An intelligent control system for service data acquisition and processing based on end-cloud cooperation

Abstract

The application discloses a kind of service data acquisition processing intelligent control systems based on end cloud cooperation, belong to service data processing technical field, determine each analysis function of user to service data analysis, each analysis function is divided into cloud analysis function and edge analysis function;According to each edge analysis function, the corresponding modular analysis unit is configured for server;Real-time data acquisition is carried out, acquisition data is obtained, each cloud analysis function and edge analysis function are acquired, and the acquisition data corresponding to the cloud analysis function is sent to cloud end;According to the modular analysis unit configured, the received acquisition data is analyzed, and the corresponding data analysis result or control analysis result is obtained, and the data analysis result is sent to cloud end;Cloud end is analyzed according to the cloud analysis function to the received acquisition data and data analysis result, and the corresponding control analysis result is obtained;According to control analysis result, control processing is carried out.

Description

Technical Field

[0001] This invention belongs to the field of service data processing technology, specifically an intelligent control system for service data acquisition and processing based on edge-cloud collaboration. Background Technology

[0002] With the rapid development of information technology, the amount of data generated across various industries is exploding. Traditional data processing methods, whether centralized cloud processing or local processing relying entirely on terminal devices, are struggling to meet the demands of increasingly complex application scenarios. While centralized cloud processing boasts powerful computing and storage capabilities, data transmission to the cloud requires traversing the network, introducing latency. For scenarios with extremely high real-time requirements, such as autonomous driving and industrial real-time control, timely response is difficult to guarantee. Moreover, transmitting large amounts of data to the cloud consumes significant network bandwidth resources, increasing the risk of network congestion. Furthermore, uploading all data to the cloud also poses risks to data security and privacy.

[0003] While relying entirely on local processing on terminal devices can reduce data transmission latency, these devices have limited computing and storage resources, making it difficult to handle large-scale data and complex computational tasks. For example, in smart home scenarios, smart cameras collect massive amounts of image data, which terminal devices cannot efficiently recognize and analyze. Furthermore, the heterogeneity among different terminal devices, with significant differences in performance and capabilities, makes unified collaborative processing difficult.

[0004] In order to solve the above problems, this invention provides an intelligent control system for service data acquisition and processing based on edge-cloud collaboration. Summary of the Invention

[0005] To address the problems of the above solutions, this invention provides an intelligent control system for service data acquisition and processing based on edge-cloud collaboration.

[0006] The objective of this invention can be achieved through the following technical solutions: A smart control system for service data acquisition and processing based on edge-cloud collaboration, comprising cloud and server; Furthermore, communication connections between the cloud and the server.

[0007] The cloud includes a service analysis module and a cloud analysis module; The service analysis module is used to perform real-time service analysis, determine the various analysis functions that users use to analyze service data, and divide the various analysis functions into cloud analysis functions and edge analysis functions; based on the various edge analysis functions, determine the various modular analysis units included in the modular modules in the server, and configure the corresponding modular analysis units for the modular modules.

[0008] Furthermore, real-time service analysis is conducted, including: The platform establishes a function reserve library, which stores various reserve functions, and each reserve is associated with corresponding demand information; The system acquires user service material data, matches and analyzes the service material data with various reserve functions in the function reserve library, obtains each successfully matched reserve function, displays each reserve function to the user, allows the user to determine which reserve function to apply, and marks the reserve function selected by the user as the analysis function.

[0009] Furthermore, the service material data is matched and analyzed with various reserve functions in the function reserve library, including: Establish a matching analysis model; The service material data and the corresponding reserve functions in the function reserve library are integrated into the input data and input into the matching analysis model for analysis to obtain the matching value of the corresponding reserve function. The matching value is 1 or 0. When the match value is 1, the match is evaluated as successful. When the match value is 0, the match evaluation fails.

[0010] Furthermore, the expression for the matching analysis model is: ; In the formula: (x i , SU) is the input data, x i This represents the corresponding reserve function in the function reserve library, where i is the subscript (i = 1, 2, ..., n), n is the number of reserve functions in the function reserve library, and SU represents service material data; x i →SU indicates that the service material data has the aforementioned reserve function application requirement; the output data is the matching value PL(x) i ,SU).

