Big Data-Based Landscape Greening Maintenance System and Methods

Abstract

This invention relates to the field of forestry data processing technology, specifically to a big data-based landscape greening maintenance system and method. The system includes: a water potential monitoring module, a block division module, a pruning adjustment module, a work time scheduling module, and an anomaly identification module. In this invention, by tracking the consistency of soil moisture fluctuations in real time, the dynamic influence of root type and soil structure on water absorption is accurately analyzed. Combined with plant transpiration physiological indicators and differences in meteorological conditions, water demand levels are refined, achieving efficient matching between water supply and plant physiological state. The pruning cycle is dynamically adjusted according to the actual changes in plant photosynthesis and tissue expansion, effectively reducing coordination errors between maintenance work time calculation and geographical path planning, improving the continuity and timeliness of anomaly response identification, significantly improving the accuracy and refinement of landscape plant maintenance decisions, and enhancing the scientific decision-making ability, spatial adaptability, and intelligent response level of greening maintenance management.

Description

Technical Field

[0001] This invention relates to the field of forestry data processing technology, and in particular to a landscaping maintenance system and method based on big data. Background Technology

[0002] The field of forestry data processing technology encompasses the collection, storage, analysis, and utilization of various data and information within forestry ecosystems. It primarily aims to improve the scientific rigor and precision of forestry resource management, including forest resource surveys, forest health monitoring, vegetation growth analysis, disaster early warning, and monitoring of environmental factors in forest areas. Data sources include remote sensing images, sensor data, geographic information system data, and manually collected data. Forestry data processing, through the establishment of data models and information system platforms, enables information-based management and decision support in forestry activities, forming a complete technical system covering front-end data collection, mid-stage processing, and back-end applications. This system is applied to multiple sub-fields such as forest resource management, ecological restoration, carbon sequestration assessment, pest and disease monitoring, and greening maintenance. Among these, big data-based landscaping maintenance systems... The system refers to the construction of a data management and decision support platform for urban landscaping management by integrating environmental monitoring nodes, GIS map data of green areas, plant variety databases, and maintenance behavior records. It addresses technical aspects of landscaping such as vegetation growth status identification, maintenance frequency setting, pest and disease early warning, and irrigation and fertilization scheduling. By deploying IoT monitoring devices to acquire parameters such as light, temperature, humidity, and soil moisture, and combining the spatial location of green areas with plant variety characteristics, it utilizes rule-based matching maintenance strategy models and database query algorithms to complete the classification management of green areas and the generation of dynamic maintenance tasks. Combined with a fixed-block-based patrol path planning method, it supports the partitioned storage and time-series analysis of maintenance data, enabling the generation of daily maintenance operation suggestions and task scheduling for the region.

[0003] Traditional landscaping maintenance techniques rely on static rule matching and database queries for landscaping area management. They lack the ability to process real-time feedback on soil water potential fluctuations and actual plant growth dynamics in the arrangement of plant growth and maintenance tasks. There is a time lag and incoordination between the frequency of plant maintenance operations and environmental changes. They are unable to adapt flexibly to rapidly changing environmental conditions, resulting in reduced accuracy of maintenance operations and negative impacts such as water waste, decreased plant health, and increased maintenance costs. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by proposing a big data-based garden greening maintenance system and method.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a big data-based landscaping maintenance system includes:

[0006] The water potential monitoring module divides the garden area into multiple blocks, analyzes the consistency of soil moisture changes at multiple humidity and water potential sensor nodes within the blocks, combines the influence of plant root type and soil structure on water absorption behavior, detects abnormal water events in the blocks, and generates water absorption offset comparison results.

[0007] The block division module calls the water absorption offset comparison results to obtain the leaf area index, transpiration rate per unit area, air temperature, and wind speed of the plant samples in the block, calculates the water evapotranspiration intensity of the plants in each block, groups and classifies the blocks, and generates water requirement level aggregated segments.

[0008] The pruning adjustment module uses the water requirement level aggregation segment to obtain daily plant leaf area and chlorophyll index data in each segment, analyzes the consistency and trend of plant photosynthesis and tissue expansion, calculates the pruning demand intensity of the plant, adjusts the pruning cycle, and generates maintenance cycle adjustment results.

[0009] The work scheduling module uses the maintenance cycle adjustment results to calculate the workload and duration requirements for each section based on the correspondence between plant type and maintenance work density. Combined with geographical location information, it plans a maintenance task list and generates a work task planning record.

[0010] As a further aspect of the present invention, the water absorption offset comparison result specifically includes the frequency index of wetting change, the water absorption behavior difference coefficient, and the node consistency judgment result; the water requirement level aggregation section includes the evapotranspiration intensity distribution range, water requirement level classification number, and spatial continuous segment information; the maintenance cycle adjustment result specifically includes the leaf area growth coordination coefficient, photosynthetic expansion matching degree, and pruning rhythm change cycle; and the operation task planning record includes the plant type operation density distribution, task combination arrangement order, and path continuity sorting information.

[0011] As a further aspect of the present invention, the water potential monitoring module includes:

[0012] The garden area division submodule divides the garden area into multiple blocks, extracts data collected from multiple humidity and water potential sensor nodes, and generates a humidity node spatial distribution table by combining the geographical coordinates of the nodes.

[0013] The humidity fluctuation analysis submodule extracts the humidity and water potential nodes within each block in the continuous monitoring period based on the humidity node spatial distribution table, analyzes the correlation and temporal consistency of the change trends between nodes, evaluates the degree of coordination of humidity changes within each block, and generates a humidity change consistency index.

[0014] The moisture anomaly detection submodule calls the moisture change consistency index, combines the influence of plant root type and soil structure on water absorption behavior, sets a moisture offset judgment interval for each node, filters abnormal data points, calculates the degree of moisture anomaly in each block, detects moisture anomaly events in the block, and generates water absorption offset comparison results.

[0015] As a further aspect of the present invention, the block partitioning module includes:

[0016] The sample index extraction submodule calls the water absorption offset comparison results to obtain the leaf area index, transpiration rate per unit area, air temperature, and wind speed values ​​of the plant samples in the block, and generates a sample index collection table.

[0017] The water evapotranspiration calculation submodule uses the sample index aggregation table to call the leaf area index, normalized transpiration rate, normalized temperature, and normalized wind speed of each sample to calculate the water evapotranspiration intensity index of each block.

[0018] The grade aggregation and classification submodule calls the water evapotranspiration intensity index, merges and groups the blocks according to the index values ​​of adjacent blocks, marks the aggregation number of the grouped blocks, and generates water demand grade aggregation segments.

