Infrared temperature measurement method and device based on decision tree regression and electronic equipment

Abstract

The invention provides an infrared temperature measurement method and device based on decision tree regression and electronic equipment. According to the embodiment of the invention, when any infrared temperature measurement device measures the temperature of the target object, the device characteristics of the infrared temperature measurement device, such as the temperature control level and the gain gear, and the environmental influence factors, such as the environmental temperature, are fully considered, so that the accuracy of the measured temperature is ensured, and accurate infrared temperature measurement is realized.

Description

Technical Field

[0001] The present application relates to infrared temperature measurement technology, and in particular to an infrared temperature measurement method, device and electronic equipment based on decision tree regression. Background Art

[0002] In order to ensure the smooth progress of infrared temperature measurement, black bodies are often used to calibrate infrared temperature measurement equipment on site. However, when using black bodies to calibrate infrared temperature measurement equipment on site, the ambient temperature and the characteristics of the infrared temperature measurement equipment itself, such as the temperature control level, are often ignored, which will lead to inaccurate temperature measured by the infrared temperature measurement equipment and temperature errors. Summary of the invention

[0003] The present application provides an infrared temperature measurement method, device and electronic equipment based on decision tree regression to realize infrared temperature measurement based on decision tree regression and improve the temperature measurement accuracy.

[0004] The embodiment of the present application provides an infrared temperature measurement method based on decision tree regression, the method comprising:

[0005] Obtain N pieces of sample data; the N pieces of sample data include sample data obtained when any specified infrared temperature measuring device performs infrared temperature measurement on a black body at different target temperatures T_target under fixed conditions; wherein the sample data obtained when any specified infrared temperature measuring device performs infrared temperature measurement on a black body at any target temperature T_target is related to the ambient temperature of the specified infrared temperature measuring device, the device characteristics of the specified infrared temperature measuring device, and the temperature measured by the specified infrared temperature measuring device; the device characteristics at least include: current temperature control level, current gain gear;

[0006] Divide the N sample data into a training set and a test set; train a decision tree regression model using the training set under different model hyperparameters, and test each trained decision tree regression model using the test set to determine the optimal decision tree regression model;

[0007] The optimal decision tree regression model is used to output the corrected temperature T1 of the target object based on the input data obtained when the target infrared temperature measuring device performs infrared temperature measurement on the target object, so that the corrected temperature T1 is combined with the current data corresponding to the fixed data type to determine the real temperature T_real of the target object; the fixed data type is the data type to which each data in the fixed condition belongs;

[0008] The input data is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device, and the temperature measured by the target infrared temperature measuring device; the device characteristics at least include: the current temperature control level and the current gain gear.

[0009] The embodiment of the present application provides an infrared temperature measurement method based on decision tree regression, the method comprising:

[0010] Obtain input data corresponding to the target infrared temperature measuring device; the input data corresponding to the target infrared temperature measuring device is data corresponding to when the target infrared temperature measuring device performs infrared temperature measurement on the target object, and is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device, and the temperature measured by the target infrared temperature measuring device; the device characteristics at least include: current temperature control level, current gain gear;

[0011] Input the input data into the optimal decision tree regression model to obtain the corrected temperature T1 of the target object; the optimal decision tree regression model is determined under fixed conditions according to the first method as above;

[0012] The real temperature T_real of the target object is determined based on the corrected temperature T1 of the target object, the fixed condition, and current data corresponding to a fixed data type; the fixed data type is the data type to which each data in the fixed condition belongs.

[0013] The embodiment of the present application provides an infrared temperature measurement device based on decision tree regression, the device comprising:

[0014] A data processing unit is used to obtain N pieces of sample data; the N pieces of sample data include sample data obtained when any designated infrared temperature measuring device performs infrared temperature measurement on a black body at different target temperatures T_target under fixed conditions; wherein the sample data obtained when any designated infrared temperature measuring device performs infrared temperature measurement on a black body at any target temperature T_target is related to the ambient temperature of the designated infrared temperature measuring device, the device characteristics of the designated infrared temperature measuring device, and the temperature measured by the designated infrared temperature measuring device; the device characteristics at least include: current temperature control level, current gain gear;

[0015] A model unit, used for dividing the N sample data into a training set and a test set; training a decision tree regression model using the training set under different model hyperparameters, and testing each trained decision tree regression model using the test set to determine an optimal decision tree regression model;

[0016] The optimal decision tree regression model is used to output the corrected temperature T1 of the target object based on the input data obtained when the target infrared temperature measuring device performs infrared temperature measurement on the target object, so that the corrected temperature T1 is combined with the current data corresponding to the fixed data type to determine the real temperature T_real of the target object; the fixed data type is the data type to which each data in the fixed condition belongs;

[0017] The input data is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device, and the temperature measured by the target infrared temperature measuring device; the device characteristics at least include: the current temperature control level and the current gain gear.

[0018] The embodiment of the present application provides an infrared temperature measurement device based on decision tree regression, the device comprising:

[0019] An obtaining unit is used to obtain input data corresponding to a target infrared temperature measuring device; the input data corresponding to the target infrared temperature measuring device is data corresponding to when the target infrared temperature measuring device performs infrared temperature measurement on a target object, and is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device, and the temperature measured by the target infrared temperature measuring device; the device characteristics at least include: a current temperature control level and a current gain gear;

[0020] A processing unit, used for inputting the input data into an optimal decision tree regression model to obtain a corrected temperature T1 of the target object; the optimal decision tree regression model is determined under fixed conditions according to the first method as described above; and,

[0021] The real temperature T_real of the target object is determined based on the corrected temperature T1 of the target object, the fixed condition, and current data corresponding to a fixed data type; the fixed data type is the data type to which each data in the fixed condition belongs.

[0022] An embodiment of the present application provides an electronic device, the electronic device comprising: a processor and a machine-readable storage medium;

[0023] The machine-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the steps in the above method are implemented.

