Air conditioner, control method thereof, storage medium and program product

Abstract

The invention relates to an air conditioner and a control method thereof, a storage medium and a program product. The method comprises the steps that multi-source information of a target animal is obtained; the multi-source information comprises radar data, image data and sound data; determining a first confidence coefficient set according to the multi-source information; the first confidence coefficient set comprises N preset state confidence coefficients; each preset state confidence coefficient is used for representing the probability that the target animal is in each preset state in the preset state set; n is the number of preset states contained in the preset state set; the preset state set comprises a heatstroke state, a hot state, a cold state and a sleep state; and on the basis of a preset adjusting rule, according to the determined first confidence coefficient set, air conditioner operation parameters are adjusted so as to improve the comfort level of the target animal. According to the method, the adjusted operation parameters of the air conditioner can more accurately adapt to the actual environment requirements of the target animal, so that the comfort improvement effect brought by the air conditioner to the target animal is improved.

Description

Technical Field

[0001] This application relates to the field of air conditioning technology, and in particular to an air conditioner and its control method, storage medium, and program product. Background Technology

[0002] With the increasing popularity of pet ownership, the comfort of pets' living environment has gradually become a core concern for owners. To provide a comfortable living environment for pets, some air conditioners have a pet mode. Specifically, in pet mode, the air conditioner identifies the pet's current state based on vital signs such as body temperature and heart rate, and then adjusts the air conditioner's operating parameters (such as set temperature and fan speed) accordingly to improve the pet's comfort. However, because pet behavior is complex and changes frequently, the current state identified by the air conditioner cannot accurately represent the pet's true environmental needs. This makes it difficult for the adjusted air conditioner parameters to adapt to the pet's actual environmental requirements, resulting in a limited effect on improving pet comfort. Summary of the Invention

[0003] Based on this, this application provides an air conditioning control method that enables the adjusted air conditioning operating parameters to more accurately adapt to the actual environmental needs of the target animal, thereby improving the comfort effect of the air conditioning on the target animal.

[0004] On one hand, this application provides an air conditioning control method, the method comprising: acquiring multi-source information of a target animal; the multi-source information including radar data, image data, and sound data; determining a first confidence set based on the multi-source information; the first confidence set including N preset state confidences; each preset state confidence is used to characterize the probability that the target animal is in each preset state in the preset state set; N is the number of preset states included in the preset state set; the preset state set includes heatstroke state, hot state, cold state, and sleep state; and adjusting the air conditioning operating parameters based on preset adjustment rules and according to the determined first confidence set to improve the comfort of the target animal.

[0005] Optionally, the step of determining the first set of confidence scores based on multi-source information includes: extracting preset judgment features from multi-source information; the preset judgment features include the target animal's position, movement trajectory, posture information, and sound feature vector; performing temporal alignment on the preset judgment features; inputting the aligned preset judgment features in parallel into N preset attention models to obtain N preset state confidence scores; and the preset attention models correspond one-to-one with the preset state confidence scores.

[0006] Optionally, the step of adjusting the air conditioning operating parameters to improve the comfort of the target animal based on a preset adjustment rule and a determined first set of confidence levels includes: when at least one target confidence level exists among N preset state confidence levels, determining the target operating parameters of the air conditioner from N sets of preset operating parameters according to a preset safety priority and the target confidence level; wherein, the target confidence level is a preset state confidence level with a confidence level greater than or equal to a first preset threshold; the preset operating parameters correspond one-to-one with the preset state confidence levels; when all N preset state confidence levels are less than the first preset threshold and greater than or equal to a second preset threshold, calculating the target operating parameters according to a preset weighted calculation rule based on at least two of the N preset state confidence levels; the second preset threshold is less than the first preset threshold; and adjusting the current operating parameters of the air conditioner to the target operating parameters.

[0007] Optionally, the air conditioner operating parameters include the set temperature; the preset weighted calculation rule includes the following formula: T1=T0-TX*(A1*C1+A2*C2-A3*C3+A4*C4) / Ca1. Where, T1 is the target set temperature; T0 is the current set temperature; TX is the preset temperature adjustment step size; A1 is the first weighting coefficient; C1 is the preset state confidence level corresponding to the heatstroke state; A2 is the second weighting coefficient; C2 is the preset state confidence level corresponding to the hot state; A3 is the third weighting coefficient; C3 is the preset state confidence level corresponding to the cold state; A4 is the fourth weighting coefficient; C4 is the preset state confidence level corresponding to the sleep state; Ca1 is the sum of the four confidence levels C1, C2, C3, and C4.

[0008] Optionally, the first to fourth weight coefficients are obtained based on the first learning model; the first learning model is trained based on historical air conditioning adjustment data.

