A temperature control method and device, electronic equipment, and storage medium

Abstract

The embodiment of the application discloses a temperature control method and device, relates to the computer technical field, and can intelligently control the temperature of a target region and effectively improves the temperature control effect. The method comprises the following steps: acquiring real-time temperature values of a target region in sequence at intervals of a preset time length to obtain a real-time temperature sequence; determining an average temperature value corresponding to a current moment according to a real-time temperature value of the current moment and at least part of real-time temperature values corresponding to previous moments in the real-time temperature sequence; and determining a required cooling state at the current moment based on a first model and a temperature feature vector, wherein the first model is a model pre-trained based on artificial intelligence technology, and the temperature feature vector comprises a real-time temperature value corresponding to the current moment, a real-time temperature change of the real-time temperature value relative to a real-time temperature value of a previous moment, an average temperature value corresponding to the current moment, and an average temperature change of the average temperature value relative to an average temperature value of the previous moment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer technology, and in particular to a temperature control method and device, electronic equipment and storage medium. BACKGROUND

[0002] When an electronic device is running, various electronic components inside the electronic device will generate energy dissipation, and a part of the electric energy will be converted into heat energy and released, thereby increasing the temperature of the electronic device. Excessive temperature not only affects the performance of the electronic device, but also easily causes device damage or fire hazards. Therefore, the temperature of the electronic device needs to be monitored and controlled, for example, appropriate cooling measures can be taken when necessary.

[0003] In related technologies, the current temperature and temperature change of the electronic device are compared with preset threshold values, and appropriate temperature control measures are taken when exceeding a threshold value. However, this method of controlling temperature is relatively simple and rough, and the temperature control measures taken are often not the most appropriate. For example, when the temperature fluctuates greatly for a short time, it may be unnecessary to frequently turn on and off the cooling device.

[0004] In addition, some temperature control algorithms also introduce the classic PID (proportional integral derivative) control algorithm in the automatic control field to achieve the purpose of temperature control. However, since the PID control algorithm is introduced, the PID algorithm also inherits the problem of adjusting and determining the PID coefficients Kp, Ki, and Kd, which is very difficult, and therefore it is also difficult to achieve good temperature control effect. SUMMARY

[0005] Therefore, the embodiments of the present application provide a temperature control method and device, electronic equipment and storage medium, which can effectively improve the temperature control effect.

[0006] In a first aspect, the embodiments of the present application provide a temperature control method, comprising:

[0007] obtaining real-time temperature values of a target region in a preset time interval to obtain a real-time temperature sequence;

[0008] determining an average temperature value corresponding to a current time according to the real-time temperature value at the current time and at least part of the real-time temperature values corresponding to previous times in the real-time temperature sequence;

[0009] determine a current required cooling state based on the first model and a temperature feature vector, wherein the first model is a model pre-trained based on artificial intelligence technology, and the temperature feature vector comprises a real-time temperature value corresponding to the current moment, a real-time temperature change condition of the real-time temperature value relative to a real-time temperature value of a previous moment, an average temperature value corresponding to the current moment, and an average temperature change condition of the average temperature value relative to an average temperature value of the previous moment.

[0010] With reference to the first aspect, in a first implementation form of the first aspect, the determining of the average temperature value corresponding to the current moment according to at least part of the real-time temperature values corresponding to the current moment and the previous moment in the real-time temperature sequence comprises:

[0011] for each latest current moment in the real-time temperature sequence, calculating an exponentially weighted average value corresponding to the latest current moment, and taking the exponentially weighted average value as the average temperature value corresponding to the latest current moment.

[0012] With reference to the first aspect, in a second implementation form of the first aspect, after the determining of the average temperature value corresponding to the current moment according to at least part of the real-time temperature values corresponding to the current moment and the previous moment in the real-time temperature sequence, and before the determining of the current required cooling state based on the first model and the temperature feature vector, the method further comprises:

[0013] determining the real-time temperature change condition according to a difference between the real-time temperature values of the current moment and the previous moment, and determining the average temperature change condition according to a difference between the average temperature values of the current moment and the previous moment;

[0014] constructing the temperature feature vector according to the real-time temperature value corresponding to the current moment, the real-time temperature change condition, the average temperature value corresponding to the current moment, and the average temperature change condition.

[0015] With reference to the first aspect, in a third implementation form of the first aspect, the determining of the current required cooling state based on the first model and the temperature feature vector comprises:

[0016] determining a temperature interval to which the real-time temperature value corresponding to the current moment belongs based on a first rule, to obtain a first interval;

[0017] determining a temperature interval to which the average temperature value corresponding to the current moment belongs based on a second rule, to obtain a second interval;

[0018] determining a temperature change interval to which the real-time temperature change condition belongs based on a third rule, to obtain a third interval;

[0019] According to the fourth rule, a temperature variation interval to which the average temperature variation belongs is determined, and a fourth interval is obtained;

[0020] The first interval, the second interval, the third interval and the fourth interval are input into the first model;

[0021] According to an output of the first model, a current required cooling state is determined.

[0022] With reference to any one of the first to third implementations of the first aspect, in a fourth implementation of the first aspect, before the current required cooling state is determined based on the first model and the temperature feature vector, the method further includes:

[0023] Sample data of temperature control is obtained, the sample data including actually collected temperatures of the target region and corresponding cooling states, and / or virtually constructed temperatures of the target region and corresponding cooling states;

[0024] The sample data is preprocessed to obtain sample feature vectors corresponding to the temperature feature vectors and cooling states corresponding to the sample feature vectors;

[0025] Based on a preset classification algorithm, the sample feature vectors and the corresponding cooling states are used for model training to obtain the first model.

