Intelligent control method, device and equipment for battery energy consumption of pet-finding car

Abstract

The present invention relates to the field of pet care technology, solves the problem that pets cannot be accurately positioned and monitored in the prior art, and the energy utilization rate of pet positioning and tracking equipment is poor, and provides a method, device and equipment for intelligent battery energy consumption control of a pet-finding car. The method includes: obtaining multiple frames of real-time images captured by a camera on a pet-care car in a pet-care scenario; inputting each frame of the real-time image into a pre-trained pet target detection model, and outputting the pet detection result; using image processing technology or UWB positioning technology to track the pet target, and adjusting the real-time state of the car through tracking information; analyzing the real-time state of the pet to determine the pet state information; adaptively adjusting the data transmission frequency, and transmitting data through the adjusted target frequency. The present invention realizes efficient, flexible and energy-saving positioning and care of pets, greatly improving the quality of pet care services and user experience.

Description

Technical Field

[0001] The present invention relates to the field of pet care technology, and in particular to a method, device and equipment for intelligently controlling battery energy consumption of a pet-finding vehicle. Background Art

[0002] With the development of society and the improvement of living standards, more and more people choose to keep pets for emotional comfort and companionship. Pets, especially dogs and cats, have become an indispensable member of many families. This trend not only reflects people's pursuit of quality of life, but also reflects the importance of animal welfare and the status of companion animals in modern society. In addition, as people's understanding of pets deepens, the social status of pets is also constantly improving. Positioning and tracking pets and analyzing their status are very important to ensure the safety and health of pets. Positioning and tracking enable pet owners to understand the location of their pets in real time and prevent them from getting lost. At the same time, monitoring the status of pets not only helps to assess the physical health of pets, such as exercise volume and rest patterns, but also provides important clues to the emotional state of pets, such as signs of anxiety or depression. This monitoring can guide pet owners to adjust their pets' daily activities and environment to promote their physical and mental health. Furthermore, it is very necessary to adjust the energy power of its positioning and tracking equipment according to the status of the pet. This adjustment can significantly improve the energy efficiency and endurance of the equipment, thereby ensuring that the pet can be effectively monitored at any time.

[0003] The existing Chinese patent CN110100757A discloses an LED luminous pet collar with a positioning function, comprising: a collar strap, a positioning box, a flexible curved LCD screen, a colorful light strip and a collar electromagnetic lock, wherein two anti-cut lines are buried near the edge of the collar strap along its length, and the positioning box and the colorful light strip are installed on the outside of the collar strap, wherein: an MCU microcontroller, a lithium battery, a UWB chip, a GPS chip and a communication chip are arranged in the positioning box, the lithium battery is connected to the power supply port of the MCU microcontroller through a voltage drop module, and the UWB chip, the GPS chip and the communication chip are all connected to the serial port of the MCU microcontroller. Although the above patent discloses a UWB receiver with a total of 3 antennas, the receiver is installed flat on the car; the UWB transmitter is used to transmit non-sinusoidal narrow pulses with a frequency bandwidth of more than 1GHz, which is installed on the neck of the pet. That is to say, although the above patent discloses the content of monitoring pets through UWB positioning technology, it does not disclose the content of energy management of positioning and tracking devices. However, due to the small size of positioning and tracking devices, they usually rely on built-in batteries for power supply. Energy saving can significantly extend battery life, reduce the number of charging times, and ensure that the device can continue to work when necessary, especially when the pet is lost. This is crucial for pet owners because they rely on these devices to keep in touch with and monitor their pets; at the same time, by optimizing energy use and reducing battery consumption, it can directly reduce Waste batteries and electronic waste, thereby reducing the impact on the environment. Improper handling of batteries and electronic devices can lead to the release of harmful substances into the environment, damaging land and water resources; on the other hand, energy saving can not only extend the service life of the device, but also reduce the pet owner's spending on batteries or power. In the long run, this means that users can save a considerable amount of money, making the use of pet positioning and tracking devices more economical; the improvement of device energy efficiency means that pet owners do not need to charge or replace batteries frequently, which greatly improves the user experience, especially for those who often take their pets out for activities, it is very important to ensure that the device works for a long time; and, low-power design often means that the device generates low heat during operation, which can reduce device failures caused by overheating and improve the stability and reliability of the device.

[0004] Therefore, how to accurately locate and monitor pets and achieve effective energy management of pet positioning and tracking devices are urgent issues to be solved. Summary of the invention

[0005] In view of this, the present invention provides a method, device and equipment for intelligently controlling battery energy consumption of a pet-finding car, so as to solve the problem in the prior art that pets cannot be accurately located and monitored, and the energy utilization rate of pet positioning and tracking equipment is poor.

[0006] The technical solution adopted by the present invention is:

[0007] In a first aspect, the present invention provides a method for intelligently controlling battery energy consumption of a pet-finding vehicle, the method comprising:

[0008] S1: obtaining real-time video data collected by a camera on a pet care cart in a pet care scene, and decomposing the real-time video data into multiple frames of real-time images;

[0009] S2: Inputting the real-time image of each frame into a pre-trained pet target detection model, and outputting a pet detection result;

[0010] S3: According to the pet detection result, the pet target is tracked by using image processing technology or UWB positioning technology, and the real-time state of the car is adjusted according to the tracking information;

[0011] S4: Analyze the real-time state of the pet according to the real-time state of the car to determine the pet state information;

[0012] S5: Adaptively adjust the data transmission frequency according to the pet status information, and transmit data at the adjusted target frequency.

[0013] Preferably, S3 includes:

[0014] S31: If a pet is detected, a preset target tracking algorithm is used to track the pet target in the real-time image to obtain the pet target position information;

[0015] S32: Obtain image size information corresponding to the real-time image, and determine whether the pet target is within a preset area based on the image size information and the pet target position information;

[0016] S33: If the pet target is within the preset area, the real-time state of the car is adjusted to a stationary state;

[0017] S34: If the pet target is not in the preset area, the real-time state of the car is adjusted to a moving state.

