Intelligent environment monitoring device integrating NB-IoT (Narrow Band Internet of Things) and embedded system

Abstract

The invention provides an intelligent environment monitoring device integrating NB-IoT (Narrow Band Internet of Things) and an embedded system, which comprises a sensor module comprising a temperature, humidity and air quality sensor unit, and an embedded processing module comprising a data receiving, processing and integrating unit, an NB-IoT communication module and a power supply module. The device collects environment data, processes and fuses the data, and sends the data to a remote monitoring end through NB-IoT. According to the invention, real-time acquisition, processing and remote transmission of environment data can be realized, and the accuracy and efficiency of environment monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent environment monitoring technology, and more specifically, to an intelligent environment monitoring device integrating NB-IoT and an embedded system. Background Art

[0002] The intelligent environmental monitoring system is a technical system that uses modern information technology to monitor and control environmental factors in real time. These systems usually include key components such as high-precision sensor networks, big data analysis and prediction, and public participation and feedback. The high-precision sensor network can monitor the concentration of pollutants such as PM2.5, PM10, sulfur dioxide, nitrogen dioxide, ozone, and meteorological parameters such as temperature, humidity, wind speed, and wind direction in real time, and transmit the data wirelessly to the data center to form a real-time air quality map. Big data analysis and prediction technology uses massive environmental data, big data analysis and machine learning algorithms to identify pollution sources, predict air quality trends, and promptly detect pollution events and issue warnings. The public participation and feedback mechanism uses mobile applications equipped with the intelligent environmental monitoring platform to enable the public to view air quality information in real time, participate in environmental supervision, and even submit pollution clues, forming an environmental protection mechanism involving the joint participation of the government, enterprises, and the public.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: the existing environmental monitoring system may have limitations in remote data transmission, and cannot use the mobile phone network to remotely view information and adjust the upper and lower limits of data; at the same time, some systems may only know the data by viewing the screen, and lack the ability to remotely transmit data. In addition, the requirements for the real-time and accuracy of environmental data are getting higher and higher, and the existing technology may have deficiencies in data processing and analysis, and more efficient and intelligent solutions are needed to meet the needs of environmental monitoring. Summary of the invention

[0004] The present invention provides an intelligent environment monitoring device integrating NB-IoT and an embedded system, comprising: The sensor module is used to collect environmental data; the sensor module includes: a temperature sensor unit, used to collect environmental temperature data; a humidity sensor unit, used to collect environmental humidity data; an air quality sensor unit, used to collect environmental air quality data; An embedded processing module, connected to the sensor module, for receiving and processing environmental data collected by the sensor module; Embedded processing modules include: A data receiving unit, used for receiving environmental data transmitted by the sensor module; A data processing unit, used for preprocessing the received environmental data, including data cleaning and data format conversion; A data fusion unit is used to fuse a variety of environmental data using a specific algorithm; NB-IoT communication module, connected to the embedded processing module, is used to send the processed environmental data to the remote monitoring end; The power module is connected to the sensor module, the embedded processing module and the NB-IoT communication module respectively, and is used to supply power to each module. Furthermore, the data fusion unit adopts a weighted average fusion algorithm, and the steps are as follows: Assume the temperature data is , humidity data is , the air quality data is The corresponding weights are , , ,and ; Wherein, T is the ambient temperature data collected by the temperature sensor unit, H is the ambient humidity data collected by the humidity sensor unit, and Q is the ambient air quality data collected by the air quality sensor unit. is the weight corresponding to the temperature data, is the weight corresponding to the humidity data, is the weight corresponding to the air quality data; The temperature data is fused by weighted average algorithm. , humidity data , air quality data Fusion, the fused data ; Where F is the comprehensive environmental data after data fusion. The fused data ; Where F is the comprehensive environmental data after data fusion. Furthermore, the weight , , The method of determining is as follows: Based on the historical data of environmental monitoring, the impact of temperature, humidity and air quality data on comprehensive environmental assessment is statistically analyzed; Determined by normalization , , The specific value of . Furthermore, the data fusion process also includes the abnormal data judgment step: Set the temperature data threshold range to , the humidity data threshold range is , the air quality data threshold range is ;in, is the lower limit of the temperature data threshold, is the upper threshold of the temperature data, is the lower limit of humidity data threshold, is the upper limit of humidity data threshold, is the lower limit of the air quality data threshold, is the upper threshold of air quality data. If the collected temperature data T is not range, or the humidity data H is not range, or the air quality data Q is not If the data is within the range, it is determined to be abnormal data and marked.

