Temperature compensation method, device, equipment, medium and intelligent panel

Abstract

The present invention discloses a temperature compensation method, device, equipment, medium and intelligent panel. The temperature compensation method includes: reading a temperature sensor reading and a temperature value of a first heat source element; using the temperature sensor reading and the temperature value of the first heat source element as inputs of a prediction model to output a temperature prediction value at the current moment; assigning a weight ratio between the output temperature value at the previous moment and the temperature prediction value at the current moment, fitting and outputting the output temperature value at the current moment, wherein the state of a second heat source element is monitored and the weight ratio between the output temperature value at the previous moment and the temperature prediction value at the current moment is adjusted according to a change in the state of the second heat source element. The present application only uses the temperature sensor reading and the CPU temperature sensor reading as variables, uses a BP neural network for fitting, and then uses a smoothing technique to ensure that the device does not undergo abrupt changes in actual experience and improves prediction accuracy.

Description

Technical Field

[0001] The present invention relates to temperature control technology, and in particular to a temperature compensation method, device, equipment, medium and intelligent panel, so as to reduce interference when the installation environment of the temperature sensor is susceptible to the calorific value interference of the heat source element, improve the temperature monitoring accuracy and reduce oscillation. Background Art

[0002] Temperature monitoring is widely used in life. Most of them use temperature sensors installed at the measured points to obtain temperature data in real time so that equipment or people can know the temperature information and use it as a reference for executing the next instruction or operation. It plays an important role in environmental monitoring, equipment operation, and monitoring.

[0003] Smart homes, for example, are a typical application scenario for temperature monitoring. Driven by the rapid development of IoT technology, smart homes are transforming people's lives, and sensor devices, as data collection nodes, are an essential component of smart home connectivity. Some smart panels rely heavily on sensor readings for temperature display. However, since temperature sensors are often installed internally, the heat generated by the panel's internal components directly affects the sensor reading, resulting in an inability to directly reflect the actual ambient temperature. This makes accurate ambient temperature display a technical challenge for these panel-like devices.

[0004] To solve this problem, from a hardware perspective, the relative position of the sensor can be adjusted to reduce the impact of the heating components. However, this is often limited by the device size and installation environment, and the improvement effect is limited. Therefore, this application intends to find the influence of each internal heating component on the temperature sensor and perform fitting regression. Summary of the Invention

[0005] The present invention aims to address one of the technical problems in the aforementioned technologies to a certain extent. To this end, in a first aspect, the present invention proposes a temperature compensation method that utilizes the correlation between the current temperature value and the temperature at the previous moment to fit and predict the current temperature. Furthermore, when the input variables available to the prediction model are extremely limited, the fitting weights are flexibly adjusted by monitoring the status of other heat sources to eliminate phenomena such as oscillations caused by insufficient variables.

[0006] Specifically, the temperature compensation method includes the following steps:

[0007] reading a temperature sensor reading and a temperature value of a first heat source element, wherein the temperature sensor is configured to measure an ambient temperature, and the first heat source element and the temperature sensor are in the same installation environment;

[0008] The prediction model uses the temperature sensor reading and the temperature value of the first heat source element as inputs and outputs the temperature prediction value at the current moment;

[0009] Assign a weight ratio between the output temperature value at the previous moment and the temperature prediction value at the current moment, fit and output the output temperature value at the current moment, wherein the state of the second heat source element is monitored, and the weight ratio between the output temperature value at the previous moment and the temperature prediction value at the current moment is adjusted according to the state change of the second heat source element.

[0010] In a further embodiment, if the state of the second heat source element at the current moment and the previous moment is maintained, the weight ratio is a fixed weight ratio; if the state of the second heat source element at the current moment and the previous moment changes, then during the transition time, as the number of moments maintained after the state of the second heat source element is switched increases, the fitting weight of the output temperature value at the previous moment is reduced, and the fitting weight of the temperature prediction value at the current moment is increased; when the number of moments maintained after the state of the second heat source element is switched is greater than the number of transition moments, the number of moments maintained after the state of the second heat source element is switched is cleared to zero, and the output temperature value at the current moment is made equal to the temperature prediction value at the current moment.