[0011] Furthermore, the various analytical functions are divided into cloud-based analytical functions and edge-based analytical functions, including: Simulate each analysis function to obtain cloud analysis effect data and server analysis effect data for each analysis function applied by the cloud and server respectively. The service optimization value of the analytical function is evaluated based on cloud-based and server-side analytical performance data. Analysis functions with service optimization values ​​greater than the threshold X1 are marked as candidate service functions; candidate service functions are sorted in descending order of service optimization values ​​to obtain a priority sequence; each candidate service function is determined as an edge analysis function based on the priority sequence; and the remaining non-edge analysis functions are marked as cloud analysis functions.

[0012] Furthermore, the service optimization value of the analysis function is evaluated based on cloud-based analysis performance data and server-side analysis performance data, including: Pre-set the performance evaluation indicators and weighting coefficients for each analysis function; Based on various performance evaluation indicators, feature extraction is performed on the cloud-based analysis performance data and the server-side analysis performance data to obtain individual service features and individual cloud features corresponding to each performance evaluation indicator. The individual service features corresponding to the performance evaluation indicators are compared with individual cloud features to obtain the individual optimization values ​​of the analysis function on the performance evaluation indicators. The performance evaluation index is labeled j, where j = 1, 2, ..., m, and m is the number of performance evaluation indexes. The single optimization value is labeled Y. j The weighting coefficient of the aforementioned performance evaluation index is denoted as λ. j ; The service optimization value of the analysis function is calculated according to the preset service optimization formula.

[0013] Furthermore, the service optimization formula is: ; In the formula: FY is the service optimization value.

[0014] The cloud analysis module is used to analyze the received collected data and data analysis results according to the cloud analysis function, obtain the corresponding control analysis results, and send the control analysis results to the control module. The server includes a data acquisition module, a modular module, and a control module; The acquisition module is used to acquire data in real time, obtain the acquired data, acquire various cloud analysis functions and edge analysis functions, and transmit the acquired data to the modular module and the cloud analysis module in the cloud according to the cloud analysis functions and edge analysis functions. The modular module is used to analyze the received collected data according to the configured modular analysis units, obtain the corresponding data analysis results or control analysis results, send the control analysis results to the control module, and send the data analysis results to the cloud analysis module in the cloud. The control module is used to perform control processing based on the received control analysis results.

[0015] Compared with the prior art, the beneficial effects of the present invention are: The intelligent control system for service data acquisition and processing based on edge-cloud collaboration proposed in this invention effectively integrates the advantages of cloud and terminal devices, avoiding the inherent defects of traditional data processing methods. On the one hand, through the edge-cloud collaboration mechanism, the system can perform preliminary processing on terminal devices close to the data source, significantly reducing the latency of data transmission to the cloud, while reducing the network bandwidth occupation caused by large-scale data transmission and reducing the risk of network congestion. On the other hand, the cloud, with its powerful computing and storage capabilities, can perform in-depth analysis and mining of the pre-processed data from the terminal devices, breaking through the resource limitations of the terminal devices and efficiently processing large-scale data and complex tasks. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a block diagram illustrating the principle of the present invention. Detailed Implementation

[0018] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0019] like Figure 1 As shown, a service data acquisition and processing intelligent control system based on edge-cloud collaboration includes a cloud and a server. The cloud and the server are generally connected via a communication link.

[0020] The cloud includes a service analysis module and a cloud analysis module; The service analysis module is used to perform real-time service analysis, identify various analysis functions for users to analyze service data, such as fault diagnosis, risk assessment, business trend prediction, and service quality assessment; divide each analysis function into cloud analysis function and edge analysis function; determine the modular analysis units included in the modular modules in the server based on each edge analysis function, configure the corresponding modular analysis units for the modular modules, and use the modular analysis units to implement the corresponding edge analysis functions.

[0021] In one embodiment, real-time service analysis can be performed by the user determining their various analysis needs and then determining the various analysis functions based on those needs; alternatively, the platform can assist the user in determining the various analysis needs, for example, by having platform staff assist the user in determining the various analysis functions.