[0026] With reference to the fourth implementation of the first aspect, in a fifth implementation of the first aspect, the preset classification algorithm includes at least one of the following: a decision tree algorithm, a support vector machine algorithm and a random forest algorithm.

[0027] With reference to any one of the first to third implementations of the first aspect, in the fifth implementation of the first aspect, the cooling state includes at least one of the following: a working state of a fan, a working frequency of a processor and an on or off state of a preset circuit module.

[0028] Secondly, an embodiment of the present application provides a temperature control device, which includes:

[0029] A temperature acquisition module is configured to sequentially obtain real-time temperature values of a target region at preset intervals of time length, and obtain a real-time temperature sequence;

[0030] A first determination module is configured to determine an average temperature value corresponding to a current time according to a real-time temperature value at the current time and at least part of real-time temperature values corresponding to previous times in the real-time temperature sequence.

[0031] The second determining module is configured to determine a current required cooling state based on a first model and a temperature feature vector, wherein the first model is a model pre-trained based on an artificial intelligence technology, and the temperature feature vector comprises a real-time temperature value corresponding to the current moment, a real-time temperature change condition of the real-time temperature value relative to a real-time temperature value of a previous moment, an average temperature value corresponding to the current moment, and an average temperature change condition of the average temperature value relative to an average temperature value of the previous moment.

[0032] With reference to the second aspect, in a first implementation of the second aspect, the first determining module is specifically configured to:

[0033] For each latest current moment in a continuation process of the real-time temperature sequence, an exponential weighted average value corresponding to the latest current moment is calculated, and the exponential weighted average value is taken as the average temperature value corresponding to the latest current moment.

[0034] With reference to the second aspect, in a second implementation of the second aspect, the first determining module comprises:

[0035] A first determining unit is configured to determine the real-time temperature change condition according to a difference between the real-time temperature values of the current moment and a previous moment;

[0036] A second determining unit is configured to determine the average temperature change condition according to a difference between the average temperature values of the current moment and the previous moment;

[0037] A constructing unit is configured to construct the temperature feature vector according to the real-time temperature value corresponding to the current moment, the real-time temperature change condition, the average temperature value corresponding to the current moment, and the average temperature change condition.

[0038] With reference to the second aspect, in a third implementation of the second aspect, the second determining module comprises:

[0039] A third determining unit is configured to determine a temperature interval to which the real-time temperature value corresponding to the current moment belongs based on a first rule, to obtain a first interval;

[0040] A fourth determining unit is configured to determine a temperature interval to which the average temperature value corresponding to the current moment belongs based on a second rule, to obtain a second interval;

[0041] A fifth determining unit is configured to determine a temperature change interval to which the real-time temperature change condition belongs based on a third rule, to obtain a third interval;

[0042] A sixth determining unit is configured to determine a temperature change interval to which the average temperature change condition belongs based on a fourth rule, to obtain a fourth interval;

[0043] an input unit configured to input the first interval, the second interval, the third interval, and the fourth interval into the first model;

[0044] a seventh determining unit configured to determine a current required cooling state according to an output of the first model.

[0045] With reference to any one of the first to third implementations of the second aspect, in a fourth implementation of the second aspect, the device further includes:

[0046] a sample obtaining module configured to obtain sample data of temperature control, the sample data including actual collected temperature and corresponding cooling state of the target region, and / or virtually constructed temperature and corresponding cooling state of the target region;

[0047] a preprocessing module configured to pre-process the sample data to obtain a sample feature vector corresponding to the temperature feature vector and a cooling state corresponding to the sample feature vector;

[0048] a training module configured to perform model training based on a preset classification algorithm, using the sample feature vector and the corresponding cooling state, to obtain the first model.

[0049] With reference to the fourth implementation of the second aspect, in a fifth implementation of the second aspect, the preset classification algorithm includes at least one of the following: a decision tree algorithm, a support vector machine algorithm, and a random forest algorithm.

[0050] With reference to any one of the first to third implementations of the second aspect, in the fifth implementation of the second aspect, the cooling state includes at least one of the following: a working state of a fan, a working frequency of a processor, and an on or off state of a preset circuit module.

[0051] In a third aspect, an embodiment of the present application further provides an electronic device, which includes: a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is arranged inside a space enclosed by the housing, the processor and the memory are arranged on the circuit board; the power supply circuit is configured to supply power to each circuit or device of the electronic device; the memory is configured to store executable program codes; and the processor is configured to run a program corresponding to the executable program codes by reading the executable program codes stored in the memory, so as to execute the temperature control method provided by any one of the embodiments of the present application.

[0052] In a fourth aspect, an embodiment of the present application further provides a computer readable storage medium, which stores one or more programs, and the one or more programs are executable by one or more processors to implement the temperature control method provided by any one of the embodiments of the present application.

[0053] The temperature control method and device, the electronic device, and the storage medium provided by the embodiments of the present application can obtain real-time temperature values of a target region in sequence at intervals of a preset time length, obtain a real-time temperature sequence, determine an average temperature value corresponding to a current moment according to a real-time temperature value of the current moment and at least part of real-time temperature values corresponding to previous moments in the real-time temperature sequence, and determine a required cooling state at present based on a first model and a temperature feature vector. Since the temperature feature vector includes a real-time temperature value corresponding to the current moment and a real-time temperature change of the real-time temperature value relative to real-time temperature values of the previous moments, an average temperature value corresponding to the current moment and an average temperature change of the average temperature value relative to average temperature values of the previous moments, compared with the prior art, the temperature control method provided by the embodiments of the present application includes not only real-time temperature and its change, but also average temperature and its change as evaluation factors of the cooling state, so that unnecessary temperature control measures can be effectively reduced or avoided. Meanwhile, since the evaluation factors are more diversified and the combination of different factors is more complex, the first model can well play the advantages of artificial intelligence technology, accurately grasp the influence of subtle differences between different combinations on the cooling state, and thus more accurately predict the required cooling state of the target region, greatly improving the temperature control effect. BRIEF DESCRIPTION OF DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0055] Figure 1 A flow chart of the temperature control method provided by the embodiments of the present application;

[0056] Figure 2 A detailed flow chart of the temperature control method provided by the embodiments of the present application;

[0057] Figure 3 A structural schematic diagram of the temperature control device provided by the embodiments of the present application;

[0058] Figure 4 A structural schematic diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0059] The embodiments of the present application will be described in detail below with reference to the drawings.

