WO2022120563A1 - 温度预测方法、装置和存储介质 - Google Patents

温度预测方法、装置和存储介质 Download PDF

Info

Publication number
WO2022120563A1
WO2022120563A1 PCT/CN2020/134508 CN2020134508W WO2022120563A1 WO 2022120563 A1 WO2022120563 A1 WO 2022120563A1 CN 2020134508 W CN2020134508 W CN 2020134508W WO 2022120563 A1 WO2022120563 A1 WO 2022120563A1
Authority
WO
WIPO (PCT)
Prior art keywords
temperature
temperature change
compensation
change curve
relationship
Prior art date
Application number
PCT/CN2020/134508
Other languages
English (en)
French (fr)
Inventor
肖科
张宁玲
金星亮
孟梨斌
何先梁
Original Assignee
深圳迈瑞生物医疗电子股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳迈瑞生物医疗电子股份有限公司 filed Critical 深圳迈瑞生物医疗电子股份有限公司
Priority to PCT/CN2020/134508 priority Critical patent/WO2022120563A1/zh
Priority to CN202080107741.3A priority patent/CN116648184A/zh
Publication of WO2022120563A1 publication Critical patent/WO2022120563A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry

Definitions

  • the present application relates to the technical field of temperature prediction, and more particularly to a temperature prediction method, device and storage medium.
  • the principle of rapid body temperature measurement is to use the characteristics of the temperature change process when the body temperature probe just touches the measurement target to predict the thermal equilibrium temperature after a few minutes, which greatly shortens the body temperature measurement time.
  • the ambient temperature has a significant effect on the measurement results during the measurement. Different ambient temperatures will directly lead to different probe sheath temperatures, different probe preheating temperatures, and inconsistent starting points for temperature changes during actual measurement. Therefore, the difference in ambient temperature will lead to significant differences in the characteristics of the temperature change curve measured by the probe, resulting in deviations in the final prediction result. Generally speaking, the lower the ambient temperature, the slower the overall temperature change rate of the probe, resulting in a lower prediction result; on the contrary, the higher the ambient temperature, the faster the temperature change rate of the probe and the higher prediction result.
  • a temperature prediction method comprising: acquiring the temperature of the environment where the object to be measured is located as the ambient temperature; acquiring compensation features corresponding to the ambient temperature based on a pre-built compensation relationship.
  • the compensation relationship reflects the compensation features that should be used in temperature measurement under different ambient temperatures; based on the obtained compensation features, the temperature prediction of the measured object is compensated and corrected to obtain and output the temperature prediction result of the measured object .
  • a temperature prediction method comprising: acquiring the temperature of the environment where a measured object is located as the ambient temperature, and acquiring a temperature change obtained by measuring the measured object by a measuring device curve; obtain the target temperature corresponding to the ambient temperature and the temperature change curve based on the pre-built target temperature prediction model, and obtain and output the temperature prediction result of the measured object.
  • a temperature prediction apparatus includes a memory, a processor, and an output device, the memory stores a computer program executed by the processor, and the computer program is executed by the processor.
  • the processor runs, the following steps are performed: acquiring the temperature of the environment where the measured object is located as the ambient temperature; acquiring the compensation feature corresponding to the ambient temperature based on a pre-built compensation relationship, the compensation relationship reflecting the temperature under different ambient temperatures Compensation feature to be used during measurement; based on the acquired compensation feature, the temperature prediction of the measured object is compensated and corrected, so as to obtain and output the temperature prediction result of the measured object by the output device.
  • a temperature prediction apparatus includes a memory, a processor, and an output device, the memory stores a computer program executed by the processor, and the computer program is run by the processor.
  • the processor runs, the following steps are performed: obtaining the temperature of the environment where the measured object is located as the ambient temperature, and obtaining a temperature change curve obtained after the measuring device measures the measured object; obtaining the target temperature prediction model based on the pre-built The target temperature corresponding to the ambient temperature and the temperature change curve is obtained and the output device outputs the temperature prediction result of the measured object.
  • a storage medium is provided, and a computer program is stored on the storage medium, and the computer program executes the above temperature prediction method when running.
  • the temperature prediction method, device, and storage medium consider the influence of the temperature of the environment where the measured object is located on the temperature prediction when predicting the temperature of the measured object, so as to avoid the prediction deviation caused by the environmental temperature and improve the temperature prediction accuracy of results.
  • FIG. 1 shows a schematic diagram of a temperature change curve when measuring the temperature of the same object under different ambient temperatures.
  • FIG. 2 shows a schematic flowchart of a temperature prediction method according to an embodiment of the present application.
  • FIG. 3 shows a schematic flowchart of an example process of compensation correction in the temperature prediction method according to an embodiment of the present application.
  • FIG. 4 shows a schematic flowchart of another exemplary process of performing compensation correction in the temperature prediction method according to an embodiment of the present application.
  • FIG. 5 shows a comparison of the temperature prediction results obtained without using and using the temperature prediction method according to the embodiment of the present application under different ambient temperatures.
  • FIG. 6 shows a schematic flowchart of a temperature prediction method according to another embodiment of the present application.
  • FIG. 7 shows a schematic flowchart of a temperature prediction method according to still another embodiment of the present application.
  • FIG. 8 shows a schematic structural block diagram of a temperature prediction apparatus according to an embodiment of the present application.
  • FIG. 1 shows a schematic diagram of a temperature change curve when measuring the temperature of the same object under different ambient temperatures.
  • the temperature change curve when the ambient temperature is 25°C is 110
  • the temperature change curve when the ambient temperature is 20°C is 120.
  • the curve 110 and the curve 120 do not There is a clear difference between the two. Therefore, the difference in ambient temperature will lead to significant differences in the characteristics of the temperature change curve measured by the probe, resulting in deviations in the final prediction result.
  • FIG. 2 shows a schematic flowchart of a temperature prediction method 200 according to an embodiment of the present application.
  • the temperature prediction method 200 may include the following steps:
  • step S210 the temperature of the environment where the measured object is located is obtained as the ambient temperature.
  • step S220 a compensation feature corresponding to the ambient temperature is obtained based on a pre-built compensation relationship, where the compensation relationship reflects the compensation feature that should be used when temperature measurement is performed under different ambient temperatures.
  • step S230 compensation and correction are performed on the temperature prediction of the measured object based on the acquired compensation feature, so as to obtain and output a temperature prediction result of the measured object.
  • the temperature of the environment where the measured object is located may be acquired in various ways to obtain the ambient temperature.
  • the ambient temperature can be obtained by directly measuring the environment where the measured object is located, such as through various temperature measuring devices or various measuring methods capable of measuring the ambient temperature.
  • the ambient temperature can be obtained according to a temperature change curve obtained after measuring the measured object by a measuring device (such as a body temperature measuring probe).
  • the temperature of the environment where the measured object is located can also be obtained in any other suitable manner to obtain the ambient temperature.
  • the compensation relationship in step S220 is pre-built to compensate and correct the deviation of the prediction result caused by the ambient temperature, and the compensation relationship can reflect what compensation feature should be used under various ambient temperatures
  • the process or result of temperature prediction is compensated. Therefore, the compensation relationship may include at least a corresponding relationship between the ambient temperature and the compensation characteristic.
  • the compensation relationship may include a curve, function, or graph of the relationship between different ambient temperatures and compensation characteristics. Based on the pre-built compensation relationship, after the current ambient temperature is acquired in step S210, the compensation feature corresponding to the current ambient temperature may be acquired according to the pre-built compensation relationship for compensating and correcting the temperature prediction of the measured object.
  • the compensation and correction of the temperature prediction of the measured object may include compensation and correction of the temperature prediction process, and may also include the correction of the temperature prediction result.
  • Different compensation and correction objects will obtain different compensation features and different compensation and correction processes. The following description will be made with reference to FIGS. 3 to 4 .
  • FIG. 3 shows a schematic flowchart of an exemplary process 300 for compensation and correction in a temperature prediction method according to an embodiment of the present application.
  • the acquired compensation feature is a prediction result deviation.
  • process 300 may include the following steps:
  • step S310 the initial temperature prediction result of the measured object by the measurement device according to the prediction model is obtained.
  • step S320 the initial temperature prediction result is corrected based on the obtained prediction result deviation, and the corrected result is the temperature prediction result of the measured object.
  • the compensation feature obtained based on the pre-built compensation relationship is the deviation of the prediction result, that is, in this example, the temperature prediction result can be compensated and corrected. Therefore, the initial temperature prediction result of the measured object may be output by the measurement device first, and the initial temperature prediction result is the result predicted by the prediction model after the measurement device (such as a body temperature measurement probe) routinely measures the measured object to obtain some data.
  • the initial temperature prediction result is a result without compensation and correction, and is named so to distinguish it from the final temperature prediction result (ie, the result after compensation and correction).
  • the initial temperature prediction result of the measuring device can be corrected based on the acquired compensation feature (in this example, the prediction result deviation) to obtain the corrected result as the temperature prediction result of the measured object.
  • the temperature prediction result is a more accurate temperature prediction result obtained by compensating the compensation feature obtained according to the ambient temperature.
  • the compensation feature obtained based on the pre-built compensation relationship is the deviation of the prediction result, that is, the pre-built compensation relationship reflects the relationship between different ambient temperatures and the deviation of the prediction result. Based on this, the construction of the compensation relationship can be achieved through different implementations. It should be understood that since the compensation relationship is pre-constructed, the various data used in its construction are not the data obtained for the current measured object, but the data obtained from the experimental object under different experimental conditions. At present, it is not ruled out that the current subject may have also been the subject of the experiment.
  • the measurement equipment used in the experiment and the measurement equipment in the method according to the embodiment of the present application may be the same equipment or different equipment, and when they are different equipment, they may be of the same type, the same model, and the same manufacturer. equipment, etc. Different implementations of constructing the compensation relationship in the example shown in FIG. 3 are described below.
  • the construction of the compensation relationship can be achieved by the following steps: obtaining the deviation of the prediction result of the measuring device for the same target temperature under different ambient temperatures; The relationship between the ambient temperature and the deviation of the prediction result is used as the compensation relationship.
  • the constructed compensation relationship can reflect the relationship between different ambient temperatures and the deviation of the predicted result when measuring the same target temperature (the target temperature refers to the actual thermal equilibrium temperature of the measured object).
  • the construction method can be, for example, by fitting a relationship curve or function between the ambient temperature and the deviation of the predicted result, or using a machine learning method to construct a relationship model between different ambient temperatures and the deviation of the predicted result, and so on.
  • the corresponding deviation of the prediction result can be obtained according to the relationship as a compensation feature, so as to be used for the initial temperature prediction result of the measuring device. Correction.
  • the construction of the compensation relationship can be realized by the following steps: obtaining the prediction results of the measuring device for the same target temperature under different ambient temperatures, including the reference prediction results under the reference ambient temperature and other predictions under other ambient temperatures Result; take the difference between the reference ambient temperature and the other ambient temperatures as the independent variable, and take the difference between the reference prediction result and the other prediction results as the dependent variable to construct the deviation between the different ambient temperatures and the prediction results
  • the relationship between is used as the compensation relationship.
  • This embodiment is similar to the previous embodiment, and the compensation relationship constructed can also reflect the relationship between different ambient temperatures and the deviation of the predicted result when the same target temperature is measured.
  • the difference from the previous embodiment is that instead of taking the ambient temperature as a variable and the deviation of the prediction result as the dependent variable, an ambient temperature is set from different ambient temperatures as the reference ambient temperature, and the reference ambient temperature is compared with other ambient temperatures.
  • the difference in temperature is used as the independent variable, and the compensation is constructed by using the difference between the prediction result at the reference ambient temperature (referred to as the reference prediction result) and the prediction result at other ambient temperatures (referred to as the other prediction result) as the dependent variable relation.
  • the way of construction can also be, for example, by fitting or machine learning methods.
  • the difference between the aforementioned reference ambient temperature and the currently acquired ambient temperature may be calculated first, and then another corresponding to the difference may be acquired according to the compensation relationship.