[0018] Preferably, the S3 further includes:

[0019] S35: If it is detected that there is no pet, the pet target is tracked through UWB positioning to obtain the real-time relative distance of the pet target with respect to the nursing car;

[0020] S36: Determine the tracking distance interval according to a preset tracking distance threshold;

[0021] S37: If the real-time relative distance is within the tracking distance interval, adjusting the real-time state of the vehicle to a stationary state;

[0022] S38: If the real-time relative distance is not within the tracking distance interval, the real-time state of the vehicle is adjusted to a moving state.

[0023] Preferably, the S4 includes:

[0024] S41: If the real-time state of the car is static, the real-time location information of the pet is obtained through target tracking algorithm or UWB positioning;

[0025] S42: obtaining the displacement of the pet within a preset time window according to the real-time position information of the pet;

[0026] S43: Calculating a real-time index related to the pet state according to the displacement and the time window;

[0027] S44: Compare the real-time index with a preset index threshold, and divide the real-time index into a pet stillness index and a pet movement index.

[0028] Preferably, the S4 further includes:

[0029] S45: Obtaining the real-time relative distance of the pet target to the care cart and a preset threshold of the distance from home;

[0030] S46: comparing the real-time relative distance with the distance-from-home threshold, and when the real-time relative distance is greater than the preset distance-from-home threshold, determining that the pet has left home;

[0031] S47: When it is determined that the pet has left home, the real-time distance of the pet from home is obtained.

[0032] Preferably, the S5 includes:

[0033] S51: Obtaining original data transmission frequency;

[0034] S52: If the real-time index is the pet stillness index, calculating the target frequency according to the original data transmission frequency and the pet stillness index;

[0035] S53: If the real-time index is a pet exercise index, obtaining a preset pet exercise quantification coefficient and a user-preset personalized demand parameter;

[0036] S54: Calculate the target frequency according to the pet exercise index, the pet exercise quantification coefficient and the personalized demand parameter.

[0037] Preferably, the S5 further includes:

[0038] S55: If it is determined that the pet has left home, the original data transmission frequency and the real-time distance of the pet from home are obtained;

[0039] S56: Calculate the target frequency according to the original data transmission frequency and the real-time distance of the pet from home.

[0040] In a second aspect, the present invention provides a battery energy consumption intelligent control device for a pet-finding vehicle, the device comprising:

[0041] An image acquisition module is used to acquire real-time video data collected by a camera on a pet care cart in a pet care scenario, and decompose the real-time video data into multiple frames of real-time images;

[0042] A pet target detection module, used for inputting each frame of the real-time image into a pre-trained pet target detection model and outputting a pet detection result;

[0043] A pet target tracking and car adjustment module is used to track the pet target according to the pet detection result and adjust the real-time state of the car through the tracking information;

[0044] A pet real-time status analysis module is used to analyze the real-time status of the pet according to the real-time status of the vehicle and determine the pet status information;

[0045] The frequency adjustment module is used to adaptively adjust the data transmission frequency according to the pet status information, and transmit data through the adjusted target frequency.

[0046] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, which, when executed by the processor, implement the method of the first aspect in the above-mentioned embodiment.

[0047] In a fourth aspect, an embodiment of the present invention further provides a storage medium on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method of the first aspect in the above-mentioned embodiment is implemented.

[0048] In summary, the beneficial effects of the present invention are as follows:

[0049] The present invention provides a method, device and equipment for intelligently controlling battery energy consumption of a pet-finding car, the method comprising: obtaining real-time video data collected by a camera on a pet-finding car in a pet-finding scene, and decomposing the real-time video data into multiple frames of real-time images; inputting each frame of the real-time image into a pre-trained pet target detection model, and outputting a pet detection result; based on the pet detection result, using image processing technology or UWB positioning technology, tracking the pet target, and adjusting the real-time state of the car through tracking information; based on the real-time state of the car, analyzing the real-time state of the pet, and determining the pet state information; based on the pet state information, adaptively adjusting the data transmission frequency, and transmitting data through the adjusted target frequency. The present invention provides a highly intelligent, automated and efficient solution for pet care by combining real-time video data acquisition, advanced pet target detection models, image processing or UWB positioning technology, and adaptive data transmission frequency adjustment. First, real-time video is collected by a camera and decomposed into multiple frames of images, and accurate pet detection is performed using a pre-trained pet target detection model. This step greatly improves the accuracy and efficiency of pet recognition. Subsequently, according to the detection results, the image processing technology or UWB positioning technology is used to track the pet in real time, which can not only accurately grasp the location information of the pet, but also adjust the real-time status of the care cart through the tracking information to ensure that the cart can effectively follow or monitor the pet. In addition, according to the real-time status analysis of the pet, the data transmission frequency is adaptively adjusted, which not only guarantees the demand for real-time monitoring, but also optimizes energy consumption and data processing burden, and improves the overall efficiency and economy. Through the strategy of adaptively adjusting the data transmission frequency, the relationship between real-time and resource consumption is delicately balanced, thereby optimizing energy consumption and data processing burden, reducing unnecessary energy consumption and data processing work, which not only extends the endurance of the equipment and reduces energy costs, but also reduces the load of data storage and processing equipment, and improves the overall efficiency and economy of the system. In general, the present invention realizes efficient, flexible and energy-saving care for pets through technical integration and intelligent management, greatly improving the quality of pet care services and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the drawings required for use in the embodiment of the present invention will be briefly introduced below. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work, and these are all within the protection scope of the present invention.

