specific bottlenecks. The main contents of the optimization instructions include: path optimization. If the bandwidth utilization of a certain path is monitored to be too high, the delay is too large, or the node load is too heavy, the control center will issue instructions to transfer data traffic to a path with lower load and more sufficient bandwidth; node load balancing. If the load of some nodes is too high, the control center will migrate tasks from nodes with heavier loads to nodes with lighter loads to avoid node overload and ensure the stability of data processing; traffic scheduling. The control center dynamically adjusts data traffic based on real-time bandwidth utilization and network load, optimizes the allocation of network resources, and reduces conflicts and bottlenecks in data traffic; adjusts the transmission mode. If it is found that the current transmission mode is not suitable for the current network status, the control center will switch to a more suitable transmission mode (for example, from wired transmission to wireless transmission, or from parallel transmission to serial transmission) to improve the efficiency of data transmission.

[0044] Optimization instructions will be sent to relevant nodes and paths through the control center's command system, and corresponding adjustments will be made immediately.

[0045] After the optimization command is issued, the control center will continue to monitor the optimization effect and make real-time adjustments. If it is found that the optimization measures have not completely solved the bottleneck problem, the control center will continue to make detailed adjustments. For example, the control center will dynamically adjust the data flow according to the real-time status of the network, node feedback and transmission delay, and gradually eliminate unstable factors in the transmission process.

[0046] In addition, the control center will analyze and summarize the effects of optimization measures, and revise the optimization strategies based on historical data, so that optimization measures can be more accurate and efficient in the future.

[0047] By monitoring the transmission status in real time and issuing optimization instructions, the control center can maintain the stability and efficiency of the system throughout the data sharing process, ensuring that data transmission can continue to be smooth and efficient in the face of various network fluctuations and bottlenecks.

[0048] Embodiment 2 like Figure 2 As shown, Embodiment 2 of the present application provides a data annotation system based on big data management, including: The collection center 21 is used to obtain multi-dimensional data features in the data source system and calculate the sharing priority of the data; The collection center is the core component of the entire data labeling system. It is responsible for obtaining multidimensional data features from the data source system and calculating the data sharing priority to ensure that the data can be transmitted and shared efficiently and orderly.

[0049] The collection center obtains various data features in real time through interfaces with multiple data source systems. These data sources include but are not limited to sensor networks, user behavior data, external data platforms, and internal enterprise systems. The acquired data features may include but are not limited to: sensor data, such as environmental parameters such as temperature, humidity, and pressure; equipment status, such as the operating status of machine equipment, fault records, performance data, etc.; user behavior data, such as click data, search history, consumption records, etc.; external data, including weather data, geographic location data, social media data, etc.

[0050] All acquired raw data will be preprocessed, including denoising, standardization, and missing value filling, to ensure data quality and consistency. The collection center converts the data into a unified feature vector format for subsequent processing. Data features are acquired by direct collection, batch acquisition, or through an API interface.

[0051] In order to optimize the data sharing process, the collection center calculates the sharing priority of each piece of data based on its characteristics. The calculation of sharing priority takes into account factors such as the time-varying nature of multidimensional data characteristics, historical variability, data importance, and real-time changes. The specific calculation method is: , where P represents the sharing priority of each piece of data, which determines the order in which the data is processed in the subsequent transmission process. The data with higher priority will be transmitted first; n represents the total number of features in the data; Indicates feature weight. The importance of each data feature is different. The collection center assigns weights to the features according to their actual application scenarios in data sharing. The size of the weight reflects the importance of the feature to the final sharing decision. and is a regulating factor used to balance the effects of time variability and feature volatility on the calculation of shared priorities; Indicates the i-th feature in the time interval The rate of change within reflects the speed at which the feature changes over time. It is used to measure the time-varying nature of the feature. Features with a larger rate of change will have a greater weight in the priority calculation. represents the volatility of the ith feature, Representation characteristics The value at time k, is the mean of the feature, is the standard deviation, A constant introduced to prevent division by zero errors. This formula is used to measure the fluctuation of feature values. Features with larger fluctuations are more important in priority calculation, indicating that changes in this feature have a greater impact on system decisions. It is the real-time change rate of the i-th feature during the transmission process, reflecting the dynamic change of the feature. Features with a larger change rate will be transmitted first. Represents the sum of the squares of the change rates of all features, which is used to normalize the dynamic changes of each feature. Through this value, the dynamic changes of different features can be adjusted to the same scale; It is an adjustment factor used to control the influence of the weight after the normalization of the change rate in the priority calculation. Through this formula, the collection center can dynamically calculate the priority of each data based on real-time data changes, thereby determining the order in which the data is processed during transmission. Data with higher priority will be processed and shared first, ensuring that critical data can be transmitted in a timely manner.

[0052] In order to ensure that the calculated sharing priority accurately reflects the actual importance of the data, the collection center will also monitor and optimize the data quality. By introducing data quality assessment indicators (such as data completeness, accuracy, consistency, etc.), the collection center can perform quality checks on the collected raw data. If some data has quality problems (such as missing values, outliers, etc.), the collection center will repair or remove the data to ensure that the data used for priority calculation is of high quality.

