Control method, vehicle and medium

Abstract

The invention discloses a control method, a vehicle and a computer readable storage medium. The method comprises the following steps: determining the credibility of a fish biting behavior according to image data at a target fishing position; and under the condition that the credibility is greater than a preset threshold value, feeding back fishing prompt information to the target object to prompt the target object to execute fishing operation. Thus, according to the image data of the target fishing position, the credibility of the fish biting behavior can be determined, automatic monitoring of the user leaving a fishing site is achieved, fishing prompt information is fed back to the user under the condition that the credibility is larger than a preset threshold value, the user is prompted to execute fishing operation, the accuracy of biting opportunity judgment is improved, and the user experience is improved. The user is prevented from missing the opportunity of biting the hook, and the fishing experience of the user is improved to a certain extent.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a control method, a vehicle, and a computer-readable storage medium. Background Technology

[0002] In related technologies, with the widespread use of vehicles, driving to the wild for fishing has become a common leisure activity. However, when users temporarily leave the fishing spot, they may miss the opportunity to bite, affecting the fishing experience. Summary of the Invention

[0003] This application provides a control method, a vehicle, and a computer-readable storage medium.

[0004] This application provides a control method, the method comprising: The credibility of fish biting behavior is determined based on image data of the target fishing location; If the credibility level is greater than a preset threshold, a phishing warning message is sent to the target object to prompt the target object to perform a phishing operation.

[0005] Thus, in this embodiment of the application, the credibility of a fish biting behavior can be determined based on the image data at the target fishing location, enabling automated monitoring of the user leaving the fishing site. If the credibility is greater than a preset threshold, fishing prompts can be sent to the user to prompt them to perform fishing operations, thereby improving the accuracy of judging the timing of the bite and preventing the user from missing the opportunity to bite the fish, thus improving the user's fishing experience to a certain extent.

[0006] In some embodiments, the method further includes: Establish a communication connection with the video capture device; Receive the image data forwarded by the video acquisition device.

[0007] In this way, a communication connection is established with the video capture device, and the vehicle receives image data forwarded by the video capture device. By establishing this communication connection between the vehicle and the video capture device, data interaction can be achieved. The vehicle's infotainment system can then receive real-time image data of the target fishing location, captured and forwarded by the video capture device, based on this communication link. This provides a real-time and reliable data source for subsequent calculations of the credibility of fish bite behavior and for triggering alerts based on the image data.

[0008] In some implementations, determining the credibility of a fish biting behavior based on image data at the target fishing location includes: Based on a pre-trained image processing model, image processing is performed on the image data to determine the credibility.

[0009] Thus, based on the pre-trained image processing model, image data is processed to determine credibility. This pre-trained image processing model, by accurately distinguishing between features related to fish biting behavior and environmental interference features, can comprehensively analyze features related to fish biting behavior, improving the accuracy of the final output credibility, reducing the probability of false positives and false negatives, and providing a reliable basis for triggering alerts.

[0010] In some implementations, the step of performing image processing on the image data based on a pre-trained image processing model to determine the credibility includes: Based on a pre-trained image processing model, feature extraction is performed on the image data to determine fishing feature data. The credibility is determined based on the fishing characteristic data.

[0011] Thus, based on a pre-trained image processing model, feature extraction is performed on the image data to determine fishing characteristic data; based on the fishing characteristic data, the credibility is determined. In this way, based on the pre-trained image processing model, multimodal feature information related to fish biting can be extracted to obtain fishing characteristic data. This data is then used to comprehensively analyze the multimodal features related to fish biting behavior in the fishing scene, calculate the credibility of the fish biting behavior, and ensure that the credibility accurately represents the fish biting situation. This provides a basis for subsequent credibility-based alerts to users, preventing missed bite opportunities and improving the fishing experience and success rate to some extent.

[0012] In some embodiments, the fishing feature data includes physical feature data, biological feature data, and environmental feature data. The step of performing feature extraction processing on the image data based on a pre-trained image processing model to determine the fishing feature data includes: Identify the motion state of a first target object in the image data to obtain the physical feature data, wherein the first target object includes a water float and / or a fishing rod; Identify the behavioral state of a second target object in the image data to obtain the biometric data, wherein the second target object includes a fish; The environmental state in the image data is identified to obtain the environmental feature data.

[0013] Thus, the motion state of a first target object in the image data is identified to obtain physical feature data, where the first target object includes a float and / or a fishing rod; the behavioral state of a second target object in the image data is identified to obtain biological feature data, where the second target object includes a fish; and the environmental state in the image data is identified to obtain environmental feature data. In this way, by identifying different target objects and environmental states in the image data, physical feature data, biological feature data, and environmental feature data can be obtained separately, improving the accuracy of feature extraction and providing a comprehensive and accurate basis for subsequent credibility calculations. This ensures that the model can accurately capture fish-biting-related features from complex scenes and reduces the influence of interference factors.

[0014] In some implementations, determining the credibility based on the phishing feature data includes: The credibility is determined based on the physical characteristic data, the biological characteristic data, and the environmental characteristic data.