[0009] Optionally, the preset state set also includes an anxiety state; the air conditioner operating parameters also include the set fan speed; the preset weighted calculation rule includes the following formula: V1=V0+VX*(A5*C1+A6*C2-A7*C3-A8*C4-A9*C5) / Ca2. Where, V1 is the target set fan speed; V0 is the current set fan speed; VX is the preset fan speed adjustment step size; A5 is the fifth weight coefficient; C1 is the preset state confidence level corresponding to the heatstroke state; A6 is the sixth weight coefficient; C2 is the preset state confidence level corresponding to the hot state; A7 is the seventh weight coefficient; C3 is the preset state confidence level corresponding to the cold state; A8 is the eighth weight coefficient; C4 is the preset state confidence level corresponding to the sleep state; A9 is the ninth weight coefficient; C5 is the preset state confidence level corresponding to the anxiety state; Ca2 is the sum of the five confidence levels of C1, C2, C3, C4 and C5.

[0010] Optionally, the method also includes: when the confidence levels of N preset states are all less than a third preset threshold, controlling the air conditioner to operate according to preset safe operating parameters and executing an alarm command.

[0011] On the other hand, this application also provides an air conditioner, comprising: an acquisition module for acquiring multi-source information of a target animal; the multi-source information including radar data, image data, and sound data; a determination module for determining a first confidence set based on the multi-source information; the first confidence set including N preset state confidences; each preset state confidence is used to characterize the probability that the target animal is in each preset state in the preset state set; N is the number of preset states included in the preset state set; the preset state set includes heatstroke state, hot state, cold state, and sleeping state; and an adjustment module for adjusting the air conditioner operating parameters based on preset adjustment rules and according to the determined first confidence set, so as to improve the comfort of the target animal.

[0012] In another aspect, this application also provides another type of air conditioner, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the aforementioned method.

[0013] In another aspect, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the aforementioned method.

[0014] In another aspect, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the aforementioned method.

[0015] The embodiments provided in this application determine a first confidence set based on multi-source information, and then adjust the air conditioning operating parameters according to the first confidence set to improve the comfort of the target animal. The first confidence set includes N preset state confidence levels used to characterize different preset states of the target animal, such as heatstroke, hot, cold, and sleep. This can more accurately reflect the actual environmental needs of the target animal, so that the adjusted air conditioning operating parameters can more accurately adapt to the actual environmental needs of the target animal and improve the comfort improvement effect of the air conditioning on the target animal. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating an air conditioner control method according to some embodiments of this application;

[0017] Figure 2 This is a flowchart illustrating a method for adjusting air conditioning operating parameters according to some embodiments of this application;

[0018] Figure 3 This is a schematic diagram of the structure of an air conditioner according to some embodiments of this application;

[0019] Figure 4 This is a schematic diagram of the structure of an air conditioner according to other embodiments of this application. Detailed Implementation

[0020] To make the technical solution and beneficial effects of this application more apparent and understandable, a detailed description is provided below by listing specific embodiments. Unless otherwise defined, the technical and scientific terms used in this application have the same meaning as those in the technical field to which this application pertains. The terminology used in the specification of this application is for the purpose of describing specific embodiments only and is not intended to limit this application.

[0021] See Figure 1 Some embodiments of this application provide a method for controlling an air conditioner, the method comprising:

[0022] S101, Acquire multi-source information about the target animal. This multi-source information includes radar data, image data, and sound data.

[0023] S102, Based on multi-source information, determine the first confidence set. The first confidence set includes N preset state confidence levels. Each preset state confidence level is used to characterize the probability that the target animal is in each preset state in the preset state set. N is the number of preset states included in the preset state set. The preset state set includes heatstroke state, hot state, cold state, and sleeping state.

[0024] S103, based on preset adjustment rules and according to the determined first confidence set, adjusts the air conditioning operating parameters to improve the comfort of the target animal.

