Data processing method, automated horticulture device, and computer program product

Abstract

This invention provides a data processing method, an automated gardening device, and a computer program product. The data processing method includes: performing feature recognition on an environmental image of the automated gardening device; determining a first confidence level of weather information for the environment where the automated gardening device is located based on the feature recognition results, wherein the first confidence level indicates whether the environment where the automated gardening device is located is rainy or snowy; obtaining a second confidence level, which is determined based on monitoring results from environmental monitoring sensors mounted on the automated gardening device; and determining whether the environment where the automated gardening device operates during rainy or snowy weather based on the first confidence level and the second confidence level. This method can accurately predict the weather.

Description

Technical Field

[0001] This invention relates to the field of intelligent device technology, and in particular to a data processing method, an automatic gardening device, and a computer program product. Background Technology

[0002] Existing automated gardening equipment (also known as self-service gardening equipment, intelligent gardening equipment, or self-moving equipment, etc.), such as automatic lawnmowers, can automatically mow lawns without human supervision or control, thereby reducing the time spent on users and reducing repetitive labor.

[0003] Since automated gardening equipment often operates outdoors, such as on lawns, the weather conditions at these locations are highly variable, including rain and snow. Rain and snow can negatively impact the safety of automated gardening equipment. For example, in rainy or snowy conditions, equipment exposed to water or snow is prone to short circuits and damage. Therefore, a method is needed to accurately determine the ambient weather conditions while the automated gardening equipment is operating, in order to protect it. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed, which provide a data processing method, an automatic gardening device, and a computer program product, so as to at least solve the problem that existing automatic gardening devices cannot accurately detect the weather in their environment.

[0005] One or more embodiments of the present invention provide a data processing method, comprising: performing feature recognition on an environmental image of an automated gardening device, and determining a first confidence level of weather information of the environment in which the automated gardening device is located based on the feature recognition result, wherein the first confidence level is used to indicate whether the environment in which the automated gardening device is located is a rainy or snowy day; obtaining a second confidence level, wherein the second confidence level is determined based on the monitoring results of an environmental monitoring sensor mounted on the automated gardening device; and determining whether the environment in which the automated gardening device operates is a rainy or snowy day based on the first confidence level and the second confidence level.

[0006] According to another aspect of the present invention, an automatic gardening device is provided, which includes a controller for performing the data processing method described above.

[0007] According to another aspect of the present invention, a computer program product is provided, comprising computer instructions that instruct a computing device to perform the data processing method as described above.

[0008] In this embodiment, feature recognition is performed based on environmental images collected by automated gardening equipment to obtain a first confidence level of weather information. By combining the first confidence level with a second confidence level determined based on the monitoring results of environmental monitoring sensors, it is determined whether the environment where the automated gardening equipment is located is rainy or snowy. This makes the weather judgment of the automated gardening equipment more accurate and effectively avoids the problem of inaccurate weather judgment caused by the simple rain and snow sensors being prone to false detection. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a flowchart illustrating the steps of a data processing method according to Embodiment 1 of this application;

[0011] Figure 2 This is a flowchart of the data processing method according to Embodiment 2 of this application;

[0012] Figure 3 This is a structural block diagram of the data processing device according to Embodiment 3 of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0014] To facilitate explanation and understanding, before describing the data processing methods, the structure and working environment of the automated gardening equipment will be briefly described as follows:

[0015] In this embodiment, the automatic gardening equipment can be an automatic lawnmower. Of course, in other embodiments, it can also be other self-moving equipment, and there is no limitation on this.

[0016] Automated gardening equipment can be used to mow lawns to ensure the grass reaches the required height. Automated gardening equipment includes a housing, mowing assembly, drive assembly, control assembly, and sensors. The mowing assembly, mounted on the housing, cuts the grass. The drive assembly moves the automated gardening equipment to automatically mow the lawn. The control assembly connects to the sensors, mowing assembly, and drive assembly, controlling the drive assembly and mowing assembly based on sensor monitoring results, thus enabling the automated gardening equipment to operate autonomously.