[0019] As a further aspect of the present invention, the trimming adjustment module includes:

[0020] The leaf data acquisition submodule uses the water requirement level aggregation section to collect daily plant leaf area and chlorophyll index data of plants in each section, and performs normalization processing on the data to generate a leaf physiological normalization parameter sequence.

[0021] The growth trend analysis submodule analyzes the consistency and trend of plant photosynthesis and tissue expansion based on the leaf physiological normalization parameter sequence, and on the degree of coordination and growth trend of data changes, to obtain growth coordination trend information.

[0022] The pruning demand calculation submodule calls the growth coordination trend information to calculate the pruning demand intensity of each segment, calculates the pruning demand intensity index of each segment, adjusts the pruning cycle of each segment, and generates the maintenance cycle adjustment result.

[0023] As a further aspect of the present invention, the work time scheduling module includes:

[0024] The task requirement calculation submodule uses the maintenance cycle adjustment results to calculate the task quantity and duration requirements for each section based on the correspondence between each plant type and the density of maintenance work, combined with the distribution of various plants in the section, and obtains the task quantity requirement data.

[0025] The path order adjustment submodule calls the task volume requirement data, combines it with the geographical location information of each block, and adjusts the execution order of each segment by analyzing the continuity of the path to obtain the optimized sequence.

[0026] The maintenance task planning submodule optimizes the sequence according to the given order, and plans the maintenance task list by combining the duration requirements and execution order of maintenance tasks in each section, and establishes a work task planning record.

[0027] As a further aspect of the present invention, the system further includes:

[0028] The anomaly identification module calls the task planning record, collects and compares the variation differences between sunlight intensity and leaf color response in a continuous time period, analyzes the abnormal response state of the plant to light changes, and identifies abnormal light response events based on the persistence of the abnormal response state, records the start time of the event, and generates light response lag information.

[0029] The light response lag information specifically refers to the difference value between sunlight and color response, the continuous time period of response lag, and the abnormal state marker node.

[0030] As a further aspect of the present invention, the anomaly identification module includes:

[0031] The sunshine data acquisition submodule calls the operation task planning record to collect sunshine intensity data and leaf color response data in each section within a continuous period, and generates sunshine response dataset.

[0032] The response difference analysis submodule compares the changes in solar intensity and leaf color response in each cycle based on the solar response dataset, identifies the degree of difference in each time period, analyzes the abnormal response state, and obtains the light response abnormal state sequence.

[0033] The abnormal state recording submodule uses the light response abnormal state sequence to record the start time and duration of abnormal events according to the duration period of the abnormal state, and establishes light response hysteresis information.

[0034] A big data-based method for landscape greening maintenance, which is executed based on the aforementioned big data-based landscape greening maintenance system, includes the following steps:

[0035] S1: Divide the garden area into multiple blocks, collect the soil moisture change curves of humidity sensing nodes and water potential sensing nodes in each block, analyze the synchronicity of soil moisture fluctuations between different nodes in the block, and combine the characteristics of plant root system and soil layer distribution to detect abnormal water events in the block and generate water absorption offset comparison results.

[0036] S2: Based on the water absorption offset comparison results, collect the leaf area index, transpiration rate per unit area, air temperature, and wind speed values ​​of plant samples in each block, calculate the water evapotranspiration intensity of plants in each block, group and classify the blocks to obtain water requirement level aggregation sections.

[0037] S3: Based on the water requirement level aggregation section, collect the daily leaf area index and chlorophyll index of plants in each section, analyze the consistency and trend of plant photosynthesis and tissue expansion, quantify the pruning requirements of plants, adjust the pruning and maintenance cycle, and establish the maintenance cycle adjustment results.

[0038] S4: Based on the maintenance cycle adjustment results, according to the correspondence between plant type and maintenance work density, combined with the quantity distribution of each type of plant in the section and the maintenance work content, calculate the total maintenance work and expected operation time of each section, and adjust the execution order of maintenance tasks in combination with geographical location, maintenance task list, and obtain operation task planning records.

[0039] S5: Based on the task planning record, collect and compare the variation differences between sunlight intensity and leaf color response in a continuous time period, analyze the abnormal response state of the plant to light changes, and identify abnormal light response events based on the persistence of the abnormal response state, record the start time of the event, and establish light response lag information.

[0040] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0041] In this invention, by tracking the consistency of soil moisture fluctuations in real time, the dynamic impact of root type and soil structure on water absorption is accurately analyzed. Combined with plant transpiration physiological indicators and differences in meteorological conditions, water requirement levels are refined to achieve efficient matching between water supply and plant physiological state. The pruning cycle is dynamically adjusted according to the actual changes in plant photosynthesis and tissue expansion, effectively reducing the coordination error between maintenance time calculation and geographical path planning, improving the continuity and timeliness of abnormal response identification of light changes, significantly improving the accuracy and refinement of garden plant maintenance decisions, and enhancing the scientific decision-making ability, spatial adaptability and intelligent response level of greening maintenance management. Attached Figure Description

[0042] Figure 1 This is a system flowchart of the present invention;

[0043] Figure 2 This is a flowchart of the water potential monitoring module of the present invention;

[0044] Figure 3 This is a flowchart of the block partitioning module of the present invention;

[0045] Figure 4 This is a flowchart of the trimming and adjustment module of the present invention;

[0046] Figure 5 This is a flowchart of the work time scheduling module of the present invention;

[0047] Figure 6 This is a flowchart of the anomaly identification module of the present invention. Detailed Implementation

[0048] 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.

[0049] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0050] Please see Figure 1 This invention provides a technical solution: a big data-based landscaping maintenance system comprising:

[0051] The water potential monitoring module divides the garden area into multiple blocks, analyzes the consistency of soil moisture changes at multiple humidity and water potential sensor nodes within the blocks, combines the influence of plant root type and soil structure on water absorption behavior, detects abnormal water events in the blocks, and generates water absorption offset comparison results.

[0052] The block division module calls the water absorption offset comparison results to obtain the leaf area index, transpiration rate per unit area, air temperature, and wind speed values ​​of plant samples within the block. It calculates the water evapotranspiration intensity of plants within each block, groups and classifies the blocks, and generates aggregated water requirement levels.

[0053] The pruning adjustment module aggregates water requirement levels into zones, obtains daily plant leaf area and chlorophyll index data for each zone, analyzes the consistency and trends of plant photosynthesis and tissue expansion, calculates the intensity of plant pruning needs, adjusts the pruning cycle, and generates maintenance cycle adjustment results.

[0054] The work scheduling module uses the maintenance cycle adjustment results to calculate the workload and duration requirements of each section based on the correspondence between plant type and maintenance work density. Combined with geographical location information, it plans the maintenance task list and generates work task planning records.

