Terminal equipment data collection method and system based on Internet of Things
By integrating multiple sensors and deep learning models on IoT terminal devices, combining optimized network protocols and coding technologies, real-time monitoring and optimization of data acquisition and transmission processes, existing systems solve the data acquisition accuracy, transmission reliability and response in existing systems. The problem of insufficient capabilities has achieved efficient and stable environmental monitoring data collection and transmission.
Patent Information
- Application Number
- CN202411281219.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-13
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-09-13
AI Technical Summary
The existing environmental monitoring and data acquisition systems have shortcomings in data acquisition accuracy, transmission reliability and processing efficiency, especially in complex and dynamic environments, showing low responsiveness and adaptability.
Adopting a terminal device data acquisition system based on the Internet of Things, through the terminal acquisition module, central processing module, data acquisition status analysis module, comprehensive analysis module and optimization iteration module, the timing acquisition of multiple sensors, deep learning model prediction, and optimization multi-hop LoRa network protocol and network coding technology, real-time monitoring and optimization of data acquisition, transmission and processing processes.
It significantly improves the accuracy of data acquisition and transmission reliability, improves the system's response ability and adaptability, ensures the high quality and reliability of environmental monitoring data, and provides a solid foundation for subsequent analysis.
Smart Images

Figure CN118802988B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of terminal acquisition equipment, and in particular to a terminal equipment data acquisition method and system based on the Internet of Things. Background Art
[0002] The terminal device data acquisition system based on the Internet of Things is a broad field involving networks, sensor technology, big data analysis and automatic control. Specifically for the application of the Internet of Things, environmental monitoring and data acquisition is a key sub-field. Through sensors deployed at various nodes, the system can collect various data in the environment in real time. These data include parameters such as temperature, humidity, gas concentration, light intensity, etc., which are used for environmental monitoring in application scenarios such as industrial parks, smart cities, and agricultural management. The data acquisition system of the terminal acquisition device of the Internet of Things is in this specific field, through the sensor network, real-time collection, transmission, storage and analysis of these environmental parameters.
[0003] In the Chinese invention application with application publication number CN108073093B, a data collection and management system based on Internet of Things home appliances is disclosed. The data collection and management system based on Internet of Things home appliances has main modules including data collection module, data storage module, monitoring module and remote processing center; the data collection module includes a communication module that can be connected to the remote processing center; the data collection module is connected to the interface of each terminal collection device of the Internet of Things home appliances, and is responsible for collecting device terminal information; the working mode of the data collection module is divided into initial data collection and multiple data collection. During the initial data collection, each hardware information of the Internet of Things home appliances is bundled with the only legal addressing information when the refrigerator is connected to the Internet of Things. The data collection and management system of the present invention can store data more conveniently and safely. During the initial data collection, each hardware information of the Internet of Things home appliances is bundled with the only legal addressing information when the refrigerator is connected to the Internet of Things. The data collection module is triggered again, and the security verification unit is started when new data information is taken.
[0004] In combination with the prior art, the above application still has the following deficiencies:
[0005] At present, there are some deficiencies in the existing environmental monitoring and data collection systems at the technical and application levels. For example, the accuracy of data collection is often limited by the quality of sensors, environmental interference and collection frequency, resulting in an inability to accurately reflect the true situation of the environment. In addition, data is easily affected by network instability during transmission, and the reliability and efficiency of data transmission are difficult to guarantee. After the data is transmitted to the server, if the processing and analysis are not timely or accurate, it will affect the prediction and decision-making of environmental conditions. These deficiencies make the existing system show low responsiveness and adaptability when facing complex and dynamic environments. Summary of the invention
[0006] In view of the deficiencies in the prior art, the present invention provides a terminal device data collection method and system based on the Internet of Things, which solves the problems mentioned in the background technology.
[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: including a terminal acquisition module, a central processing module, a data acquisition state analysis module, a comprehensive analysis module and an optimization iteration module;
[0008] The terminal acquisition module is equipped with multiple sensors on the terminal acquisition device of the Internet of Things, and the sensor nodes collect the environmental parameter set Pj of the park within the set time interval, and transmit the collected environmental parameter set to the central processing module through the Internet of Things gateway device, and record the transmission data;
[0009] The central processing module is used to receive the collected environmental parameter set Pj in real time, preprocess the environmental parameter set to generate a preprocessed data set, then build a distributed database to store the sensor data set, and then use the deep learning model to predict the time series data to obtain a predicted data set;
[0010] The data acquisition state analysis module is used to construct relevant algorithm formulas, and calculate the data acquisition accuracy UPAA, the data transmission index DTRR and the data processing and prediction accuracy DPPA respectively according to the acquired environmental parameter set Pj, the transmission data and the prediction data set;
[0011] The comprehensive analysis module is used to comprehensively calculate the acquired data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA, output the comprehensive acquisition performance index SYS, and then perform preliminary comparative evaluation on the preset performance threshold X and the comprehensive acquisition performance index SYS;
[0012] The optimization iteration module is used to generate an optimization prompt report when it is evaluated that there is an abnormality in the data collection of the terminal collection device of the current Internet of Things, and re-execute the system after optimization, output the secondary comprehensive collection performance indicator SYS2, and perform a secondary comparative evaluation with the performance threshold X, analyze the data collection situation, and execute the iteration strategy.
