Data acquisition and analysis method and system based on humidity sensor
By building a sensor network and optimizing data collection energy consumption, and using graph neural networks and deep neural networks to screen reliable data, the problems of high energy consumption and data anomalies in the humidity sensor network were solved, and low-energy and high-authenticity data collection was achieved.
Patent Information
- Application Number
- CN202411704003.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-26
- Publication Date
- 2025-09-30
- Estimated Expiration
- 2044-11-26
AI Technical Summary
The existing humidity sensor network consumes too much energy when collecting data and the collected data may be abnormal, affecting the authenticity of the data.
By building a sensor network, optimizing data collection energy consumption, and using graph neural networks and deep neural networks to build performance data prediction models, reliable sensor data can be screened out and abnormal data can be eliminated.
The data collection energy consumption of wireless sensor networks is reduced, ensuring the authenticity and accuracy of the collected data.
Smart Images
Figure CN119643789B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of humidity sensor data acquisition technology, and in particular to a humidity sensor-based data acquisition and analysis method and system. Background Art
[0002] Social activities are closely related to humidity. With the advancement of modernization, it is difficult to find a field unrelated to humidity. The technical requirements for humidity sensors vary depending on the application area. Humidity is the percentage of water in the air. It is used to indicate the humidity level of the air. A hygrometer is the simplest humidity sensor. Humidity sensors are mainly classified into two types: resistive and capacitive. A hygrometer features a film made of a humidity-sensitive material coated on a substrate. When water vapor in the air adsorbs onto the film, the resistivity and resistance of the element change, allowing humidity to be measured. Humidity-sensitive capacitors are generally made of polymer film capacitors. Common polymer materials include polystyrene, polyimide, and butyric acid acetate. When the ambient humidity changes, the dielectric constant of the hygrometer changes, causing the capacitance to also change. The change in capacitance is proportional to the relative humidity. Sensors have many application scenarios, such as agriculture and meteorology. However, sensors are often clustered to form wireless sensor networks. Currently, data collection using wireless sensors consumes excessive energy and can contain anomalies. Summary of the Invention
[0003] The present invention overcomes the deficiencies of the prior art and provides a data acquisition and analysis method and system based on a humidity sensor.
[0004] In order to achieve the above object, the technical solution adopted by the present invention is:
[0005] A first aspect of the present invention provides a data acquisition and analysis method based on a humidity sensor, comprising:
[0006] A sensor network is constructed by arranging humidity sensors in a target area, and an optimized sensor network is obtained by optimizing the data acquisition energy consumption of the sensor network;
[0007] The sensor data of each timestamp is obtained through the optimized sensor network, and the sensor data of each timestamp is evaluated and analyzed to obtain the reliable sensor data at each timestamp;
[0008] Collecting performance change characteristic data of the humidity sensor under various environmental factors within a preset time, and building a performance data prediction model based on the performance change characteristic data of the humidity sensor under various environmental factors within the preset time;
[0009] The performance data prediction model is used to predict the performance data of each humidity sensor under the environmental factors of the target area, and the reliable sensor data in each timestamp is further screened based on the performance data of each humidity sensor under the environmental factors of the target area to obtain the final sensor data.
[0010] Furthermore, in the data collection and analysis method based on humidity sensors, humidity sensors are arranged in the target area to construct a sensor network, and the data collection energy consumption of the sensor network is optimized to obtain an optimized sensor network, specifically:
[0011] Humidity sensors are arranged in a target area to construct a sensor network, the arrangement position of each humidity sensor is obtained, and the installation position of a data aggregation node is initialized, and a Euclidean distance value is calculated based on the arrangement position of the humidity sensors and the installation position of the data aggregation node;
[0012] Obtaining a data collection energy consumption value per unit Euclidean distance value through big data, and calculating a data collection energy consumption value for each data aggregation node based on the data collection energy consumption value per unit Euclidean distance value and the Euclidean distance value, and calculating a total data collection energy consumption value;
[0013] Setting a total data collection energy consumption threshold, and determining whether the total data collection energy consumption value is greater than the total data collection energy consumption threshold; if not, outputting the installation location of the data aggregation node, and optimizing according to the installation location of the data aggregation node to obtain an optimized sensor network;
[0014] If the total data collection energy consumption value is greater than the total data collection energy consumption threshold, the installation position of the data aggregation node is replanned until it is no greater than the total data collection energy consumption threshold, and the optimized sensor network is obtained according to the new installation position of the data aggregation node.
