Industrial internet edge multi-source heterogeneous data collaborative collection method and device

Abstract

The application provides an industrial internet edge multi-source heterogeneous data collaborative collection method and device, using the cross-source data difference of each edge node in the industrial internet and the business function weight of each data source to fuse the time sequence change gradient of the information transmission amount of each data source in the edge node into the data value density of the corresponding edge node; the transmission delay characteristics between the cloud center end and each edge node and the fluctuation characteristics of the network bandwidth in the cloud center end are used to determine the network resource constraint of the cloud center end; according to all the data value densities, the network resource constraint is used as the constraint condition of each edge node in the industrial internet, and the total data value transmitted to the cloud center end is maximized under the constraint condition, so that the data collection frequency of each edge node in the industrial internet is individually optimized. Based on the above scheme, the collection frequency optimization under the collaborative constraint of the edge node data value and the network resource delay can be realized.

Description

Technical Field

[0001] This application relates to the field of edge computing technology, and more specifically, to a method and apparatus for collaborative acquisition of multi-source heterogeneous data at the edge of an industrial internet. Background Technology

[0002] The Industrial Internet is an ecosystem that deeply integrates industrial systems with Internet technology. It achieves comprehensive interconnection of people, machines, and things through intelligent sensing, the Internet of Things, big data, and artificial intelligence. The core of the Industrial Internet lies in building a data-driven intelligent analysis and optimization closed loop. Through the deep collection and aggregation of data from all industrial elements, the entire industrial chain, and the entire value chain, it enables real-time perception, precise execution, and intelligent decision-making in the production process.

[0003] In traditional industrial network environments, network resource allocation strategies (such as bandwidth scheduling) rely solely on real-time indicators of the underlying network status. While this purely network-based allocation approach can guarantee link connectivity and basic performance, it completely ignores a crucial dimension: the actual value of upper-layer business data. This leads to high-value real-time control commands competing for the same bandwidth resources with low-value daily status monitoring data, resulting in delayed responses to critical business operations while non-critical data consumes a significant amount of network capacity. Consequently, resource allocation becomes disconnected from business needs, leading to inefficient use of transmission resources. This makes it impossible to guarantee deterministic transmission of high-value data in complex and ever-changing industrial scenarios, thus limiting the improvement of overall system performance. Therefore, how to optimize the acquisition frequency under the co-constraint of edge node data value and network resource latency has become a challenge for the industry. Summary of the Invention

[0004] This application provides a method and apparatus for collaborative acquisition of multi-source heterogeneous data at the edge of an industrial internet, which can optimize the acquisition frequency under the constraints of data value of edge nodes and network resource latency, thereby improving the value efficiency of industrial internet data transmission.

[0005] Firstly, this application provides a method for collaborative acquisition of multi-source heterogeneous data at the edge of an industrial internet, including:

[0006] Acquire multi-source data transmission information between the cloud center and various edge nodes in the industrial internet, and monitor the device status information of the cloud center;

[0007] For each edge node in the Industrial Internet, the temporal variation gradient of the information transmission volume of each data source in the edge node is calculated by using the multi-source data transmission information of the edge node. The cross-source data differences in the edge node and the business function weights of each data source are used to fuse all the temporal variation gradients into the data value density of the edge node, thereby obtaining the data value density of each edge node in the Industrial Internet.

[0008] The transmission delay features between the cloud center and each edge node are extracted from the device status information. The transmission resources between the cloud center and each edge node are constrained by the transmission delay features and the fluctuation features of the network bandwidth in the cloud center, so as to obtain the network resource constraints of the cloud center.

[0009] Based on all data value densities and using the network resource constraints as constraints for each edge node in the Industrial Internet, the total data value transmitted to the cloud center is maximized, and the data acquisition frequency of each edge node in the Industrial Internet is optimized in a personalized manner.

[0010] In some embodiments, calculating the temporal variation gradient of the information transmission volume of each data source in the edge node using the multi-source data transmission information of the edge node specifically includes:

[0011] For each data source in the edge node, the information transmission volume of the data source at each sampling point is obtained from the multi-source data transmission information of the edge node.