[0060] It should be noted that the embodiments described above are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0061] In a first aspect, embodiments of the present application provide a temperature control method, which can intelligently control the temperature of a target region, and effectively improve the temperature control effect.

[0062] As shown in Figure 1 Embodiments of the present application provide a temperature control method, which comprises:

[0063] S11, obtaining the real-time temperature value of the target region in sequence at intervals of a preset time length, to obtain a real-time temperature sequence;

[0064] In embodiments of the present application, the target region can refer to a region that needs to be monitored for temperature, which can include, for example, a specified region inside the case of various electronic devices, a region near the CPU (Central Processing Unit), etc. Optionally, the electronic device can be based on various operating systems, such as the Linux operating system, the Windows operating system, or various single-chip microcomputer systems, etc.

[0065] The real-time temperature value can refer to the instantaneous temperature value corresponding to a certain moment, i.e., the real-time temperature value only indicates the temperature at that moment. In order to achieve better monitoring effect, in embodiments of the present application, the target region can be collected for a longer time and more densely, for example, the real-time temperature value of the target region can be obtained in sequence at intervals of a preset time length. The preset time length can be, for example, 0.5 seconds, 1 second, 5 seconds, 20 seconds, etc., and can be set and adjusted according to the actual application scenario. In this way, a series of real-time temperature values corresponding to each moment can be obtained, thereby forming a real-time temperature sequence.

[0066] S12, determining the average temperature value corresponding to the current moment according to the real-time temperature value of the current moment and at least part of the real-time temperature values corresponding to the previous moments in the real-time temperature sequence;

[0067] In an embodiment of the present application, after obtaining the real-time temperature sequence in step S11, in addition to knowing the real-time temperature value corresponding to each moment, the average temperature value corresponding to the moment can also be determined using part or all of the real-time temperature values of the moment and the previous moments. The most recent moment in the real-time temperature sequence is the current moment. Since the average temperature value can reflect the cumulative effect of temperature over time to some extent, it can evaluate the temperature state of the target region from another angle different from the real-time temperature, and then determine the cooling state required by the target region.

[0068] In a specific implementation, when calculating the average temperature value, the real-time temperature value at the current time is usually required, and the real-time temperature value at the previous time can be selected according to requirements, for example, in one embodiment of the present application, the average temperature value at the current time can be calculated according to the real-time temperature values at the current time and the three most recent times, and in another embodiment of the present application, the average temperature value at the current time can be calculated according to the real-time temperature values at the current time and all previous times.

[0069] Optionally, the average temperature value can be calculated by using various average value calculation methods, and different average value calculation methods can correspond to different average effects. For example, a simple arithmetic average algorithm, a geometric average algorithm, a weighted average algorithm, etc. can be used, and embodiments of the present application are not limited in this regard.

[0070] S13, determining a cooling state required at the current time based on the first model and the temperature feature vector, wherein the first model is a model pre-trained based on artificial intelligence technology, and the temperature feature vector includes a real-time temperature value corresponding to the current time and a real-time temperature change of the real-time temperature value relative to a real-time temperature value at a previous time, and an average temperature value corresponding to the current time and an average temperature change of the average temperature value relative to an average temperature value at the previous time.

[0071] In this step, the cooling state required at the current time can be determined based on the first model and the temperature feature vector. The first model is a model based on artificial intelligence technology, and the temperature feature vector can include a real-time temperature value corresponding to the current time and a real-time temperature change of the real-time temperature value relative to a real-time temperature value at a previous time, and an average temperature value corresponding to the current time and an average temperature change of the average temperature value relative to an average temperature value at the previous time. The cooling state required at the current time can refer to which measures need to be taken to control the temperature of the target region, for example, whether active heat dissipation is required, whether power consumption needs to be reduced, etc.

[0072] Specifically, as described above, in the foregoing step, the real-time temperature value at the current time and the average temperature value at the current time can be obtained according to the real-time temperature sequence. Since the temperature value of the target region is still being collected, with the continuous extension of the real-time temperature sequence, each "current time" will become "previous time" when the next time comes. Based on this, in one embodiment of the present application, the change of the real-time temperature value at the current time relative to the real-time temperature value at the previous time can be obtained according to the real-time temperature values at each time in the real-time temperature sequence, and the change of the average temperature value at the current time relative to the average temperature value at the previous time can be obtained according to the calculated average temperature value at the current time.

[0073] Optionally, in the embodiments of the present application, the real-time temperature change condition can be the real-time temperature change of the current time relative to the previous time, or the real-time temperature change of the current time relative to other times in the previous time. For example, in a real-time temperature sequence, the real-time temperature at time 0 is 25℃, the real-time temperature at time 1 is 28℃, the real-time temperature at time 2 is 35℃, the real-time temperature at time 3 is 40℃, and the real-time temperature at time 4 is 47℃. Assuming that the current time is time 4, the real-time temperature change condition can be the difference between the real-time temperatures at time 4 and time 3 (47℃-40℃), or the difference between the real-time temperatures at time 4 and time 2, or time 1, or time 0. Among them, the difference between the real-time temperatures at time 4 and time 3 is more accurate and the control is more sensitive. Similarly, the change condition of the average temperature value can be the average temperature change of the current time relative to the previous time, or the average temperature change of the current time relative to other times in the previous time, which will not be described here.

