A method and apparatus for constructing a temperature compensation model

Abstract

The present application discloses a method and device for constructing a temperature compensation model, which is applied to a small weather station including a large mass body, an environmental sensor and two temperature sensors. The method includes: obtaining two current temperature data and two offset temperature data corresponding to the two temperature sensors, and environmental parameters in the offset time period corresponding to the environmental sensor; combining multiple current combination data and multiple offset combination data based on the two current temperature data, the two offset temperature data and the environmental data; constructing a training data set based on the two current temperature data, the multiple current combination data, the multiple offset combination data and the target temperature data; training a linear regression model based on the training data set to obtain a temperature compensation model. The temperature compensation model constructed by the method of the present application and the two temperature sensors and the environmental sensor of the small weather station can compensate the detected temperature in real time, thereby improving the accuracy of temperature measurement of the small weather station.

Description

Technical Field

[0001] The present application relates to the field of temperature measurement technology, and in particular to a method and device for constructing a temperature compensation model. Background Art

[0002] A small weather station is a small device used to detect and record environmental parameters. It is widely used in meteorology, agriculture and other technical fields due to its convenience, easy installation and low cost.

[0003] Due to the structural characteristics of the small weather station, under high temperature conditions or direct sunlight, heat sources gather inside the small weather station, causing the temperature sensor in the small weather station to measure a higher temperature; in a snowy environment in winter, if ice and snow cover the small weather station, it will hinder the good contact between the temperature sensor and the surrounding air. The temperature sensor may measure the temperature of the ice and snow covering the small weather station instead of the temperature of the surrounding air, causing the temperature sensor in the small weather station to measure a lower temperature; and when the temperature changes rapidly (increases or decreases), the temperature sensor measures a lower or higher temperature because the temperature of the large mass body cannot respond quickly to the change.

[0004] It can be seen from this that the temperature measurement of small meteorological stations is inaccurate in extreme weather, which affects the accuracy of the overall temperature measurement of small meteorological stations. Summary of the invention

[0005] Based on the above problems, the present application provides a method and device for constructing a temperature compensation model. The temperature compensation model constructed by the method of the present application and the two temperature sensors and environmental sensors in the small meteorological station can perform real-time compensation for the detected temperature, thereby solving the problem of inaccurate temperature measurement of the small meteorological station in extreme weather conditions, thereby improving the overall temperature measurement accuracy of the small meteorological station.

[0006] The embodiments of the present application disclose the following technical solutions:

[0007] In a first aspect, the present application discloses a method for constructing a temperature compensation model, which is applied to a small weather station, wherein the weather station comprises: a large mass body, an environmental sensor, and two temperature sensors, wherein the two temperature sensors are placed at different positions on the same medium, wherein one temperature sensor is close to the large mass body, and the other temperature sensor is far away from the large mass body; the method comprises:

[0008] Acquire two current temperature data and two offset temperature data corresponding to the two temperature sensors, and the environmental data in the offset time period corresponding to the environmental sensor; wherein the current temperature data is the temperature data collected by the temperature sensor at the current time; the offset temperature data is the temperature data collected by the temperature sensor at the offset time, and the offset time is the time corresponding to the preset time interval after the current time; the offset time period is the time period between the current time and the offset time;

[0009] Based on the two current temperature data and the environmental data, a plurality of current combination data corresponding to the two current temperature data are obtained by combination; and based on the two offset temperature data and the environmental data, a plurality of offset combination data corresponding to the two offset temperature data are obtained by combination;

[0010] Based on the two current temperature data, the multiple current combination data, the multiple offset combination data, and the corresponding target temperature data, a training data set is constructed; wherein the training data set includes multiple data subsets consisting of the two current temperature data, the multiple current combination data, the multiple offset combination data, and the corresponding target temperature data;

[0011] Based on the training data set, a linear regression model is trained to obtain a temperature compensation model.

[0012] Optionally, the environmental sensor includes: a wind speed sensor; the environmental data in the offset time period corresponding to the environmental sensor includes: wind speed data in the offset time period corresponding to the wind speed sensor;

[0013] The combining of the two current temperature data and the environment data to obtain a plurality of current combination data corresponding to the two current temperature data respectively; and combining of the two offset temperature data and the environment data to obtain a plurality of offset combination data corresponding to the two offset temperature data respectively, comprises:

[0014] Based on the two current temperature data and the wind speed data, two current combination data corresponding to the two current temperature data are obtained by combination; and based on the two offset temperature data and the wind speed data, two offset combination data corresponding to the two offset temperature data are obtained by combination;

[0015] The constructing of a training data set based on the two current temperature data, the multiple current combination data, the multiple offset combination data, and the corresponding target temperature data includes:

[0016] A training data set is constructed based on the two current temperature data, the two current combination data, the two offset combination data, and the corresponding target temperature data; wherein the training data set includes multiple data subsets consisting of two current temperature data, two current combination data, two offset combination data and corresponding target temperature data.

[0017] Optionally, constructing a training data set based on the two current temperature data, the two current combination data, the two offset combination data, and the corresponding target temperature data includes:

[0018] Based on the two current temperature data, the two current combination data and the two offset combination data, construct a corresponding six-variable quadratic polynomial feature;

[0019] Based on the corresponding six-variable quadratic polynomial features and the corresponding target temperature data, a training data set is constructed; wherein the training data set includes a plurality of data subsets consisting of six-variable quadratic polynomial features and the corresponding target temperature data.

[0020] Optionally, the wind speed data within the offset time period includes: the average wind speed within the offset time period.

[0021] Optionally, the average wind speed in the offset time period is obtained by:

[0022] Acquiring multiple wind speeds within the offset time period through a wind speed sensor;

[0023] Based on the multiple wind speeds, an average wind speed within the offset time period is calculated.

[0024] Optionally, the combining, based on the two current temperature data and the wind speed data, to obtain two current combination data corresponding to the two current temperature data respectively includes:

[0025] Based on the two current temperature data and the wind speed data, two current combination data corresponding to the two current temperature data are obtained by combining them through a first preset formula;

[0026] The first preset formula is as follows:

[0027]

[0028] in, E c is the current combination data corresponding to the current temperature data, T c is the current temperature data, v is the wind speed data within the offset time period;

[0029] The combining, based on the two offset temperature data and the wind speed data, to obtain two offset combination data corresponding to the two offset temperature data respectively comprises:

[0030] Based on the two offset temperature data and the wind speed data, two offset combination data corresponding to the two offset temperature data are obtained by combining them through a second preset formula;

[0031] The second preset formula is as follows:

[0032]

[0033] in, E p is the offset combination data corresponding to the offset temperature data, T p is the offset temperature data, v is the wind speed data within the offset time period.