[0015] Furthermore, in the data collection and analysis method based on the humidity sensor, the sensor data of each timestamp is obtained through the optimized sensor network, and the sensor data of each timestamp is evaluated and analyzed to obtain the reliable sensor data in each timestamp, which specifically includes:
[0016] Obtain sensor data at each timestamp through the optimized sensor network, obtain the acquisition delay of the sensor data at each timestamp during acquisition, and set the acquisition delay threshold;
[0017] If the acquisition delay of the sensor data of each timestamp is greater than the acquisition delay threshold, the corresponding sensor data is regarded as untrustworthy sensor data;
[0018] If the acquisition delay of the sensor data of each timestamp is not greater than the acquisition delay threshold during acquisition, the corresponding sensor data is regarded as credible sensor data and the credible sensor data is output.
[0019] Furthermore, in the data collection and analysis method based on the humidity sensor, a performance data prediction model is constructed based on the performance change characteristic data of the humidity sensor under various environmental factors within the preset time, specifically:
[0020] Acquire performance change characteristic data of the humidity sensor under various environmental factors within a preset time, introduce a graph neural network, and input the performance change characteristic data of the humidity sensor under various environmental factors within the preset time into the graph neural network;
[0021] Taking the environmental factor as the first node and the performance characteristic data as the second node, constructing a directed description relationship, and connecting the first node and the second node based on the directed description relationship to construct a topological structure diagram;
[0022] Obtaining a relevant adjacency matrix based on the topological structure graph, building a performance data prediction model based on a deep neural network, and inputting the relevant adjacency matrix into the performance data prediction model for training;
[0023] When the prediction accuracy of the performance data prediction model is greater than a preset accuracy threshold, the training of the performance data prediction model is completed.
[0024] Furthermore, in the data collection and analysis method based on the humidity sensor, the performance data of each humidity sensor under the environmental factors of the target area is predicted by the performance data prediction model, specifically including:
[0025] Acquire performance change characteristic data of each temperature sensor within a preset time and the current working environment factors, and input the performance change characteristic data of each temperature sensor within the preset time and the current working environment factors into the performance data prediction model for prediction;
[0026] The performance data of each humidity sensor under the environmental factors of the target area at the current time stamp is obtained through prediction, and the performance data of each humidity sensor under the environmental factors of the target area at the current time stamp is output.
[0027] Furthermore, in the humidity sensor-based data collection and analysis method, the reliable sensor data in each timestamp is further screened based on the performance data of each humidity sensor under the environmental factors of the target area to obtain the final sensor data, specifically including:
[0028] Setting performance threshold data, and determining whether performance data of the humidity sensor under environmental factors of a target area is greater than the performance threshold data;
[0029] When the performance data of the humidity sensor under the environmental factors of the target area is greater than the performance threshold data, the corresponding credible sensor data is output as the final sensor data;
[0030] When the performance data of the humidity sensor under the environmental factors of the target area is not greater than the performance threshold data, the corresponding credible sensor data is eliminated, the credible sensor data is updated, and is output as the final sensor data.
[0031] A second aspect of the present invention provides a data acquisition and analysis system based on a humidity sensor, comprising a memory and a processor, wherein the memory includes a data acquisition and analysis method program based on a humidity sensor. When the data acquisition and analysis method program based on a humidity sensor is executed by the processor, the steps of any one of the data acquisition and analysis methods based on a humidity sensor are implemented.
[0032] A third aspect of the present invention provides a computer-readable storage medium, characterized in that it includes a data acquisition and analysis method program based on a humidity sensor. When the data acquisition and analysis method program based on a humidity sensor is executed by a processor, it implements any step of the data acquisition and analysis method based on a humidity sensor.