[0015] Thus, credibility is determined based on physical, biological, and environmental characteristic data. This comprehensive analysis of these data improves the reliability of the characteristic data, avoids credibility bias caused by distortion of a single characteristic, and ultimately enhances the accuracy of the calculated credibility, laying the foundation for subsequent credibility-based grading suggestions.

[0016] In some implementations, the step of sending a phishing warning message to the target object when the confidence level is greater than a preset threshold, to prompt the target object to perform a phishing operation, includes: If the credibility is greater than the first credibility threshold and less than or equal to the second credibility threshold, a first prompt message is sent to the target object. If the duration of the confidence level being greater than the second confidence threshold is greater than the first time threshold, a second prompt message is sent to the target object to prompt the target object to perform a phishing operation. The prompt message in the second prompt message has a prompting method and / or prompting content that is more than that in the first prompt message.

[0017] Thus, when the credibility is greater than the first credibility threshold and less than or equal to the second credibility threshold, a first prompt is sent to the target. When the credibility is greater than the second credibility threshold for a duration greater than the first time threshold, a second prompt is sent to the target to prompt them to perform a fishing action. The second prompt's prompting method and / or content are more extensive than the first prompt. In this way, the credibility and matching first and second prompts can be distinguished using the first, second, and first credibility thresholds and the first time threshold, ensuring that the intensity of the prompts precisely matches the urgency of the bite signal. This avoids false alarms and excessive disturbance while ensuring that the user does not miss the fish's bite, thereby improving the user's fishing experience to some extent.

[0018] In some embodiments, the method further includes: A data report is generated based on the image data of the target fishing location and the credibility of the fish biting behavior.

[0019] Thus, a data report is generated based on the image data of the target fishing location and the credibility of the fish biting behavior. This data report allows for a review of the fishing process, enabling targeted adjustments to the time, location, or equipment selection for the next fishing trip. This provides a basis for optimizing the user's fishing techniques, increasing the success rate of subsequent catches, and ultimately enhancing the user's fishing experience.

[0020] This application provides a vehicle including a memory and a processor. The memory stores a computer program, which, when executed by the processor, implements the steps of the above-described method.

[0021] This application provides a computer-readable storage medium storing a computer program that, when executed by one or more processors, implements the steps of the above-described method.

[0022] The vehicle and computer-readable storage medium provided in this application determine the credibility of a fish biting behavior based on image data at the target fishing location. If the credibility exceeds a preset threshold, a fishing prompt is sent to the target user to prompt them to perform a fishing action. Thus, in this application embodiment, the credibility of a fish biting behavior can be determined based on image data at the target fishing location, enabling automated monitoring of users leaving the fishing area. By sending a fishing prompt to the target user when the credibility exceeds a preset threshold, the accuracy of judging the timing of a bite is improved, preventing users from missing the opportunity to bite and enhancing the user's fishing experience to some extent.

[0023] Additional aspects and advantages of embodiments of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of embodiments of this application. Attached Figure Description

[0024] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, wherein: Figure 1 This is one of the flowcharts illustrating the control method of certain embodiments of this application; Figure 2 This is a second schematic flowchart of the control method in some embodiments of this application; Figure 3 This is the third flowchart illustrating the control method of certain embodiments of this application; Figure 4 This is the fourth flowchart illustrating the control method of certain embodiments of this application; Figure 5 This is the fifth flowchart illustrating the control method of certain embodiments of this application; Figure 6 This is a schematic diagram of the overall flow of the control method in some embodiments of this application. Detailed Implementation

[0025] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the embodiments of this application, and should not be construed as limiting the embodiments of this application.

[0026] In related technologies, with the increasing popularity of vehicles, driving to wild waters for fishing has gradually become a leisure activity for some users. In the context of wild fishing, users spend time waiting for schools of fish to gather and for fish to bite the hook, enjoying the tranquility of the fishing process and the pleasure of a catch.

[0027] However, in actual fishing, users often face the problem of leaving the fishing spot due to temporary needs, such as needing to go to the car to get spare fishing gear, replenish drinking water, or briefly leave the fishing spot to handle other matters.

[0028] While users are away, they cannot know whether the float has moved or whether there are fish biting the hook, which may cause them to miss the best time to set the hook. For example, if a fish bites the hook and the user fails to notice and set the hook in time, the fish may escape, thus reducing the success rate of fishing and affecting the user's fishing experience.

[0029] Based on the above issues, please refer to Figure 1This application provides a control method, the method comprising: 01: Determine the credibility of fish biting behavior based on image data of the target fishing location; 02: When the credibility level is greater than the preset threshold, send a phishing prompt message to the target object to prompt the target object to perform a phishing operation.

[0030] This application provides a control device. The control method of this application can be implemented by the control device of this application. Specifically, the control device includes a control module. The control module is used to determine the credibility of a fish biting behavior based on image data at the target fishing location. The control module is also used to provide fishing prompt information to the target object when the credibility is greater than a preset threshold, so as to prompt the target object to perform a fishing operation.

[0031] This application also provides a vehicle, which includes a memory and a processor. The control method of this application can be implemented by the vehicle of this application. Specifically, the memory stores a computer program, and the processor is used to determine the credibility of a fish biting behavior based on image data at the target fishing location. The processor is also used to provide fishing prompt information to the target object when the credibility is greater than a preset threshold, so as to prompt the target object to perform a fishing operation.