[0051] Figure 1 It is a schematic diagram of the overall working process of the battery energy consumption intelligent control method of the pet-finding car in Example 1 of the present invention;

[0052] Figure 2It is a schematic diagram of a process of adjusting the state of the vehicle by tracking information when the presence of a pet is detected in Embodiment 1 of the present invention;

[0053] Figure 3 It is a schematic diagram of a process of adjusting the state of the vehicle by tracking information when detecting that no pet exists in Embodiment 1 of the present invention;

[0054] Figure 4 This is a schematic diagram of a process for obtaining a real-time index related to a pet's status in Embodiment 1 of the present invention;

[0055] Figure 5 This is a schematic diagram of a process for obtaining the real-time distance of a pet from home in Embodiment 1 of the present invention;

[0056] Figure 6 Schematic diagram of a process for calculating a target frequency according to a real-time index in Embodiment 1 of the present invention;

[0057] Figure 7 This is a flow chart of calculating the target frequency according to the real-time distance of the pet from the home in Embodiment 1 of the present invention;

[0058] Figure 8 This is a structural block diagram of the battery energy consumption intelligent control device of the pet-finding car in Example 3 of the present invention;

[0059] Fig. 9 It is a schematic diagram of the structure of an electronic device in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described in conjunction with the drawings in the embodiment of the present invention. It should be noted that, in this article, relational 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. In the description of the present invention, it should be understood that the orientation or position relationship indicated by the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. Moreover, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such a process, method, article or device. In the absence of further restrictions, the elements defined by the phrase "comprising..." do not exclude the existence of other identical elements in the process, method, article or device comprising the elements. If there is no conflict, the embodiments of the present invention and the various features in the embodiments can be combined with each other, all within the protection scope of the present invention. Example

[0061] See also Figure 1 Embodiment 1 of the present invention discloses a method for intelligently controlling battery energy consumption of a pet-finding vehicle, the method comprising:

[0062] S1: obtaining real-time video data collected by a camera on a pet care cart in a pet care scene, and decomposing the real-time video data into multiple frames of real-time images;

[0063] Specifically, first, obtain the video data of the pet care scene collected in real time by the camera installed on the care cart, which can capture the pet's dynamic position, behavioral habits and interaction with the surrounding environment; decompose the received video data into a series of continuous image frames, each of which represents a static picture in the video. Through this process, real-time video data is converted into image data that can be further analyzed and processed, which provides a basis for subsequent pet target detection, behavior analysis and automatic adjustment of the care cart, making pet care more intelligent and automated, and able to respond to changes in the pet's status in real time, effectively improving the quality and efficiency of care.

[0064] S2: Inputting the real-time image of each frame into a pre-trained pet target detection model, and outputting a pet detection result;

[0065] Specifically, each frame of real-time image is input into a pre-trained pet target detection model, for example, the pet target detection model is a cat and dog detection model based on the YoloV8s architecture. Yolo is a popular target detection algorithm with fast and accurate detection capabilities, and YoloV8s is a newer version in this series, optimized for speed and efficiency, and is very suitable for running on resource-constrained devices, such as mobile platforms such as pet care carts. In this process, continuous frames of real-time images are obtained by decomposing real-time video data, and then each frame of real-time image is sent to the pre-trained YoloV8s model, which has been trained to recognize and distinguish cats and dogs in the image. When each frame of real-time image is input into the model, YoloV8s analyzes the image content through its deep neural network structure to detect the position, size and category (cat or dog) of the pet in the image. The results output by the model usually include a bounding box of each detected pet (identifying the specific position and range of the pet) and a confidence score (indicating the model's confidence in the accuracy of the detection result). This information is crucial for subsequent tracking and analysis because it provides the precise location and identification information of the pet, enabling the care cart to effectively track and monitor the pet and achieve real-time dynamic monitoring and care. The benefit of using the YoloV8s cat and dog detection model is its fast processing speed and high accuracy, which means that even when the pet moves quickly or the environment is complex, it can accurately identify and track the pet in real time, ensuring the safety of the pet and reducing the risk of disappearance. In addition, because YoloV8s is designed for efficient performance, it also helps to optimize the battery usage of the care cart and extend the working time.

[0066] S3: According to the pet detection result, the pet target is tracked by using image processing technology or UWB positioning technology, and the real-time state of the car is adjusted according to the tracking information;

[0067] Specifically, according to the pet detection results of the YoloV8s model, the pet detection results are divided into the target pet being detected and the target pet not being detected. Image processing technology is used for pet tracking between consecutive frames. The image processing technology includes an optical flow method or a deep learning method. The image processing technology can continuously track the position and movement trajectory of the pet in each frame of real-time image according to the pet's morphology and movement characteristics; at the same time, according to the pet detection results, UWB positioning technology can also be used. Since the pet wears a UWB tag, the distance between the pet tag and the UWB receiver is measured to accurately calculate the position of the pet. UWB technology is known for its high precision and anti-interference ability. It is particularly suitable for precise positioning in indoor environments and complex terrains. According to the position and movement trajectory of the pet, the control system of the nursing car will adjust its direction of action, speed and stop position in real time. For example, if the pet moves to the other side of the park, the car will automatically adjust its route to follow the pet to ensure that the pet is always within the monitoring range; the real-time position and status information of the pet is continuously fed back through the car's sensors and cameras to form a closed-loop control mechanism, so that the car can flexibly respond to the pet's behavioral changes and potential safety threats. This tracking method that combines image processing and UWB positioning technology not only improves the accuracy and response speed of pet monitoring, but also increases flexibility and reliability. By adjusting the state of the car in real time to adapt to the dynamic changes of the pet, it can effectively protect the safety of the pet, reduce the risk of the pet getting lost, and provide a more free and open activity space for the pet.

[0068] In one embodiment, see Figure 2 , said S3 comprises:

[0069] S31: If a pet is detected, a preset target tracking algorithm is used to track the pet target in the real-time image to obtain the pet target position information;

[0070] Specifically, if a pet is detected, the preset target tracking algorithm DeepSort is used to track the pet target in the real-time image to obtain the location information of the pet target. The DeepSort algorithm is an efficient tracking algorithm designed specifically for processing target tracking in video sequences. It combines deep learning and traditional sorting algorithms to achieve high-precision target tracking. In this process, the pet target is defined as a rectangular box R (x, y, w, h), where x and y represent the coordinates of the upper left corner of the rectangular box, and w and h represent the width and height of the pet target detection box, respectively. When the YoloV8s model detects the pet, the DeepSort algorithm takes over and uses the detected pet as the initial tracking target. DeepSort tracks the position change of the pet by combining the appearance information and motion information of the target. The appearance information is extracted by the deep learning model to help the algorithm identify the same pet in different frames, while the motion information is obtained by predicting the position change of the pet between consecutive real-time image frames. During the tracking process, the algorithm continuously updates the pet's position R (x, y, w, h) to reflect the real-time position of the pet in the video. By tracking the location information of the pet target in real time, important data is provided for subsequent behavior analysis and status monitoring. The advantage of DeepSort lies in its high robustness to occlusion processing and identity switching, which enables it to perform well in complex pet care scenarios. It can effectively track the dynamic position of pets and maintain high tracking accuracy even when the pet moves quickly or there is occlusion in the picture.