[0055] The anomaly identification module calls the task planning record, collects and compares the differences in changes between sunlight intensity and leaf color response over a continuous time period, analyzes the abnormal response state of the plant to changes in light, and identifies abnormal light response events based on the persistence of the abnormal response state, records the start time of the event, and generates light response lag information.

[0056] The water absorption offset comparison results specifically include the frequency index of wetting changes, the difference coefficient of water absorption behavior, and the node consistency judgment results. The water requirement level aggregation section includes the evapotranspiration intensity distribution range, water requirement level classification number, and spatial continuous segment information. The maintenance cycle adjustment results specifically include the leaf area growth coordination coefficient, the degree of photosynthetic expansion matching, and the pruning rhythm change cycle. The operation task planning record includes the plant type operation density distribution, the task combination arrangement order, and the path continuity sorting information. The light response lag information specifically refers to the difference value between sunlight and color response, the continuous time period of response lag, and the abnormal state marker node.

[0057] Please see Figure 2 The water potential monitoring module includes:

[0058] The garden area division submodule divides the garden area into multiple blocks, extracts data collected from multiple humidity and water potential sensor nodes, and generates a humidity node spatial distribution table by combining the geographical coordinates of the nodes.

[0059] First, a GPS positioning instrument was used to measure the overall outline of the garden area, obtaining its latitude and longitude coordinates. Then, GIS software was used for data processing, dividing the entire garden area into multiple sub-areas using a regular rectangular grid method. Each sub-area was set to 25 square meters and numbered 1, 2, 3, etc. For example, area number 1 is located in the southeast corner of the garden, with latitude and longitude coordinates ranging from (31.212345, 121.567890) to (31.212500, 121.568045), and so on. Based on this grid division, the geographic coordinates of the moisture and water potential sensor nodes pre-installed in the garden soil were matched. The system automatically extracts the latitude and longitude coordinates of nodes using GIS tools and marks the specific blocks where the nodes are located. For example, if block number 1 contains humidity sensors A1 and A2 and water potential sensor B1, then the node data for A1 (31.212400, 121.567950), A2 (31.212480, 121.568030), and B1 (31.212420, 121.567970) are recorded. After all nodes are located, the system uses GIS tools to export the complete set of data corresponding to latitude and longitude coordinates and node numbers. Combining the numbering sorting rules and node types, a spatial distribution table of humidity nodes is finally generated.

[0060] Table 1 Spatial Distribution of Humidity Nodes:

[0061] ;

[0062] As shown in Table 1, the spatial distribution table of humidity nodes clearly describes the location distribution of each node in the garden space and the block to which it belongs, providing a basis for subsequent monitoring data processing.

[0063] The humidity fluctuation analysis submodule extracts the humidity and water potential data sequence of each block within a continuous monitoring period based on the spatial distribution table of humidity nodes, analyzes the correlation and temporal consistency of the changing trends between nodes, evaluates the degree of coordination of humidity changes within each block, and generates a humidity change consistency index.

[0064] Based on the spatial distribution table of humidity nodes, humidity and water potential sensor node data for each block in the garden area are continuously collected. Each monitoring node automatically records data once per hour. Assuming a complete monitoring cycle of 24 hours, for example, nodes A1 and A2 in block 1 record humidity data at 00:00, 01:00...23:00 respectively, generating data sequences for the nodes. For example, the data sequence for node A1 is [32.1%, 31.8%, 31.5%...30.9%], and the data sequence for node A2 is [32.2%, 32.0%, 31.6%...30.7%]. Subsequently, the trends of humidity changes between nodes are compared. The correlation calculation first calculates the change value between adjacent time points. For example, the humidity change of node A1 from 00:00 to 01:00 is 0.3%. Then, the correlation between the change trends of the two nodes at each time point is calculated. For example, the correlation coefficient between nodes A1 and A2 in the 24-hour period is calculated using the Pearson correlation coefficient, and the value is 0.93, indicating that the humidity change trends of the two nodes are highly coordinated. Finally, after processing all block nodes using a similar method, the average value of the correlation coefficient is used as the humidity change consistency index of each block. For example, the humidity change consistency index of block 1 is 0.89. This process is repeated to complete the data processing of all blocks, and finally, a humidity change consistency index table is generated.

[0065] The moisture anomaly detection submodule calls the moisture change consistency index, combines the influence of plant root type and soil structure on water absorption behavior, sets a moisture offset judgment interval for each node, and filters out abnormal data points using the following formula:

[0066] ;

[0067] Calculate the degree of moisture anomaly in each block, detect moisture anomaly events in the blocks, and generate water absorption offset comparison results;

[0068] in, Let q represent the degree of moisture anomaly in the q-th block. The humidity monitoring value for the a-th abnormal node is obtained by collecting data from the humidity or water potential sensor at that node during the current monitoring period. The wetting offset judgment boundary for the a-th node is set based on root type and soil structure, and is jointly set by a lookup table of root type and soil structure parameters of the plant to which the node belongs. The humidity difference data between the c-th pair of adjacent nodes is calculated by the difference between the monitoring values ​​of the two adjacent nodes. To determine the spatial continuity level of the b-th anomalous node, the level classification is calculated by analyzing the spatial distance and arrangement direction of this node relative to surrounding anomalous nodes. denoted as b, the number of anomalous nodes within its neighborhood is obtained by counting anomalous nodes within a fixed radius. A represents the total number of nodes identified as anomalous in the block, obtained by determining whether the wetting offset exceeds the set judgment boundary and counting the number of nodes that meet the condition. B represents the number of spatially clustered anomalous groups in the block, obtained by clustering continuously distributed anomalous nodes and counting the number of clusters. C represents the number of adjacent node pairs used for difference calculation in the block, obtained by extracting node pairs that meet the distance condition based on the spatial layout and counting them. a represents the index number of the anomalous node, b represents the index number of the anomalous node in the anomalous cluster, and c represents the index number of the adjacent node pair.