[0022] In one embodiment, real-time service analysis includes: The platform establishes a function reserve library, which stores various analytical functions that may be available in various industries within the platform's service or business scope, and marks the analytical requirements corresponding to each analytical function. To distinguish them, the analytical functions stored in the function reserve library are marked as reserve functions, and each reserve is associated with corresponding requirement information. The requirement information is used to indicate the analytical requirements that the reserve function is adapted to, as well as other data related to the analytical requirements, such as the service data characteristics and user characteristics of the analytical requirements, which are set by the platform.

[0023] Obtaining user service material data can be either the user's historical service data or other relevant data that can indicate the suitability of existing user service data for analysis needs, such as supplementing the user's description of analysis needs. The service material data is matched and analyzed with each reserve function in the function reserve library to obtain each successfully matched reserve function. Each of the reserve functions is then displayed to the user, who determines which reserve function to apply. The reserve function selected by the user is marked as the analysis function.

[0024] It can simultaneously display the demand information corresponding to each reserve function, and can also supplement it with other information that is easy for users to understand.

[0025] In one embodiment, service material data is matched and analyzed with various reserve functions in the function reserve library. The matching is performed based on existing methods, such as meeting the corresponding analysis requirements, identifying the analysis requirements corresponding to the service material data, and matching them with the requirement information corresponding to the reserve functions to obtain the matching results.

[0026] In one embodiment, matching and analyzing service material data with various reserve functions in the function reserve library includes: Establish a matching analysis model. The expression for the matching analysis model is: ; In the formula: (x i , SU) is the input data, x i This represents the corresponding reserve function in the function reserve library, where i is the subscript (i = 1, 2, ..., n), n is the number of reserve functions in the function reserve library, and SU represents service material data; x i→SU indicates that the service material data has the application requirement of this reserve function; the output data is the matching value PL(x) i ,SU), with a matching value of 1 or 0; the platform will train the corresponding training set marked by the function reserve library; The service material data and the corresponding reserve functions in the function reserve library are integrated into the input data and input into the matching analysis model for analysis to obtain the matching value of the corresponding reserve function. When the match value is 1, the match is evaluated as successful. When the match value is 0, the match evaluation fails.

[0027] In one embodiment, the various analytical functions are divided into cloud-based analytical functions and edge-based analytical functions. Users can categorize these functions and select which analytical functions are applied on the server side; alternatively, they can be configured in other ways.

[0028] In one embodiment, the various analytics functions are divided into cloud analytics functions and edge analytics functions, including: Each analytical function is simulated to obtain cloud-based and server-side analytical performance data for each function, applied separately by the cloud and server. This involves loading and running the analytical function on both the cloud and server sides to obtain corresponding performance data, such as complete performance data from data collection, transmission, analysis process, analysis results, feedback execution, and execution results. This can be based on existing methods for simulation and prediction, or by utilizing relevant historical data to determine the corresponding performance data. The service optimization value of the analytical function is evaluated based on the cloud-based and server-side analytical performance data. This means analyzing the degree of optimization in applying the analytical function on the server side, for example, if the performance is higher than 50% on the cloud side, the service optimization value is 50. Analytical functions with service optimization values ​​greater than a threshold X1 are marked as candidate service functions. The candidate service functions are sorted in descending order of service optimization value to obtain a priority sequence. Based on the priority sequence, each candidate service function is determined as an edge analysis function. The remaining non-edge analysis functions are marked as cloud analysis functions, which include the candidate service functions.

[0029] In one embodiment, the user adjusts certain cloud analytics and edge analytics features.

[0030] In one embodiment, each candidate service function is determined as an edge analysis function according to a priority sequence, and selected based on the server's computing power, storage and other resources, and used as an edge analysis function according to priority, until the server's resources can no longer meet the requirements.

[0031] In one embodiment, the service optimization value of the analysis function is evaluated based on cloud analysis performance data and server analysis performance data. The evaluation is then compared with existing performance comparison methods to determine the superiority of the server. If the server is not superior to the cloud, the result is negative.