[0024] It can be seen from the above technical solutions that in this embodiment, when any infrared temperature measuring device measures the temperature of the target object, the device characteristics of the infrared temperature measuring device, such as the temperature control level, the gain gear, etc., and the environmental influencing factors, such as the ambient temperature, etc., are fully considered, which ensures the accuracy of the measured temperature and realizes accurate infrared temperature measurement;

[0025] Furthermore, the training data in the training set used in the present embodiment when training the decision tree regression model also fully considers the equipment characteristics of the infrared temperature measuring device under fixed conditions, such as the temperature control level, the gain gear, etc. and environmental influencing factors such as the ambient temperature, etc., and tests the trained decision tree regression model based on test data different from the training data (which also fully considers the equipment characteristics of the infrared temperature measuring device under fixed conditions, such as the temperature control level, the gain gear, etc. and environmental influencing factors such as the ambient temperature, etc.) to obtain the optimal decision tree regression model, so as to first determine the corrected temperature T1 when the target infrared temperature measuring device performs infrared temperature measurement on the target object based on the optimal decision tree regression model, and then the real temperature T_real of the target object can be determined based on the corrected temperature T1 combined with the current data under the fixed data type (the data type belonging to the fixed condition), which further improves the accuracy of infrared temperature measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0027] Figure 1 A flow chart of the method provided in the embodiment of the present application;

[0028] Figure 2 This is a specific implementation flow chart of Example 1 of the present application;

[0029] Figure 3 This is a specific implementation flow chart of Example 2 of the present application;

[0030] Figure 4 A structural diagram of a device provided in an embodiment of the present application;

[0031] Figure 5 Another device structure diagram provided for an embodiment of the present application;

[0032] Figure 6 Provided in the embodiments of this application Figure 4 or Figure 5 Hardware structure diagram of the device shown. DETAILED DESCRIPTION

[0033] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0034] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0035] In order to enable those skilled in the art to better understand the technical solutions provided by the embodiments of the present application and to make the above-mentioned purposes, features and advantages of the embodiments of the present application more obvious and understandable, the technical solutions in the embodiments of the present application are further described in detail below in conjunction with the accompanying drawings.

[0036] See also Figure 1 , Figure 1 This is a flow chart of a method provided in an embodiment of the present application. The process can be applied to an electronic device. For example, the electronic device here can be a server, a terminal, etc., which is not specifically limited in this embodiment.

[0037] like Figure 1 As shown, the process may include the following steps:

[0038] Step 101 , obtaining N pieces of sample data, wherein the N pieces of sample data include sample data obtained when any designated infrared temperature measurement device performs infrared temperature measurement on a black body at different target temperatures (T_target) under fixed conditions.

[0039] As an embodiment, the sample data obtained when any designated infrared temperature measuring device performs infrared temperature measurement on a black body at any target temperature T_target is related to the ambient temperature of the designated infrared temperature measuring device, the device characteristics of the designated infrared temperature measuring device (such as the current temperature control level, the current gain gear, etc.), and the temperature measured when the designated infrared temperature measuring device performs infrared temperature measurement on a black body at the target temperature T_target. The above N sample data will be described by example below, and will not be repeated here.

[0040] Step 102, divide the N sample data into a training set and a test set; use the training set to train the decision tree regression model under different model hyperparameters, and use the test set to test each trained decision tree regression model to determine the optimal decision tree regression model.

[0041] Optionally, in this embodiment, a set of model hyperparameters is pre-set. For example, the model hyperparameter set includes: a model depth subset (denoted as max_depth) and a learning rate subset (denoted as learning_rate). Here, the model depth subset includes multiple different model depths. For example, the multiple model depths can be increased in sequence with a step size of 1. Optionally, the range of each model depth included in the model depth subset is 1 to 20. As for the learning rate subset, it can be set according to actual needs, for example, it is set to: [1, 0.3, 0.1, 0.03, 0.01, 0.003, 0.001, 0.0003, 0.0001].

[0042] Based on this, in this step 102, training the decision tree regression model using the training set under different model hyperparameters includes: traversing the model hyperparameter set, and using the traversed model hyperparameters as the current model hyperparameters; training the corresponding decision tree regression model using the training set under the current model hyperparameters; if there are still model hyperparameters that have not been traversed in the model hyperparameter set, continue to traverse the model hyperparameter set, and return the traversed model hyperparameters as the current model hyperparameters.

[0043] Optionally, if the model hyperparameter set includes: a model depth subset and a learning rate subset, then in this embodiment, traversing the model hyperparameter set may include: traversing the model depth subset and the learning rate subset respectively. Correspondingly, the traversed model hyperparameters may be the current model depth and the current learning rate traversed.

[0044] In this embodiment, a commonly used regression model training method such as the XGBRegressor regression model can be used to train a corresponding decision tree regression model according to the above training set. That is, when the model is trained based on the training set under each traversal of the current model hyperparameters such as the current model depth and the current learning rate, the loss function requirements in the regression model training method such as the XGBRegressor regression model training method will be combined to determine whether the training iteration is completed. Once it is determined to be completed, the model at this time will be determined as the trained decision tree regression model.

[0045] Afterwards, each decision tree regression model trained is tested using the test set to determine the optimal decision tree regression model. As an embodiment, this embodiment may first subdivide the test set into a first data set and a second data set; wherein, each decision tree regression model trained is tested using the first data set to obtain a reference decision tree regression model that meets the test requirements. For example, for each sample data in the first data set, the data except T_target contained in the sample data is recorded as test data, and T_target is recorded as the target temperature corresponding to the test data. The test data is input into the decision tree regression model that currently needs to be tested to obtain the corrected temperature corresponding to the test data; if the test data above the set proportion in the first data set meets the following requirements: the difference between the corresponding corrected temperature and the corresponding target temperature T_target meets the set difference requirements such as ±1 or ±1%, etc., then it means that the decision tree regression model at this time is a reference decision tree regression model that meets the test requirements. On the contrary, if less than the set proportion of test data in the first data set meets the following requirements: the difference between the corresponding corrected temperature and the corresponding target temperature T_target meets the set difference requirement such as ±1 or ±1%, etc., then it means that the decision tree regression model at this time is not a reference decision tree regression model that meets the test requirements.

[0046] Afterwards, the second data set is used to verify each reference decision tree regression model to obtain an optimal decision tree regression model that meets the verification requirements. Optionally, in this embodiment, a loss function such as mean square error can be set, and each reference decision tree regression model is verified by means of the loss function and using the second data set as a verification set, and finally an optimal decision tree regression model (i.e., one that meets the verification requirements) is obtained.

[0047] In this embodiment, the optimal decision tree regression model is used to output the corrected temperature T1 of the target object based on the input data obtained when the target infrared temperature measurement device performs infrared temperature measurement on the target object, so that the corrected temperature T1 is combined with the current data corresponding to the fixed data type to determine the real temperature T_real of the target object; the fixed data type is the data type to which each data in the fixed condition belongs.