[0034] Optionally, the preset time interval is a time interval corresponding to a preset number of interval units.

[0035] Optionally, training a linear regression model based on the training data set to obtain a temperature compensation model includes:

[0036] Based on the training data set, train a linear regression model and record the corresponding root mean square error and determination coefficient;

[0037] When the corresponding root mean square error and determination coefficient meet the preset requirements, the training of the linear regression model is terminated to obtain a temperature compensation model.

[0038] Optionally, after training a linear regression model based on the training data set to obtain a temperature compensation model, the method further includes:

[0039] Acquire two current temperature data corresponding to the two temperature sensors respectively, and environmental data of an offset time period corresponding to the environmental sensor;

[0040] Based on the two current temperature data and the environmental data of the offset time period, actual temperature data is obtained through the temperature compensation model.

[0041] In a second aspect, the present application discloses a device for constructing a temperature compensation model, which is applied to a small weather station, wherein the small weather station comprises: a large mass body, an environmental sensor, and two temperature sensors, wherein the two temperature sensors are placed at different positions on the same medium, wherein one temperature sensor is close to the large mass body, and the other temperature sensor is far away from the large mass body; the device comprises:

[0042] An acquisition module, used to acquire two current temperature data and two offset temperature data corresponding to the two temperature sensors, and environmental data within an offset time period corresponding to the environmental sensor; wherein the current temperature data is the temperature data collected by the temperature sensor at the current time; the offset temperature data is the temperature data collected by the temperature sensor at an offset time, and the offset time is the time corresponding to a preset time interval after the current time; and the offset time period is the time period between the current time and the offset time;

[0043] A combining module, configured to combine the two current temperature data and the environmental data to obtain a plurality of current combined data corresponding to the two current temperature data respectively; and to combine the two offset temperature data and the environmental data to obtain a plurality of offset combined data corresponding to the two offset temperature data respectively;

[0044] A construction module, configured to construct a training data set based on the two current temperature data, the multiple current combination data, the multiple offset combination data, and the corresponding target temperature data; wherein the training data set includes multiple data subsets consisting of the two current temperature data, the multiple current combination data, the multiple offset combination data, and the corresponding target temperature data;

[0045] The training module is used to train a linear regression model based on the training data set to obtain a temperature compensation model.

[0046] Optionally, an acquisition module is specifically used to obtain two current temperature data and two offset temperature data corresponding to two temperature sensors, and wind speed data in an offset time period corresponding to a wind speed sensor;

[0047] A combination module, specifically used to combine the two current temperature data and the wind speed data to obtain two current combination data corresponding to the two current temperature data respectively; and to combine the two offset temperature data and the wind speed data to obtain two offset combination data corresponding to the two offset temperature data respectively;

[0048] The construction module is specifically used to construct a training data set based on the two current temperature data, the two current combination data, the two offset combination data, and the corresponding target temperature data.

[0049] Optionally, the building module is specifically used for:

[0050] Based on the two current temperature data, the two current combination data and the two offset combination data, construct a corresponding six-variable quadratic polynomial feature;

[0051] Based on the corresponding six-variable quadratic polynomial features and the corresponding target temperature data, a training data set is constructed; wherein the training data set includes a plurality of data subsets consisting of six-variable quadratic polynomial features and the corresponding target temperature data.

[0052] Optionally, a construction module is specifically used to construct corresponding six-dimensional quadratic polynomial features based on two current temperature data, two current combination data and two offset combination data; and to construct a training data set based on the corresponding six-dimensional quadratic polynomial features and corresponding target temperature data; wherein the training data set includes multiple data subsets consisting of six-dimensional quadratic polynomial features and corresponding target temperature data.

[0053] Optionally, a combination module is specifically used to combine two current combination data corresponding to the two current temperature data through a first preset formula based on two current temperature data and wind speed data; and to combine two offset combination data corresponding to the two offset temperature data through a second preset formula based on two offset temperature data and wind speed data.

[0054] Optionally, a training module is specifically used to train a linear regression model based on a training data set, and record the corresponding root mean square error and determination coefficient; when the corresponding root mean square error and determination coefficient meet the preset requirements, the training of the linear regression model is terminated to obtain a temperature compensation model.

[0055] Compared with the prior art, the present application has the following beneficial effects: the present application takes into account the influence of temperature conduction delay and other environmental parameters, so that the offset temperature data and environmental data participate in the construction of the temperature compensation model, thereby improving the performance of the temperature compensation model; and the present application takes into account the temperature curve of a single temperature sensor caused by the periodic switching of the internal heat source device presents a second-order Fourier curve characteristic, and it is impossible to achieve a one-to-one mapping relationship between the output value of the temperature sensor and the target value, thereby adding a temperature sensor at different positions of the same medium, that is, there are two temperature sensors inside the small meteorological station to participate in temperature measurement, so that the temperature compensation model constructed by the method of the present application and the two temperature sensors and environmental sensors in the small meteorological station can perform real-time compensation for the detected temperature, solving the problem of inaccurate temperature measurement of the small meteorological station in extreme weather, thereby improving the accuracy of temperature measurement of the small meteorological station. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0057] Figure 1 A schematic diagram of the distribution of two temperature sensors provided in an embodiment of the present application;

[0058] Figure 2 A schematic diagram of a process for constructing a temperature compensation model provided in an embodiment of the present application;

[0059] Figure 3 A schematic diagram of a process for realizing temperature measurement through a temperature compensation model provided in an embodiment of the present application;

[0060] Figure 4 A schematic flow chart of another method for constructing a temperature compensation model provided in an embodiment of the present application;

[0061] Figure 5 A schematic diagram of the structure of a device for constructing a temperature compensation model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] As described above, the small weather stations in current technology do not accurately measure temperature in extreme weather conditions due to their structural characteristics. In high temperature environments or direct sunlight, heat sources accumulate inside the small weather stations, causing the temperature sensors to measure inaccurate temperatures (too high). In winter, in addition to the small weather stations being covered by ice and snow, causing the temperature sensors to measure ice and snow temperatures, the small weather stations covered by ice and snow will also affect the performance of their internal sensors, especially the temperature sensors, causing inaccurate sensor readings.