[0012] By determining the temporal variation gradient of the data source information transmission volume through all information transmission volumes, the temporal variation gradient of the information transmission volume of each data source in the edge node can be obtained.

[0013] In some embodiments, using cross-source data differences in edge nodes and the business function weights of each data source to fuse all temporal variation gradients into the data value density of the edge nodes specifically includes:

[0014] Determine the cross-source data differences in edge nodes and obtain the business function weights of each data source;

[0015] By merging the temporal variation gradients of each business function weight into an initial value density for the edge nodes;

[0016] The initial value of the value density is adjusted based on the cross-source data differences to obtain the data value density of the edge nodes.

[0017] In some embodiments, extracting transmission delay features between the cloud center and each edge node from the device status information specifically includes:

[0018] For each edge node, multiple echo request data packets between the cloud center and the edge node are obtained from the device status information;

[0019] Extract the round-trip time value of each echo request data packet;

[0020] The transmission delay characteristics between the cloud center and edge nodes are determined by all round-trip delay values, thereby obtaining the transmission delay characteristics between the cloud center and each edge node.

[0021] In some embodiments, delay constraints are applied to the transmission resources between the cloud center and each edge node based on various transmission delay characteristics and the fluctuation characteristics of network bandwidth in the cloud center, resulting in network resource constraints at the cloud center. Specifically, these constraints include:

[0022] Extract the fluctuation characteristics of network bandwidth in the cloud center;

[0023] The delay constraint of transmission resources between the cloud center and each edge node is determined based on the fluctuation characteristics and various transmission delay characteristics.

[0024] The network resource constraints at the cloud center are determined by all latency constraints.

[0025] In some embodiments, based on all data value densities and using the network resource constraints as constraints for each edge node in the Industrial Internet, the data acquisition frequency of each edge node in the Industrial Internet is personalizedly optimized to maximize the total data value transmitted to the cloud center. This specifically includes:

[0026] Initialize a node constraint model based on linear programming;

[0027] Use all data value density as the value decision parameter of the node constraint model;

[0028] Maximizing the total value of data transmitted to the cloud center is taken as the constraint objective of the node constraint model;

[0029] The network resource constraints are used as resource constraints for each edge node in the node constraint model.

[0030] The node constraint model described above is used to apply personalized constraints to the data acquisition frequency of each edge node in the Industrial Internet.

[0031] In some embodiments, the edge node is an embedded gateway based on the ARM Cortex-A7 architecture.

[0032] Secondly, this application provides a multi-source heterogeneous data collaborative acquisition device for the edge of an industrial internet, comprising:

[0033] The acquisition module is used to acquire multi-source data transmission information between the cloud center and various edge nodes in the industrial internet, and to monitor the device status information of the cloud center.

[0034] The processing module is used to calculate the temporal variation gradient of the information transmission volume of each data source in the edge node through the multi-source data transmission information of the edge node. It uses the cross-source data differences in the edge node and the business function weights of each data source to fuse all the temporal variation gradients into the data value density of the edge node, thereby obtaining the data value density of each edge node in the industrial internet.

[0035] The processing module is also used to extract the transmission delay features between the cloud center and each edge node from the device status information, and to impose delay constraints on the transmission resources between the cloud center and each edge node by using the transmission delay features and the fluctuation features of the network bandwidth in the cloud center, so as to obtain the network resource constraints of the cloud center.

[0036] The execution module is used to optimize the data acquisition frequency of each edge node in the industrial internet in a personalized manner, based on all data value densities and using the network resource constraints as constraints for each edge node in the industrial internet, to maximize the total data value transmitted to the cloud center.

[0037] Thirdly, this application provides a computer device, which includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-described method for collaborative acquisition of multi-source heterogeneous data at the edge of the industrial Internet.

[0038] Fourthly, this application provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the aforementioned method for collaborative acquisition of multi-source heterogeneous data at the edge of the industrial internet.