[0032] In one embodiment, evaluating the service optimization value of the analysis function based on cloud-based analysis performance data and server-side analysis performance data includes: The system presets performance evaluation indicators for each analytical function, such as efficiency and accuracy, and determines the weight coefficients for each indicator based on user needs. Different analytical functions may have different weight coefficients for the same performance evaluation indicator. For example, for analytical functions with high timeliness, the weight coefficient for efficiency will be greater. The weight coefficients can also be preset by the platform based on the analytical needs of each analytical function and then matched later. When users need to make adjustments, the weight coefficients are adjusted based on the matched weight coefficients.

[0033] Based on various performance evaluation indicators, feature extraction is performed on the cloud-based analysis performance data and the server-side analysis performance data to obtain individual service features and individual cloud features corresponding to each performance evaluation indicator. For example, features such as analysis duration and analysis accuracy in the cloud-based analysis performance data and the server-side analysis performance data are extracted or calculated and summarized into individual service features and individual cloud features. These features are then extracted based on the data corresponding to the performance evaluation indicators. The individual service features and individual cloud features corresponding to the respective performance evaluation indicators are compared to determine the proportion of individual service features that are superior to individual cloud features, and this proportion is marked as the individual optimization value. For example, if the individual service feature is 1.2 and the individual cloud feature is 1, then the individual optimization value is [(1.2-1)÷1]×100=20. Let the performance evaluation index be j, j=1, 2, ..., m, where m is the number of performance evaluation indexes, and let the individual optimization value be Y. j The weighting coefficients of the corresponding performance evaluation indicators are denoted as λ. j ; Calculate the service optimization value of the corresponding analysis function according to the preset service optimization formula; The service optimization formula is: ; In the formula: FY is the service optimization value.

[0034] In one embodiment, the modular analysis units included in the modular modules of the server are determined according to each edge analysis function. The platform pre-sets the modular analysis units corresponding to each reserve function according to the function reserve library. For reserve functions that are unlikely to be used as edge analysis functions, modular analysis units may not be pre-set, or they may not be set in the early stage, but set when there is user demand. The set modular analysis units are stored. The corresponding modular analysis units are matched according to the edge analysis function.

[0035] In one embodiment, when a user has a new edge analysis function requirement, the modular module is supplemented with a corresponding modular analysis unit according to the new edge analysis function.

[0036] The cloud analysis module is used to analyze the received collected data and data analysis results according to the cloud analysis function, obtain the corresponding control analysis results, and send the control analysis results to the control module.

[0037] The server includes a data acquisition module, a modular module, and a control module; The acquisition module is used to acquire data in real time, obtain the acquired data, acquire various cloud analysis functions and edge analysis functions, and transmit the acquired data to the modular module and the cloud analysis module in the cloud according to the cloud analysis functions and edge analysis functions.

[0038] This means transmitting data according to the data requirements corresponding to cloud analytics and edge analytics functions, respectively.

[0039] The modular module is used to analyze the received collected data according to the configured modular analysis units, obtain the corresponding data analysis results or control analysis results, send the control analysis results to the control module, and send the data analysis results to the cloud analysis module in the cloud.

[0040] Data analysis results refer to data obtained through preprocessing and process analysis on the server side, and subsequent control analysis results obtained through cloud analysis; the specifics depend on the actual situation of the edge analysis function.

[0041] The control module is used to perform control processing based on the received control analysis results.

[0042] In one embodiment, control processing is performed based on the results of control analysis, using existing methods. For example, processing may be based on user-required methods, and fault warnings or emergency shutdowns may be initiated based on the analysis results, which can be done according to the original processing methods.