[0025] It is understandable that the target animal refers to the animal that the air conditioner is targeting to identify abnormal behavioral states. The target animal can be a pet (such as a cat or dog) or livestock (such as a pig, cow, or chicken) from a farm. When there are multiple animals within the air conditioner's detection range, one can be designated as the target animal through user specification or other methods. Multi-source information refers to real-time data of the target animal obtained through various types of acquisition devices. Radar data can be acquired via radar to detect the target animal's location, micro-motion information (such as breathing and heartbeat), and movement trajectory. Image data can be acquired via cameras to identify the target animal's location and real-time posture (such as curling up, stretching, panting, and trembling). Sound data can be acquired via microphone arrays to collect animal vocalizations, panting sounds, and other auditory information. Preset state confidence level characterizes the probability that the target animal is in a specific preset state within a preset state set. The higher the preset state confidence level, the higher the probability that the target animal is in that preset state. The preset state set refers to the collection of multiple preset states of the target animal; the target animal's behavioral patterns will differ significantly under different preset states. For example, in hot conditions, the target animal will exhibit behaviors such as frequent licking of its fur, rapid panting, and reduced activity; while in a state of heatstroke, the target animal will lie motionless, breathe deeply and slowly (indicating difficulty breathing), and have an unsteady gait; in a cold condition, the target animal will exhibit behaviors such as curling up, shivering, and seeking heat sources; and while asleep, the target animal will exhibit behaviors such as ceasing movement, steady breathing, and slow response to external stimuli. Air conditioning operating parameters refer to the adjustable settings such as the set temperature, set fan speed, airflow direction, and set humidity.

[0026] The aforementioned air conditioning control method determines a first confidence set based on multi-source information and then adjusts the air conditioning operating parameters according to the first confidence set to improve the comfort of the target animal. The first confidence set includes N preset state confidence levels used to characterize different preset states of the target animal, such as heatstroke, hot weather, cold weather, and sleep. This can more comprehensively and accurately reflect the actual environmental needs of the target animal, thereby enabling the adjusted air conditioning operating parameters to more precisely adapt to the actual environmental needs of the target animal and improve the comfort improvement effect of the air conditioning on the target animal.

[0027] Specifically, in real life, target animals are often in a superposition or transitional state of multiple preset states. For example, a target animal may be simultaneously in a sleeping state and a hot state. Or, it may be in a transitional state between a hot state and a heatstroke state. Therefore, the actual environmental needs of the target animal are relatively complex. In the air conditioning control method described above, the current state of the target animal is described by determining the confidence levels of N preset states in the first confidence level set. This method is closer to the superposition or transitional states of the target animal in real life, and therefore can more accurately reflect the actual environmental needs of the target animal. This allows the air conditioner to select more appropriate operating parameters to adapt to the actual environmental needs. For example, when the confidence levels of the preset states corresponding to the sleeping state and the hot state are both high, it indicates that the target animal feels hot while sleeping. At this time, the air conditioner can prioritize lowering the set temperature or increasing the set fan speed, while adjusting the airflow direction to avoid blowing directly on the target animal. This alleviates the heat condition of the target animal while avoiding disturbing its sleep. For transitional states, such as the transition between a hot state and a heatstroke state, the air conditioner can dynamically adjust the set temperature and set fan speed according to the confidence level of the corresponding preset states to prevent the target animal's hot state from deteriorating into a heatstroke state.

[0028] Furthermore, the aforementioned air conditioning control method also acquires multi-source information about the target animal and then determines N preset state confidence levels in the first confidence level set based on this multi-source information. The multi-source information includes radar data, image data, and sound data. These data can reflect the current state of the target animal from different dimensions, enabling the multi-source information to more comprehensively reflect the current state of the target animal, thereby increasing the accuracy of the determined preset state confidence levels.

[0029] Furthermore, it is understood that in the above embodiments, the multi-source information includes radar data, image data, and sound data, and this configuration is exemplary. In some other embodiments, the multi-source data may also include data from other sources; for example, the multi-source data may also include physiological characteristic data of the target animal detected by the smart collar.

[0030] In some embodiments, step S102, which determines the first confidence set based on multi-source information, includes:

[0031] Pre-defined judgment features are extracted from multi-source information. These features include the target animal's location, movement trajectory, posture information, and vocal feature vectors. Temporal alignment of these features is then performed. The aligned features are then input in parallel into N pre-defined attention models to obtain N pre-defined state confidence scores. Each pre-defined attention model corresponds one-to-one with a pre-defined state confidence score.

[0032] Specifically, the preset judgment features refer to multimodal features extracted from multi-source information that can be used to infer the current state of the target animal. The target animal's position, extracted from radar data, reflects its distance from the air conditioner, thus inferring its current state. For example, if the target animal is far from the heat source when the air conditioner is in heating mode, it can be inferred that the animal is in a hot state. Conversely, if the target animal is close to the heat source, it can be inferred that it is in a cold state. The target animal's movement trajectory reflects its movement frequency and speed, which can also be used to infer its current state. For example, if both its movement frequency and speed are low, it may be that the animal is cold and curled up in a specific location, or it may be sleeping. The target animal's posture information characterizes its current posture, such as standing, sitting, curled up, or lying down. Posture information can be used to create a 3D model based on the target animal's image data, and then the determination can be based on the resulting 3D model. A sound feature vector refers to the sound characteristics of a target animal, such as frequency and volume. Sound feature vectors can be used to determine the type of a target animal's call (such as growling, purring, barking, etc.), and then to infer the current state of the target animal.

