An information management method and system for ancient trees and famous trees

Abstract

The application is suitable for the technical field of ancient tree and famous tree management, and particularly relates to an ancient tree and famous tree information management method and system. The method comprises the following steps: delimiting a growth area of the ancient tree and famous tree, collecting a Bluetooth signal of a source terminal by using a Bluetooth receiver pre-deployed in the growth area, establishing a communication link, generating a shooting task, recording an entering time of each Bluetooth signal, calculating a staying duration based on a current time, and defining the source terminal with a staying duration greater than a threshold value as a target terminal; the shooting task is sent to the target terminal, image data of the ancient tree and famous tree uploaded by the target terminal is received, a lightweight feature recognition model is constructed, and the lightweight feature recognition model is integrated into the Bluetooth receiver. By determining a risk coefficient, invalid inspection of a low-risk area is avoided, manpower, time and materials are saved, the information management level of the ancient tree and famous tree is greatly improved, and accurate and timely ancient tree risk management is realized.

Description

Technical Field

[0001] This invention relates to the field of ancient and famous tree management technology, and in particular to an information management method and system for ancient and famous trees. Background Technology

[0002] Ancient and famous trees refer to trees that are over a certain age and possess significant historical, cultural, scientific, ecological, and ornamental value. They are not only "living fossils" of nature but also witnesses to the historical changes and cultural accumulation of a region. Due to their high ornamental and cultural value, ancient and famous trees often become popular tourist destinations. However, excessive visitor traffic can increase the pressure on their root systems, trunks, and the surrounding ecological environment, thereby accelerating damage and degradation.

[0003] The current management of ancient and famous trees generally relies on manual inspections. However, due to the low frequency of inspections and the heavy reliance on the personal experience and subjective judgment of the inspectors, the monitoring results are often not comprehensive or objective. This can easily lead to perfunctory records or even so-called "office data," where the data is not derived from actual on-site monitoring but is obtained through speculation or supplementation. This makes it difficult to detect and deal with problems such as pests and diseases, tree damage, or human-caused damage in a timely manner, missing the best time for intervention and maintenance, and posing potential risks to the healthy growth of ancient trees.

[0004] Therefore, "how to provide a data foundation for health monitoring of ancient and famous trees through pictures taken by tourists" is the technical problem that this invention needs to solve. Summary of the Invention

[0005] The purpose of this invention is to provide an information management method and system for ancient and famous trees, in order to solve the problem mentioned in the background art of "how to provide a data basis for health monitoring of ancient and famous trees through pictures taken by tourists".

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] An information management method for ancient and famous trees, the method comprising:

[0008] The growth areas of ancient and famous trees are delineated. Bluetooth receivers pre-deployed in the growth areas are used to collect Bluetooth signals from source terminals, establish communication links, generate shooting tasks, record the entry time of each Bluetooth signal, calculate the dwell time based on the current time, and define source terminals with dwell time greater than the threshold as target terminals.

[0009] The shooting task is sent to the target terminal, the image data of ancient and famous trees uploaded by the target terminal is received, a lightweight feature recognition model is constructed and integrated into the Bluetooth receiver, the feature recognition model is trained using a pre-labeled dataset, and it is determined whether the image data meets the valid standard rules.

[0010] If so, the image data is input into the pre-built risk identification model, the risk features are output, the location of the risk features is identified, and they are marked on the panoramic image of ancient and famous trees to obtain the guidance map, generate the risk review task, and send it to the reconstructed target terminal.

[0011] If not, generate a reminder pop-up, write a prompt message, and send the reminder pop-up to the target terminal;

[0012] Establish a time window, determine the monitoring results of each ancient and famous tree, configure a risk coefficient, and trigger a pre-built manual inspection mechanism when the risk coefficient exceeds the threshold.