[0017] Sensors include, but are not limited to, cameras, rain and snow sensors, and collision sensors. Cameras can be used to acquire images of the environment in which automated gardening equipment is located, and the equipment can be positioned based on these images to determine its pose within the working area, thereby enabling navigation of the automated gardening equipment.

[0018] Collision sensors can detect collisions when automated gardening equipment encounters obstacles, allowing the equipment to replan its path.

[0019] When water droplets or snowflakes fall on a rain / snow sensor, its voltage or capacitance changes, thus detecting rain or snow. However, due to the complexity of real-world environments, dew, water droplets from lawn sprays, or other accidental water droplets falling onto the rain / snow sensor can also cause changes in its capacitance or voltage, leading to false detections.

[0020] To address this issue, this embodiment provides a data processing method, the implementation of which is described below:

[0021] like Figure 1 As shown, the method includes the following steps:

[0022] Step S102: Perform feature recognition on the environmental image of the automatic gardening equipment, and determine the first confidence level of the environment where the automatic gardening equipment is located based on the feature recognition results.

[0023] Environmental images can be images of the environment in which the automated gardening equipment is located, taken by a camera mounted on the equipment. For example, when the automated gardening equipment is performing a lawn mowing task according to a preset work assignment, it may take environmental images of the surrounding environment, including weather information, as it moves.

[0024] A trained neural network model capable of recognizing rain and snow is used to identify features in environmental images to obtain feature recognition results. Based on these results, a first confidence level of the weather information for the environment can be determined. This first confidence level indicates whether the environment in which the automated gardening equipment is located is rainy or snowy.

[0025] Of course, different neural network models can output weather information and first confidence scores in different forms. For example, the weather information can be rainy, and the first confidence score is the confidence score for rainy days, with a value of 0.95. Alternatively, the weather information can include multiple possible weather types, and the first confidence score is the confidence score corresponding to each possible weather type. In this case, the weather information and the first confidence score can be combined, such as: "light rain - 0.93", "moderate rain - 0.05", "heavy rain - 0.02", where light rain, moderate rain, and heavy rain can be possible weather types determined based on feature recognition results of environmental images, and 0.93, 0.05, and 0.02 can be the probabilities of each weather type.

[0026] Step S104: Obtain a second confidence level, which is determined based on the monitoring results of the environmental monitoring sensors mounted on the automated gardening equipment.

[0027] Environmental monitoring sensors can be rain and snow sensors. If the rain and snow sensor outputs a "true" result, meaning it has detected possible rain or snow, then the second confidence level is 100%. If the rain and snow sensor outputs a "false" result, meaning it has not detected rain or snow, then the second confidence level is 0%.

[0028] Step S106: Based on the first confidence level and the second confidence level, determine whether the working environment of the automatic gardening equipment is in a rainy or snowy weather.

[0029] Since individual rain and snow sensors may produce false detections, in order to improve reliability, a weighted sum is performed based on the first confidence level and the second confidence level. The result of the weighted sum is used to determine whether the environment is rainy or snowy.

[0030] For example, if the weighted sum is greater than or equal to a set weather threshold, it indicates that the environment is experiencing rain or snow. This method integrates information from environmental images and monitoring results from environmental sensors, improving the reliability of rain or snow detection and addressing the issue of insufficient accuracy in rain and snow sensors.

[0031] In this embodiment, feature recognition is performed based on environmental images collected by automated gardening equipment to obtain a first confidence level of weather information. By combining the first confidence level with a second confidence level determined based on the monitoring results of environmental monitoring sensors, it is determined whether the environment where the automated gardening equipment is located is rainy or snowy. This makes the weather judgment of the automated gardening equipment more accurate and effectively avoids the problem of inaccurate weather judgment caused by the simple rain and snow sensors being prone to false detection.

[0032] Example 2

[0033] Reference Figure 2The flowchart of the data processing method according to Embodiment 2 of this application is shown.