[0069] Based on the consistency index of moisture change, for example, if the consistency index of moisture change in block 1 is 0.89, the preset moisture offset judgment boundary is first queried. According to the plant root type (soil-rooted plants) and soil structure (sandy loam), the moisture offset judgment boundary is set at 28%-33%. Therefore, the moisture monitoring value of node A1 in block 1 is 30.9%, and that of node A2 is 30.7%, both within the boundary range. Assuming there is a node A3 located in block 2 with a monitoring value of 27.0%, significantly lower than the lower limit of the judgment boundary of 28%, this node is defined as an abnormal node. Subsequently, [further steps are taken]. The calculation of humidity difference data between adjacent nodes within Block 2 is as follows: For example, the humidity difference between node A3 (27.0%) and its neighboring node B2 (29.2%) is 2.2%. The square root of the sum of the squares of all adjacent node differences is taken, assuming the result is 3.6%. The spatial continuity level is then assessed. The spatial distance between node A3 and surrounding anomalous nodes is calculated using Euclidean distance. For example, if the distance to the nearest anomalous node is 0.8 meters, the spatial continuity level is defined as level 2. If there are 3 anomalous nodes within a fixed radius of 1 meter, the number of anomalous clusters in the region, B, is 1. The degree of anomalousness is then calculated using a formula. :

[0070] ;

[0071] ;

[0072] In the formula, For node A3 monitoring value, To determine the lower limit of the boundary value for wetness, Differences between adjacent nodes For spatial continuity, The parameter represents the number of abnormal nodes. The degree of water anomaly refers to the combined expression of the intensity and concentration trend of the deviation of the soil moisture state in the root zone of plants within a garden area from their normal water absorption behavior. This parameter reflects not only whether the moisture state of an individual node is abnormal, but also whether these anomalies exhibit regional clustering, thereby identifying problems such as localized water supply imbalance, soil permeability barriers, or system irrigation failure. In garden maintenance systems, this parameter can serve as a priority indicator in task scheduling, dynamically adjusting inspection frequency, irrigation resource input, or control system response rhythm, focusing management actions on areas with significant water imbalance risks. The calculated anomaly degree value is 1.94. This value is then compared to a preset anomaly judgment benchmark of 1.5. If it exceeds the benchmark, a water anomaly event is confirmed in the area, generating a water absorption offset comparison result for that area as "anomaly event occurred," and marking the start time of the event, for example, 23:00 on the same day. The formula accurately quantifies the degree of node anomaly through the combined calculation of moisture differences between nodes and the clustering of node anomalies, making the detection results more sensitive and accurate.

[0073] Please see Figure 3 The block partitioning module includes:

[0074] The sample index extraction submodule calls the water absorption offset comparison results to obtain the leaf area index, transpiration rate per unit area, air temperature, and wind speed values ​​of plant samples within the block, and generates a sample index aggregation table.

[0075] The water absorption offset comparison results are used as the input basis. Taking block 2 as an example, the system first retrieves the water absorption offset comparison results. Block 2 is the area where water anomalies occur. The system automatically filters and determines the plant sample numbers for this block from the garden plant database, for example, three plant samples numbered Z1, Z2, and Z3. Then, the specific index data of each plant sample is retrieved, and data collection and processing are performed item by item. The leaf area index (LAI) is obtained by identifying and processing UAV remote sensing images. Taking sample Z1 as an example, the LAI value is 2.4 obtained by analyzing the plant canopy and using image analysis tools for pixel analysis and area conversion. The transpiration rate per unit area is measured in the field by a transpiration meter. For example, the transpiration rate measured for plant Z1 is 4.2 mmol·m³. -2 ·s -1 Temperature parameters are measured by temperature sensors within the block; for example, sensor T1 measures 30.0°C. Wind speed parameters are measured using anemometers; for example, anemometer F1 records a wind speed of 2.3 m / s. -1 After collecting data from all plant samples, database management software is used to compile and form a unified data table, namely the sample index collection table, which records the specific monitoring indicators and numbers of each sample for easy calculation and retrieval later.

[0076] Table 2 Sample Index Collection Table:

[0077] ;

[0078] As shown in Table 2, the sample index aggregation table clearly reflects the specific parameter data of each sample, providing basic data for the next step of evapotranspiration intensity calculation.

[0079] The water evapotranspiration calculation submodule, based on the sample index aggregation table, calls up the leaf area index, normalized transpiration rate, normalized air temperature, and normalized wind speed for each sample, using the following formula:

[0080] ;

[0081] Calculate the moisture evapotranspiration intensity index for each block;

[0082] in, Let x be the moisture evapotranspiration intensity index of block x. The leaf area index of the nth sample is obtained through remote sensing imagery or on-site measurement. This is the normalized value of the transpiration rate per unit area for the nth sample, obtained through normalization processing of transpiration measurement data. The normalized value of the air temperature for the nth sample is obtained through normalization processing of temperature sensor data. The normalized value of the wind speed for the nth sample is obtained by normalizing the measured data from the anemometer. The area of ​​block x is the normalized value, obtained by the ratio of the current block area to the largest block area. N is the number of samples in the block, obtained by counting the number of all sample points in the block. n is the sample index number.

[0083] Based on the sample data of Block 2 in Table 2, the following explanation is provided. First, the parameters are normalized. The normalized leaf area index (LAI) value is based on the maximum LAI value of 4.0 for the entire garden. For example, the normalized leaf area index value of sample Z1 is 2.4 / 4.0 = 0.6. Similarly, Z2 and Z3 are 0.7 and 0.75, respectively. The transpiration rate is normalized based on the maximum measured value of 6.0 mmol·m³ within the garden area. -2 ·s -1 Based on the baseline, the normalized value of sample Z1 is 4.2 / 6.0 = 0.7, Z2 and Z3 are 0.77 and 0.83 respectively. Temperature normalization is based on the highest annual temperature of 38.0°C in the garden, so Z1 is 30.0 / 38.0 = 0.79, and similarly Z2 and Z3 are 0.80 and 0.82 respectively. Wind speed normalization is based on the highest historical wind speed of 4.0 m / s in the garden. -1Based on this, Z1 is 2.3 / 4.0 = 0.58. Similarly, Z2 and Z3 are 0.65 and 0.53 respectively. The normalized area value is based on the largest area of ​​the entire garden, 40 square meters. Block 2 has an area of ​​25 square meters, so the normalized area value is 25 / 40 = 0.625. Substituting the above normalized data into the formula, we calculate the moisture evapotranspiration intensity index of block 2:

[0084] ;

[0085] ;

[0086] ;

[0087] ;

[0088] The evapotranspiration intensity index reflects the overall water loss capacity of a vegetation community under the adjustment of current environmental conditions within a specific garden block at a spatial scale. Specifically, it measures the overall water demand and stress intensity of plants in that block. This index not only describes the evapotranspiration output characteristics within a single block but also ensures direct comparison between indices of different blocks through normalization. It can serve as a key input factor for subsequent water management, block water demand classification, and irrigation scheduling priority allocation, helping the management system focus on spatial areas with higher water demand risk. The calculated evapotranspiration intensity index for Block 2 is 3.5152, indicating the water evapotranspiration capacity of the plant community under current environmental conditions and clarifying the relative intensity of water demand in that block. The formula, by comprehensively considering multiple factors such as leaf area index, transpiration rate, air temperature, and wind speed, yields a more accurate and comprehensive quantitative index of plant evapotranspiration intensity.