[0013] Furthermore, the steps of delineating the growth area of ​​ancient and famous trees, using Bluetooth receivers pre-deployed within the growth area to collect Bluetooth signals from the source terminal, establishing a communication link, and generating a shooting task include:

[0014] Configure the influencing factors of the shooting task, wherein the influencing factors include at least: weather and time;

[0015] Based on the aforementioned influencing factors, an activation time is selected, with each shooting task corresponding to an activation time. When the activation time arrives, the shooting task is sent to the target terminal.

[0016] Furthermore, the method also includes:

[0017] Identify the risk factors that may affect the growth of ancient and famous trees, wherein the risk factors include at least: traffic flow and geographical location;

[0018] Obtain the identity information of each ancient and famous tree, set a monitoring frequency that corresponds one-to-one with each ancient and famous tree, and offset the activation time.

[0019] Furthermore, the step of training the feature recognition model using the pre-labeled dataset includes:

[0020] By using markers pre-placed among the ancient and famous trees, the ancient and famous trees corresponding to each image data can be identified;

[0021] Integrate all image data that meet valid standard rules to generate an image set, establish a one-to-one correspondence between risk features and the image set, and correct the monitoring results.

[0022] Furthermore, the steps of identifying the location of risk features and marking them on the panoramic image of ancient and famous trees to obtain a guidance map and generate a risk review task include:

[0023] Risk characteristics are clustered into several categories, each of which corresponds to a priority level, which consists of high, medium, and low.

[0024] When the risk review task has a high priority, the manual inspection mechanism is activated.

[0025] Furthermore, the steps of constructing a time window, determining the monitoring results for each ancient and famous tree, and configuring the risk coefficient include:

[0026] Edit a strategy set consisting of several emergency plans and create a comparison table, wherein the comparison table consists of: monitoring result items, risk coefficient items, and emergency plan items;

[0027] Plot a risk change trend graph with time on the horizontal axis and risk coefficient on the vertical axis, and insert labels generated from identity information.

[0028] Furthermore, the system includes:

[0029] The delineation module is used to delineate the growth area of ​​ancient and famous trees. It uses Bluetooth receivers pre-deployed in the growth area to collect Bluetooth signals from source terminals, establish communication links, generate shooting tasks, record the entry time of each Bluetooth signal, calculate the dwell time based on the current time, and define source terminals with dwell time greater than the threshold as target terminals.

[0030] The training module is used to send the shooting task to the target terminal, receive the image data of ancient and famous trees uploaded by the target terminal, build a lightweight feature recognition model, and integrate it into the Bluetooth receiver. The feature recognition model is trained using a pre-labeled dataset.

[0031] The judgment module is used to determine whether the image data meets the valid standard rules. If yes, the image data is input into the pre-built risk identification model, the risk features are output, the location of the risk features is identified, and they are marked on the panoramic image of ancient and famous trees to obtain the guidance map. The risk review task is generated and sent to the reconstructed target terminal. If no, a reminder pop-up is generated, a prompt message is written, and the reminder pop-up is sent to the target terminal.

[0032] The trigger module is used to construct a time window, determine the monitoring results of each ancient and famous tree, configure the risk coefficient, and trigger the pre-built manual inspection mechanism when the risk coefficient is greater than the threshold.

[0033] Furthermore, the delineation module includes:

[0034] A configuration unit is used to configure the influencing factors of the shooting task, wherein the influencing factors include at least: weather and time;

[0035] The distribution unit is used to select an activation time based on the influencing factors, wherein each shooting task corresponds to an activation time, and when the activation time is reached, the shooting task is distributed to the target terminal.

[0036] Furthermore, the training module includes:

[0037] The identification unit is used to identify the ancient and famous tree corresponding to each image data by using the markers pre-placed among the ancient and famous trees;

[0038] The correction unit is used to integrate all image data that conform to valid standard rules, generate an image set, establish a one-to-one correspondence between risk features and the image set, and correct the monitoring results.

[0039] Furthermore, the determination module includes:

[0040] Clustering unit, used to cluster risk characteristics into several categories, where each category corresponds to a priority, which consists of high, medium and low;

[0041] The activation unit is used to activate the manual inspection mechanism when the priority corresponding to the risk review task is high.