[0011] In a further embodiment, a counter C is used to record the number of moments maintained after the state of the second heat source element is switched, and the initial state is set to 0; and the output temperature value at the first moment is directly equal to the temperature sensor reading; if the state of the second heat source element at time i-1 is the same as that at time i and C=0, then Y[i]=a*Y[i-1]+(1-a)*S[i], where a is a weight parameter, Y[i-1] is the output temperature value at the previous moment, and S[i] is the temperature prediction value at the current moment; if the state of the second heat source element at time i-1 is different from that at time i, the counter C is set to 1 and starts counting, if C≤t, then Y[i]=(1-(1-a) / t*C)*Y[i-1]+((1-a) / t*C)*S[i], and the counter is increased by 1; if C>t, then Y[i]=S[i], and the counter C is reset to 0; where t is the number of transition moments.

[0012] In a further embodiment, the weight parameter a=0.8, and the number of transition moments t=50.

[0013] In a further embodiment, humidity compensation is also included; the humidity sensor reading at startup is read as the initial value; a mapping relationship between temperature change and humidity change is established to calculate the humidity change value at the corresponding moment based on the temperature change value at any moment, and output the humidity value.

[0014] In a further embodiment, the second heat source element is a screen, and when the screen switches between bright and dark, it is determined that the state of the second heat source element has changed; otherwise, it is determined that the state of the second heat source element has remained unchanged.

[0015] Based on the temperature compensation method proposed in the present invention, the output value of the prediction model can be corrected. When the variables that can be obtained by the prediction model are extremely limited, the accuracy of the predicted value of the final output prediction value can be improved, and the oscillation phenomenon of the final output prediction value can be reduced to avoid causing a sense of abruptness to the user.

[0016] To achieve the above-mentioned purpose, the second aspect of the present invention is to propose an intelligent panel, which includes: a temperature sensor, which is configured to collect ambient temperature; a first heat source element and a second heat source element, which are in the same installation environment as the temperature sensor, the first heat source element has a readable temperature value, and the second heat source element has an identifiable state change; the first heat source element includes a processor; a memory, which stores a computer program, and the computer program is loaded and executed by the processor to implement the method as described above.

[0017] The proposed intelligent panel, when applied to smart home scenarios, can perform regression fitting by identifying the patterns of influence exerted by internal heat sources on the temperature sensor, even when the temperature sensor is inevitably interfered with by other heat source components. Furthermore, given the extremely limited variables available in the prediction model, this can improve the accuracy of the final output prediction value and reduce fluctuations in the final output prediction value, thus avoiding sensory abruptness for the user.

[0018] To achieve the above-mentioned purpose, the third aspect of the present invention is to propose a temperature compensation device, comprising: a temperature reading module, used to read the temperature sensor reading and the temperature value of the first heat source element; a prediction model, used to predict the temperature prediction value at the current moment based on the read data of the temperature reading module; a monitoring module, used to monitor the state change of the second heat source element; a compensation module, used to read the output temperature value at the previous moment and the temperature prediction value at the current moment and assign a weight ratio to fit and output the output temperature value at the current moment, wherein the weight ratio of the output temperature value at the previous moment and the temperature prediction value at the current moment is adjusted according to the state change of the second heat source element.

[0019] The temperature compensation device proposed in this invention can be installed on equipment that requires temperature monitoring. Even in environments where temperature sensors are restricted and inevitably affected by heat source components, the device can output a relatively accurate predicted temperature through temperature compensation. Furthermore, the compensation process requires fewer variables and effectively avoids the problem of temperature fluctuations that can result from fewer dependent variables, thereby improving monitoring effectiveness.

[0020] To achieve the above object, the fourth aspect of the present invention is to provide a computer device, the computer device comprising a processor and a memory, the memory storing a computer program, the computer program being loaded and executed by the processor to implement the method as described above

[0021] To achieve the above-mentioned object, a fifth aspect of the present invention is to propose a computer-readable storage medium, wherein the computer-readable storage medium includes one or more program instructions, and when the one or more program instructions are executed, the method described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a prediction example where the neural network prediction model only considers the CPU temperature factor;

[0023] Figure 2 Schematic diagram of the temperature compensation method of the present invention;

[0024] Figure 3 This is a schematic diagram of the BP neural network prediction model of this application;

[0025] Figure 4 This is a specific prediction example of the present invention;

[0026] Figure 5 This is a schematic diagram of the smart panel of the present invention;

[0027] Figure 6 Schematic diagram of the temperature compensation device of the present invention;

[0028] Figure 7 Schematic diagram of computer equipment of the present invention. DETAILED DESCRIPTION

[0029] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0030] This application aims to predict and output the actual temperature by finding the influence of internal heat source elements on the temperature sensor.

