Watering operation control method, system and device and medium

Abstract

The invention provides a watering operation control method, which comprises the following steps: acquiring movement data of a target object, the movement data comprising at least one of position data, movement speed and movement direction of the target object; determining a risk score of the target object based on the mobile data; and triggering risk avoiding control in response to the fact that the risk score is greater than the preset threshold, thereby realizing intelligent identification of the working environment, realizing intelligent control, reducing the influence on residents and improving the working efficiency.

Description

Technical Field

[0001] This specification relates to the field of environmental sanitation management technology, and in particular to a watering operation control method, system, device and medium. Background Art

[0002] With the advancement of smart city construction, the demand for intelligent sanitation operations is growing. Sprinkler trucks, as important equipment for urban sanitation, rely heavily on manual operation for traditional control methods. They are unable to dynamically sense obstacles or people ahead and are prone to accidentally injuring pedestrians when spraying water in densely populated areas (such as schools and business districts), leading to frequent complaints and even accidents.

[0003] Therefore, it is necessary to provide an improved sprinkler operation control method, system, device and medium that can realize intelligent identification of the working environment, realize intelligent control, reduce the impact on residents and improve work efficiency. Summary of the Invention

[0004] One or more embodiments of the present specification provide a method for controlling a watering operation, comprising: obtaining movement data of a target object, wherein the movement data includes at least one of position data, movement speed, and movement direction of the target object; determining a risk score of the target object based on the movement data; and triggering risk avoidance control in response to the risk score being greater than a preset threshold.

[0005] In some embodiments, the method further includes: acquiring vehicle status data, the vehicle status data including at least one of vehicle speed, driving direction, and watering status; and determining a watering control instruction based on the movement data and the vehicle status data.

[0006] In some embodiments, the method further includes: acquiring environmental data; the environmental data includes at least one of environmental wind speed, environmental type, and light intensity; and determining a vehicle control mode based on the environmental data.

[0007] In some embodiments, the method further includes: obtaining risk avoidance control data, water sprinkler control data, and control mode data; and determining the operation score of the water sprinkler operation through a scoring model based on the risk avoidance control data, water sprinkler control data, and control mode data, wherein the scoring model is a machine learning model.

[0008] At the same time, one or more embodiments of the specification provide a sprinkler operation control system, including a first acquisition module, configured to: acquire movement data of a target object, wherein the movement data includes at least one of the position data, movement speed, and movement direction of the target object; a risk assessment module, configured to: determine the risk score of the target object based on the movement data; and a risk avoidance control module, configured to: trigger risk avoidance control in response to the risk score being greater than a preset threshold.

[0009] One or more embodiments of the present specification provide a watering operation control device, including a processor, wherein the processor is configured to execute the watering operation control method.

[0010] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a watering operation control method.

[0011] Beneficial effects: The present invention proposes a quantifiable and adaptive watering and avoidance control system with the advantages of high recognition accuracy, fast response speed, and strong platform verification closed loop. It can significantly reduce complaints and accidents caused by watering, improve the quality of sanitation operations and government supervision satisfaction, and has broad market promotion value. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0013] Figure 1 is a schematic diagram of a sprinkler control system according to some embodiments of this specification;

[0014] Figure 2 is an exemplary flow chart of a watering operation control method according to some embodiments of this specification;

[0015] Figure 3 is an exemplary schematic diagram of a scoring model according to some embodiments of this specification. DETAILED DESCRIPTION

[0016] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0017] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0018] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0019] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0020] Existing technologies have shortcomings in object recognition, response speed, environmental adaptability, and behavioral verification, and they also lack the collaborative integration of AI recognition, vehicle control, and cloud-based analysis. This invention aims to build a closed-loop pedestrian avoidance control system combining visual recognition, intelligent control, and platform verification, effectively improving the safety and intelligence of urban sanitation operations.

[0021] Figure 1 is an exemplary module diagram of a sprinkler operation control system according to some embodiments of this specification.

[0022] In some embodiments, as Figure 1 As shown, the watering operation control system 100 may include a first acquisition module 110 , a risk assessment module 120 , and a risk avoidance control module 130 .

[0023] In some embodiments, the first acquisition module is configured to acquire movement data of the target object, where the movement data includes at least one of position data, movement speed, and movement direction of the target object.

[0024] In some embodiments, the risk assessment module is configured to determine a risk score of the target object based on the movement data.

[0025] In some embodiments, the risk avoidance control module is configured to trigger risk avoidance control in response to the risk score being greater than a preset threshold.

[0026] In some embodiments, the watering operation control system also includes: a second acquisition module, configured to: acquire vehicle status data, wherein the vehicle status data includes at least one of vehicle speed, driving direction, and watering status; an instruction determination module, configured to: determine the watering control instruction based on the movement data and the vehicle status data.