[0033] The present invention solves the defects existing in the background technology and has the following beneficial effects:
[0034] The present invention arranges humidity sensors in a target area to construct a sensor network, optimizes the data acquisition energy consumption of the sensor network, obtains an optimized sensor network, and then obtains sensor data at each timestamp through the optimized sensor network. The sensor data at each timestamp is evaluated and analyzed to obtain reliable sensor data at each timestamp, thereby collecting performance change characteristic data of the humidity sensors under various environmental factors within a preset time. A performance data prediction model is constructed based on the performance change characteristic data of the humidity sensors under various environmental factors within the preset time. Finally, the performance data prediction model is used to predict the performance data of each humidity sensor under the environmental factors of the target area. The reliable sensor data at each timestamp is further screened based on the performance data of each humidity sensor under the environmental factors of the target area to obtain final sensor data. By optimizing the wireless sensor network, the present invention can further reduce the energy consumption of wireless sensors during data acquisition, further eliminate abnormal data during data acquisition, and ensure the authenticity of the data collected by the humidity sensors. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying any creative work, they can also obtain drawings of other embodiments based on these drawings.
[0036] Figure 1 Shows the overall flow chart of the data acquisition and analysis method based on humidity sensor;
[0037] Figure 2 Shows a partial flow chart of the data acquisition and analysis method based on the humidity sensor;
[0038] Figure 3 Shows the system block diagram of the data acquisition and analysis system based on humidity sensor. DETAILED DESCRIPTION
[0039] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.
[0040] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.
[0041] like Figure 1 As shown, the first aspect of the present invention provides a data acquisition and analysis method based on a humidity sensor, comprising:
[0042] S102: constructing a sensor network by arranging humidity sensors in the target area, and optimizing the data acquisition energy consumption of the sensor network to obtain an optimized sensor network;
[0043] S104: Obtain sensor data at each timestamp through the optimized sensor network, and obtain credible sensor data at each timestamp by evaluating and analyzing the sensor data at each timestamp;
[0044] S106: Collecting performance change characteristic data of the humidity sensor under various environmental factors within a preset time, and building a performance data prediction model based on the performance change characteristic data of the humidity sensor under various environmental factors within the preset time;
[0045] S108: Predict the performance data of each humidity sensor under the environmental factors of the target area through the performance data prediction model, and further screen the reliable sensor data in each timestamp based on the performance data of each humidity sensor under the environmental factors of the target area to obtain the final sensor data.
[0046] It should be noted that the present invention can further reduce the energy consumption of wireless sensors during data collection by optimizing the wireless sensor network, and can further clear abnormal data during data collection, thereby ensuring the authenticity of the data collected by the humidity sensor.
[0047] Furthermore, in the data collection and analysis method based on humidity sensors, humidity sensors are arranged in the target area to construct a sensor network, and the data collection energy consumption of the sensor network is optimized to obtain an optimized sensor network, specifically:
[0048] By arranging humidity sensors in the target area, building a sensor network, obtaining the layout position of each humidity sensor, and initializing the installation position of the data aggregation node, the Euclidean distance value is calculated based on the layout position of the humidity sensors and the installation position of the data aggregation node;
[0049] Obtain the data collection energy consumption value per unit Euclidean distance value through big data, calculate the data collection energy consumption value of each data aggregation node based on the data collection energy consumption value per unit Euclidean distance value and the Euclidean distance value, and calculate the total data collection energy consumption value;
[0050] Set a total data collection energy consumption threshold, and determine whether the total data collection energy consumption value is greater than the total data collection energy consumption threshold. If not, output the installation location of the data aggregation node, optimize according to the installation location of the data aggregation node, and obtain the optimized sensor network;
[0051] If the total data collection energy consumption value is greater than the total data collection energy consumption threshold, the installation position of the data aggregation node is replanned until it is no greater than the total data collection energy consumption threshold, and the optimized sensor network is obtained according to the new installation position of the data aggregation node.
[0052] It should be noted that, during use, the data collected by several wireless sensors are aggregated to a data aggregation node and then uniformly transmitted to a computer remote control terminal. The greater the Euclidean distance between the layout position of the humidity sensor and the installation position of the data aggregation node, the higher the energy consumption. By optimizing the energy consumption of the sensor network through this method, the energy consumption during data collection can be reduced.
