Intelligent temperature adjusting system based on Internet of Things

Abstract

The invention provides an intelligent temperature adjusting system based on the Internet of Things, and relates to the technical field of intelligent adjustment, and the system comprises an instruction obtaining module which obtains a temperature detection instruction; the real-time temperature detection module activates a platinum resistor temperature sensor to dynamically detect and obtain the target real-time temperature of the target digestive system in real time based on the temperature detection instruction; the temperature transmission module transmits the target real-time temperature to the Internet of Things data processing holder; the temperature prediction module performs prediction analysis through the Internet of Things data processing holder to obtain a predicted target temperature at a target time; and if the predicted target temperature is not in the preset temperature threshold value, the intervention adjustment module sends a health adjustment instruction to perform health intervention adjustment on the target animal body. According to the method and the device, the technical problem of temperature regulation lag caused by lack of prediction analysis means in the prior art is solved, and the technical effects of improving the recognition accuracy and foresight of temperature abnormity and further improving the temperature regulation response speed are achieved.

Description

Technical Field

[0001] The present application relates to the field of intelligent regulation technology, and in particular to an intelligent temperature regulation system based on the Internet of Things. Background Art

[0002] The digestive system plays a key role in the process of energy acquisition and nutrient absorption in animals. The stability and suitability of its temperature directly affect the activity of digestive enzymes, the living environment of microorganisms, etc., and thus affect the function of the entire digestive system. At present, the temperature regulation of the animal digestive system is mainly measured by contact temperature measurement and non-contact temperature measurement, and then intervention and regulation are carried out. Although contact temperature measurement, such as rectal temperature measurement, has high accuracy, it is cumbersome to operate, easily causes animal stress response, and it is difficult to achieve continuous monitoring. Non-contact temperature measurement technology, such as infrared thermal imaging and temperature sensing system based on biosensors, has the advantages of non-invasiveness and rapidity, but it is easily interfered by environmental factors (such as temperature, humidity, wind speed), resulting in inaccurate measurement results and unable to directly reflect the actual temperature changes of the digestive system. At the same time, these methods can only monitor real-time temperature, resulting in managers taking remedial measures to intervene and adjust only after temperature abnormalities occur. The hysteresis of temperature regulation is difficult to meet the high-precision and high-efficiency requirements of modern breeding industry for animal health management. Summary of the invention

[0003] The present application provides an intelligent temperature control system based on the Internet of Things, which solves the technical problem of delayed temperature control due to the lack of predictive analysis methods in the prior art, and achieves the technical effect of improving the accuracy and foresight of identifying temperature anomalies, thereby improving the temperature control response speed.

[0004] In view of the above problems, the present application provides an intelligent temperature control system based on the Internet of Things, the system comprising: an instruction acquisition module, used to acquire a temperature detection instruction, wherein the temperature detection instruction refers to an instruction automatically issued by a microcontroller based on a predetermined detection frequency to perform temperature detection on a target digestive system of a target animal body; a real-time temperature detection module, used to activate a platinum resistance temperature sensor based on the temperature detection instruction, and dynamically detect the target real-time temperature of the target digestive system at real time through the platinum resistance temperature sensor; a temperature transmission module, used to transmit the target real-time temperature to an Internet of Things data processing gimbal through a LoRa communicator; a temperature prediction module, used to perform predictive analysis through the Internet of Things data processing gimbal to obtain a predicted target temperature at a target time; an intervention and adjustment module, used to issue a health adjustment instruction if the predicted target temperature is not at a predetermined temperature threshold, and perform health intervention and adjustment on the target animal body based on the health adjustment instruction.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application realizes automatic temperature detection triggering through the instruction acquisition module to ensure the regularity and continuity of monitoring; the real-time temperature detection module uses a high-precision platinum resistance sensor to dynamically capture temperature changes, providing an accurate data basis for subsequent temperature prediction and intervention adjustment; the temperature transmission module uses LoRa technology to efficiently transmit data to the cloud to achieve remote management and centralized processing of data; the temperature prediction module uses big data analysis and the computing power of the cloud platform to predict temperature change trends in advance and provide forward-looking decision support; the intervention adjustment module issues adjustment instructions in time according to the prediction results to achieve rapid and accurate intervention adjustment of animal body temperature. In summary, this application solves the problem of temperature regulation lag in the prior art, improves the accuracy and foresight of identifying temperature anomalies, thereby improving the temperature regulation response speed and realizing the intelligent and refined animal health management.