[0074] The temperature control method provided by the embodiments of the present application can obtain the real-time temperature values of the target region at intervals of a preset time length, obtain a real-time temperature sequence, determine the average temperature value corresponding to the current time according to the real-time temperature value of the current time and at least part of the real-time temperature values corresponding to the previous time in the real-time temperature sequence, and determine the required cooling state at the current time based on the first model and the temperature feature vector. Since the temperature feature vector includes the real-time temperature value corresponding to the current time and the real-time temperature change of the real-time temperature value relative to the real-time temperature value of the previous time, the average temperature value corresponding to the current time and the average temperature change of the average temperature value relative to the average temperature value of the previous time, compared with the prior art, the evaluation factors of the temperature control method provided by the embodiments of the present application for the cooling state include not only the real-time temperature and its change condition, but also the average temperature and its change condition, so that unnecessary temperature control measures can be effectively reduced or avoided. At the same time, since the evaluation factors are more diverse and the combination of different factors is more complex, the first model can well play the advantages of artificial intelligence technology, accurately grasp the influence of the subtle differences between different combinations on the cooling state, thereby more accurately predicting the required cooling state of the target region, and greatly improving the temperature control effect.

[0075] Specifically, after obtaining the real-time temperature sequence of the target region, the average temperature value at the current time can be determined based on the real-time temperature sequence in step S12. The average temperature value can refer to the average of real-time temperature values at at least two time points. In an embodiment of the present application, the average temperature value corresponding to the current time can be determined according to the real-time temperature value at the current time and at least part of the real-time temperature values corresponding to previous time points in the real-time temperature sequence. The algorithm for calculating the average value is various, and the embodiments of the present application do not limit this. For example, in an embodiment of the present application, the exponentially weighted average value corresponding to each latest current time during the extension of the real-time temperature sequence can be calculated, and the exponentially weighted average value is taken as the average temperature value corresponding to the latest current time. Since the weighting coefficient of each real-time temperature value in the exponentially weighted average value decays exponentially with the time length from the current time, that is, the real-time temperature value corresponding to the time point close to the current time is given a larger weight, and the real-time temperature value corresponding to the time point far from the current time is given a smaller weight, the influence of the real-time temperature value at the recent time on the average temperature value can be highlighted. The calculation method of the exponentially weighted average value can be shown in formula 1.

[0076] v t = β * v t-1 + (1 - β) * θ t Formula (1)

[0077] wherein v t represents the exponentially weighted average temperature at the current time, β represents the speed of the weighting decline, θ t represents the real-time temperature at the current time, and it can be deduced from the formula that the real-time temperature close to the current time has a greater influence on the average temperature at the current time.

[0078] After determining the average temperature value corresponding to the current time, in order to determine the required cooling state in the subsequent steps by using the temperature feature vector, in an embodiment of the present application, the temperature feature vector can be constructed first. For example, in an implementation, the construction of the temperature feature vector can specifically include: determining the real-time temperature change according to the difference between the real-time temperature values at the current time and the previous time, determining the average temperature change according to the difference between the average temperature values at the current time and the previous time; and constructing the temperature feature vector according to the real-time temperature value at the current time, the real-time temperature change, the average temperature value at the current time, and the average temperature change.

[0079] For example, the preset time length can be 1 second, a real-time temperature value of the target region is obtained every 1 second, a series of real-time temperature values with an interval of 1 second can be obtained, for example, 5 real-time temperature values a, b, c, d and e within 5 seconds are obtained; according to the 5-second real-time temperature sequence, the current time is the 5th second, the corresponding real-time temperature value is e, the previous 4 real-time temperature values corresponding to the 4th second are a, b, c and d, and the average temperature value x5 corresponding to the 5th second can be calculated by using a preset algorithm (for example, a simple arithmetic mean algorithm), that is, x5=(a+b+c+d+e) / 5, the average temperature value x4 corresponding to the 4th second is x4=(a+b+c+d) / 4, and the real-time temperature change between the current time (that is, the 5th second) and the previous time (that is, the 4th second) is (e-d), and the average temperature change between the current time (that is, the 5th second) and the previous time (that is, the 4th second) is (x5-x4). Based on this, the temperature feature vector corresponding to the current time (that is, the 5th second) is e, (e-d), x5, (x5-x4).

[0080] In the above embodiment, each feature in the temperature feature vector is a specific temperature value or a temperature difference value, but the embodiment of the present application is not limited thereto. In other embodiments of the present application, various temperature values or temperature difference values can be discretized, that is, various temperature values or temperature difference values are attributed to corresponding temperature intervals, and the current required cooling state is determined according to the temperature interval corresponding to each feature in the temperature feature vector. Since the temperature feature is discretized, the temperature control will focus more on distinguishing the differences between the temperature intervals and weaken the differences between different temperatures in the temperature intervals, so the calculation amount of the temperature control algorithm will be greatly reduced, and the temperature control efficiency will be effectively improved.