[0053] Furthermore, in the data collection and analysis method based on the humidity sensor, the sensor data of each timestamp is obtained through the optimized sensor network, and the sensor data of each timestamp is evaluated and analyzed to obtain the reliable sensor data in each timestamp, which specifically includes:
[0054] Obtain sensor data at each timestamp through the optimized sensor network, obtain the acquisition delay of the sensor data at each timestamp during acquisition, and set the acquisition delay threshold;
[0055] If the collection delay of the sensor data of each timestamp is greater than the collection delay threshold, the corresponding sensor data will be regarded as untrustworthy sensor data;
[0056] If the collection delay of the sensor data of each timestamp is not greater than the collection delay threshold during collection, the corresponding sensor data is regarded as credible sensor data and the credible sensor data is output.
[0057] like Figure 2 As shown, further, in the data collection and analysis method based on the humidity sensor, a performance data prediction model is constructed based on the performance change characteristic data of the humidity sensor under various environmental factors within a preset time, specifically:
[0058] S202: Obtaining characteristic data of performance changes of the humidity sensor under various environmental factors within a preset time, and introducing a graph neural network to input the characteristic data of performance changes of the humidity sensor under various environmental factors within the preset time into the graph neural network;
[0059] S204: Taking the environmental factor as the first node and the performance characteristic data as the second node, constructing a directed description relationship, and connecting the first node and the second node based on the directed description relationship to construct a topology diagram;
[0060] S206: Obtaining a relevant adjacency matrix based on the topological structure graph, building a performance data prediction model based on a deep neural network, and inputting the relevant adjacency matrix into the performance data prediction model for training;
[0061] S208: When the prediction accuracy of the performance data prediction model is greater than the preset accuracy threshold, the training of the performance data prediction model is completed.
[0062] It should be noted that the performance of humidity sensors under different environmental factors is different. For example, in acidic soil environment, alkaline soil environment, and acid rain environment, the performance in acidic soil environment, alkaline soil environment, and acid rain environment is often abnormal, that is, the collected data may be abnormal. The performance data includes sensitivity performance data, response time, humidity sensing characteristic quantity, humidity temperature coefficient and other data.
[0063] Furthermore, in the data collection and analysis method based on the humidity sensor, the performance data of each humidity sensor under the environmental factors of the target area is predicted by the performance data prediction model, specifically including:
[0064] Obtaining performance change characteristic data of each temperature sensor within a preset time and the current working environment factors, and inputting the performance change characteristic data of each temperature sensor within the preset time and the current working environment factors into a performance data prediction model for prediction;
[0065] Through prediction, the performance data of each humidity sensor under the environmental factors of the target area at the current timestamp is obtained, and the performance data of each humidity sensor under the environmental factors of the target area at the current timestamp is output.
[0066] Furthermore, in the humidity sensor-based data collection and analysis method, the reliable sensor data in each timestamp is further screened based on the performance data of each humidity sensor under the environmental factors of the target area to obtain the final sensor data, specifically including:
[0067] Setting performance threshold data and determining whether the performance data of the humidity sensor under the environmental factors of the target area is greater than the performance threshold data;
[0068] When the performance data of the humidity sensor under the environmental factors of the target area is greater than the performance threshold data, the corresponding reliable sensor data is output as the final sensor data;
[0069] When the performance data of the humidity sensor under the environmental factors of the target area is not greater than the performance threshold data, the corresponding credible sensor data is eliminated, the credible sensor data is updated, and is output as the final sensor data.
[0070] It should be noted that this method can eliminate abnormal data and ensure the authenticity of the sensor data.
[0071] In addition, the method further comprises:
[0072] Obtain network fluctuation data information of sensor networks under various influencing factors during data transmission through big data, and build a network fluctuation data prediction model based on deep neural networks;
[0073] Inputting the network fluctuation data information of the sensor network when performing data transmission under the various influencing factors into the network fluctuation data prediction model for training, and obtaining a trained network fluctuation data prediction model;
[0074] Acquiring influencing factor data in a target area, and inputting the influencing factor data in the target area into the trained network fluctuation data prediction model for prediction, thereby acquiring network fluctuation data in the target area;
[0075] The collection delay of the sensor data of each timestamp during collection is updated according to the network fluctuation data in the target area, and the sensor data that needs to be eliminated is updated.