[0006] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 A schematic diagram of the structure of an intelligent temperature control system based on the Internet of Things provided in an embodiment of the present application.

[0008] Figure 2 A schematic diagram of a process for obtaining a predicted target temperature at a target time in an IoT-based intelligent temperature control system provided in an embodiment of the present application.

[0009] Explanation of the reference numerals: instruction acquisition module 10 , real-time temperature detection module 20 , temperature transmission module 30 , temperature prediction module 40 , intervention and adjustment module 50 . DETAILED DESCRIPTION

[0010] The embodiment of the present application solves the technical problem of delayed temperature regulation due to the lack of predictive analysis means in the prior art by providing an intelligent temperature control system based on the Internet of Things, thereby achieving the technical effect of improving the accuracy and foresight of identifying temperature anomalies and thereby improving the temperature control response speed.

[0011] like Figure 1 As shown, the embodiment of the present application provides an intelligent temperature adjustment system based on the Internet of Things, and the system includes: The instruction acquisition module 10 is used to acquire a temperature detection instruction, wherein the temperature detection instruction refers to an instruction automatically issued by the microcontroller based on a predetermined detection frequency to perform temperature detection on a target digestive system of a target animal body.

[0012] Specifically, the target animal body is a specific animal that needs to be temperature monitored, such as ruminants such as cattle and sheep. The target digestive system refers to the digestive system part of the target animal body that is of particular concern, such as the rumen of a cow. The scheduled detection frequency is a pre-set time interval for temperature detection of the target animal body. For example, if the animal's body temperature is set to be detected every 10 minutes, the 10 minutes is the scheduled detection frequency.

[0013] The microcontroller automatically issues a temperature detection instruction for the target digestive system of the target animal body according to a predetermined detection frequency. The instruction acquisition module 10 automatically receives the temperature detection instruction from the microcontroller and triggers the real-time temperature detection module 20 to perform temperature monitoring according to the temperature detection instruction, thereby ensuring the regularity and timeliness of the temperature detection of the specific digestive system of the target animal body, and laying a foundation for subsequent temperature monitoring and management.

[0014] The real-time temperature detection module 20 is used to activate the platinum resistance temperature sensor based on the temperature detection instruction, and dynamically detect the target real-time temperature of the target digestive system in real time through the platinum resistance temperature sensor.

[0015] Specifically, the platinum resistance temperature sensor is a temperature sensor with high precision and good stability. It uses the characteristic that the resistance of platinum material changes with temperature to sense temperature. After the instruction acquisition module 10 receives the temperature detection instruction and triggers the real-time temperature detection module 20, the real-time temperature detection module 20 activates the platinum resistance temperature sensor to monitor the temperature of the target animal's digestive system in real time. The platinum resistance temperature sensor has high-precision measurement capabilities, can dynamically sense temperature changes, and transmit data in real time. The platinum resistance temperature sensor dynamically measures the temperature of the target digestive system in real time by contacting or approaching the target digestive system of the target animal body, using the characteristic that its resistance changes with temperature, and obtains the target real-time temperature. For example, the platinum resistance temperature sensor is attached to a contactable position near the rumen of a cow to accurately measure the current temperature of the rumen.

[0016] By dynamically monitoring the body temperature of the target animal, the real-time temperature of the target digestive system can be obtained in real time, providing accurate current temperature data for subsequent transmission, prediction and intervention.

[0017] The temperature transmission module 30 is used to transmit the target real-time temperature to the IoT data processing cloud platform through the LoRa communicator.

[0018] Specifically, the LoRa communicator is a low-power, long-distance wireless communication device. The temperature transmission module 30 transmits the target real-time temperature data collected by the sensor to a remote IoT data processing platform. This IoT data processing platform is used to process IoT data and can receive, store, and analyze data from sensors. The LoRa communicator enables long-distance, low-power data transmission from the temperature detection end to the data processing platform, ensuring timely and stable data transmission and providing a data source for subsequent temperature prediction.