[0032] Specifically, the target fishing location is the area where the target person engages in fishing activities, including the area where the fishing rod and float are located, as well as the surrounding waters. The target person is the user engaging in fishing activities.

[0033] The video data can be collected by a video capture device at the target fishing location. It contains visual information about the real-time status of the target fishing location, such as the displacement of the float, changes in the shape of the fishing rod, fish activity, and dynamic information such as the surrounding environment. It is the basic data for analyzing fish biting behavior.

[0034] Fish biting behavior is the action that occurs when a fish comes into contact with and attempts to swallow the hook, which can indirectly cause the float to move or the fishing rod to deform.

[0035] Credibility is a probability value obtained by analyzing and calculating image data. It is used to quantify the actual likelihood of a fish biting the hook. For example, the higher the credibility value, the greater the probability of a fish biting the hook.

[0036] The preset threshold is a credibility threshold set in advance based on the actual use scenario and user needs. It can be adjusted according to the actual situation and is used to determine whether to send a phishing prompt to the user to prompt the user to perform a phishing operation.

[0037] Fishing alerts are signals that inform users of the possibility of a fish biting the hook. These can take the form of voice announcements, screen flashes, or app notifications, ensuring that users can quickly perceive the information. Performing a fishing operation refers to the actions a user takes after receiving a notification, such as lifting the rod and reeling in the line, to catch fish and avoid missing the opportunity to bite.

[0038] By acquiring real-time image data of the target fishing location and analyzing it, the credibility of a fish biting behavior can be determined. The credibility is then compared with a preset threshold to determine the probability of a fish biting. When the probability of a fish biting is high, fishing tips are sent to the user, guiding them to return to the scene to fish. This achieves automated fish monitoring and bite alerts while the user is away.

[0039] In one example, the received image data can be input into a pre-trained image processing model to analyze fish behavior. The model can process the image data through a multimodal biofeature extraction algorithm to obtain multi-dimensional feature data. Through comprehensive analysis and calculation of multi-dimensional features, the model can accurately identify fish biting behavior, output the credibility of fish biting behavior, and achieve accurate judgment of fish behavior.

[0040] By comparing the calculated confidence level with a preset threshold in real time, if the confidence level exceeds the preset threshold, the probability of a fish biting the hook is considered to have reached the standard requiring an alert. An alert mechanism is then activated, sending a fishing tip to the user. Upon receiving the tip, the user can quickly know that a fish has bitten and promptly return to the target fishing location to continue fishing.

[0041] Based on the judgment logic of credibility and preset thresholds, it can accurately identify fish biting behavior, reduce false or missed alerts, improve the accuracy of judging the timing of the bite, and ensure that timely fishing prompts can ensure that users can quickly return to perform operations when a fish bites, avoiding missing the opportunity to fish bite, and improving the user's fishing experience to a certain extent.

[0042] It should be noted that this application embodiment also provides a server, which includes a memory and a processor. The control method of this application embodiment can also be implemented by the server. Specifically, the memory stores a computer program, and the processor is used to determine the credibility of a fish biting behavior based on image data at the target fishing location. The processor is also used to provide fishing prompt information to the target object when the credibility is greater than a preset threshold, so as to prompt the target object to perform a fishing operation.

[0043] In summary, in this embodiment, the credibility of a fish biting behavior can be determined based on image data at the target fishing location, enabling automated monitoring of users leaving the fishing area. When the credibility exceeds a preset threshold, fishing prompts are sent to the user to prompt them to perform fishing operations, improving the accuracy of judging the timing of the bite, preventing users from missing the opportunity to bite, and enhancing the user's fishing experience to a certain extent.

[0044] Please see Figure 2 In some implementations, the method further includes: 03: Establish a communication connection with the video acquisition device; 04: Receive video data forwarded by the video capture device.

[0045] In some implementations, the control module is also used to establish a communication connection with the video acquisition device. The control module is also used to receive image data forwarded by the video acquisition device.

[0046] In some implementations, the processor is also used to establish a communication connection with the video acquisition device. The processor is also used to receive image data forwarded by the video acquisition device.

[0047] Specifically, a video capture device refers to a device with image capture capabilities, such as a user's mobile phone, which can be tilted at a fixed angle toward the target fishing location to continuously collect image data of that area.

[0048] Before acquiring image data on the vehicle's infotainment system, a stable communication link can be established between the vehicle and the video capture device, for example, by using a local area network hotspot to establish a communication connection. This ensures that the vehicle and the video capture device can interact with each other, allowing the infotainment system to receive image data of the target fishing location that is collected and forwarded in real time by the video capture device based on this communication link. This provides a real-time and reliable data source for subsequent calculation of the credibility of the fish biting behavior and triggering alerts.

[0049] Understandably, since the vehicle itself cannot directly aim at the fishing rod and float to collect image data of the target fishing location, a more convenient video capture device can be used to achieve accurate image capture of the target fishing location.

[0050] By adjusting the placement and angle of the video capture device, it can be focused on the target fishing location to collect image data, thus avoiding the problem of insufficient capture capability of the vehicle itself.