[0005] 5. According to the intelligent environment monitoring device of claim 4, the method for processing abnormal data is: If the number of consecutive occurrences of abnormal data exceeds the set number N, an abnormal alarm message is sent to the remote monitoring terminal; At the same time, the data smoothing algorithm is used to correct the abnormal data. The formula of the data smoothing algorithm is:

[0006] in, For the corrected data, is the normal data of the previous moment, is the historical average value of this type of data, is the smoothing coefficient, and its value range is . Furthermore, a data standardization step is also included before data fusion: For temperature data T, the formula is used

[0007] Standardization is performed, where is the standardized temperature data; For humidity data H, the formula is used

[0008] Standardization is performed, where is the standardized humidity data; For air quality data Q, the formula is used

[0009] Standardization is performed, where The air quality data is standardized.

[0010] Furthermore, during the data fusion process, the weights are recalculated every preset time interval t. : Collect all normalized data within this time interval; Calculate the variance of temperature data , the variance of humidity data , the variance of air quality data ;in, is the variance of the temperature data in this time interval, is the variance of humidity data in this time interval, is the variance of the air quality data in this time interval.

[0011] According to the formula

[0012]

[0013]

[0014] Calculate new weights , and update the original weight; in, are the weights of the updated temperature, humidity and air quality data respectively. Furthermore, during the data fusion process, if the environmental data change amplitude is detected to exceed the set change threshold , then suspend data fusion and re-collect and verify the data: Re-collect the same type of data n times; Calculate the average value of these n times of data; Compare the average value with the original data. If the difference still exceeds , it is determined that the data acquisition device may be faulty, and a fault alarm message is sent to the remote monitoring terminal; is the set environmental data change threshold, and n is the number of times the data is recollected. Furthermore, after data fusion, the data reliability assessment step is also included: Calculate the deviation between the fused data and the original data, respectively

[0015] in, is the deviation between the fusion data and the original temperature data, is the deviation between the fused data and the original humidity data, is the deviation value between the fused data and the original air quality data.

[0016] If the deviation value The maximum value in exceeds the set reliability threshold , the data fusion results are marked, and the marking information is included in the subsequent data transmission so that the remote monitoring end can perform targeted analysis and processing; is the data reliability threshold that is set. Furthermore, the NB-IoT communication module includes: A data sending unit, used for sending the environmental data processed by the embedded processing module to a remote monitoring terminal; The signal receiving unit is used to receive control instructions sent by the remote monitoring terminal.

[0017] According to the above-mentioned embodiments of the present invention, at least the following beneficial effects are achieved: the intelligent environmental monitoring device can comprehensively collect environmental temperature, humidity and air quality data by integrating multiple sensor units, thereby providing more accurate environmental monitoring results. Its embedded processing module has the ability to pre-process and fuse data, and can effectively clean and convert the collected data to ensure that the data transmitted to the remote monitoring terminal is accurate and reliable. In addition, the device adopts NB-IoT communication technology, which can remotely monitor environmental conditions in real time, improving the timeliness and response speed of environmental monitoring.