[0019] The temperature prediction module 40 is used to perform prediction analysis through the IoT data processing platform to obtain a predicted target temperature at a target time.

[0020] Specifically, after the IoT data processing platform receives the target real-time temperature from the temperature transmission module 30, the temperature prediction module 40 uses the algorithm inside the IoT data processing platform (e.g., based on historical data and machine learning algorithms, etc.) to predict and analyze the temperature of the target digestive system to obtain the predicted target temperature at the target time. The target time is a certain time point or time period in the future. For example, by analyzing the temperature data of the cow's rumen in the past week and combining it with the current real-time temperature, the temperature of the cow's rumen in the next two hours is predicted.

[0021] Temperature prediction analysis can help us know the future temperature conditions of the target animal in advance, providing a decision-making basis for early health intervention.

[0022] The intervention and regulation module 50 is used to issue a health regulation instruction if the predicted target temperature is not within a predetermined temperature threshold, and perform health intervention regulation on the target animal body based on the health regulation instruction.

[0023] Specifically, the predetermined temperature threshold is the upper and lower limits of the pre-set normal temperature range. Comparing the predicted target temperature with the predetermined temperature threshold, when the predicted target temperature obtained by the temperature prediction module 40 is not within the predetermined temperature threshold range, the intervention adjustment module 50 will issue a health adjustment instruction. This health adjustment instruction is used to adjust the environment in which the animal is located to ensure that the target digestive system of the target animal body remains within the predetermined temperature threshold range, such as adjusting the ambient temperature (such as turning on or off the heater, air conditioner, etc.), or performing special feeding and management operations on the animal (such as adjusting the feed formula, etc.). For example, the normal temperature range of the cow's rumen is 38°C to 40°C (predetermined temperature threshold). If the cow's rumen temperature is predicted to be lower than 38°C, the heater can be turned on to increase the ambient temperature or the cow can be provided with some high-calorie feed to regulate the cow's body temperature.

[0024] According to the prediction results, timely health intervention can be carried out on the animal body to prevent possible temperature abnormalities in advance, thereby improving the response speed and foresight of temperature regulation.

[0025] Further, such as Figure 2 As shown, the temperature prediction module 40 in the embodiment of the present application is also used to perform the following steps: Step P41: Obtain a preprocessor in the IoT data processing gimbal, wherein the preprocessor is embedded with a predetermined signal loss correction function.

[0026] Step P42: Perform loss correction analysis on the target real-time temperature according to the predetermined signal loss correction function to obtain the target actual temperature.

[0027] Step P43: Establishing a corresponding relationship between the target actual temperature and the real time to establish a target temperature signal timing.

[0028] Step P44: Perform predictive analysis on the target temperature signal timing through the IoT data processing gimbal to obtain the predicted target temperature at the target time.

[0029] Specifically, the temperature prediction module 40 first obtains a preprocessor from the IoT data processing cloud platform. A predetermined signal loss correction function is embedded in the preprocessor, which is used to correct the error in the temperature signal. For example, in a farm environment, the signal collected by the temperature sensor may be affected by environmental noise or sensor accuracy limitations. The role of the preprocessor is to perform preliminary processing on these signals to improve data quality.

[0030] The target real-time temperature is corrected using the predetermined signal loss correction function in the preprocessor. The correction function takes into account a variety of factors, such as signal attenuation, transmission distance, noise interference, etc., to obtain a more accurate target actual temperature. This target actual temperature is a corrected temperature value that is closer to the actual temperature inside the animal.

[0031] The corrected target actual temperature is corresponding to the real time, and the target actual temperatures are arranged in time sequence to form a target temperature signal time series. This target temperature signal time series can clearly show the temperature change trend of the target digestive system of the target animal body over time.

[0032] The computing power of the IoT data processing gimbal is used to perform predictive analysis on the target temperature signal time series. Through statistical analysis and machine learning algorithms (such as linear regression, time series analysis, or neural networks), time series data is modeled and predicted to estimate the temperature value at a certain point in the future.