[0063] Furthermore, in order to avoid the influence of ice and snow covering the small weather station on the performance of the internal sensor, a heat source device is added inside the small weather station to increase the internal temperature of the small weather station, thereby melting the ice and snow covering the small weather station. For example, a heating plate is added inside the small weather station, and when the small weather station is covered with ice and snow, the internal temperature of the small weather station is increased by the internal heat source device, thereby melting the ice and snow covering the small weather station.

[0064] However, since a heat source device is added inside the small weather station, new heat source interference is brought to the sensors inside the small weather station, especially the temperature sensor, so that in the snowy environment in winter, the temperature sensor inside the small weather station still cannot accurately measure the actual outdoor temperature.

[0065] The following only takes the addition of a heating plate inside a small weather station as an example to introduce the impact of the internal heat source device on temperature measurement. It should be noted that high temperature conditions or direct sunlight environments are similar to adding an internal heat source device.

[0066] The opening and closing of the heating plate (i.e., the internal heat source device) is affected by the ambient temperature and heat dissipation, that is, the working characteristics of the heating plate are affected by the ambient temperature and heat dissipation conditions, and it does not perform specific heating at a fixed temperature point. For example, in a relatively closed environment, the heat generated by the heating plate is not easy to dissipate, resulting in a more obvious heating effect; under high wind speed conditions, the heat is more easily taken away, so the heating plate needs to input more heat to maintain the set temperature. Furthermore, the heating plate has its own energy-saving mode, which means that it will stop heating when a certain temperature is reached and restart when the temperature drops to a certain threshold; and the energy-saving mode of the heating plate has a critical temperature range, within which the heating plate will be periodically turned on and off. Under the action of the periodic switching of the heating plate, the temperature curve recorded by the temperature sensor in the small weather station shows the characteristics of a second-order Fourier curve.

[0067] Generally, a temperature sensor is arranged in a small meteorological station. However, due to the addition of a heat source device inside the small meteorological station and the periodic switching of the internal heat source device within the critical temperature range, heat conduction modeling is performed through a single temperature sensor in the small meteorological station, that is, the current temperature sensor output value is mapped into the actual (target) value. However, due to the periodic switching of the internal heat source device, a one-to-one mapping relationship between the output value and the target value cannot be formed within some temperature ranges, resulting in the small meteorological station being unable to accurately measure the temperature.

[0068] The present application provides a method for constructing a temperature compensation model, including: obtaining two current temperature data and two offset temperature data corresponding to two temperature sensors, and environmental data in an offset time period corresponding to an environmental sensor; combining to obtain multiple current combination data corresponding to the two current temperature data based on the two current temperature data and the environmental data; and combining to obtain multiple offset combination data corresponding to the two offset temperature data based on the two temperature offset temperature data and the environmental data; constructing a training data set based on the two current temperature data, multiple current combination data, multiple offset combination data, and corresponding target temperature data; and training a linear regression model based on the training data set to obtain a temperature compensation model. The present application takes into account the influence of temperature conduction delay and other environmental parameters, so that the offset temperature data and environmental data participate in the construction of the temperature compensation model, improves the performance of the temperature compensation model, and enables the temperature compensation model constructed by the method of the embodiment of the present application and the two temperature sensors and environmental sensors in the small weather station to compensate the detected temperature in real time, solves the problem of inaccurate temperature measurement of the small weather station in extreme weather, and thus improves the accuracy of temperature measurement of the small weather station.

[0069] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0070] Embodiment 1:

[0071] Combine the following Figure 1-Figure 3 , a method for constructing a temperature compensation model provided in an embodiment of the present application is introduced in detail.

[0072] First, a method for constructing a temperature compensation model provided in an embodiment of the present application is applied to a small weather station. The small weather station includes: a large mass body, an environmental sensor, and two temperature sensors. The two temperature sensors are located at different positions of the same medium, one of which is close to the large mass body and the other is far away from the large mass body.

[0073] Among them, the environmental sensor refers to a device for detecting and measuring environmental data. In the embodiment of the present application, the environmental sensor refers to a device for detecting and measuring environmental data other than a temperature sensor. Exemplary: environmental sensors include: wind speed sensors, light sensors, air pressure sensors, etc.

[0074] From the perspective of thermodynamics, a small weather station is a non-steady-state heat conduction system with a heat source device inside, but there is no control over the internal heat source device, so the heat source inside the small weather station is uncontrollable or unknown. If the traditional heat conduction partial differential equation is used for mathematical modeling, it cannot be used because of the uncontrollable or positional factors that make it difficult to obtain variables; if the numerical method is used in actual scenarios, it will take up a lot of computing resources, and the speed is slow and the accuracy is low. It cannot solve the problems in the current technology, and it takes up a lot of computing resources and does not meet the application scope of small weather stations.

[0075] Furthermore, according to the first-class boundary conditions in the traditional heat conduction partial differential equation, it can be known that for a simple first-order heat conduction system without a heat source (i.e., a weather station without a heat source), the temperatures of the two endpoints can be obtained, and the analytical solution of the heat conduction partial differential equation can be derived. Therefore, in the embodiment of the present application, two temperature sensors are arranged inside the small weather station to obtain the temperature data collected by the two temperature sensors respectively, so as to perform mathematical modeling, thereby realizing real-time temperature compensation.

[0076] In the embodiment of the present application, a temperature sensor is added at a different position on the same medium, one of the two temperature sensors is close to the large mass body, and the other temperature sensor is far away from the large mass body (that is, the two temperature sensors are both in the main heat conduction direction) to achieve two current output values ​​and one actual (target) value, which can greatly reduce the ambiguity of the mapping and increase the availability of data features, thereby improving the accuracy and versatility of temperature testing.

[0077] Furthermore, two temperature sensors are placed at different positions of the same medium, and one of the two temperature sensors is close to the large mass body, and the other temperature sensor is far away from the large mass body. In this way, the two temperature sensors are actually distributed / placed in the main heat conduction direction of the small weather station, which can effectively capture the information of the temperature gradient, further increasing the availability of temperature data, so that data modeling can be performed based on the temperature data collected by the two temperature sensors, so as to accurately compensate for the accurate and reliable actual temperature.

[0078] For ease of understanding, the following Figure 1 The distribution of the two temperature sensors in the main heat conduction direction is shown in detail.