[0033] Furthermore, it is understandable that time alignment refers to the process of aligning multiple judgment features to the same time according to a timetable. This allows multiple judgment features to reflect the target animal's state at the same time, so that N preset attention models can process them. A preset attention model is a model that uses multimodal fusion of multiple judgment features to determine whether the target animal is in a corresponding preset state, thereby obtaining a preset state confidence score. Each preset attention model corresponds to a preset state confidence score.

[0034] The aforementioned air conditioning control method uses N preset attention models to process aligned preset judgment features in parallel to obtain N preset state confidence scores. This allows radar data, image data, and sound data to be projected into the same dimensional space. Furthermore, by suppressing noise through cross-modal attention, errors are reduced, resulting in higher accuracy of the generated preset state confidence scores.

[0035] It is understood that the preset judgment features in the above-described air conditioning control method include four features such as the location of the target animal, and this setting is exemplary. In some other embodiments, the judgment features may also include other features that can reflect the characteristics of the target animal. For example, the preset judgment features may also include respiratory rate. Alternatively, the preset judgment features may also include physiological signs such as heart rate and body temperature.

[0036] refer to Figure 2In some embodiments, step S103, based on preset adjustment rules and according to a determined first confidence set, adjusts the air conditioning operating parameters to improve the comfort of the target animal, including:

[0037] S201, when at least one target confidence level exists among N preset state confidence levels, the target operating parameters of the air conditioner are determined from N sets of preset operating parameters according to the preset safety priority and the target confidence level. The target confidence level is a preset state confidence level whose confidence level is greater than or equal to a first preset threshold. There is a one-to-one correspondence between the preset operating parameters and the preset state confidence levels.

[0038] S202, when the confidence levels of all N preset states are less than the first preset threshold and greater than or equal to the second preset threshold, the target operating parameters are calculated according to a preset weighted calculation rule based on at least two of the N preset state confidence levels. The second preset threshold is less than the first preset threshold.

[0039] S203, adjust the current operating parameters of the air conditioner to the target operating parameters.

[0040] Understandably, preset safety priorities refer to the order in which multiple preset states are prioritized according to their ability to ensure the safety of the target animal. For example, a target animal in a heatstroke state is in a more critical condition and therefore has a higher safety priority. As a concrete example, preset safety priorities from highest to lowest could be: heatstroke state, hot state, cold state, and sleeping state. Preset operating parameters refer to the ideal operating parameters that the air conditioner is pre-set for different preset states of the target animal, which can improve the comfort of the target animal in the corresponding preset state.

[0041] Specifically, when the confidence value of a preset state is greater than or equal to a first preset threshold, it indicates that the target animal is more likely to be in the preset state corresponding to that preset state confidence value. When there are multiple target confidence values ​​among N preset state confidence values, the target operating parameters can be determined jointly based on the preset safety priority and the target confidence values. That is, the preset operating parameters corresponding to the target confidence value with the highest priority are selected as the target operating parameters of the air conditioner, which allows the air conditioner to prioritize the health and safety of the target animal.

[0042] When the confidence levels of all N preset states are less than the first preset threshold and greater than or equal to the second preset threshold, it indicates that the target animal may be in a mixed or transitional state of multiple states. In this case, the target operating parameters can be calculated based on at least two of the N preset state confidence levels according to a preset weighted calculation rule. This allows the air conditioner to comprehensively consider at least two preset state confidence levels to generate the target operating parameters, making the target operating parameters closer to the actual environmental needs of the target animal, thereby improving the comfort improvement effect of the air conditioner on the target animal.

[0043] As a specific example, the first preset threshold can be set to 0.7, and the second preset threshold can be set to 0.3. It is understood that in some other embodiments, the first and second preset thresholds may also be other preset values, such as 0.8 and 0.2.

[0044] In some embodiments, the air conditioning operating parameters include the set temperature. The preset weighted calculation rule includes the following formula (1):

[0045] T1=T0-TX*(A1*C1+A2*C2-A3*C3+A4*C4) / Ca1 (1)

[0046] Where T1 is the target set temperature. T0 is the current set temperature. TX is the preset temperature adjustment step size. A1 is the first weighting coefficient. C1 is the preset state confidence level corresponding to heatstroke. A2 is the second weighting coefficient. C2 is the preset state confidence level corresponding to hot weather. A3 is the third weighting coefficient. C3 is the preset state confidence level corresponding to cold weather. A4 is the fourth weighting coefficient. C4 is the preset state confidence level corresponding to sleep. Ca1 is the sum of the four confidence levels C1, C2, C3, and C4.