[0071] S32: Obtain image size information corresponding to the real-time image, and determine whether the pet target is within a preset area based on the image size information and the pet target position information;

[0072] Specifically, the real-time image and its size information are obtained, and the pet is judged whether it is located in the preset area according to the size information of the image and the location information of the pet target. This process involves accurate calculation and analysis of the location and size of the pet target to ensure that the monitoring of the pet is not only based on its location, but also takes into account its proportion in the picture; first, according to the location information R(x, y, w, h) of the pet target, the location x+w / 2 of the pet center point is calculated, and it is compared with the width img_width of the image in the size information to ensure that the pet center point is located in the 35% to 65% area around the center of the image. This condition is intended to ensure that the pet is located in the central area of ​​the picture to avoid the pet being at the edge of the picture and difficult to observe and monitor. At the same time, by calculating the area w×h of the pet target and comparing it with 0.05 times and 0.3 times of the total area img_width×img_height of the image, it is determined whether the size of the pet is within a reasonable range. This step is intended to ensure that the pet target is neither too small (which may mean that the pet is too far from the camera or is misdetected) nor too large (which may mean that the pet is too close to the camera or a too large pet image appears in the picture).

[0073] S33: If the pet target is within the preset area, the real-time state of the car is adjusted to a stationary state;

[0074] S34: If the pet target is not in the preset area, the real-time state of the car is adjusted to a moving state.

[0075] Specifically, if the pet target is within the preset area, the car is kept stationary; if the pet does not meet the above conditions, that is, the pet target is not within the preset area or the size does not meet the preset range, the car is controlled to move accordingly, including changing the position of the car to reposition the pet to the central area of ​​the screen, or adjusting the distance between the car and the pet to ensure that the size of the pet image meets the preset range. This design not only ensures the real-time monitoring effect of the pet, but also optimizes the movement strategy of the car, ensuring that the car can effectively track and maintain an appropriate distance, thereby ensuring the safety of the pet while minimizing unnecessary movement and energy consumption.

[0076] In one embodiment, see Figure 3 , the S3 further includes:

[0077] S35: If it is detected that there is no pet, the pet target is tracked through UWB positioning to obtain the real-time relative distance of the pet target with respect to the nursing car;

[0078] Specifically, when it is detected that there is no pet, the pet target is tracked through UWB positioning, and the distance information of the pet relative to the nursing cart is obtained in real time. In this process, the layout and calculation of the UWB receiver and transmitter and the processing of the positioning unit are all key components. First, the UWB receiver is installed with a total of 3 antennas, which are placed flat on the nursing cart. The UWB transmitter is installed on the neck of the pet to transmit non-sinusoidal narrow pulses with a frequency bandwidth of more than 1GHz. The UWB data calculation and positioning unit mainly uses the time difference positioning (TDoA) algorithm to process the UWB signal and calculate the three-dimensional coordinates of the pet relative to the cart P{UWB}=(x{UWB},y{UWB},z{UWB}), where the TDoA algorithm establishes a nonlinear set of equations based on the time difference of the signals received by the three antennas. The form of the equation group is:

[0079]

[0080] By solving the above nonlinear equations, the three-dimensional coordinates of the pet relative to the nursing car are obtained, that is, the real-time relative distance relative to the nursing car. This UWB positioning method has high precision and real-time performance, and is suitable for the needs of accurately tracking the position of pets in pet care scenarios. Through such positioning means, even if the pet is not detected, the pet can still be tracked in real time, ensuring the effective monitoring and care of the pet by the nursing car.

[0081] S36: Determine the tracking distance interval according to a preset tracking distance threshold;

[0082] Specifically, when tracking a pet, an effective tracking distance Tra_dis is first preset. Next, the threshold interval of the tracking distance is determined based on the preset distance, that is, between 0.9*Tra_dis and 1.1*Tra_dis. This process aims to ensure that the car maintains a suitable distance from the pet in order to effectively monitor and protect the pet.

[0083] S37: If the real-time relative distance is within the tracking distance interval, adjusting the real-time state of the vehicle to a stationary state;

[0084] S38: If the real-time relative distance is not within the tracking distance interval, the real-time state of the vehicle is adjusted to a moving state.

[0085] In the UWB real-time positioning and tracking of step S35, the real-time relative distance D of the pet relative to the nursing car is obtained through UWB positioning; the real-time relative distance is compared with the preset distance threshold interval. If the real-time relative distance is between 0.9*Tra_dis and 1.1*Tra_dis, it is considered that the distance between the car and the pet is within the effective tracking range. At this time, the real-time state of the car is adjusted to a stationary state, that is, the movement of the car is stopped to ensure that the relative distance between the pet and the car is within a suitable range and will not be too close or too far away; on the contrary, if the real-time relative distance is not within the preset distance threshold interval, it is considered that the car needs to continue to move to maintain effective pet tracking. In this case, the system will adjust the real-time state of the car to a moving state to ensure that the car can follow the movement of the pet in time and maintain a suitable distance. Through this process, while constantly monitoring the real-time relative distance, the movement state of the car is intelligently adjusted so that it can adapt to the behavioral changes of the pet, ensure the safety of the pet, and effectively track when needed. This dynamic adjustment strategy enables the nursing car to flexibly respond to various pet activities, which not only guarantees the free movement of the pet, but also ensures the timeliness and effectiveness of the care.

[0086] S4: Analyze the real-time state of the pet according to the real-time state of the car to determine the pet state information;

[0087] Specifically, based on the real-time status of the car, the system analyzes the real-time status of the pet to determine the pet's status information. This process involves monitoring and evaluating the pet's position, movement, distance, and possible behavioral changes. By analyzing the real-time status of the car, the system can obtain the pet's current situation, such as whether the pet is moving, staying in a certain position, or keeping a safe distance from the car. Such status information is of great significance for timely adjusting the car's movement strategy, providing real-time alarms, or recording the pet's activity patterns, thereby enhancing the intelligence and personalized services of the pet care system.