[0079] like Figure 1 As shown, it includes temperature sensor s1 and temperature sensor s2, wherein temperature sensor s1 and temperature sensor s2 are arranged / set in the heat conduction direction, wherein temperature sensor s1 is close to the large mass body, and temperature sensor s2 is close to the external environment (which can also be understood as ambient air). Temperature sensor s1 is close to the large mass body, and is greatly affected by the temperature change of the large mass body; temperature sensor s2 is close to the external environment, that is, far away from the large mass body, and is less affected by the temperature change of the large mass body.

[0080] Among them, the large mass body refers to the device or structure used for stable temperature measurement in a small meteorological station. The purpose of designing these devices or structures is to reduce the impact of rapid fluctuations in ambient temperature on the temperature sensor, thereby improving the accuracy and stability of the measurement. Figure 1 As shown, in the embodiment of the present application, the large mass body includes a heat source device, thereby it can also be obtained that the temperature sensor s1 is close to the heat source device and the temperature sensor s2 is far away from the heat source device.

[0081] It should be noted that, in addition to being located in the large-mass main body, the heat source device can also be arranged / set at other locations of the small meteorological station, depending on the actual structure of the small meteorological station, and this application does not make any specific limitations.

[0082] like Figure 1As shown in the figure, the heat conduction efficiencies corresponding to the temperature sensors s1 and s2 in the main heat conduction direction (thermal temperature gradient) are different. This is because the relationship between the heat conduction efficiency and the heat transfer distance is approximately linear and inversely proportional, that is, under the same conditions (such as the same material, the same cross-sectional area, etc.), the shorter the heat transfer distance, the higher the heat transfer efficiency, and vice versa.

[0083] Heat transfer efficiency refers to the ability of heat to be transferred from a high temperature area to a low temperature area (i.e., along the main heat transfer direction) through a solid material; heat transfer distance refers to the distance that heat is transferred during the heat conduction process. Under the same conditions, the shorter the heat transfer distance, the higher the heat transfer efficiency, because a shorter heat transfer distance means a smaller thermal resistance, and heat is more easily transferred from a high temperature area to a low temperature area.

[0084] Due to the above concept, in the main heat conduction direction, the relationship between the heat conduction efficiency and the heat transfer distance presents a nearly linear relationship. Therefore, the temperature data collected by the temperature sensor s1 and the temperature sensor s2 distributed in the main heat conduction direction can capture the temperature gradient information (i.e., the temperature gradient), so that the temperature distribution between the two points s1 and s2 can be inferred through the heat conduction equation through relevant physical parameters, so as to facilitate the subsequent data modeling based on the temperature data collected by the two temperature sensors, thereby accurately compensating for the accurate and reliable actual temperature.

[0085] In a possible implementation, two temperature sensors are fixed / set on the temperature and humidity small board of the small weather station and are separated by a preset distance; one temperature sensor is close to the large mass body and has poor air circulation; the other temperature sensor is far away from the large mass body and has good air circulation. The temperature and humidity small board of the small weather station usually refers to a sensor module used to measure temperature and humidity in the small weather station. This module usually contains one or more sensor chips and can measure the temperature and humidity of the air at the same time.

[0086] Exemplarily, two temperature sensor chips are disposed on the temperature and humidity plate and are spaced about 8 mm apart, with one temperature sensor chip close to the heating plate and the other temperature sensor chip away from the heating plate.

[0087] In the embodiment of the present application, the two temperature sensors placed in the same medium but at different positions are consistent. Whether in a high temperature environment or a direct sunlight environment, or in a low temperature environment in winter or when the heating plate is turned on, the temperature data collected by the temperature sensor closer to the large mass body of the two temperature sensors inside the small weather station will be higher than the temperature data collected by the temperature sensor farther from the large mass body. Since the two temperature sensors are placed in the same medium but at different positions, and one temperature sensor is close to the large mass body and the other temperature sensor is far away from the large mass body (that is, both temperature sensors are in the main heat conduction direction), they are consistent, which is helpful for the subsequent construction of the temperature compensation model.

[0088] Furthermore, since the two temperature sensors are located on one medium, the uncertainties encountered by the two temperature sensors when collecting / measuring temperature data are reduced by controlling variables, thereby making the temperature data collected / measured by the temperature sensors more effective.

[0089] like Figure 2 As shown, a method for constructing a temperature compensation model provided in an embodiment of the present application includes the following steps:

[0090] S201, acquiring two current temperature data and two offset temperature data corresponding to two temperature sensors respectively, and environmental data within an offset time period corresponding to the environmental sensor.

[0091] Among them, the current temperature data is the temperature data collected by the temperature sensor at the current time; the offset temperature data is the temperature data collected by the temperature sensor at the offset time, and the offset time is the time corresponding to the preset time interval after the current time.

[0092] The offset time period is the time period between the current time and the offset time, that is, the offset time period is a preset time interval.

[0093] Among them, the environmental sensors include: wind speed sensor, light sensor, air pressure sensor, rainfall sensor, etc. The corresponding environmental data include: wind speed data, light data, air pressure data, rainfall data, etc.

[0094] In a possible implementation manner, the interval unit is preset, and the preset time interval is a time interval corresponding to a preset number of interval units.

[0095] Exemplarily, assuming that the interval unit is 8.75s and the preset number is 28, the preset time interval is the time interval corresponding to 28 interval units, that is, 28*8.75=245s; the offset time period is 245s; and the offset time is the time corresponding to 245s before the current time.

[0096] In a possible implementation manner, the environmental data within the offset time period is average data within the offset time period.

[0097] Exemplarily, assuming that the offset time period is a time interval corresponding to a preset number of interval units, the environmental data at the moment corresponding to each interval unit in the offset time period is obtained through the environmental sensor, that is, the preset number of environmental data are obtained; based on the preset number of environmental data, the average data in the offset time period is calculated.

[0098] S202, combining two current temperature data and environmental data to obtain a plurality of current combination data corresponding to the two current temperature data; and combining two temperature offset temperature data and environmental data to obtain a plurality of offset combination data corresponding to the two offset temperature data.

[0099] In one possible implementation, when the environmental data within the offset time period corresponding to the environmental sensor is one (kind of) environmental data (for example, wind speed data), based on two current temperature data and one environmental data, two current combined data corresponding to the two current temperature data are combined; and based on two temperature offset temperature data and one environmental data, two offset combined data corresponding to the two offset temperature data are combined.

[0100] In another possible implementation, when the environmental data within the offset time period corresponding to the environmental sensor is two (two kinds) of environmental data (for example, wind speed data and light data), based on two current temperature data and two environmental data, four current combination data corresponding to the two current temperature data are combined (for example, including two current combination data combined with wind speed data, and two current combination data combined with light data); and based on two temperature offset temperature data and two environmental data, four offset combination data corresponding to the two offset temperature data are combined.