[0033] Through the above execution steps, the temperature prediction module 40 realizes the prediction of the future temperature of the target animal body, can understand the temperature change trend in advance, provide decision-making basis for the intervention and regulation module 50, and improve the accuracy and foresight of temperature regulation.

[0034] Further, step P41 includes: Step P411: Perform temperature detection simulation on the target digestive system to obtain a simulation record.

[0035] Step P412: Compare and calculate the analog signal power and the analog noise power in the analog record to obtain a target signal-to-noise ratio.

[0036] Step P413: Obtain the predetermined signal loss correction function according to the target signal-to-noise ratio, and store it in the preprocessor.

[0037] Specifically, the real-time temperature measured by the temperature sensor is affected by many factors, such as signal attenuation, interference, etc. Directly using these data for processing may lead to deviations in the temperature prediction results, so it is necessary to use a correction function to correct the real-time temperature. In order to determine the specific predetermined signal loss correction function, it is necessary to simulate the temperature detection of the target digestive system. Exemplarily, a simulation model of the target digestive system can be established, and this simulation model can simulate the temperature conditions of the target digestive system under different environments and states. For example, a temperature simulation model of the target digestive system can be established using computer software, which takes into account factors such as the physiological structure of the target digestive system, the ambient temperature, and the heat generated during the digestion process, and then performs a simulation test to obtain a simulation record. This simulation record contains various data related to temperature detection during the simulation process, such as temperature changes at different time points, signal strength, and noise level. Through simulation, a more comprehensive understanding of various situations that may occur during the temperature detection process of the target digestive system can be obtained, so as to prepare for accurate correction of signal loss.

[0038] The two key data, analog signal power and analog noise power, are extracted from the simulation record, and then compared and calculated to obtain the target signal-to-noise ratio. The signal-to-noise ratio is an important parameter for measuring signal quality, which is defined as the ratio of signal power to noise power. The higher the signal-to-noise ratio, the better the signal quality and the more accurate the temperature data. By calculating the target signal-to-noise ratio, the relationship between signal and noise in the simulated target digestive system temperature detection process can be quantified, providing a key basis for determining the predetermined signal loss correction function.

[0039] The predetermined signal loss correction function is determined based on the target signal-to-noise ratio. The predetermined signal loss correction function is established based on some pre-set algorithms or empirical formulas, which determine how to correct possible signal losses based on the value of the target signal-to-noise ratio. For example, if the target signal-to-noise ratio is low, indicating that the noise has a greater impact on the signal, then the predetermined signal loss correction function may make a larger adjustment to the temperature data; if the target signal-to-noise ratio is high, the adjustment may be smaller. After the predetermined signal loss correction function is determined, it is stored in the preprocessor for use in subsequent steps.

[0040] Through the above steps, a predetermined signal loss correction function adapted to the target digestive system temperature detection simulation situation is established and stored in the preprocessor, which provides a technical means for accurately correcting signal loss in the actual temperature detection process and improves the accuracy of temperature monitoring data.

[0041] Furthermore, the expression of the predetermined signal loss correction function is as follows: ;in, refers to the actual target temperature, refers to the target real-time temperature, It refers to the comprehensive loss function, wherein the comprehensive loss function includes the signal attenuation loss function, the transmission distance loss function and the interference loss function, and the signal attenuation loss function is expressed as To characterize, is the attenuation coefficient, It refers to the transmission distance of the signal in the target digestive system. The transmission distance loss function is expressed as To characterize, It refers to the transmission distance of the signal in space, and the interference loss function is Characterization, refers to the target signal-to-noise ratio.

[0042] Specifically, the predetermined signal loss correction function is obtained by using the signal attenuation loss function , transmission distance loss function And the interference loss function (i.e. the target signal-to-noise ratio calculated by the temperature detection simulation above) quantifies the comprehensive loss of signal transmission during temperature monitoring Among them, the signal attenuation loss function According to the propagation distance and attenuation coefficient Calculate the signal attenuation loss, which describes the signal strength attenuation caused by medium absorption and other reasons when the signal is transmitted inside the target digestive system. During the signal propagation process, due to the impedance of the air or the characteristics of the transmission medium, the signal strength will decrease with the increase of distance. Transmission distance loss function It reflects the energy dispersion of the signal as the distance increases during the transmission of the signal in space. As the signal propagation distance increases, the signal strength decays in inverse proportion to the square. The longer the signal propagation distance, the weaker the received signal strength. Interference loss function The impact of external interference on the signal is reflected by the target signal-to-noise ratio. The lower the signal-to-noise ratio, the greater the interference, and the greater the impact on temperature measurement. Correction is performed to obtain the actual target temperature , effectively improve the accuracy of target temperature data, reduce errors caused by external interference, and enable the temperature control system to provide high-quality data support under various environmental conditions.