[0042] Compared with the prior art, the beneficial effects of the present invention are:

[0043] By defining shooting tasks, precise monitoring of ancient and famous trees can be achieved, improving the timeliness of data acquisition and effectively reducing labor costs. Calculating the duration of visitor stays improves the quality of image data, increases the completion rate of shooting tasks, and greatly enhances the ability to detect risks to ancient and famous trees. It also increases the enjoyment of visitors. By judging whether image data meets valid standards and rules, real-time feedback and correction can be provided, further improving the quality of image data and reducing data processing volume. By constructing a risk identification model, risk characteristics such as pests and diseases, mechanical damage, and branch breakage of ancient and famous trees can be quickly identified, improving monitoring accuracy and facilitating timely handling by management, thus greatly improving the management efficiency of ancient and famous trees. By generating review tasks, high-precision data of risk characteristic areas can be obtained. Data can be collected again based on the initial identification, greatly reducing misjudgments and omissions and improving the reliability of risk identification. By determining risk coefficients, ineffective inspections of low-risk areas can be avoided, saving manpower, time, and materials, greatly improving the level of information management of ancient and famous trees, and achieving accurate and timely risk management of ancient trees. Attached Figure Description

[0044] Figure 1 A flowchart illustrating the information management method for ancient and famous trees provided in this embodiment of the invention;

[0045] Figure 2 This is a first sub-flowchart of the information management method for ancient and famous trees provided in an embodiment of the present invention;

[0046] Figure 3 This is a second sub-flowchart of the information management method for ancient and famous trees provided in an embodiment of the present invention;

[0047] Figure 4 This is a third sub-flow flowchart of the information management method for ancient and famous trees provided in an embodiment of the present invention;

[0048] Figure 5 This is a fourth sub-flow flowchart of the information management method for ancient and famous trees provided in an embodiment of the present invention;

[0049] Figure 6 A block diagram illustrating the composition of the ancient and famous tree information management system provided in this embodiment of the invention;

[0050] Figure 7 A block diagram showing the composition of the delineation module in the ancient and famous trees information management system provided in this embodiment of the invention;

[0051] Figure 8 A block diagram illustrating the composition of the training module in the ancient and famous trees information management system provided in this embodiment of the invention;

[0052] Figure 9 A block diagram showing the composition of the judgment module in the ancient and famous tree information management system provided in this embodiment of the invention;

[0053] Figure 10 This is a block diagram of the trigger module in the ancient and famous tree information management system provided in this embodiment of the invention. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0055] In Example 1, Figure 1 The implementation flow of the information management method for ancient and famous trees provided in this embodiment of the invention is illustrated below, and is described in detail below:

[0056] S100: Delineate the growth area of ​​ancient and famous trees, use Bluetooth receivers pre-deployed in the growth area to collect Bluetooth signals from source terminals, establish a communication link, generate shooting tasks, record the entry time of each Bluetooth signal, calculate the dwell time based on the current time, and define source terminals with dwell times greater than the threshold as target terminals.

[0057] The growth area of ​​each ancient and famous tree is delineated. This area can be a park or scenic area. Depending on the number of ancient and famous trees in the area, one or more Bluetooth receivers are deployed. The Bluetooth receivers can be deployed in open areas under the canopy of the ancient and famous trees, but should not affect their normal growth. The Bluetooth receivers can collect Bluetooth signals from source terminals in real time. When a source terminal is detected, a communication link is established between the source terminal and the Bluetooth receiver. Source terminals include various types of devices used by tourists. A shooting task is generated, which includes shooting instructions or operation guides. The shooting task is mainly used to guide tourists to collect targeted data from the designated ancient trees in order to obtain image information that can be used for health monitoring and risk assessment. For example, a shooting task might be: "Please stand next to the red sign next to the ancient tree and take a horizontal photo of the entire ancient tree with your mobile phone, ensuring that the trunk, canopy, and ground soil are completely included in the frame."