[0101] In summary, it can be simply summarized as follows: when the environmental data in the offset time period corresponding to the environmental sensor is n (n types) environmental data, based on the two current temperature data and the n environmental data, 2n current combination data corresponding to the two current temperature data are combined; and based on the two temperature offset temperature data and the n environmental data, 2n offset combination data corresponding to the two offset temperature data are combined. Where n is a positive integer.

[0102] S203: construct a training data set based on two current temperature data, a plurality of current combination data, a plurality of offset combination data and corresponding target temperature data.

[0103] The training data set includes a plurality of data subsets consisting of two current temperature data, a plurality of current combination data, a plurality of offset combination data and corresponding target temperature data.

[0104] The target temperature data is the standard temperature data at the current time. For example, a standard thermometer can be placed, which is not affected by the internal heat source device (heating plate), and the temperature data collected by the standard thermometer at the current time is used as the standard temperature data (ie, the target temperature data).

[0105] S204: Based on the training data set, train a linear regression model to obtain a temperature compensation model.

[0106] Among them, the linear regression model is a widely used statistical method to establish the mathematical relationship between a dependent variable (usually called a response variable or target variable) and one or more independent variables.

[0107] In one possible implementation, a linear regression model is trained based on a training data set, and the corresponding root mean square error and determination coefficient are recorded; when the corresponding root mean square error and determination coefficient meet preset requirements, the training of the linear regression model is terminated to obtain a temperature compensation model.

[0108] Among them, the root mean square error (RMSE) is an important indicator for evaluating the performance of a regression model. It is used to measure the difference between the output value of the regression model and the actual value (target value). Specifically, the root mean square error is the square root of the average of the squares of the prediction errors. The smaller the RMSE, the closer the output value of the regression model is to the actual value, and the better the performance of the regression model.

[0109] Among them, the coefficient of determination (Coefficient of Determination, R 2 ) is an important indicator for evaluating the performance of a regression model, providing a quantitative way to measure the ability of a regression model to explain the variation of the dependent variable. Specifically, the coefficient of determination represents the ratio of the difference between the output value of the regression model and the actual value (i.e., the residual sum of squares) to the total variation (i.e., the sum of squares of the difference between the actual value and its mean value). In other words, the coefficient of determination can represent the effect of the regression model in fitting the data. The larger the value of the coefficient of determination, the better the regression model fits the data, and the better the performance of the regression model.

[0110] Specifically, when the corresponding root mean square error and the determination coefficient meet the preset requirements, the corresponding root mean square error is less than a first preset value, and the corresponding determination coefficient is greater than a second preset value.

[0111] In a method for constructing a temperature compensation model provided in an embodiment of the present application, the delay in temperature conduction is taken into consideration, and offset temperature data is used to participate in the training of the temperature compensation model.

[0112] Among them, the delay in temperature conduction means that when heat is transferred from one object to another, the temperature change will not be reflected immediately on the adjacent object, but it takes a certain amount of time to be transferred to a farther distance. This delay is determined by the physical properties of heat conduction. For example, when the heating plate is periodically turned on and off, the time points at which the minimum and maximum values ​​of the two temperature sensors in the small weather station appear are not completely synchronized, and there is a time delay of about 3-6 seconds.

[0113] Furthermore, other environmental data / parameters have an impact on the measured temperature, so other environmental data are added and other environmental data and temperature data are combined to participate in the training of the temperature compensation model.

[0114] After obtaining the temperature compensation model provided in the method for constructing a temperature compensation model in an embodiment of the present application, the small meteorological station implements temperature measurement through the temperature compensation model.

[0115] For ease of understanding, the following Figure 3 This article introduces in detail how to realize temperature measurement based on the temperature compensation model.

[0116] S301, obtaining two current temperature data corresponding to two temperature sensors respectively, and environmental data of an offset time period corresponding to an environmental sensor.

[0117] Specifically, the temperature data collected by the two temperature sensors at the same time are obtained. The method for obtaining the environmental data in the offset time period is the same as that in S201, and will not be repeated here.

[0118] S302: Based on the two current temperature data and the environmental data of the offset time period, actual temperature data is obtained through the temperature compensation model.

[0119] Specifically, the two current temperature data and the environmental data of the offset time period are input into the temperature compensation model; the temperature compensation model outputs the corresponding target temperature data (i.e., actual temperature data) based on the two current temperature data and the environmental data of the offset time period. The temperature compensation model realizes real-time compensation of the two current temperature data, thereby obtaining the actual temperature data, which improves the accuracy of temperature measurement of the small weather station.

[0120] The embodiment of the present application provides a method for constructing a temperature compensation model, including: obtaining two current temperature data and two offset temperature data corresponding to two temperature sensors, and environmental data in an offset time period corresponding to an environmental sensor; combining to obtain multiple current combination data corresponding to the two current temperature data based on the two current temperature data and the environmental data; and combining to obtain multiple offset combination data corresponding to the two offset temperature data based on the two temperature offset temperature data and the environmental data; constructing a training data set based on the two current temperature data, multiple current combination data, multiple offset combination data, and corresponding target temperature data; training a linear regression model based on the training data set to obtain a temperature compensation model. The embodiment of the present application takes into account the influence of temperature conduction delay and other environmental parameters, so that the offset temperature data and environmental data participate in the construction of the temperature compensation model, improve the performance of the temperature compensation model, so that the temperature compensation model constructed by the method of the embodiment of the present application and the two temperature sensors and environmental sensors in the small weather station can compensate the detected temperature in real time, solve the problem of inaccurate temperature measurement of the small weather station in extreme weather, and thus improve the accuracy of temperature measurement of the small weather station.

[0121] Furthermore, the two temperature sensors placed in the same medium but at different positions have consistency, which further helps to build a temperature compensation model; and being placed on the same medium can reduce the uncertainty factors when the two temperature sensors collect / measure temperature data, thereby making the temperature data collected / measured by the temperature sensors more effective.

[0122] Embodiment 2:

[0123] Combine the following Figure 4 , a method for constructing a temperature compensation model provided by an embodiment of the present application is introduced in detail. Wherein, the environmental sensor includes a wind speed sensor, and the corresponding environmental data is wind speed data.

[0124] S401. Acquire two current temperature data and two offset temperature data corresponding to two temperature sensors, and wind speed data in an offset time period corresponding to a wind speed sensor.