[0013] Preferably, the terminal acquisition module includes a terminal acquisition device acquisition unit and an Internet of Things transmission unit;
[0014] The terminal acquisition device acquisition unit is used to install multiple sensors in the industrial park, and set each sensor to collect the environmental parameter set Pj of the industrial park once every half an hour, wherein the environmental parameter set Pj={P1, P2, ..., Pn};
[0015] The IoT transmission unit is used to set the IoT gateway device as a data aggregation center, which is responsible for receiving the environmental parameter set Pj collected by multiple sensor nodes, and then transmitting it to the central processing module through the optimized multi-hop LoRa network protocol. At the same time, network coding technology is used to optimize the transmission efficiency, and a data transmission log is generated during the transmission process to record the transmission data. The transmission data includes the transmission rate Rs, the number of error-free data packets Tf, the channel bandwidth Bw, the total transmission data volume Lt and the redundant data volume R.
[0016] Preferably, the central processing module includes a data processing unit and a data storage unit;
[0017] The data processing unit is used to perform denoising on the collected environmental parameter set Pj using Kalman filtering, and then perform average processing on the denoised environmental parameter set Pj to obtain the average value of the environmental parameters , and then calibrate and linearize the environmental parameter set Pj to obtain the calibration coefficient Rj, and then calculate the average value of the obtained environmental parameters and calibration coefficients Rj are summarized to generate a preprocessed data set;
[0018] The data storage unit includes a storage unit and a prediction unit;
[0019] The storage unit is used to construct a distributed database, divide the collected environmental parameter set Pj and the pre-processed data set into several 64MB data blocks, back up each data block into three copies, and then distribute each data block to different storage nodes;
[0020] The prediction unit integrates the LSTM model and the GRU model to build a deep learning model, extracts the historical time series data of the environmental parameter set Pj from the distributed database, trains the deep learning model, and then inputs the real-time environmental parameter set Pj into the trained deep learning model. The deep learning model outputs the environmental parameter prediction value Pj. Pred The time Tp required for data processing and prediction is calculated and summarized to generate a prediction data set.
[0021] Preferably, the data acquisition status analysis module includes a data acquisition accuracy analysis unit, a data transmission analysis unit and a prediction accuracy analysis unit;
[0022] The data acquisition accuracy analysis unit is used to construct a data acquisition accuracy algorithm formula, and then input the environmental parameter set Pj and the pre-processed data set to calculate and output the data acquisition accuracy UPAA;
[0023] The data acquisition accuracy UPAA is calculated by the following data acquisition accuracy algorithm formula;
[0024] ;
[0025] Where Pij represents the jth environmental parameter value collected for the i-th time. represents the average value of the j-th environmental parameter, Rj represents the calibration coefficient of the j-th environmental parameter, which is used to eliminate the dimensional influence of different parameters, and M represents the number of dimensions of the environmental parameter.
[0026] Preferably, the data transmission analysis unit is used to construct a data transmission robustness and redundancy algorithm, and then calculate and obtain a data transmission index DTRR based on the transmission data;
[0027] The data transmission indicator DTRR is obtained by calculating the following data transmission robustness and redundancy algorithm;
[0028] ;
[0029] Where Tf c Indicates the data packet data without errors in the cth transmission, Rs c Indicates the actual transmission rate of the cth transmission, Bw c represents the channel bandwidth of the cth transmission, Lt c represents the total amount of data transmitted for the cth time, R c Indicates the amount of data introduced during the transmission process, used to optimize the reliability of data transmission.
[0030] Preferably, the prediction accuracy analysis unit is used to construct a data processing and prediction accuracy algorithm formula, and calculate and obtain the data processing and prediction accuracy DPPA according to the prediction data set;
[0031] The data processing and prediction accuracy DPPA is calculated and obtained by the following data processing and prediction accuracy algorithm formula;
[0032] ;
[0033] In the formula, Pj Pred represents the predicted value of the jth environmental parameter, Pj actual Represents the actual value of the jth environmental parameter.
[0034] Preferably, the comprehensive analysis module includes a collection performance analysis unit and a performance evaluation unit;
[0035] The acquisition performance analysis unit is used to correlate the acquired data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA, and output a comprehensive acquisition performance index SYS;
[0036] The comprehensive acquisition performance index SYS is calculated and obtained by the following algorithm formula;
[0037] ;
[0038] In the formula, , and They respectively represent the preset weight values of data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA.
[0039] Preferably, the performance evaluation unit sets the performance threshold X through the user, and then compares it with the obtained comprehensive collection performance index SYS to perform a preliminary comparative evaluation and analysis of the data collection status of the terminal collection device of the Internet of Things. The specific evaluation content is as follows;
[0040] When the comprehensive collection performance index SYS ≥ performance threshold X, it means that the comprehensive collection performance of the data collection accuracy, data transmission reliability, and data processing and prediction accuracy of the terminal collection equipment of the Internet of Things are normal, and no optimization is required at this time;
[0041] When the comprehensive collection performance index SYS is less than the performance threshold X, it indicates that the comprehensive collection performance of the terminal collection device of the Internet of Things is abnormal, and an early warning prompt is generated at this time.