[0034] In this embodiment, the method includes the following steps:

[0035] Step S202: Perform feature recognition on the environmental image of the automatic gardening equipment, and determine the first confidence level of the weather information of the environment where the automatic gardening equipment is located based on the feature recognition results.

[0036] Environmental images can be captured by cameras installed on automated gardening equipment. These cameras can be integrated into the visual perception system of the automated gardening equipment. They can capture images of the surrounding environment of the equipment. Feature recognition results are then obtained by using a neural network model based on machine vision technology (such as a convolutional neural network model) to perform feature recognition on the environmental images.

[0037] The features identified by neural network models with different structures may vary. For example, a neural network model can identify at least one of the following features in an environmental image: ground moisture or snow cover, raindrop trajectory, snow trajectory, ambient color temperature, ambient light intensity, cloud shape, and cloud color. The neural network model can process the feature recognition results (the specific processing method is determined by the structure of the neural network model) to determine the first confidence level of the weather information. Some neural network models can directly output the first confidence level for rainy or snowy days, such as "rainy day -0.95" or "snowy day -0.05". Some neural network models can output more granular first confidence levels for different weather types, such as "light rain -0.93", "moderate rain -0.05", or "heavy rain -0.02".

[0038] The first confidence level of the ambient weather information can be the highest possible first confidence level. For example, in the example above, the first confidence level of the ambient weather information could be "light rain -0.93".

[0039] Step S204: Obtain a second confidence level, which is determined based on the monitoring results of the environmental monitoring sensors mounted on the automated gardening equipment.

[0040] Environmental monitoring sensors can be sensors capable of detecting rain or snow, such as rain and snow sensors. A rain and snow sensor includes at least two contacts exposed outside the housing of an automated gardening device, each contact connected to an electrode plate with an output circuit connected to it. When conductive substances such as rain, snow, or water droplets fall on the two contacts, at least one of the capacitance and voltage between the electrode plates changes, thereby changing the electrical signal (i.e., the monitoring result) output by the output circuit. The second confidence level can be 100% when the electrical signal output by the rain and snow sensor indicates that rain or snow has been detected. The second confidence level can be 0% when the electrical signal output by the rain and snow sensor indicates that rain or snow has not been detected.

[0041] Step S206: Based on the first confidence level and the second confidence level, determine whether the working environment of the automatic gardening equipment is in a rainy or snowy weather.

[0042] Since the second confidence level output by the rain and snow sensor can only indicate that a conductive object has fallen on the two contact points, but cannot accurately determine whether the conductive object is real rain or snow, it could be sprayed water droplets or dew, which may not necessarily mean that it is actually raining or snowing. In order to improve the accuracy of rain or snow detection and prevent the reduction in work efficiency caused by frequent task interruptions due to misjudgment, in this embodiment, step S206 can be implemented as follows: determine the first weight corresponding to the first confidence level and the second weight corresponding to the second confidence level, the sum of the first weight and the second weight is equal to 1; determine the total confidence level based on the first weight, the second weight, the first confidence level and the second confidence level; if the total confidence level is greater than or equal to a set weather threshold, then determine that the working environment of the automatic gardening equipment is a rainy or snowy day.

[0043] For example, the first and second weights are both 0.5, and the weather threshold can be set to 0.9. The first confidence level is "light rain -0.93". If the monitoring result output by the rain and snow sensor is true, then the second confidence level is 100%. The total confidence level is calculated as: 0.93 * 0.5 + 1 * 0.5 = 0.965. This value is greater than the set weather threshold (i.e., 0.9). Therefore, the current working environment is determined to be rainy.

[0044] Optionally, to further improve the accuracy of the determination, when determining the second weight corresponding to the second confidence level, the second weight can be determined based on the position of the environmental monitoring sensor on the automatic gardening equipment.

[0045] For example, when the environmental monitoring sensor is located in a position where it is easily dripped with dew, such as at the front of the vehicle, the second weight is reduced. It should be noted that since the sum of the second weight and the first weight is 1, the first weight can be determined accordingly after the second weight is determined.