[0048] The input data is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device, and the temperature measured by the target infrared temperature measuring device; the device characteristics at least include: the current temperature control level and the current gain gear. Here, the target infrared temperature measuring device is different from any of the above-mentioned designated infrared temperature measuring devices or is one of the designated infrared temperature measuring devices, which is not specifically limited in this embodiment.

[0049] From the above, it can be seen that in this embodiment, when any infrared temperature measuring device measures the temperature of the target object, the device characteristics of the infrared temperature measuring device such as the temperature control level, gain gear, etc. and environmental influencing factors such as ambient temperature are fully considered, which ensures the accuracy of the measured temperature and realizes accurate infrared temperature measurement.

[0050] Furthermore, the training data in the training set used in the present embodiment when training the decision tree regression model also fully considers the equipment characteristics of the infrared temperature measuring device under fixed conditions, such as the temperature control level, the gain gear, etc. and environmental influencing factors such as the ambient temperature, etc., and tests the trained decision tree regression model based on test data different from the training data (which also fully considers the equipment characteristics of the infrared temperature measuring device under fixed conditions, such as the temperature control level, the gain gear, etc. and environmental influencing factors such as the ambient temperature, etc.) to obtain the optimal decision tree regression model, so as to first determine the corrected temperature T1 when the target infrared temperature measuring device performs infrared temperature measurement on the target object based on the optimal decision tree regression model, and then the real temperature T_real of the target object can be determined based on the corrected temperature T1 combined with the current data under the fixed data type (the data type belonging to the fixed condition), which further improves the accuracy of infrared temperature measurement.

[0051] In order to make the above Figure 1 The process shown is clearer, and the following is a detailed description of the process in conjunction with the specific embodiments. Figure 1 The process shown is described as follows:

[0052] Embodiment 1:

[0053] See also Figure 2 , Figure 2 This is a specific implementation flow chart of Example 1 of this application. Figure 2 As shown, the process may include the following steps:

[0054] Step 201 , obtaining N pieces of sample data under the following fixed conditions: fixed humidity (denoted as humidity), fixed blackbody emissivity (denoted as emiss), and fixed blackbody imaging pixel size (denoted as D).

[0055] Corresponding to the above fixed conditions, the data types to which the fixed conditions belong (recorded as fixed data types) are: humidity type, emissivity type, and imaging pixel size type.

[0056] As an embodiment, in this embodiment 1, the above N pieces of sample data may be: under fixed humidity, fixed blackbody emissivity, and fixed blackbody imaging pixel size D, the initial data corresponding to each designated infrared temperature measuring device is obtained: the temperatures Temp1, Temp2, and Temp3 measured by the temperature sensors deployed at three different positions on the designated infrared temperature measuring device, the integration time of the designated infrared temperature measuring device (denoted as Tint), the ambient temperature of the designated infrared temperature measuring device (denoted as Env), the current device characteristics of the designated infrared temperature measuring device such as the temperature control level TEC, the gain gear sen, etc., and the temperature measured by the designated infrared temperature measuring device when performing infrared temperature measurement on a blackbody at any target temperature T_target (denoted as the response value Gray). Optionally, each piece of initial data obtained may be represented by the following formula: [Temp1, Temp2, Temp3, Tint, Env, TEC, sen, Gray, T_target].

[0057] The obtained initial data is subjected to data preprocessing such as noise removal, and eventually N pieces of sample data (for example, N> the set number such as 5000) are obtained.

[0058] In this embodiment, the number of designated infrared temperature measuring devices can be set according to actual needs, for example, the number n of designated infrared temperature measuring devices is greater than 70.

[0059] In this embodiment, the designated infrared temperature measurement device includes at least a detector, a cavity, and a housing; the temperature sensors at the above three different positions include: a temperature sensor deployed at an adjacent position of the detector, a temperature sensor deployed in the cavity, and a temperature sensor deployed on the device housing.

[0060] In this embodiment, the temperature (recorded as the response value Gray) measured when the designated infrared temperature measuring device performs infrared temperature measurement on a black body at a target temperature T_target may be the temperature at the center or a designated position of the black body, or may be the temperature at a designated position, such as a center position, in an infrared image obtained when the designated infrared temperature measuring device performs infrared temperature measurement on the black body, which is not specifically limited in this embodiment.

[0061] In this embodiment, the black body imaging pixel size refers to the size of pixels in an infrared image obtained when a designated infrared temperature measuring device performs infrared temperature measurement on the black body.

[0062] Step 202: Obtain an optimal decision tree model based on the N pieces of sample data.

[0063] Optionally, in this embodiment, N pieces of sample data may be first divided into a training set, a test set (the first data set mentioned above), and a validation set (the second data set mentioned above). For example, the number of sample data in the training set is N*0.8*0.8), the number of sample data in the test set is N*0.8*0.2), and the number of sample data in the validation set is N*0.2.

[0064] After that, the model hyperparameter set is traversed. For example, the model hyperparameter set includes: model depth subset and learning rate subset. Taking the model depth subset including the range of each model depth from 1 to 20, and the learning rate subset as [1, 0.3, 0.1, 0.03, 0.01, 0.003, 0.001, 0.0003, 0.0001] as an example, a model depth and a learning rate will be traversed each time. At the currently traversed model depth and learning rate, the model is trained using the training set, such as using the training set and a regression model based on the gradient boosting algorithm (XGBRegressor regression model) to train the model, so as to train a decision tree regression model at the currently traversed model depth and learning rate. Taking the model depth subset including the range of model depths from 1 to 20 and the learning rate subset of [1, 0.3, 0.1, 0.03, 0.01, 0.003, 0.001, 0.0003, 0.0001] as an example, after 20*9 (20 model depths, 9 learning rates) training times, a maximum of 20*9 decision tree regression models will be trained.