[0042] Preferably, the optimization iteration module is used to be triggered when an early warning prompt is received, at which time an optimization instruction is sent to the terminal to execute the optimization strategy. The optimization strategy automatically increases the sensor accuracy by 10% and automatically switches the network connection mode step by step. The step-by-step switching network connection mode is 3G network>WIFI network>4G network>5G network, optimizes the network transmission protocol, and automatically releases the system server memory to optimize the data processing speed. After executing the optimization strategy, the coefficient is re-executed, and the secondary comprehensive acquisition performance index SYS2 is output, and then a secondary comparative evaluation is performed with the performance threshold X, and an iteration mechanism is generated. The specific evaluation content is as follows;
[0043] When the secondary comprehensive collection performance index SYS2 ≥ performance threshold X, it means that the comprehensive collection performance of the terminal collection equipment of the Internet of Things is normal, and no iterative optimization is required at this time;
[0044] When the secondary comprehensive acquisition performance index SYS2 is less than the performance threshold X, it indicates that the comprehensive acquisition performance of the terminal acquisition device of the Internet of Things is abnormal. At this time, the optimization iteration module is iteratively executed to adjust the sensor configuration, optimize the network transmission and optimize the data processing capability, and output the comprehensive acquisition performance index SYS again for comparative evaluation.
[0045] The terminal device data collection method based on the Internet of Things includes the following steps:
[0046] S1, by equipping the terminal collection device of the Internet of Things with multiple sensors, and the sensor nodes collect the environmental parameter set Pj of the park within the set time interval, and transmit the collected environmental parameter set to the central processing module through the Internet of Things gateway device, and record the transmission data;
[0047] S2, receiving the collected environmental parameter set Pj in real time, and preprocessing the environmental parameter set to generate a preprocessed data set, then building a distributed database to store the sensor data set, and then using a deep learning model to predict the time series data to obtain a predicted data set;
[0048] S3, construct relevant algorithm formulas, and calculate and obtain data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA respectively according to the obtained environmental parameter set Pj, transmission data and prediction data set;
[0049] S4, comprehensively calculate the acquired data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA, output the comprehensive acquisition performance index SYS, and then perform preliminary comparative evaluation on the preset performance threshold X and the comprehensive acquisition performance index SYS;
[0050] S5. When it is evaluated that the data collection of the terminal collection device of the current Internet of Things is abnormal, an optimization prompt report is generated, and the system is re-executed after optimization, and the secondary comprehensive collection performance index SYS2 is output, and a secondary comparative evaluation is performed with the performance threshold X, the data collection situation is analyzed, and an iterative strategy is executed.
[0051] The present invention provides a terminal device data collection method and system based on the Internet of Things, which has the following beneficial effects:
[0052] (1) The system can effectively collect environmental parameters Pi in the park through the precise deployment and timing collection mechanism of multiple sensors in the terminal collection module. Through the preprocessing of the collected data by the central processing module and the predictive analysis of the deep learning model, the system can greatly improve the accuracy of data collection. At the same time, the optimized multi-hop LoRa network protocol and network coding technology of the IoT transmission unit further ensure the reliability of data transmission and reduce data loss and transmission delay. This efficient and stable collection and transmission mechanism ensures the high quality of environmental monitoring data and provides a reliable basis for subsequent analysis.
[0053] (2) The system monitors the status of data collection, transmission, processing and prediction in real time through the data collection status analysis module by constructing and applying the algorithms of data collection accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA. Combined with the comprehensive analysis module to generate the comprehensive collection performance index SYS and conduct preliminary comparative evaluation with the preset performance threshold X, the system can comprehensively analyze the data collection status of the IoT terminal collection equipment and timely identify and evaluate abnormal situations in the data collection process. Through this intelligent analysis and real-time monitoring mechanism, the system can quickly respond to abnormal situations and generate optimization prompts to improve the responsiveness and adaptability of the entire data collection system.