[0043] Further, step P44 includes: Step a: Obtain a target scatter plot of the target temperature signal timing.

[0044] Step b: drawing a first temperature curve based on the first scattered point sample, and determining whether the first temperature curve reaches a predetermined curve constraint.

[0045] Step c: If the first temperature curve does not reach the predetermined curve constraint, repeat step b until the predetermined curve constraint is reached, and output the first temperature curve at that time.

[0046] Step d: performing trend prediction analysis on the first temperature curve in combination with the target time to obtain the predicted target temperature.

[0047] Specifically, extract the time and corresponding temperature data from the established target temperature signal time series data, and then use data visualization tools or programming libraries (such as the matplotlib library in Python) to draw the target scatter plot. These tools can accurately draw scatter plots based on given data points, intuitively showing the change of temperature over time, which helps to quickly understand the general trend of temperature change and the degree of data dispersion.

[0048] A portion of sample data is selected from the target scatter plot and recorded as the first scatter sample. For example, some data points can be selected from all data points in the scatter plot at a certain time interval or randomly selected as the first scatter sample. A first temperature curve is drawn according to the first scatter sample using a data fitting method (such as the least square method). The least square method finds a curve so that the sum of the squares of the vertical distances from the sample data points to the curve is minimized, thereby obtaining a curve equation that can better fit these data points, which is recorded as the first temperature curve. Then, the drawn first temperature curve is compared with the predetermined curve constraint to determine whether it meets the predetermined curve constraint requirements. This predetermined curve constraint is a pre-set restriction condition on the shape, trend, smoothness, etc. of the temperature curve. For example, the predetermined curve constraint may require that the temperature curve is monotonically increasing or decreasing within a certain time range, or that the curvature of the curve is within a certain range. If the first temperature curve meets the predetermined curve constraint, it means that the curve model conforms to the expected temperature change law to a certain extent; if it does not meet the predetermined curve constraint, it needs to be adjusted.

[0049] When the first temperature curve does not meet the predetermined curve constraint, repeat step b. In each repetition, adjust the selection method of the first scattered sample or the parameters of the fitting method. For example, if the number of scattered samples selected for the first time is too small, resulting in inaccurate curve fitting, the number of scattered samples can be increased; or if the initial parameter setting is unreasonable when using the least squares method, these parameters can be adjusted. This process is repeated until the first temperature curve meets the predetermined curve constraint. Finally, the first temperature curve that meets the conditions is output, which improves the accuracy and reliability of the temperature curve, making the subsequent trend prediction analysis based on this curve more scientific and reasonable.

[0050] After obtaining the first temperature curve that meets the predetermined curve constraint, the trend prediction analysis of this curve is performed in combination with the target time. For example, if the first temperature curve is a quadratic function curve, the temperature value corresponding to the target time can be calculated according to the curve equation and the position of the target time. This temperature value is the predicted target temperature.

[0051] The temperature at the target time is predicted by curve fitting, which provides an important decision-making basis for the intervention and regulation module 50 and helps to timely intervene in the health of the target animal.

[0052] Furthermore, after step P411, the following steps are further included: Step P411-1: Activate the IoT device group, and use the IoT device group to perform multi-dimensional monitoring on the target animal body to obtain IoT information.

[0053] Step P411-2: Input the IoT information into a predetermined signal calibration analysis function obtained based on the simulation record to obtain a calibration coefficient.

[0054] Step P411-3: Calibrate and adjust the predicted target temperature using the calibration coefficient as a weight.