[0047] Specifically, in formula (1) above, if C1 and C2 increase, the positive value inside the parentheses increases, and the target set temperature T1 will be lower than the current set temperature, thereby alleviating the heatstroke or heat-related condition of the target animal. When the heatstroke or heat-related condition of the target animal is relieved, C1 and C2 decrease, causing the positive value inside the parentheses to decrease, which in turn causes the adjustment range of the target set temperature T1 (the adjustment range is proportional to the absolute value inside the parentheses) to decrease, eventually converging and stabilizing the air conditioner's set temperature at a comfortable temperature for the target animal. Similarly, in formula (1) above, if C3 increases, the negative value inside the parentheses increases, and the target set temperature T1 will be higher than the current set temperature T0, thereby alleviating the cold-related condition of the target animal. When the cold-related condition of the target animal is relieved, C3 decreases, causing the adjustment range of the target set temperature T1 to decrease, and stabilizing the air conditioner's set temperature at a comfortable temperature for the target animal. Therefore, by using the target set temperature determined by the above formula (1), negative feedback regulation of the air conditioning set temperature can be achieved, so that the target set temperature approaches the comfort temperature of the target animal, thereby alleviating the heatstroke, heat and cold conditions of the target animal and improving the comfort of the target animal.

[0048] Furthermore, in the above formula (1), if C4 increases, the target set temperature T1 will be lower than the current set temperature T0, providing a cool sleeping environment for the target animal in its sleeping state, preventing overheating due to sleep, and meeting the target animal's environmental temperature requirements during sleep. After the requirements are met, the target animal's sleeping state will not change. Therefore, C4 will generate a relatively stable temperature regulation value, eventually reaching a balance with the aforementioned C1, C2, and C3. This ensures that after adjustment, the air conditioner's set temperature will stabilize at the difference between the target animal's comfortable temperature and this temperature regulation value. Therefore, by determining the target set temperature through the above formula (1), the target animal's environmental temperature requirements during sleep can also be met, thereby further improving the target animal's comfort.

[0049] Furthermore, in the above formula (1), the denominator Ca1 is the sum of the four confidence levels C1, C2, C3, and C4. This allows the above formula (1) to adjust the target set temperature based on the total confidence levels of C1, C2, C3, and C4. The advantage of this adjustment method is that when the four confidence levels of C1, C2, C3, and C4 are all small, the denominator Ca1 will also decrease, so that the adjustment range will not decrease rapidly as the confidence level decreases, thus ensuring that the temperature adjustment speed of the air conditioner is always maintained within a suitable range. This can both avoid drastic fluctuations in the air conditioner temperature, which could lead to health abnormalities in the target animal due to drastic temperature fluctuations, and avoid the problem of the air conditioner adjusting the temperature too slowly, which could lead to the air conditioner not being effective in improving the comfort of the target animal, thereby improving the temperature adjustment effect of the air conditioner.

[0050] Optionally, the first to fourth weight coefficients are obtained based on the first learning model. The first learning model is trained based on historical air conditioning adjustment data. This allows the first to fourth weight coefficients to be adaptively adjusted according to the individual habits of the target animal, making the target set temperature generated by the above formula (1) closer to the actual environmental needs of the target animal, thereby improving the comfort improvement effect of air conditioning on the target animal.

[0051] It is understood that the first to fourth weight coefficients are obtained based on the first learning model, and this method of obtaining weight coefficients is exemplary. In some other embodiments, the first to fourth weight coefficients can also be set in other ways. For example, the first to fourth weight coefficients can also be preset coefficients between 0 and 1, and the sum of these four weight coefficients is 1.

[0052] In some embodiments, the preset state set also includes an anxiety state. Air conditioning operating parameters also include a set fan speed. The preset weighted calculation rule includes the following formula (2):

[0053] V1=V0+VX*(A5*C1+A6*C2-A7*C3-A8*C4-A9*C5) / Ca2 (2)

[0054] Wherein, V1 is the target wind speed. V0 is the current wind speed. VX is the preset wind speed adjustment step size. A5 is the fifth weighting coefficient. C1 is the preset confidence level for the heatstroke state. A6 is the sixth weighting coefficient. C2 is the preset confidence level for the hot state. A7 is the seventh weighting coefficient. C3 is the preset confidence level for the cold state. A8 is the eighth weighting coefficient. C4 is the preset confidence level for the sleep state. A9 is the ninth weighting coefficient. C5 is the preset confidence level for the anxiety state. Ca2 is the sum of the five confidence levels C1, C2, C3, C4, and C5.