[0054] (3) When the system finds performance anomalies during the evaluation, the optimization iteration module will automatically trigger optimization strategies, such as improving sensor accuracy, switching network connection modes, and releasing server memory. These measures can effectively improve the sensor's acquisition accuracy, improve the efficiency of data transmission, and speed up data processing. After optimizing the terminal acquisition device, the system will generate a secondary comprehensive acquisition performance index SYS2 and conduct a secondary comparative evaluation with the performance threshold X to ensure that the optimized system can meet the expected requirements. Even if there are still problems after the secondary evaluation, the system will continue to execute the iteration strategy for further optimization to ensure that the IoT data acquisition system can operate stably and effectively in the long term. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] Figure 1 This is a flow chart of a terminal device data acquisition system based on the Internet of Things of the present invention;
[0056] Figure 2 The figure is a schematic diagram of the steps of the terminal device data collection method based on the Internet of Things of the present invention. DETAILED DESCRIPTION
[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0058] Example 1
[0059] See also Figure 1 The present invention provides a terminal device data acquisition system based on the Internet of Things. To achieve the above purpose, the present invention is implemented through the following technical solutions: including a terminal acquisition module, a central processing module, a data acquisition state analysis module, a comprehensive analysis module and an optimization iteration module;
[0060] The terminal acquisition module equips the terminal acquisition device of the Internet of Things with multiple sensors, and the sensor nodes collect the environmental parameter set Pj of the park within the set time interval, and transmits the collected environmental parameter set to the central processing module through the Internet of Things gateway device, and records the transmission data;
[0061] The central processing module is used to receive the collected environmental parameter set Pj in real time, preprocess the environmental parameter set, generate a preprocessed data set, build a distributed database to store the sensor data set, and then use the deep learning model to predict the time series data to obtain the predicted data set;
[0062] The data acquisition status analysis module is used to construct relevant algorithm formulas, and calculate the data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA according to the acquired environmental parameter set Pj, transmission data and prediction data set;
[0063] The comprehensive analysis module is used to comprehensively calculate the acquired data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA, output the comprehensive acquisition performance index SYS, and then perform preliminary comparative evaluation with the preset performance threshold X and the comprehensive acquisition performance index SYS;
[0064] The optimization iteration module is used to re-evaluate the abnormalities in the data collection of the terminal collection equipment of the current Internet of Things, generate an optimization prompt report, re-execute the system after optimization, output the secondary comprehensive collection performance index SYS2, and conduct a secondary comparative evaluation with the performance threshold X, analyze the data collection situation, and execute the iteration strategy.
[0065] In this embodiment, the system configures multiple sensors through the terminal acquisition module to ensure accurate collection of environmental parameter sets Pj within the set time interval, and uses the Internet of Things gateway device to transmit these data to the central processing module, and comprehensively records the key data in the transmission process. The central processing module receives, preprocesses and stores environmental parameters in real time, uses a deep learning model to predict time series data, and generates a high-precision prediction data set, thereby improving the system's prediction ability and response speed to environmental changes. In the data acquisition status analysis module, the system constructs an algorithm formula for evaluating data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA, and conducts a detailed analysis of key performance indicators in the acquisition, transmission and prediction processes. The comprehensive analysis module calculates these indicators comprehensively to generate a comprehensive acquisition performance index SYS, and compares it with the preset performance threshold X to evaluate the overall operating status of the system. If the system performance is lower than expected, the optimization iteration module will automatically generate an optimization prompt report and execute optimization strategies, such as improving sensor accuracy, optimizing network transmission protocols and speeding up data processing. Through this cyclic iterative optimization method, the system can quickly adjust when an abnormality occurs, recalculate and output the optimized comprehensive acquisition performance index SYS2, and ensure that the system continues to operate efficiently. Compared with traditional technical means, the system has achieved significant improvements in data collection accuracy, transmission reliability, real-time processing capabilities, and intelligent optimization. Through modular design and the application of intelligent algorithms, the system can not only accurately reflect environmental changes, but also perform adaptive optimization when abnormalities occur, ensuring the stability and reliability of the system in complex environments. This comprehensive improvement enables the system to provide more accurate, timely, and intelligent environmental monitoring services in large-scale IoT applications, significantly improving overall efficiency and responsiveness.
[0066] Example 2
[0067] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the terminal acquisition module includes a terminal acquisition device acquisition unit and an ,Internet of Things transmission unit;
[0068] The terminal collection device collection unit is used to install multiple sensors in the industrial park, and set each sensor to collect the environmental parameter set Pj of the industrial park once every half an hour, where the environmental parameter set Pj = {P1, P2, ..., Pn};
[0069] The IoT transmission unit is used to set the IoT gateway device as the data aggregation center, which is responsible for receiving the environmental parameter set Pj collected by multiple sensor nodes, and then transmitting it to the central processing module through the optimized multi-hop LoRa network protocol. At the same time, it uses network coding technology to optimize the transmission efficiency and generates a data transmission log during the transmission process to record the transmission data. The transmission data includes the transmission rate Rs, the number of error-free data packets Tf, the channel bandwidth Bw, the total transmission data volume Lt and the redundant data volume R.
[0070] In this embodiment, the system uses the terminal collection device collection unit to deploy multiple sensors in the park and periodically collect environmental parameter sets Pj at intervals of half an hour, ensuring the comprehensiveness and timeliness of the data. The IoT transmission unit uses the optimized multi-hop LoRa network protocol to improve the stability and efficiency of data transmission by setting up the IoT gateway device as the data aggregation center. At the same time, network coding technology is used to further optimize the transmission process, reduce data packet loss and delay, and generate detailed data transmission logs during the transmission process.