[0039] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0040] This application provides a method and apparatus for collaborative acquisition of multi-source heterogeneous data at the edge of an industrial internet. The method acquires multi-source data transmission information between the cloud center and various edge nodes in the industrial internet, and monitors the device status information of the cloud center. For each edge node in the industrial internet, the method calculates the temporal variation gradient of the data transmission volume of each data source in the edge node using the multi-source data transmission information. It then uses the cross-source data differences in the edge nodes and the business function weights of each data source to fuse all the temporal variation gradients into the data value density of the edge node, thereby obtaining the data value density of each edge node in the industrial internet. The method extracts transmission delay features between the cloud center and each edge node from the device status information. It then uses these transmission delay features and the fluctuation characteristics of the network bandwidth in the cloud center to impose delay constraints on the transmission resources between the cloud center and each edge node, obtaining the network resource constraints of the cloud center. Based on all the data value densities and using the network resource constraints as constraints for each edge node in the industrial internet, the method maximizes the total data value transmitted to the cloud center and performs personalized optimization of the data acquisition frequency of each edge node in the industrial internet.

[0041] Therefore, this application, based on all data value densities and using the network resource constraints as constraints for each edge node in the Industrial Internet, maximizes the total data value transmitted to the cloud center and personalizes the data acquisition frequency of each edge node in the Industrial Internet. Firstly, determining the data value density yields a data quantification standard oriented towards business value. Determining the data value density, which dynamically reflects the importance and timeliness of data services, allows Industrial Internet devices to move beyond the traditional extensive management approach based solely on data volume. It enables precise identification of data blocks with higher value to upper-layer applications at the current moment. For example, a sensor data stream with a sudden and sharp increase in transmission volume has a large gradient; if further weighted with higher business functions, it will obtain a high value density score. This provides a clear value orientation for subsequent optimization decisions, enabling Industrial Internet devices to distinguish between high-value data and ordinary data, laying the foundation for improving value efficiency. Having laid the foundation, determining network resource constraints allows for the precise boundary of cloud service capabilities. This anchors value transmission demands to the fluctuating characteristics of feasible physical reality. By quantifying the maximum data reception capacity of the cloud from each edge node within a specific time period through constraint models, the transmission boundary of data value can be clearly defined, improving the feasibility of optimization schemes. For example, industrial internet devices can identify a surge in network latency or a sudden drop in bandwidth to a certain edge node, thus explicitly informing the optimization algorithm that requesting too much data from that edge node is currently infeasible. This transforms the abstract network state into concrete mathematical constraints that can be directly processed by the optimization algorithm, ensuring that any optimization decisions regarding the acquisition frequency are made within the limits allowed by actual network physical conditions, guaranteeing the feasibility of the scheme. In summary, based on the above scheme, acquisition frequency optimization under the synergistic constraints of edge node data value and network resource latency can be achieved, thereby improving the value efficiency of industrial internet data transmission. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is an exemplary flowchart of a collaborative acquisition method for multi-source heterogeneous data at the industrial internet edge, as shown in some embodiments of this application.

[0044] Figure 2 This is a flowchart illustrating the process of determining network resource constraints according to some embodiments of this application;

[0045] Figure 3 This is a schematic diagram of the structure for collaborative acquisition of multi-source heterogeneous data at the edge of the industrial internet, as shown in some embodiments of this application.

[0046] Figure 4 This is a schematic diagram of the structure of a computer device for implementing a multi-source heterogeneous data collaborative acquisition method at the edge of the Industrial Internet, according to some embodiments of this application. Detailed Implementation

[0047] To better understand the technical solution of this application, the technical solution of this application will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0048] refer to Figure 1 The figure is an exemplary flowchart of a method for collaborative acquisition of multi-source heterogeneous data at the edge of an industrial internet, according to some embodiments of this application. This method mainly includes the following steps:

[0049] In step 101, multi-source data transmission information between the cloud center and various edge nodes in the industrial internet is obtained, and the device status information of the cloud center is monitored.

[0050] It should be noted that in this application, the edge node is an embedded gateway based on the ARM Cortex-A7 architecture; multi-source data transmission information refers to the set of transmission parameters generated during the transmission of data from various edge devices to the cloud center in the industrial internet; and device status information refers to the real-time operating parameters of the cloud center server itself and its network interface.