[0031] It should be understood that the heat source element referred to in this application refers to a component that generates heat during operation and is located in the same installation environment as the temperature sensor. This heat generation affects the accuracy of the temperature sensor's readings to some extent. The term "same installation environment" does not necessarily mean that the heat source element and the temperature sensor must be located in the same cavity; they can be located in adjacent cavities where heat conduction occurs. As long as the heat from the heat source element can be transferred to the temperature sensor to a certain extent and sensed, thereby affecting the accuracy of the temperature sensor's readings, it can be considered to be in the same installation environment as the temperature sensor.

[0032] This application uses a neural network to identify the influence of heat source elements on temperature sensors. Specifically, this application is implemented using a BP neural network prediction model. BP neural networks do have powerful fitting capabilities. An ideal approach is to first build a neural network prediction model, then extract various variables that can affect the temperature sensor, the temperature sensor's value, and the corresponding temperature's true label to obtain a training set. This neural network prediction model is then trained to obtain a predicted value for the true temperature, thereby at least partially eliminating the temperature sensor's error caused by heat source interference.

[0033] However, in reality, there may be several heat source elements that can affect the temperature sensor, and the main influencing factor that can actually be extracted may only be the CPU (processor) temperature variable. Then, directly using the CPU temperature and temperature reading for fitting may cause a sudden change during the device display process, making the user experience very abrupt.

[0034] The reason is that in the process of temperature fitting, the variables considered are often not comprehensive. They simply capture the main influencing factors such as CPU temperature, while ignoring other minor factors. This may actually cause two real results in one state in the data. However, since the main factors are extracted, this situation does not occur in most cases. It will only cause fluctuations in the fitted algorithm and cause rapid temperature changes. The fitting example can be seen in Figure 1 Among them, the figure records a total of 8355 time nodes, including operations such as switching between bright and dark screens, which are recorded once every minute. The light gray is the predicted temperature value, and the dark black is the actual temperature value. It can be found that the dark black curve is almost covered by the oscillating light gray curve. If the prediction is made directly in this way, the entire device display will fluctuate very abruptly. Specifically, among the 8355 time nodes, only 7941 time points have an error controlled within 2 degrees, and the maximum oscillation error reaches 7 degrees. Only 6457 time points are within 1 degree.

[0035] Therefore, after the prediction model finds the influence law of the heat source element on the temperature sensor, the present application further corrects the predicted value of the prediction model to eliminate the oscillation value.

[0036] Specifically, the first aspect of the present invention proposes a temperature compensation method, which can eliminate certain abnormal mutation points and prevent the temperature from changing rapidly and strangely. Tests have shown that it can improve a certain degree of accuracy.

[0037] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. Instead, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0038] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0039] First, obtain the training set data required for neural network training.

[0040] Two devices were placed in a variable temperature box. The box temperature and device states, such as turning on the screen and playing music, were controlled. The CPU temperature sensor readings, temperature sensor readings, and the box temperature were recorded for each temperature range and device state. The data from one device was used as the training set. The input variables for the training data were the CPU temperature sensor reading and the temperature sensor temperature, and the corresponding true label was the variable temperature box temperature reading. The test set consisted of the data from the other device.

[0041] Secondly, build a BP neural network prediction model.

[0042] Build a BP neural network prediction model, set the input layer to two neurons, set two hidden layers, and each hidden layer has 5 neurons. Use sigmoid activation function between layers to increase nonlinear fitting ability. The output layer is one neuron and does not use activation function. In this way, since no normalization preprocessing is used, there is no need to use activation function to constrain the output range. Its structure is as follows Figure 2 shown.

[0043] Next, train the prediction model. Use the L1 loss function, set a specific training cycle, select the Adam gradient descent method, set an initial step size, and repeatedly reduce the step size after several training cycles to prevent the model from failing to converge. After training, a neural network prediction model is generated. Simply inputting the CPU temperature sensor reading and the temperature sensor reading as parameters, the prediction model can generate a preliminary predicted ambient temperature value.

[0044] In one feasible training method, the number of training epochs is set to 1000, the initial step size is set to 0.01, and it is adjusted to 0.001 after 500 epochs and to 0.0001 after 800 epochs.