[0018] The data fusion unit of the device adopts a weighted average fusion algorithm and dynamically adjusts the weights according to the historical data of environmental monitoring, so that the monitoring results are more in line with the actual environmental conditions. The application of abnormal data processing and data smoothing algorithms can reduce the impact of errors and outliers, and further improve the accuracy of the data. The device can also suspend data fusion when a sudden and significant change in environmental data is detected, and re-collect and verify it, effectively avoiding false alarms caused by equipment failure or temporary environmental changes, and can enhance the reliability and stability of monitoring results. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which: Figure 1 A schematic diagram of the structure of an intelligent environment monitoring device integrating NB-IoT and an embedded system provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0020] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0021] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0022] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0023] Reference below Figure 1 , Figure 1 This is a schematic diagram of the structure of an intelligent environment monitoring device that integrates NB-IoT and an embedded system provided by an embodiment of the present invention. Figure 1 As shown, an intelligent environment monitoring device 100 integrating NB-IoT and embedded system includes: The sensor module 101 is used to collect environmental data; The sensor module includes: a temperature sensor unit for collecting ambient temperature data; a humidity sensor unit for collecting ambient humidity data; an air quality sensor unit for collecting ambient air quality data; The embedded processing module 102 is connected to the sensor module and is used to receive and process the environmental data collected by the sensor module; The embedded processing module includes: a data receiving unit for receiving environmental data transmitted by the sensor module; a data processing unit for preprocessing the received environmental data, including data cleaning and data format conversion; a data fusion unit for fusing multiple environmental data using a specific algorithm; The NB-IoT communication module 103 is connected to the embedded processing module and is used to send the processed environmental data to the remote monitoring terminal; The power module 104 is connected to the sensor module, the embedded processing module and the NB-IoT communication module respectively, and is used to supply power to each module. It should be noted that the intelligent environment monitoring device includes a sensor module, an embedded processing module, an NB-IoT communication module and a power module, wherein the sensor module is responsible for collecting environmental data, including parameters such as temperature, humidity and air quality. The embedded processing module is used to receive and process the data collected by the sensor module, while the NB-IoT communication module is responsible for sending the processed data to the remote monitoring terminal. The power module provides the required power for each module.

[0024] Specifically, the sensor module consists of a temperature sensor unit, a humidity sensor unit and an air quality sensor unit, which are used to collect the temperature, humidity and air quality data of the environment respectively. The embedded processing module includes a data receiving unit, a data processing unit and a data fusion unit, wherein the data receiving unit is responsible for receiving the environmental data transmitted by the sensor module, the data processing unit pre-processes the received environmental data, including data cleaning and data format conversion, and the data fusion unit uses a specific algorithm to fuse multiple environmental data. The NB-IoT communication module includes a data sending unit and a signal receiving unit, which are used to send the processed environmental data and receive the control instructions of the remote monitoring end respectively.

[0025] Preferably, the data fusion unit adopts a weighted average fusion algorithm, which calculates the comprehensive environmental data by assigning different weights to the temperature, humidity and air quality data. The weights are assigned based on the degree of influence of each parameter on the comprehensive environmental assessment, and these weights can be determined by statistically analyzing historical data and performing normalization processing. For example, if the temperature data has a greater impact on the environmental assessment, it may be assigned a higher weight.

[0026] Furthermore, in order to ensure the accuracy of the data, the device also includes an abnormal data judgment step, which identifies abnormal data by setting a threshold range and marks it. In this way, the device can not only provide accurate environmental monitoring data, but also detect and handle abnormal situations in a timely manner to ensure the reliability and effectiveness of the data.

[0027] In some embodiments, the data fusion unit adopts a weighted average fusion algorithm, and the steps are as follows: Assume the temperature data is , humidity data is , the air quality data is The corresponding weights are , , ,and ; Wherein, T is the ambient temperature data collected by the temperature sensor unit, H is the ambient humidity data collected by the humidity sensor unit, and Q is the ambient air quality data collected by the air quality sensor unit. is the weight corresponding to the temperature data, is the weight corresponding to the humidity data, is the weight corresponding to the air quality data.

[0028] The fused data ; Where F is the comprehensive environmental data after data fusion. It should be noted that this embodiment describes a data fusion unit of an intelligent environmental monitoring device, which uses a weighted average fusion algorithm to process the collected environmental data. The weighted average fusion algorithm is a multi-sensor data fusion technology that calculates comprehensive environmental data by assigning different weights to different sensor data. In this process, temperature data, humidity data, and air quality data correspond to T, H, and Q, respectively, and the corresponding weights are α, β, and γ, respectively, and satisfy the condition of α+β+γ=1.

[0029] Specifically, the data fusion unit first sets the weights of each environmental parameter, which are determined based on the historical data of environmental monitoring and the degree of influence of each parameter on the comprehensive environmental assessment. For example, if temperature has a greater impact on the environment, a higher weight may be given to temperature data. The weight determination can be achieved by normalizing the historical data to ensure that the sum of the weights is 1. The calculation formula for the fused data F is F=α×T+β×H+γ×Q, where F represents the fused comprehensive environmental data.