[0053] In addition, the collection center will adjust the weight coefficient in the data priority calculation based on real-time network conditions, node load and other factors to ensure that in different application scenarios, the data priority calculation can dynamically adapt to system requirements.

[0054] In the process of acquiring and processing data, the collection center is also responsible for data caching and temporary storage. To improve system efficiency, the collection center will cache the data to be shared, especially for large-scale, frequently changing data. The collection center will store the data in a temporary cache and share it on demand after calculating the sharing priority.

[0055] The control center 22 is used to calculate and select the optimal data transmission path, monitor the data transmission process, adjust the transmission mode, and issue optimization instructions; The control center is the core component of the entire data annotation system, responsible for coordinating and managing the data transmission process to ensure that data can be efficiently and stably transmitted from the source node to the target node. The main tasks of the control center include calculating and selecting the optimal data transmission path, monitoring the data transmission process in real time, adjusting the transmission mode according to the monitoring results, and issuing optimization instructions to optimize system performance when necessary.

[0056] Before data transmission begins, the control center needs to calculate and select the optimal data transmission path. The basis for selecting the optimal path includes: bandwidth requirements, delay requirements, node load, and network congestion.

[0057] To select the optimal path, the control center uses the following formula to evaluate: ,in, is the total transmission benefit of path k, representing the comprehensive transmission capacity of the path; n represents the number of paths or nodes; is the bandwidth of the i-th node on path k; is the performance evaluation value of the i-th node on path k; is the transmission delay of the i-th node on path k; is the network load factor of path k, indicating the current network congestion; is the transmission load adjustment factor of path k; is the real-time change rate of the i-th data on path k; is the computing processing capacity of the i-th node on path k. The control center calculates the comprehensive benefit of each path according to this formula , and choose the path that is most effective and best meets your needs.

[0058] The control center will monitor the entire data transmission process in real time to ensure that data can be transmitted smoothly along the predetermined path. The monitoring content includes: delay monitoring, bandwidth utilization, node load, and network status.

[0059] Real-time monitoring data is transmitted to the control center through a feedback mechanism for further analysis and decision-making.

[0060] When the control center detects problems such as high latency, insufficient bandwidth, heavy node load or network congestion during transmission, the control center will automatically adjust the data transmission mode. The adjustment modes include: path switching, load balancing, and bandwidth adjustment.

[0061] By dynamically adjusting the transmission mode, the control center can ensure the stability and efficiency of data transmission when the network load changes, node performance fluctuates, or path quality decreases.

[0062] Based on the real-time monitoring and adjusted transmission mode, the control center will issue optimization instructions to ensure that the performance of the data transmission process is improved. The optimization instructions include: path reallocation instructions, node adjustment instructions, and bandwidth adjustment instructions.

[0063] The optimization instructions are transmitted to the corresponding nodes and paths through the data exchange platform, and the corresponding adjustments are immediately executed to ensure the stability and efficiency of data transmission.

[0064] The data exchange platform 23 is used to share and transmit data according to the instructions of the control center.

[0065] The data exchange platform plays a core role in data sharing and transmission in the entire system. It ensures that data can be shared and transmitted smoothly between different systems and nodes according to the instructions issued by the control center. The data exchange platform realizes efficient data circulation through efficient transmission and management mechanisms, ensuring that data can be transmitted, processed and shared in a timely manner, thereby improving the overall efficiency of the system.

[0066] The work of the data exchange platform begins with receiving optimization instructions and transmission tasks from the control center. The control center will issue adjustment instructions based on real-time monitoring results and system requirements, and the data exchange platform will determine the data transmission path, transmission mode and traffic distribution based on these instructions. For example: path selection instructions, bandwidth adjustment instructions, node adjustment instructions. These instructions are transmitted through the communication interface between the control center and the data exchange platform to ensure the timeliness and accuracy of the instructions.

[0067] The core task of the data exchange platform is to manage and schedule the sharing and transmission of data. The platform uses a variety of mechanisms to ensure that data is transmitted smoothly and securely from the source node to the target node: The data exchange platform dynamically manages data traffic by real-time monitoring and analysis of network load, bandwidth utilization, and the status of each node. The platform will reasonably allocate data flow based on factors such as bandwidth limitations, transmission delays, and node loads to ensure that high-priority data can be transmitted in a timely manner and to prevent low-priority data from affecting the transmission efficiency of key data.

[0068] According to the optimization instructions of the control center, the data exchange platform can flexibly switch the data transmission mode. The platform supports multiple transmission modes, such as wired transmission, wireless transmission, parallel transmission, serial transmission, etc., and can automatically select the most appropriate mode according to the real-time network status and transmission requirements.

[0069] The data exchange platform performs real-time detection of errors during the transmission process. If packet loss or errors are found during data transmission, the platform will retransmit the data to ensure data integrity and reliability.