[0045] Finally, the temperature prediction value of the prediction model is compensated and output. Considering that the output temperature value at the current moment should be related to the output temperature value at the previous moment, and it is observed that Figure 1 When the output temperature value suddenly changes in a wide range, it is usually when the state of the second heat source element changes (specifically Figure 1 In the example, this corresponds to the moment when the screen switches between bright and dark. Therefore, we consider using the idea of ​​a smoothing function to eliminate the impact of oscillation caused by insufficient variables;

[0046] Specifically:

[0047] reading a temperature sensor reading and a temperature value of a first heat source element, wherein the temperature sensor is configured to measure an ambient temperature, and the first heat source element and the temperature sensor are in the same installation environment;

[0048] The prediction model uses the temperature sensor reading and the temperature value of the first heat source element as inputs and outputs the temperature prediction value at the current moment;

[0049] Assign a weight ratio between the output temperature value at the previous moment and the temperature prediction value at the current moment, fit and output the output temperature value at the current moment, wherein the state of the second heat source element is monitored, and the weight ratio between the output temperature value at the previous moment and the temperature prediction value at the current moment is adjusted according to the state change of the second heat source element.

[0050] It should be understood that, in one example of this embodiment, the first heat source element is a CPU element, but it may also be another element that affects the accuracy of the temperature sensor reading and can implement its own temperature monitoring. The second heat source element is an element that also affects the accuracy of the temperature sensor reading, but its impact on the temperature sensor reading is less than that of the first heat source element. It does not have the ability to implement its own temperature monitoring, but its state changes can be monitored.

[0051] It should be understood that a monitorable state change refers to a state change of a component that can be identified and acquired by a processor via a certain signal method. This may include the component being powered on or off, switching between high and low power consumption, etc. For example, if the component is a display screen, the monitorable state change may be the screen being bright or dark.

[0052] For different state changes, in further implementations:

[0053] If the state of the second heat source element at the current moment and the previous moment remains the same, the weight ratio is a fixed weight ratio;

[0054] If the state of the second heat source element at the current moment and the previous moment changes, the predicted mutation amplitude will be larger at this time. Therefore, a transition time is set to filter its mutation value. During the transition time, as the number of maintenance moments after the state of the second heat source element switches increases, the fitting weight of the output temperature value at the previous moment is slowly reduced, and the fitting weight of the temperature prediction value at the current moment is correspondingly increased, wherein the sum of the weight coefficients remains 1;

[0055] When the number of moments maintained after the state of the second heat source element is switched is greater than the number of transition moments, the number of moments maintained after the state of the second heat source element is switched is cleared to zero, and the output temperature value at the current moment is made directly equal to the temperature prediction value at the current moment, so as to prevent the temperature from having too large an error during the transition process, resulting in inaccurate output temperature (at this time, clearing the number of moments maintained after the state is switched to zero serves as a reset).

[0056] In a more specific embodiment, a counter C is used to record the number of moments maintained after the state of the second heat source element is switched, and the initial state is 0, and the output temperature at the first moment is set to be the temperature directly read by the device. Then, if the state of the second heat source element at time i-1 is the same as that at time i and C=0, then Y[i]=a*Y[i-1]+(1-a)*S[i], where a is a weight parameter, Y[i-1] is the output temperature value at the previous moment, and S[i] is the temperature prediction value at the current moment. If the state of the second heat source element at time i-1 is different from that at time i, the counter C is set to 1 and starts counting. If C≤t, then Y[i]=(1-(1-a) / t*C)*Y[i-1]+((1-a) / t*C)*S[i], and the counter is incremented by 1. If C > t, then the counter C is reset to 0, the fitting weight of the previous temperature output value Y[i-1] decreases to 0, and the fitting weight of the current temperature prediction value S[i] increases to 1. That is, Y[i] = S[i], and the predicted temperature value is output as the actual result. In each formula, t is the number of transition moments.

[0057] More specifically, at this time, the second heat source element is the screen. When the screen switches between bright and dark, it is determined that the state of the second heat source element has changed; otherwise, it is determined that the state of the second heat source element has been maintained.

[0058] At the initial moment of device startup, it is considered that the temperature sensor reading is relatively accurate. At this time, the temperature sensor reading is output as the output temperature value at the current moment.

[0059] Please refer to Figure 3As shown in the figure, it is a specific example result with a value of a = 0.8 and t = 50. The light gray is still the final output temperature value, and the dark black is the actual ambient temperature. It can be seen that the oscillation of the entire function graph has been eliminated a lot. After testing, 8355 of the 8355 time points have errors within 2 degrees, and 7535 are within 1 degree, and no huge mutations are found. Figure 1 The results shown (only 7941 time points had errors within 2 degrees, and the maximum oscillation error reached 7 degrees, and 6457 time points were within 1 degree) achieved significant oscillation filtering results and improved the prediction accuracy to a certain extent.