[0030] Preferably, in order to improve the accuracy of data fusion, the present embodiment also includes an abnormal data judgment step. By setting the threshold range of temperature, humidity and air quality data, abnormal data can be identified and marked. For example, if the collected temperature data T exceeds the preset range, the system will determine that the data is abnormal and perform corresponding processing. This abnormal data processing mechanism helps to improve the reliability of data fusion results and avoid the accuracy of the overall monitoring results being affected by individual abnormal values.

[0031] In some embodiments, the weight , , The method of determining is as follows: Based on the historical data of environmental monitoring, the impact of temperature, humidity and air quality data on comprehensive environmental assessment is statistically analyzed; Determined by normalization , , The specific value of . It should be noted that this embodiment relates to a weight determination method for a data fusion unit in an intelligent environment monitoring device. In this context, the weight determination method refers to determining the relative importance of each environmental parameter (such as temperature, humidity, and air quality) in a comprehensive assessment based on historical data of environmental monitoring, and assigning different weights accordingly. The weight is a numerical value that measures the degree of influence of each parameter on the comprehensive environmental assessment, and the specific value is determined through normalization processing.

[0032] Specifically, the determination of weights first requires the collection of environmental monitoring data within a certain time range, including historical data of temperature, humidity and air quality. Then, the initial weights of each parameter are determined by statistically analyzing the degree of influence of these data on the comprehensive environmental assessment. Next, normalization is used to convert these initial weights into a set of weights with a sum of 1 to ensure the reasonable distribution of weights. Normalization is a mathematical method used to scale data so that it falls into a small specific interval, and is used in this embodiment to ensure that the sum of the weights is 1.

[0033] Preferably, the determination of the weights may also take into account the dynamic change characteristics of the environmental parameters. For example, an adaptive mechanism may be provided so that the weights can be dynamically adjusted according to the latest environmental data.

[0034] Furthermore, expert experience or additional environmental influencing factors, such as seasonal changes, special events, etc., can be introduced to fine-tune the weight determination process to improve the accuracy and adaptability of environmental monitoring. These alternatives can make the weight determination more flexible and accurate, thereby improving the reliability of data fusion results.

[0035] In some embodiments, the data fusion process further includes an abnormal data determination step: Set the temperature data threshold range to , the humidity data threshold range is , the air quality data threshold range is ;in, is the lower limit of the temperature data threshold, is the upper threshold of the temperature data, is the lower limit of humidity data threshold, is the upper limit of humidity data threshold, is the lower limit of the air quality data threshold, is the upper threshold of air quality data. If the collected temperature data T is not range, or the humidity data H is not range, or the air quality data Q is not If the data is within the range, it is determined to be abnormal data and marked.

[0036] It should be noted that this embodiment describes in detail the method for judging abnormal data in the intelligent environment monitoring device. Abnormal data judgment refers to identifying data points that exceed the normal fluctuation range by setting a threshold range. In this context, the temperature data threshold range, humidity data threshold range and air quality data threshold range refer to the normal value ranges of temperature, humidity and air quality parameters respectively. The lower threshold and the upper threshold are the boundary values ​​for determining whether the data is abnormal.

[0037] Specifically, the abnormal data judgment step involves setting a specific threshold range for each environmental data. For example, the threshold range of temperature data may be set to [-10°C, 50°C], the threshold range of humidity data may be set to [0%, 100%], and the threshold range of air quality data may be set to [0, 500μg / m³]. These threshold ranges are determined based on historical monitoring data and the normal fluctuation range of environmental parameters. If the collected data exceeds these ranges, the system will determine that the data is abnormal and mark it.

[0038] Preferably, the method for processing abnormal data can be further refined. For example, if the temperature data collected three times in a row exceeds the set threshold range, the system will not only mark these data as abnormal, but also trigger the alarm mechanism to send abnormal alarm information to the remote monitoring terminal. At the same time, the system can use a data smoothing algorithm to correct the abnormal data to reduce misjudgment caused by instantaneous fluctuations.

[0039] Furthermore, the formula of the data smoothing algorithm can be

[0040] in For the corrected data, For the currently collected data, is the historical average, is the smoothing coefficient, and its value range is This approach helps to improve the stability and reliability of monitoring data.