[0027] In some embodiments, the sprinkler operation control system also includes: a third acquisition module, configured to: acquire environmental data; the environmental data includes at least one of environmental wind speed, environmental type, and light intensity; a mode control module, configured to: determine the vehicle control mode based on the environmental data.

[0028] In some embodiments, the sprinkler operation control system also includes: a fourth acquisition module, configured to: acquire risk avoidance control data, sprinkler control data, and control mode data; an operation scoring module, configured to: determine the operation score of the sprinkler operation based on the risk avoidance control data, sprinkler control data, and control mode data through a scoring model, and the scoring model is a machine learning model.

[0029] It should be noted that the above description of the sprinkler control system and its modules is for convenience only and does not limit this specification to the scope of the embodiments. It is understandable that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the modules or form subsystems connected to other modules without deviating from the principles. In some embodiments, Figure 1 The first acquisition module 110, risk assessment module 120, and risk avoidance control module 130 can be different modules within a system, or a single module can implement the functions of two or more of the aforementioned modules. For example, each module can share a storage module, or each module can have its own storage module. Such variations are within the scope of protection of this specification.

[0030] Figure 2 is an exemplary flow chart of a watering operation control method according to some embodiments of this specification. Figure 2 As shown, the process 200 includes the following steps: In some embodiments, the process 200 can be executed by a sprinkler operation control system.

[0031] Step 210: Acquire movement data of the target object.

[0032] The movement data includes at least one of the position data, movement speed, and movement direction of the target object.

[0033] In some embodiments, the sprinkler operation control system can be based on the AI ​​camera deployed at the front end of the vehicle and the deep learning model to identify pedestrians, bicycles, small tricycles and other objects in real time and obtain their parameters such as position, speed, and movement direction.

[0034] Step 220: Determine a risk score of the target object based on the movement data.

[0035] In some embodiments, the sprinkler operation control system can determine the risk scores of various target objects based on the following formula: Si = w1·Ci+w2·(1-di / Dmax), where Si is the comprehensive score, Ci is the recognition confidence, which can be obtained based on the AI ​​camera, di is the distance of the target object, which can be obtained based on the AI ​​camera, w1 and w2 are weights, which can be preset; Dmax is the upper limit of the recognition distance of the AI ​​camera.

[0036] Step 230: In response to the risk score being greater than a preset threshold, triggering risk avoidance control.

[0037] In some embodiments, the sprinkler operation control system can trigger the avoidance control logic when Si exceeds a set threshold (such as 0.75), thereby realizing visual perception and intelligent recognition of the sprinkler truck.

[0038] In some embodiments, the method further includes: acquiring vehicle status data, the vehicle status data including at least one of vehicle speed, driving direction, and watering status; and determining a watering control instruction based on the movement data and the vehicle status data.

[0039] In some embodiments, the sprinkler operation control system can send the recognition results to the VCU based on the AI ​​controller. The VCU issues sprinkler start and stop instructions based on the current status of the vehicle (speed, direction, sprinkler status, etc.). The response time is controlled within 300ms to ensure timely and reliable avoidance, thereby realizing intelligent avoidance of people by the sprinkler truck.

[0040] In some embodiments, the method further includes: acquiring environmental data; the environmental data includes at least one of environmental wind speed, environmental type, and light intensity; and determining a vehicle control mode based on the environmental data.

[0041] In some embodiments, the sprinkler operation control system can dynamically adjust the recognition strategy according to the operating environment. For example, when the wind speed is greater than 5m / s, the avoidance distance is increased, the recognition sensitivity is improved around schools, infrared recognition assistance is enabled at night, etc., thereby realizing dynamic parameter adjustment and regional strategy of the sprinkler truck.

[0042] In some embodiments, the method further includes: obtaining risk avoidance control data, water sprinkler control data, and control mode data; and determining the operation score of the water sprinkler operation through a scoring model based on the risk avoidance control data, water sprinkler control data, and control mode data, wherein the scoring model is a machine learning model.

[0043] For further explanation of the scoring model, see Figure 3 The corresponding content.

[0044] In some embodiments, the sprinkler control system can upload all avoidance behaviors, sprinkler records, and video data in real time to a cloud platform for statistical analysis and model training. The platform generates daily avoidance reports and risk level maps, supporting driver and operation area assessments, enabling platform verification and effectiveness evaluation.

[0045] In some embodiments, the sprinkler operation control system can use mechanisms such as federated learning to train the recognition model, combine manual review and big data statistics to continuously optimize parameters, and remotely update to the front-end AI controller via OTA to achieve closed-loop iteration, thereby realizing cloud-based optimization and closed-loop feedback.