[0051] In specific implementation, firstly, acquiring multi-source data transmission information between the cloud center and various edge nodes in the Industrial Internet can be achieved in the following way: It is implemented by deploying a dedicated data acquisition agent program at the cloud center. This agent program can listen to and parse network data packets from all edge nodes at each sampling point (default once per second). By statistically analyzing the source address, destination address, size, and timestamp of each data packet, it automatically calculates the uplink data traffic, data transmission duration, and data transmission rate of each edge node per unit time. The set of all uplink data traffic, data transmission duration, and data transmission rate serves as the multi-source data transmission information between the cloud center and various edge nodes in the Industrial Internet. Then, this is accomplished by calling the operating system interface and hardware management interface of the cloud center server. The cloud center periodically queries the server's CPU utilization, memory usage, disk read / write speed, and network interface card bandwidth utilization and connection status. The set of these parameters serves as the device status information of the cloud center.

[0052] In step 102, for each edge node in the industrial internet, the temporal variation gradient of the information transmission volume of each data source in the edge node is calculated by using the multi-source data transmission information of the edge node. The cross-source data differences in the edge node and the business function weights of each data source are used to fuse all the temporal variation gradients into the data value density of the edge node, thereby obtaining the data value density of each edge node in the industrial internet.

[0053] In some embodiments, calculating the temporal variation gradient of the information transmission volume of each data source in the edge node using the multi-source data transmission information of the edge node can be achieved by the following steps:

[0054] For each data source in the edge node, the information transmission volume of the data source at each sampling point is obtained from the multi-source data transmission information of the edge node.

[0055] By determining the temporal variation gradient of the data source information transmission volume through all information transmission volumes, the temporal variation gradient of the information transmission volume of each data source in the edge node can be obtained.

[0056] It should be noted that, in this application, the temporal variation gradient represents the rate at which the information transmission volume of a data source changes over time. Specifically, in the implementation, firstly, for each data source in the edge node, obtaining the information transmission volume of the data source at each sampling point from the multi-source data transmission information of the edge node can be achieved in the following way: For each data source in the edge node, obtain all data packets in the multi-source data transmission information of the edge node, thereby parsing the size of each data packet and the data source, filtering out all data packets of the data source from all data packets, and calculating the total size of all data packets of the data source at each sampling point as the information transmission volume of the corresponding sampling point. This information transmission volume is the size of the data transmitted from one data source to the edge node at a single sampling time point. Then, the temporal variation gradient of the data source information transmission volume is determined through all information transmission volumes. The temporal variation gradient of the information transmission volume of each data source in the edge node can then be obtained in the following way: Calculate the average value of the difference in information transmission volume between adjacent sampling points as the temporal variation gradient of the data source information transmission volume. This method yields the temporal variation gradient of the information transmission volume of each data source in the edge node.

[0057] In some embodiments, fusing all temporal variation gradients into the data value density of the edge node using cross-source data differences in the edge node and the business function weights of each data source can be achieved through the following steps:

[0058] Determine the cross-source data differences in edge nodes and obtain the business function weights of each data source;

[0059] By merging the temporal variation gradients of each business function weight into an initial value density for the edge nodes;

[0060] The initial value of the value density is adjusted based on the cross-source data differences to obtain the data value density of the edge nodes.

[0061] It should be noted that, in this application, data value density is a quantitative indicator used to characterize the overall data value level of the entire edge node; cross-source data difference is a quantitative indicator used to measure the inconsistency of data behavior among multiple different data sources connected within the same edge node; business function weight refers to a numerical coefficient pre-set for each data source to represent its importance; and the initial value of value density is a quantitative value reflecting the data value of all data sources within the edge node.

[0062] In specific implementation, firstly, determining the cross-source data differences in the edge nodes and obtaining the business function weights of each data source can be achieved in the following way: collecting all time-series change gradients of all data sources under the edge node within a specified time period (default is 24h), and calculating the standard deviation of all time-series change gradients as the cross-source data difference; reading the business function weights corresponding to each data source from the preset configuration database; then, merging all time-series change gradients into the initial value density of the edge node through each business function weight can be achieved in the following way: using each business function weight as a weight, calculating the weighted sum of all time-series change gradients as the initial value density of the edge node; finally, differentiating the initial value density based on the cross-source data differences to obtain the data value density of the edge node can be achieved in the following way: the product of the cross-source data differences and the initial value density is taken as the data value density of the edge node.