[0041] In some embodiments, the method for processing abnormal data is: If the number of consecutive occurrences of abnormal data exceeds the set number N, an abnormal alarm message is sent to the remote monitoring terminal; At the same time, the data smoothing algorithm is used to correct the abnormal data. The formula of the data smoothing algorithm is:

[0042] in, For the corrected data, is the normal data of the previous moment, is the historical average value of this type of data, is the smoothing coefficient, and its value range is . It should be noted that this embodiment describes a method for processing abnormal data in an intelligent environment monitoring device. Abnormal data refers to data points that are beyond the normal range, which may be caused by sensor failure, environmental changes or other abnormal factors. The processing of abnormal data is crucial to ensure the accuracy and reliability of environmental monitoring data. In this embodiment, the processing of abnormal data includes setting the number of consecutive occurrences and applying a data smoothing algorithm.

[0043] Specifically, the abnormal data processing method first involves setting a threshold value N to determine whether the abnormal data has appeared continuously for more than the set number of times. For example, if the temperature data exceeds the normal range for 5 consecutive times, it is considered that the number of consecutive occurrences of the abnormal data exceeds the set number N. At this time, the device will send an abnormal alarm message to the remote monitoring end. At the same time, a data smoothing algorithm is used to correct the abnormal data to reduce the impact of the abnormal data on the overall monitoring results.

[0044] The formula of the data smoothing algorithm can be expressed as

[0045] in For the corrected data, For the currently collected data, is the normal data of the previous moment, is the smoothing coefficient, and its value range is .

[0046] Preferably, the smoothing coefficient in the data smoothing algorithm is It can be adjusted according to the actual monitoring environment and data characteristics. For example, if the environment changes frequently, a smaller To reduce the smoothing effect and keep the data real-time. On the contrary, if the environment changes relatively smoothly, you can choose a larger value. value to enhance the smoothing effect and reduce data fluctuations.

[0047] Furthermore, it can also be dynamically adjusted based on historical data and statistical analysis results. Through these detailed operation steps and alternative solutions, the intelligent environmental monitoring device can further improve its ability to process abnormal data and ensure the accuracy and reliability of environmental monitoring data.

[0048] In some embodiments, a data normalization step is also included before data fusion: For temperature data T, the formula is used

[0049] Standardization is performed, where is the standardized temperature data; For humidity data H, the formula is used

[0050] Standardization is performed, where is the standardized humidity data; For air quality data Q, the formula is used

[0051] Standardization is performed, where The air quality data is standardized.

[0052] It should be noted that this embodiment describes in detail the data standardization steps in the intelligent environment monitoring device. Data standardization refers to converting the original data into a universal standard scale to eliminate the influence of different dimensions and magnitudes so that the data can be compared and integrated under the same standard. In this context, the standardized temperature data, humidity data and air quality data are respectively used , and express.

[0053] Specifically, the data normalization step involves processing the temperature, humidity, and air quality data using specific formulas. For example, for temperature data T, the normalization formula is

[0054] in and are the minimum and maximum values ​​of the temperature data, respectively. Similarly, the humidity data H and air quality data Q are also processed using corresponding standardized formulas. These formulas convert the raw data into values ​​in the [0, 1] interval, so that data from different sensors can be compared and fused on the same scale.

[0055] Preferably, the specific parameters of data standardization can be adjusted according to the actual environment and historical data. and It can be set according to the actual observation range of historical temperature data. In addition, these parameters can be dynamically adjusted according to the seasonal characteristics of environmental changes to adapt to environmental changes in different seasons. This dynamic adjustment can improve the adaptability and accuracy of data standardization, so that the data fusion results can more accurately reflect the actual environmental conditions.

[0056] In some embodiments, during the data fusion process, the weight is recalculated every preset time interval t. : Collect all normalized data within this time interval; Calculate the variance of temperature data , the variance of humidity data , the variance of air quality data ;in, is the variance of the temperature data in this time interval, is the variance of humidity data in this time interval, is the variance of the air quality data in this time interval.

[0057] According to the formula

[0058]

[0059]

[0060] Calculate new weights , and update the original weight; in, are the weights of the updated temperature, humidity and air quality data respectively. It should be noted that this embodiment describes a calculation method for weight update in an intelligent environmental monitoring device. In this context, weight update refers to dynamically adjusting the weights of various environmental parameters (temperature, humidity, air quality) in data fusion according to the variance changes of environmental data, so as to more accurately reflect the degree of influence of each parameter on the comprehensive environmental assessment. Variance is a statistic that measures the degree of data dispersion. The larger the variance, the greater the fluctuation of the data.