[0076] It should be noted that due to different influencing factors, the network fluctuation data information (information transmission speed) of the sensor network during data transmission is different, including temperature, humidity and other data. Different information transmission speeds will lead to different data collection delays. This method fully considers the network fluctuation problem and timely updates the collection delay of the sensor data of each timestamp during collection, further ensuring the authenticity of the sensor data obtained.
[0077] like Figure 3 As shown, the second aspect of the present invention provides a data acquisition and analysis system 4 based on a humidity sensor, including a memory 41 and a processor 42. The memory 41 includes a data acquisition and analysis method program based on the humidity sensor. When the data acquisition and analysis method program based on the humidity sensor is executed by the processor 42, it includes:
[0078] By arranging humidity sensors in the target area, a sensor network is constructed, and the energy consumption of data collection of the sensor network is optimized to obtain an optimized sensor network;
[0079] The sensor data of each timestamp is obtained through the optimized sensor network, and the sensor data of each timestamp is evaluated and analyzed to obtain the reliable sensor data at each timestamp;
[0080] Collecting performance change characteristic data of the humidity sensor under various environmental factors within a preset time, and building a performance data prediction model based on the performance change characteristic data of the humidity sensor under various environmental factors within the preset time;
[0081] The performance data prediction model is used to predict the performance data of each humidity sensor under the environmental factors of the target area. The reliable sensor data in each timestamp is further screened based on the performance data of each humidity sensor under the environmental factors of the target area to obtain the final sensor data.
[0082] Furthermore, in the data acquisition and analysis system based on humidity sensors, humidity sensors are arranged in the target area to construct a sensor network, and the data acquisition energy consumption of the sensor network is optimized to obtain an optimized sensor network, specifically:
[0083] By arranging humidity sensors in the target area, building a sensor network, obtaining the layout position of each humidity sensor, and initializing the installation position of the data aggregation node, the Euclidean distance value is calculated based on the layout position of the humidity sensors and the installation position of the data aggregation node;
[0084] Obtain the data collection energy consumption value per unit Euclidean distance value through big data, calculate the data collection energy consumption value of each data aggregation node based on the data collection energy consumption value per unit Euclidean distance value and the Euclidean distance value, and calculate the total data collection energy consumption value;
[0085] Set a total data collection energy consumption threshold, and determine whether the total data collection energy consumption value is greater than the total data collection energy consumption threshold. If not, output the installation location of the data aggregation node, optimize according to the installation location of the data aggregation node, and obtain the optimized sensor network;
[0086] If the total data collection energy consumption value is greater than the total data collection energy consumption threshold, the installation position of the data aggregation node is replanned until it is no greater than the total data collection energy consumption threshold, and the optimized sensor network is obtained according to the new installation position of the data aggregation node.
[0087] It should be noted that, during use, the data collected by several wireless sensors are aggregated to a data aggregation node and then uniformly transmitted to a computer remote control terminal. The greater the Euclidean distance between the layout position of the humidity sensor and the installation position of the data aggregation node, the higher the energy consumption. By optimizing the energy consumption of the sensor network through this method, the energy consumption during data collection can be reduced.
[0088] Furthermore, in the humidity sensor-based data acquisition and analysis system, the sensor data at each timestamp is obtained through the optimized sensor network. The sensor data at each timestamp is evaluated and analyzed to obtain reliable sensor data at each timestamp, specifically including:
[0089] Obtain sensor data at each timestamp through the optimized sensor network, obtain the acquisition delay of the sensor data at each timestamp during acquisition, and set the acquisition delay threshold;
[0090] If the collection delay of the sensor data of each timestamp is greater than the collection delay threshold, the corresponding sensor data will be regarded as untrustworthy sensor data;
[0091] If the collection delay of the sensor data of each timestamp is not greater than the collection delay threshold during collection, the corresponding sensor data is regarded as credible sensor data and the credible sensor data is output.