[0089] The grade aggregation and classification submodule calls the water evapotranspiration intensity index, merges and groups the blocks according to the index values ​​of adjacent blocks, marks the aggregation number of the grouped blocks, and generates water demand grade aggregation segments.

[0090] Based on the aforementioned water evapotranspiration intensity index data, adjacent blocks are grouped and classified according to the difference in intensity index. For example, the index of block 2 is 3.5152, the index of neighboring block 1 is 3.2100, and the index of block 3 is 3.8200. First, the intensity index merging difference threshold is set to 0.5. This threshold is obtained from historical garden maintenance experience and has been experimentally verified. Blocks with differences within 0.5 are merged into the same aggregate segment, while those exceeding the threshold are divided separately. The intensity index difference between block 2 and neighboring block 1 is 0.3052, which is less than the threshold of 0.5, so they are merged into the same aggregate segment. The difference between block 3 and block 2 is 0.3048, which is also less than the threshold. The three together form an aggregate segment, which is marked as G1. Other blocks are evaluated in this way to generate a complete table of aggregate segments based on water demand level.

[0091] Table 3: Water Demand Level Aggregation Zone Table

[0092] ;

[0093] As shown in Table 3, the water demand level aggregation section table reflects the aggregation status of each block combination and the corresponding index range, which facilitates the subsequent formulation of targeted irrigation and maintenance measures.

[0094] Please see Figure 4 The trimming adjustment module includes:

[0095] The leaf data acquisition submodule uses water requirement level aggregation sections to collect daily plant leaf area and chlorophyll index data of plants in each section, and performs normalization processing on the data to generate a leaf physiological normalization parameter sequence.

[0096] The water requirement level aggregation section serves as the basic input for leaf data collection. Taking aggregation section G1 (including blocks 1, 2, and 3) as an example, representative plant samples (numbered Z1, Z2, and Z3) are first selected, and daily leaf area data for each plant is collected. This is measured daily using a laser leaf area meter. For example, the leaf area of ​​plant Z1 over three consecutive days is 25.0 cm², 25.6 cm², and 26.2 cm², respectively. Simultaneously, the chlorophyll index is measured daily using a chlorophyll meter. For example, the corresponding chlorophyll index for Z1 is 40 SPAD, 42 SPAD, and 43 SPAD. SPAD data were acquired and then normalized. Based on the maximum leaf area of ​​32.0 cm² and the maximum chlorophyll index of 50 SPAD, the normalized data for plant Z1 on the first day were leaf area 25.0 / 32.0 = 0.78 and chlorophyll index 40 / 50 = 0.80, respectively. The normalized data for the next two days were (0.80, 0.84) and (0.82, 0.86). After normalization of other plants Z2 and Z3, the data were arranged in sequence to form a sequence of normalized leaf physiological parameters, laying the data foundation for growth trend analysis.

[0097] The growth trend analysis submodule analyzes the consistency and trend of plant photosynthesis and tissue expansion based on the leaf physiological normalized parameter sequence, the degree of coordination of data changes and growth trends, and obtains growth coordination trend information.

[0098] Using leaf physiological normalized parameter sequence data as input, the daily normalized growth and growth trend of each plant were calculated. Taking plant Z1 as an example, the normalized growth of leaf area over two consecutive days was calculated as follows: Day 2: 0.80 - 0.78 = 0.02; Day 3: 0.82 - 0.80 = 0.02. Similarly, the normalized growth of chlorophyll index was calculated as 0.04 and 0.02. A data consistency analysis was then performed, specifically by comparing the absolute differences in leaf area and chlorophyll index growth each day. For example, the difference on Day 2 was |0.02 - 0.04| = 0.02, and on Day 3... |0.02-0.02|=0.00. The mean of the difference values ​​represents the degree of coordination as (0.02+0.00) / 2=0.01. Further analysis of the overall growth trend is conducted to calculate whether the continuous growth amount shows a daily increasing or decreasing trend. The high consistency of the growth amount of plant Z1 indicates good coordination. Similarly, the coordination and trend of Z2 and Z3 are calculated. The coordination indicators of each plant are summarized to obtain the overall coordination trend information of section G1, that is, the average coordination value of leaf area and chlorophyll index of each plant is 0.015, indicating the coordinated growth status of the plants in the section.

[0099] The pruning demand calculation submodule calls the growth coordination trend information to calculate the pruning demand intensity for each segment using the following formula:

[0100] ;

[0101] Calculate the pruning demand intensity index for each section, adjust the pruning cycle for each section, and generate maintenance cycle adjustment results;

[0102] in, The pruning demand intensity index for segment k is... The number of plants within segment k. Assign index numbers to the plants within the section. The normalized increase in leaf area index (LAI) of plant j is obtained by dividing the change in LAI over consecutive days by the maximum LAI. The normalized increase in chlorophyll index for the j-th plant is obtained by dividing the change in chlorophyll index over consecutive observation days by the maximum chlorophyll index. The normalized growth rate of the leaf area index of the j-th plant is obtained by statistically analyzing the average of the normalized increments of the leaf area index over three or more days. The normalized growth rate of the chlorophyll index of the j-th plant is obtained by statistically analyzing the average of the normalized increments of the chlorophyll index over three or more days. For section numbering;

[0103] Based on the growth coordination trend information, taking the data of plant G1 in the aggregation section as an example, and using three plants (Z1, Z2, and Z3) as examples, the standardized and growth rate indices of the normalized difference in growth for each plant are calculated sequentially. Taking plant Z1 as an example, its normalized difference in growth is 0.02 on the second day and 0.00 on the third day. The average growth rate of leaf area index is (0.02 + 0.02) / 2 = 0.02, and the growth rate of chlorophyll index is (0.04 + 0.02) / 2 = 0.03. Substituting these data into the formula:

[0104] ;

[0105] ;

[0106] ;

[0107] ;

[0108] ;

[0109] The pruning demand intensity index is a comprehensive expression of the coordination and growth rate of plant structure expansion and functional growth within a section, used to quantify the urgency of pruning operations in that area. A higher index value indicates a more active plant growth trend, poorer synchronicity between structure and function, and a higher priority for pruning tasks. This index can be directly applied to decision-making scenarios such as pruning cycle adjustment, task sequencing, and work planning in intelligent maintenance systems, improving the initiative, accuracy, and rationality of resource allocation in garden maintenance. The calculated pruning demand intensity index is 0.0106. Through experimental data verification, a pruning demand index judgment standard was set: below 0.01 is low demand, 0.01-0.02 is medium demand, and above 0.02 is high demand. Section G1 falls into the medium demand state. Based on this index, the pruning cycle is adjusted appropriately, resulting in a maintenance cycle adjustment: the pruning cycle is adjusted from once every 15 days to once every 12 days. The formula, through comprehensive analysis of the normalized growth difference and growth rate of leaf area index and chlorophyll index, more accurately quantifies the urgency of plant pruning, effectively supporting refined management decisions.