[0061] Specifically, the calculation of weight update first requires collecting all standardized data within a certain time interval and calculating the variance of the temperature data , the variance of humidity data , the variance of air quality data Then, according to the formula

[0062]

[0063]

[0064] Calculate new weights , , , and update the original weights. These formulas use the inverse of the variance as the basis for calculating the weights, reflecting that the parameters with smaller variances (more stable data) should have greater weights in data fusion.

[0065] Preferably, the calculation method for weight update can be further refined or an alternative solution can be provided. For example, it can be considered to introduce expert experience to fine-tune the calculated weights to adapt to specific environmental monitoring needs.

[0066] Furthermore, a threshold for weight update can be set, and the weight update is performed only when the variance change exceeds the threshold, so as to reduce the consumption of computing resources and improve the response speed of the system. These alternatives can make the weight update process more flexible and efficient, and better adapt to environmental changes and monitoring needs.

[0067] In some embodiments, during the data fusion process, if a sudden and significant change in the environmental data is detected (the change exceeds a set change threshold), ), then the data fusion is suspended and the data is re-collected and verified: Re-collect the same type of data n times; Calculate the average value of these n times of data; Compare the average value with the original data. If the difference still exceeds , it is determined that the data acquisition device may be faulty, and a fault alarm message is sent to the remote monitoring terminal; is the set environmental data change threshold, and n is the number of times the data is recollected. It should be noted that this embodiment describes a method for processing sudden changes in environmental data after data fusion in an intelligent environmental monitoring device. Sudden changes in environmental data refer to large changes in environmental parameters in a short period of time, which may be caused by equipment failure or real drastic changes in environmental conditions. Setting a change threshold refers to a preset standard for determining whether data changes exceed the normal range. When it is detected that the data change exceeds this threshold, the system will suspend data fusion and start the re-collection and verification process.

[0068] Specifically, the operation steps include suspending the data fusion process and then recollecting the same type of data when a sudden and significant change in environmental data is detected. For example, if the temperature data suddenly rises and exceeds the set change threshold in a short period of time, the system will suspend fusion and recollect the temperature data n times, where n is the preset number of collections, which is usually determined based on actual monitoring needs and data stability. Then, the average value of these n data is calculated and compared with the original data to determine whether the data acquisition device may have failed.

[0069] Preferably, in order to improve the accuracy and reliability of the processing of environmental data mutations, the operation steps can be further refined or alternatives can be provided. For example, multiple change thresholds can be set, and different response measures can be taken for different levels of data changes. In addition, intelligent algorithms can be introduced to analyze the re-collected data to automatically identify and exclude occasional extreme values, thereby reducing false alarms. These refined steps and alternatives help improve the responsiveness and processing efficiency of intelligent environmental monitoring devices to environmental data mutations.

[0070] In some embodiments, after data fusion, a data reliability assessment step is also included: Calculate the deviation between the fused data and the original data, respectively

[0071] in, is the deviation between the fusion data and the original temperature data, is the deviation between the fused data and the original humidity data, is the deviation value between the fused data and the original air quality data.

[0072] If the deviation value The maximum value in exceeds the set reliability threshold , the data fusion results are marked, and the marking information is included in the subsequent data transmission so that the remote monitoring end can perform targeted analysis and processing; is the data reliability threshold that is set. It should be noted that this embodiment describes the data reliability assessment step after data fusion in the intelligent environment monitoring device. Data reliability assessment refers to judging the accuracy of the fusion result by calculating the deviation value between the fused data and each original data. The deviation value is an indicator to measure the difference between the fused data and the original data. If the deviation value exceeds the set reliability threshold, the data fusion result is considered unreliable.

[0073] Specifically, the data reliability evaluation step includes calculating the deviation between the fused data F and the original temperature data T, the original humidity data H, and the original air quality data Q. The calculation formulas for the deviation values ​​are: , and

[0074] in , and are the deviation values ​​between the fused data and the original data of temperature, humidity and air quality, respectively. , and are the corresponding weights respectively. The reliability threshold set It is a preset value used to determine whether the deviation value is within the acceptable range.