[0055] Understandably, anxiety is one of the pre-defined states of the target animal, which can manifest as frequent pacing, scratching at doors, windows, or furniture, or emitting growling or whimpering sounds. The confidence level of the pre-defined state corresponding to the anxiety state can be generated by the corresponding pre-defined attention model.

[0056] Specifically, in formula (2) above, if C1 and C2 increase, the positive value within the parentheses increases, and the target set wind speed V1 will be higher than the current set wind speed V0. A high wind speed is beneficial for the target animal to dissipate heat, thereby alleviating the target animal's heatstroke or heat-related condition. When the target animal's heatstroke or heat-related condition is relieved, C1 and C2 decrease, causing the adjustment range of the target set wind speed V1 to decrease as well, eventually converging and stabilizing the air conditioner's set wind speed at a comfortable wind speed for the target animal. Similarly, in formula (2) above, if C3 and C5 increase, the negative value within the parentheses increases, and the target set wind speed V1 will be lower than the current set wind speed V0. A low wind speed is beneficial for reducing the target animal's heat dissipation level, thus alleviating the target animal's cold condition. At the same time, a low wind speed is also beneficial for reducing the stimulation of the external environment on the target animal, alleviating the target animal's anxiety. When the target animal's cold and anxiety conditions are relieved, C3 and C5 will decrease, causing the adjustment range of the target set wind speed V1 to decrease, thereby stabilizing the air conditioning set wind speed at the target animal's comfortable wind speed. Therefore, by determining the target set wind speed through the above formula (2), negative feedback adjustment of the air conditioning set wind speed can be achieved, making the target set wind speed approach the target animal's comfortable wind speed, thereby alleviating the target animal's heatstroke, heat, cold and anxiety conditions, and improving the target animal's comfort.

[0057] Furthermore, in the above formula (2), if C4 increases, the target set wind speed V1 will be lower than the current set wind speed V1, thereby reducing the stimulation of the external environment on the target animal and meeting the wind speed requirements of the target animal in its sleep state. After the requirements are met, the sleep state of the target animal will not change. Therefore, C4 will generate a relatively stable wind speed adjustment value, which will eventually reach a balance with the aforementioned C1, C2, C3 and C5. This makes the set wind speed of the air conditioner stable as the sum of the comfortable wind speed for the target animal and the wind speed adjustment value after adjustment. Therefore, by determining the target set wind speed through the above formula (2), the wind speed requirements of the target animal in its sleep state can also be met, thereby further improving the comfort of the target animal.

[0058] Furthermore, in the above formula (2), the denominator Ca2 is the sum of the five confidence levels C1, C2, C3, C4, and C5. This allows the above formula (2) to adjust the target set wind speed based on the total confidence level from C1 to C5. The advantage of this adjustment is that it can keep the air conditioner's wind speed adjustment speed within a suitable range, thereby improving the air conditioner's wind speed adjustment effect. The specific principle is the same as that of the denominator Ca1 in the aforementioned formula (1), and will not be elaborated here.

[0059] It is understood that the preset state set in the above-mentioned air conditioning control method includes heatstroke state, hot state, cold state, sleep state, and anxiety state. This setting is exemplary. In some other embodiments, the preset state set may also include other preset states. For example, the preset state set may also include a comfortable state and an abnormal health state. The comfortable state refers to the ideal state of the target animal, characterized by stable activity frequency, relaxed posture, and no abnormal vocalizations. The abnormal health state refers to the target animal exhibiting health abnormalities such as a cold or vomiting, characterized by frequent vomiting or diarrhea, lethargy, and refusal to move. The comfortable state and the abnormal health state can also generate corresponding preset state confidence levels through corresponding preset attention models. It should be noted that when the preset state set includes both comfortable and abnormal health states, the safety priority of the abnormal health state is the highest, and the safety priority of the comfortable state is the lowest among the preset safety priorities.

[0060] Optionally, the fifth to ninth weight coefficients are obtained based on the second learning model; the second learning model can be trained based on historical air conditioning adjustment data. This allows the fifth to ninth weight coefficients to be adaptively adjusted according to the individual habits of the target animal, making the target wind speed generated by the above formula (2) more closely match the actual environmental needs of the target animal.

[0061] It is understood that the fifth to ninth weight coefficients are obtained based on the second learning model, and this method of obtaining weight coefficients is exemplary. In some other embodiments, the first to fourth weight coefficients can also be set in other ways. For example, the first to fourth weight coefficients can also be preset coefficients between 0 and 1, and the sum of these four weight coefficients is 1.