[0060] Furthermore, based on the temperature compensation method of this application, humidity compensation can also be implemented. Similarly, assuming that the humidity sensor reading is more accurate when the device is powered on, the humidity sensor reading at power-on is used as the initial value. In the subsequent humidity change prediction process, a mapping relationship between temperature change and humidity change is established using historical data. Based on the temperature change value at any given moment, the humidity change value at the corresponding moment is calculated and output as the humidity value.

[0061] In a specific embodiment, the humidity value is fitted according to the mapping relationship that a temperature change of 1° corresponds to a humidity change of 5°.

[0062] Based on the above method, this application only uses temperature sensor readings and CPU temperature sensor readings as variables, uses BP neural network for fitting, and then uses smoothing technology to ensure that the device will not change abruptly when operating operations such as turning on and off the screen, playing music, etc. in actual experience, and controls the temperature error within 1 degree in most cases, and within 2 degrees in a few cases, achieving good prediction results.

[0063] Please refer to Figure 4 As shown, the second aspect of the present invention is to provide an intelligent panel, which includes a temperature sensor 110 , a processor 130 , a screen 140 and a memory 150 .

[0064] The temperature sensor 110 is configured to collect ambient temperature. The processor 130 (a first heat source element) and the screen 140 (a second heat source element) are installed in the same environment as the temperature sensor 110. The processor 130 has a readable temperature value, and the screen 140 has a state change that can be recognized by the processor 130. The memory 150 stores a computer program that is loaded and executed by the processor 130 to implement the temperature compensation method described above.

[0065] The intelligent panel may further include a humidity sensor 120. It should be understood that in this embodiment, the temperature sensor 100 and the humidity sensor 120 may be of an integrated or separate design, and this application does not specifically limit this. When the intelligent panel includes the humidity sensor 120, a corresponding computer program is stored in the memory 150. When the computer program is loaded by the processor, it also executes the aforementioned humidity compensation method to achieve humidity prediction.

[0066] The proposed intelligent panel, when applied to smart home scenarios, can identify the influence of internal heat sources on the temperature sensor, allowing for regression analysis when the temperature sensor is inevitably interfered with by other heat sources. Furthermore, given the extremely limited variables available in the prediction model, it can improve the accuracy of the final output prediction value and reduce fluctuations in the final output prediction value, thus avoiding sensory abruptness for the user.

[0067] The third aspect of the present invention is to propose a temperature compensation device, which includes a temperature reading module 210, a prediction model 220, a monitoring module 230 and a compensation module 240. The temperature reading module 210 is used to read the temperature sensor reading and the temperature value of the first heat source element. The prediction model 220 predicts the temperature prediction value at the current moment based on the reading data of the temperature reading module 210, and the prediction model 220 is obtained by the aforementioned model construction and training method. The monitoring module 230 is used to monitor the state change of the second heat source element, such as obtaining the brightness and darkness signal of the display screen, and calculating the number of moments maintained after the state of the second heat source element is switched. The compensation module 240 is used to read the output temperature value at the previous moment and the temperature prediction value at the current moment and assign a weight ratio to fit and output the output temperature value at the current moment, wherein the weight ratio of the output temperature value at the previous moment and the temperature prediction value at the current moment is adjusted according to the state change of the second heat source element.

[0068] The temperature compensation device proposed in this invention can be installed on equipment that requires temperature monitoring. Even in environments where temperature sensors are restricted and inevitably affected by heat source components, the device can output a relatively accurate predicted temperature through temperature compensation. Furthermore, the compensation process requires fewer variables and effectively avoids the problem of temperature fluctuations that can result from fewer dependent variables, thereby improving monitoring effectiveness.

[0069] The temperature compensation device of the present invention may further include a humidity reading module 250 , which reads humidity data, so that the compensation module 240 can adjust the predicted humidity value according to the temperature change value to achieve humidity control.

[0070] The specific details of the implementation process of the functions and effects of each module in the above-mentioned device can be found in the implementation process of the corresponding steps in the above-mentioned method, which will not be repeated here.

[0071] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed over multiple modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution. Those of ordinary skill in the art can understand and implement it without paying any creative work.