[0081] In an embodiment, the step S13 of determining the current required cooling state based on the first model and the temperature feature vector can include: determining a temperature interval to which the real-time temperature value corresponding to the current time belongs based on a first rule to obtain a first interval; determining a temperature interval to which the average temperature value corresponding to the current time belongs based on a second rule to obtain a second interval; determining a temperature change interval to which the real-time temperature change belongs based on a third rule to obtain a third interval; determining a temperature change interval to which the average temperature change belongs based on a fourth rule to obtain a fourth interval; inputting the first interval, the second interval, the third interval and the fourth interval into the first model; and determining the current required cooling state according to the output of the first model.

[0082] The first interval can refer to any one of a series of temperature intervals divided according to the real-time temperature value, wherein each temperature interval can represent a temperature level, and the specific interval division strategy is the first rule. For example, less than or equal to 40 degrees can be determined as normal temperature, 41-50 degrees as high temperature, 51-65 degrees as excessive temperature, and more than 65 degrees as extremely high temperature.

[0083] The second interval can refer to any one of a series of temperature intervals divided according to the average temperature value, wherein each temperature interval can represent a temperature level, and the specific interval division strategy is the second rule. For example, less than or equal to 40 degrees can be determined as normal temperature, 41-50 degrees as high temperature, 51-65 degrees as excessive temperature, and more than 65 degrees as extremely high temperature.

[0084] The third interval can refer to any one of a series of temperature intervals divided according to the real-time temperature change, wherein each temperature interval can represent a temperature change level, and the specific interval division strategy is the third rule. For example, less than or equal to 0.2 degrees can be determined as instantaneous temperature stability, 0.2-0.5 degrees as large instantaneous temperature rise, 0.5-1 degree as excessive instantaneous temperature rise, and more than 1 degree as extremely large instantaneous temperature rise.

[0085] The fourth interval can refer to any one of a series of temperature intervals divided according to the average temperature change, wherein each temperature interval can represent a temperature change level, and the specific interval division strategy is the fourth rule. For example, less than or equal to 0.1 degree can be determined as average temperature stability, 0.1-0.3 degree as large average temperature rise, 0.3-0.5 degree as excessive average temperature rise, and more than 0.5 degree as extremely large average temperature rise.

[0086] Optionally, the first rule and the second rule can be the same or different, the third rule and the fourth rule can be the same or different, and the number of specific intervals in each rule can be set and adjusted as needed. Considering that the change speed and change amplitude of the instantaneous temperature are generally larger than those of the average temperature, in some embodiments of the present application, the temperature change amplitude set by the fourth rule can be smaller than that set by the third rule.

[0087] After obtaining the first interval, the second interval, the third interval, and the fourth interval, the first interval, the second interval, the third interval, and the fourth interval can be input into the first model; according to the output of the first model, the current required cooling state is determined. The cooling state can include one or more of the following: the working state of the fan, the working frequency of the processor, and the opening or closing state of the preset circuit module.

[0088] For example, in an embodiment of the present application, the current temperature of a certain CPU currently detected by a sensor is 85 degrees Celsius. The previous real-time temperature of the CPU is 83 degrees Celsius, and the instantaneous temperature difference obtained by subtracting the current temperature from the previous temperature is +2 degrees, which belongs to rapid rise. The exponentially weighted average temperature calculated from the current real-time temperature is 79 degrees, which is in a medium-speed rising trend compared with the previous exponentially weighted average temperature of 78.5 degrees. The above features are input into the first model, and the cooling state obtained by the first model is that cooling is needed, and the cooling state can be notified to the corresponding device for processing, such as fan opening, related CPU frequency reduction, etc.

[0089] In an embodiment of the present application, the first model is a model trained based on artificial intelligence technology. In order to obtain the first model, in an embodiment of the present application, before step S13 determines the cooling state required by the current temperature feature vector based on the first model, the temperature control method provided by the embodiment of the present application can further include:

[0090] Obtaining sample data of temperature control, the sample data including actually collected temperature of the target area and corresponding cooling state, and / or virtually constructed temperature of the target area and corresponding cooling state;

[0091] Preprocessing the sample data to obtain a sample feature vector corresponding to the temperature feature vector and a cooling state corresponding to the sample feature vector;

[0092] Based on a preset classification algorithm, training a model using the sample feature vector and the corresponding cooling state to obtain the first model. Optionally, the preset classification algorithm includes one or more of the following: decision tree algorithm, support vector machine algorithm, random forest algorithm.

[0093] Taking the decision tree algorithm as an example, in an embodiment of the present application, the training of the first model can include the following steps:

[0094] Step one, combining actual samples and virtual samples to construct a temperature control sample data set;

[0095] Step two, preprocessing the data set, discretizing each temperature feature corresponding to the temperature feature vector, and randomly dividing the temperature feature vector into a training set, a validation set, and a test set according to a certain proportion;

[0096] Step three, calculating the information gain rate of each feature in the training set in turn, the specific calculation method being the prior art, which is not described here.

[0097] Step four, selecting the feature with the maximum information gain rate as the first division feature, i.e. the root node;

[0098] Step five, after determining the root node, the same operation of step three is repeated on the sample set classified according to the root node to determine the decision nodes at each level under the root node until all nodes are completely classified, or there are no more features that can be used, or the information gain of all features is less than a threshold, and the decision tree is generated;

[0099] Step six, the generated decision tree is verified by the validation set data. If the prediction result meets the expectation, the verification is passed; if the prediction result does not meet the expectation, post-pruning operation is performed on the decision tree.

[0100] Step seven, the post-pruning operation judges whether a node should be split by minimizing the loss function of the whole decision tree, and pruning operation is performed on the node that should not be split, that is, no splitting is performed.

[0101] Step eight, the generated decision tree is tested by the test set data. If the prediction result meets the expectation, the test is passed; if the prediction result does not meet the expectation, the data set is expanded and more data samples are added, and steps one to eight are repeated.