[0071] Example 3
[0072] This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the central processing module includes a data processing unit and a data storage unit;
[0073] The data processing unit is used to perform denoising on the collected environmental parameter set Pj using Kalman filtering, and then perform average processing on the denoised environmental parameter set Pj to obtain the average value of the environmental parameters. , and then calibrate and linearize the environmental parameter set Pj to obtain the calibration coefficient Rj, and then calculate the average value of the obtained environmental parameters and calibration coefficients Rj are summarized to generate a preprocessed data set;
[0074] The data storage unit includes a storage unit and a prediction unit;
[0075] The storage unit is used to build a distributed database, which divides the collected environmental parameter set Pj and pre-processed data set into several 64MB data blocks, backs up each data block in three copies, and then distributes each data block to different storage nodes;
[0076] The prediction unit integrates the LSTM model and the GRU model to build a deep learning model, extracts the historical time series data of the environmental parameter set Pj from the distributed database, trains the deep learning model, and then inputs the real-time environmental parameter set Pj into the trained deep learning model. The deep learning model outputs the environmental parameter prediction value Pj. PredThe time Tp required for data processing and prediction is calculated and summarized to generate a prediction data set.
[0077] In this embodiment, the system realizes efficient processing, accurate storage and intelligent prediction of environmental parameters through the effective cooperation of the data processing unit and the data storage unit of the central processing module. The data processing unit first performs denoising on the collected environmental parameter set Pj through Kalman filtering to eliminate noise interference and ensure the accuracy of the data. Subsequently, the system performs average processing on the denoised data to obtain a stable average value of the environmental parameters, and calculates the calibration coefficient Rj through calibration and linearization processing, and finally generates a high-quality preprocessed data set. This processing chain greatly improves the authenticity and reliability of the data, laying a solid foundation for subsequent analysis. The data storage unit efficiently stores the preprocessed data by constructing a distributed database, assigns each data block to different storage nodes, and performs triple backup to ensure the security and availability of the data. At the same time, the system integrates the LSTM model and the GRU model to train the deep learning model to predict historical time series data. The system can input new environmental parameter data in real time and output accurate prediction values Pj through the trained deep learning model. Pred , and the time Tp required for processing and prediction, to form a comprehensive prediction data set.
[0078] Example 4
[0079] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the data acquisition state analysis module includes a data acquisition accuracy ,analysis unit, a data transmission analysis unit and a prediction accuracy ,analysis unit;
[0080] The data acquisition accuracy analysis unit is used to construct a data acquisition accuracy algorithm formula, and then input the environmental parameter set Pj and the preprocessed data set to calculate and output the data acquisition accuracy UPAA;
[0081] The data acquisition accuracy UPAA is calculated by the following data acquisition accuracy algorithm formula;
[0082] ;
[0083] Where Pij represents the jth environmental parameter value collected for the i-th time. represents the average value of the j-th environmental parameter, Rj represents the calibration coefficient of the j-th environmental parameter, which is used to eliminate the dimensional influence of different parameters, and M represents the number of dimensions of the environmental parameter.
[0084] The data transmission analysis unit is used to construct a data transmission robustness and redundancy algorithm, and then calculate and obtain the data transmission index DTRR based on the transmission data;
[0085] The data transmission indicator DTRR is obtained by calculating the following data transmission robustness and redundancy algorithm;
[0086] ;
[0087] Where Tf c Indicates the data packet data without errors in the cth transmission, Rs c Indicates the actual transmission rate of the cth transmission, Bw c represents the channel bandwidth of the cth transmission, Lt c represents the total amount of data transmitted for the cth time, R c Indicates the amount of data introduced during the transmission process, used to optimize the reliability of data transmission.
[0088] The prediction accuracy analysis unit is used to construct the data processing and prediction accuracy algorithm formula, and calculate the data processing and prediction accuracy DPPA according to the prediction data set;
[0089] Data processing and prediction accuracy DPPA is calculated and obtained through the following data processing and prediction accuracy algorithm formula;
[0090] ;
[0091] In the formula, Pj Pred represents the predicted value of the jth environmental parameter, Pj actual Represents the actual value of the jth environmental parameter.
[0092] In this embodiment, the system comprehensively improves the system's ability to accurately monitor and evaluate data collection, transmission and prediction through the data collection state analysis module through the combined effects of the data collection accuracy analysis unit, the data transmission analysis unit and the prediction accuracy analysis unit. The data collection accuracy analysis unit accurately calculates the data collection accuracy UPAA by constructing and applying the data collection accuracy algorithm formula to ensure the high accuracy and consistency of the collected data. The data transmission analysis unit evaluates and optimizes the stability and reliability of the data transmission process by calculating the data transmission robustness and redundancy DTRR, reducing data loss and delay. The prediction accuracy analysis unit ensures the accuracy of the system's prediction of future environmental parameter changes by accurately calculating the data processing and prediction accuracy DPPA. The collaborative work of these modules not only realizes a comprehensive evaluation of the key performance indicators of the system, but also provides a scientific basis for subsequent optimization through quantitative analysis results. Compared with the traditional Internet of Things data acquisition system, this modular analysis method significantly improves the controllability and response speed of the system, enabling the system to maintain efficient and accurate operation in a complex environment. Ultimately, this improvement brings about a significant improvement in the overall performance of the system, including the accuracy of data collection, the stability of transmission and the reliability of prediction, laying a solid foundation for the realization of intelligent and automated data collection and processing.