[0058] When tourists enter the growth area, Bluetooth receivers deployed within the area can capture their Bluetooth signals in real time and record the corresponding moment, i.e., the entry time. The difference between the entry time and the current moment is calculated, and this difference represents the duration of stay. Source terminals whose duration of stay exceeds a preset threshold are defined as target terminals. In real life, if a tourist stays for a long time in the growth area of ​​ancient and famous trees, it often means that the tourist has a greater interest in the ancient and famous trees or is more familiar with the scenic area. Of course, it is also possible that the tourist is resting there. In any case, the tourist can be regarded as a high-potential data collection target because their stay provides a usable time window, which facilitates the issuance of shooting tasks, and the quality of the collected data will be higher. The collection process will not excessively affect the tourist's experience.

[0059] S200: Sends the shooting task to the target terminal, receives the image data of ancient and famous trees uploaded by the target terminal, constructs a lightweight feature recognition model, integrates it into the Bluetooth receiver, and trains the feature recognition model using a pre-labeled dataset.

[0060] The shooting task is sent to the target terminal. After receiving the shooting task, the target terminal takes pictures of the ancient and famous trees to obtain image data. A lightweight feature recognition model is constructed, which has the characteristics of low computing resource requirements, small model size and fast inference speed. The lightweight feature recognition model adopts a classic network architecture and is constructed by combining depthwise separable convolution technology. It is mainly used for real-time image recognition on edge devices (such as Bluetooth receivers, smart terminals, etc.). The feature recognition model is deployed in the Bluetooth receiver. Historical image data of ancient and famous trees are collected and manually labeled to obtain a dataset. In other words, the dataset consists of clear historical image data containing the full picture of ancient and famous trees (trunk, crown and ground soil environment). The feature recognition model is trained using the dataset. By constructing the feature recognition model, the data quality of image data can be improved and the data processing volume of the risk recognition model can be reduced.

[0061] S300: Determine whether the image data conforms to the valid standard rules. If yes, input the image data into the pre-built risk identification model, output the risk features, identify the location of the risk features, mark them on the panoramic image of ancient and famous trees, obtain the guidance map, generate the risk review task, and send it to the reconstructed target terminal. If no, generate a reminder pop-up window, write the prompt information, and send the reminder pop-up window to the target terminal.

[0062] Image data is input into a feature recognition model, which analyzes the image content and assesses whether it conforms to valid criteria, such as image clarity, angle (whether the image is tilted), complete representation of the ancient tree, and whether it includes the crown and ground soil environment. If the image data conforms to the criteria (valid criteria), it is then input into a risk identification model. This model, built on artificial intelligence, is primarily used to identify and judge potential risk features in images of ancient and famous trees. It requires training with a large amount of labeled data, including image samples of ancient and famous trees in different health states. The labels cover pests and diseases, broken branches, decay, mechanical damage, abnormal leaves, and dried ground soil. The risk identification model outputs the risk features in the image data, which are the aforementioned labeled content. If the image data does not... If a risk feature is identified, the risk identification model outputs a "no risk feature" or "no risk" result. The location of the risk feature in the image data is determined and mapped onto a panoramic view of the ancient and famous trees, resulting in a guidance map. In the guidance map, each risk feature is clearly displayed using a marker, color, or icon. Using the guidance map, a risk review task is generated. Similar to the shooting task, the risk review task typically involves magnifying the marked area, supplementing angles or details. For example, a risk review task might be: "Take close-up shots of the area with cracks or cavities in the middle of the ancient tree trunk (the specific location is shown in the guidance map in this window), capturing the length, width, and depth of the cracks, and ensuring that details are clearly visible." The target terminal is then reselected, and the risk review task is sent to it. The above steps are then repeated to continue analyzing and processing the image data uploaded by tourists corresponding to the risk review task.