[0046] Figure 3 It is a schematic diagram of the structure of the scoring model shown in some embodiments of this specification.

[0047] Scoring model 320 is a model used for scoring the operation of sanitation vehicles. In some embodiments, scoring model 320 can be a machine learning model, such as a neural network model (NN).

[0048] In some embodiments, the input of the scoring model 320 may include the risk avoidance control data 311, the watering control data 312, and the control mode data 313, and the output may include the operation score 330. For more information about the risk avoidance control data 311, the watering control data 312, and the control mode data 313, see Figure 2 corresponding instructions.

[0049] In some embodiments, the sprinkler operation control system may train the scoring model 320 based on the first training sample set.

[0050] The first sample set includes a first training sample and a corresponding first label.

[0051] In some embodiments, the first training sample includes sample risk avoidance control data, sample watering control data, and sample control mode data of a sample sprinkler truck in historical operation. The sprinkler operation control system can obtain the first training sample from the historical operation data of the sample sprinkler truck.

[0052] In some embodiments, the watering operation control system may determine the actual operation score of the historical operation corresponding to the first training sample as the first label. The actual operation score may be obtained based on manual review of the operation results or based on data such as employee performance evaluation.

[0053] In some embodiments, the sprinkler operation control system can perform multiple rounds of iterations, at least one of which includes: selecting one or more first training samples from a first sample data set, inputting the one or more first training samples into an initial scoring model, and obtaining model prediction outputs corresponding to the one or more first training samples; substituting the model prediction outputs corresponding to the one or more first training samples and the first labels of the one or more first training samples into a predefined loss function formula to calculate the value of the loss function; and reversely updating the model parameters in the initial scoring model based on the value of the loss function. This step can be performed using various methods. For example, the update can be based on the gradient descent method. When the iteration end condition is met, the iteration ends and a trained scoring model is obtained.

[0054] In some embodiments, the sprinkler operation control system can continuously optimize the scoring model through data learning to improve accuracy and adaptability.

[0055] In summary, the present invention proposes a quantifiable and adaptive watering and avoidance control system, which has the advantages of high recognition accuracy, fast response speed, and strong platform verification closed loop. It can greatly reduce complaints and accidents caused by watering, improve the quality of sanitation operations and government supervision satisfaction, and has broad market promotion value.

[0056] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0057] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0058] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0059] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A watering operation control method, characterized in that: include: Acquire movement data of a target object, wherein the movement data includes at least one of position data, movement speed, and movement direction of the target object; determining a risk score of the target object based on the movement data; In response to the risk score being greater than a preset threshold, risk avoidance control is triggered.

2. The method according to claim 1, characterized in that The method further comprises: Acquiring vehicle status data, wherein the vehicle status data includes at least one of vehicle speed, driving direction, and watering status; A watering control instruction is determined based on the movement data and the vehicle status data.

3. The method according to claim 1, characterized in that The method further comprises: Acquiring environmental data; the environmental data includes at least one of environmental wind speed, environmental type, and light intensity; Based on the environmental data, a vehicle control mode is determined.

4. The method according to claim 1, wherein The method further comprises: Obtain risk avoidance control data, sprinkler control data, and control mode data; Based on the risk avoidance control data, the watering control data, and the control mode data, an operation score of the watering operation is determined by a scoring model, and the scoring model is a machine learning model.

5. A watering operation control system, characterized in that: include A first acquisition module is configured to: acquire movement data of a target object, wherein the movement data includes at least one of position data, movement speed, and movement direction of the target object; a risk assessment module configured to: determine a risk score of the target object based on the movement data; The risk avoidance control module is configured to trigger risk avoidance control in response to the risk score being greater than a preset threshold.

6. The system according to claim 5, characterized in that The system further comprises: The second acquisition module is configured to: acquire vehicle status data, wherein the vehicle status data includes at least one of vehicle speed, driving direction, and watering status; The instruction determination module is configured to determine a watering control instruction based on the movement data and the vehicle status data.

7. The system according to claim 5, characterized in that The system further comprises: The third acquisition module is configured to: acquire environmental data; the environmental data includes at least one of environmental wind speed, environmental type, and light intensity; The mode control module is configured to determine a vehicle control mode based on the environmental data.

8. The system according to claim 5, wherein: The system further comprises: A fourth acquisition module is configured to: acquire risk avoidance control data, watering control data, and control mode data; The operation scoring module is configured to determine the operation score of the watering operation based on the risk avoidance control data, the watering control data, and the control mode data through a scoring model, wherein the scoring model is a machine learning model.

9. A watering operation control device, characterized in that: The method comprises a processor configured to execute the method according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that The storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method according to any one of claims 1 to 4.

Images