[0070] In order to improve the efficiency of data transmission, the data exchange platform also has caching and preprocessing functions. When there is a short-term delay in certain nodes or paths during the data transmission process, the data exchange platform will first cache the data to local storage and continue to transmit after the network condition is restored. Cache management strategies include: Temporary cache: When the system finds that the network or node load is too high, the data exchange platform will cache some data and transmit it after the network load is reduced. The data in the cache is sorted according to priority, and the data with high priority will be transmitted first.

[0071] Data flow control: When network conditions are poor, the platform will dynamically control the transmission rate of the data stream based on the current bandwidth and node status to avoid network congestion caused by excessive data transmission at the same time.

[0072] The data exchange platform is also responsible for ensuring the security of data during transmission. The platform will encrypt sensitive data to prevent data theft or tampering during transmission and dynamically generate and manage encryption keys according to the security requirements of the control center to ensure the confidentiality and integrity of data throughout the transmission process.

[0073] The data exchange platform monitors various indicators in the data transmission process in real time, such as transmission rate, delay, bandwidth utilization, node load, etc., and feeds this information back to the control center. The control center continues to optimize and adjust based on the feedback data. The data exchange platform provides detailed logs and reports to record the detailed information of each data transmission, including data source, target, transmission path, transmission duration, etc., to facilitate subsequent analysis and optimization.

[0074] When faced with a dynamically changing network environment, the data exchange platform can automatically adapt to different network conditions. For example, when a network failure occurs, the platform can automatically switch to an alternative path; when the bandwidth suddenly increases, the platform can immediately increase the data transmission rate, thereby achieving a smooth transition in the transmission process.

[0075] Corresponding to the above embodiment, an embodiment of the present invention provides a computer storage medium, including: at least one memory and at least one processor; The memory is used to store one or more program instructions; A processor is used to run one or more program instructions to execute an artificial intelligence-based data sharing method.

[0076] Corresponding to the above embodiments, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer storage medium contains one or more program instructions, and the one or more program instructions are used by a processor to execute an artificial intelligence-based data sharing method.

[0077] The embodiments disclosed in the present invention provide a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are executed on a computer, the computer executes the above-mentioned artificial intelligence-based data sharing method.

[0078] In the embodiment of the present invention, the processor may be an integrated circuit chip having the ability to process signals. The processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0079] The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present invention can be directly embodied as a hardware decoding processor for execution, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The processor reads the information in the storage medium and completes the steps of the above method in combination with its hardware.

[0080] The storage medium may be a memory, which may be, for example, a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memory.

[0081] Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.

[0082] The volatile memory may be a random access memory (RAM) which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced synchronous DRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus DRAM (DRRAM).

[0083] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0084] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the present invention can be implemented using a combination of hardware and software. When software is used, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any media that facilitates the transmission of computer programs from one place to another. Storage media can be any available media that can be accessed by general or special-purpose computers.

[0085] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A data sharing method based on artificial intelligence, characterized in that: The following steps are involved: The collection center obtains the multidimensional data features in the data source system and calculates the data sharing priority based on the features; The control center calculates and selects the optimal data transmission path based on the sharing priority, and determines the performance indicators of the transmission nodes and the transmission capacity of the intelligent sharing system; The control center selects the most appropriate data transmission mode and adjusts the data flow based on the calculated optimal transmission path and node performance; The control center monitors the data transmission process in real time. If a bottleneck problem occurs, the data flow is dynamically adjusted by optimizing the transmission path and transmission nodes. Based on the real-time transmission status, the control center issues optimization instructions to ensure performance improvement and transmission stability during data sharing.

2. The data sharing method based on artificial intelligence as claimed in claim 1, characterized in that: The method further includes dynamically adjusting the transmission priority according to real-time feedback during the data transmission process.

3. The data sharing method based on artificial intelligence as claimed in claim 1, characterized in that: The method trains historical data transmission patterns through machine learning algorithms to optimize data sharing decisions.

4. The data sharing method based on artificial intelligence as claimed in claim 1, characterized in that: The method adjusts the data transmission path according to the device status and environmental conditions of the data source system to improve the sharing efficiency.

5. The data sharing method based on artificial intelligence as claimed in claim 1, characterized in that: The method predicts data transmission bottlenecks through a data flow prediction algorithm and takes advance measures to avoid the bottlenecks.

6. The data sharing method based on artificial intelligence as claimed in claim 1, characterized in that: The method adopts an adaptive algorithm to adjust the data transmission mode in real time to cope with network changes or data volume fluctuations.

7. The data sharing method based on artificial intelligence as claimed in claim 1, characterized in that: The method shares data through a cloud platform and optimizes data transmission efficiency in combination with multi-node computing.

8. A data annotation system based on big data management, characterized in that: The system comprises: The collection center is used to obtain multi-dimensional data features in the data source system and calculate the sharing priority of the data; The control center is used to calculate and select the optimal data transmission path, monitor the data transmission process, adjust the transmission mode, and issue optimization instructions; The data exchange platform is used to share and transmit data according to the instructions of the control center.

9. A computer storage medium comprising: at least one memory and at least one processor; The memory is used to store one or more program instructions; A processor, configured to run one or more program instructions to execute an artificial intelligence-based data sharing method as described in any one of claims 1 to 7.

Images