  • the difference value according to the other difference value and the aforementioned reference prediction result deviation, obtains the prediction result deviation under the current ambient temperature, that is, the compensation feature, so as to correct the initial temperature prediction result of the measuring device.
  • the construction of the compensation relationship can be realized by the following steps: obtaining the deviation of the prediction results of the measuring equipment for different target temperatures under different ambient temperatures; taking the ambient temperature and the target temperature as independent variables, and taking the deviation of the predicted results as the cause variable, and the relationship between different ambient temperatures and target temperatures and the deviation of the predicted result is constructed as the compensation relationship.
  • the constructed compensation relationship can reflect the relationship between different ambient temperatures and the deviation of the predicted result when measuring different target temperatures (the target temperature refers to the actual thermal equilibrium temperature of the measured object).
  • the construction method can be, for example, by fitting the relationship surface or function between the ambient temperature, the target temperature and the deviation of the prediction result, or using machine learning methods to construct the relationship model between different ambient temperature and target temperature and the deviation of the prediction result, etc.
  • the target temperature is obtained (the target temperature is still an unknown value at this time because it is the amount that needs to be finally obtained, but It can be represented by a known quantity (ambient temperature and compensation feature), and then the corresponding prediction result deviation is obtained according to the relationship as a compensation feature, which is used to correct the initial temperature prediction result of the measuring device.
  • process 400 may include the following steps:
  • step S410 an initial temperature change curve obtained after the measuring device measures the measured object is obtained.
  • step S420 the initial temperature change curve is corrected based on the acquired temperature change curve characteristics, and the temperature prediction result of the measured object is obtained according to the corrected temperature change curve and the prediction model.
  • the compensation feature obtained based on the pre-built compensation relationship is the temperature change curve feature (such as the time constant of the temperature change curve, the curve slope of the temperature change curve, the temperature value at the preset time point of the temperature change curve, etc.), That is, in this example, a compensation correction can be made to the temperature prediction process.
  • the compensation correction for the temperature prediction process can be to correct the temperature change curve according to the obtained temperature change curve characteristics (as shown in Figure 4), or directly input the obtained temperature change curve characteristics into the prediction model to obtain the final temperature. Prediction results (not shown). Therefore, in the example shown in FIG.
  • an initial temperature change curve obtained by measuring the measured object by the measurement equipment may be obtained, and the initial temperature change curve is the measurement equipment (such as a body temperature measuring probe) The results obtained by routinely measuring the measured object.
  • the initial temperature change curve is not corrected by compensation, and is named as such to distinguish it from the compensated temperature change curve.
  • the initial temperature change curve of the measuring device can be corrected based on the acquired compensation feature (in this example, the temperature change curve feature) to obtain a corrected temperature change curve, and the measuring device can perform a correction according to the corrected temperature change curve and
  • the prediction model can obtain the final temperature prediction result of the measured object.
  • the temperature prediction result is a more accurate temperature prediction result obtained by compensating the compensation characteristic obtained according to the ambient temperature.
  • the compensation feature obtained based on the pre-built compensation relationship is the temperature change curve feature, that is, the pre-built compensation relationship reflects the relationship between different ambient temperatures and the temperature change curve feature.
  • the construction of the compensation relationship can be achieved through different implementations. It should be understood that since the compensation relationship is pre-constructed, the various data used in its construction are not the data obtained for the current measured object, but the data obtained from the experimental object under different experimental conditions. At present, it is not ruled out that the current subject may have also been the subject of the experiment.
  • the measurement equipment used in the experiment and the measurement equipment in the method according to the embodiment of the present application may be the same equipment or different equipment, and when they are different equipment, they may be of the same type, the same model, and the same manufacturer. equipment, etc. Different implementations of constructing the compensation relationship in the example shown in FIG. 4 are described below.
  • the compensation relationship can be constructed by the following steps: acquiring the respective temperature change curves of the measuring equipment from different ambient temperatures to the same target temperature; extracting the characteristics of the temperature change curves to obtain the characteristics of the temperature change curves; The temperature is the independent variable, and the temperature change curve feature is used as the dependent variable to construct the relationship between different ambient temperatures and the temperature change curve feature as the compensation relationship.
  • the constructed compensation relationship can reflect the relationship between different ambient temperatures and the temperature change curve characteristics when measuring the same target temperature (the target temperature refers to the actual thermal equilibrium temperature of the measured object).
  • the construction method can be, for example, by fitting a relationship curve or function between the ambient temperature and the temperature change curve feature, or using a machine learning method to build a relationship model between different ambient temperatures and the temperature change curve feature, and so on. Based on the relationship between different ambient temperatures and the temperature change curve characteristics, after the ambient temperature is obtained in step S210, the corresponding temperature change curve characteristics can be obtained according to the relationship as compensation characteristics, which are used to measure the initial temperature change of the device. Curve is corrected. The measuring device can obtain the final temperature prediction result of the measured object according to the corrected temperature change curve and the prediction model.
  • the compensation relationship can be constructed by the following steps: acquiring the respective temperature change curves of the measuring device from different ambient temperatures to the same target temperature, including the reference temperature change curve corresponding to the reference ambient temperature and the temperature change curve corresponding to other ambient temperatures Corresponding other temperature change curves; extract the respective characteristics of the reference temperature change curve and the other temperature change curves to obtain the reference curve characteristics and other curve characteristics respectively; The difference is an independent variable, and the difference between the reference curve feature and the other curve features is used as a dependent variable to construct the relationship between different ambient temperatures and the temperature change curve feature as the compensation relationship.
  • This embodiment is similar to the previous embodiment, and the compensation relationship constructed can also reflect the relationship between different ambient temperatures and the temperature change curve characteristics when the same target temperature is measured.
  • the difference from the previous embodiment is that instead of taking the ambient temperature as a variable and the temperature change curve feature as the dependent variable, an ambient temperature is set from different ambient temperatures as the reference ambient temperature, and the reference ambient temperature is compared with other ambient temperatures.
  • the difference value of the ambient temperature is used as an independent variable, and the difference between the temperature change curve characteristics at the reference ambient temperature (called the reference curve characteristics) and the temperature change curve characteristics at other ambient temperatures (called other curve characteristics) is used as dependent variables to construct a compensation relationship.
  • the way of construction can also be, for example, by fitting or machine learning methods.
  • the difference between the aforementioned reference ambient temperature and the currently acquired ambient temperature may be calculated first, and then another corresponding to the difference may be acquired according to the compensation relationship.
  • the difference value is obtained according to the other difference value and the aforementioned reference curve feature to obtain the temperature change curve feature under the current ambient temperature, that is, the compensation feature, so as to correct the initial temperature change curve of the measuring device.
  • the measuring device can obtain the final temperature prediction result of the measured object according to the corrected temperature change curve and the prediction model.
  • the construction of the compensation relationship can be achieved by the following steps: acquiring the respective temperature change curves of the measuring equipment from different ambient temperatures to different target temperatures; extracting the characteristics of the temperature change curves to obtain the characteristics of the temperature change curves; The ambient temperature and the target temperature are used as independent variables, and the temperature change curve feature is used as the dependent variable to construct the relationship between different ambient temperatures, the target temperature and the temperature change curve feature as the compensation relationship.
  • the constructed compensation relationship can reflect the relationship between different ambient temperatures and the temperature change curve characteristics when measuring different target temperatures (the target temperature refers to the actual thermal equilibrium temperature of the measured object).
  • the construction method can be, for example, by fitting the relationship surface or function between the ambient temperature, the target temperature and the temperature change curve features, or using machine learning methods to build a relationship model between different ambient temperatures, target temperature and temperature change curve features, etc. .
  • the target temperature is obtained again (the target temperature is still an unknown value at this time because it is the amount that needs to be finally obtained, However, it can be represented by a known quantity (ambient temperature and compensation characteristics), and then the corresponding temperature change curve characteristics are obtained according to the relationship as compensation characteristics, so as to be used to correct the initial temperature change curve of the measuring device.
  • the measuring device can obtain the final temperature prediction result of the measured object according to the corrected temperature change curve and the prediction model.
  • the above exemplarily shows the compensation correction process and the construction of the compensation relationship when the acquired compensation feature is the temperature change curve feature.
  • the construction of the compensation relationship can be simplified.
  • the compensation relationship is constructed as an empirical compensation coefficient, and the empirical compensation coefficient is directly multiplied by the ambient temperature to obtain the compensation feature, and then the temperature prediction is performed according to the compensation feature. Compensation can be corrected.
  • FIG. 5 shows a comparison of the temperature prediction results obtained without adopting and adopting the temperature prediction method according to the embodiment of the present application under different ambient temperatures.
  • the curve 510 shows the temperature prediction results without using the temperature prediction method according to the embodiment of the present application under different ambient temperatures
  • the curve 520 shows the temperature prediction result using the embodiment of the present application under different ambient temperatures Method temperature prediction results.
  • the temperature prediction results obtained by using the temperature prediction method according to the embodiment of the present application under different ambient temperatures are very close to the target predicted temperature (target temperature), while the temperature prediction results obtained by the temperature prediction method according to the embodiment of the present application are not used. Results There is a large deviation between the temperature prediction results obtained at different ambient temperatures.
  • the temperature prediction method 200 considers the influence of the temperature of the environment where the measured object is located on the temperature prediction, and obtains the location where the measured object is located through the relationship between the pre-built ambient temperature and the compensation feature.
  • the compensation feature corresponding to the temperature of the environment compensates and corrects the current temperature prediction, so that the prediction deviation caused by the ambient temperature can be compensated, and the accuracy of the temperature prediction result can be improved.
  • the temperature prediction method 600 may include the following steps:
  • step S610 the temperature of the environment where the measured object is located is obtained as the ambient temperature, and the temperature change curve obtained after the measuring device measures the measured object is obtained.
  • step S620 a target temperature corresponding to the ambient temperature and the temperature change curve is acquired based on a pre-built target temperature prediction model, and a temperature prediction result of the measured object is obtained and output.
  • the temperature prediction method 600 is similar to the above-mentioned temperature prediction method 200 , both of which take into account the influence of the ambient temperature on the temperature prediction result of the measured object, and exclude the influence of the ambient temperature on the temperature prediction result.
  • the difference is that the temperature prediction method 200 is based on a pre-built compensation relationship reflecting the relationship between the ambient temperature and the compensation feature, and the compensation feature corresponding to the current ambient temperature is obtained to compensate the process or result of the temperature prediction;
  • the method 600 is based on a pre-built target temperature prediction model reflecting the relationship between the ambient temperature and the temperature change curve and the target temperature, and inputting the obtained ambient temperature and the temperature change curve obtained after the measurement device measures the measured object into the target temperature.
  • the model directly obtains the temperature prediction result of the measured object (ie, the target temperature).
  • the target temperature prediction model in step S620 can be constructed by the following methods: acquiring the respective temperature change curves of the measuring equipment from different ambient temperatures to different target temperatures; taking the ambient temperature and the temperature change curves as independent variables , with the target temperature as the dependent variable, the relationship between different ambient temperatures and temperature change curves and the target temperature is constructed, and the target temperature prediction model is obtained.