[0063] In step 103, the transmission delay features between the cloud center and each edge node are extracted from the device status information. The transmission resources between the cloud center and each edge node are then constrained by the transmission delay features and the fluctuation features of the network bandwidth in the cloud center, thereby obtaining the network resource constraints of the cloud center.

[0064] In some embodiments, extracting the transmission delay characteristics between the cloud center and each edge node from the device status information can be achieved using the following steps:

[0065] For each edge node, multiple echo request data packets between the cloud center and the edge node are obtained from the device status information;

[0066] Extract the round-trip time value of each echo request data packet;

[0067] The transmission delay characteristics between the cloud center and edge nodes are determined by all round-trip delay values, thereby obtaining the transmission delay characteristics between the cloud center and each edge node.

[0068] It should be noted that, in this application, the transmission delay feature is a representative value that can characterize the overall network delay status and fluctuation characteristics; the echo request data packet refers to a special network data packet actively sent by the cloud center to the target edge node to detect network connectivity and performance; the round-trip time value refers to the total time length from when an echo request data packet is sent by the cloud center to when the data packet is returned by the target edge node and finally received by the cloud center.

[0069] In specific implementation, firstly, for each edge node, obtaining multiple echo request data packets between the cloud center and the edge node from the device status information can be achieved in the following way: the cloud center has a built-in network probe scheduler. This network probe scheduler sends small data packets to the IP address of each edge node to be monitored at preset time intervals. These data packets are specifically used for network probes, and their protocol type is set to the echo request type in ICMP (Internet Control Message Protocol). Their core function is to be responded to and returned by the target node. Then, extracting the round-trip time value of each echo request data packet can be achieved in the following way: the cloud center records the precise sending time while sending each echo request data packet. The timestamp is recorded immediately upon receiving the corresponding response data packet. The difference between the received timestamp and the sent timestamp is calculated, and this difference is the round-trip time (RTT) value for that probe, in milliseconds. All probe packets that successfully receive a response will generate a corresponding RTT value, thus obtaining the RTT value for each echo request data packet. Finally, the transmission delay characteristics between the cloud center and edge nodes are determined by using all the RTT values. The transmission delay characteristics between the cloud center and each edge node can be obtained by the following method: the 95th percentile of all RTT values ​​is used as the transmission delay characteristics between the cloud center and edge nodes.

[0070] In some embodiments, delay constraints are applied to the transmission resources between the cloud center and each edge node based on various transmission delay characteristics and the fluctuation characteristics of network bandwidth in the cloud center, thereby obtaining the network resource constraints of the cloud center. (Refer to...) Figure 2 The diagram is a flowchart illustrating the determination of network resource constraints in some embodiments of this application. In this embodiment, the determination of network resource constraints can be achieved through the following steps:

[0071] In step 1031, the fluctuation characteristics of network bandwidth in the cloud center are extracted;

[0072] In step 1032, the delay constraint of transmission resources between the cloud center and each edge node is determined based on the fluctuation characteristics and each transmission delay characteristics.

[0073] In step 1033, network resource constraints at the cloud center are determined using all delay constraints.

[0074] It should be noted that in this application, network resource constraints are a set of global restrictions composed of the latency constraints of all links; fluctuation characteristics are a statistical indicator used to quantify the stability of uplink network bandwidth at the cloud center; and latency constraints are the upper limit of resource usage of network links between the cloud center and each edge node.