[0065] Afterwards, each decision tree regression model trained is tested using the test set to determine the optimal decision tree regression model. As an embodiment, the following steps may be performed for each decision tree regression model: for each sample data in the test set, the data contained in the sample data except T_target is recorded as the test data, and the T_target is recorded as the target temperature corresponding to the test data, and the test data is input into the decision tree regression model to obtain the corrected temperature corresponding to the test data; if the test data in the test set that exceeds the set ratio meets the following requirements: the difference between the corresponding corrected temperature and the corresponding target temperature T_target meets the set difference requirements such as ±1 or ±1%, etc., then it means that the decision tree regression model at this time is a reference decision tree regression model that meets the test requirements. On the contrary, if the test data in the test set that is less than the set ratio meets the following requirements: the difference between the corresponding corrected temperature and the corresponding target temperature T_target meets the set difference requirements such as ±1 or ±1%, etc., then it means that the decision tree regression model at this time is a reference decision tree regression model that does not meet the test requirements.

[0066] Afterwards, the validation set is used to validate each reference decision tree regression model to obtain an optimal decision tree regression model that meets the validation requirements. Optionally, in this embodiment, a loss function such as mean square error can be set, and each reference decision tree regression model can be validated by means of the loss function and the validation set, and finally an optimal (i.e., one that meets the validation requirements) optimal decision tree regression model can be obtained. Afterwards, the optimal decision tree regression model can be applied to perform temperature correction, as shown in step 203.

[0067] Step 203, when the target infrared temperature measuring device performs infrared temperature measurement on the target object, the measured temperature of the target object measured by the target infrared temperature measuring device is obtained based on the optimal decision tree regression model, and then corrected to obtain the corrected temperature T1 of the target object.

[0068] In this embodiment, the input data obtained when the target infrared temperature measuring device performs infrared temperature measurement on the target object can be first obtained. Based on the description of the above sample data, the data type of the input data here is the same as the data type of the data in the above sample data except for the above target temperature. For example, the input data is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device (including at least: the current temperature control level, the current gain gear, etc.), and the measured temperature measured by the target infrared temperature measuring device.

[0069] As an embodiment, the input data here may include: the temperature detected by the temperature sensors deployed at different positions of the target infrared temperature measuring device, the integration time of the target infrared temperature measuring device, the ambient temperature of the target infrared temperature measuring device, the current temperature control level of the target infrared temperature measuring device, the current gain gear, and the temperature measured by the target infrared temperature measuring device when performing infrared temperature measurement on the target object. Here, the input data can be expressed by the following formula: [cur_Temp1, cur_Temp2, cur_Temp3, cur_Tint, cur_Env, cur_TEC, cur_sen, cur_Gray].

[0070] Among them, cur_Temp1, cur_Temp2, and cur_Temp3 respectively represent the temperatures detected by the temperature sensors deployed at three different positions of the target infrared temperature measuring device (specifically refer to the adjacent positions of the detectors, the cavity, and the housing described above). cur_Tint represents the integration time of the target infrared temperature measuring device, cur_Env represents the ambient temperature of the target infrared temperature measuring device, cur_TEC and cur_sen represent the current temperature control level and the current gain gear of the target infrared temperature measuring device respectively; cur_Gray represents the temperature measured by the target infrared temperature measuring device when performing infrared temperature measurement on the target object.

[0071] By inputting the input data into the optimal decision tree regression model, the corrected temperature T1 of the target object can be obtained.

[0072] It should be emphasized that the above steps 201 to 202 are not necessarily executed when any target infrared temperature measurement device performs infrared temperature measurement on the target object. The optimal decision tree regression model is only obtained first when there is no optimal decision tree regression model currently.

[0073] Step 204: Calculate the real temperature T_real of the target object.

[0074] Since the above optimal decision tree regression model is trained under the above fixed humidity, fixed black body emissivity emiss, and fixed black body imaging pixel size D, only the characteristics of the infrared temperature measurement device itself are considered, which also shows that the above corrected temperature T1 is only related to the characteristics of the infrared temperature measurement device itself. Based on this, this embodiment will further consider the humidity, ambient temperature, target object imaging pixel size, and target object emissivity of the target infrared temperature measurement device at present, and adjust the above corrected temperature T1 based on these considerations to obtain the real temperature T_real of the target object.

[0075] As an embodiment, the real temperature T_real of the target object is determined by:

[0076] The above-mentioned fixed humidity, fixed blackbody emissivity, fixed blackbody imaging pixel size, as well as the current humidity of the target infrared temperature measurement device, ambient temperature, target object imaging pixel size, target object emissivity, the obtained conversion coefficient coeff, and the above-mentioned T1 are input into the set conversion algorithm to obtain the real temperature T_real of the target object.

[0077] Considering that the above-mentioned fixed humidity and fixed blackbody emissivity have little effect on determining the real temperature T_real of the target object, the real temperature T_real of the target object can be simply determined by the following formula: T_real = f1 (cur_humidity, cur_emiss, D, curD, temp4, coeff, T1). Here, f1 represents the above-mentioned first setting conversion algorithm. cur_humidity and cur_emiss represent the humidity of the target infrared temperature measuring device and the emissivity of the target object respectively, D represents the above-mentioned fixed blackbody imaging pixel size, and curD represents the target object imaging pixel size (specifically, the size of the pixel in the infrared image obtained when the target infrared temperature measuring device performs infrared temperature measurement on the target object). temp4 represents the current ambient temperature of the target infrared temperature measuring device to suppress the sudden change of ambient temperature from affecting the above-mentioned real temperature. coeff represents the obtained conversion coefficient.

[0078] As an example, T_real=f1(cur_humidity, cur_emiss, D, curD, temp4, coeff, T1) can be expanded to: T_real=T4 / (curD / D); Optionally, T4=f3(cur_humidity)*T3. T3=[cur_emiss*T2 4 +(1-cur_emiss)*temp4】 1 / 4 T2 = k1 (calibrated ambient temperature - temp4) + b1 + T1. b1 is the setting parameter. f3 is the setting conversion formula. Finally, the real temperature T_real of the target object can be determined.

[0079] So far, completed Figure 2 The process shown.

[0080] pass Figure 2 The process shown realizes training the optimal decision tree regression model under fixed humidity, fixed blackbody emissivity, and fixed blackbody imaging pixel size, so that when the target infrared temperature measuring device performs infrared temperature measurement on the target object, the measured temperature of the target object measured by the target infrared temperature measuring device is obtained based on the optimal decision tree regression model for correction to obtain the corrected temperature T1 of the target object; and combined with the above-mentioned fixed blackbody imaging pixel size, the current humidity of the target infrared temperature measuring device, the ambient temperature, the target object imaging pixel size, the emissivity of the target object, the obtained conversion coefficient coeff, and the above-mentioned T1, the above-mentioned T1 is converted into the real temperature T_real of the target object. Finally, the determination of the real temperature T_real of the target object is realized.