[0088] In one embodiment, see Figure 4 , said S4 comprises:

[0089] S41: If the real-time state of the car is static, the real-time location information of the pet is obtained through target tracking algorithm or UWB positioning;

[0090] S42: obtaining the displacement of the pet within a preset time window according to the real-time position information of the pet;

[0091] Specifically, based on the pet's real-time position information, the displacement of the pet within a preset time window is calculated. This is achieved by calculating the difference between consecutive position information within the time window, namely Δdt, where dt represents the time difference between two consecutive time points, and Δdt represents the displacement of the pet during this period of time.

[0092] S43: Calculating a real-time index related to the pet state according to the displacement and the time window;

[0093] Specifically, based on the calculated displacement and the preset time window length, the real-time index related to the pet state is calculated. For the real-time index, it is the ratio of the pet's movement to the time window length, and the formula is index=(Δd1+Δd2+Δd3+...+ΔdT-1) / T, where Δdt is the displacement difference of the pet between time t and t-1, and T is the time window length.

[0094] S44: Compare the real-time index with a preset index threshold, and divide the real-time index into a pet stillness index and a pet movement index.

[0095] Specifically, the calculated real-time index is compared with the preset index threshold, and the real-time index is divided into two categories: pet stillness index Sindex and pet movement index Aindex. Specifically, when the index is lower than the preset threshold S_th, the pet is considered to be in a still state, and this is the stillness index Sindex. The smaller the Sindex value, the higher the stillness of the pet; and for the activity index Aindex not lower than the preset threshold S_th, it indicates that the pet is in an active state, and the larger the Aindex, the higher the activity of the pet. Such an analysis process enables the system to understand the pet's movement status in real time, providing an important basis for subsequent decision-making and adjustments.

[0096] In one embodiment, see Figure 5 , the S4 further comprises:

[0097] S45: Obtaining the real-time relative distance of the pet target to the care cart and a preset threshold of the distance from home;

[0098] Specifically, UWB positioning is used to obtain the real-time relative distance of the pet target to the nursing car, and at the same time obtain the preset distance threshold from home. This is to monitor the distance between the pet and the nursing car in real time and provide necessary information for subsequent judgment of the away-from-home status.

[0099] S46: comparing the real-time relative distance with the distance-from-home threshold, and when the real-time relative distance is greater than the preset distance-from-home threshold, determining that the pet has left home;

[0100] Specifically, the obtained real-time relative distance is compared with the preset distance threshold. When the real-time relative distance is greater than the preset distance threshold, the system determines that the pet is away from home. The distance threshold (L_th) here is set comprehensively based on factors such as the actual length and width of the building, aiming to ensure that the pet is judged as away from home when it is outside the specified distance range.

[0101] S47: When it is determined that the pet has left home, the real-time distance of the pet from home is obtained.

[0102] Specifically, when the system determines that the pet is away from home, the real-time distance of the pet from home is obtained. This distance information provides real-time feedback for tracking the degree of the pet's departure from home and possible activity areas. By monitoring the real-time distance from home, it can respond accordingly when the pet is away from the care cart, such as sending an alarm notification or adjusting the car's movement strategy to ensure the pet's safety. By real-time monitoring the distance between the pet and the care cart, the pet's departure status can be flexibly determined, and the real-time distance of the pet from home can be obtained in a timely manner, so that the system can take appropriate measures when necessary to ensure timely monitoring and protection of the pet.

[0103] S5: Adaptively adjust the data transmission frequency according to the pet status information, and transmit data at the adjusted target frequency.

[0104] Specifically, according to the obtained pet status information, an intelligent data transmission frequency adaptive adjustment mechanism is implemented, which is specifically applied to the UWB data transmission frequency. By monitoring the pet's activity status, location information, etc., the pet's current needs and the degree of response to real-time monitoring can be identified. Based on this pet status information, the frequency of UWB data transmission is dynamically adjusted to optimize the frequency of data transmission to the most appropriate level; first, the pet status information, such as the pet's exercise intensity, relative position, etc., is collected and analyzed, and then, based on the obtained information, the urgency and real-time requirements of the current monitoring needs are evaluated. Based on these evaluations, the UWB data transmission frequency is automatically adjusted to make it more in line with the needs of the current scenario; if the pet is active or away from home, the data transmission frequency is increased to update the pet's location and status information in real time. On the contrary, if the pet is stationary or near home, the data transmission frequency is reduced to save energy and reduce the data processing burden. Through this adaptive adjustment mechanism, the UWB data transmission frequency is flexibly controlled in different scenarios, which not only ensures the real-time requirements, but also effectively reduces energy consumption. This intelligent data transmission frequency adjustment method effectively balances the real-time and energy efficiency of the monitoring system, and improves the overall performance and user experience of the system.

[0105] In one embodiment, see Figure 6 , the S5 comprises:

[0106] S51: Obtaining original data transmission frequency;

[0107] S52: If the real-time index is the pet stillness index, calculating the target frequency according to the original data transmission frequency and the pet stillness index;

[0108] Specifically, the original data transmission frequency is first obtained. When the pet is detected to be stationary, the new target transmission frequency is calculated based on the original data transmission frequency and the pet's stationary index. This intelligent frequency adjustment mechanism aims to optimize the data transmission frequency in real time according to the pet's activity status to achieve a balance between energy saving and system performance. Specifically, when the pet is detected to be stationary, the UWB data transmission frequency is automatically reduced according to the following formula to reduce energy consumption:

[0109]

[0110] When the pet inactivity index value is smaller, it means that the pet is in a low activity state. At this time, the UWB transmission frequency is reduced accordingly to achieve energy saving. The advantage of this solution is that it intelligently adjusts the UWB data transmission frequency according to the real-time monitored pet status information, avoiding unnecessary high-frequency transmission when the pet is in a static state, thereby reducing energy consumption. Through this adaptive frequency adjustment, the system optimizes the energy efficiency of the system to the greatest extent while ensuring real-time monitoring, extending the service life of the equipment, and improving overall performance and sustainability.