[0075] In specific implementation, firstly, extracting the network bandwidth fluctuation characteristics in the cloud center can be achieved as follows: the cloud center continuously monitors the real-time bandwidth data of its uplink network interface, records the bandwidth sampling value of the cloud center at fixed time intervals (default 1 second), and uses the standard deviation of all bandwidth sampling values ​​within a specified time period (default 24 hours) as the network bandwidth fluctuation characteristic in the cloud center. Then, determining the delay constraint of transmission resources between the cloud center and each edge node based on the fluctuation characteristics and various transmission delay characteristics can be achieved as follows: for each edge node, the transmission delay characteristics of the edge node and the network bandwidth... Multiplying the wide fluctuation characteristics by an empirically set baseline constant yields the latency constraint for that edge node. Through this calculation process, for high-latency links or when the entire network fluctuates significantly, resource usage must be more strictly limited, resulting in a smaller latency constraint value, indicating a tighter constraint. This method yields the latency constraint for resource transmission between the cloud center and each edge node. Finally, determining the network resource constraints of the cloud center using all latency constraints can be achieved by using the set of all latency constraints as the network resource constraints for the cloud center.

[0076] In step 104, based on all data value densities and using the network resource constraints as constraints for each edge node in the industrial internet, the total data value transmitted to the cloud center is maximized, and the data acquisition frequency of each edge node in the industrial internet is optimized in a personalized manner.

[0077] In some embodiments, based on all data value densities and using the network resource constraints as constraints for each edge node in the Industrial Internet, the following steps can be used to personalize the data acquisition frequency of each edge node in the Industrial Internet to maximize the total data value transmitted to the cloud center:

[0078] Initialize a node constraint model based on linear programming;

[0079] Use all data value density as the value decision parameter of the node constraint model;

[0080] Maximizing the total value of data transmitted to the cloud center is taken as the constraint objective of the node constraint model;

[0081] The network resource constraints are used as resource constraints for each edge node in the node constraint model.

[0082] The node constraint model described above is used to apply personalized constraints to the data acquisition frequency of each edge node in the Industrial Internet.

[0083] It should be noted that in this application, the node constraint model is a mathematical optimization framework based on linear programming theory. The node constraint model seeks the optimal resource allocation scheme under given system resource constraints. It defines the data acquisition frequency of each edge node as a decision variable and uses the data value density, which characterizes the data value level of a node, as the coefficient of the decision variable in the objective function. This quantifies the contribution of different frequency configurations to the total value. The constraint objective is set to maximize the weighted sum of the data value densities of all nodes, i.e., to maximize the overall data value output of the system. Simultaneously, the node constraint model transforms network resource constraints into a system of linear inequalities, precisely representing that the bandwidth resource consumption of each node's data flow must not exceed the upper limit specified by its delay constraint, and the total resource consumption of all nodes must not exceed the total bandwidth capacity of the cloud center. By solving this node constraint model using optimization algorithms such as the simplex method, a set of optimal acquisition frequency configurations that maximize the total data value of the system under all network constraints can be obtained, thereby achieving personalized and precise control based on node value differences and resource conditions.

[0084] Furthermore, in another aspect of this application, in some embodiments, this application provides a multi-source heterogeneous data collaborative acquisition device for the edge of an industrial internet, referring to... Figure 3 The figure is a schematic diagram of the structure of collaborative acquisition of multi-source heterogeneous data at the edge of the industrial internet according to some embodiments of this application. The collaborative acquisition of multi-source heterogeneous data at the edge of the industrial internet includes: an acquisition module 201, a processing module 202, and an execution module 203, which are described below:

[0085] The acquisition module 201 in this application is mainly used to acquire multi-source data transmission information between the cloud center and various edge nodes in the industrial Internet, and to monitor the device status information of the cloud center.

[0086] Processing module 202, in this application, is used to calculate the temporal variation gradient of the information transmission volume of each data source in the edge node through the multi-source data transmission information of the edge node, and use the cross-source data differences in the edge node and the business function weight of each data source to fuse all the temporal variation gradients into the data value density of the edge node, thereby obtaining the data value density of each edge node in the industrial internet.

[0087] It should be noted that the processing module 202 is also used to extract the transmission delay features between the cloud center and each edge node from the device status information, and to impose delay constraints on the transmission resources between the cloud center and each edge node by using the various transmission delay features and the fluctuation features of the network bandwidth in the cloud center, so as to obtain the network resource constraints of the cloud center.