[0051] Among them, the video acquisition device collects and forwards real-time streaming data containing continuous frames, which can characterize dynamic features such as float displacement, fishing rod deformation, and fish activity.

[0052] Based on the communication connection between the vehicle and the video acquisition device, image data of the target fishing location can be stably transferred from the acquisition end to the vehicle end, providing data support for the accuracy of credibility calculation.

[0053] In one example, a user's everyday mobile phone can be used as a video capture device.

[0054] By enabling a dedicated in-vehicle hotspot on the vehicle's infotainment system and connecting the mobile phone to the hotspot, a dedicated communication link can be established, laying the foundation for image data transmission. Then, a dedicated image transmission application, such as a fishing assistance application developed by the car manufacturer, can be opened on the mobile phone to activate the fishing streaming function. Meanwhile, in fishing scenarios, by adjusting the position and angle of the phone, it can be aimed at the fishing rod and the float to continuously capture images. Finally, the application will encapsulate the collected real-time image data into a video stream format and actively forward it to the vehicle through the established communication connection, providing a data source for subsequent calculation of the credibility of fish biting behavior based on image data.

[0055] In this way, a communication connection is established with the video capture device, and the vehicle receives image data forwarded by the video capture device. By establishing this communication connection between the vehicle and the video capture device, data interaction can be achieved. The vehicle's infotainment system can then receive real-time image data of the target fishing location, captured and forwarded by the video capture device, based on this communication link. This provides a real-time and reliable data source for subsequent calculations of the credibility of fish bite behavior and for triggering alerts based on the image data.

[0056] Please see Figure 3 In some implementations, step 01 (determining the credibility of a fish biting behavior based on image data at the target fishing location) includes: 011: Based on the pre-trained image processing model, perform image processing on the image data to determine the credibility.

[0057] In some implementations, the control module is also used to perform image processing on the image data based on a pre-trained image processing model to determine the credibility.

[0058] In some implementations, the processor is also used to perform image processing on the image data based on a pre-trained image processing model to determine credibility.

[0059] Specifically, the pre-trained image processing model is an algorithm model that has been trained in advance with a large amount of sample data and has reached a preset accuracy. By inputting the image data of the target fishing location into the pre-trained image processing model, the model can identify features related to fish biting behavior from complex image data and output the credibility of the fish biting behavior.

[0060] Understandably, image data from the target fishing location contains a wealth of information, such as water surface ripples caused by weather, differences in brightness due to changes in lighting, and interference from obstructions. Therefore, simple image analysis, such as judging a fish's bite solely by whether the float moves, cannot accurately distinguish between feature changes caused by a genuine bite and those caused by environmental interference. This can easily lead to misjudgments or missed detections, such as misinterpreting a wind-blown float movement as a bite.

[0061] Image data of the target fishing location is input into a pre-trained image processing model. The model can automatically filter out interference information and perform multimodal feature extraction on the image data. It comprehensively analyzes the features related to fish biting and accurately distinguishes between features related to fish biting behavior and environmental interference features, thereby improving the accuracy of the final output credibility, reducing the probability of misjudgment and missed judgment, and providing a reliable basis for triggering alerts in the future.

[0062] Thus, based on the pre-trained image processing model, image data is processed to determine credibility. This pre-trained image processing model, by accurately distinguishing between features related to fish biting behavior and environmental interference features, can comprehensively analyze features related to fish biting behavior, improving the accuracy of the final output credibility, reducing the probability of false positives and false negatives, and providing a reliable basis for triggering alerts.

[0063] In some implementations, step 011 (based on a pre-trained image processing model, performing image processing on the image data to determine credibility) includes: 0111: Based on a pre-trained image processing model, feature extraction is performed on the image data to determine fishing feature data; 0112: Determine the credibility based on the fishing characteristic data.

[0064] In some implementations, the control module is further configured to perform feature extraction processing on the image data based on a pre-trained image processing model to determine fishing feature data. The control module is also configured to determine the confidence level based on the fishing feature data.

[0065] In some implementations, the processor is further configured to perform feature extraction processing on the image data based on a pre-trained image processing model to determine fishing feature data. The processor is also configured to determine confidence level based on the fishing feature data.

[0066] Specifically, fishing feature data refers to dynamic signals that are directly or indirectly related to fish biting behavior, including dynamic changes in physical form caused by changes in fish activity, dynamic pattern features of fish due to biting, etc., which can be obtained through feature extraction processing.

[0067] Based on a pre-trained image processing model, image data can be processed frame by frame. By removing irrelevant interference, misjudgments caused by interfering information can be avoided. Then, multimodal feature information related to fish biting can be extracted and transformed into fishing feature data, laying the foundation for improving the accuracy of quantifying fish biting behavior based on fishing feature data.

[0068] In one example, the model performs feature processing on the image frame by frame, first identifying the positions of the float and fishing rod, marking areas where fish may exist, and distinguishing interfering targets such as vegetation on the shore and debris on the water surface. Then, the features of the located float, fishing rod, and fish targets are quantified. For example, the direction and distance of the float's movement and the rate of position change between each frame are calculated in real time, the degree of bending and deformation trend of the fishing rod are detected, the trajectory and frequency of fish approaching the hook are captured, and the amplitude of water surface fluctuations caused by environmental factors are recorded. Finally, the quantified information is integrated into structured fishing feature data, and the credibility of a fish biting the hook is output based on the quantified fishing feature data.