[0093] Example 5
[0094] This embodiment is explained in Example 4. Please refer to Figure 1 ,Specifically: the comprehensive analysis module includes the acquisition ,performance analysis unit and the performance evaluation unit;
[0095] The acquisition performance analysis unit is used to correlate the acquired data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA, and output a comprehensive acquisition performance index SYS;
[0096] The comprehensive acquisition performance index SYS is calculated and obtained through the following algorithm formula;
[0097] ;
[0098] In the formula, , and They respectively represent the preset weight values of data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA.
[0099] The performance evaluation unit sets the performance threshold X through the user, and then compares it with the obtained comprehensive collection performance index SYS to conduct a preliminary comparative evaluation and analysis of the data collection status of the terminal collection equipment of the Internet of Things. The specific evaluation contents are as follows;
[0100] When the comprehensive collection performance index SYS ≥ performance threshold X, it means that the comprehensive collection performance of the data collection accuracy, data transmission reliability, and data processing and prediction accuracy of the terminal collection equipment of the Internet of Things are normal, and no optimization is required at this time;
[0101] When the comprehensive collection performance index SYS is less than the performance threshold X, it indicates that the comprehensive collection performance of the terminal collection device of the Internet of Things is abnormal, and an early warning prompt is generated at this time.
[0102] In this embodiment, the system significantly improves the performance evaluation and intelligent decision-making capabilities of the data acquisition system of the Internet of Things terminal equipment through the design of the data acquisition state analysis module and the comprehensive analysis module. The data acquisition state analysis module conducts in-depth analysis and quantitative evaluation of the data acquisition accuracy UPAA, the data transmission robustness and redundancy DTRR, and the data processing and prediction accuracy DPPA by constructing an accurate algorithm formula. Each unit works together to ensure that every link from the collected data, the transmission process to the final prediction can be accurately controlled and optimized. The comprehensive analysis module associates and calculates these key indicators through the acquisition performance analysis unit to generate a comprehensive acquisition performance index SYS. The performance evaluation unit evaluates the overall performance status of the system in real time by making a preliminary comparison between the comprehensive acquisition performance index SYS and the performance threshold X set by the user. When SYS is higher than the threshold X, it indicates that the system is running normally and no further optimization is required; when the comprehensive acquisition performance index SYS is lower than or higher than the threshold X, the system can generate an early warning prompt in time, indicating an abnormality and triggering an optimization mechanism.
[0103] Example 6
[0104] This embodiment is explained in Example 5. Please refer to Figure 1 Specifically: the optimization iteration module is used to be triggered when an early warning prompt is received. At this time, the optimization instruction is sent to the terminal to execute the optimization strategy. The optimization strategy automatically increases the sensor accuracy by 10% and automatically switches the network connection mode step by step. The network connection mode is switched step by step to 3G network>WIFI network>4G network>5G network, optimizes the network transmission protocol, and automatically releases the system server memory to optimize the data processing speed. After executing the optimization strategy, the coefficient is re-executed, and the secondary comprehensive acquisition performance index SYS2 is output, and then a secondary comparative evaluation is performed with the performance threshold X, and an iteration mechanism is generated. The specific evaluation content is as follows;
[0105] When the secondary comprehensive collection performance index SYS2 ≥ performance threshold X, it means that the comprehensive collection performance of the terminal collection equipment of the Internet of Things is normal, and no iterative optimization is required at this time;
[0106] When the secondary comprehensive acquisition performance index SYS2 is less than the performance threshold X, it indicates that the comprehensive acquisition performance of the terminal acquisition device of the Internet of Things is abnormal. At this time, the optimization iteration module is iteratively executed to adjust the sensor configuration, optimize the network transmission and optimize the data processing capability, and output the comprehensive acquisition performance index SYS again for comparative evaluation.
[0107] In this embodiment, the optimization iteration module of the system significantly enhances the adaptability and continuous optimization capability of the data acquisition system of the IoT terminal acquisition device through an automated optimization strategy. When the system receives an early warning prompt, the module can immediately send an optimization instruction to the terminal and perform a series of intelligent optimization operations, such as automatically improving the sensor accuracy by 10%, dynamically switching the network connection mode from 3G to 5G step by step, optimizing the network transmission protocol, and automatically releasing the server memory to increase the data processing speed. Through these optimization measures, the system recalculates and generates the secondary comprehensive acquisition performance index SYS2, and performs a secondary evaluation with the performance threshold X. If the secondary comprehensive acquisition performance index SYS2 reaches or exceeds the threshold X, the system performance is considered normal and no further optimization is required; if not, the module will continue to iterate and execute the optimization strategy, further adjust the sensor configuration, optimize the network transmission and data processing capabilities, and ensure that the system is always in the best operating state.