[0088] The execution module 203 in this application is mainly used to optimize the data acquisition frequency of each edge node in the industrial internet by maximizing the total data value transmitted to the cloud center based on all data value densities and using the network resource constraints as constraints for each edge node in the industrial internet.

[0089] The foregoing has detailed examples of the multi-source heterogeneous data collaborative acquisition method and apparatus for the industrial internet edge provided in the embodiments of this application. It is understood that, in order to achieve the above functions, the corresponding apparatus includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0090] In some embodiments, this application also provides a computer device, the computer device including a memory and a processor, the memory for storing a computer program, and the processor for calling and running the computer program from the memory, so that the computer device executes the above-described method for collaborative acquisition of multi-source heterogeneous data at the edge of the industrial internet.

[0091] In some embodiments, reference Figure 4 The dashed lines in the figure indicate that the unit or module is optional. This figure is a structural schematic diagram of a computer device for implementing a multi-source heterogeneous data collaborative acquisition method for the industrial internet edge, according to an embodiment of this application. The multi-source heterogeneous data collaborative acquisition method for the industrial internet edge described in the above embodiments can... Figure 4 The computer device shown is used to implement this, and the computer device includes at least one processor 301, a memory 302 and at least one communication unit 305. The computer device may be a terminal device, a server or a chip.

[0092] Processor 301 can be a general-purpose processor or a special-purpose processor. For example, processor 301 can be a central processing unit (CPU), which can be used to control computer devices, execute software programs, and process data from software programs. The computer device may also include a communication unit 305 for inputting (receiving) and outputting (transmitting) signals.

[0093] For example, the computer device may be a chip, and the communication unit 305 may be the input and / or output circuit of the chip, or the communication unit 305 may be the communication interface of the chip, which may be a component of a terminal device, network device or other device.

[0094] For example, the computer device may be a terminal device or a server, and the communication unit 305 may be a transceiver of the terminal device or the server, or the communication unit 305 may be a transceiver circuit of the terminal device or the server.

[0095] The computer device may include one or more memories 302 storing a program 304. The program 304 can be executed by a processor 301 to generate instructions 303, causing the processor 301 to execute the method described in the above method embodiments according to the instructions 303. Optionally, the memory 302 may also store data (such as a target audit model). Optionally, the processor 301 may also read data stored in the memory 302, which may be stored at the same storage address as the program 304, or it may be stored at a different storage address than the program 304.

[0096] The processor 301 and memory 302 can be configured separately or integrated together, for example, integrated on the system on chip (SOC) of the terminal device.

[0097] It should be understood that each step of the above method embodiment can be completed by hardware logic circuits or software instructions in the processor 301. The processor 301 can be a CPU, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, such as discrete gate, transistor logic devices, or discrete hardware components.

[0098] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] For example, in some embodiments, this application also provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the above-described method for collaborative acquisition of multi-source heterogeneous data at the edge of the industrial internet.

[0100] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0101] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for collaborative acquisition of multi-source heterogeneous data at the edge of an industrial internet, characterized in that, Includes the following steps: Acquire multi-source data transmission information between the cloud center and various edge nodes in the industrial internet, and monitor the device status information of the cloud center; For each edge node in the Industrial Internet, the temporal variation gradient of the information transmission volume of each data source in the edge node is calculated by using the multi-source data transmission information of the edge node. The cross-source data differences in the edge node and the business function weights of each data source are used to fuse all the temporal variation gradients into the data value density of the edge node, thereby obtaining the data value density of each edge node in the Industrial Internet. The transmission delay features between the cloud center and each edge node are extracted from the device status information. The transmission resources between the cloud center and each edge node are constrained by the transmission delay features and the fluctuation features of the network bandwidth in the cloud center, so as to obtain the network resource constraints of the cloud center. Based on all data value densities and using the network resource constraints as constraints for each edge node in the Industrial Internet, the total data value transmitted to the cloud center is maximized, and the data acquisition frequency of each edge node in the Industrial Internet is optimized in a personalized manner.