[0055] Specifically, after simulating the temperature detection of the target digestive system and obtaining the simulation record, the IoT device group is activated. This IoT device group is a collection of IoT devices, including various sensors such as temperature sensors, humidity sensors, biosensors, and data acquisition and transmission devices. Then, each device in the IoT device group performs multi-dimensional monitoring of the target animal body according to its respective function. For example, the temperature sensor measures the temperature around the animal body, the camera takes the animal's behavior video, and the biosensor detects the animal's physiological indicators. These devices integrate the collected data to obtain IoT information. This IoT information is a collection of various data, such as temperature data, humidity data, animal behavior data, etc., which are stored and transmitted in a certain format, reflecting the state of the target animal body and its living environment.

[0056] According to the simulation record of the aforementioned temperature detection simulation, a predetermined signal calibration analysis function is determined. This function is based on the analysis and processing of the simulation record, and takes into account various factors in the simulation process, such as signal characteristics, interference factors, etc., to determine how to calibrate the predicted temperature according to the IoT information. The obtained IoT information is input into the predetermined signal calibration analysis function for analysis and calculation to obtain the calibration coefficient. The calibration coefficient is a weight coefficient used to calibrate and adjust the predicted target temperature, reflecting the degree of influence of the IoT information on the predicted temperature.

[0057] The predicted target temperature is calibrated and adjusted with the calibration coefficient as the weight, and the calibrated temperature value is obtained by multiplying the predicted target temperature by the calibration coefficient. Through calibration adjustment, the impact of multi-dimensional information monitored by the IoT device group on temperature prediction is taken into account, making the predicted target temperature more in line with the actual situation, further improving the accuracy of temperature prediction, and thus providing more reliable temperature data basis for subsequent animal health intervention and regulation operations.

[0058] Further, step P411-2 includes: Step P411-21: Extract the simulated actual temperature and simulated IoT information in the simulation record.

[0059] Step P411-22: Perform a correlation analysis between the first simulated IoT data corresponding to the first IoT indicator in the simulated IoT information and the simulated actual temperature to obtain a first correlation coefficient.

[0060] Step P411-23: Establish the predetermined signal calibration analysis function according to the corresponding relationship between the first correlation coefficient and the first IoT indicator.

[0061] Specifically, two parts of data, simulated actual temperature and simulated IoT information, are extracted from the obtained simulation records. Among them, the simulated actual temperature is the temperature data close to the actual situation obtained during the temperature detection simulation of the target digestive system. The simulated IoT information is the environmental and physiological data related to the target animal body generated during the simulation process, such as simulated environmental humidity, animal behavior characteristics and other information, which corresponds to the actual monitoring data and is used to calibrate and verify the prediction model.

[0062] The first IoT indicator refers to any IoT indicator in the IoT information. The simulated IoT information is traversed to extract the simulated IoT data corresponding to the first IoT indicator, i.e., the first simulated IoT data. A statistical analysis method is used to perform a correlation analysis on the first simulated IoT data and the simulated actual temperature. For example, the Pearson correlation coefficient calculation method can be used, and its calculation formula is ,in is the i-th data in the first simulated IoT data, is the mean of the first simulated IoT data, is the ith data in the simulated actual temperature. is the mean of the simulated actual temperature, and n is the number of data points. The first correlation coefficient is calculated by the above formula. This first correlation coefficient is used to measure the strength and direction of the linear relationship between the first simulated IoT data and the simulated actual temperature.

[0063] A predetermined signal calibration analysis function is established according to the correspondence between the first correlation coefficient and the first IoT index. Exemplarily, this function can be a weighted average expression based on the correlation coefficient. By constructing a predetermined signal calibration analysis function based on the correlation analysis between the simulated IoT information and the actual temperature, the error in the temperature prediction can be flexibly adjusted according to different IoT indexes and environmental factors, thereby improving the accuracy and dynamic adaptability of the prediction.

[0064] Furthermore, the first IoT indicator refers to any one of the predetermined IoT indicators, and the predetermined IoT indicators include predetermined external IoT indicators and predetermined internal IoT indicators, and the predetermined external IoT indicators at least include ambient temperature, feed type and feed quantity, and the predetermined internal IoT indicators at least include activity level, rumen fermentation, physiological state, water intake and individual heat dissipation rate.