[0081] Embodiment 2 is described below:

[0082] Embodiment 2:

[0083] See also Figure 3 , Figure 3 This is a specific implementation flow chart provided in Example 2 of this application. Figure 3 As shown, the process may include the following steps:

[0084] Step 301 , obtaining N pieces of sample data under the following fixed conditions: a fixed blackbody emissivity (denoted as emiss), a fixed temperature control level, and a fixed gain gear.

[0085] For the above fixed conditions, the data types to which the fixed conditions belong (recorded as fixed data types) are: emissivity type, temperature control level type, and gain gear type.

[0086] As an embodiment, in this embodiment 2, the above N pieces of sample data may be: under a fixed blackbody emissivity, a fixed temperature control level, and a fixed gain gear, the initial data corresponding to each designated infrared temperature measuring device is obtained: the current environment temperature Env and humidity humidity of the designated infrared temperature measuring device, and the temperature measured by the designated infrared temperature measuring device when performing infrared temperature measurement on any blackbody at any target temperature T_target under the current environment temperature Env and humidity humidity (recorded as the response value Gray), the imaging pixel size of the blackbody on the target surface (recorded as cur_D), and the target temperature T_target. Optionally, each piece of initial data obtained may be represented by the following formula: [Env, humidity, cur_d, Gray, T_target].

[0087] The obtained initial data is subjected to data preprocessing such as noise removal, and eventually N pieces of sample data (for example, N> the set number such as 5000) are obtained.

[0088] In this embodiment, the temperature (recorded as the response value Gray) measured by any designated infrared temperature measuring device when performing infrared temperature measurement on any black body at any target temperature T_target may be the temperature at the center or designated position of the black body, or may be the temperature at a designated position in the infrared image obtained when the designated infrared temperature measuring device performs infrared temperature measurement on the black body, such as the center position, which is not specifically limited in this embodiment.

[0089] In this embodiment, the black body imaging pixel size refers to the size of pixels in an infrared image obtained when a designated infrared temperature measuring device performs infrared temperature measurement on the black body.

[0090] Step 302: Obtain an optimal decision tree model based on the N sample data.

[0091] The training method of step 302 is similar to step 203 and will not be described again here.

[0092] Step 303, when the target infrared temperature measuring device performs infrared temperature measurement on the target object, the measured temperature of the target object measured by the target infrared temperature measuring device is obtained based on the optimal decision tree regression model and corrected to obtain the corrected temperature T1 of the target object.

[0093] In this embodiment, the input data obtained when the target infrared temperature measuring device performs infrared temperature measurement on the target object can be first obtained. Based on the description of the above sample data, the data type of the input data here is the same as the data type of the data in the above sample data except for the above target temperature. For example, the input data is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device (including at least: the current temperature control level, the current gain gear, etc.), and the measured temperature measured by the target infrared temperature measuring device.

[0094] As an embodiment, the input data here may include: the current ambient temperature and humidity of the target infrared temperature measuring device, the temperature measured by the target infrared temperature measuring device when performing infrared temperature measurement on the target object, and the pixel size of the target object imaging. Here, the input data can be expressed by the following formula: [cur_Env, cur_humidity, cur_Gray, curD].

[0095] Among them, cur_Env and cur_humidity respectively represent the current ambient temperature and humidity of the target infrared temperature measuring device; cur_Gray represents the temperature measured by the target infrared temperature measuring device when performing infrared temperature measurement on the target object; curD represents the imaging pixel size of the target object.

[0096] By inputting the input data into the optimal decision tree regression model, the corrected temperature T1 of the target object can be obtained.

[0097] It should be emphasized that the above steps 301 to 302 are not necessarily executed when any target infrared temperature measurement device performs infrared temperature measurement on the target object. The optimal decision tree regression model is only obtained when there is no optimal decision tree regression model currently.

[0098] Step 304: Calculate the real temperature T_real of the target object.

[0099] Since the above optimal decision tree regression model is trained under the above fixed blackbody emissivity, fixed temperature control level, and fixed gain gear, this embodiment will further consider the current temperature control level, gain gear of the target infrared temperature measuring device, and the emissivity of the target object. Based on these considerations, the above corrected temperature T1 is adjusted to obtain the real temperature T_real of the target object.

[0100] As an embodiment, the real temperature T_real of the target object is determined by:

[0101] The above-mentioned fixed blackbody emissivity, fixed temperature control level, fixed gain gear, as well as the emissivity of the target object, the current temperature control level and gain gear of the target infrared temperature measuring device, the temperature detected by the temperature sensors deployed at different positions of the target infrared temperature measuring device, and the current ambient temperature of the target infrared temperature measuring device are input into the second setting conversion algorithm to obtain the real temperature T_real of the target object.

[0102] Considering that the above-mentioned fixed blackbody emissivity, fixed temperature control level, fixed gain gear and imaging pixel size of the target object have little effect on determining the real temperature T_real of the target object, the real temperature T_real of the target object can be simply determined by the following formula: T_real = f2(cur_emiss, cur_TEC, cur_Sen, cur_temp1, cur_temp2, cur_temp3, temp4).

[0103] Here, f2 represents the second setting conversion algorithm. cur_emiss represents the emissivity of the target object, cur_TEC and cur_Sen represent the current temperature control level and gain gear of the target infrared temperature measuring device respectively; cur_temp1, cur_temp2, and cur_temp3 represent the temperatures detected by the temperature sensors deployed at three different positions of the target infrared temperature measuring device respectively; temp4 represents the current ambient temperature of the target infrared temperature measuring device to suppress the sudden change of ambient temperature from affecting the above-mentioned real temperature.

[0104] As an example, T_real=f2(cur_emiss, cur_TEC, cur_Sen, cur_temp1, cur_temp2, cur_temp3, temp4) can be expanded as follows:

[0105] T_real=

cur_emiss*T2 4 +(1-cur_emiss)*temp4

[0106] [calibrated temperature of the first position - cur_temp1] + b1 + k2 [calibrated temperature of the second position - cur_temp2] + b2 + k3 [calibrated temperature of the third position - cur_temp3] + b3.