[0069] Based on fishing feature data, a comprehensive analysis of multimodal features related to fish biting behavior in fishing scenarios can be conducted to calculate the credibility of fish biting behavior. This ensures that the credibility can accurately represent the situation of fish biting, providing a basis for subsequent credibility-based reminders to users, avoiding missing the biting opportunity, and improving the fishing experience and success rate to a certain extent.

[0070] Thus, based on a pre-trained image processing model, feature extraction is performed on the image data to determine fishing characteristic data; based on the fishing characteristic data, the credibility is determined. In this way, based on the pre-trained image processing model, multimodal feature information related to fish biting can be extracted to obtain fishing characteristic data. This data is then used to comprehensively analyze the multimodal features related to fish biting behavior in a fishing scene, calculate the credibility of the fish biting behavior, and ensure that the credibility accurately represents the fish biting situation. This provides a basis for subsequent credibility-based alerts to users, preventing missed bite opportunities and improving the fishing experience and success rate to some extent.

[0071] In some implementations, the fishing feature data includes physical feature data, biological feature data, and environmental feature data. Step 0111 (based on a pre-trained image processing model, performing feature extraction processing on the image data to determine the fishing feature data) includes: 01111: Identify the motion state of a first target object in the image data to obtain physical feature data, wherein the first target object includes a water float and / or a fishing rod; 01112: Identify the behavioral state of a second target object in the image data to obtain biometric data, wherein the second target object includes fish; 01113: Identify the environmental state in the image data to obtain environmental feature data.

[0072] In some embodiments, the control module is further configured to identify the motion state of a first target object in the image data to obtain physical feature data, wherein the first target object includes a float and / or a fishing rod. The control module is also configured to identify the behavioral state of a second target object in the image data to obtain biometric data, wherein the second target object includes a fish. The control module is further configured to identify the environmental state in the image data to obtain environmental feature data.

[0073] In some embodiments, the processor is further configured to identify the motion state of a first target object in the image data to obtain physical feature data, wherein the first target object includes a float and / or a fishing rod. The processor is also configured to identify the behavioral state of a second target object in the image data to obtain biometric data, wherein the second target object includes a fish. The processor is further configured to identify the environmental state in the image data to obtain environmental feature data.

[0074] Specifically, the first target object includes a float and / or a fishing rod, and the second target object includes a fish.

[0075] In some examples, fishing feature data includes physical feature data, biological feature data, and environmental feature data.

[0076] Among them, physical feature data are physical signals used to determine the fish biting the hook, and quantitative information used to characterize the motion state of the first target object, including the displacement vector (direction and distance of movement), displacement speed, swaying frequency of the float, and data such as the deformation angle, deformation speed, and deformation duration of the fishing rod. Biometric data are biological signals used to determine when a fish bites a hook. They are quantitative information used to characterize the behavior of a second target object, including the fish's swimming trajectory (movement path in the image), the number of times it approaches the hook per unit time, the contact action between the fish and the hook, and the fish's body shape characteristics. Environmental feature data is information that characterizes the environmental state in image data. It is used to correct the bias of physical feature data and biological feature data, and to filter the influence of environmental interference on the bite detection. For example, data such as the amplitude of water surface ripples corresponding to wind speed, light intensity, and the position and movement of floating objects.

[0077] In the fish biting behavior, there are the fish's actions of approaching the hook, i.e., biological feature data, and the changes in the movement of the float and fishing rod that cause this, i.e., physical feature data. Therefore, based on the pre-trained image processing model, feature extraction processing can be performed on the image data to identify the motion state of the first target object to obtain physical feature data, and to identify the behavior state of the second target object to obtain biological feature data, providing an accurate basis for subsequent credibility calculation.

[0078] In addition, environmental factors such as wind and light can continuously interfere with the motion state of the first target object and the behavior state of the second target object. For example, the swaying of water caused by wind may be misjudged as a physical feature of the hook bite. Therefore, the environmental state in the image data can be distinguished to obtain environmental feature data. Then, by combining physical feature data and biological feature data, comprehensive data basis can be provided for subsequent credibility calculation, ensuring that the model can accurately capture hook bite-related signals from complex scenes and reduce the influence of interference factors.

[0079] In some examples, the image processing model can identify the motion of the float and fishing rod in the image data frame by frame.

[0080] For a float, the displacement vector between adjacent frames can be calculated, such as the lateral movement distance and the vertical sinking depth; the displacement velocity can be calculated, that is, the displacement per unit time; abnormal displacement can be marked, such as sinking more than a preset distance in a short period of time; for a fishing rod, the algorithm can capture changes in the rod's contour and calculate the deformation angle, such as the degree of bending of the rod tip; the deformation duration can be used to filter out sudden deformations that are not caused by human operation; finally, these quantitative information are integrated into physical feature data.