  • the constructed target temperature prediction model can be used to directly output the temperature prediction result of the measured object according to the current ambient temperature and the temperature change curve measured by the measuring device on the measured object. Since the target temperature prediction model has considered the influence of the ambient temperature, the obtained temperature prediction result is equivalent to the compensated result, which is an accurate result.
  • the method for constructing the target temperature prediction model may include, for example, function fitting, machine learning method training, and the like.
  • the temperature prediction method 700 may include the following steps:
  • step S710 the temperature of the environment where the measured object is located is obtained as the ambient temperature, and the temperature change curve obtained after the measuring device measures the measured object is obtained.
  • step S720 the feature of the temperature change curve is extracted to obtain the feature of the temperature change curve.
  • step S730 a target temperature corresponding to the ambient temperature and temperature change curve characteristics is obtained based on a pre-built target temperature prediction model, and a temperature prediction result of the measured object is obtained and output.
  • the temperature prediction method 700 is substantially similar to the aforementioned temperature prediction method 600, except that the temperature prediction method 600 is based on a pre-built relationship between the ambient temperature and the temperature change curve and the target temperature
  • the target temperature prediction model is based on the target temperature prediction model, and the obtained ambient temperature and the temperature change curve obtained after the measurement equipment measures the measured object are input into the model, and the temperature prediction result of the measured object is directly obtained; and the temperature prediction method 700 is based on pre-built A target temperature prediction model that reflects the relationship between the ambient temperature and the characteristics of the temperature change curve and the target temperature.
  • the time constant of the temperature change curve, the curve slope of the temperature change curve, the temperature value at the preset time point of the temperature change curve, etc. are input into the model, and the temperature prediction result (ie the target temperature) of the measured object is directly obtained.
  • the target temperature prediction model in step S720 may be constructed by the following methods: acquiring the respective temperature change curves of the measuring device from different ambient temperatures to different target temperatures; extracting the features of the temperature change curves , obtain the temperature change curve characteristics; take the ambient temperature and the temperature change curve characteristics as independent variables, and use the target temperature as the dependent variable, construct the relationship between different ambient temperatures and temperature change curve characteristics and the target temperature, and obtain the target temperature prediction model .
  • the constructed target temperature prediction model can be used to directly output the temperature prediction result of the measured object according to the current ambient temperature and the characteristics of the temperature change curve measured by the measuring device on the measured object.
  • the target temperature prediction model Since the target temperature prediction model has considered the influence of the ambient temperature, the obtained temperature prediction result is equivalent to the compensated result, which is an accurate result.
  • the method for constructing the target temperature prediction model may include, for example, function fitting, machine learning method training, and the like.
  • the temperature prediction method considers the influence of the temperature of the environment where the measured object is located on the temperature prediction when predicting the temperature of the measured object, which can avoid the prediction deviation caused by the environmental temperature and improve the temperature prediction. accuracy of results.
  • FIG. 8 shows a schematic structural block diagram of a temperature prediction apparatus 800 according to an embodiment of the present application.
  • the temperature prediction apparatus 800 may include a memory 810 , a processor 820 and an output device 830 .
  • the memory 810 stores a computer program executed by the processor 820 , and the computer program executes the foregoing when executed by the processor 820 .
  • the described temperature prediction method according to the embodiment of the present application. Those skilled in the art can understand the operation of each component in the temperature prediction apparatus 800 according to the embodiment of the present application in combination with the foregoing description. For the sake of brevity, only the main operation thereof will be described here, and the details will not be described.
  • the computer program executes the following steps when being run by the processor 820: acquiring the temperature of the environment where the measured object is located as the ambient temperature; acquiring the temperature corresponding to the ambient temperature based on a pre-built compensation relationship Compensation characteristics of the measured object, the compensation relationship reflects the compensation characteristics that should be used when temperature measurement is performed under different ambient temperatures; based on the acquired compensation characteristics, the temperature prediction of the measured object is compensated and corrected to obtain and output by the output device. A temperature prediction result of the measured object is output.
  • the compensation relationship includes a curve, function or graph reflecting the relationship between different ambient temperatures and compensation characteristics.
  • the compensation feature is a deviation of a prediction result
  • the compensation and correction performed by the computer program when the computer program is executed by the processor 820 includes: acquiring the measurement equipment's accuracy of the measured object according to the prediction model.
  • the construction of the compensation relationship includes: obtaining the deviation of the prediction result of the measuring device for the same target temperature under different ambient temperatures; taking the ambient temperature as an independent variable, and taking the deviation of the prediction result as a dependent variable, The relationship between different ambient temperatures and the deviation of the predicted result is constructed as the compensation relationship.
  • the construction of the compensation relationship includes: acquiring the deviation of the prediction results of the measuring device for different target temperatures under different ambient temperatures; taking the ambient temperature and the target temperature as independent variables, and taking the deviation of the prediction results as As the dependent variable, the relationship between different ambient temperature and target temperature and the deviation of the predicted result is constructed as the compensation relationship.
  • the construction of the compensation relationship includes: obtaining the prediction results of the measurement device for the same target temperature under different ambient temperatures, including the reference prediction results under the reference ambient temperature and other ambient temperatures under other ambient temperatures. Prediction result; take the difference between the reference ambient temperature and the other ambient temperatures as the independent variable, and take the difference between the reference prediction result and the other prediction results as the dependent variable to construct different ambient temperatures and prediction results The relationship between the deviations is used as the compensation relationship.
  • the compensation feature is a temperature change curve feature
  • the compensation and correction performed by the computer program when the computer program is executed by the processor 820 includes: acquiring a measurement device to measure the measured object after The obtained initial temperature change curve is modified based on the obtained temperature change curve characteristics, and the temperature prediction result of the measured object is obtained according to the revised temperature change curve and the prediction model; or the The temperature change curve feature is input into the prediction model to obtain the temperature prediction result of the measured object.
  • the construction of the compensation relationship includes: acquiring the respective temperature change curves of the measuring equipment from different ambient temperatures to the same target temperature; extracting the characteristics of the temperature change curve to obtain the temperature change curve characteristics; Taking the ambient temperature as an independent variable and the temperature change curve feature as a dependent variable, the relationship between different ambient temperatures and the temperature change curve feature is constructed as the compensation relationship.
  • the construction of the compensation relationship includes: acquiring respective temperature change curves of the measuring device from different ambient temperatures to different target temperatures; extracting the characteristics of the temperature change curves to obtain the temperature change curve characteristics; Taking the ambient temperature and the target temperature as independent variables, and taking the temperature change curve feature as the dependent variable, the relationship between different ambient temperatures, the target temperature and the temperature change curve feature is constructed as the compensation relationship.
  • the construction of the compensation relationship includes: acquiring the respective temperature change curves of the measurement device from different ambient temperatures to the same target temperature, including the reference temperature change curve corresponding to the reference ambient temperature and the temperature change curve corresponding to the reference ambient temperature and other ambient temperatures. other temperature change curves corresponding to the temperature; extract the respective characteristics of the reference temperature change curve and the other temperature change curves, and obtain the reference curve characteristics and other curve characteristics respectively;
  • the difference is an independent variable, and the difference between the reference curve feature and the other curve features is used as a dependent variable to construct the relationship between different ambient temperatures and temperature change curve features as the compensation relationship.
  • the compensation relationship includes an empirical compensation coefficient
  • the obtaining of the compensation feature corresponding to the ambient temperature when the computer program is executed by the processor 820 includes: converting the obtained The ambient temperature is multiplied by the empirical compensation coefficient to obtain the compensation feature.
  • the following steps are performed: obtaining the temperature of the environment where the measured object is located as the ambient temperature, and obtaining the measured object after the measuring device measures the measured object.
  • the obtained temperature change curve; the target temperature corresponding to the ambient temperature and the temperature change curve is obtained based on the pre-built target temperature prediction model, and the temperature prediction result of the measured object is obtained and output by the output device.
  • the construction of the target temperature prediction model includes: acquiring the respective temperature change curves of the measuring device from different ambient temperatures to different target temperatures; taking the ambient temperature and the temperature change curves as independent variables, Taking the target temperature as a dependent variable, the relationship between different ambient temperatures and temperature change curves and the target temperature is constructed to obtain the target temperature prediction model.
  • the following steps are further performed: after obtaining the initial temperature change curve, extract the characteristics of the initial temperature change curve to obtain the temperature change curve characteristics ; and the acquisition of the target temperature corresponding to the ambient temperature and the temperature change curve performed by the computer program when being executed by the processor includes: acquiring the characteristics of the ambient temperature and the temperature change curve the corresponding target temperature.
  • the construction of the target temperature prediction model includes: acquiring respective temperature change curves of the measuring device from different ambient temperatures to different target temperatures; extracting the characteristics of the temperature change curves to obtain the temperature Variation curve characteristics; take the ambient temperature and the temperature variation curve characteristics as independent variables and the target temperature as the dependent variable, construct the relationship between different ambient temperatures and temperature variation curve characteristics and the target temperature, and obtain the target temperature prediction model.
  • the temperature change curve feature includes any one of the following: a time constant of the temperature change curve, a curve slope of the temperature change curve, and a temperature value at a preset time point of the temperature change curve.
  • the measuring device is a body temperature measuring probe.
  • the ambient temperature is obtained by direct measurement of the environment where the measured object is located, or is obtained according to a temperature change curve obtained after the measured object is measured by a measuring device obtained.
  • a storage medium is also provided, and program instructions are stored on the storage medium, and the program instructions are used to execute the temperature prediction method of the embodiment of the present application when the program instructions are run by a computer or a processor. corresponding steps.
  • the storage medium may include, for example, a memory card of a smartphone, a storage component of a tablet computer, a hard disk of a personal computer, read only memory (ROM), erasable programmable read only memory (EPROM), portable compact disk read only memory (CD-ROM), USB memory, or any combination of the above storage media.
  • the computer-readable storage medium can be any combination of one or more computer-readable storage media.
  • a computer program is also provided, and the computer program can be stored in the cloud or on a local storage medium.
  • the computer program is run by a computer or a processor, it is used to execute the corresponding steps of the temperature prediction method of the embodiments of the present application.
  • the temperature prediction method, device and storage medium consider the influence of the temperature of the environment where the measured object is located on the temperature prediction when predicting the temperature of the measured object, which can avoid the prediction deviation caused by the environmental temperature and improve the temperature prediction. accuracy of results.
  • the disclosed apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or May be integrated into another device, or some features may be omitted, or not implemented.
  • Various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof.
  • a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some modules according to the embodiments of the present application.
  • DSP digital signal processor
  • the present application can also be implemented as a program of apparatus (eg, computer programs and computer program products) for performing part or all of the methods described herein.
  • Such a program implementing the present application may be stored on a computer-readable medium, or may be in the form of one or more signals. Such signals may be downloaded from Internet sites, or provided on carrier signals, or in any other form.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Medical Informatics (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Measuring Temperature Or Quantity Of Heat (AREA)
  • Indication And Recording Devices For Special Purposes And Tariff Metering Devices (AREA)