[0110] Table 4: Physiological growth data of plants in different sections

[0111] ;

[0112] As shown in Table 4, the physiological growth data of the plants in the section clearly reflects the daily growth of the plants. The data has been normalized to facilitate the calculation and evaluation of coordination and growth trend, and accurately support the analysis of subsequent pruning needs and the adjustment of maintenance cycles.

[0113] Please see Figure 5 The work time scheduling module includes:

[0114] The task requirement calculation submodule uses the maintenance cycle adjustment results to calculate the task quantity and duration requirements for each section based on the correspondence between each plant type and the density of maintenance work, combined with the distribution of various plants within the section, and obtains the task quantity requirement data.

[0115] The maintenance cycle adjustment results serve as the input basis for calculating task requirements. Taking aggregate section G1 as an example, it includes three plant types: shrubs, trees, and lawns. First, corresponding data is established based on the relationship between plant type and maintenance work density. For example, the maintenance density for shrubs is defined as 0.5 man-hours per square meter, for trees 0.8 man-hours, and for lawns 0.3 man-hours. The specific area proportion of each plant is recorded. For example, the area of ​​section G1 is 75 square meters, of which shrubs account for 40% (30 square meters), trees account for 30% (22.5 square meters), and lawns account for 30%. % (22.5 square meters), calculate the maintenance time for each type of plant by multiplying the area ratio by the work density: shrubs 30 × 0.5 = 15 hours, trees 22.5 × 0.8 = 18 hours, lawns 22.5 × 0.3 = 6.75 hours. Add the maintenance time for the three types of plants to obtain the overall task volume of the section. Calculate the task volume of section G1 as 15 + 18 + 6.75 = 39.75 hours. At the same time, set the standard work volume per worker per day as 8 hours. Then, this section needs 39.75 ÷ 8 ≈ 5 work days. Obtain the task volume requirement data of the section and clarify the time and scale of the maintenance work.

[0116] The path order adjustment submodule calls the task volume requirement data, combines it with the geographical location information of each block, analyzes the continuity of the path, adjusts the execution order of each segment, and obtains the order optimization sequence.

[0117] The task load requirement data for segment G1 is retrieved, and the actual geographical location information of each block is referenced, such as block 1 (latitude and longitude 31.212345, 121.567890), block 2 (31.213000, 121.568500), and block 3 (31.213600, 121.569000). First, the straight-line distance between adjacent blocks is calculated based on the geographical coordinate distance calculation formula. For example, the distance between block 1 and block 2 is calculated to be 65 meters, and the distance between block 2 and block 3 is 60 meters. According to the principle of prioritizing shorter distances, the continuity of the paths between blocks is compared and analyzed. For example, the sequential distance from the starting block (block 1) to the ending block (block 3) is 125 meters, which is less than other sequences (such as block 3 first and then block 2, totaling 135 meters). The optimal maintenance path sequence is determined to be block 1 → block 2 → block 3, and this is recorded to form an optimized sequence, providing specific path guidance for actual operation route planning.

[0118] The maintenance task planning submodule optimizes the sequence according to the order, and plans the maintenance task list and establishes a work task planning record by combining the duration requirements and execution order of maintenance tasks in each section.

[0119] Using a sequential optimization sequence, taking segment G1 (containing blocks 1, 2, and 3) as an example, the maintenance task arrangement is refined based on the specific workload and optimization path of each block. With a total of 5 man-days as the base, for example, the first man-day is for the maintenance of block 1, with a specific maintenance duration of 15 man-days, arranged by 2 workers, completing a total of 16 man-days, with 1 man-day exceeding the requirement for flexible adjustments. The second and third man-days are for the maintenance of block 2, totaling 18 man-days, completed by 2 workers working 8 man-days each day, with 2 man-days remaining as reserves. The fourth man-day is for the task of block 3, requiring 6.75 man-days, arranged by only 1 worker, with the remaining 1.25 man-days reserved for flexible or emergency tasks. The fifth man-day is for comprehensive re-inspection and flexible arrangements. This detailed planning of the daily maintenance work duration, number of personnel, specific dates, and work content for each block ultimately forms a clear work task planning record.

[0120] Table 5. Task Planning Record Table:

[0121] ;

[0122] As shown in Table 5, the task planning record clearly displays the specific workload, personnel arrangement, and standby time for each maintenance workday, which facilitates task allocation and execution in actual work.

[0123] Please see Figure 6 The anomaly detection module includes:

[0124] The sunshine data acquisition submodule calls the job task planning record to collect sunshine intensity data and leaf color response data in each section within a continuous period, and generates sunshine response dataset.

[0125] Based on the task planning records, taking aggregation segment G1 as an example, the working hours for 7 consecutive days within the block are defined as the basis for solar radiation data collection. Specifically, data collection is carried out continuously from 8:00 to 18:00 every day. First, a solar radiation intensity sensor is installed at the center of the segment, and the solar radiation intensity is automatically recorded every hour. For example, the solar radiation intensity measured at 8:00 on the first day is 150 W·m. -2 The data up to day 7 are [150, 220, 320, 450, 580, 600, 610, 590, 480, 350, 200] W·m -2Meanwhile, three representative plants (Z1, Z2, and Z3) were selected at the same time each day, and the RGB values ​​of the plant leaves were measured hourly using a color analyzer and converted into a green index. For example, at 8:00 on day 1, the green index value of Z1 was 0.75, Z2 was 0.76, and Z3 was 0.78. Subsequent data were continuously measured and recorded daily. After collecting complete data for 7 days, the solar intensity and leaf color response data were synchronized and aligned in time, and data matching was performed to form a solar response dataset for the next stage of response difference analysis.

[0126] The response difference analysis submodule compares the changes in solar intensity and leaf color response in each cycle based on the solar response dataset, identifies the degree of difference in each time period, analyzes the abnormal response state, and obtains the sequence of abnormal light response states.