[0111] S53: If the real-time index is a pet exercise index, obtaining a preset pet exercise quantification coefficient and a user-preset personalized demand parameter;

[0112] S54: Calculate the target frequency according to the pet exercise index, the pet exercise quantification coefficient and the personalized demand parameter.

[0113] Specifically, when the system detects that the pet is in motion (the real-time index is the pet's motion index), the UWB data transmission frequency will be intelligently adjusted according to the preset pet motion quantification coefficient and the personalized demand parameters set by the user, aiming to optimize the data transmission frequency in real time according to the pet's activity level and the user's personalized needs, so as to balance the needs of real-time monitoring and energy efficiency. Specifically, when the pet is detected to be in motion, the UWB data transmission frequency is intelligently adjusted through the following formula:

[0114]

[0115] By comprehensively considering the activity level of pets and the personalized needs of users, the system uses a dynamic frequency adjustment method to achieve intelligent management of UWB data transmission frequency. When the pet is active, the system will increase the data transmission frequency accordingly to ensure real-time monitoring; when the pet is relatively still, the system will reduce the data transmission frequency to reduce energy consumption. Through this intelligent adjustment mechanism, while meeting the personalized needs of users, it maximizes energy efficiency and overall performance.

[0116] In one embodiment, see Figure 7 , the S5 further includes:

[0117] S55: If it is determined that the pet has left home, the original data transmission frequency and the real-time distance of the pet from home are obtained;

[0118] S56: Calculate the target frequency according to the original data transmission frequency and the real-time distance of the pet from home.

[0119] Specifically, when the pet is detected to be away from home, an intelligent frequency adjustment scheme is adopted. The UWB data transmission frequency is updated according to the following formula to gradually decrease in order to save energy and reduce the frequency of data transmission:

[0120]

[0121] Through this intelligent adjustment, when the pet is away from home, the data transmission frequency can be flexibly adjusted according to the distance, achieving a balance between energy conservation and network resource utilization at different distances. This solution not only takes into account the pet's away state, but also makes full use of mathematical logic functions to make the frequency adjustment more flexible and accurate, providing important support for sustainability and efficiency. Example

[0122] In Example 1, if a pet target is detected in the image, the pet is tracked by the DeepSort tracking algorithm, and the movement of the car is controlled to keep the pet target always in the center area of ​​the image. However, in the actual application of pet-finding scenarios, pet targets are lively and active. Direct real-time tracking of lively and active pets will lead to high energy consumption, because the pet's rapid movement and unpredictable behavior activities will require constant adjustment of direction and speed, thereby increasing battery energy consumption. For this reason, Example 2 of the present invention, based on Example 1, further optimizes and reduces the energy consumption of the pet-finding car through the following scheme.

[0123] In one embodiment, the method further comprises:

[0124] Input each frame of real-time image into a pre-trained preset target detection model, and output a preset target detection result, wherein the preset targets include pet food, pet toys, and pet owners;

[0125] Specifically, first, you need to collect a large amount of image data containing preset targets and perform detailed annotations, such as creating a training dataset by marking the location and category of pet food, toys, and pet owners in the image. Then, select a deep learning framework and target detection model architecture, such as YOLO, SSD, or Faster. R-CNN, pre-trained models are usually trained on large-scale general datasets, such as ImageNet or COCO, to learn the basic feature representation of images; during the training process, the model is fine-tuned on the training dataset, and the model's weights are adjusted to optimize the recognition accuracy of preset targets such as pet food, toys, and owners. Fine-tuning enables the model to learn more specific and task-related features from general image features. In addition, after the model is fine-tuned, data enhancement is performed, such as image rotation, scaling, and cropping, to improve the generalization and robustness of the model. After fine-tuning, the model can recognize and locate pet food, toys, and pet owners on new images, and achieve effective detection of these preset targets. The model output by this training process has high accuracy and efficiency when processing real-time image streams, and is suitable for various application scenarios that require real-time target detection, such as pet monitoring systems, automatic feeders, and interactive toys. Each frame of real-time image is input into the above-mentioned pre-trained preset target detection model, and the preset target detection result is output, where the preset target detection result includes successful detection of the preset target and unsuccessful detection of the preset target.

[0126] If the preset target is successfully detected, the preset target location information and the preset pet-finding strategy are obtained;

[0127] Specifically, when the preset targets of the above-mentioned pet food, pet toys and pet owners are successfully detected, the position information of the preset targets is obtained. The preset target position information includes the precise coordinates and size of the preset target in the real-time image frame, that is, the bounding box of the preset target. The bounding box not only reveals the spatial position of the preset target, that is, the specific position of the preset target in the image, for example, the coordinates of the upper left corner and the lower right corner of the bounding box, but also indicates the physical size of the preset target, that is, the width and height it occupies in the image. The preset target position information is crucial for realizing an automated pet-finding car based on a preset pet-finding strategy. The preset pet-finding strategy involves analyzing the target position information and controlling the movement of the pet-finding car accordingly, so as to guide the car to the current actual position of the pet.

[0128] According to the pet-finding strategy, combined with the preset target location information and the pet location information, the car is controlled to track the pet target.