Abstract

一种温度预测方法、装置和存储介质，该方法包括：获取被测对象所处环境的温度作为环境温度（S210）；基于预构建的补偿关系获取与环境温度对应的补偿特征，所述补偿关系反映不同环境温度下进行温度测量时应采用的补偿特征（S220）；基于所获取的补偿特征对所述被测对象的温度预测进行补偿修正，以获得并输出所述被测对象的温度预测结果（S230）。该方法在对被测对象进行温度预测时考虑被测对象所处环境的温度对温度预测的影响，能够避免因环境温度造成预测偏差，提高温度预测结果的准确性。

Description

温度预测方法、装置和存储介质
说明书
技术领域
本申请涉及温度预测技术领域，更具体地涉及一种温度预测方法、装置和存储介质。
背景技术
快速体温测量原理是利用体温探头刚接触测量目标时温度变化过程的特征来预测几分钟后的热平衡温度，大幅缩短体温测量时间。
但是，在测量过程中环境温度对测量结果具有显著的影响。环境温度不同会直接导致探头护套的温度不同、探头预加热的温度不同以及实际测量时的温度变化起点不一致。因此，环境温度的不同会导致探头测量的温度变化曲线特征显著差异，导致最后的预测结果出现偏差。一般来说，环境温度越低会导致探头整体的温度变化速度变慢，导致预测结果偏低；相反，环境温度越高，会导致探头的温度变化速度越快，预测结果偏高。
发明内容
为了解决问题而提出了本申请。根据本申请一方面，提供了一种温度预测方法，所述方法包括：获取被测对象所处环境的温度作为环境温度；基于预构建的补偿关系获取与所述环境温度对应的补偿特征，所述补偿关系反映不同环境温度下进行温度测量时应采用的补偿特征；基于所获取的补偿特征对所述被测对象的温度预测进行补偿修正，以获得并输出所述被测对象的温度预测结果。
根据本申请另一方面，提供了一种温度预测方法，所述方法包括：获取被测对象所处环境的温度作为环境温度，并获取测量设备对所述被测对象进行测量后得到的温度变化曲线；基于预构建的目标温度预测模型获取与所述环境温度和温度变化曲线对应的目标温度，得到并输出所述被测对象的温度预测结果。
根据本申请再一方面，提供了一种温度预测装置，所述装置包括存储 器、处理器和输出设备，所述存储器上存储有由所述处理器运行的计算机程序，所述计算机程序在被所述处理器运行时执行如下步骤：获取被测对象所处环境的温度作为环境温度；基于预构建的补偿关系获取与所述环境温度对应的补偿特征，所述补偿关系反映不同环境温度下进行温度测量时应采用的补偿特征；基于所获取的补偿特征对所述被测对象的温度预测进行补偿修正，以获得并由所述输出设备输出所述被测对象的温度预测结果。
根据本申请又一方面，提供了一种温度预测装置，所述装置包括存储器、处理器和输出设备，所述存储器上存储有由所述处理器运行的计算机程序，所述计算机程序在被所述处理器运行时执行如下步骤：获取被测对象所处环境的温度作为环境温度，并获取测量设备对所述被测对象进行测量后得到的温度变化曲线；基于预构建的目标温度预测模型获取与所述环境温度和温度变化曲线对应的目标温度，得到并由所述输出设备输出所述被测对象的温度预测结果。
本申请再一方面，提供了一种存储介质，所述存储介质上存储有计算机程序，所述计算机程序在运行时执行上述温度预测方法。
根据本申请实施例的温度预测方法、装置和存储介质在对被测对象就行温度预测时考虑被测对象所处环境的温度对温度预测的影响，能够避免因环境温度造成预测偏差，提高温度预测结果的准确性。
附图说明
图1示出在不同环境温度下对同一被测对象测量温度时的温度变化曲线的示意图。
图2示出根据本申请一个实施例的温度预测方法的示意性流程图。
图3示出根据本申请实施例的温度预测方法中进行补偿修正的一个示例过程的示意性流程图。
图4示出根据本申请实施例的温度预测方法中进行补偿修正的另一个示例过程的示意性流程图。
图5示出不同环境温度下未采用和采用根据本申请实施例的温度预测方法得到的温度预测结果的比较。
图6示出根据本申请另一个实施例的温度预测方法的示意性流程图。
图7示出根据本申请再一个实施例的温度预测方法的示意性流程图。
图8示出根据本申请实施例的温度预测装置的示意性结构框图。
具体实施方式
为了使得本申请的目的、技术方案和优点更为明显，下面将参照附图详细描述根据本申请的示例实施例。显然，所描述的实施例仅仅是本申请的一部分实施例，而不是本申请的全部实施例，应理解，本申请不受这里描述的示例实施例的限制。基于本申请中描述的本申请实施例，本领域技术人员在没有付出创造性劳动的情况下所得到的所有其它实施例都应落入本申请的保护范围之内。
在下文的描述中，给出了大量具体的细节以便提供对本申请更为彻底的理解。然而，对于本领域技术人员而言显而易见的是，本申请可以无需一个或多个这些细节而得以实施。在其他的例子中，为了避免与本申请发生混淆，对于本领域公知的一些技术特征未进行描述。
应当理解的是，本申请能够以不同形式实施，而不应当解释为局限于这里提出的实施例。相反地，提供这些实施例将使公开彻底和完全，并且将本申请的范围完全地传递给本领域技术人员。
在此使用的术语的目的仅在于描述具体实施例并且不作为本申请的限制。在此使用时，单数形式的“一”、“一个”和“所述/该”也意图包括复数形式，除非上下文清楚指出另外的方式。还应明白术语“组成”和/或“包括”，当在该说明书中使用时，确定所述特征、整数、步骤、操作、元件和/或部件的存在，但不排除一个或更多其它的特征、整数、步骤、操作、元件、部件和/或组的存在或添加。在此使用时，术语“和/或”包括相关所列项目的任何及所有组合。
为了彻底理解本申请，将在下列的描述中提出详细的步骤以及详细的结构，以便阐释本申请提出的技术方案。本申请的较佳实施例详细描述如下，然而除了这些详细描述外，本申请还可以具有其他实施方式。
图1示出了在不同环境温度下对同一被测对象测量温度时的温度变化曲线的示意图。如图1所示，对于同一被测对象，在环境温度为25℃时的温度变化曲线为110，在环境温度为20℃时的温度变化曲线为120，很明显，曲线110和曲线120并不重合，两者有很明显的差异。因此，环境温度的不同会导致探头测量的温度变化曲线特征差异显著，导致最后的预测 结果出现偏差。
基于此，本申请提供一种温度预测方案，下面结合图2到图8来描述。图2示出了根据本申请一个实施例的温度预测方法200的示意性流程图。如图2所示，温度预测方法200可以包括如下步骤：
在步骤S210，获取被测对象所处环境的温度作为环境温度。
在步骤S220，基于预构建的补偿关系获取与环境温度对应的补偿特征，所述补偿关系反映不同环境温度下进行温度测量时应采用的补偿特征。
在步骤S230，基于所获取的补偿特征对所述被测对象的温度预测进行补偿修正，以获得并输出所述被测对象的温度预测结果。
在本申请的实施例中，考虑到环境温度影响对被测对象的温度(体温)预测结果，因而首先需要在步骤S210中获取被测对象所处环境的温度作为环境温度，并通过下文中将描述的方法补偿或排除环境温度对温度预测结果的影响。在本申请的实施例中，可以通过多种方式获取被测对象所处环境的温度以得到环境温度。在一个示例中，可以通过对被测对象所处的环境进行直接测量而得到环境温度，诸如通过能够对环境温度进行测量的各种温度测量设备或者各种测量方法。在另一个示例中，可以根据测量设备(诸如体温测量探头)对被测对象进行测量后得到的温度变化曲线而得到环境温度。在其他示例中，还可以通过任何其他合适的方式获取被测对象所处环境的温度以得到环境温度。
在本申请的实施例中，步骤S220中的补偿关系是为了补偿修正因环境温度造成的预测结果偏差而预先构建的，该补偿关系能够反映在各种环境温度下应该采用怎样的补偿特征来对温度预测的过程或结果进行补偿。因此，补偿关系至少可以包括环境温度与补偿特征之间的对应关系。在一个示例中，补偿关系可以包括不同环境温度与补偿特征之间关系的曲线、函数或图表。基于预先构建的补偿关系，在步骤S210获取到当前环境温度后，可根据该预先构建的补偿关系获取与当前环境温度相对应的补偿特征，以用于对被测对象的温度预测进行补偿修正。
在本申请的实施例中，对被测对象的温度预测的补偿修正可以包括对温度预测过程的补偿修正，也可以包括对温度预测结果的修正。补偿修正对象不同，所获取的补偿特征将是不同的，补偿修正的过程也是不同的。下面结合图3到图4来描述。
图3示出根据本申请实施例的温度预测方法中进行补偿修正的一个示例过程300的示意性流程图，在该示例中，所获取的补偿特征为预测结果偏差。如图3所示，过程300可以包括以下步骤：
在步骤S310，获取测量设备根据预测模型对所述被测对象的初始温度预测结果。
在步骤S320，基于所获取的预测结果偏差对所述初始温度预测结果进行修正，修正后的结果为所述被测对象的温度预测结果。
在该示例中，基于预构建的补偿关系获取的补偿特征是预测结果偏差，也就是说，在该示例中，可以对温度预测结果进行补偿修正。因此，可以首先由测量设备输出被测对象的初始温度预测结果，该初始温度预测结果是测量设备(诸如体温测量探头)常规对被测对象进行测量得到一些数据后根据预测模型预测得到的结果。该初始温度预测结果是没有经过补偿修正的结果，为了与最终的温度预测结果(即补偿修正后的结果)相区分而如此命名。接着，可以基于获取的补偿特征(在该示例中为预测结果偏差)对测量设备的初始温度预测结果进行修正，以得到修正后的结果，作为被测对象的温度预测结果。该温度预测结果是根据环境温度获取的补偿特征补偿得到的更为准确的温度预测结果。
在该示例中，基于预构建的补偿关系获取的补偿特征是预测结果偏差，也就是说，预构建的补偿关系反映的是不同环境温度与预测结果偏差之间的关系。基于此，可以通过不同的实施方式来实现补偿关系的构建。应理解，由于补偿关系是预先构建，因此其构建时采用的各种数据并非是针对当前被测对象得到的数据，而是在不同实验条件下根据实验对象得到的数据。当前，也不排除当前被测对象曾经可能也是实验对象。此外，实验中采用的测量设备和根据本申请实施例方法中的测量设备可以是同一设备，也可以是不同设备，当为不同设备时，它们可以是同类型的、同型号的、同厂商的设备等。下面描述在图3所示的示例中构建补偿关系的不同实施方式。
在一个实施方式中，可以通过如下步骤实现补偿关系的构建：获取测量设备在不同环境温度下对同一目标温度的预测结果偏差；以环境温度为自变量，以预测结果偏差为因变量，构建不同环境温度与预测结果偏差之间的关系，作为所述补偿关系。在该实施方式中，构建的补偿关系能够反 映在测量同一目标温度(目标温度是指被测对象实际的热平衡温度)时不同环境温度与预测结果偏差之间的关系。构建的方法例如可以通过拟合环境温度与预测结果偏差之间的关系曲线或函数，或者使用机器学习方法构建不同环境温度与预测结果偏差之间的关系模型等等。基于不同环境温度与预测结果偏差之间的关系，当在步骤S210中获取到环境温度后，可以根据该关系获取相应的预测结果偏差作为补偿特征，以用于对测量设备的初始温度预测结果进行修正。
在另一个实施方式中，可以通过如下步骤实现补偿关系的构建：获取测量设备在不同环境温度下对同一目标温度的预测结果，包括参考环境温度下的参考预测结果和其他环境温度下的其他预测结果；以所述参考环境温度与所述其他环境温度的差值为自变量，以所述参考预测结果与所述其他预测结果之间的差值为因变量，构建不同环境温度与预测结果偏差之间的关系，作为所述补偿关系。该实施方式与上一实施方式类似，构建的补偿关系也能够反映在测量同一目标温度时不同环境温度与预测结果偏差之间的关系。但与上一实施方式不同的是，其不是以环境温度为变量且以预测结果偏差为因变量，而是从不同环境温度中设置一个环境温度作为参考环境温度，并将参考环境温度与其他环境温度的差值作为自变量、且将参考环境温度下的预测结果(称为参考预测结果)与其他环境温度下的预测结果(称为其他预测结果)之间的差值作为因变量来构建补偿关系。构建的方式也例如可以是通过拟合或者机器学习方法。根据该补偿关系，当在步骤S210中获取到环境温度后，可以首先计算前述的参考环境温度与当前获取的环境温度之间的差值，然后根据该补偿关系获取与该差值对应的另一差值，根据该另一差值和前述的参考预测结果偏差得到当前环境温度下的预测结果偏差，即补偿特征，以用于对测量设备的初始温度预测结果进行修正。