[0127] Based on the solar response dataset, the variation range between solar intensity and leaf color response was analyzed daily and hourly. Specifically, the second and third days were used as examples. On the second day at 9:00 AM, the solar intensity increased from 220 W·m⁻². -2 Increased to 320 W·m -2 The variation range is 100 W·m -2 During the same period, the average change in leaf green index increased from 0.76 to 0.79, an increase of 0.03. The calculated proportion of the change in leaf green index per unit increase in solar radiation intensity was 0.03 / 100 = 0.0003. On the third day, during the same period, the solar radiation intensity increased from 320 W·m⁻². -2 Increased to 450 W·m -2 The variation range is 130 W·m -2 However, the leaf green index only increased from 0.79 to 0.795, an increase of 0.005; the calculated proportion was 0.005 / 130≈0.0000385, which was significantly smaller than the data of the previous day. Further analysis of the proportion values ​​of data in each time period was conducted, and a change proportion threshold of 0.0001 was set. This threshold was determined through a large amount of experimental data in the early stage. When the proportion value of a time period was less than this threshold, it was defined as an abnormal response state. For example, on the third day, the above proportion was 0.0000385, which was less than the threshold, and it was recorded as an abnormal response. Using this method, all data for 7 consecutive days were analyzed hourly to form a light response abnormal state sequence, record the occurrence of abnormal states in each time period, and reflect the actual response state of the plant to light changes.

[0128] The abnormal state recording submodule utilizes the light response abnormal state sequence to record the start time and duration of abnormal events based on the duration period of the abnormal state, and establishes light response hysteresis information.

[0129] Based on the sequence data of abnormal light response states, the persistence of abnormal response states in each time period is analyzed. For example, an abnormal response state is first detected at 9:00 on the 3rd day. The analysis continues to determine whether the abnormal state persists in subsequent adjacent time periods. A continuous abnormal state occurs from 10:00 to 11:00 on the 3rd day. An abnormal state that meets the condition of two or more consecutive time periods is defined as a persistent abnormal event. The first abnormal time period (9:00 on the 3rd day) is taken as the starting time point of the abnormal event, and the starting time and duration of the abnormal event are recorded as 3 consecutive hours. Similarly, an abnormal response is first recorded at 15:00 on the 6th day, and if it does not return to normal by 17:00, it is also marked as an abnormal event and the time is recorded. After processing all abnormal states over 7 consecutive days using this method, a clear sequence of light response lag information is formed. The specific start time and duration of each abnormal event are recorded to clarify the lag of the plant's physiological response and the continuous abnormal manifestations.

[0130] The big data-based landscape maintenance method, implemented based on the aforementioned big data-based landscape maintenance system, includes the following steps:

[0131] S1: Divide the garden area into multiple blocks, collect the soil moisture change curves of humidity sensing nodes and water potential sensing nodes in each block, analyze the synchronicity of soil moisture fluctuations between different nodes in the block, and combine the characteristics of plant root system and soil layer distribution to detect abnormal water events in the block and generate water absorption offset comparison results.

[0132] S2: Based on the water absorption offset comparison results, the leaf area index, transpiration rate per unit area, air temperature, and wind speed of plant samples in each block are collected. The water evapotranspiration intensity of plants in each block is calculated, and the blocks are grouped and classified to obtain the water requirement level aggregation segment.

[0133] S3: Based on the water requirement level aggregation section, collect the daily leaf area index and chlorophyll index of plants in each section, analyze the consistency and trend of plant photosynthesis and tissue expansion, quantify the pruning requirements of plants, adjust the pruning and maintenance cycle, and establish the maintenance cycle adjustment results.

[0134] S4: Based on the maintenance cycle adjustment results, according to the correspondence between plant type and maintenance work density, combined with the quantity distribution of each type of plant in the section and the maintenance work content, calculate the total maintenance work and expected operation time of each section, and adjust the execution order of maintenance tasks in combination with geographical location, maintenance task list, and obtain operation task planning records.

[0135] S5: Based on the task planning records, collect and compare the differences in changes between sunlight intensity and leaf color response over a continuous time period, analyze the abnormal response state of plants to light changes, identify abnormal light response events based on the persistence of abnormal response states, record the start time of the events, and establish light response lag information.

[0136] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A big data-based landscaping maintenance system, characterized in that, The system includes: The water potential monitoring module divides the garden area into multiple blocks, analyzes the consistency of soil moisture changes at multiple humidity and water potential sensor nodes within the blocks, combines the influence of plant root type and soil structure on water absorption behavior, detects abnormal water events in the blocks, and generates water absorption offset comparison results. The detection of abnormal moisture events in the detection area is specifically achieved using the following formula: ； Calculate the degree of moisture anomaly in each block and detect moisture anomaly events in the blocks; in, Let q represent the degree of moisture anomaly in the q-th block. Let a be the humidity monitoring value of the a-th abnormal node. The wetting offset judgment boundary is set for the a-th node based on root type and soil structure. This represents the humidity difference data between the c-th pair of adjacent nodes. For the spatial continuation level of the b-th anomalous node, Let A be the number of anomalous nodes in the neighborhood of the b-th anomalous node, A be the total number of nodes identified as anomalous in the block, B be the number of spatial clustering anomalous groups in the block, C be the number of adjacent node pairs used for difference calculation in the block, a be the index number of the anomalous node, b be the index number of the anomalous node in the anomalous clustering group, and c be the index number of the adjacent node pair. The block division module calls the water absorption offset comparison results to obtain the leaf area index, transpiration rate per unit area, air temperature, and wind speed of the plant samples in the block, calculates the water evapotranspiration intensity of the plants in each block, groups and classifies the blocks, and generates water requirement level aggregated segments. The calculation of the water evapotranspiration intensity of plants within each block is specifically performed using the following formula: ； Calculate the moisture evapotranspiration intensity index for each block; in, Let x be the moisture evapotranspiration intensity index of block x. Let be the leaf area index of the nth sample. This is the normalized value of the transpiration rate per unit area for the nth sample. Let be the normalized value of the temperature of the nth sample. Let be the normalized value of the wind speed for the nth sample. is the normalized area value of block x, N is the number of samples in the block, and n is the sample index number; The pruning adjustment module uses the water requirement level aggregation segment to obtain daily plant leaf area and chlorophyll index data in each segment, analyzes the consistency and trend of plant photosynthesis and tissue expansion, calculates the pruning demand intensity of the plant, adjusts the pruning cycle, and generates maintenance cycle adjustment results. The calculation of the pruning intensity required by the plant is specifically performed using the following formula: ； Calculate the pruning demand intensity index for each section; in, The pruning demand intensity index for segment k is... The number of plants within segment k. Assign index numbers to the plants within the section. Let be the normalized increase in leaf area index of the j-th plant. Let be the normalized increase in chlorophyll index of the j-th plant. Let be the normalized growth rate of the leaf area index of the j-th plant. The normalized growth rate of the chlorophyll index of the j-th plant For section numbering; The work scheduling module uses the maintenance cycle adjustment results to calculate the workload and duration requirements for each section based on the correspondence between plant type and maintenance work density. Combined with geographical location information, it plans a maintenance task list and generates a work task planning record.