[0107] Among them, the first position calibration temperature is the calibration temperature corresponding to the temperature sensor that detects temperature cur_temp1 on the target infrared temperature measuring device; the second position calibration temperature is the calibration temperature corresponding to the temperature sensor that detects temperature cur_temp2 on the target infrared temperature measuring device; the third position calibration temperature is the calibration temperature corresponding to the temperature sensor that detects temperature cur_temp3 on the target infrared temperature measuring device.

[0108] Among them, k1, b1, k2, b2, k3, b3 are determined based on cur_TEC, cur_Sen and the obtained conversion coefficient coeff. For example, [k1, b1, k2, b2, k3, b3] = coeff [TEC] [Sen].

[0109] Finally, the real temperature T_real of the target object can be determined.

[0110] So far, completed Figure 3 The process shown.

[0111] pass Figure 3 The process shown realizes training the optimal decision tree regression model under the fixed black body emissivity, fixed temperature control level and gain gear, so that when the target infrared temperature measuring device performs infrared temperature measurement on the target object, the measured temperature of the target object measured by the target infrared temperature measuring device is obtained based on the optimal decision tree regression model for correction, and the corrected temperature T1 of the target object is obtained; and combined with the above-mentioned fixed black body emissivity, fixed temperature control level, fixed gain gear, and the emissivity of the target object, the current temperature control level and gain gear of the target infrared temperature measuring device, the temperature detected by the temperature sensors deployed at different positions of the target infrared temperature measuring device, and the current ambient temperature of the target infrared temperature measuring device, the above T1 is converted into the real temperature T_real of the target object. Finally, the determination of the real temperature T_real of the target object is realized.

[0112] The method provided in the embodiment of the present application is described above. The device provided in the embodiment of the present application is described below:

[0113] See also Figure 4 , Figure 4 The device structure diagram provided in the embodiment of the present application includes:

[0114] A data processing unit is used to obtain N pieces of sample data; the N pieces of sample data include sample data obtained when any designated infrared temperature measuring device performs infrared temperature measurement on a black body at different target temperatures T_target under fixed conditions; wherein the sample data obtained when any designated infrared temperature measuring device performs infrared temperature measurement on a black body at any target temperature T_target is related to the ambient temperature of the designated infrared temperature measuring device, the device characteristics of the designated infrared temperature measuring device, and the temperature measured by the designated infrared temperature measuring device; the device characteristics at least include: current temperature control level, current gain gear;

[0115] A model unit, used for dividing the N sample data into a training set and a test set; training a decision tree regression model using the training set under different model hyperparameters, and testing each trained decision tree regression model using the test set to determine an optimal decision tree regression model;

[0116] The optimal decision tree regression model is used to output the corrected temperature T1 of the target object based on the input data obtained when the target infrared temperature measuring device performs infrared temperature measurement on the target object, so that the corrected temperature T1 is combined with the current data corresponding to the fixed data type to determine the real temperature T_real of the target object; the fixed data type is the data type to which each data in the fixed condition belongs;

[0117] The input data is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device, and the temperature measured by the target infrared temperature measuring device; the device characteristics at least include: the current temperature control level and the current gain gear.

[0118] As an embodiment, the training of the decision tree regression model using training sets under different model hyperparameters includes:

[0119] Traverse the model hyperparameter set and use the traversed model hyperparameters as the current model hyperparameters;

[0120] Use the training set to train the corresponding decision tree regression model under the current model hyperparameters;

[0121] If there are still model hyperparameters that have not been traversed in the model hyperparameter set, continue to traverse the model hyperparameter set and return the traversed model hyperparameters as the current model hyperparameters.

[0122] As an embodiment, the model hyperparameter set includes: a model depth subset, a learning rate subset;

[0123] The traversing the model hyperparameter set includes: traversing the model depth subset and the learning rate subset respectively;

[0124] The current model hyperparameters include the current model depth and the current learning rate.

[0125] As an embodiment, the test set includes a first data set and a second data set;

[0126] The method of using the test set to test each decision tree regression model trained to determine the optimal decision tree regression model includes:

[0127] Using the first data set to test each trained decision tree regression model to obtain a reference decision tree regression model that meets the test requirements;

[0128] The second data set is used to verify each reference decision tree regression model to obtain an optimal decision tree regression model that meets the verification requirements.

[0129] As an embodiment, the fixed data types include: humidity type, black body emissivity type, black body imaging pixel size type; the fixed conditions include: fixed humidity, fixed black body emissivity, fixed black body imaging pixel size;

[0130] The sample data obtained when any designated infrared temperature measuring device performs infrared temperature measurement on a black body at any target temperature T_target includes: the temperature detected by the temperature sensors deployed at different positions of the designated infrared temperature measuring device, the integration time of the designated infrared temperature measuring device, the ambient temperature of the designated infrared temperature measuring device, the current temperature control level and the current gain gear, the target temperature T_target, and the temperature measured when the designated infrared temperature measuring device performs infrared temperature measurement on a black body at the target temperature T_target;

[0131] The input data includes: the temperature detected by the temperature sensors deployed at different positions of the target infrared temperature measuring device, the integration time of the target infrared temperature measuring device, the ambient temperature of the target infrared temperature measuring device, the current temperature control level of the target infrared temperature measuring device, the current gain gear, and the temperature measured by the target infrared temperature measuring device when performing infrared temperature measurement on the target object;

[0132] The current data includes: the current humidity, ambient temperature, target object imaging pixel size, and target object emissivity of the target infrared temperature measuring device.

[0133] As an embodiment, the real temperature T_real is determined by:

[0134] The fixed humidity, fixed blackbody emissivity, fixed blackbody imaging pixel size, the current humidity of the target infrared temperature measurement device, the ambient temperature, the target object imaging pixel size, the emissivity of the target object, the obtained conversion coefficient coeff, and the T1 are input into the first setting conversion algorithm to obtain the real temperature T_real of the target object.