[0043] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0044] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A smart control system for service data acquisition and processing based on edge-cloud collaboration, characterized in that, Including cloud and server sides; The cloud includes a service analysis module and a cloud analysis module; The service analysis module is used to perform real-time service analysis, determine the various analysis functions that users use to analyze service data, and divide the various analysis functions into cloud analysis functions and edge analysis functions; based on the various edge analysis functions, determine the various modular analysis units included in the modular modules in the server, and configure the corresponding modular analysis units for the modular modules; The cloud analysis module is used to analyze the received collected data and data analysis results according to the cloud analysis function, obtain the corresponding control analysis results, and send the control analysis results to the control module. The server includes a data acquisition module, a modular module, and a control module; The acquisition module is used to acquire data in real time, obtain the acquired data, acquire various cloud analysis functions and edge analysis functions, and transmit the acquired data to the modular module and the cloud analysis module in the cloud according to the cloud analysis functions and edge analysis functions. The modular module is used to analyze the received collected data according to the configured modular analysis units, obtain the corresponding data analysis results or control analysis results, send the control analysis results to the control module, and send the data analysis results to the cloud analysis module in the cloud. The control module is used to perform control processing based on the received control analysis results.

2. The intelligent control system for service data acquisition and processing based on edge-cloud collaboration according to claim 1, characterized in that, Communication connection between the cloud and the server.

3. The intelligent control system for service data acquisition and processing based on edge-cloud collaboration according to claim 1, characterized in that, Perform real-time service analysis, including: The platform establishes a function reserve library, which stores various reserve functions, and each reserve is associated with corresponding demand information; The system acquires user service material data, matches and analyzes the service material data with various reserve functions in the function reserve library, obtains each successfully matched reserve function, displays each reserve function to the user, allows the user to determine which reserve function to apply, and marks the reserve function selected by the user as the analysis function.

4. The intelligent control system for service data acquisition and processing based on edge-cloud collaboration according to claim 3, characterized in that, The service material data is matched and analyzed with the various reserve functions in the function reserve library, including: Establish a matching analysis model; The service material data and the corresponding reserve functions in the function reserve library are integrated into the input data and input into the matching analysis model for analysis to obtain the matching value of the corresponding reserve function. The matching value is 1 or 0. When the match value is 1, the match is evaluated as successful. When the match value is 0, the match evaluation fails.

5. The intelligent control system for service data acquisition and processing based on edge-cloud collaboration according to claim 4, characterized in that, The expression for the matching analysis model is: ； In the formula: (x i , SU) is the input data, x i This represents the corresponding reserve function in the function reserve library, where i is the subscript (i = 1, 2, ..., n), n is the number of reserve functions in the function reserve library, and SU represents service material data; x i →SU indicates that the service material data has the aforementioned reserve function application requirement; the output data is the matching value PL(x) i ,SU).

6. The intelligent control system for service data acquisition and processing based on edge-cloud collaboration according to claim 1, characterized in that, The various analytics functions are divided into cloud analytics functions and edge analytics functions, including: Simulate each analysis function to obtain cloud analysis effect data and server analysis effect data for each analysis function applied by the cloud and server respectively. The service optimization value of the analytical function is evaluated based on cloud-based and server-side analytical performance data. Analysis functions with service optimization values ​​greater than the threshold X1 are marked as candidate service functions; candidate service functions are sorted in descending order of service optimization values ​​to obtain a priority sequence; each candidate service function is determined as an edge analysis function based on the priority sequence; and the remaining non-edge analysis functions are marked as cloud analysis functions.

7. The intelligent control system for service data acquisition and processing based on edge-cloud collaboration according to claim 6, characterized in that, The service optimization value of the analysis function is evaluated based on cloud-based analysis performance data and server-side analysis performance data, including: Pre-set the performance evaluation indicators and weighting coefficients for each analysis function; Based on various performance evaluation indicators, feature extraction is performed on the cloud-based analysis performance data and the server-side analysis performance data to obtain individual service features and individual cloud features corresponding to each performance evaluation indicator. The individual service features corresponding to the performance evaluation indicators are compared with individual cloud features to obtain the individual optimization values ​​of the analysis function on the performance evaluation indicators. The performance evaluation index is labeled j, where j = 1, 2, ..., m, and m is the number of performance evaluation indexes. The single optimization value is labeled Y. j The weighting coefficient of the aforementioned performance evaluation index is denoted as λ. j ; The service optimization value of the analysis function is calculated according to the preset service optimization formula.

8. The intelligent control system for service data acquisition and processing based on edge-cloud collaboration according to claim 7, characterized in that, The service optimization formula is: ； In the formula: FY is the service optimization value.

Images