[0129] Specifically, for example, if pet food or toys are detected, it indicates that the pet will be attracted to the location of these items; if the location of the pet owner is identified, it is hoped that the pet will be guided to the owner's location; by analyzing the location information of these preset targets, the pet-finding car formulates the optimal path, automatically adjusts its direction and speed, and finally moves to the location of the pet safely and efficiently, achieving rapid pet-finding and return. For example, when the pet-finding car detects the location information of the pet toy, it analyzes the direction and distance of the pet toy target relative to the current location of the car, and uses an intelligent path planning algorithm, which includes the Dijkstra algorithm, the RRT algorithm, and deep reinforcement learning. The Dijkstra algorithm calculates the shortest path from each node to the starting point, but the computational complexity is high in large-scale graph structures; the RRT algorithm adopts a random exploration method, which is suitable for high-dimensional space, and expands the search space by randomly generating nodes; deep reinforcement learning uses deep learning methods to train intelligent agents to learn the best path selection strategy, which is suitable for complex and dynamic environments. In the smart pet-finding car, the selection of appropriate path planning algorithms depends on the specific application scenario and system requirements, such as considering environmental characteristics, real-time obstacle information and motion dynamics. The application of these algorithms helps the car to achieve fast, safe and energy-saving movement, improving the efficiency and adaptability of the system. The pet-finding car will develop the optimal path, avoid obstacles, and then automatically adjust the direction and speed of travel to move to the location of the pet toy in an efficient and safe manner. This automatic adjustment behavior can ensure that the pet-finding car quickly reaches the target with the shortest path, reducing energy consumption, while avoiding collisions or unnecessary steering movements, and improving operating efficiency. Through intelligent path planning and automatic adjustment of travel direction and speed, unnecessary energy waste can be minimized. Compared with blind movement or full-time real-time tracking, this accurate and efficient path planning makes the pet-finding car more intelligent and energy-saving in the process of finding pets. Reducing energy consumption not only helps environmental protection, but also extends the service life of the pet-finding car, improves the sustainability of the system, and provides pet owners with a more economical, efficient and environmentally friendly smart pet-finding service. Example

[0130] See also Figure 8 Embodiment 3 of the present invention further provides a battery energy consumption intelligent control device for a pet-finding vehicle, the device comprising:

[0131] An image acquisition module is used to acquire real-time video data collected by a camera on a pet care cart in a pet care scenario, and decompose the real-time video data into multiple frames of real-time images;

[0132] A pet target detection module, used for inputting each frame of the real-time image into a pre-trained pet target detection model and outputting a pet detection result;

[0133] A pet target tracking and car adjustment module is used to track the pet target according to the pet detection result and adjust the real-time state of the car through the tracking information;

[0134] A pet real-time status analysis module is used to analyze the real-time status of the pet according to the real-time status of the vehicle and determine the pet status information;

[0135] The frequency adjustment module is used to adaptively adjust the data transmission frequency according to the pet status information, and transmit data through the adjusted target frequency.

[0136] Specifically, the battery energy consumption intelligent control device of the pet-finding car provided by the embodiment of the present invention includes: an image acquisition module, which is used to acquire real-time video data collected by the camera on the pet-finding car in the pet-finding scene, and decompose the real-time video data into multiple frames of real-time images; a pet target detection module, which is used to input each frame of the real-time image into a pre-trained pet target detection model and output the pet detection result; a pet target tracking and car adjustment module, which is used to track the pet target according to the pet detection result, and adjust the real-time state of the car through the tracking information; a pet real-time state analysis module, which is used to analyze the real-time state of the pet according to the real-time state of the car and determine the pet state information; a frequency adjustment module, which is used to adaptively adjust the data transmission frequency according to the pet state information, and transmit data through the adjusted target frequency. This device provides a highly intelligent, automated and efficient solution for pet care by combining real-time video data acquisition, advanced pet target detection model, image processing or UWB positioning technology and adaptive data transmission frequency adjustment. First, the real-time video is collected by the camera and decomposed into multiple frames of images, and the pre-trained pet target detection model is used to perform accurate pet detection. This step greatly improves the accuracy and efficiency of pet identification. Subsequently, according to the detection results, the pet is tracked in real time using image processing technology or UWB positioning technology, which can not only accurately grasp the location information of the pet, but also adjust the real-time status of the care car through tracking information to ensure that the car can effectively follow or monitor the pet. In addition, according to the real-time status analysis of the pet, the data transmission frequency is adaptively adjusted, which not only guarantees the demand for real-time monitoring, but also optimizes energy consumption and data processing burden, and improves the overall efficiency and economy. Through the strategy of adaptively adjusting the data transmission frequency, the relationship between real-time and resource consumption is delicately balanced, thereby optimizing energy consumption and data processing burden, reducing unnecessary energy consumption and data processing work, which not only extends the endurance of the device and reduces energy costs, but also reduces the load of data storage and processing equipment, and improves the overall efficiency and economy of the system. In general, through technical integration and intelligent management, this device realizes efficient, flexible and energy-saving care for pets, greatly improving the quality of pet care services and user experience. Example

[0137] In addition, combined Figure 1 The method for intelligently controlling battery energy consumption of the pet-finding vehicle described in Embodiment 1 of the present invention may be implemented by an electronic device. Fig. 9 A schematic diagram of the hardware structure of an electronic device provided in Embodiment 4 of the present invention is shown.

[0138] The electronic device may include a processor and a memory storing computer program instructions.

[0139] Specifically, the processor may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.

[0140] The memory may include a large capacity memory for data or instructions. By way of example and not limitation, the memory may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory may include a removable or non-removable (or fixed) medium. Where appropriate, the memory may be inside or outside the data processing device. In a particular embodiment, the memory is a non-volatile solid-state memory. In a particular embodiment, the memory includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM) or a flash memory or a combination of two or more of these.

[0141] The processor implements any one of the battery energy consumption intelligent control methods of the pet-finding vehicle in the above-mentioned embodiments by reading and executing computer program instructions stored in the memory.

[0142] In one example, the electronic device may further include a communication interface and a bus. Fig. 9 As shown, the processor, memory, and communication interface are connected via a bus and communicate with each other.

[0143] The communication interface is mainly used to implement communication between the modules, devices, units and / or equipment in the embodiments of the present invention.

[0144] The bus includes hardware, software or both, and the components of the device are coupled to each other. For example, but not limitation, the bus may include an accelerated graphics port (AGP) or other graphics bus, an enhanced industrial standard architecture (EISA) bus, a front-side bus (FSB), a hypertransport (HT) interconnection, an industrial standard architecture (ISA) bus, an infinite bandwidth interconnection, a low pin count (LPC) bus, a memory bus, a microchannel architecture (MCA) bus, a peripheral component interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a serial advanced technology attachment (SATA) bus, a video electronics standard association local (VLB) bus or other suitable bus or a combination of two or more of these. Where appropriate, the bus may include one or more buses. Although the embodiments of the present invention describe and illustrate a specific bus, the present invention contemplates any suitable bus or interconnection. Example

[0145] In addition, in combination with the battery energy consumption intelligent control method of the pet-finding car in the above embodiment 1, the embodiment 5 of the present invention can also provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any of the battery energy consumption intelligent control methods of the pet-finding car in the above embodiments is implemented.