[0075] Preferably, the data reliability assessment step can be further refined or alternative solutions can be provided. For example, the concept of confidence interval in statistics can be introduced to determine the reliability of the fused data by calculating the confidence interval of the fused data. In addition, machine learning methods such as random forests or neural networks can be used to learn historical data to dynamically adjust the reliability threshold. , making it more adaptable to actual environmental changes. These refined steps and alternatives help to improve the accuracy of data fusion results and the flexibility of reliability assessment.

[0076] In some embodiments, the NB-IoT communication module includes: A data sending unit, used for sending the environmental data processed by the embedded processing module to a remote monitoring terminal; The signal receiving unit is used to receive control instructions sent by the remote monitoring terminal.

[0077] It should be noted that this embodiment describes the specific functions and operations of the NB-IoT communication module in the intelligent environment monitoring device. The NB-IoT communication module is a key part of the device responsible for data transmission and receiving remote commands. The module sends the processed environmental data to the remote monitoring end through the wireless network and receives control commands from the monitoring end to achieve remote monitoring and management.

[0078] Specifically, the NB-IoT communication module consists of two main parts: a data transmission unit and a signal receiving unit. The data transmission unit is responsible for sending the environmental data processed by the embedded processing module to the remote monitoring end through the NB-IoT network, while the signal receiving unit is used to receive control instructions sent by the remote monitoring end, which may include adjustments to sensor parameters, changes in data collection frequency, etc. In actual settings, the parameter configuration of the data transmission unit and the signal receiving unit needs to be determined according to the specific network environment and data transmission requirements, including transmission rate, signal strength, data packet size, etc.

[0079] Preferably, the operation steps of the NB-IoT communication module can be further refined or alternative solutions can be provided. For example, data encryption and security authentication mechanisms can be introduced to ensure the security and reliability of transmitted data.

[0080] Furthermore, the module's automatic diagnosis function can also be set to quickly locate and repair problems when there are problems with the communication link. These detailed steps and alternatives help improve the stability and practicality of the NB-IoT communication module and ensure that the intelligent environmental monitoring device can operate stably in various environments.

[0081] The above-mentioned embodiments of the present invention have the following beneficial effects: The intelligent environmental monitoring device described in the present invention can realize real-time collection, processing and remote transmission of environmental data by combining sensor modules, embedded processing modules and NB-IoT communication modules, and can improve the efficiency and accuracy of environmental monitoring. The data fusion unit adopts a weighted average fusion algorithm, which can dynamically adjust the weight of each environmental data according to historical data and normalization processing, so that the monitoring results are more accurate. In addition, the device also includes abnormal data judgment and processing steps, which can timely discover and correct abnormal data, avoid the spread of erroneous information, and enhance the reliability of monitoring data.

[0082] The present invention can further enhance the functionality and stability of the monitoring device. The data standardization step ensures that data from different sensors are compared and fused under the same standard, which can improve the scientific nature of data fusion. The method of updating weights in real time can dynamically adjust the weights according to the latest environmental data, so that the monitoring results are more in line with actual environmental changes. The device can also suspend fusion and re-verify when a significant change in data is detected, effectively preventing misjudgments caused by equipment failure or temporary environmental fluctuations. Finally, the data reliability evaluation step can evaluate the accuracy of the fused data, ensure the quality of data received by the remote monitoring end, and provide solid data support for subsequent environmental management and decision-making.

[0083] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0084] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. An intelligent environment monitoring device integrating NB-IoT and embedded system, characterized in that: include: The sensor module is used to collect environmental data; the sensor module includes: a temperature sensor unit, used to collect environmental temperature data; a humidity sensor unit, used to collect environmental humidity data; an air quality sensor unit, used to collect environmental air quality data; The embedded processing module is connected to the sensor module and is used to receive and process the environmental data collected by the sensor module; the embedded processing module includes: a data receiving unit, which is used to receive the environmental data transmitted by the sensor module; a data processing unit, which is used to pre-process the received environmental data, including data cleaning and data format conversion; A data fusion unit is used to fuse a variety of environmental data using a specific algorithm; NB-IoT communication module, connected to the embedded processing module, is used to send the processed environmental data to the remote monitoring end; The power module is connected to the sensor module, the embedded processing module and the NB-IoT communication module respectively, and is used to supply power to each module.