[0065] Specifically, the first IoT indicator is any one indicator selected from predetermined IoT indicators, which cover multiple aspects of internal and external factors, including predetermined external IoT indicators related to the external environment of the target animal and predetermined internal IoT indicators related to the internal physiology and behavior of the target animal, comprehensively considering various factors that may affect the temperature of the target animal.

[0066] The predetermined external IoT indicators include at least ambient temperature, feed type and feed quantity. Ambient temperature is the temperature of the environment surrounding the target animal, which directly affects the heat dissipation and temperature regulation of the animal. The types of feed consumed by animals vary in nutritional content, digestion and absorption processes, etc., thus affecting the physiological state and body temperature of the animal. The amount of feed consumed by animals will affect their energy intake and metabolic level, and thus affect their body temperature. Intake of too much or too little feed may affect the temperature regulation of the animal.

[0067] The predetermined internal factor IoT indicators include at least activity level, rumen fermentation, physiological state, water intake and individual heat dissipation rate. Activity level reflects the energy consumption of the animal body. Animals with high activity levels generate more heat, and their body temperature will also be affected. For ruminants, rumen fermentation is an important physiological process. Microbial fermentation in the rumen generates heat, which will affect the body temperature of the animal. Physiological state includes physiological factors such as the health status and reproductive status of the animal. The body temperature regulation mechanism and ability of the animal body may be different under different physiological states. For example, sick animals may have abnormal body temperature. Water intake affects the heat dissipation and metabolic process of the animal body. Insufficient water intake may cause difficulty in heat dissipation and affect body temperature. Different animal individuals have different heat dissipation rates due to factors such as their body shape and fur. This is an important internal factor affecting the body temperature of animals.

[0068] By monitoring the predetermined external IoT indicators, we can understand the impact of external environmental factors on animal body temperature; by monitoring the predetermined internal IoT indicators, we can understand the impact of the animal's own physiological and behavioral factors on body temperature. Taking these internal and external factors into consideration, we can build a temperature prediction and calibration system that is more in line with the actual situation, thereby improving the accuracy of the calibration adjustment of the predicted target temperature.

[0069] In summary, the intelligent temperature control system based on the Internet of Things provided by the embodiments of the present application has the following technical effects: The command acquisition module 10 is used to realize automatic temperature detection triggering to ensure the regularity and continuity of monitoring; the real-time temperature detection module 20 uses a high-precision platinum resistance sensor to dynamically capture temperature changes, providing an accurate data basis for subsequent temperature prediction and intervention adjustment; the temperature transmission module 30 uses LoRa technology to efficiently transmit data to the cloud to achieve remote management and centralized processing of data; the temperature prediction module 40 uses big data analysis and the computing power of the cloud platform to obtain the signal loss correction function in the preprocessor, correct the temperature deviation caused by signal attenuation and interference, and thus obtain the actual temperature of the target animal. Further, trend analysis is performed based on the target temperature signal time series to predict the temperature changes of the target animal in the future. To ensure the accuracy of the prediction, by analyzing the correlation between the simulated actual temperature in the simulation record and various IoT indicators (such as activity level, feed type, etc.) in the IoT data, a signal calibration analysis function is established, and the calibration coefficient is used to correct the predicted temperature data, thereby improving the prediction accuracy and providing forward-looking decision support for subsequent temperature regulation; the intervention adjustment module 50 issues adjustment instructions in a timely manner according to the prediction results to achieve rapid and accurate intervention and adjustment of the animal body temperature.

[0070] Overall, the embodiments of the present application improve the accuracy and foresight of temperature regulation and the response speed of temperature regulation by combining real-time monitoring, signal correction and predictive analysis, and utilizing IoT data to dynamically calibrate and optimize temperature prediction, thereby providing a more scientific and effective means for animal health management.