[0081] In some examples, the image processing model can identify the behavioral state of fish in image data frame by frame.

[0082] The algorithm identifies fish in images, eliminates interference such as debris and light and shadow on the water surface, and records the fish's swimming path to determine if there is a tendency to move towards the hook. It analyzes the fish's mouth movements to detect whether there are behaviors that approach or contact the hook, such as pecking. At the same time, it records the fish's body characteristics, such as body length and outline, to help determine the likelihood of biting the hook. For example, larger fish have a stronger bite signal. Finally, this behavioral information is integrated into biometric data.

[0083] In some examples, the image processing model can identify the environmental state in the image data frame by frame.

[0084] Wind intensity is determined by the shape of water ripples, such as the density of ripples corresponding to wind speed, and finally integrated into environmental characteristic data.

[0085] In addition, environmental characteristic data can also be obtained through pre-acquired wind level reports or by sensors mounted on vehicles.

[0086] By identifying different target objects and environmental states in image data, physical feature data, biological feature data, and environmental feature data can be obtained separately, improving the accuracy of feature extraction and providing a comprehensive and accurate basis for subsequent credibility calculation. This ensures that the model can accurately capture fish bite-related features from complex scenes and reduce the influence of interference factors.

[0087] Thus, the motion state of a first target object in the image data is identified to obtain physical feature data, where the first target object includes a float and / or a fishing rod; the behavioral state of a second target object in the image data is identified to obtain biological feature data, where the second target object includes a fish; and the environmental state in the image data is identified to obtain environmental feature data. In this way, by identifying different target objects and environmental states in the image data, physical feature data, biological feature data, and environmental feature data can be obtained separately, improving the accuracy of feature extraction and providing a comprehensive and accurate basis for subsequent credibility calculations. This ensures that the model can accurately capture fish-biting-related features from complex scenes and reduces the influence of interference factors.

[0088] In some implementations, step 0112 (determining confidence based on phishing feature data) includes: 01121: Determine the credibility based on physical characteristic data, biological characteristic data, and environmental characteristic data.

[0089] In some implementations, the control module is also used to determine the credibility based on physical characteristic data, biological characteristic data, and environmental characteristic data.

[0090] In some implementations, the processor is also used to determine credibility based on physical feature data, biometric data, and environmental feature data.

[0091] Specifically, by using physical feature data, biological feature data, and environmental feature data as the common basis for credibility calculation, and by using a pre-trained image processing model to perform collaborative analysis and verification of the three types of data, an accurate and realistic credibility can be obtained.

[0092] Based on a pre-trained image processing model, reverse compensation can be performed on physical and biological feature data according to environmental feature data.

[0093] For example, if strong winds cause the float to move or the fishing rod to bend, and this is identified as a fish biting, the deformation of the fishing rod and the displacement of the float can be compensated for in reverse based on the currently obtained wind level to eliminate environmental interference. The mutual verification of physical feature data, biological feature data, and environmental feature data can avoid the credibility deviation caused by the distortion of a single feature data, improve the reliability of feature data, and thus improve the accuracy of the calculated credibility. This makes the credibility results more consistent with the actual hooking situation, avoids misjudgment and omission, and lays the foundation for subsequent credibility-based graded prompts.

[0094] Thus, credibility is determined based on physical, biological, and environmental characteristic data. This comprehensive analysis of these data improves the reliability of the characteristic data, avoids credibility bias caused by distortion of a single characteristic, and ultimately enhances the accuracy of the calculated credibility, laying the foundation for subsequent credibility-based grading suggestions.

[0095] Please see Figure 4 In some implementations, step 02 (when the confidence level is greater than a preset threshold, sending a phishing warning message to the target object to prompt the target object to perform a phishing operation) includes: 021: If the credibility is greater than the first credibility threshold and less than or equal to the second credibility threshold, the first prompt message is sent to the target object; 022: If the duration of the credibility being greater than the second credibility threshold is greater than the first time threshold, a second prompt message is sent to the target object to prompt the target object to perform a phishing operation. The prompt message in the second prompt message has a prompting method and / or prompting content that is more than that in the first prompt message.

[0096] In some implementations, the control module is further configured to provide a first prompt to the target object when the confidence level is greater than a first confidence threshold and less than or equal to a second confidence threshold. The control module is also configured to provide a second prompt to the target object when the duration of the confidence level being greater than the second confidence threshold is greater than a first time threshold, thereby prompting the target object to perform a phishing operation.

[0097] In some implementations, the processor is further configured to provide a first prompt to the target object when the confidence level is greater than a first confidence threshold and less than or equal to a second confidence threshold. The processor is also configured to provide a second prompt to the target object when the duration of the confidence level being greater than the second confidence threshold is greater than a first time threshold, thereby prompting the target object to perform a phishing operation.

[0098] Specifically, the preset thresholds include a first confidence threshold, a second confidence threshold, and a first time threshold.

[0099] The first confidence threshold is a preset lower confidence level threshold, such as 70%. The second confidence threshold is a preset higher level of confidence threshold, such as 85%, and the second confidence threshold is greater than the first confidence threshold. The first time threshold is the critical time value for the duration during which the confidence level of continuous image data exceeds the second confidence threshold.