2. The big data-based landscaping maintenance system according to claim 1, characterized in that, The water absorption offset comparison results specifically include the frequency index of wetting changes, the difference coefficient of water absorption behavior, and the node consistency judgment results. The water requirement level aggregation section includes the evapotranspiration intensity distribution range, water requirement level classification number, and spatial continuous segment information. The maintenance cycle adjustment results specifically include the leaf area growth coordination coefficient, the photosynthetic expansion matching degree, and the pruning rhythm change cycle. The operation task planning record includes the plant type operation density distribution, the task combination arrangement order, and the path continuity sorting information.

3. The big data-based landscaping maintenance system according to claim 1, characterized in that, The water potential monitoring module includes: The garden area division submodule divides the garden area into multiple blocks, extracts data collected from multiple humidity and water potential sensor nodes, and generates a humidity node spatial distribution table by combining the geographical coordinates of the nodes. The humidity fluctuation analysis submodule extracts the humidity and water potential nodes within each block in the continuous monitoring period based on the humidity node spatial distribution table, analyzes the correlation and temporal consistency of the change trends between nodes, evaluates the degree of coordination of humidity changes within each block, and generates a humidity change consistency index. The moisture anomaly detection submodule calls the moisture change consistency index, combines the influence of plant root type and soil structure on water absorption behavior, sets a moisture offset judgment interval for each node, filters abnormal data points, calculates the degree of moisture anomaly in each block, detects moisture anomaly events in the block, and generates water absorption offset comparison results.

4. The big data-based landscaping maintenance system according to claim 3, characterized in that, The block partitioning module includes: The sample index extraction submodule calls the water absorption offset comparison results to obtain the leaf area index, transpiration rate per unit area, air temperature, and wind speed values ​​of the plant samples in the block, and generates a sample index collection table. The water evapotranspiration calculation submodule uses the sample index aggregation table to call the leaf area index, normalized transpiration rate, normalized temperature, and normalized wind speed of each sample to calculate the water evapotranspiration intensity index of each block. The grade aggregation and classification submodule calls the water evapotranspiration intensity index, merges and groups the blocks according to the index values ​​of adjacent blocks, marks the aggregation number of the grouped blocks, and generates water demand grade aggregation segments.

5. The big data-based landscaping maintenance system according to claim 4, characterized in that, The trimming adjustment module includes: The leaf data acquisition submodule uses the water requirement level aggregation section to collect daily plant leaf area and chlorophyll index data of plants in each section, and performs normalization processing on the data to generate a leaf physiological normalization parameter sequence. The growth trend analysis submodule analyzes the consistency and trend of plant photosynthesis and tissue expansion based on the leaf physiological normalization parameter sequence, and on the degree of coordination and growth trend of data changes, to obtain growth coordination trend information. The pruning demand calculation submodule calls the growth coordination trend information to calculate the pruning demand intensity of each segment, calculate the pruning demand intensity index of each segment, adjust the pruning cycle of each segment, and generate the maintenance cycle adjustment result.

6. The big data-based landscaping maintenance system according to claim 5, characterized in that, The work time scheduling module includes: The task requirement calculation submodule uses the maintenance cycle adjustment results to calculate the task quantity and duration requirements for each section based on the correspondence between each plant type and the density of maintenance work, combined with the distribution of various plants in the section, and obtains the task quantity requirement data. The path order adjustment submodule calls the task volume requirement data, combines it with the geographical location information of each block, and adjusts the execution order of each segment by analyzing the continuity of the path to obtain the optimized sequence. The maintenance task planning submodule optimizes the sequence according to the given order, and plans the maintenance task list by combining the duration requirements and execution order of maintenance tasks in each section, and establishes a work task planning record.

7. The big data-based landscaping maintenance system according to claim 1, characterized in that, The system also includes: The anomaly identification module calls the task planning record, collects and compares the variation differences between sunlight intensity and leaf color response in a continuous time period, analyzes the abnormal response state of the plant to light changes, and identifies abnormal light response events based on the persistence of the abnormal response state, records the start time of the event, and generates light response lag information. The light response lag information specifically refers to the difference value between sunlight and color response, the continuous time period of response lag, and the abnormal state marker node.

8. The big data-based landscaping maintenance system according to claim 7, characterized in that, The anomaly detection module includes: The sunshine data acquisition submodule calls the operation task planning record to collect sunshine intensity data and leaf color response data in each section within a continuous period, and generates sunshine response dataset. The response difference analysis submodule compares the changes in solar intensity and leaf color response in each cycle based on the solar response dataset, identifies the degree of difference in each time period, analyzes the abnormal response state, and obtains the light response abnormal state sequence. The abnormal state recording submodule uses the light response abnormal state sequence to record the start time and duration of abnormal events according to the duration period of the abnormal state, and establishes light response lag information.

9. A big data-based method for landscaping maintenance, characterized in that: The method is used to implement the big data-based landscaping maintenance system according to any one of claims 1-8, and includes the following steps: S1: Divide the garden area into multiple blocks, collect the soil moisture change curves of humidity sensing nodes and water potential sensing nodes in each block, analyze the synchronicity of soil moisture fluctuations between different nodes in the block, and combine the characteristics of plant root system and soil layer distribution to detect abnormal water events in the block and generate water absorption offset comparison results. S2: Based on the water absorption offset comparison results, collect the leaf area index, transpiration rate per unit area, air temperature, and wind speed values ​​of plant samples in each block, calculate the water evapotranspiration intensity of plants in each block, group and classify the blocks to obtain water requirement level aggregation sections. S3: Based on the water requirement level aggregation section, collect the daily leaf area index and chlorophyll index of plants in each section, analyze the consistency and trend of plant photosynthesis and tissue expansion, quantify the pruning requirements of plants, adjust the pruning and maintenance cycle, and establish the maintenance cycle adjustment results. S4: Based on the maintenance cycle adjustment results, according to the correspondence between plant type and maintenance work density, combined with the quantity distribution of each type of plant in the section and the maintenance work content, calculate the total maintenance work and expected operation time of each section, and adjust the execution order of maintenance tasks in combination with geographical location, maintenance task list, and obtain operation task planning records. S5: Based on the task planning record, collect and compare the variation differences between sunlight intensity and leaf color response in a continuous time period, analyze the abnormal response state of the plant to light changes, and identify abnormal light response events based on the persistence of the abnormal response state, record the start time of the event, and establish light response lag information.

Images