在再一个实施方式中，可以通过如下步骤实现补偿关系的构建：获取测量设备在不同环境温度下对不同目标温度的预测结果偏差；以环境温度和目标温度为自变量，以预测结果偏差为因变量，构建不同环境温度和目标温度与预测结果偏差之间的关系，作为所述补偿关系。在该实施方式中，构建的补偿关系能够反映在测量不同目标温度(目标温度是指被测对象实际的热平衡温度)时不同环境温度与预测结果偏差之间的关系。构建的方 法例如可以通过拟合环境温度、目标温度与预测结果偏差之间的关系曲面或函数，或者使用机器学习方法构建不同环境温度和目标温度与预测结果偏差之间的关系模型等等。基于不同环境温度和目标温度与预测结果偏差之间的关系，当在步骤S210中获取到环境温度后，再获取目标温度(目标温度由于是最终需要求得的量，此时还是未知量，但可以用已知量(环境温度和补偿特征)来表示)，然后根据该关系获取相应的预测结果偏差作为补偿特征，以用于对测量设备的初始温度预测结果进行修正。
以上示例性地示出了获取的补偿特征为预测结果偏差时补偿修正的过程以及补偿关系的构建。下面结合图4描述根据本申请实施例的温度预测方法中进行补偿修正的另一个示例过程400的示意性流程图，在该示例中，所获取的补偿特征为温度变化曲线特征。如图4所示，过程400可以包括以下步骤：
在步骤S410，获取测量设备对所述被测对象进行测量后得到的初始温度变化曲线。
在步骤S420，基于所获取的温度变化曲线特征对所述初始温度变化曲线进行修正，所述被测对象的温度预测结果是根据修正后的温度变化曲线和预测模型得到的。
在该示例中，基于预构建的补偿关系获取的补偿特征是温度变化曲线特征(诸如温度变化曲线的时间常数、温度变化曲线的曲线斜率、温度变化曲线预设时间点的温度值等等)，也就是说，在该示例中，可以对温度预测过程进行补偿修正。对温度预测过程的补偿修正可以是根据获取的温度变化曲线特征对温度变化曲线进行修正(如图4所示的)，也可以是直接将获取的温度变化曲线特征输入到预测模型得到最终的温度预测结果(未示出)。因此，在图4所示的示例中，可以在测试设备预测结果之前，先获取测量设备对被测对象进行测量得到的初始温度变化曲线，该初始温度变化曲是测量设备(诸如体温测量探头)常规对被测对象进行测量得到的结果。该初始温度变化曲线是没有经过补偿修正的，为了与补偿后的温度变化曲线相区分而如此命名。接着，可以基于获取的补偿特征(在该示例中为温度变化曲线特征)对测量设备的初始温度变化曲线进行修正，以得到修正后的温度变化曲线，测量设备根据该修正后的温度变化曲线和预测模型可得到被测对象的最终的温度预测结果。该温度预测结果是根据环境温度获 取的补偿特征补偿得到的更为准确的温度预测结果。
在该示例中，基于预构建的补偿关系获取的补偿特征是温度变化曲线特征，也就是说，预构建的补偿关系反映的是不同环境温度与温度变化曲线特征之间的关系。基于此，可以通过不同的实施方式来实现补偿关系的构建。应理解，由于补偿关系是预先构建，因此其构建时采用的各种数据并非是针对当前被测对象得到的数据，而是在不同实验条件下根据实验对象得到的数据。当前，也不排除当前被测对象曾经可能也是实验对象。此外，实验中采用的测量设备和根据本申请实施例方法中的测量设备可以是同一设备，也可以是不同设备，当为不同设备时，它们可以是同类型的、同型号的、同厂商的设备等。下面描述在图4所示的示例中构建补偿关系的不同实施方式。
在一个实施方式中，可以通过如下步骤实现补偿关系的构建：获取测量设备从不同环境温度到达同一目标温度各自的温度变化曲线；提取所述温度变化曲线的特征，得到温度变化曲线特征；以环境温度为自变量，以温度变化曲线特征为因变量，构建不同环境温度与温度变化曲线特征之间的关系，作为所述补偿关系。在该实施方式中，构建的补偿关系能够反映在测量同一目标温度(目标温度是指被测对象实际的热平衡温度)时不同环境温度与温度变化曲线特征之间的关系。构建的方法例如可以通过拟合环境温度与温度变化曲线特征之间的关系曲线或函数，或者使用机器学习方法构建不同环境温度与温度变化曲线特征之间的关系模型等等。基于不同环境温度与温度变化曲线特征之间的关系，当在步骤S210中获取到环境温度后，可以根据该关系获取相应的温度变化曲线特征作为补偿特征，以用于对测量设备的初始温度变化曲线进行修正。测量设备根据该修正后的温度变化曲线和预测模型可得到被测对象的最终的温度预测结果。
在另一个实施方式中，可以通过如下步骤实现补偿关系的构建：获取测量设备从不同环境温度到达同一目标温度各自的温度变化曲线，包括与参考环境温度对应的参考温度变化曲线和与其他环境温度对应的其他温度变化曲线；提取所述参考温度变化曲线和所述其他温度变化曲线各自的特征，分别得到参考曲线特征和其他曲线特征；以所述参考环境温度与所述其他环境温度之间的差值为自变量，以所述参考曲线特征与所述其他曲线特征之间的差值为因变量，构建不同环境温度与温度变化曲线特征之间的 关系，作为所述补偿关系。该实施方式与上一实施方式类似，构建的补偿关系也能够反映在测量同一目标温度时不同环境温度与温度变化曲线特征之间的关系。但与上一实施方式不同的是，其不是以环境温度为变量且以温度变化曲线特征为因变量，而是从不同环境温度中设置一个环境温度作为参考环境温度，并将参考环境温度与其他环境温度的差值作为自变量、且将参考环境温度下的温度变化曲线特征(称为参考曲线特征)与其他环境温度下的温度变化曲线特征(称为其他曲线特征)之间的差值作为因变量来构建补偿关系。构建的方式也例如可以是通过拟合或者机器学习方法。根据该补偿关系，当在步骤S210中获取到环境温度后，可以首先计算前述的参考环境温度与当前获取的环境温度之间的差值，然后根据该补偿关系获取与该差值对应的另一差值，根据该另一差值和前述的参考曲线特征得到当前环境温度下的温度变化曲线特征，即补偿特征，以用于对测量设备的初始温度变化曲线进行修正。测量设备根据该修正后的温度变化曲线和预测模型可得到被测对象的最终的温度预测结果。
在再一个实施方式中，可以通过如下步骤实现补偿关系的构建：获取测量设备从不同环境温度到达不同目标温度各自的温度变化曲线；提取所述温度变化曲线的特征，得到温度变化曲线特征；以环境温度和目标温度为自变量，以温度变化曲线特征为因变量，构建不同环境温度和目标温度与温度变化曲线特征之间的关系，作为所述补偿关系。在该实施方式中，构建的补偿关系能够反映在测量不同目标温度(目标温度是指被测对象实际的热平衡温度)时不同环境温度与温度变化曲线特征之间的关系。构建的方法例如可以通过拟合环境温度、目标温度与温度变化曲线特征之间的关系曲面或函数，或者使用机器学习方法构建不同环境温度和目标温度与温度变化曲线特征之间的关系模型等等。基于不同环境温度和目标温度与温度变化曲线特征之间的关系，当在步骤S210中获取到环境温度后，再获取目标温度(目标温度由于是最终需要求得的量，此时还是未知量，但可以用已知量(环境温度和补偿特征)来表示)，然后根据该关系获取相应的温度变化曲线特征作为补偿特征，以用于对测量设备的初始温度变化曲线进行修正。测量设备根据该修正后的温度变化曲线和预测模型可得到被测对象的最终的温度预测结果。
以上示例性地示出了获取的补偿特征为温度变化曲线特征时补偿修 正的过程以及补偿关系的构建。
在本申请的其他实施例中，补偿关系的构建可以更为简化，例如将补偿关系构建为是经验补偿系数，直接将经验补偿系数乘以环境温度得到补偿特征，再根据补偿特征对温度预测进行补偿修正即可。
以上示例性地示出了根据本申请一个实施例的温度预测方法200。图5示出了不同环境温度下未采用和采用根据本申请实施例的温度预测方法得到的温度预测结果的比较。如图5所示的，曲线510示出了不同环境温度下未采用根据本申请实施例的温度预测方法的温度预测结果，曲线520示出了不同环境温度下采用根据本申请实施例的温度预测方法的温度预测结果。很明显，采用根据本申请实施例的温度预测方法在不同环境温度下得到的温度预测结果均非常接近于目标预测温度(目标温度)，而未采用根据本申请实施例的温度预测方法的温度预测结果在不同环境温度下得到的温度预测结果之间有较大的偏差。
基于上面的描述，根据本申请实施例的温度预测方法200考虑被测对象所处环境的温度对温度预测的影响，通过预先构建的环境温度与补偿特征之间的关系，得到被测对象所处环境的温度对应的补偿特征对当前温度预测进行补偿修正，从而能够补偿因环境温度造成的预测偏差，提高温度预测结果的准确性。
下面结合图6描述根据本申请另一个实施例的温度预测方法600的示意性流程图。如图6所示，温度预测方法600可以包括如下步骤：
在步骤S610，获取被测对象所处环境的温度作为环境温度，并获取测量设备对所述被测对象进行测量后得到的温度变化曲线。
在步骤S620，基于预构建的目标温度预测模型获取与所述环境温度和温度变化曲线对应的目标温度，得到并输出所述被测对象的温度预测结果。
根据本申请实施例的温度预测方法600与前文的温度预测方法200类似，都是考虑到环境温度影响对被测对象的温度预测结果，排除环境温度对温度预测结果的影响。不同之处在于，温度预测方法200是基于预构建的反映环境温度与补偿特征之间关系的补偿关系，获取与当前环境温度相对应的补偿特征对温度预测的过程或结果进行补偿；而温度预测方法600则是基于预构建的反映环境温度和温度变化曲线与目标温度之间的关系的目标温度预测模型，将获取的环境温度和测量设备对被测对象进行测量后 得到的温度变化曲线输入该模型，直接得到被测对象的温度预测结果(即目标温度)。
在本申请的实施例中，步骤S620中的目标温度预测模型可以通过如下方式来构建：获取测量设备从不同环境温度到达不同目标温度各自的温度变化曲线；以环境温度和温度变化曲线为自变量，以目标温度为因变量，构建不同环境温度和温度变化曲线与目标温度之间的关系，得到目标温度预测模型。在该实施例中，构建的目标温度预测模型能够用于根据当前环境温度和测量设备对被测对象测量得到的温度变化曲线直接输出被测对象的温度预测结果。由于该目标温度预测模型已考虑了环境温度的影响，因而得到的温度预测结果相当于是补偿后的结果，是准确的结果。示例性地，构建该目标温度预测模型的方法例如可以包括函数拟合、机器学习方法训练等等。
下面结合图7描述根据本申请另一个实施例的温度预测方法700的示意性流程图。如图7所示，温度预测方法700可以包括如下步骤：
在步骤S710，获取被测对象所处环境的温度作为环境温度，并获取测量设备对所述被测对象进行测量后得到的温度变化曲线。
在步骤S720，提取所述温度变化曲线的特征，得到温度变化曲线特征。
在步骤S730，基于预构建的目标温度预测模型获取与所述环境温度和温度变化曲线特征对应的目标温度，得到并输出所述被测对象的温度预测结果。
根据本申请实施例的温度预测方法700与前文的温度预测方法600大体上类似，不同之处仅在于，温度预测方法600是基于预构建的反映环境温度和温度变化曲线与目标温度之间的关系的目标温度预测模型，将获取的环境温度和测量设备对被测对象进行测量后得到的温度变化曲线输入该模型，直接得到被测对象的温度预测结果；而温度预测方法700是基于预构建的反映环境温度和温度变化曲线特征与目标温度之间的关系的目标温度预测模型，将获取的环境温度和测量设备对被测对象进行测量后得到的温度变化曲线的特征(即温度变化曲线特征，例如温度变化曲线的时间常数、温度变化曲线的曲线斜率、温度变化曲线预设时间点的温度值等等)输入该模型，直接得到被测对象的温度预测结果(即目标温度)。