[0046] Furthermore, the second weight can be adjusted appropriately based on the hardware configuration of the automated gardening equipment. For example, the second weight can be appropriately reduced for highly sensitive environmental monitoring sensors to avoid misjudgments. Similarly, the first and second weights can be adjusted according to different environments. For instance, the first weight can be increased and the second weight decreased for tropical or humid environments. Alternatively, the first weight can be adjusted based on the accuracy of the neural network model, without any restrictions.

[0047] By combining the camera with a traditional rain and snow sensor, the accuracy of weather information assessment of the surrounding environment is improved. If rain or snow is detected, this method can also execute step S208 to adjust the currently performing tasks of the automated gardening equipment, thereby ensuring the safety of the automated gardening equipment and improving its service life, reliability, and security.

[0048] Step S208: If it is determined that the environment is rainy or snowy, then the precipitation information of the environment is determined, and the working task of the automatic gardening equipment is adjusted according to the precipitation information.

[0049] In this embodiment, the precipitation information includes at least one of the actual precipitation level and the estimated precipitation amount.

[0050] The actual precipitation level can be determined as follows: based on the feature recognition results, determine the number of rain pixels or snow pixels in the environmental image; based on the proportion of rain pixels or snow pixels in the total pixels of the environmental image, determine the actual precipitation level of the environment.

[0051] For example, a neural network model can be used to perform feature recognition on an environmental image to obtain the feature recognition results. Based on the feature recognition results, pixels in the environmental image that belong to rain or snow can be determined. Typically, if rain pixels exist, the number of rain pixels and their proportion in the total number of pixels in the environmental image are calculated. Based on this proportion, the actual precipitation level of the environment can be determined, which can be heavy rain, moderate rain, or light rain.

[0052] The estimated precipitation can be determined by: obtaining weather forecast information for the local environment; and determining the estimated precipitation for the local environment based on the estimated precipitation per unit time and the duration of precipitation in the weather forecast information.

[0053] For example, a weather forecast server obtains weather forecast information for its location. This forecast information includes estimated precipitation per unit time and the duration of the precipitation. The estimated precipitation per unit time can be expressed as light rain, moderate rain, or heavy rain. For instance, if the precipitation within a unit time period is in the first level (the first level can range from 0 to a first set value, which can be determined as needed, such as 5 mm; the first level may not include the first set value), it is classified as light rain. If the precipitation within a unit time period is in the second level (which can be determined as needed), it is classified as moderate rain, etc. Based on this principle, a corresponding estimated precipitation per unit time can be determined based on whether the weather forecast indicates heavy rain, moderate rain, or light rain.

[0054] The duration of precipitation can be determined based on the start and end times of precipitation indicated in the weather forecast. More accurate precipitation information can be determined based on the precipitation duration, estimated precipitation per unit time, and the actual precipitation intensity. The estimated precipitation is determined using the estimated precipitation per unit time and the precipitation duration.

[0055] Based on precipitation information, the current work task being performed can be processed. For example, if the precipitation information indicates that the actual precipitation level is Level 1 (e.g., light rain), and the estimated precipitation is less than the safety threshold (which can be determined based on the structure of the automated gardening equipment to withstand a safe amount of water), then it can be determined that the precipitation will not affect the work and the current work task can continue. In a specific example, taking an automated lawnmower as an example, if it is determined that it is raining lightly in the environment, and the weather forecast information indicates that it is in the shower stage, and the estimated precipitation is less than the safety threshold and will not affect the safe operation of the automated lawnmower, then there is no need to stop the current lawnmower task.

[0056] Alternatively, if the real-time precipitation indicated by the precipitation information is at level one, and the estimated precipitation is greater than or equal to the safety threshold, the current task is stopped and the machine returns to the charging station. In a specific example, taking an automatic lawnmower as an example, if, during the automatic lawnmower's mowing task, it is determined that the environment is currently experiencing light rain, but the weather forecast indicates that continuous rainfall is imminent, and the estimated precipitation may gradually increase, exceeding the safety threshold, then the current mowing task needs to be stopped, and the machine needs to return to the charging station to avoid damage from the precipitation.