[0063] If the image data taken by the tourist does not meet the valid standard rules, a reminder pop-up will be generated, and specific prompts will be written in the pop-up, such as "Please retake the photo to ensure that the main body of the ancient tree is clear and complete" or "Please adjust the shooting angle to cover the trunk and all branches". The reminder pop-up will be sent to the target terminal through the communication link so that the tourist can make corrections based on the feedback as soon as possible.

[0064] S400: Construct a time window, determine the monitoring results of each ancient and famous tree, configure the risk coefficient, and trigger the pre-constructed manual inspection mechanism when the risk coefficient is greater than the threshold.

[0065] Establish a time window, for example, from January 1st to February 1st. During this period, update the monitoring results of each ancient and famous tree and determine the corresponding risk coefficient. When the risk coefficient is greater than the threshold, activate the manual inspection mechanism and notify the inspection personnel to go to the site for further inspection and treatment.

[0066] For example, if the monitoring results of a certain ancient and famous tree show that a small number of dead branches or slightly yellowed leaves, and the corresponding risk coefficient is 0.2 (assuming the threshold is 0.5), then there is no need to carry out manual inspection immediately; regular inspections or observations can be arranged instead.

[0067] In Example 2, Figure 2 The implementation flow of the information management method for ancient and famous trees provided by an embodiment of the present invention is illustrated. The following details the steps of delineating the growth area of ​​ancient and famous trees, using a Bluetooth receiver pre-deployed in the growth area to collect Bluetooth signals from the source terminal, establishing a communication link, and generating a shooting task:

[0068] S101: Configure the influencing factors of the shooting task, wherein the influencing factors include at least: weather and time.

[0069] Identify the influencing factors for the shooting task, including weather and time; if the ancient and famous trees are in good health and do not show any risk characteristics in a short period of time, for example, when the weather is cloudy or rainy, image shooting can be avoided.

[0070] S102: Select an activation time based on the aforementioned influencing factors, wherein each shooting task corresponds to an activation time. When the activation time arrives, the shooting task is sent to the target terminal.

[0071] Based on the influencing factors, an activation time is selected, which is the time suitable for image capture. When the activation time arrives, the capture task is issued. It should be noted that in this application, each ancient and famous tree corresponds to one capture task, and the activation time for each capture task is not the same.

[0072] In Embodiment 3, unlike Embodiment 1, the method further includes:

[0073] Identify the risk factors that may affect the growth of ancient and famous trees, wherein the risk factors include at least: traffic flow and geographical location;

[0074] Obtain the identity information of each ancient and famous tree, set a monitoring frequency that corresponds one-to-one with each ancient and famous tree, and offset the activation time.

[0075] Based on the environment and location within the growth area of ​​ancient and famous trees, identify factors that may affect their normal growth, i.e., risk factors; set identity information for each ancient and famous tree, such as a number or identifier, and set a monitoring frequency for each tree, adjusting the activation time according to the monitoring frequency; for example, if an ancient and famous tree is located in a tourist route or core area of ​​the scenic spot, is popular, and has a large flow of people, making it prone to human damage, a higher monitoring frequency can be set, while ancient and famous trees located in corners of the scenic spot with less traffic can be set to a lower monitoring frequency.

[0076] In Example 4, Figure 3 The implementation flow of the information management method for ancient and famous trees provided in this embodiment of the invention is illustrated. The following details the steps of training the feature recognition model using a pre-labeled dataset:

[0077] S201: Using markers pre-placed among ancient and famous trees, identify the ancient and famous tree corresponding to each image data.

[0078] To quickly identify the ancient or famous tree corresponding to each image data, an identifier can be placed on each tree, such as a colored ribbon, which can be tied to a branch or trunk.

[0079] S202: Integrate all image data that meet the valid standard rules, generate an image set, establish a one-to-one correspondence between risk features and the image set, and correct the monitoring results.

[0080] In actual management, multiple images of an ancient or famous tree may exist within the same time window. By integrating all the image data and generating an image set, if the risk identification model discovers that the ancient or famous tree has risk characteristics, and the existence of these risk characteristics is confirmed through a risk review task, then the specific scope and details of the risk characteristics can be analyzed by examining the image set.