在本申请的实施例中，步骤S720中的目标温度预测模型可以通过如 下方式来构建：获取所述测量设备从不同环境温度到达不同目标温度各自的温度变化曲线；提取所述温度变化曲线的特征，得到温度变化曲线特征；以环境温度和温度变化曲线特征为自变量，以目标温度为因变量，构建不同环境温度和温度变化曲线特征与目标温度之间的关系，得到所述目标温度预测模型。在该实施例中，构建的目标温度预测模型能够用于根据当前环境温度和测量设备对被测对象测量得到的温度变化曲线的特征直接输出被测对象的温度预测结果。由于该目标温度预测模型已考虑了环境温度的影响，因而得到的温度预测结果相当于是补偿后的结果，是准确的结果。示例性地，构建该目标温度预测模型的方法例如可以包括函数拟合、机器学习方法训练等等。
基于上面的描述，根据本申请实施例的温度预测方法在对被测对象就行温度预测时考虑被测对象所处环境的温度对温度预测的影响，能够避免因环境温度造成预测偏差，提高温度预测结果的准确性。
下面结合图8描述根据本申请另一方面提供的温度预测装置。图8示出了根据本申请实施例的温度预测装置800的示意性结构框图。如图8所示，温度预测装置800可以包括存储器810、处理器820和输出设备830，存储器810上存储有由处理器820运行的计算机程序，所述计算机程序在被处理器820运行时执行前文所述的根据本申请实施例的温度预测方法。本领域技术人员可以结合前文的描述理解根据本申请实施例的温度预测装置800中各部件的操作，为了简洁，此处仅描述其主要操作，不再描述细节。
在本申请的一个实施例中，所述计算机程序在被处理器820运行时执行如下步骤：获取被测对象所处环境的温度作为环境温度；基于预构建的补偿关系获取与所述环境温度对应的补偿特征，所述补偿关系反映不同环境温度下进行温度测量时应采用的补偿特征；基于所获取的补偿特征对所述被测对象的温度预测进行补偿修正，以获得并由所述输出设备输出所述被测对象的温度预测结果。
在本申请的一个实施例中，所述补偿关系包括反映不同环境温度与补偿特征之间关系的曲线、函数或图表。
在本申请的一个实施例中，所述补偿特征为预测结果偏差，所述计算机程序在被处理器820运行时执行的所述补偿修正包括：获取测量设备根据预测模型对所述被测对象的初始温度预测结果；基于所获取的预测结果偏 差对所述初始温度预测结果进行修正，修正后的结果为所述被测对象的温度预测结果。
在本申请的一个实施例中，所述补偿关系的构建，包括：获取测量设备在不同环境温度下对同一目标温度的预测结果偏差；以环境温度为自变量，以预测结果偏差为因变量，构建不同环境温度与预测结果偏差之间的关系，作为所述补偿关系。
在本申请的一个实施例中，所述补偿关系的构建，包括：获取测量设备在不同环境温度下对不同目标温度的预测结果偏差；以环境温度和目标温度为自变量，以预测结果偏差为因变量，构建不同环境温度和目标温度与预测结果偏差之间的关系，作为所述补偿关系。
在本申请的一个实施例中，所述补偿关系的构建，包括：获取测量设备在不同环境温度下对同一目标温度的预测结果，包括参考环境温度下的参考预测结果和其他环境温度下的其他预测结果；以所述参考环境温度与所述其他环境温度的差值为自变量，以所述参考预测结果与所述其他预测结果之间的差值为因变量，构建不同环境温度与预测结果偏差之间的关系，作为所述补偿关系。
在本申请的一个实施例中，所述补偿特征为温度变化曲线特征，所述计算机程序在被处理器820运行时执行的所述补偿修正包括：获取测量设备对所述被测对象进行测量后得到的初始温度变化曲线，基于所获取的温度变化曲线特征对所述初始温度变化曲线进行修正，所述被测对象的温度预测结果是根据修正后的温度变化曲线和预测模型得到的；或者将所述温度变化曲线特征输入到预测模型，得到所述被测对象的温度预测结果。
在本申请的一个实施例中，所述补偿关系的构建，包括：获取测量设备从不同环境温度到达同一目标温度各自的温度变化曲线；提取所述温度变化曲线的特征，得到温度变化曲线特征；以环境温度为自变量，以温度变化曲线特征为因变量，构建不同环境温度与温度变化曲线特征之间的关系，作为所述补偿关系。
在本申请的一个实施例中，所述补偿关系的构建，包括：获取测量设备从不同环境温度到达不同目标温度各自的温度变化曲线；提取所述温度变化曲线的特征，得到温度变化曲线特征；以环境温度和目标温度为自变量，以温度变化曲线特征为因变量，构建不同环境温度和目标温度与温度 变化曲线特征之间的关系，作为所述补偿关系。
在本申请的一个实施例中，所述补偿关系的构建，包括：获取测量设备从不同环境温度到达同一目标温度各自的温度变化曲线，包括与参考环境温度对应的参考温度变化曲线和与其他环境温度对应的其他温度变化曲线；提取所述参考温度变化曲线和所述其他温度变化曲线各自的特征，分别得到参考曲线特征和其他曲线特征；以所述参考环境温度与所述其他环境温度之间的差值为自变量，以所述参考曲线特征与所述其他曲线特征之间的差值为因变量，构建不同环境温度与温度变化曲线特征之间的关系，作为所述补偿关系。
在本申请的一个实施例中，所述补偿关系包括经验补偿系数，所述计算机程序在被处理器820运行时执行的所述获取与所述环境温度对应的补偿特征，包括：将所获取的环境温度乘以所述经验补偿系数，得到所述补偿特征。
在本申请的一个实施例中，所述计算机程序在被处理器820运行时执行如下步骤：获取被测对象所处环境的温度作为环境温度，并获取测量设备对所述被测对象进行测量后得到的温度变化曲线；基于预构建的目标温度预测模型获取与所述环境温度和温度变化曲线对应的目标温度，得到并由所述输出设备输出所述被测对象的温度预测结果。
在本申请的一个实施例中，所述目标温度预测模型的构建，包括：获取所述测量设备从不同环境温度到达不同目标温度各自的温度变化曲线；以环境温度和温度变化曲线为自变量，以目标温度为因变量，构建不同环境温度和温度变化曲线与目标温度之间的关系，得到所述目标温度预测模型。
在本申请的一个实施例中，所述计算机程序在被处理器820运行时还执行如下步骤：在得到所述初始温度变化曲线后，提取所述初始温度变化曲线的特征，得到温度变化曲线特征；并且所述计算机程序在被所述处理器运行时执行的所述获取与所述环境温度和所述温度变化曲线对应的目标温度，包括：获取与所述环境温度和所述温度变化曲线特征对应的目标温度。
在本申请的一个实施例中，所述目标温度预测模型的构建，包括：获取所述测量设备从不同环境温度到达不同目标温度各自的温度变化曲线；提取所述温度变化曲线的特征，得到温度变化曲线特征；以环境温度和温 度变化曲线特征为自变量，以目标温度为因变量，构建不同环境温度和温度变化曲线特征与目标温度之间的关系，得到所述目标温度预测模型。
在本申请的一个实施例中，所述温度变化曲线特征包括以下中的任一项：温度变化曲线的时间常数、温度变化曲线的曲线斜率、温度变化曲线预设时间点的温度值。
在本申请的一个实施例中，所述测量设备为体温测量探头。
在本申请的一个实施例中，所述环境温度是对所述被测对象所处的环境进行直接测量而得到的，或者是根据测量设备对所述被测对象进行测量后得到的温度变化曲线而得到的。
此外，根据本申请实施例，还提供了一种存储介质，在所述存储介质上存储了程序指令，在所述程序指令被计算机或处理器运行时用于执行本申请实施例的温度预测方法的相应步骤。所述存储介质例如可以包括智能电话的存储卡、平板电脑的存储部件、个人计算机的硬盘、只读存储器(ROM)、可擦除可编程只读存储器(EPROM)、便携式紧致盘只读存储器(CD-ROM)、USB存储器、或者上述存储介质的任意组合。所述计算机可读存储介质可以是一个或多个计算机可读存储介质的任意组合。
此外，根据本申请实施例，还提供了一种计算机程序，该计算机程序可以存储在云端或本地的存储介质上。在该计算机程序被计算机或处理器运行时用于执行本申请实施例的温度预测方法的相应步骤。
根据本申请实施例的温度预测方法、装置和存储介质在对被测对象就行温度预测时考虑被测对象所处环境的温度对温度预测的影响，能够避免因环境温度造成预测偏差，提高温度预测结果的准确性。
尽管这里已经参考附图描述了示例实施例，应理解上述示例实施例仅仅是示例性的，并且不意图将本申请的范围限制于此。本领域普通技术人员可以在其中进行各种改变和修改，而不偏离本申请的范围和精神。所有这些改变和修改意在被包括在所附权利要求所要求的本申请的范围之内。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范 围。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个装置，或一些特征可以忽略，或不执行。
在此处所提供的说明书中，说明了大量具体细节。然而，能够理解，本申请的实施例可以在没有这些具体细节的情况下实践。在一些实例中，并未详细示出公知的方法、结构和技术，以便不模糊对本说明书的理解。
类似地，应当理解，为了精简本申请并帮助理解各个发明方面中的一个或多个，在对本申请的示例性实施例的描述中，本申请的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而，并不应将该本申请的方法解释成反映如下意图：即所要求保护的本申请要求比在每个权利要求中所明确记载的特征更多的特征。更确切地说，如相应的权利要求书所反映的那样，其发明点在于可以用少于某个公开的单个实施例的所有特征的特征来解决相应的技术问题。因此，遵循具体实施方式的权利要求书由此明确地并入该具体实施方式，其中每个权利要求本身都作为本申请的单独实施例。
本领域的技术人员可以理解，除了特征之间相互排斥之外，可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者装置的所有过程或单元进行组合。除非另外明确陈述，本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。
此外，本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征，但是不同实施例的特征的组合意味着处于本申请的范围之内并且形成不同的实施例。例如，在权利要求书中，所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
本申请的各个部件实施例可以以硬件实现，或者以在一个或者多个处理器上运行的软件模块实现，或者以它们的组合实现。本领域的技术人员应当理解，可以在实践中使用微处理器或者数字信号处理器(DSP)来实 现根据本申请实施例的一些模块的一些或者全部功能。本申请还可以实现为用于执行这里所描述的方法的一部分或者全部的装置程序(例如，计算机程序和计算机程序产品)。这样的实现本申请的程序可以存储在计算机可读介质上，或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到，或者在载体信号上提供，或者以任何其他形式提供。
应该注意的是上述实施例对本申请进行说明而不是对本申请进行限制，并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在权利要求中，不应将位于括号之间的任何参考符号构造成对权利要求的限制。本申请可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中，这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。
以上所述，仅为本申请的具体实施方式或对具体实施方式的说明，本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。本申请的保护范围应以权利要求的保护范围为准。