[0057] Alternatively, if the real-time precipitation indicated by the precipitation information is at level two (e.g., moderate rain), and the estimated precipitation is greater than or equal to a safety threshold, the current task is terminated, and an anomaly message is generated. In a specific example, taking an automatic lawnmower as an example, if, during the lawnmower's mowing task, it is determined that heavy rain is starting and the weather forecast indicates it will continue for a considerable period, and the estimated precipitation exceeds the safety threshold, then the current task's movement needs to be stopped, and an anomaly message is generated and reported. This anomaly message alerts the user that the automatic lawnmower is currently experiencing strong environmental interference and may not be able to return to the charging station, urging them to pay attention to equipment safety, etc.

[0058] This allows for the assessment of environmental conditions, such as rainfall or snowfall, and, combined with weather forecast information, the risk level of the task can be predicted. This enables decisions on whether to continue the task, ensuring the intelligence, accuracy, and reliability of the decisions, and thus guaranteeing the safety of the automated gardening equipment.

[0059] Optionally, in order to achieve better working results, adjusting the working tasks of the automatic gardening equipment according to the precipitation information further includes: obtaining information on the termination of tasks; and generating a successor task to be executed within the allowed operating time period based on the information on the termination of tasks and the allowed operating time period.

[0060] For example, information on aborting a task includes, but is not limited to: the time the task was aborted, the position of the automated gardening equipment at the time the task was aborted, and the planned path of the aborted task.

[0061] Based on the information about the aborted task and the allowed running time (also known as the window time) set by the user for the automatic gardening equipment to work automatically, the running time of the successor task is determined so that the aborted task can be resumed at an appropriate time.

[0062] This embodiment utilizes visual perception combined with rain and snow sensors to determine whether the environment is rainy or snowy, thereby improving the accuracy of the judgment. Visual perception based on environmental images can analyze whether it is raining or snowing and determine the amount of precipitation, thus improving both accuracy and information richness. Based on richer environmental information, decisions can be made that better meet the machine's performance requirements and the user's cognitive needs, improving the lawnmower's environmental adaptability, mowing efficiency, and overall user experience.

[0063] Example 3

[0064] Reference Figure 3 The diagram shows a structural block diagram of the data processing apparatus according to Embodiment 3 of this application.

[0065] The device includes:

[0066] The identification module 302 is used to perform feature recognition on the environmental image of the automatic gardening equipment, and determine the first confidence level of the weather information of the environment where the automatic gardening equipment is located based on the feature recognition result. The first confidence level is used to indicate whether the environment where the automatic gardening equipment is located is a rainy day or a snowy day.

[0067] The acquisition module 304 is used to acquire a second confidence level, which is determined based on the monitoring results of the environmental monitoring sensors mounted on the automated gardening equipment;

[0068] The first determining module 306 is used to determine, based on the first confidence level and the second confidence level, whether the working environment of the automatic gardening equipment is in a rainy or snowy weather.

[0069] Optionally, the device further includes:

[0070] The second determining module 308 is used to determine the precipitation information of the environment if it is determined that the environment is rainy or snowy, and adjust the working task of the automatic gardening equipment according to the precipitation information.

[0071] Optionally, the precipitation information includes the actual precipitation level, and the second determining module 308 is used to determine the number of rain pixels or snow pixels in the environmental image based on the feature recognition result when determining the precipitation information of the environment; and to determine the actual precipitation level of the environment based on the proportion of the number of rain pixels in the total pixels of the environmental image or the proportion of the number of snow pixels in the total pixels of the environmental image.

[0072] Optionally, the precipitation information includes estimated precipitation, and the second determining module 308 is used to obtain weather forecast information of the environment when determining the precipitation information of the environment; and to determine the estimated precipitation of the environment based on the estimated precipitation per unit time and precipitation duration in the weather forecast information.