[0092] Furthermore, in the data acquisition and analysis system based on the humidity sensor, a performance data prediction model is constructed based on the performance change characteristic data of the humidity sensor under various environmental factors within a preset time, specifically:
[0093] Obtain performance change characteristic data of the humidity sensor under various environmental factors within a preset time, and introduce a graph neural network to input the performance change characteristic data of the humidity sensor under various environmental factors within the preset time into the graph neural network;
[0094] Taking the environmental factor as the first node and the performance characteristic data as the second node, a directed description relationship is constructed, and the first node and the second node are connected based on the directed description relationship to construct a topological structure diagram;
[0095] Obtain the relevant adjacency matrix based on the topological structure graph, build a performance data prediction model based on a deep neural network, and input the relevant adjacency matrix into the performance data prediction model for training;
[0096] When the prediction accuracy of the performance data prediction model is greater than a preset accuracy threshold, the training of the performance data prediction model is completed.
[0097] It should be noted that the performance of humidity sensors in different environments is different. For example, in acidic soil environment, alkaline soil environment, and acid rain environment, the performance in acidic soil environment, alkaline soil environment, and acid rain environment is often abnormal, that is, the collected data may be abnormal. The performance data includes sensitivity performance data, response time, humidity sensing characteristic quantity, humidity temperature coefficient and other data.
[0098] Furthermore, in the humidity sensor-based data acquisition and analysis system, the performance data of each humidity sensor under the environmental factors of the target area is predicted by the performance data prediction model, specifically including:
[0099] Obtaining performance change characteristic data of each temperature sensor within a preset time and the current working environment factors, and inputting the performance change characteristic data of each temperature sensor within the preset time and the current working environment factors into a performance data prediction model for prediction;
[0100] Through prediction, the performance data of each humidity sensor under the environmental factors of the target area at the current timestamp is obtained, and the performance data of each humidity sensor under the environmental factors of the target area at the current timestamp is output.
[0101] Furthermore, in the humidity sensor-based data acquisition and analysis system, the reliable sensor data in each timestamp is further screened based on the performance data of each humidity sensor under the environmental factors of the target area to obtain the final sensor data, specifically including:
[0102] Setting performance threshold data and determining whether the performance data of the humidity sensor under the environmental factors of the target area is greater than the performance threshold data;
[0103] When the performance data of the humidity sensor under the environmental factors of the target area is greater than the performance threshold data, the corresponding reliable sensor data is output as the final sensor data;
[0104] When the performance data of the humidity sensor under the environmental factors of the target area is not greater than the performance threshold data, the corresponding credible sensor data is eliminated, the credible sensor data is updated, and is output as the final sensor data.
[0105] It should be noted that this method can eliminate abnormal data and ensure the authenticity of the sensor data.
[0106] The third aspect of the present invention provides a computer-readable storage medium, characterized in that it includes a data acquisition and analysis method program based on a humidity sensor. When the data acquisition and analysis method program based on a humidity sensor is executed by a processor, it implements any step of the data acquisition and analysis method based on a humidity sensor.
[0107] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0108] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.
[0109] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0110] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.
[0111] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.
[0112] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.
Claims
1. A data acquisition and analysis method based on a humidity sensor, characterized in that: include: A sensor network is constructed by arranging humidity sensors in a target area, and an optimized sensor network is obtained by optimizing the data acquisition energy consumption of the sensor network; The sensor data of each timestamp is obtained through the optimized sensor network, and the sensor data of each timestamp is evaluated and analyzed to obtain the reliable sensor data at each timestamp; Collecting performance change characteristic data of the humidity sensor under various environmental factors within a preset time, and building a performance data prediction model based on the performance change characteristic data of the humidity sensor under various environmental factors within the preset time; Predicting the performance data of each humidity sensor under the environmental factors of the target area using the performance data prediction model, and further screening the credible sensor data in each timestamp based on the performance data of each humidity sensor under the environmental factors of the target area to obtain final sensor data; By arranging humidity sensors in the target area to build a sensor network, and optimizing the data acquisition energy consumption of the sensor network, an optimized sensor network is obtained, specifically: Humidity sensors are arranged in a target area to construct a sensor network, the arrangement position of each humidity sensor is obtained, and the installation position of a data aggregation node is initialized, and a Euclidean distance value is calculated based on the arrangement position of the humidity sensors and the installation position of the data aggregation node; Obtaining a data collection energy consumption value per unit Euclidean distance value through big data, and calculating a data collection energy consumption value for each data aggregation node based on the data collection energy consumption value per unit Euclidean distance value and the Euclidean distance value, and calculating a total data collection energy consumption value; Setting a total data collection energy consumption threshold, and determining whether the total data collection energy consumption value is greater than the total data collection energy consumption threshold; if not, outputting the installation location of the data aggregation node, and optimizing according to the installation location of the data aggregation node to obtain an optimized sensor network; If the total data collection energy consumption value is greater than the total data collection energy consumption threshold, re-plan the installation position of the data aggregation node until it is no greater than the total data collection energy consumption threshold, and optimize according to the new installation position of the data aggregation node to obtain an optimized sensor network; Predicting the performance data of each humidity sensor under the environmental factors of the target area using the performance data prediction model specifically includes: Acquire performance change characteristic data of each humidity sensor within a preset time and the current working environment factors, and input the performance change characteristic data of each humidity sensor within the preset time and the current working environment factors into the performance data prediction model for prediction; The performance data of each humidity sensor under the environmental factors of the target area at the current time stamp is obtained through prediction, and the performance data of each humidity sensor under the environmental factors of the target area at the current time stamp is output.