Claims (37)

  1. 一种温度预测方法，其特征在于，所述方法包括：
    获取被测对象所处环境的温度作为环境温度；
    基于预构建的补偿关系获取与所述环境温度对应的补偿特征，所述补偿关系反映不同环境温度下进行温度测量时应采用的补偿特征；
    基于所获取的补偿特征对所述被测对象的温度预测进行补偿修正，以获得并输出所述被测对象的温度预测结果。
  2. 根据权利要求1所述的方法，其特征在于，所述补偿关系包括反映不同环境温度与补偿特征之间关系的曲线、函数或图表。
  3. 根据权利要求1所述的方法，其特征在于，所述补偿特征为预测结果偏差，所述补偿修正包括：
    获取测量设备根据预测模型对所述被测对象的初始温度预测结果；
    基于所获取的预测结果偏差对所述初始温度预测结果进行修正，修正后的结果为所述被测对象的温度预测结果。
  4. 根据权利要求3所述的方法，其特征在于，所述补偿关系的构建，包括：
    获取测量设备在不同环境温度下对同一目标温度的预测结果偏差；
    以环境温度为自变量，以预测结果偏差为因变量，构建不同环境温度与预测结果偏差之间的关系，作为所述补偿关系。
  5. 根据权利要求3所述的方法，其特征在于，所述补偿关系的构建，包括：
    获取测量设备在不同环境温度下对不同目标温度的预测结果偏差；
    以环境温度和目标温度为自变量，以预测结果偏差为因变量，构建不同环境温度和目标温度与预测结果偏差之间的关系，作为所述补偿关系。
  6. 根据权利要求3所述的方法，其特征在于，所述补偿关系的构建，包括：
    获取测量设备在不同环境温度下对同一目标温度的预测结果偏差，包括参考环境温度下的参考预测结果偏差和其他环境温度下的其他预测结果偏差；
    以所述参考环境温度与所述其他环境温度的差值为自变量，以所述参考预测结果偏差与所述其他预测结果偏差之间的差值为因变量，构建不同 环境温度与预测结果偏差之间的关系，作为所述补偿关系。
  7. 根据权利要求1所述的方法，其特征在于，所述补偿特征为温度变化曲线特征，所述补偿修正包括：
    获取测量设备对所述被测对象进行测量后得到的初始温度变化曲线，基于所获取的温度变化曲线特征对所述初始温度变化曲线进行修正，所述被测对象的温度预测结果是根据修正后的温度变化曲线和预测模型得到的；或者
    将所述温度变化曲线特征输入到预测模型，得到所述被测对象的温度预测结果。
  8. 根据权利要求7所述的方法，其特征在于，所述补偿关系的构建，包括：
    获取测量设备从不同环境温度到达同一目标温度各自的温度变化曲线；
    提取所述温度变化曲线的特征，得到温度变化曲线特征；
    以环境温度为自变量，以温度变化曲线特征为因变量，构建不同环境温度与温度变化曲线特征之间的关系，作为所述补偿关系。
  9. 根据权利要求7所述的方法，其特征在于，所述补偿关系的构建，包括：
    获取测量设备从不同环境温度到达不同目标温度各自的温度变化曲线；
    提取所述温度变化曲线的特征，得到温度变化曲线特征；
    以环境温度和目标温度为自变量，以温度变化曲线特征为因变量，构建不同环境温度和目标温度与温度变化曲线特征之间的关系，作为所述补偿关系。
  10. 根据权利要求7所述的方法，其特征在于，所述补偿关系的构建，包括：
    获取测量设备从不同环境温度到达同一目标温度各自的温度变化曲线，包括与参考环境温度对应的参考温度变化曲线和与其他环境温度对应的其他温度变化曲线；
    提取所述参考温度变化曲线和所述其他温度变化曲线各自的特征，分别得到参考曲线特征和其他曲线特征；
    以所述参考环境温度与所述其他环境温度之间的差值为自变量，以所述参考曲线特征与所述其他曲线特征之间的差值为因变量，构建不同环境温度与温度变化曲线特征之间的关系，作为所述补偿关系。
  11. 根据权利要求1或3或7所述的方法，其特征在于，所述补偿关系包括经验补偿系数，所述获取与所述环境温度对应的补偿特征，包括：
    将所获取的环境温度乘以所述经验补偿系数，得到所述补偿特征。
  12. 一种温度预测方法，其特征在于，所述方法包括：
    获取被测对象所处环境的温度作为环境温度，并获取测量设备对所述被测对象进行测量后得到的温度变化曲线；
    基于预构建的目标温度预测模型获取与所述环境温度和温度变化曲线对应的目标温度，得到并输出所述被测对象的温度预测结果。
  13. 根据权利要求12所述的方法，其特征在于，所述目标温度预测模型的构建，包括：
    获取所述测量设备从不同环境温度到达不同目标温度各自的温度变化曲线；
    以环境温度和温度变化曲线为自变量，以目标温度为因变量，构建不同环境温度和温度变化曲线与目标温度之间的关系，得到所述目标温度预测模型。
  14. 根据权利要求12所述的方法，其特征在于，所述方法还包括：
    在得到所述温度变化曲线后，提取所述温度变化曲线的特征，得到温度变化曲线特征；并且
    所述获取与所述环境温度和所述温度变化曲线对应的目标温度，包括：获取与所述环境温度和所述温度变化曲线特征对应的目标温度。
  15. 根据权利要求14所述的方法，其特征在于，所述目标温度预测模型的构建，包括：
    获取所述测量设备从不同环境温度到达不同目标温度各自的温度变化曲线；
    提取所述温度变化曲线的特征，得到温度变化曲线特征；
    以环境温度和温度变化曲线特征为自变量，以目标温度为因变量，构建不同环境温度和温度变化曲线特征与目标温度之间的关系，得到所述目标温度预测模型。
  16. 根据权利要求7-10以及14-15中的任一项所述的方法，其特征在于，所述温度变化曲线特征包括以下中的任一项：
    温度变化曲线的时间常数、温度变化曲线的曲线斜率、温度变化曲线预设时间点的温度值。
  17. 根据权利要求3-16中的任一项所述的方法，其特征在于，所述测量设备为体温测量探头。
  18. 根据权利要求1-17中的任一项所述的方法，其特征在于，所述环境温度是对所述被测对象所处的环境进行直接测量而得到的，或者是根据测量设备对所述被测对象进行测量后得到的温度变化曲线而得到的。
  19. 一种温度预测装置，其特征在于，所述装置包括存储器、处理器和输出设备，所述存储器上存储有由所述处理器运行的计算机程序，所述计算机程序在被所述处理器运行时执行如下步骤：
    获取被测对象所处环境的温度作为环境温度；
    基于预构建的补偿关系获取与所述环境温度对应的补偿特征，所述补偿关系反映不同环境温度下进行温度测量时应采用的补偿特征；
    基于所获取的补偿特征对所述被测对象的温度预测进行补偿修正，以获得并由所述输出设备输出所述被测对象的温度预测结果。
  20. 根据权利要求19所述的装置，其特征在于，所述补偿关系包括反映不同环境温度与补偿特征之间关系的曲线、函数或图表。
  21. 根据权利要求19所述的装置，其特征在于，所述补偿特征为预测结果偏差，所述计算机程序在被所述处理器运行时执行的所述补偿修正包括：
    获取测量设备根据预测模型对所述被测对象的初始温度预测结果；
    基于所获取的预测结果偏差对所述初始温度预测结果进行修正，修正后的结果为所述被测对象的温度预测结果。
  22. 根据权利要求21所述的装置，其特征在于，所述补偿关系的构建，包括：
    获取测量设备在不同环境温度下对同一目标温度的预测结果偏差；
    以环境温度为自变量，以预测结果偏差为因变量，构建不同环境温度与预测结果偏差之间的关系，作为所述补偿关系。
  23. 根据权利要求21所述的装置，其特征在于，所述补偿关系的构 建，包括：
    获取测量设备在不同环境温度下对不同目标温度的预测结果偏差；
    以环境温度和目标温度为自变量，以预测结果偏差为因变量，构建不同环境温度和目标温度与预测结果偏差之间的关系，作为所述补偿关系。
  24. 根据权利要求21所述的装置，其特征在于，所述补偿关系的构建，包括：
    获取测量设备在不同环境温度下对同一目标温度的预测结果偏差，包括参考环境温度下的参考预测结果偏差和其他环境温度下的其他预测结果偏差；
    以所述参考环境温度与所述其他环境温度的差值为自变量，以所述参考预测结果偏差与所述其他预测结果偏差之间的差值为因变量，构建不同环境温度与预测结果偏差之间的关系，作为所述补偿关系。
  25. 根据权利要求19所述的装置，其特征在于，所述补偿特征为温度变化曲线特征，所述计算机程序在被所述处理器运行时执行的所述补偿修正包括：
    获取测量设备对所述被测对象进行测量后得到的初始温度变化曲线，基于所获取的温度变化曲线特征对所述初始温度变化曲线进行修正，所述被测对象的温度预测结果是根据修正后的温度变化曲线和预测模型得到的；或者
    将所述温度变化曲线特征输入到预测模型，得到所述被测对象的温度预测结果。
  26. 根据权利要求25所述的装置，其特征在于，所述补偿关系的构建，包括：
    获取测量设备从不同环境温度到达同一目标温度各自的温度变化曲线；
    提取所述温度变化曲线的特征，得到温度变化曲线特征；
    以环境温度为自变量，以温度变化曲线特征为因变量，构建不同环境温度与温度变化曲线特征之间的关系，作为所述补偿关系。
  27. 根据权利要求25所述的装置，其特征在于，所述补偿关系的构建，包括：
    获取测量设备从不同环境温度到达不同目标温度各自的温度变化曲 线；
    提取所述温度变化曲线的特征，得到温度变化曲线特征；
    以环境温度和目标温度为自变量，以温度变化曲线特征为因变量，构建不同环境温度和目标温度与温度变化曲线特征之间的关系，作为所述补偿关系。
  28. 根据权利要求25所述的装置，其特征在于，所述补偿关系的构建，包括：
    获取测量设备从不同环境温度到达同一目标温度各自的温度变化曲线，包括与参考环境温度对应的参考温度变化曲线和与其他环境温度对应的其他温度变化曲线；
    提取所述参考温度变化曲线和所述其他温度变化曲线各自的特征，分别得到参考曲线特征和其他曲线特征；
    以所述参考环境温度与所述其他环境温度之间的差值为自变量，以所述参考曲线特征与所述其他曲线特征之间的差值为因变量，构建不同环境温度与温度变化曲线特征之间的关系，作为所述补偿关系。
  29. 根据权利要求19或21或25所述的装置，其特征在于，所述补偿关系包括经验补偿系数，所述计算机程序在被所述处理器运行时执行的所述获取与所述环境温度对应的补偿特征，包括：
    将所获取的环境温度乘以所述经验补偿系数，得到所述补偿特征。
  30. 一种温度预测装置，其特征在于，所述装置包括存储器、处理器和输出设备，所述存储器上存储有由所述处理器运行的计算机程序，所述计算机程序在被所述处理器运行时执行如下步骤：
    获取被测对象所处环境的温度作为环境温度，并获取测量设备对所述被测对象进行测量后得到的温度变化曲线；
    基于预构建的目标温度预测模型获取与所述环境温度和温度变化曲线对应的目标温度，得到并由所述输出设备输出所述被测对象的温度预测结果。
  31. 根据权利要求30所述的装置，其特征在于，所述目标温度预测模型的构建，包括：
    获取所述测量设备从不同环境温度到达不同目标温度各自的温度变化曲线；
    以环境温度和温度变化曲线为自变量，以目标温度为因变量，构建不同环境温度和温度变化曲线与目标温度之间的关系，得到所述目标温度预测模型。
  32. 根据权利要求30所述的装置，其特征在于，所述计算机程序在被所述处理器运行时还执行如下步骤：在得到所述温度变化曲线后，提取所述温度变化曲线的特征，得到温度变化曲线特征；并且
    所述计算机程序在被所述处理器运行时执行的所述获取与所述环境温度和所述温度变化曲线对应的目标温度，包括：获取与所述环境温度和所述温度变化曲线特征对应的目标温度。
  33. 根据权利要求32所述的装置，其特征在于，所述目标温度预测模型的构建，包括：
    获取所述测量设备从不同环境温度到达不同目标温度各自的温度变化曲线；
    提取所述温度变化曲线的特征，得到温度变化曲线特征；
    以环境温度和温度变化曲线特征为自变量，以目标温度为因变量，构建不同环境温度和温度变化曲线特征与目标温度之间的关系，得到所述目标温度预测模型。
  34. 根据权利要求25-28以及32-33中的任一项所述的装置，其特征在于，所述温度变化曲线特征包括以下中的任一项：
    温度变化曲线的时间常数、温度变化曲线的曲线斜率、温度变化曲线预设时间点的温度值。
  35. 根据权利要求21-34中的任一项所述的装置，其特征在于，所述测量设备为体温测量探头。
  36. 根据权利要求19-35中的任一项所述的装置，其特征在于，所述环境温度是对所述被测对象所处的环境进行直接测量而得到的，或者是根据测量设备对所述被测对象进行测量后得到的温度变化曲线而得到的。
  37. 一种存储介质，其特征在于，所述存储介质上存储有计算机程序，所述计算机程序在运行时执行如权利要求1-18中的任一项所述的温度预测方法。
PCT/CN2020/134508 2020-12-08 2020-12-08 温度预测方法、装置和存储介质 WO2022120563A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2020/134508 WO2022120563A1 (zh) 2020-12-08 2020-12-08 温度预测方法、装置和存储介质
CN202080107741.3A CN116648184A (zh) 2020-12-08 2020-12-08 温度预测方法、装置和存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/134508 WO2022120563A1 (zh) 2020-12-08 2020-12-08 温度预测方法、装置和存储介质