[0146] In summary, the embodiments of the present invention provide a method, device and equipment for intelligently controlling battery energy consumption of a pet-finding vehicle.

[0147] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0148] The functional blocks shown in the structural block diagram described above can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier. "Machine-readable medium" may include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0149] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in a different order from the embodiments, or several steps can be performed simultaneously.

[0150] The above is only a specific implementation of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be covered within the protection scope of the present invention.

Claims

1. A method for intelligently controlling battery energy consumption of a pet-finding vehicle, characterized in that: The method comprises: S1: obtaining real-time video data collected by a camera on a pet care cart in a pet care scene, and decomposing the real-time video data into multiple frames of real-time images; S2: Inputting the real-time image of each frame into a pre-trained pet target detection model, and outputting a pet detection result; S3: According to the pet detection result, the pet target is tracked by using image processing technology or UWB positioning technology, and the real-time state of the car is adjusted according to the tracking information; S4: Analyze the real-time state of the pet according to the real-time state of the car to determine the pet state information; S5: Adaptively adjusting the data transmission frequency according to the pet status information, and performing data transmission at the adjusted target frequency; The S4 includes: S41: If the real-time state of the car is static, the real-time location information of the pet is obtained through target tracking algorithm or UWB positioning; S42: obtaining the displacement of the pet within a preset time window according to the real-time position information of the pet; S43: Calculating a real-time index related to the pet state according to the displacement and the time window; S44: comparing the real-time index with a preset index threshold, and dividing the real-time index into a pet stillness index and a pet movement index; The S5 includes: S51: Obtaining original data transmission frequency; S52: If the real-time index is the pet stillness index, calculating the target frequency according to the original data transmission frequency and the pet stillness index; S53: If the real-time index is a pet exercise index, obtaining a preset pet exercise quantification coefficient and a user-preset personalized demand parameter; S54: Calculate the target frequency according to the pet exercise index, the pet exercise quantification coefficient and the personalized demand parameter.

2. The method for intelligently controlling battery energy consumption of a pet-finding vehicle according to claim 1 is characterized in that: The S3 includes: S31: If a pet is detected, a preset target tracking algorithm is used to track the pet target in the real-time image to obtain the pet target position information; S32: Obtain image size information corresponding to the real-time image, and determine whether the pet target is within a preset area based on the image size information and the pet target position information; S33: If the pet target is within the preset area, the real-time state of the car is adjusted to a stationary state; S34: If the pet target is not in the preset area, the real-time state of the car is adjusted to a moving state.

3. The method for intelligently controlling battery energy consumption of a pet-finding vehicle according to claim 1 is characterized in that: The S3 further includes: S35: If it is detected that there is no pet, the pet target is tracked through UWB positioning to obtain the real-time relative distance of the pet target with respect to the nursing car; S36: Determine the tracking distance interval according to a preset tracking distance threshold; S37: If the real-time relative distance is within the tracking distance interval, adjusting the real-time state of the vehicle to a stationary state; S38: If the real-time relative distance is not within the tracking distance interval, the real-time state of the vehicle is adjusted to a moving state.

4. The method for intelligently controlling battery energy consumption of a pet-finding vehicle according to claim 1, characterized in that: The S4 further comprises: S45: Obtaining the real-time relative distance of the pet target to the care cart and a preset threshold of the distance from home; S46: comparing the real-time relative distance with the distance-from-home threshold, and when the real-time relative distance is greater than the preset distance-from-home threshold, determining that the pet has left home; S47: When it is determined that the pet has left home, the real-time distance of the pet from home is obtained.

5. The method for intelligently controlling battery energy consumption of a pet-finding vehicle according to claim 4 is characterized in that: The S5 further includes: S55: If it is determined that the pet has left home, the original data transmission frequency and the real-time distance of the pet from home are obtained; S56: Calculate the target frequency according to the original data transmission frequency and the real-time distance of the pet from home.

6. An intelligent battery energy consumption control device for a pet-finding vehicle, characterized in that: The device comprises: An image acquisition module is used to acquire real-time video data collected by a camera on a pet care cart in a pet care scenario, and decompose the real-time video data into multiple frames of real-time images; A pet target detection module, used for inputting each frame of the real-time image into a pre-trained pet target detection model and outputting a pet detection result; A pet target tracking and car adjustment module is used to track the pet target according to the pet detection result and adjust the real-time state of the car through the tracking information; A pet real-time status analysis module is used to analyze the real-time status of the pet according to the real-time status of the vehicle and determine the pet status information; A frequency adjustment module, used to adaptively adjust the data transmission frequency according to the pet status information, and transmit data through the adjusted target frequency; The analyzing the real-time state of the pet according to the real-time state of the car to determine the pet state information includes: If the car is stationary in real time, the pet's real-time location information is obtained through target tracking algorithm or UWB positioning; According to the real-time position information of the pet, the displacement of the pet within a preset time window is obtained; Calculating a real-time index related to the pet state based on the displacement and the time window; Comparing the real-time index with a preset index threshold, and dividing the real-time index into a pet stillness index and a pet movement index; Adaptively adjusting the data transmission frequency according to the pet status information, and performing data transmission at the adjusted target frequency includes: Get the original data transmission frequency; If the real-time index is a pet stillness index, the target frequency is calculated according to the original data transmission frequency and the pet stillness index; If the real-time index is a pet exercise index, a preset pet exercise quantification coefficient and a user-preset personalized demand parameter are obtained; The target frequency is calculated based on the pet exercise index, the pet exercise quantification coefficient and the personalized demand parameter.

7. An electronic device, characterized in that: include: At least one processor, at least one memory and computer program instructions stored in the memory, when the computer program instructions are executed by the processor, implement the method according to any one of claims 1 to 5.

8. A storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images