[0108] Example 7
[0109] See also Figure 1 and Figure 2 , a terminal device data collection method based on the Internet of Things includes the following steps:
[0110] S1, by equipping the terminal collection device of the Internet of Things with multiple sensors, and the sensor nodes collect the environmental parameter set Pj of the park within the set time interval, and transmit the collected environmental parameter set to the central processing module through the Internet of Things gateway device, and record the transmission data;
[0111] S2, receiving the collected environmental parameter set Pj in real time, and preprocessing the environmental parameter set to generate a preprocessed data set, then building a distributed database to store the sensor data set, and then using a deep learning model to predict the time series data to obtain a predicted data set;
[0112] S3, construct relevant algorithm formulas, and calculate and obtain data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA respectively according to the obtained environmental parameter set Pj, transmission data and prediction data set;
[0113] S4, comprehensively calculate the acquired data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA, output the comprehensive acquisition performance index SYS, and then perform preliminary comparative evaluation on the preset performance threshold X and the comprehensive acquisition performance index SYS;
[0114] S5. When it is evaluated that the data collection of the terminal collection device of the current Internet of Things is abnormal, an optimization prompt report is generated, and the system is re-executed after optimization, and the secondary comprehensive collection performance index SYS2 is output, and a secondary comparative evaluation is performed with the performance threshold X, the data collection situation is analyzed, and an iterative strategy is executed.
[0115] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.
Claims
1. The terminal equipment data acquisition system based on the Internet of Things is characterized by: It includes terminal acquisition module, central processing module, data acquisition status analysis module, comprehensive analysis module and optimization iteration module; The terminal acquisition module is equipped with multiple sensors on the terminal acquisition device of the Internet of Things, and the sensor nodes collect the environmental parameter set Pj of the park within the set time interval, and transmit the collected environmental parameter set to the central processing module through the Internet of Things gateway device, and record the transmission data; The terminal acquisition module includes a terminal acquisition device acquisition unit and an Internet of Things transmission unit; The terminal acquisition device acquisition unit is used to install multiple sensors in the industrial park, and set each sensor to collect the environmental parameter set Pj of the industrial park once every half an hour, wherein the environmental parameter set Pj={P1, P2, ..., Pn}; The Internet of Things transmission unit is used to set the Internet of Things gateway device as a data aggregation center, which is responsible for receiving the environmental parameter set Pj collected by multiple sensor nodes, and then transmitting it to the central processing module through the optimized multi-hop LoRa network protocol. At the same time, network coding technology is used to optimize the transmission efficiency, and a data transmission log is generated during the transmission process to record the transmission data. The transmission data includes the transmission rate Rs, the number of error-free data packets Tf, the channel bandwidth Bw, the total transmission data volume Lt and the redundant data volume R; The central processing module is used to receive the collected environmental parameter set Pj in real time, preprocess the environmental parameter set to generate a preprocessed data set, then build a distributed database to store the sensor data set, and then use the deep learning model to predict the time series data to obtain a predicted data set; The data acquisition state analysis module is used to construct relevant algorithm formulas, and calculate the data acquisition accuracy UPAA, the data transmission index DTRR and the data processing and prediction accuracy DPPA respectively according to the acquired environmental parameter set Pj, the transmission data and the prediction data set; The comprehensive analysis module is used to comprehensively calculate the acquired data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA, output the comprehensive acquisition performance index SYS, and then perform preliminary comparative evaluation on the preset performance threshold X and the comprehensive acquisition performance index SYS; The optimization iteration module is used to generate an optimization prompt report when it is evaluated that there is an abnormality in the data collection of the terminal collection device of the current Internet of Things, and re-execute the system after optimization, output the secondary comprehensive collection performance indicator SYS2, and perform a secondary comparative evaluation with the performance threshold X, analyze the data collection situation, and execute the iteration strategy.
2. The terminal device data acquisition system based on the Internet of Things according to claim 1 is characterized in that: The central processing module includes a data processing unit and a data storage unit; The data processing unit is used to perform denoising on the collected environmental parameter set Pj using Kalman filtering, and then perform average processing on the denoised environmental parameter set Pj to obtain the average value of the environmental parameters , and then calibrate and linearize the environmental parameter set Pj to obtain the calibration coefficient Rj, and then calculate the average value of the obtained environmental parameters and calibration coefficients Rj are summarized to generate a preprocessed data set; The data storage unit includes a storage unit and a prediction unit; The storage unit is used to construct a distributed database, divide the collected environmental parameter set Pj and the pre-processed data set into several 64MB data blocks, back up each data block into three copies, and then distribute each data block to different storage nodes; The prediction unit integrates the LSTM model and the GRU model to build a deep learning model, extracts the historical time series data of the environmental parameter set Pj from the distributed database, trains the deep learning model, and then inputs the real-time environmental parameter set Pj into the trained deep learning model. The deep learning model outputs the environmental parameter prediction value Pj. Pred The time Tp required for data processing and prediction is calculated and summarized to generate a prediction data set.
3. The terminal device data acquisition system based on the Internet of Things according to claim 2 is characterized in that: The data acquisition state analysis module includes a data acquisition accuracy analysis unit, a data transmission analysis unit and a prediction accuracy analysis unit; The data acquisition accuracy analysis unit is used to construct a data acquisition accuracy algorithm formula, and then input the environmental parameter set Pj and the pre-processed data set to calculate and output the data acquisition accuracy UPAA; The data acquisition accuracy UPAA is calculated by the following data acquisition accuracy algorithm formula; ; In the formula, Pij represents the jth environmental parameter value collected for the i-th time, represents the average value of the j-th environmental parameter, Rj represents the calibration coefficient of the j-th environmental parameter, which is used to eliminate the dimensional influence of different parameters, and N represents the number of acquisitions.