[0073] Optionally, the second determining module 308 is configured to, when adjusting the working task of the automatic gardening equipment based on the precipitation information, if the actual precipitation level indicated by the precipitation information belongs to the first level and the estimated precipitation amount of the precipitation information is greater than or equal to the safety threshold, then suspend the current working task and return to the charging pile; or, if the actual precipitation level indicated by the precipitation information belongs to the second level and the estimated precipitation amount of the precipitation information is greater than or equal to the safety threshold, then suspend the current working task and generate abnormal information.

[0074] Optionally, the second determining module 308 is used to obtain information on task suspension when adjusting the working task of the automatic gardening equipment according to the precipitation information; and to generate a successor task to be executed within the allowed operating time period based on the information on task suspension and the allowed operating time period.

[0075] Optionally, the first determining module 306 is used to determine the first weight corresponding to the first confidence level and the second weight corresponding to the second confidence level, wherein the sum of the first weight and the second weight is equal to 1; to determine the total confidence level based on the first weight, the second weight, the first confidence level and the second confidence level; and if the total confidence level is greater than or equal to a set weather threshold, then it is determined that the working environment of the automatic gardening equipment is in a rainy or snowy weather.

[0076] Optionally, the first determining module 306 is used to determine the second weight based on the position of the environmental monitoring sensor in the automatic gardening equipment when determining the second weight corresponding to the second confidence level.

[0077] The device can achieve the same effect as the method described above, so it will not be described in detail here.

[0078] Example 4

[0079] In this embodiment, an automatic gardening device is provided, which includes a controller. The controller is used to execute the aforementioned data processing method and achieve the corresponding effect, which will not be described in detail here.

[0080] Example 5

[0081] In this embodiment, a computer program product is provided, including computer instructions that instruct a computing device to perform the data processing method described above.

[0082] It should be noted that in the description of this invention, the terms "first" and "second" are used only for convenience in describing different components or names, and should not be construed as indicating or implying a sequential relationship, relative importance, or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first" and "second" may explicitly or implicitly include at least one of those features.

[0083] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0084] It should be noted that although specific embodiments of the present invention have been described in detail with reference to the accompanying drawings, this should not be construed as limiting the scope of protection of the present invention. Various modifications and variations that can be made by those skilled in the art without inventive effort within the scope described in the claims still fall within the scope of protection of the present invention.

[0085] The examples of the embodiments of the present invention are intended to concisely illustrate the technical features of the embodiments of the present invention, so that those skilled in the art can intuitively understand the technical features of the embodiments of the present invention, and are not intended to be an improper limitation of the embodiments of the present invention.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data processing method, characterized in that, include: The environmental image of the automated gardening equipment is subjected to feature recognition, and a first confidence level of the weather information of the environment where the automated gardening equipment is located is determined based on the feature recognition result. The first confidence level is used to indicate whether the environment where the automated gardening equipment is located is a rainy day or a snowy day. A second confidence level is obtained, which is determined based on the monitoring results of the environmental monitoring sensors mounted on the automated gardening equipment; Based on the weighted sum of the first confidence level and the second confidence level, it is determined whether the working environment of the automatic gardening equipment is in a rainy or snowy weather. If it is determined that the environment is rainy or snowy, then the precipitation information of the environment is determined, wherein the precipitation information includes at least one of the actual precipitation level and the estimated precipitation amount; and the working task of the automatic gardening equipment is adjusted according to the precipitation information, including: if the actual precipitation level indicated by the precipitation information is at level one, and the estimated precipitation amount is greater than or equal to a safety threshold, then the current working task is stopped and the device returns to the charging station; if the actual precipitation level indicated by the precipitation information is at level two, and the estimated precipitation amount is greater than or equal to a safety threshold, then the current working task is stopped and an anomaly information is generated; if the actual precipitation level indicated by the precipitation information is at level one, and the estimated precipitation amount is less than a safety threshold, then the current working task continues.

2. The method according to claim 1, characterized in that, The precipitation information includes the actual precipitation level, and the precipitation information for determining the current environment includes: Based on the feature recognition results, determine the number of rain pixels or snow pixels in the environmental image; The actual precipitation level of the environment is determined based on the proportion of rain pixels or snow pixels in the total pixels of the environmental image.