[0125] Among them, the wind speed data in the offset time period is one of the meteorological parameters that affect the temperature balance, and the wind speed has a greater impact on the measurement of the two temperature sensors. For example, an increase in wind speed will enhance the heat conduction between the air and the temperature sensor. When the wind speed is high, the air flow is accelerated, so that heat can be transferred from the higher temperature area to the lower temperature area more quickly, that is, the heat conduction rate is increased, so that the ambient temperature felt by the two temperature sensors is different. Therefore, in the embodiment of the present application, it is necessary to focus on the influence of wind speed, so the wind speed data in the offset time period corresponding to the wind speed sensor is obtained.

[0126] In a possible implementation manner, the wind speed data in the offset time period is the average wind speed in the offset time period.

[0127] Specifically, the average wind speed in the offset time period is obtained in the following manner: a plurality of wind speeds in the offset time period is acquired by a wind speed sensor; and the average wind speed in the offset time period is calculated based on the plurality of wind speeds.

[0128] Exemplarily, assuming that the offset time period is a time interval corresponding to a preset number of interval units, the wind speed sensor is used to obtain the wind speed at the moment corresponding to each interval unit in the offset time period, that is, to obtain the preset number of wind speeds; based on the preset number of wind speeds, the average wind speed in the offset time period is calculated.

[0129] In a possible implementation, the environmental sensor also includes a light sensor, and the corresponding environmental data is light data. Then, two current temperature data and two offset temperature data corresponding to the two temperature sensors, wind speed data in an offset time period corresponding to the wind speed sensor, and light data in an offset time period corresponding to the light sensor are obtained.

[0130] Among them, the light data in the offset time period is one of the meteorological parameters that affect the temperature balance. Exemplarily, light can directly irradiate the temperature sensor, causing the temperature sensor to absorb this part of energy and convert it into heat energy. This direct radiation of light will increase the temperature of the temperature sensor, thereby affecting its reading. Therefore, in the embodiment of the present application, the influence of light can also be considered, so the light data in the Pan Yi time period corresponding to the light sensor can also be obtained.

[0131] S402, combining two current temperature data and wind speed data to obtain two current combination data corresponding to the two current temperature data respectively; and combining two temperature offset temperature data and wind speed data to obtain two offset combination data corresponding to the two offset temperature data respectively.

[0132] In a possible implementation, based on the two current temperature data and the wind speed data, two current combination data corresponding to the two current temperature data are obtained by combining them through a first preset formula.

[0133] Specifically, the first preset formula is shown in formula (1):

[0134] (1)

[0135] in, E c is the current combination data corresponding to the current temperature data, T c is the current temperature data, vis the wind speed data within the offset time period.

[0136] Similarly, based on the two offset temperature data and the wind speed data, two offset combination data corresponding to the two offset temperature data are obtained by combining them through a second preset formula.

[0137] Specifically, the second preset formula is shown in formula (2):

[0138] (2)

[0139] in, E p is the offset combination data corresponding to the offset temperature data, T p is the offset temperature data, v is the wind speed data within the offset time period.

[0140] Since there is an inverse proportional relationship between the wind speed data and the temperature data, that is, the greater the wind speed data, the lower the temperature data; the smaller the wind speed data, the higher the temperature data.

[0141] Furthermore, in a possible implementation, the environmental data within the offset time period also includes: when the illumination data is present, two combination data corresponding to the two current temperature data are obtained by combining the two current temperature data and the illumination data through a third preset formula.

[0142] Specifically, the third preset formula is shown in formula (3):

[0143] (3)

[0144] in, E c is the current combination data corresponding to the current temperature data, T c is the current temperature data, k is the preset scale factor, I is the illumination data (unit: W / m 2 , watts per square meter).

[0145] Among them, the preset proportional coefficient k Used to quantify how light intensity affects the temperature sensor reading.

[0146] Similarly, based on the two offset temperature data and the illumination data, two offset combination data corresponding to the two offset temperature data are obtained by combining them through a fourth preset formula.

[0147] Specifically, the fourth preset formula is shown in formula (4):

[0148] (4)

[0149] in, E p is the offset combination data corresponding to the offset temperature data, T p is the offset temperature data, k is the preset scale factor, I is the illumination data (unit: W / m 2 , watts per square meter).

[0150] S403: construct a training data set based on two current temperature data, two current combination data, two offset combination data and corresponding target temperature data.

[0151] The training data set includes a plurality of data subsets consisting of two current temperature data, two current combination data, two offset combination data and corresponding target temperature data.

[0152] In a possible implementation, a corresponding six-dimensional quadratic polynomial feature is constructed based on two current temperature data, two current combination data, and two offset combination data; a training data set is constructed based on the corresponding six-dimensional quadratic polynomial feature and the corresponding target temperature data. In this case, the training data set includes multiple data subsets consisting of six-dimensional quadratic polynomial features and corresponding target temperature data.

[0153] Specifically, based on two current temperature data, two current combination data and two offset combination data, the corresponding six-variable quadratic polynomial features are obtained through the general formula of the six-variable quadratic polynomial.

[0154] For ease of understanding, the general formula of the six-variable quadratic polynomial is introduced in detail below in conjunction with formula (5).

[0155] (5)

[0156] in, F is the corresponding polynomial characteristic of the six-variable quadratic function, P is the general formula of a quadratic polynomial of six variables. x is a variable, T c1 is one of the two current temperature data, T c2 is the other of the two current temperature data, E c1 is one of the two current combination data, E c2 is the other of the two current combined data,E p1 One of the two offset combination data, E p2 The other of the two offset combined data. x i express( T c1 , T c2 , E c1 , E c2 , E p1 , E p2 ) i indivual, x j express( T c1 , T c2 , E c1 , E c2 , E p1 , E p2 ) j Among them, a ij , b i and c For the weight coefficient set, it should be noted that a ij , b i and c It is set according to the actual situation. i = j When , it represents the square term of a single variable.

[0157] Polynomial features can create new features by performing power operations and cross products on the original features. These features can capture nonlinear relationships in the data. For regression models, if the data itself has nonlinear relationships, then using only linear features may not fit the data well, and polynomial features can help the model capture these nonlinear relationships, thereby improving the model's predictive performance.

[0158] Since the relationship among the current temperature data, the current combination data and the offset combination data is nonlinear, the nonlinear relationship between them can be captured by a sextuple quadratic polynomial, thereby subsequently improving the prediction capability of the model.