[0100] If the credibility is less than the first credibility threshold, the current credibility can be determined to be low, i.e., a low credibility signal. No prompts will be triggered, and the monitoring of image data will continue. If the credibility is greater than the first credibility threshold and less than or equal to the second credibility threshold, it can be considered that there is a suspected fish bite signal, that is, a medium-to-high credibility signal, but the signal strength and reliability are low, and the first prompt information triggering process is initiated. If the credibility is greater than the second credibility threshold, the fish biting behavior signal can be considered strong, i.e., a high credibility signal, and the duration verification process can be initiated. If the duration of a confidence level greater than the second confidence threshold is less than or equal to the first time threshold, the instantaneous high confidence signal can be considered to be caused by interference, and no prompts will be triggered; the monitoring of image data will continue. If the duration of the confidence level being greater than the second confidence threshold is greater than the first time threshold, it can be considered that the fish biting behavior signal is strong and relatively stable, that is, a stable high confidence signal, and enter the second prompt information triggering process.

[0101] The first alert is a weaker alert with a simpler message. It is used to remind users without disturbing them. For example, it may be a simple flashing alert on the vehicle screen or a text notification such as "A suspected hook-on signal has been detected. Please be aware" pushed by the vehicle system. It is suitable for suspected hook-on scenarios with low urgency. The second type of notification is a stronger reminder. Compared to the first type of notification, the second type of notification has more methods or richer content. It is used to remind users in a more prominent and direct way. For example, while pushing a text notification through the vehicle system, it can also remind users through voice broadcast "A clear hook-up signal has been detected. Please return immediately." Alternatively, it can also provide a strong reminder by flashing the vehicle screen at high frequency and emitting a reminder sound through the vehicle's audio system. It is suitable for clear hook-up scenarios with a high degree of urgency.

[0102] It should be noted that the prompting method and content of the first and second prompt messages can be set according to the actual situation, and no restrictions are imposed here.

[0103] Understandably, based on preset thresholds and credibility, the urgency of a fish biting the hook can be determined. A stable, high-credibility signal can represent a clear bite scenario with a high degree of urgency, while a medium-to-high-credibility signal can represent a suspected bite scenario with a low degree of urgency. Then, different prompt information triggering processes are matched according to the degree of urgency, so that the intensity of the prompt information is accurately matched with the urgency of the bite signal, avoiding false alerts and excessive disturbances, while ensuring that no emergency signal is missed.

[0104] Based on preset thresholds, the system differentiates the strength of credibility signals and can match different prompts to be triggered according to the actual situation. This avoids disturbing users with strong reminders for medium-to-high credibility signals, while also preventing missed opportunities due to weak reminders for stable high credibility signals. The system ensures that the reminder strength is precisely matched with the urgency of the hook, meeting the actual needs of users and improving the comfort of the experience.

[0105] Thus, when the credibility is greater than the first credibility threshold and less than or equal to the second credibility threshold, a first prompt is sent to the target. When the credibility is greater than the second credibility threshold for a duration greater than the first time threshold, a second prompt is sent to the target to prompt them to perform a fishing action. The second prompt's prompting method and / or content are more extensive than the first prompt. In this way, the credibility and matching first and second prompts can be distinguished using the first, second, and first credibility thresholds and the first time threshold, ensuring that the intensity of the prompts precisely matches the urgency of the bite signal. This avoids false alarms and excessive disturbance while ensuring that the user does not miss the fish's bite, thereby improving the user's fishing experience to some extent.

[0106] Please see Figure 5 In some implementations, the method further includes: 05: Generate a data report based on the image data of the target fishing location and the credibility of the fish biting behavior.

[0107] In some implementations, the control module is also used to generate a data report based on image data of the target fishing location and the credibility of the fish biting behavior.

[0108] In some implementations, the processor is also used to generate a data report based on image data of the target fishing location and the credibility of the fish biting behavior.

[0109] Specifically, after the entire fishing monitoring process is completed, the overall data of the entire fishing process can be obtained and a data report can be generated based on the image data of the target fishing location and the credibility of the fish biting behavior.

[0110] Understandably, after fishing, users can only know about the single bite event at that time through the reminder, and cannot obtain the overall data of the entire fishing process. For example, they are not clear about the frequency of high-reliability bite signals during the monitoring period, which time periods the fish are more active, and the overall impact of environmental interference on the bite judgment.

[0111] Based on the data report, the fishing process can be reviewed to make targeted adjustments to the time, location, or equipment selection for the next fishing trip. This provides a basis for users to optimize their fishing skills in the future, improve the success rate of subsequent fishing, and enhance the user's fishing experience to a certain extent.

[0112] In one example, by quantitatively analyzing the credibility data stored after fishing, various indicators can be calculated, such as total monitoring time, the number of times credibility exceeds the second credibility threshold and the duration is greater than the first time threshold (number of bites), the percentage of time with credibility above 85%, and the time distribution of credibility between 70% and 85%. At the same time, combined with environmental characteristic data, such as the time of wind and rain, the impact of environmental interference on credibility judgment can be analyzed. By integrating indicator data, environmental characteristic data, and video data, a structured report can be generated according to a preset template for users to view. This allows users to review the state of the float or fishing rod at each bite through the event images corresponding to different indicators, analyze whether there is a deviation in the timing of lifting the rod, and provide a basis for optimizing subsequent fishing techniques.