4. The terminal device data acquisition system based on the Internet of Things according to claim 3 is characterized in that: The data transmission analysis unit is used to construct a data transmission robustness and redundancy algorithm, and then calculate and obtain a data transmission index DTRR based on the transmission data; The data transmission indicator DTRR is obtained by calculating the following data transmission robustness and redundancy algorithm; ; Where Tf c Indicates the data packet with no errors in the cth transmission, Rs c Indicates the actual transmission rate of the cth transmission, Bw c represents the channel bandwidth of the cth transmission, Lt c represents the total amount of data transmitted for the cth time, R c Indicates the amount of data introduced during the transmission process, used to optimize the reliability of data transmission.
5. The terminal device data acquisition system based on the Internet of Things according to claim 4 is characterized in that: The prediction accuracy analysis unit is used to construct a data processing and prediction accuracy algorithm formula, and calculate and obtain the data processing and prediction accuracy DPPA according to the prediction data set; The data processing and prediction accuracy DPPA is calculated and obtained by the following data processing and prediction accuracy algorithm formula; ; In the formula, Pj Pred represents the predicted value of the jth environmental parameter, Pj actual Represents the actual value of the jth environmental parameter.
6. The terminal device data acquisition system based on the Internet of Things according to claim 5 is characterized in that: The comprehensive analysis module includes a collection performance analysis unit and a performance evaluation unit; The acquisition performance analysis unit is used to correlate the acquired data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA, and output a comprehensive acquisition performance index SYS; The comprehensive acquisition performance index SYS is calculated and obtained by the following algorithm formula; ; In the formula, , and They respectively represent the preset weight values of data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA.
7. The terminal device data acquisition system based on the Internet of Things according to claim 6 is characterized in that: The performance evaluation unit sets the performance threshold X through the user, and then compares it with the obtained comprehensive collection performance index SYS to perform a preliminary comparison and evaluation analysis on the data collection status of the terminal collection device of the Internet of Things. The specific evaluation contents are as follows; When the comprehensive collection performance index SYS ≥ performance threshold X, it means that the comprehensive collection performance of the data collection accuracy, data transmission reliability, and data processing and prediction accuracy of the terminal collection equipment of the Internet of Things are normal, and no optimization is required at this time; When the comprehensive collection performance index SYS is less than the performance threshold X, it indicates that the comprehensive collection performance of the terminal collection device of the Internet of Things is abnormal, and an early warning prompt is generated at this time.
8. The terminal device data acquisition system based on the Internet of Things according to claim 7 is characterized in that: The optimization iteration module is used to be triggered when receiving an early warning prompt. At this time, an optimization instruction is sent to the terminal to execute the optimization strategy. The optimization strategy automatically increases the sensor accuracy by 10% and automatically switches the network connection mode step by step. The step-by-step switching network connection mode is 3G network>WIFI network>4G network>5G network, optimizes the network transmission protocol, and automatically releases the system server memory to optimize the data processing speed. After executing the optimization strategy, the coefficient is re-executed, and the secondary comprehensive acquisition performance indicator SYS2 is output, and then a secondary comparison evaluation is performed with the performance threshold X, and an iteration mechanism is generated. The specific evaluation content is as follows; When the secondary comprehensive collection performance index SYS2 ≥ performance threshold X, it means that the comprehensive collection performance of the terminal collection equipment of the Internet of Things is normal, and no iterative optimization is required at this time; When the secondary comprehensive collection performance indicator SYS2 is less than the performance threshold X, it indicates that the comprehensive collection performance of the terminal collection device of the Internet of Things is abnormal, and at this time, the optimization iteration module is iteratively executed.
9. A terminal device data collection method based on the Internet of Things, applied to a terminal device data collection system based on the Internet of Things according to any one of claims 1 to 8, characterized in that: The following steps are involved: S1, by equipping the terminal collection device of the Internet of Things with multiple sensors, and the sensor nodes collect the environmental parameter set Pj of the park within the set time interval, and transmit the collected environmental parameter set to the central processing module through the Internet of Things gateway device, and record the transmission data; S2, receiving the collected environmental parameter set Pj in real time, and preprocessing the environmental parameter set to generate a preprocessed data set, then building a distributed database to store the sensor data set, and then using a deep learning model to predict the time series data to obtain a predicted data set; S3, construct relevant algorithm formulas, and calculate the data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA respectively according to the obtained environmental parameter set Pj, transmission data and prediction data set; S4, comprehensively calculate the acquired data acquisition accuracy UPAA, data transmission index DTRR and data processing and prediction accuracy DPPA, output the comprehensive acquisition performance index SYS, and then perform preliminary comparative evaluation on the preset performance threshold X and the comprehensive acquisition performance index SYS; S5. When it is evaluated that the data collection of the terminal collection device of the current Internet of Things is abnormal, an optimization prompt report is generated, and the system is re-executed after optimization, and the secondary comprehensive collection performance index SYS2 is output, and a secondary comparative evaluation is performed with the performance threshold X, the data collection situation is analyzed, and an iterative strategy is executed.