[0062] In some embodiments, the method further includes: when the confidence levels of N preset states are all less than a third preset threshold, controlling the air conditioner to operate according to preset safe operating parameters and executing an alarm command.

[0063] Specifically, when the confidence levels of N preset states are all less than a third preset threshold, it indicates that the target animal does not belong to any of the preset state sets (such as heatstroke, hot, cold, sleeping, anxious, comfortable, and abnormal health states). This suggests that the air conditioner may be malfunctioning, such as an error in multi-source data acquisition, the target animal leaving the air-conditioned area, or the target animal being in an unidentifiable abnormal state. In these states, the air conditioner will operate according to preset safe operating parameters to ensure the target animal is in a safe environment. Simultaneously, the air conditioner will execute an alarm command to alert the user to address the current abnormal state, thereby protecting the safety and health of the target animal.

[0064] It should be noted that when an air conditioner has both a second preset threshold and a third preset threshold, the third preset threshold can be set to be less than or equal to the second preset threshold to avoid logical errors. As a specific example, the second preset threshold can be set to 0.3, and the third preset threshold can be set to 0.2.

[0065] Optionally, the air conditioning control method further includes, among N preset state confidence levels, executing an alarm command if the preset state confidence level corresponding to an abnormal health state or heatstroke state is greater than or equal to a first preset threshold. This allows the air conditioner to remind the user to pay attention to the target animal's abnormal health state or heatstroke state, so that the user can take the target animal to the vet or take other measures in a timely manner, thereby ensuring the health of the target animal.

[0066] refer to Figure 3In some embodiments of this application, an air conditioner 100 is also provided, including an acquisition module 110, a determination module 120, and an adjustment module 130. The acquisition module 110 is used to acquire multi-source information about a target animal. The preset safety priority multi-source information includes radar data, image data, and sound data. The determination module 120 is used to determine a first confidence set based on the preset safety priority multi-source information. The preset safety priority first confidence set includes N preset state confidence levels. Each preset safety priority preset state confidence level is used to characterize the probability that the target animal is in each preset state in the preset state set. N is the number of preset states included in the preset safety priority preset state set. The preset safety priority preset state set includes heatstroke state, hot state, cold state, and sleeping state. The adjustment module 130 is used to adjust the preset safety priority air conditioner operating parameters based on preset adjustment rules and according to the determined first confidence set, to improve the comfort of the target animal.

[0067] The various modules in the aforementioned air conditioner can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independently of it, or stored in the air conditioner's memory in software form, so that the processor can invoke and activate the corresponding operations of each module. It should be noted that the above module division is illustrative and represents only a logical functional division; in actual implementation, other division methods may be used.

[0068] Based on the aforementioned embodiments of the air conditioning control method, in another embodiment provided in this application, an air conditioner is provided, the internal structure of which can be shown in the diagram below. Figure 4 As shown, the air conditioner includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When the computer program is activated by the processor, it implements an air conditioner control method.

[0069] Those skilled in the art will understand that Figure 4The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the air conditioner to which the present application is applied. A specific air conditioner may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0070] Based on the aforementioned embodiments of the air conditioning control method, in another embodiment provided in this application, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is opened by a processor, it implements the steps in the above-described method embodiments.

[0071] Based on the aforementioned embodiments of the air conditioning control method, in another embodiment provided in this application, a computer program product is provided, including a computer program that, when activated by a processor, implements the steps in the above-described method embodiments.

[0072] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitation, the presence of other identical or equivalent elements in a process, method, product, or apparatus that includes said elements is not excluded. For example, the use of terms such as "first," "second," etc., is to denote names and does not indicate any specific order.

[0073] When used herein, the singular forms of “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising / including” or “having,” etc., specify the presence of the stated features, wholes, steps, operations, components, parts, or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof. Meanwhile, in this specification, the term “and / or” includes any and all combinations of the associated listed items.

[0074] In the description of this application, the references to terms such as "some embodiments," "other embodiments," "ideal embodiments," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example that are included in at least one embodiment or example of the present invention. In this specification, the illustrative descriptions of the above terms do not necessarily refer to the same embodiments or examples.

[0075] It is understood that the various embodiments of the methods described in this specification are presented in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. Relevant details can be found in the descriptions of other method embodiments.

[0076] It should be understood that the above embodiments are exemplary and are not intended to encompass all possible implementations included in the claims. Various modifications and changes can be made to the above embodiments without departing from the scope of this application. Similarly, the various technical features of the above embodiments can be arbitrarily combined to form other embodiments of this application that may not be explicitly described. Therefore, the above embodiments only illustrate several implementations of this application and do not limit the scope of protection of this patent application.