[0135] As an embodiment, the fixed data types include: black body emissivity type, temperature control level type, and gain gear type; the fixed conditions include: fixed black body emissivity, fixed temperature control level, and fixed gain gear;

[0136] The sample data obtained when any designated infrared temperature measuring device performs infrared temperature measurement on a black body at any target temperature T_target includes: the current ambient temperature and humidity of the designated infrared temperature measuring device, the target temperature T_target, the temperature measured when the designated infrared temperature measuring device performs infrared temperature measurement on a black body at the target temperature T_target, and the black body imaging pixel size;

[0137] The input data includes: the current ambient temperature and humidity of the target infrared temperature measuring device, the temperature measured by the target infrared temperature measuring device when performing infrared temperature measurement on the target object, and the imaging pixel size of the target object;

[0138] The current data includes: the temperature detected by the temperature sensors deployed at different positions of the target infrared temperature measuring device, the current ambient temperature of the target infrared temperature measuring device, the emissivity of the target object, the current temperature control level and gain gear of the target infrared temperature measuring device.

[0139] As an embodiment, the real temperature T_real is expressed by the following formula:

[0140] The fixed blackbody emissivity, the fixed temperature control level, the fixed gain gear, the emissivity of the target object, the current temperature control level and gain gear of the target infrared temperature measuring device, the temperature detected by the temperature sensors deployed at different positions of the target infrared temperature measuring device, and the current ambient temperature of the target infrared temperature measuring device are input into the second setting conversion algorithm to obtain the real temperature T_real of the target object.

[0141] As an embodiment, the designated infrared temperature measuring device or the target infrared temperature measuring device at least includes a detector, a cavity, and a housing;

[0142] The temperature sensors at different positions include: a temperature sensor deployed at a position adjacent to the detector, a temperature sensor deployed in the cavity, and a temperature sensor deployed on the device housing.

[0143] So far, completed Figure 4 Structural description of the device shown.

[0144] The present application also provides Figure 5 Another device structure diagram shown in FIG. Figure 5 As shown, the device comprises:

[0145] An obtaining unit is used to obtain input data corresponding to a target infrared temperature measuring device; the input data corresponding to the target infrared temperature measuring device is data corresponding to when the target infrared temperature measuring device performs infrared temperature measurement on a target object, and is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device, and the temperature measured by the target infrared temperature measuring device; the device characteristics at least include: a current temperature control level and a current gain gear;

[0146] A processing unit is used to input the input data into an optimal decision tree regression model to obtain a corrected temperature T1 of the target object; the optimal decision tree regression model is determined according to the above method under fixed conditions; and,

[0147] The real temperature T_real of the target object is determined based on the corrected temperature T1 of the target object, the fixed condition, and current data corresponding to a fixed data type; the fixed data type is the data type to which each data in the fixed condition belongs.

[0148] So far, completed Figure 5 Structural description of the device shown.

[0149] The present application also provides Figure 4 or Figure 5 The hardware structure diagram of the device shown in the figure. Figure 6 As shown, the hardware structure may include: a processor and a machine-readable storage medium. The machine-readable storage medium stores computer instructions, and when the computer instructions are executed by the processor, the steps in the above method are implemented.

[0150] Based on the same application concept as the above method, an embodiment of the present application also provides a machine-readable storage medium, on which a number of computer instructions are stored. When the computer instructions are executed by a processor, the method disclosed in the above example of the present application can be implemented.

[0151] Exemplarily, the above-mentioned machine-readable storage medium can be any electronic, magnetic, optical or other physical storage device that can contain or store information, such as executable instructions, data, etc. For example, the machine-readable storage medium can be: RAM (Radom Access Memory), volatile memory, non-volatile memory, flash memory, storage drive (such as hard disk drive), solid state drive, any type of storage disk (such as CD, DVD, etc.), or similar storage medium, or a combination thereof.

[0152] The systems, devices, modules or units described in the above embodiments may be implemented by computer circuits or entities, or by products with certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver, a game console, a tablet computer, a wearable device or a combination of any of these devices.

[0153] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0154] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the embodiments of the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0155] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0156] Moreover, these computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0157] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0158] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. An infrared temperature measurement method based on decision tree regression, characterized in that: The method includes: Obtain N pieces of sample data; the N pieces of sample data include sample data obtained when any specified infrared temperature measuring device performs infrared temperature measurement on a black body at different target temperatures T_target under fixed conditions; wherein the sample data obtained when any specified infrared temperature measuring device performs infrared temperature measurement on a black body at any target temperature T_target is related to the ambient temperature of the specified infrared temperature measuring device, the device characteristics of the specified infrared temperature measuring device, and the temperature measured by the specified infrared temperature measuring device; the device characteristics at least include: current temperature control level, current gain gear; Divide the N sample data into a training set and a test set; train a decision tree regression model using the training set under different model hyperparameters, and test each trained decision tree regression model using the test set to determine the optimal decision tree regression model; The optimal decision tree regression model is used to output the corrected temperature T1 of the target object based on the input data obtained when the target infrared temperature measuring device performs infrared temperature measurement on the target object, so that the corrected temperature T1 is combined with the current data corresponding to the fixed data type to determine the real temperature T_real of the target object; the fixed data type is the data type to which each data in the fixed condition belongs; The input data is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device, and the temperature measured by the target infrared temperature measuring device; the device characteristics at least include: the current temperature control level and the current gain gear.

2. The method according to claim 1, characterized in that The method of training the decision tree regression model using the training set under different model hyperparameters includes: Traverse the model hyperparameter set and use the traversed model hyperparameters as the current model hyperparameters; Use the training set to train the corresponding decision tree regression model under the current model hyperparameters; If there are still model hyperparameters that have not been traversed in the model hyperparameter set, continue to traverse the model hyperparameter set and return the traversed model hyperparameters as the current model hyperparameters.

3. The method according to claim 2, characterized in that The model hyperparameter set includes: a model depth subset and a learning rate subset; The traversing the model hyperparameter set includes: traversing the model depth subset and the learning rate subset respectively; The current model hyperparameters include the current model depth and the current learning rate.

4. The method according to claim 1, characterized in that The test set includes a first data set and a second data set; The method of using the test set to test each decision tree regression model trained to determine the optimal decision tree regression model includes: Using the first data set to test each trained decision tree regression model to obtain a reference decision tree regression model that meets the test requirements; The second data set is used to verify each reference decision tree regression model to obtain an optimal decision tree regression model that meets the verification requirements.