[0113] In addition, data reports can help users optimize their fishing strategies. Based on data reports from multiple fishing trips, users can compare the frequency of bites and signal quality at different times and locations to summarize suitable fishing times and areas; at the same time, based on environmental impact analysis, they can understand which weather conditions are better for fishing and improve the success rate of their next fishing trip.

[0114] Thus, a data report is generated based on the image data of the target fishing location and the credibility of the fish biting behavior. This data report allows for a review of the fishing process, enabling targeted adjustments to the time, location, or equipment selection for the next fishing trip. This provides a basis for optimizing the user's fishing techniques, increasing the success rate of subsequent catches, and ultimately enhancing the user's fishing experience.

[0115] The following is Figure 6 For example, Figure 6 This is a schematic diagram illustrating the overall process of an embodiment of this application, which explains the vehicle control method used in this embodiment: First, by turning on the car's hotspot, a communication connection can be established between the vehicle and the mobile phone; Then, the video streaming function can be activated to send the video shot by the mobile phone to the vehicle. The vehicle media server obtains the image data by parsing the data. Then, based on the vehicle-side fish situation big data model, i.e. the pre-trained image processing model, feature recognition processing can be performed on the image data to calculate and obtain the credibility. Next, the credibility is determined based on a preset threshold to match different notification methods: If the credibility is greater than 85% (second credibility threshold) and lasts for 3 seconds (first time threshold), a second prompt message is sent to the target (user). The user is directly reminded to perform the phishing operation through strong reminder and TTS (Text-to-Speech) voice broadcast. When the credibility is greater than 70% (first credibility threshold) and less than or equal to 85% (second credibility threshold), the first prompt message is fed back to the target object (user), and the user is lightly reminded to pay attention to the fish biting the hook through the vehicle screen flashing; If the confidence level is less than or equal to 70% (the first confidence threshold), continue monitoring without issuing any alerts; Finally, after the entire fishing monitoring is completed, a monitoring report of the entire fishing process, i.e., a data report, is output based on the credibility of the feature recognition and the image data.

[0116] This application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements the steps of the control method described above.

[0117] It is understood that a computer program includes computer program code. Computer program code can be in the form of source code, object code, executable files, or some intermediate form. Computer-readable storage media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc.

[0118] In this specification, the terms "specifically," "furthermore," "particularly," "understandably," etc., refer to specific features, structures, materials, or characteristics described in connection with embodiments or examples that are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0119] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of executable request code comprising one or more steps for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order according to the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0120] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A control method, characterized in that, The method includes: The credibility of fish biting behavior is determined based on image data of the target fishing location; If the credibility level is greater than a preset threshold, a phishing warning message is sent to the target object to prompt the target object to perform a phishing operation.

2. The method according to claim 1, characterized in that, The method further includes: Establish a communication connection with the video capture device; Receive the image data forwarded by the video acquisition device.

3. The method according to claim 1, characterized in that, The process of determining the credibility of a fish biting behavior based on image data at the target fishing location includes: Based on a pre-trained image processing model, image processing is performed on the image data to determine the credibility.

4. The method according to claim 3, characterized in that, The image processing model, based on a pre-trained model, performs image processing on the image data to determine the credibility, including: Based on a pre-trained image processing model, feature extraction is performed on the image data to determine fishing feature data. The credibility is determined based on the fishing characteristic data.

5. The method according to claim 4, characterized in that, The fishing feature data includes physical feature data, biological feature data, and environmental feature data. The step of extracting features from the image data based on a pre-trained image processing model to determine the fishing feature data includes: Identify the motion state of a first target object in the image data to obtain the physical feature data, wherein the first target object includes a water float and / or a fishing rod; Identify the behavioral state of a second target object in the image data to obtain the biometric data, wherein the second target object includes a fish; The environmental state in the image data is identified to obtain the environmental feature data.

6. The method according to claim 5, characterized in that, The step of determining the credibility based on the fishing feature data includes: The credibility is determined based on the physical characteristic data, the biological characteristic data, and the environmental characteristic data.

7. The method according to claim 1, characterized in that, When the credibility level is greater than a preset threshold, the step of sending a phishing warning message to the target object to prompt the target object to perform a phishing operation includes: If the credibility is greater than the first credibility threshold and less than or equal to the second credibility threshold, a first prompt message is sent to the target object. If the duration of the confidence level being greater than the second confidence threshold is greater than the first time threshold, a second prompt message is sent to the target object to prompt the target object to perform a phishing operation. The prompt message in the second prompt message has a prompting method and / or prompting content that is more than that in the first prompt message.

8. The method according to claim 1, characterized in that, The method further includes: A data report is generated based on the image data of the target fishing location and the credibility of the fish biting behavior.

9. A vehicle, characterized in that, The vehicle includes a memory and a processor, the memory storing a computer program that, when executed by the processor, implements the method according to any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by one or more processors, implements the method of any one of claims 1-8.

Images