[0102] Step nine, the final decision tree is constructed, and the first model training is completed.

[0103] When the first model is applied, for example, if the temperature of a chip of an electronic device is to be controlled, first, a sensor is used to continuously obtain the real-time temperature of the chip at a preset time interval to obtain a real-time temperature sequence t0, t1, t2, t3, t4…, wherein t0 is the real-time temperature at the current moment, t1 is the real-time temperature at the previous moment, the transient temperature rise is t0-t1=Δt0; the transient temperature rise Δt0 is discretized, for example, the transient temperature rise Δt0 is divided into three discrete intervals of 0-5℃, 5-10℃ and 10-20℃; the exponential weighted average temperature at the current moment is calculated from the real-time temperature sequence as T0, the exponential weighted average temperature at the previous moment is calculated as T1, the sustained temperature rise is T0-T1=ΔT0; the sustained temperature rise ΔT0 is discretized, for example, the sustained temperature rise is divided into three discrete intervals of 0-1℃, 1-3℃ and 3-10℃; the real-time temperature t0 at the current moment, the transient temperature rise Δt0, the exponential weighted average temperature T0 at the current moment and the sustained temperature rise ΔT0 are input into the constructed decision tree model (i.e. the first model) as characteristic values, and the decision tree model can determine the required cooling state at the current moment based on the four characteristic values.

[0104] The temperature control method provided by the embodiments of the present application will be described in detail below through a specific embodiment.

[0105] As shown in Figure 2 The temperature control method provided by the embodiments of the present application can include:

[0106] S201, acquire temperature-controlled sample data, the sample data including actually collected temperature and corresponding cooling state of the target region, and / or virtually constructed temperature and corresponding cooling state of the target region;

[0107] The actually collected temperature and corresponding cooling state of the target region can be the temperature and cooling state under a relatively ideal temperature control, and the virtually constructed temperature and corresponding cooling state of the target region can be the temperature and cooling state under a relatively ideal condition set according to experience.

[0108] S202, pre-process the sample data to obtain a sample feature vector and a cooling state corresponding to the sample feature vector;

[0109] The sample feature vector during model training can be consistent in form with the temperature feature vector during model application.

[0110] S203, based on a preset classification algorithm, use the sample feature vector and the corresponding cooling state to perform model training to obtain the first model;

[0111] The preset classification algorithm includes at least one of the following: decision tree algorithm, support vector machine algorithm, random forest algorithm.

[0112] S204, acquire real-time temperature values of the target region at intervals of a preset time length to obtain a real-time temperature sequence;

[0113] For example, the preset time length can be 1 second.

[0114] S205, for each latest current time in the real-time temperature sequence, calculate an exponentially weighted average value corresponding to the latest current time, and use the exponentially weighted average value as an average temperature value corresponding to the latest current time;

[0115] S206, determine the real-time temperature change condition according to the difference between the real-time temperature values of the current time and the previous time, and determine the average temperature change condition according to the difference between the average temperature values of the current time and the previous time;

[0116] S207, construct a temperature feature vector according to the real-time temperature value corresponding to the current time, the real-time temperature change condition, the average temperature value corresponding to the current time, and the average temperature change condition;

[0117] The temperature feature vector can be consistent in form with the sample feature vector, except that the specific vector values are different.

[0118] S208, determine a temperature interval to which the real-time temperature value corresponding to the current time belongs based on a first rule, to obtain a first interval; determine a temperature interval to which the average temperature value corresponding to the current time belongs based on a second rule, to obtain a second interval; determine a temperature change interval to which the real-time temperature change condition belongs based on a third rule, to obtain a third interval; determine a temperature change interval to which the average temperature change condition belongs based on a fourth rule, to obtain a fourth interval;

[0119] S209, input the first interval, the second interval, the third interval and the fourth interval into the first model;

[0120] S210, determine the cooling state required at present according to the output of the first model.

[0121] Optionally, the cooling state can include one or more of the following: the working state of the fan, the working frequency of the processor, and the opening or closing state of the preset circuit module.

[0122] In a second aspect, embodiments of the present application provide a temperature control device capable of intelligently controlling the temperature of a target area and effectively improving the temperature control effect.

[0123] As shown in Figure 3 Embodiments of the present application provide a temperature control device, which can include:

[0124] A temperature collection module 31 is configured to sequentially obtain real-time temperature values of a target area at intervals of a preset time length, to obtain a real-time temperature sequence.

[0125] A first determination module 32 is configured to determine an average temperature value corresponding to a current time according to the real-time temperature value of the current time and at least part of the real-time temperature values corresponding to previous times in the real-time temperature sequence.

[0126] A second determination module 33 is configured to determine a cooling state required at present based on a first model and a temperature feature vector, wherein the first model is a model pre-trained based on artificial intelligence technology, and the temperature feature vector includes: a real-time temperature value corresponding to the current time and a real-time temperature change condition thereof relative to the real-time temperature value of the previous time, an average temperature value corresponding to the current time and an average temperature change condition thereof relative to the average temperature value of the previous time.

[0127] The temperature control device provided by the embodiment of the present application can obtain real-time temperature values of a target region in sequence at intervals of a preset time length, obtain a real-time temperature sequence, determine an average temperature value corresponding to a current time according to a real-time temperature value at the current time and at least part of real-time temperature values corresponding to previous times in the real-time temperature sequence, and determine a required cooling state at the current time based on a first model and a temperature feature vector. Since the temperature feature vector includes a real-time temperature value at the current time, a real-time temperature change of the real-time temperature value at the current time relative to real-time temperature values at the previous times, an average temperature value at the current time, and an average temperature change of the average temperature value at the current time relative to average temperature values at the previous times, compared with the prior art, the temperature control method provided by the embodiment of the present application includes not only real-time temperature and its change, but also average temperature and its change as evaluation factors of the cooling state, so that unnecessary temperature control measures can be effectively reduced or avoided. At the same time, since the evaluation factors are more diversified and the combination of different factors is more complex, the first model can well play the advantages of artificial intelligence technology, accurately grasp the influence of subtle differences between different combinations on the cooling state, so as to more accurately predict the required cooling state of the target region, and greatly improve the temperature control effect.