2. The data acquisition and analysis method based on the humidity sensor according to claim 1 is characterized in that: The sensor data at each timestamp is obtained through the optimized sensor network. The sensor data at each timestamp is evaluated and analyzed to obtain the reliable sensor data at each timestamp. Specifically, the following steps are performed: Obtain sensor data at each timestamp through the optimized sensor network, obtain the acquisition delay of the sensor data at each timestamp during acquisition, and set the acquisition delay threshold; If the acquisition delay of the sensor data of each timestamp is greater than the acquisition delay threshold, the corresponding sensor data is regarded as untrustworthy sensor data; If the acquisition delay of the sensor data of each timestamp is not greater than the acquisition delay threshold during acquisition, the corresponding sensor data is regarded as credible sensor data and the credible sensor data is output.
3. The data acquisition and analysis method based on the humidity sensor according to claim 1 is characterized in that: A performance data prediction model is constructed based on the performance change characteristic data of the humidity sensor under various environmental factors within the preset time, specifically: Acquire performance change characteristic data of the humidity sensor under various environmental factors within a preset time, introduce a graph neural network, and input the performance change characteristic data of the humidity sensor under various environmental factors within the preset time into the graph neural network; Taking the environmental factor as the first node and the performance change characteristic data as the second node, constructing a directed edge description relationship, and connecting the first node and the second node based on the directed edge description relationship to construct a topological structure graph; Obtaining a relevant adjacency matrix based on the topological structure graph, constructing a performance data prediction model based on a graph neural network, and inputting the relevant adjacency matrix into the performance data prediction model for training; When the prediction accuracy of the performance data prediction model is greater than a preset accuracy threshold, the training of the performance data prediction model is completed.
4. The data acquisition and analysis method based on humidity sensor according to claim 1, characterized in that: The reliable sensor data in each timestamp is further screened based on the performance data of each humidity sensor under the environmental factors of the target area to obtain the final sensor data, specifically including: Setting performance threshold data, and determining whether performance data of the humidity sensor under environmental factors of a target area is greater than the performance threshold data; When the performance data of the humidity sensor under the environmental factors of the target area is greater than the performance threshold data, the corresponding credible sensor data is output as the final sensor data; When the performance data of the humidity sensor under the environmental factors of the target area is not greater than the performance threshold data, the corresponding credible sensor data is eliminated, the credible sensor data is updated, and is output as the final sensor data.
5. The data acquisition and analysis system based on humidity sensor is characterized by: It includes a memory and a processor, wherein the memory includes a data acquisition and analysis method program based on a humidity sensor, and when the data acquisition and analysis method program based on a humidity sensor is executed by the processor, the steps of the data acquisition and analysis method based on a humidity sensor as described in any one of claims 1 to 4 are implemented.
6. A computer-readable storage medium, characterized in that It includes a data acquisition and analysis method program based on a humidity sensor. When the data acquisition and analysis method program based on a humidity sensor is executed by a processor, the steps of the data acquisition and analysis method based on a humidity sensor according to any one of claims 1 to 4 are implemented.