[0081] In Example 5, Figure 4 The implementation flow of the information management method for ancient and famous trees provided by an embodiment of the present invention is illustrated below. The steps of identifying the location of risk characteristics, marking them on the panoramic map of ancient and famous trees to obtain a guidance map, and generating a risk review task are described in detail below:

[0082] S301: Cluster the risk characteristics into several categories, where each category corresponds to a priority, which consists of high, medium and low.

[0083] Risk characteristics are clustered and divided into several categories, such as branch breakage, pests and diseases, decay, and mechanical damage. Each category is assigned a corresponding priority, usually divided into three levels: high, medium, and low. High priority categories represent risk characteristics that may pose a serious threat to the growth and safety of ancient and famous trees and require immediate attention and handling.

[0084] S302: When the priority of the risk review task is high, the manual inspection mechanism is activated.

[0085] When the risk identification model is used to process the risk review task, if the ancient and famous trees do indeed have risk characteristics and the corresponding priority is high, the manual inspection mechanism will be activated immediately.

[0086] In Example 6, Figure 5 The implementation flow of the information management method for ancient and famous trees provided by an embodiment of the present invention is illustrated. The following details the steps of constructing a time window, determining the monitoring results of each ancient and famous tree, and configuring the risk coefficient:

[0087] S401: Edit a strategy set consisting of several emergency plans and create a lookup table, wherein the lookup table consists of: monitoring result items, risk coefficient items, and emergency plan items.

[0088] Multiple emergency plans are created, and the set of emergency plans constitutes a strategy set. Each possible monitoring result corresponds to an emergency plan. The correspondence between monitoring results, risk coefficients, and emergency plans is contained in a reference table. Continuing with the example in S400, the monitoring result of a certain ancient and famous tree is: a small number of dead branches or slightly yellowed leaves. The corresponding emergency plan can be to increase the monitoring frequency.

[0089] S402: Plot a risk change trend graph with time as the horizontal axis and risk coefficient as the vertical axis, and insert labels generated from identity information.

[0090] By drawing risk change trend charts, the changing trends in the health status of ancient and famous trees can be displayed intuitively, and a data basis can be provided for the formulation of inspection plans and intervention decisions.

[0091] Figure 6 This diagram illustrates the structural composition of the ancient and famous tree information management system provided in an embodiment of the present invention. The ancient and famous tree information management system 1 includes:

[0092] The delineation module 11 is used to delineate the growth area of ​​ancient and famous trees. It uses Bluetooth receivers pre-deployed in the growth area to collect Bluetooth signals from source terminals, establish communication links, generate shooting tasks, record the entry time of each Bluetooth signal, calculate the dwell time based on the current time, and define source terminals with dwell times greater than the threshold as target terminals.

[0093] Training module 12 is used to send the shooting task to the target terminal, receive the image data of ancient and famous trees uploaded by the target terminal, build a lightweight feature recognition model, and integrate it into the Bluetooth receiver. The feature recognition model is trained using a pre-labeled dataset.

[0094] The judgment module 13 is used to judge whether the image data meets the valid standard rules. If yes, the image data is input into the pre-built risk identification model, the risk features are output, the location of the risk features is identified, and they are marked on the panoramic image of ancient and famous trees to obtain the guidance map. The risk review task is generated and sent to the reconstructed target terminal. If no, a reminder pop-up is generated, a prompt message is written, and the reminder pop-up is sent to the target terminal.

[0095] Trigger module 14 is used to construct a time window, determine the monitoring results of each ancient and famous tree, configure the risk coefficient, and trigger the pre-constructed manual inspection mechanism when the risk coefficient is greater than the threshold.

[0096] Figure 7 This diagram illustrates the structural composition of the ancient and famous tree information management system provided in an embodiment of the present invention. The delineation module 11 includes:

[0097] Configuration unit 111 is used to configure the influencing factors of the shooting task, wherein the influencing factors include at least: weather and time;

[0098] The sending unit 112 is used to select an activation time based on the influencing factors, wherein each shooting task corresponds to an activation time, and when the activation time is reached, the shooting task is sent to the target terminal.