5. The method according to claim 1, characterized in that The fixed data types include: humidity type, black body emissivity type, black body imaging pixel size type; the fixed conditions include: fixed humidity, fixed black body emissivity, fixed black body imaging pixel size; The sample data obtained when any designated infrared temperature measuring device performs infrared temperature measurement on a black body at any target temperature T_target includes: the temperature detected by the temperature sensors deployed at different positions of the designated infrared temperature measuring device, the integration time of the designated infrared temperature measuring device, the ambient temperature of the designated infrared temperature measuring device, the current temperature control level and the current gain gear, the target temperature T_target, and the temperature measured when the designated infrared temperature measuring device performs infrared temperature measurement on a black body at the target temperature T_target; The input data includes: the temperature detected by the temperature sensors deployed at different positions of the target infrared temperature measuring device, the integration time of the target infrared temperature measuring device, the ambient temperature of the target infrared temperature measuring device, the current temperature control level of the target infrared temperature measuring device, the current gain gear, and the temperature measured by the target infrared temperature measuring device when performing infrared temperature measurement on the target object; The current data includes: the current humidity, ambient temperature, target object imaging pixel size, and target object emissivity of the target infrared temperature measuring device.

6. The method according to claim 5, characterized in that The real temperature T_real is determined by: The fixed humidity, fixed blackbody emissivity, fixed blackbody imaging pixel size, the current humidity of the target infrared temperature measurement device, the ambient temperature, the target object imaging pixel size, the emissivity of the target object, the obtained conversion coefficient coeff, and the T1 are input into the first setting conversion algorithm to obtain the real temperature T_real of the target object.

7. The method according to claim 1, characterized in that The fixed data types include: black body emissivity type, temperature control level type, and gain gear type; the fixed conditions include: fixed black body emissivity, fixed temperature control level, and fixed gain gear; The sample data obtained when any designated infrared temperature measuring device performs infrared temperature measurement on a black body at any target temperature T_target includes: the current ambient temperature and humidity of the designated infrared temperature measuring device, the target temperature T_target, the temperature measured when the designated infrared temperature measuring device performs infrared temperature measurement on a black body at the target temperature T_target, and the black body imaging pixel size; The input data includes: the current ambient temperature and humidity of the target infrared temperature measuring device, the temperature measured by the target infrared temperature measuring device when performing infrared temperature measurement on the target object, and the imaging pixel size of the target object; The current data includes: the temperature detected by the temperature sensors deployed at different positions of the target infrared temperature measuring device, the current ambient temperature of the target infrared temperature measuring device, the emissivity of the target object, the current temperature control level and gain gear of the target infrared temperature measuring device.

8. The method according to claim 7, characterized in that The real temperature T_real is expressed by the following formula: The fixed blackbody emissivity, the fixed temperature control level, the fixed gain gear, the emissivity of the target object, the current temperature control level and gain gear of the target infrared temperature measuring device, the temperature detected by the temperature sensors deployed at different positions of the target infrared temperature measuring device, and the current ambient temperature of the target infrared temperature measuring device are input into the second setting conversion algorithm to obtain the real temperature T_real of the target object.

9. The method according to claim 5 or 8, characterized in that: The designated infrared temperature measuring device or the target infrared temperature measuring device at least includes a detector, a cavity, and a housing; The temperature sensors at different positions include: a temperature sensor deployed at a position adjacent to the detector, a temperature sensor deployed in the cavity, and a temperature sensor deployed on the device housing.

10. An infrared temperature measurement method based on decision tree regression, characterized in that: The method includes: Obtain input data corresponding to the target infrared temperature measuring device; the input data corresponding to the target infrared temperature measuring device is data corresponding to when the target infrared temperature measuring device performs infrared temperature measurement on the target object, and is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device, and the temperature measured by the target infrared temperature measuring device; the device characteristics at least include: current temperature control level, current gain gear; Inputting the input data into an optimal decision tree regression model to obtain a corrected temperature T1 of the target object; the optimal decision tree regression model is determined under fixed conditions according to any method of claims 1 to 9; The real temperature T_real of the target object is determined based on the corrected temperature T1 of the target object, the fixed condition, and current data corresponding to a fixed data type; the fixed data type is the data type to which each data in the fixed condition belongs.

11. An infrared temperature measurement device based on decision tree regression, characterized in that: The device includes: A data processing unit is used to obtain N pieces of sample data; the N pieces of sample data include sample data obtained when any designated infrared temperature measuring device performs infrared temperature measurement on a black body at different target temperatures T_target under fixed conditions; wherein the sample data obtained when any designated infrared temperature measuring device performs infrared temperature measurement on a black body at any target temperature T_target is related to the ambient temperature of the designated infrared temperature measuring device, the device characteristics of the designated infrared temperature measuring device, and the temperature measured by the designated infrared temperature measuring device; the device characteristics at least include: current temperature control level, current gain gear; A model unit, used for dividing the N sample data into a training set and a test set; training a decision tree regression model using the training set under different model hyperparameters, and testing each trained decision tree regression model using the test set to determine an optimal decision tree regression model; The optimal decision tree regression model is used to output the corrected temperature T1 of the target object based on the input data obtained when the target infrared temperature measuring device performs infrared temperature measurement on the target object, so that the corrected temperature T1 is combined with the current data corresponding to the fixed data type to determine the real temperature T_real of the target object; the fixed data type is the data type to which each data in the fixed condition belongs; The input data is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device, and the temperature measured by the target infrared temperature measuring device; the device characteristics at least include: the current temperature control level and the current gain gear.

12. An infrared temperature measurement device based on decision tree regression, characterized in that: The device includes: An obtaining unit is used to obtain input data corresponding to a target infrared temperature measuring device; the input data corresponding to the target infrared temperature measuring device is data corresponding to when the target infrared temperature measuring device performs infrared temperature measurement on a target object, and is related to the ambient temperature of the target infrared temperature measuring device, the device characteristics of the target infrared temperature measuring device, and the temperature measured by the target infrared temperature measuring device; the device characteristics at least include: a current temperature control level and a current gain gear; A processing unit, used for inputting the input data into an optimal decision tree regression model to obtain a corrected temperature T1 of the target object; the optimal decision tree regression model is determined under fixed conditions according to any method of claims 1 to 9; and, The real temperature T_real of the target object is determined based on the corrected temperature T1 of the target object, the fixed condition, and current data corresponding to a fixed data type; the fixed data type is the data type to which each data in the fixed condition belongs.

13. An electronic device, characterized in that: The electronic device includes: a processor and a machine-readable storage medium; The machine-readable storage medium stores computer instructions, and when the computer instructions are executed by a processor, the steps in any one of the methods of claims 1 to 9 are implemented.

Images