2. The method as described in claim 1, characterized in that, Calculating the temporal variation gradient of information transmission volume from various data sources in edge nodes through multi-source data transmission information of edge nodes specifically includes: For each data source in the edge node, the information transmission volume of the data source at each sampling point is obtained from the multi-source data transmission information of the edge node. By determining the temporal variation gradient of the data source information transmission volume through all information transmission volumes, the temporal variation gradient of the information transmission volume of each data source in the edge node can be obtained.

3. The method as described in claim 1, characterized in that, Using cross-source data differences in edge nodes and the business function weights of each data source, all time-series variation gradients are fused into the data value density of the edge nodes, specifically including: Determine the cross-source data differences in edge nodes and obtain the business function weights of each data source; By merging the temporal variation gradients of each business function weight into an initial value density for the edge nodes; The initial value of the value density is adjusted based on the cross-source data differences to obtain the data value density of the edge nodes.

4. The method as described in claim 1, characterized in that, Extracting transmission delay features between the cloud center and each edge node from the device status information specifically includes: For each edge node, multiple echo request data packets between the cloud center and the edge node are obtained from the device status information; Extract the round-trip time value of each echo request data packet; The transmission delay characteristics between the cloud center and edge nodes are determined by all round-trip delay values, thereby obtaining the transmission delay characteristics between the cloud center and each edge node.

5. The method as described in claim 1, characterized in that, By applying various transmission delay characteristics and the fluctuation characteristics of network bandwidth in the cloud center, delay constraints are imposed on the transmission resources between the cloud center and each edge node. The specific network resource constraints at the cloud center include: Extract the fluctuation characteristics of network bandwidth in the cloud center; The delay constraint of transmission resources between the cloud center and each edge node is determined based on the fluctuation characteristics and various transmission delay characteristics. The network resource constraints at the cloud center are determined by all latency constraints.

6. The method as described in claim 1, characterized in that, Based on the total data value density and using the network resource constraints as constraints for each edge node in the Industrial Internet, the data acquisition frequency of each edge node in the Industrial Internet is optimized in a personalized manner to maximize the total data value transmitted to the cloud center. This includes: Initialize a node constraint model based on linear programming; Use all data value density as the value decision parameter of the node constraint model; Maximizing the total value of data transmitted to the cloud center is taken as the constraint objective of the node constraint model; The network resource constraints are used as resource constraints for each edge node in the node constraint model. The node constraint model described above is used to apply personalized constraints to the data acquisition frequency of each edge node in the Industrial Internet.

7. The method as described in claim 1, characterized in that, The edge node is an embedded gateway based on the ARM Cortex-A7 architecture.

8. A multi-source heterogeneous data collaborative acquisition device for the edge of an industrial internet, characterized in that, include: The acquisition module is used to acquire multi-source data transmission information between the cloud center and various edge nodes in the industrial internet, and to monitor the device status information of the cloud center. The processing module is used to calculate the temporal variation gradient of the information transmission volume of each data source in the edge node through the multi-source data transmission information of the edge node. It uses the cross-source data differences in the edge node and the business function weights of each data source to fuse all the temporal variation gradients into the data value density of the edge node, thereby obtaining the data value density of each edge node in the industrial internet. The processing module is also used to extract the transmission delay features between the cloud center and each edge node from the device status information, and to impose delay constraints on the transmission resources between the cloud center and each edge node by using the transmission delay features and the fluctuation features of the network bandwidth in the cloud center, so as to obtain the network resource constraints of the cloud center. The execution module is used to optimize the data acquisition frequency of each edge node in the industrial internet in a personalized manner, based on all data value densities and the network resource constraints as constraints for each edge node in the industrial internet, to maximize the total data value transmitted to the cloud center.

9. A computer device, characterized in that, The computer device includes a memory and a processor. The memory is used to store computer programs, and the processor is used to call and run the computer programs from the memory, so that the computer device executes the multi-source heterogeneous data collaborative acquisition method for the industrial internet edge as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions or code that, when executed on a computer, cause the computer to implement the multi-source heterogeneous data collaborative acquisition method for the industrial internet edge as described in any one of claims 1 to 7.

Images