[0071] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The intelligent temperature control system based on the Internet of Things is characterized by: The intelligent temperature regulation system based on the Internet of Things includes: An instruction acquisition module, used to acquire a temperature detection instruction, wherein the temperature detection instruction refers to an instruction automatically issued by the microcontroller based on a predetermined detection frequency to perform temperature detection on a target digestive system of a target animal body; A real-time temperature detection module, used to activate a platinum resistance temperature sensor based on the temperature detection instruction, and dynamically detect the target real-time temperature of the target digestive system in real time through the platinum resistance temperature sensor; A temperature transmission module is used to transmit the target real-time temperature to the IoT data processing cloud platform through a LoRa communicator; A temperature prediction module, used to perform prediction analysis through the IoT data processing platform to obtain a predicted target temperature at a target time; an intervention and regulation module, configured to issue a health regulation instruction if the predicted target temperature is not within a predetermined temperature threshold, and perform health intervention and regulation on the target animal body based on the health regulation instruction; Wherein, the temperature prediction module is also used to perform the following steps: Obtaining a preprocessor in the IoT data processing platform, wherein the preprocessor is embedded with a predetermined signal loss correction function; Performing loss correction analysis on the target real-time temperature according to the predetermined signal loss correction function to obtain the target actual temperature; Establishing a corresponding relationship between the target actual temperature and the real time to establish a target temperature signal timing; The target temperature signal timing is predictively analyzed by the IoT data processing platform to obtain the predicted target temperature at the target time.

2. The intelligent temperature control system based on the Internet of Things according to claim 1 is characterized in that: The temperature prediction module is also used to perform the following steps: Performing temperature detection simulation on the target digestive system to obtain a simulation record; Comparing and calculating the analog signal power and the analog noise power in the analog record to obtain a target signal-to-noise ratio; The predetermined signal loss correction function is obtained according to the target signal-to-noise ratio and stored in the preprocessor.

3. The intelligent temperature control system based on the Internet of Things according to claim 2 is characterized in that: The expression of the predetermined signal loss correction function is as follows: ； in, refers to the actual temperature of the target, refers to the target real-time temperature, It refers to the comprehensive loss function, wherein the comprehensive loss function includes the signal attenuation loss function, the transmission distance loss function and the interference loss function, and the signal attenuation loss function is expressed as To characterize, is the attenuation coefficient, It refers to the transmission distance of the signal in the target digestive system. The transmission distance loss function is expressed as To characterize, It refers to the transmission distance of the signal in space, and the interference loss function is Characterization, refers to the target signal-to-noise ratio.

4. The intelligent temperature control system based on the Internet of Things according to claim 1 is characterized in that: The temperature prediction module is also used to perform the following steps: Step a: obtaining a target scatter plot of the target temperature signal timing; Step b: drawing a first temperature curve based on the first scattered point sample, and determining whether the first temperature curve reaches a predetermined curve constraint; Step c: if the first temperature curve does not reach the predetermined curve constraint, repeat step b until the predetermined curve constraint is reached, and output the first temperature curve at that time; Step d: performing trend prediction analysis on the first temperature curve in combination with the target time to obtain the predicted target temperature.

5. The intelligent temperature control system based on the Internet of Things according to claim 2 is characterized in that: The temperature prediction module is also used to perform the following steps: Activating an IoT device group, and performing multi-dimensional monitoring of the target animal body through the IoT device group to obtain IoT information; Inputting the IoT information into a predetermined signal calibration analysis function obtained based on the simulation record to obtain a calibration coefficient; The predicted target temperature is calibrated and adjusted using the calibration coefficient as a weight.

6. The intelligent temperature control system based on the Internet of Things according to claim 5 is characterized in that: The temperature prediction module is also used to perform the following steps: Extracting the simulated actual temperature and simulated IoT information in the simulated record; Performing a correlation analysis between the first simulated IoT data corresponding to the first IoT indicator in the simulated IoT information and the simulated actual temperature to obtain a first correlation coefficient; The predetermined signal calibration analysis function is established according to the corresponding relationship between the first correlation coefficient and the first IoT indicator.

7. The intelligent temperature control system based on the Internet of Things according to claim 6 is characterized in that: The first IoT indicator refers to any one of the predetermined IoT indicators, wherein the predetermined IoT indicators include predetermined external IoT indicators and predetermined internal IoT indicators, and the predetermined external IoT indicators at least include ambient temperature, feed type and feed quantity, and the predetermined internal IoT indicators at least include activity level, rumen fermentation, physiological state, water intake and individual heat dissipation rate.

Images