Claims

1. A method for controlling an air conditioner, characterized in that, The method includes: Acquire multi-source information about the target animal; the multi-source information includes radar data, image data, and sound data; Based on the multi-source information, a first confidence set is determined; the first confidence set includes N preset state confidences; each preset state confidence is used to characterize the probability that the target animal is in each preset state in the preset state set; N is the number of preset states included in the preset state set; the preset state set includes heatstroke state, hot state, cold state, and sleeping state; Based on preset adjustment rules and according to a determined first confidence level set, the air conditioning operating parameters are adjusted to improve the comfort of the target animal.

2. The control method according to claim 1, characterized in that, The step of determining the first confidence set based on the multi-source information includes: Preset judgment features are extracted from the multi-source information; the preset judgment features include the target animal's position, movement trajectory, posture information, and sound feature vector; The preset judgment features are time-aligned; The aligned preset judgment features are input in parallel into N preset attention models to obtain the N preset state confidence scores; the preset attention models correspond one-to-one with the preset state confidence scores.

3. The control method according to claim 1, characterized in that, The step of adjusting the air conditioning operating parameters based on preset adjustment rules and a determined first confidence level set to improve the comfort of the target animal includes: When at least one target confidence level exists among the N preset state confidence levels, the target operating parameters of the air conditioner are determined from the N sets of preset operating parameters according to the preset safety priority and the target confidence level; wherein, the target confidence level is a preset state confidence level with a confidence level greater than or equal to a first preset threshold; the preset operating parameters correspond one-to-one with the preset state confidence levels; When the confidence levels of all N preset states are less than the first preset threshold and greater than or equal to the second preset threshold, the target operating parameters are calculated according to at least two of the N preset state confidence levels based on a preset weighted calculation rule; the second preset threshold is less than the first preset threshold. Adjust the current operating parameters of the air conditioner to the target operating parameters.

4. The control method according to claim 3, characterized in that, The air conditioner operating parameters include the set temperature; the preset weighted calculation rules include the following formula: T1=T0-TX*(A1*C1+A2*C2-A3*C3+A4*C4) / Ca1 Wherein, T1 is the target set temperature; T0 is the current set temperature; TX is the preset temperature adjustment step size; A1 is the first weighting coefficient; C1 is the preset state confidence level corresponding to the heatstroke state; A2 is the second weighting coefficient; C2 is the preset state confidence level corresponding to the hot state; A3 is the third weighting coefficient; C3 is the preset state confidence level corresponding to the cold state; A4 is the fourth weighting coefficient; C4 is the preset state confidence level corresponding to the sleep state; and Ca1 is the sum of the four confidence levels C1, C2, C3, and C4.

5. The control method according to claim 4, characterized in that, The first weight coefficient to the fourth weight coefficient are obtained based on the first learning model; the first learning model is trained based on the historical adjustment data of the air conditioner.

6. The control method according to claim 3, characterized in that, The preset state set also includes an anxiety state; the air conditioning operating parameters also include a set fan speed; the preset weighted calculation rule includes the following formula: V1=V0+VX*(A5*C1+A6*C2-A7*C3-A8*C4-A9*C5) / Ca2 Wherein, V1 is the target set wind speed; V0 is the current set wind speed; VX is the preset wind speed adjustment step size; A5 is the fifth weighting coefficient; C1 is the preset state confidence level corresponding to the heatstroke state; A6 is the sixth weighting coefficient; C2 is the preset state confidence level corresponding to the hot state; A7 is the seventh weighting coefficient; C3 is the preset state confidence level corresponding to the cold state; A8 is the eighth weighting coefficient; C4 is the preset state confidence level corresponding to the sleep state; A9 is the ninth weighting coefficient; C5 is the preset state confidence level corresponding to the anxiety state; and Ca2 is the sum of the five confidence levels C1, C2, C3, C4, and C5.

7. The control method according to any one of claims 1-6, characterized in that, The method further includes: When the confidence levels of the N preset states are all less than the third preset threshold, the air conditioner is controlled to operate according to the preset safe operating parameters and an alarm command is executed.

8. An air conditioner, characterized in that, include: The acquisition module is used to acquire multi-source information about the target animal; The multi-source information includes radar data, image data, and sound data; The determination module is used to determine a first confidence set based on the multi-source information; the first confidence set includes N preset state confidences; each preset state confidence is used to characterize the probability that the target animal is in each preset state in the preset state set; N is the number of preset states included in the preset state set; the preset state set includes heatstroke state, hot state, cold state and sleeping state; The adjustment module is used to adjust the air conditioning operating parameters based on preset adjustment rules and a determined first confidence level set, so as to improve the comfort of the target animal.

9. An air conditioner, comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images