2. According to the intelligent environment monitoring device of claim 1, the data fusion unit adopts a weighted average fusion algorithm, and the steps are as follows: Assume the temperature data is , humidity data is , the air quality data is The corresponding weights are , , ,and ;in, T is the ambient temperature data collected by the temperature sensor unit, H is the ambient humidity data collected by the humidity sensor unit, Q is the ambient air quality data collected by the air quality sensor unit, is the weight corresponding to the temperature data, is the weight corresponding to the humidity data, is the weight corresponding to the air quality data; The temperature data is fused by weighted average algorithm. , humidity data , air quality data Fusion, the fused data ; Where F is the comprehensive environmental data after data fusion.

3. The intelligent environment monitoring device according to claim 2, wherein the weight , , The method of determining is as follows: Based on the historical data of environmental monitoring, the impact of temperature, humidity and air quality data on comprehensive environmental assessment is statistically analyzed; Determined by normalization , , The specific value of .

4. The intelligent environment monitoring device according to claim 3, further comprising an abnormal data judgment step during the data fusion process: Set the temperature data threshold range to , the humidity data threshold range is , the air quality data threshold range is ;in, is the lower limit of the temperature data threshold, is the upper threshold of the temperature data, is the lower limit of humidity data threshold, is the upper limit of humidity data threshold, is the lower limit of the air quality data threshold, is the upper threshold of air quality data.

5. If the collected temperature data T is not range, or the humidity data H is not range, or the air quality data Q is not If the data is within the range, it is determined to be abnormal data and marked.

6. According to the intelligent environment monitoring device of claim 4, the method for processing abnormal data is: If the number of consecutive occurrences of abnormal data exceeds the set number N, an abnormal alarm message is sent to the remote monitoring terminal; At the same time, the data smoothing algorithm is used to correct the abnormal data. The formula of the data smoothing algorithm is: in, For the corrected data, is the normal data of the previous moment, is the historical average value of this type of data, is the smoothing coefficient, and its value range is .

7. The intelligent environment monitoring device according to claim 2 further comprises a data standardization step before data fusion: For temperature data T, the formula is used Standardization is performed, where is the standardized temperature data; For humidity data H, the formula is used Standardization is performed, where is the standardized humidity data; For air quality data Q, the formula is used Standardization is performed, where The air quality data is standardized.

8. According to the intelligent environment monitoring device of claim 2, during the data fusion process, the weight is recalculated every preset time interval t. ,include: Collect all normalized data within this time interval; Calculate the variance of temperature data , the variance of humidity data , the variance of air quality data ;in, is the variance of the temperature data in this time interval, is the variance of humidity data in this time interval, is the variance of the air quality data in this time interval.

9. According to the formula Calculate new weights , and update the original weight; in, are the weights of the updated temperature, humidity and air quality data respectively.

10. The intelligent environment monitoring device according to claim 2, during the data fusion process, if the detected environmental data change amplitude exceeds the set change threshold , then suspend data fusion and re-collect and verify the data: Re-collect the same type of data n times; Calculate the average value of n data; Compare the average value with the original data. If the difference still exceeds , it is determined that the data acquisition device may be faulty, and a fault alarm message is sent to the remote monitoring terminal; is the set environmental data change threshold, and n is the number of times the data is recollected.

11. The intelligent environment monitoring device according to claim 2, wherein the temperature data is fused by a weighted average algorithm. , humidity data , air quality data After fusion, the data reliability assessment step is also included: Calculate the deviation between the fused data and the original data, respectively ； in, is the deviation between the fusion data and the original temperature data, is the deviation between the fused data and the original humidity data, is the deviation value between the fused data and the original air quality data.

12. If the deviation value The maximum value in exceeds the set reliability threshold , the data fusion results are marked, and the marking information is included in the subsequent data transmission so that the remote monitoring end can perform targeted analysis and processing; is the data reliability threshold that is set.

13. According to the intelligent environment monitoring device of claim 1, the NB-IoT communication module comprises: A data sending unit, used for sending the environmental data processed by the embedded processing module to a remote monitoring terminal; The signal receiving unit is used to receive control instructions sent by the remote monitoring terminal.

Images