[0072] Correspondingly, the fourth aspect of the present invention further proposes a computer device, which includes a processor 310 and a memory 320. The memory 320 stores a computer program, and the computer program is loaded and executed by the processor 310 to implement the method as described above.

[0073] Correspondingly, the fifth aspect of the present invention further proposes a computer-readable storage medium, which includes one or more program instructions. When the one or more program instructions are executed, the method described above is implemented.

[0074] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code. Computer-usable storage media include permanent and non-permanent, removable and non-removable media, and may be implemented using any method or technology for information storage. Information may be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage, or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0075] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 produce 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 flowcharts and / or block diagrams. 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.

[0076] These computer program instructions may also be stored in a computer readable memory that can direct 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 an article of manufacture comprising 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.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0078] It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claim. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third etc. does not indicate any order. These words may be interpreted as names.

[0079] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0080] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

[0081] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0082] In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," "connect," "fixed," etc. should be understood broadly. For example, they may refer to fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0083] In the present invention, unless otherwise expressly specified or limited, when a first feature is "above" or "below" a second feature, it may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediary. Furthermore, when a first feature is "above," "above," or "above" a second feature, it may mean that the first feature is directly above or diagonally above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is "below," "below," or "below" a second feature, it may mean that the first feature is directly below or diagonally below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0084] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms should not be understood as necessarily referring to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0085] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A temperature compensation method, characterized in that: include: reading a temperature sensor reading and a temperature value of a first heat source element, wherein the temperature sensor is configured to measure an ambient temperature, and the first heat source element and the temperature sensor are in the same installation environment; The prediction model uses the temperature sensor reading and the temperature value of the first heat source element as inputs and outputs the temperature prediction value at the current moment; Assign a weight ratio between the output temperature value at the previous moment and the temperature prediction value at the current moment, fit and output the output temperature value at the current moment, wherein the state of the second heat source element is monitored, and the number of times the state of the second heat source element is maintained after switching is recorded by a counter C, with the initial state set to 0; and the output temperature value at the first moment is directly equal to the temperature sensor reading; If the state of the second heat source element at time i-1 is the same as that at time i and C=0, then Y[i]=a*Y[i-1]+(1-a)*S[i], where a is the weight parameter, Y[i-1] is the output temperature value at the previous moment, and S[i] is the temperature prediction value at the current moment; if the state of the second heat source element at time i-1 is different from that at time i, the counter C is set to 1 and starts counting. If C≤t, then Y[i]=(1-(1-a) / t*C)*Y[i-1]+((1-a) / t*C)*S[i], and the counter is increased by 1; if C>t, then Y[i]=S[i], and the counter C is reset to 0; where t is the number of transition moments.

2. The temperature compensation method according to claim 1, wherein: The weight parameter a=0.8, and the number of transition moments t=50.

3. The temperature compensation method according to claim 1, wherein: Also includes humidity compensation; Read the humidity sensor reading at startup as the initial value A mapping relationship between temperature change and humidity change is established to calculate the humidity change value at the corresponding moment based on the temperature change value at any moment and output the humidity value.

4. The temperature compensation method according to claim 1, wherein: The second heat source element is the screen. When the screen switches between bright and dark, it is determined that the state of the second heat source element has changed; otherwise, it is determined that the state of the second heat source element has remained unchanged.

5. Intelligent panel, characterized by: include: a temperature sensor configured to collect ambient temperature; a first heat source element and a second heat source element, wherein the first heat source element and the second heat source element are in the same installation environment as the temperature sensor, the first heat source element has a readable temperature value, and the second heat source element has a recognizable state change; the first heat source element includes a processor; A memory storing a computer program, wherein the computer program is loaded and executed by the processor to implement the temperature compensation method according to any one of claims 1 to 4.

6. A temperature compensation device, characterized in that: include: A temperature reading module is used to read the temperature sensor reading and the temperature value of the first heat source element; A prediction model, which predicts a temperature prediction value at a current moment based on the data read by the temperature reading module; A monitoring module, configured to monitor a state change of the second heat source element; A compensation module is used to read the output temperature value at the previous moment and the temperature prediction value at the current moment and assign a weight ratio to fit and output the output temperature value at the current moment, wherein the temperature compensation method as described in any one of claims 1 to 4 is executed according to the state change of the second heat source element.

7. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement the temperature compensation method according to any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes one or more program instructions, and when the one or more program instructions are executed, the temperature compensation method according to any one of claims 1 to 4 is implemented.

Images