[0128] In an embodiment, the first determining module can be specifically configured to: for each latest current time in a continuation process of the real-time temperature sequence, calculate an exponential weighted average value corresponding to the latest current time, and take the exponential weighted average value as the average temperature value corresponding to the latest current time.

[0129] In an embodiment, the first determining module can include:

[0130] A first determining unit configured to determine the real-time temperature change according to a difference between the real-time temperature value at the current time and a real-time temperature value at a previous time;

[0131] A second determining unit configured to determine the average temperature change according to a difference between the average temperature value at the current time and an average temperature value at a previous time;

[0132] A constructing unit configured to construct the temperature feature vector according to the real-time temperature value at the current time, the real-time temperature change, the average temperature value at the current time, and the average temperature change.

[0133] In an embodiment, the second determining module can include:

[0134] A third determining unit configured to determine a temperature interval to which the real-time temperature value at the current time belongs based on a first rule, to obtain a first interval;

[0135] A fourth determining unit is configured to determine, based on a second rule, a temperature interval to which the average temperature value corresponding to the current time belongs, to obtain a second interval;

[0136] A fifth determining unit is configured to determine, based on a third rule, a temperature change interval to which the real-time temperature change belongs, to obtain a third interval;

[0137] A sixth determining unit is configured to determine, based on a fourth rule, a temperature change interval to which the average temperature change belongs, to obtain a fourth interval;

[0138] An input unit is configured to input the first interval, the second interval, the third interval, and the fourth interval into the first model;

[0139] A seventh determining unit is configured to determine a current required cooling state according to an output of the first model.

[0140] In an embodiment, the apparatus can further include:

[0141] A sample obtaining module is configured to obtain sample data of temperature control, the sample data including actually collected temperature and corresponding cooling state of the target region, and / or virtually constructed temperature and corresponding cooling state of the target region;

[0142] A preprocessing module is configured to pre-process the sample data to obtain a sample feature vector corresponding to the temperature feature vector, and a cooling state corresponding to the sample feature vector;

[0143] A training module is configured to perform model training based on a preset classification algorithm, using the sample feature vector and the corresponding cooling state, to obtain the first model.

[0144] In an embodiment, the cooling state includes at least one of the following: working state of a fan, working frequency of a processor, and on / off state of a preset circuit module.

[0145] In an embodiment, the preset classification algorithm includes at least one of the following: decision tree algorithm, support vector machine algorithm, and random forest algorithm.

[0146] In a third aspect, an embodiment of the present application further provides an electronic device capable of intelligently controlling temperature of a target region.

[0147] As Figure 4As shown, the electronic device provided by the embodiment of the present application can include a housing 51, a processor 52, a memory 53, a circuit board 54 and a power supply circuit 55, wherein the circuit board 54 is arranged inside the space enclosed by the housing 51, and the processor 52 and the memory 53 are arranged on the circuit board 54; the power supply circuit 55 is configured to supply power to each circuit or device of the electronic device; the memory 53 is configured to store executable program codes; and the processor 52 is configured to run the program corresponding to the executable program codes by reading the executable program codes stored in the memory 53, so as to execute the temperature control method provided by any of the foregoing embodiments.

[0148] The specific execution process of the foregoing steps by the processor 52 and the steps further executed by the processor 52 by running the executable program codes can refer to the description of the foregoing embodiments, which will not be repeated here.

[0149] In a fourth aspect, the embodiment of the present application further provides a computer readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement any of the temperature control methods provided by the foregoing embodiments, so as to achieve the corresponding technical effects, which have been described in detail in the foregoing, and will not be repeated here.

[0150] It should be noted that, in this document, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the terms “include”, “contain” or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement “including a…” does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0151] Each embodiment in the specification is described in a relevant manner, and the same or similar parts of each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments.

[0152] Especially, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the part of the description of the method embodiment.

[0153] For ease of description, the above apparatus is described in various units / modules respectively in terms of functions. Of course, the functions of the units / modules can be implemented in one or more software and / or hardware in implementing the present application.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing relevant hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), a random access memory (RAM), etc.

[0155] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed by the present application can be easily thought of by those skilled in the art, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A temperature control method, characterized in that, include: The real-time temperature value of the target area is obtained sequentially at preset time intervals to obtain a real-time temperature sequence. Based on the real-time temperature value at the current moment and at least a portion of the real-time temperature values ​​at previous moments in the real-time temperature sequence, the average temperature value corresponding to the current moment is determined. Based on the first model and the temperature feature vector, the required cooling state is determined. The first model is a model pre-trained based on artificial intelligence technology. The temperature feature vector includes: the real-time temperature value corresponding to the current moment and its real-time temperature change relative to the real-time temperature value at the previous moment, and the average temperature value corresponding to the current moment and its average temperature change relative to the average temperature value at the previous moment. The step of determining the required cooling state based on the first model and temperature feature vector includes: Based on the first rule, the temperature range to which the real-time temperature value corresponding to the current moment belongs is determined, thus obtaining the first range; Based on the second rule, the temperature range to which the average temperature value corresponding to the current moment belongs is determined, thus obtaining the second range; Based on the third rule, the temperature change range to which the real-time temperature change belongs is determined, thus obtaining the third range; Based on the fourth rule, the temperature change interval to which the average temperature change belongs is determined, thus obtaining the fourth interval; Input the first interval, the second interval, the third interval, and the fourth interval into the first model; Based on the output of the first model, determine the current required cooling state.