[0159] Furthermore, in a possible implementation, the environmental data within the offset time period also includes: when it is lighting data, the training data set includes multiple data subsets consisting of two current temperature data, four current combination data (current combination data corresponding to two wind speed data and current combination data corresponding to two lighting data), four offset combination data (offset combination data corresponding to two wind speed data and offset combination data corresponding to two lighting data) and corresponding target temperature data.

[0160] S404: Based on the training data set, train a linear regression model to obtain a temperature compensation model.

[0161] The above S404 is the same as S204 in the first embodiment, so for details on the specific implementation of S404, please refer to the specific implementation of S204 in the first embodiment, which will not be repeated here.

[0162] Further, after obtaining the temperature compensation model based on the above S401-S404 (i.e., the temperature compensation model obtained when the environmental data is wind speed data), two current temperature data corresponding to the two temperature sensors and the wind speed data of the offset time period corresponding to the wind speed sensor are obtained; based on the two current temperature data and the wind speed data of the offset time period, the actual temperature data is obtained through the temperature compensation model.

[0163] Further, based on the above S401-S404, a temperature compensation model is obtained when the environmental data is wind speed data and light data, and two current temperature data corresponding to the two temperature sensors, the wind speed data of the offset time period corresponding to the wind speed sensor, and the light data of the offset time period corresponding to the light sensor are obtained; based on the two current temperature data, the wind speed data of the offset time period, and the light data of the offset time period, the actual temperature data is obtained through the temperature compensation model.

[0164] The embodiment of the present application provides a method for constructing a temperature compensation model, including: obtaining two current temperature data and two offset temperature data corresponding to two temperature sensors, and wind speed data within an offset time period; based on the two current temperature data and wind speed data, combining to obtain two current combination data corresponding to the two current temperature data; and based on the two temperature offset temperature data and wind speed data, combining to obtain two offset combination data corresponding to the two offset temperature data; constructing a training data set based on the two current temperature data, the two current combination data, the two offset combination data, and the corresponding target temperature data; based on the training data set, training a linear regression model to obtain a temperature compensation model. The embodiment of the present application focuses on the influence of temperature conduction delay and wind speed, so that the offset temperature data and wind speed data participate in the construction of the temperature compensation model, improve the performance of the temperature compensation model, so that the temperature compensation model constructed by the method of the embodiment of the present application and the two temperature sensors and environmental sensors in the small weather station can compensate the detected temperature in real time, solve the problem of inaccurate temperature measurement of the small weather station in extreme weather, thereby improving the accuracy of temperature measurement of the small weather station.

[0165] Embodiment three:

[0166] Combine the following Figure 5 , a device for constructing a temperature compensation model provided in an embodiment of the present application is introduced in detail.

[0167] like Figure 5 As shown, a device for constructing a temperature compensation model provided in an embodiment of the present application includes the following modules:

[0168] The acquisition module 501 is used to acquire two current temperature data and two offset temperature data corresponding to two temperature sensors, and the environmental data in the offset time period corresponding to the environmental sensor; wherein the current temperature data is the temperature data collected by the temperature sensor at the current time; the offset temperature data is the temperature data collected by the temperature sensor at the offset time, and the offset time is the time corresponding to the preset time interval after the current time; the offset time period is the time period between the current time and the offset time;

[0169] The combination module 502 is used to combine the two current temperature data and the environmental data to obtain a plurality of current combination data corresponding to the two current temperature data respectively; and to combine the two offset temperature data and the environmental data to obtain a plurality of offset combination data corresponding to the two offset temperature data respectively;

[0170] A construction module 503 is used to construct a training data set based on two current temperature data, multiple current combination data, multiple offset combination data, and corresponding target temperature data; wherein the training data set includes multiple data subsets consisting of two current temperature data, multiple current combination data, multiple offset combination data, and corresponding target temperature data;

[0171] The training module 504 is used to train a linear regression model based on a training data set to obtain a temperature compensation model.

[0172] In a possible implementation, the acquisition module 501 is specifically used to obtain two current temperature data and two offset temperature data corresponding to two temperature sensors, and the wind speed data within the offset time period corresponding to the wind speed sensor; the combination module 502 is specifically used to combine the two current combination data corresponding to the two current temperature data based on the two current temperature data and the wind speed data; and to combine the two offset combination data corresponding to the two offset temperature data based on the two offset temperature data and the wind speed data; the construction module 503 is specifically used to construct a training data set based on the two current temperature data, the two current combination data, the two offset combination data, and the corresponding target temperature data.

[0173] In one possible implementation, construction module 503 is specifically used to construct corresponding six-dimensional quadratic polynomial features based on two current temperature data, two current combination data and two offset combination data; and to construct a training data set based on the corresponding six-dimensional quadratic polynomial features and the corresponding target temperature data; wherein the training data set includes multiple data subsets consisting of six-dimensional quadratic polynomial features and corresponding target temperature data.

[0174] In one possible implementation, the combination module 502 is specifically used to combine two current combination data corresponding to the two current temperature data through a first preset formula based on two current temperature data and wind speed data; and to combine two offset combination data corresponding to the two offset temperature data through a second preset formula based on two offset temperature data and wind speed data.

[0175] In one possible implementation, the training module 504 is specifically used to train a linear regression model based on a training data set, and record the corresponding root mean square error and determination coefficient; when the corresponding root mean square error and determination coefficient meet the preset requirements, the training of the linear regression model is terminated to obtain a temperature compensation model.

[0176] The embodiment of the present application provides a device for constructing a temperature compensation model, including: an acquisition module 501, used to obtain two current temperature data and two offset temperature data corresponding to two temperature sensors, and environmental data in an offset time period corresponding to an environmental sensor; a combination module 502, used to combine and obtain multiple current combination data corresponding to the two current temperature data based on the two current temperature data and the environmental data; and based on the two offset temperature data and the environmental data, to combine and obtain multiple offset combination data corresponding to the two offset temperature data; a construction module 503, used to construct a training data set based on the two current temperature data, multiple current combination data, multiple offset combination data, and corresponding target temperature data; a training module 504, used to train a linear regression model based on the training data set to obtain a temperature compensation model. The embodiment of the present application takes into account the influence of temperature conduction delay and other environmental parameters, so that the offset temperature data and environmental data participate in the construction of the temperature compensation model, improve the performance of the temperature compensation model, so that the temperature compensation model constructed by the method of the embodiment of the present application and the two temperature sensors and environmental sensors in the small weather station can compensate the detected temperature in real time, solve the problem of inaccurate temperature measurement of the small weather station in extreme weather, and thus improve the accuracy of temperature measurement of the small weather station.