3. The method according to claim 1 or 2, characterized in that, The precipitation information includes estimated precipitation, and the precipitation information for determining the local environment includes: Obtain weather forecast information for your surroundings; Based on the estimated precipitation per unit time and precipitation duration in the weather forecast information, determine the estimated precipitation in the environment.

4. The method according to claim 3, characterized in that, The step of adjusting the working tasks of the automatic gardening equipment based on the precipitation information includes: If it is determined that the current environment is experiencing light rain, and the weather forecast information indicates that continuous rainfall is imminent and the estimated rainfall is likely to gradually increase and exceed the safety threshold, then the current work task is terminated and the user returns to the charging station. Here, the rainfall within a unit time period is considered to be at the first level when it is determined that the environment is experiencing light rain. If it is determined that the current environment is experiencing moderate rain, and the weather forecast information indicates that it will continue for a long time and the estimated precipitation exceeds the safety threshold, then the current work task will be suspended and an abnormal information will be generated. In this case, if the precipitation per unit time period is at the second level, it is determined that the environment is experiencing moderate rain. If it is determined that the current environment is experiencing light rain, the weather forecast information indicates that it is in the shower stage, and the estimated precipitation is less than the safety threshold, then the current work task can continue.

5. The method according to claim 4, characterized in that, The step of adjusting the working tasks of the automatic gardening equipment based on the precipitation information also includes: Get information about the aborted task; Based on the information of the aborted task and the allowed running time period, a follow-up task to be executed within the allowed running time period is generated.

6. The method according to claim 1, characterized in that, The step of determining whether the environment in which the automatic gardening equipment operates is in rainy or snowy weather based on the weighted sum of the first confidence level and the second confidence level includes: Determine the first weight corresponding to the first confidence level and the second weight corresponding to the second confidence level, wherein the sum of the first weight and the second weight is equal to 1; The total confidence level is determined based on the first weight, the second weight, the first confidence level, and the second confidence level. If the total confidence level is greater than or equal to the set weather threshold, then it is determined that the working environment of the automatic gardening equipment is in a rainy or snowy weather.

7. The method according to claim 6, characterized in that, Determining the second weight corresponding to the second confidence level includes: The second weight is determined based on the location of the environmental monitoring sensor on the automated gardening equipment.

8. A data processing apparatus, characterized in that, include: The recognition module is used to perform feature recognition on the environmental image of the automatic gardening equipment, and determine the first confidence level of the weather information of the environment where the automatic gardening equipment is located based on the feature recognition result. The first confidence level is used to indicate whether the environment where the automatic gardening equipment is located is a rainy day or a snowy day. An acquisition module is used to acquire a second confidence level, which is determined based on the monitoring results of environmental monitoring sensors mounted on the automated gardening equipment; The first determining module is used to determine whether the working environment of the automatic gardening equipment is in a rainy or snowy weather based on the weighted sum of the first confidence level and the second confidence level. The second determining module is used to determine the precipitation information of the environment if it is determined that the environment is rainy or snowy, wherein the precipitation information includes at least one of the actual precipitation level and the estimated precipitation amount; and to adjust the working task of the automatic gardening equipment according to the precipitation information; the second determining module is specifically used to stop the current working task and return to the charging pile if the actual precipitation level indicated by the precipitation information belongs to the first level and the estimated precipitation amount of the precipitation information is greater than or equal to the safety threshold. If the actual precipitation level indicated by the precipitation information is Level 2, and the estimated precipitation amount is greater than or equal to the safety threshold, then the current task is terminated and an anomaly information is generated; if the actual precipitation level indicated by the precipitation information is Level 1, and the estimated precipitation amount is less than the safety threshold, then the current task continues.

9. An automatic gardening device, characterized in that, Includes a controller for performing the method of any one of claims 1-7.

10. A computer program product comprising computer instructions that instruct a computing device to perform the method as described in any one of claims 1-7.

Images