2. The method according to claim 1, characterized in that, The step of determining the average temperature value corresponding to the current moment based on the real-time temperature value at the current moment and at least a portion of the real-time temperature values ​​corresponding to previous moments in the real-time temperature sequence includes: For each latest current moment during the continuation of the real-time temperature sequence, calculate the exponentially weighted average value corresponding to the latest current moment, and use the exponentially weighted average value as the average temperature value corresponding to the latest current moment.

3. The method according to claim 1, characterized in that, After determining the average temperature value corresponding to the current moment based on the real-time temperature value at the current moment and at least a portion of the real-time temperature values ​​corresponding to previous moments in the real-time temperature sequence, and before determining the required cooling state based on the first model and temperature feature vector, the method further includes: The real-time temperature change is determined based on the difference between the current temperature and the previous temperature; the average temperature change is determined based on the difference between the current temperature and the previous average temperature. The temperature feature vector is constructed based on the real-time temperature value at the current moment, the real-time temperature change, the average temperature value at the current moment, and the average temperature change.

4. The method according to any one of claims 1 to 3, characterized in that, Before determining the required cooling state based on the first model and temperature feature vector, the method further includes: Acquire sample data for temperature control, the sample data including the actual collected temperature of the target area and the corresponding cooling state, and / or the temperature of the target area and the corresponding cooling state virtually constructed; The sample data is preprocessed to obtain a sample feature vector corresponding to the temperature feature vector, and a cooling state corresponding to the sample feature vector; Based on a preset classification algorithm, the model is trained using the sample feature vectors and their corresponding cooling states to obtain the first model.

5. The method according to claim 4, characterized in that, The preset classification algorithm includes at least one of the following: decision tree algorithm, support vector machine algorithm, and random forest algorithm.

6. The method according to any one of claims 1 to 3, characterized in that, The cooling state includes at least one of the following: the operating state of the fan, the operating frequency of the processor, and the on or off state of the preset circuit module.

7. A temperature control device, characterized in that, include: The temperature acquisition module is used to acquire the real-time temperature value of the target area at preset time intervals to obtain a real-time temperature sequence. The first determining module is used to determine the average temperature value corresponding to the current moment based on the real-time temperature value at the current moment and at least a portion of the real-time temperature values ​​corresponding to previous moments in the real-time temperature sequence. The second determining module is used to determine the current required cooling state based on the first model and the temperature feature vector. The first model is a model pre-trained based on artificial intelligence technology. The temperature feature vector includes: the real-time temperature value corresponding to the current moment and its real-time temperature change relative to the real-time temperature value at the previous moment, and the average temperature value corresponding to the current moment and its average temperature change relative to the average temperature value at the previous moment. The second determining module includes: The third determining unit is used to determine the temperature range to which the real-time temperature value corresponding to the current moment belongs based on the first rule, thereby obtaining the first range; The fourth determining unit is used to determine the temperature range to which the average temperature value corresponding to the current time belongs based on the second rule, thereby obtaining the second range; The fifth determining unit is used to determine the temperature change range to which the real-time temperature change belongs based on the third rule, thereby obtaining the third range; The sixth determining unit is used to determine the temperature change interval to which the average temperature change belongs based on the fourth rule, thereby obtaining the fourth interval; An input unit is used to input the first interval, the second interval, the third interval, and the fourth interval into the first model; The seventh determining unit is used to determine the current required cooling state based on the output of the first model.

8. The apparatus according to claim 7, characterized in that, The first determining module is specifically used for: For each latest current moment during the continuation of the real-time temperature sequence, calculate the exponentially weighted average value corresponding to the latest current moment, and use the exponentially weighted average value as the average temperature value corresponding to the latest current moment.

9. The apparatus according to claim 7, characterized in that, The first determination module includes: The first determining unit is used to determine the real-time temperature change based on the difference between the real-time temperature value at the current time and the real-time temperature value at the previous time. The second determining unit is used to determine the average temperature change based on the difference between the average temperature value at the current time and the average temperature value at the previous time. The construction unit is used to construct the temperature feature vector based on the real-time temperature value corresponding to the current moment, the real-time temperature change, the average temperature value corresponding to the current moment, and the average temperature change.

10. The apparatus according to any one of claims 7 to 9, characterized in that, The device further includes: The sample acquisition module is used to acquire sample data for temperature control. The sample data includes the actual temperature of the target area and the corresponding cooling state, and / or the temperature of the target area and the corresponding cooling state virtually constructed. The preprocessing module preprocesses the sample data to obtain a sample feature vector corresponding to the temperature feature vector and a cooling state corresponding to the sample feature vector. The training module is used to train the model based on a preset classification algorithm, using the sample feature vector and its corresponding cooling state, to obtain the first model.

11. The apparatus according to any one of claims 7 to 9, characterized in that, The cooling state includes at least one of the following: the operating state of the fan, the operating frequency of the processor, and the on or off state of the preset circuit module.

12. An electronic device, characterized in that, The electronic device includes: a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is disposed inside the space enclosed by the housing, and the processor and the memory are disposed on the circuit board; the power supply circuit is used to supply power to various circuits or devices of the electronic device; the memory is used to store executable program code; the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, for executing the temperature control method of any one of claims 1 to 6.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the temperature control method according to any one of claims 1 to 6.

Images