[0177] It should be noted that each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the method and device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments. The method and device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components indicated as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0178] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for constructing a temperature compensation model, characterized in that: Applied to a small weather station, the small weather station comprises: a large mass body, an environmental sensor and two temperature sensors, the two temperature sensors are placed at different positions of the same medium, one temperature sensor is close to the large mass body, and the other temperature sensor is far away from the large mass body; the method comprises: Acquire two current temperature data and two offset temperature data corresponding to the two temperature sensors, and the environmental data in the offset time period corresponding to the environmental sensor; wherein the current temperature data is the temperature data collected by the temperature sensor at the current time; the offset temperature data is the temperature data collected by the temperature sensor at the offset time, and the offset time is the time corresponding to the preset time interval after the current time; the offset time period is the time period between the current time and the offset time; Based on the two current temperature data and the environmental data, a plurality of current combination data corresponding to the two current temperature data are obtained by combination; and based on the two offset temperature data and the environmental data, a plurality of offset combination data corresponding to the two offset temperature data are obtained by combination; Based on the two current temperature data, the multiple current combination data, the multiple offset combination data, and the corresponding target temperature data, a training data set is constructed; wherein the training data set includes multiple data subsets consisting of the two current temperature data, the multiple current combination data, the multiple offset combination data, and the corresponding target temperature data; Based on the training data set, a linear regression model is trained to obtain a temperature compensation model.

2. The method according to claim 1, characterized in that The environmental sensor includes: a wind speed sensor; the environmental data in the offset time period corresponding to the environmental sensor includes: wind speed data in the offset time period corresponding to the wind speed sensor; The combining of the two current temperature data and the environment data to obtain a plurality of current combination data corresponding to the two current temperature data respectively; and combining of the two offset temperature data and the environment data to obtain a plurality of offset combination data corresponding to the two offset temperature data respectively, includes: Based on the two current temperature data and the wind speed data, two current combination data corresponding to the two current temperature data are obtained by combination; and based on the two offset temperature data and the wind speed data, two offset combination data corresponding to the two offset temperature data are obtained by combination; The constructing of a training data set based on the two current temperature data, the multiple current combination data, the multiple offset combination data, and the corresponding target temperature data includes: A training data set is constructed based on the two current temperature data, the two current combination data, the two offset combination data, and the corresponding target temperature data; wherein the training data set includes multiple data subsets consisting of two current temperature data, two current combination data, two offset combination data and corresponding target temperature data.

3. The method according to claim 2, characterized in that The constructing of a training data set based on the two current temperature data, the two current combination data, the two offset combination data, and the corresponding target temperature data includes: Based on the two current temperature data, the two current combination data and the two offset combination data, construct a corresponding six-variable quadratic polynomial feature; Based on the corresponding six-variable quadratic polynomial features and the corresponding target temperature data, a training data set is constructed; wherein the training data set includes a plurality of data subsets consisting of six-variable quadratic polynomial features and the corresponding target temperature data.

4. The method according to claim 2, characterized in that: The wind speed data within the offset time period includes: an average wind speed within the offset time period.

5. The method according to claim 4, characterized in that The average wind speed during the offset time period is obtained as follows: Acquiring multiple wind speeds within the offset time period through a wind speed sensor; Based on the multiple wind speeds, an average wind speed within the offset time period is calculated.

6. The method according to claim 2, characterized in that The combining, based on the two current temperature data and the wind speed data, to obtain two current combination data corresponding to the two current temperature data respectively comprises: Based on the two current temperature data and the wind speed data, two current combination data corresponding to the two current temperature data are obtained by combining them through a first preset formula; The first preset formula is as follows: ; in, E c is the current combination data corresponding to the current temperature data, T c is the current temperature data, v is the wind speed data within the offset time period; The combining, based on the two offset temperature data and the wind speed data, to obtain two offset combination data corresponding to the two offset temperature data respectively comprises: Based on the two offset temperature data and the wind speed data, two offset combination data corresponding to the two offset temperature data are obtained by combining them through a second preset formula; The second preset formula is as follows: ; in, E p is the offset combination data corresponding to the offset temperature data, T p is the offset temperature data, v is the wind speed data within the offset time period.

7. The method according to claim 2, characterized in that The preset time interval is a time interval corresponding to a preset number of interval units.

8. The method according to claim 1, characterized in that: The step of training a linear regression model based on the training data set to obtain a temperature compensation model includes: Based on the training data set, train a linear regression model and record the corresponding root mean square error and determination coefficient; When the corresponding root mean square error and determination coefficient meet the preset requirements, the training of the linear regression model is terminated to obtain a temperature compensation model.

9. The method according to any one of claims 1 to 8, characterized in that: After training the linear regression model based on the training data set to obtain the temperature compensation model, the method further includes: Acquire two current temperature data corresponding to the two temperature sensors respectively, and environmental data of an offset time period corresponding to the environmental sensor; Based on the two current temperature data and the environmental data of the offset time period, actual temperature data is obtained through the temperature compensation model.

10. A device for constructing a temperature compensation model, characterized in that: Applied to a small weather station, the small weather station comprises: a large mass body, an environmental sensor and two temperature sensors, the two temperature sensors are placed at different positions of the same medium, one temperature sensor is close to the large mass body, and the other temperature sensor is far away from the large mass body; the device comprises: An acquisition module, used to acquire two current temperature data and two offset temperature data corresponding to the two temperature sensors, and environmental data within an offset time period corresponding to the environmental sensor; wherein the current temperature data is the temperature data collected by the temperature sensor at the current time; the offset temperature data is the temperature data collected by the temperature sensor at an offset time, and the offset time is the time corresponding to a preset time interval after the current time; and the offset time period is the time period between the current time and the offset time; A combining module, configured to combine the two current temperature data and the environmental data to obtain a plurality of current combined data corresponding to the two current temperature data respectively; and to combine the two offset temperature data and the environmental data to obtain a plurality of offset combined data corresponding to the two offset temperature data respectively; A construction module, configured to construct a training data set based on the two current temperature data, the multiple current combination data, the multiple offset combination data, and the corresponding target temperature data; wherein the training data set includes multiple data subsets consisting of the two current temperature data, the multiple current combination data, the multiple offset combination data, and the corresponding target temperature data; The training module is used to train a linear regression model based on the training data set to obtain a temperature compensation model.

Images