[0099] Figure 8 This diagram illustrates the structural composition of the ancient and famous tree information management system provided in an embodiment of the present invention. The training module 12 includes:

[0100] The determining unit 121 is used to determine the ancient and famous tree corresponding to each image data by using the markers pre-placed among the ancient and famous trees;

[0101] The correction unit 122 is used to integrate all image data that conform to valid standard rules, generate an image set, establish a one-to-one correspondence between risk features and the image set, and correct the monitoring results.

[0102] Figure 9 This diagram illustrates the structural composition of the ancient and famous tree information management system provided in an embodiment of the present invention. The judgment module 13 includes:

[0103] Clustering unit 131 is used to cluster risk characteristics into several categories, wherein each category corresponds to a priority, and the priority consists of high, medium and low.

[0104] The activation unit 132 is used to activate the manual inspection mechanism when the priority corresponding to the risk review task is high.

[0105] Figure 10 This diagram illustrates the structural composition of the ancient and famous tree information management system provided in an embodiment of the present invention. The trigger module 14 includes:

[0106] Editing unit 141 is used to edit a strategy set consisting of several emergency plans and create a comparison table, wherein the comparison table includes: monitoring result items, risk coefficient items and emergency plan items;

[0107] The plotting unit 142 is used to plot a risk change trend graph with time as the horizontal axis and risk coefficient as the vertical axis, and insert labels generated from identity information.

[0108] The delineation module 11 is mainly used to complete step S100, the training module 12 is mainly used to complete step S200, the judgment module 13 is mainly used to complete step S300, and the triggering module 14 is mainly used to complete step S400.

[0109] Configuration unit 111 is mainly used to complete step S101, and distribution unit 112 is mainly used to complete step S102;

[0110] The determining unit 121 is mainly used to complete step S201, and the correcting unit 122 is mainly used to complete step S202;

[0111] Clustering unit 131 is mainly used to complete step S301, and activation unit 132 is mainly used to complete step S302;

[0112] The editing unit 141 is mainly used to complete step S401, and the drawing unit 142 is mainly used to complete step S402.

[0113] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0115] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An information-based management method for ancient and famous trees, characterized in that, The method includes: The growth areas of ancient and famous trees are delineated. Bluetooth receivers pre-deployed in the growth areas are used to collect Bluetooth signals from source terminals, establish communication links, generate shooting tasks, record the entry time of each Bluetooth signal, calculate the dwell time based on the current time, and define source terminals with dwell time greater than the threshold as target terminals. The shooting task is sent to the target terminal, the image data of ancient and famous trees uploaded by the target terminal is received, a lightweight feature recognition model is constructed and integrated into the Bluetooth receiver, the feature recognition model is trained using a pre-labeled dataset, and it is determined whether the image data meets the valid standard rules. If so, the image data is input into the pre-built risk identification model, the risk features are output, the location of the risk features is identified, and they are marked on the panoramic image of ancient and famous trees to obtain a guidance map, generate a risk review task, and send it to the reselected target terminal; If not, generate a reminder pop-up, write a prompt message, and send the reminder pop-up to the target terminal; Establish a time window, determine the monitoring results of each ancient and famous tree, configure a risk coefficient, and trigger a pre-built manual inspection mechanism when the risk coefficient exceeds the threshold.

2. The information management method for ancient and famous trees according to claim 1, characterized in that, The steps of delineating the growth area of ​​ancient and famous trees, using Bluetooth receivers pre-deployed within the growth area to collect Bluetooth signals from the source terminal, establishing a communication link, and generating a shooting task include: Configure the influencing factors of the shooting task, wherein the influencing factors include at least: weather and time; Based on the aforementioned influencing factors, an activation time is selected, with each shooting task corresponding to an activation time. When the activation time arrives, the shooting task is sent to the target terminal.