Publications (1)

Publication Number Publication Date
WO2022120563A1 true WO2022120563A1 (zh) 2022-06-16

Family

ID=81973966

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/134508 WO2022120563A1 (zh) 2020-12-08 2020-12-08 温度预测方法、装置和存储介质

Country Status (2)

Country Link
CN (1) CN116648184A (zh)
WO (1) WO2022120563A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115165461A (zh) * 2022-07-01 2022-10-11 佳木斯大学 智能化血浆取样装置及其操作系统
CN115736844A (zh) * 2022-11-16 2023-03-07 吉林省科英医疗激光有限责任公司 一种体表温度实时检测系统和检测方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101435727A (zh) * 2007-11-12 2009-05-20 深圳迈瑞生物医疗电子股份有限公司 温度预测方法及装置
CN107576421A (zh) * 2017-08-23 2018-01-12 王沛 一种体温测量设备、方法及其装置
CN109696248A (zh) * 2018-11-28 2019-04-30 武汉高德智感科技有限公司 一种人体检验检疫系统温度基于环境温度的自动补偿方法
CN111964786A (zh) * 2020-07-20 2020-11-20 四川虹美智能科技有限公司 温度检测方法及装置
CN111982302A (zh) * 2020-08-24 2020-11-24 广东工业大学 一种带噪声滤波和环境温度补偿的测温方法
US20200378834A1 (en) * 2019-05-30 2020-12-03 Melexis Technologies Nv Temperature measurement apparatus and method of measuring temperature

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101435727A (zh) * 2007-11-12 2009-05-20 深圳迈瑞生物医疗电子股份有限公司 温度预测方法及装置
CN107576421A (zh) * 2017-08-23 2018-01-12 王沛 一种体温测量设备、方法及其装置
CN109696248A (zh) * 2018-11-28 2019-04-30 武汉高德智感科技有限公司 一种人体检验检疫系统温度基于环境温度的自动补偿方法
US20200378834A1 (en) * 2019-05-30 2020-12-03 Melexis Technologies Nv Temperature measurement apparatus and method of measuring temperature
CN111964786A (zh) * 2020-07-20 2020-11-20 四川虹美智能科技有限公司 温度检测方法及装置
CN111982302A (zh) * 2020-08-24 2020-11-24 广东工业大学 一种带噪声滤波和环境温度补偿的测温方法

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115165461A (zh) * 2022-07-01 2022-10-11 佳木斯大学 智能化血浆取样装置及其操作系统
CN115736844A (zh) * 2022-11-16 2023-03-07 吉林省科英医疗激光有限责任公司 一种体表温度实时检测系统和检测方法
CN115736844B (zh) * 2022-11-16 2023-10-24 吉林省科英医疗激光有限责任公司 一种体表温度实时检测系统和检测方法

Also Published As

Publication number Publication date
CN116648184A (zh) 2023-08-25

Similar Documents

Publication Publication Date Title
WO2022120563A1 (zh) 温度预测方法、装置和存储介质
TWI648606B (zh) System and method for frequency compensation of an instant clock system
WO2017113875A1 (zh) 预测温度的方法及其系统
CN109060899B (zh) 电化学传感器测量结果的补偿方法、装置和设备
CN110888065B (zh) 电池包荷电状态修正方法和装置
JP2016519605A (ja) センサ較正方法および装置
US10914643B2 (en) System and method for modeling and correcting frequency of quartz crystal oscillator
CN108345953A (zh) 温度预测方法及装置
JP2014149252A (ja) 温度計の校正データの生成方法、校正データを格納した記憶装置、及びこの方法を採用した温度計
CN109580549B (zh) 物质含量的计算、定标方法及装置
US20230395411A1 (en) Data collection system, data collection apparatus, data collection method, and data collection program
CN110646134B (zh) 一种气压传感器的校准方法和校准装置
CN113419020A (zh) 糖化血红蛋白重叠峰识别方法、装置、系统、设备及介质
US20150160274A1 (en) Method and apparatus for power estimation
CN114158791A (zh) 产品测温方法及装置
CN109642827B (zh) 温度推算系统、温度推算方法及记录有温度推算程序的记录媒体
CN115712316A (zh) 一种温控器的温度补偿方法及装置
JP2010113527A (ja) バグ摘出予測システム
CN109286461B (zh) 用于匹配在检测传感器数据时的时间戳的方法
JP6568486B2 (ja) 温度変化予測解析装置および温度変化予測解析方法
US20140076032A1 (en) Waterproof testing system and method thereof
CN114111695B (zh) 一种提高高温应变测量精度的修正方法
TW201131413A (en) Estimating polynomial generating device, estimating device, estimating polynomial generating method and estimating method
JP2020003282A5 (zh)
US11995617B2 (en) Maintenance method for zirconia-type oxygen analyzer, maintenance system, and zirconia-type oxygen analyzer

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20964509

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202080107741.3

Country of ref document: CN

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20964509

Country of ref document: EP

Kind code of ref document: A1