3. The information management method for ancient and famous trees according to claim 2, characterized in that, The method further includes: Identify the risk factors that may affect the growth of ancient and famous trees, wherein the risk factors include at least: traffic flow and geographical location; Obtain the identity information of each ancient and famous tree, set a monitoring frequency that corresponds one-to-one with each ancient and famous tree, and offset the activation time.

4. The information management method for ancient and famous trees according to claim 1, characterized in that, The steps of training the feature recognition model using a pre-labeled dataset include: By using markers pre-placed among the ancient and famous trees, the ancient and famous trees corresponding to each image data can be identified; Integrate all image data that meet valid standard rules to generate an image set, establish a one-to-one correspondence between risk features and the image set, and correct the monitoring results.

5. The information management method for ancient and famous trees according to claim 1, characterized in that, The steps of identifying the location of risk features, marking them on the panoramic image of ancient and famous trees to obtain a guidance map, and generating a risk review task include: Risk characteristics are clustered into several categories, each of which corresponds to a priority level, which consists of high, medium, and low. When the risk review task has a high priority, the manual inspection mechanism is activated.

6. The information management method for ancient and famous trees according to claim 3, characterized in that, The steps for establishing the time window, determining the monitoring results for each ancient and famous tree, and configuring the risk coefficient include: Edit a strategy set consisting of several emergency plans and create a comparison table, wherein the comparison table consists of: monitoring result items, risk coefficient items, and emergency plan items; Taking time as the abscissa and the risk coefficient as the ordinate, draw a risk change trend graph and insert the label generated from the identity information.

7. An information management system for ancient and famous trees, characterized in that, The system includes: A demarcation module, which is used to demarcate the growth area of ancient and famous trees, collect the Bluetooth signals of the source terminals by using the Bluetooth receivers pre-deployed in the growth area, establish a communication link, generate a shooting task, record the entry time of each Bluetooth signal, calculate the residence duration based on the current moment, and define the source terminals with a residence duration greater than the threshold as target terminals; A training module, which is used to send the shooting task to the target terminals, receive the image data of the ancient and famous trees uploaded by the target terminals, construct a lightweight feature recognition model and integrate it into the Bluetooth receivers, and use the pre-annotated dataset to train the feature recognition model; A judgment module, which is used to judge whether the image data meets the effective standard rules. If so, input the image data into the pre-constructed risk recognition model, output the risk features, identify the locations where the risk features are located, and mark them on the panoramic image of the ancient and famous trees to obtain a guidance map, generate a risk review task, and send it to the re-selected target terminals. If not, generate a reminder pop-up window, write the prompt information, and send the reminder pop-up window to the target terminals; A trigger module, which is used to construct a time window, determine the monitoring results of each ancient and famous tree, configure the risk coefficient, and trigger the pre-constructed manual inspection mechanism when the risk coefficient is greater than the threshold.

8. The information management system for ancient and famous trees according to claim 7, characterized in that, The demarcation module includes: A configuration unit, which is used to configure the influencing factors of the shooting task, where the influencing factors at least include: weather and time; A sending unit, which is used to select the activation time via the influencing factors, where each shooting task corresponds to an activation time, and when the activation time comes, send the shooting task to the target terminals.

9. The information management system for ancient and famous trees according to claim 7, characterized in that, The training module includes: A determination unit, which is used to determine the ancient and famous trees corresponding to each image data by using the markers pre-laid in the ancient and famous trees; A correction unit, which is used to integrate all the image data that meet the effective standard rules, generate an image set, establish a one-to-one correspondence between the risk features and the image set, and correct the monitoring results.

10. The information management system for ancient and famous trees according to claim 7, characterized in that, The judgment module includes: A clustering unit, which is used to cluster the risk features into several categories, where each category corresponds to a priority, and the priorities are composed of high, medium, and low; An activation unit, which is used to activate the manual inspection mechanism when the priority corresponding to the risk review task is high.

Images