Intelligent roof greening construction and maintenance method and system based on data driving

Abstract

The invention relates to the technical field of roof greening, in particular to an intelligent roof greening construction and maintenance method and system based on data driving. According to the method, firstly, overall maintenance parameters are determined based on greening scheme selection information, then function division is performed according to roof area characteristics, differentiated maintenance adjustment coefficients are set, and basic maintenance is executed through an intelligent maintenance instruction; meanwhile, a partition growth condition real-time monitoring mechanism is established, when abnormity is detected, early warning is triggered immediately, environment data is collected, and a maintenance scheme is adjusted dynamically; intelligent maintenance based on real-time data is realized, and the survival rate and growth quality of roof greening are improved.

Description

Technical Field

[0001] The present application relates to the technical field of roof greening, and in particular to a data-driven intelligent roof greening construction and maintenance method and system. Background Art

[0002] With the acceleration of urbanization, urban heat island effect and air pollution are becoming increasingly prominent. Roof greening, as a sustainable urban greening method, can not only improve the urban ecological environment, but also enhance building energy efficiency, playing an important role in urban ecological construction.

[0003] At present, the maintenance of roof greening is mainly managed by automatic sprinkler systems and preset maintenance procedures. Environmental data is collected through sensor networks, and basic maintenance measures such as irrigation and ventilation are automatically adjusted based on preset thresholds.

[0004] However, the existing roof greening maintenance parameters are fixed and difficult to adapt to the dynamic changes in plant growth. They are unable to provide timely warnings and intelligent adjustments for abnormal situations, resulting in unsatisfactory maintenance effects. This situation needs to be further improved. Summary of the invention

[0005] In order to solve the problem that the existing roof greening maintenance parameters are fixed and difficult to adapt to the dynamic changes of plant growth, the present application provides a data-driven intelligent roof greening construction and maintenance method and system, which adopts the following technical solutions: In a first aspect, the present application provides a data-driven intelligent green roof construction and maintenance method, comprising the following steps: Obtaining greening scheme selection information, and obtaining overall maintenance parameter information according to the greening scheme selection information; Acquire roof area characteristic information, divide the roof into several areas according to the roof area characteristic information, and obtain the area maintenance adjustment coefficient; triggering intelligent maintenance instructions according to the partition maintenance adjustment coefficient and the overall maintenance parameter information; Acquire partition growth status detection information, compare the partition growth status detection information with preset standard growth parameters to obtain a growth difference value, compare the growth difference value with a preset change threshold value, and if the growth difference value is outside the preset change threshold range, trigger an abnormal warning and data collection instruction; According to the abnormal warning and data collection instructions, obtain partition adjustment parameter information; According to the partition adjustment parameter information, a maintenance plan adjustment instruction is triggered.

[0006] By adopting the above technical scheme, the existing roof greening maintenance parameters are fixed, and the same irrigation frequency may be used for the sun area and shade area of ​​the same roof, resulting in uneven plant growth conditions, or the maintenance plan cannot be discovered and adjusted in time when the plants show early signs of disease. This application first determines the overall maintenance parameters based on the greening plan selection information, and then divides the functional areas according to the characteristics of the roof area and sets differentiated maintenance adjustment coefficients, and performs basic maintenance through intelligent maintenance instructions; at the same time, a real-time monitoring mechanism for the growth status of the partition is established. When an abnormality is detected, an early warning is immediately triggered and environmental data is collected to dynamically adjust the maintenance plan; intelligent maintenance based on real-time data is realized, and the survival rate and growth quality of roof greening are improved.

[0007] Optionally, the greening scheme selection information includes plant varieties, greening areas and expected coverage, and the overall maintenance parameter information includes suitable temperature range, humidity range, light requirements and maintenance cycle; acquiring the greening scheme selection information, and acquiring the overall maintenance parameter information according to the greening scheme selection information, specifically includes the following steps: Extract plant variety information from the greening scheme selection information, and obtain corresponding suitable temperature range, humidity range and light requirements according to the plant variety database; Obtaining a maintenance period according to the greening area and the expected coverage combined with the growth characteristics of the plant varieties; The suitable temperature range, humidity range, light requirement and curing cycle are correlated and integrated to obtain the overall curing parameter information.

[0008] By adopting the above technical scheme, in order to solve the one-sided problems existing in the maintenance parameter setting process of the existing roof greening system, such as only setting fixed irrigation parameters according to the plant variety and ignoring the influence of the greening area and the expected coverage, resulting in uneven growth of ground cover plants such as clover when planted on a large scale due to improper setting of maintenance parameters; the application first extracts plant variety information from the greening plan and queries the professional database to obtain basic growth parameters, and then calculates the maintenance cycle by taking the greening area and the expected coverage as influencing factors, and finally establishes a complete overall maintenance parameter system through correlation and integration, and establishes a maintenance parameter determination method considering multi-dimensional factors, thereby improving the scientificity and applicability of the maintenance plan.

[0009] Optionally, the maintenance cycle includes a growth period maintenance cycle and a dormancy period maintenance cycle. The maintenance cycle is obtained according to the greening area and the expected coverage, combined with the growth characteristics of the plant variety, and specifically includes the following steps: According to the growth characteristics and expected coverage of the plant variety, the growing period maintenance cycle and the dormant period maintenance cycle are obtained, wherein the growing period maintenance cycle includes the growing period irrigation frequency, the growing period fertilization frequency and the growing period pruning frequency, and the dormant period maintenance cycle includes the dormant period irrigation frequency, the dormant period fertilization frequency and the dormant period pruning frequency; An annual maintenance plan schedule is determined based on the growth period maintenance cycle and the dormancy period maintenance cycle.

[0010] By adopting the above-mentioned technical solution, in order to solve the problem that the existing roof greening maintenance plan fails to fully consider the periodic characteristics of plant growth, this application first determines the specific frequency of various maintenance operations during the growth period and the dormant period according to the growth characteristics and expected coverage of the plant variety, and then integrates these differentiated parameters into the annual maintenance plan schedule to achieve periodic adjustment of maintenance measures and improve maintenance efficiency and resource utilization.

[0011] Optionally, the roof area characteristic information includes orientation, sunshine duration and shading conditions; obtaining the roof area characteristic information, dividing the roof into a plurality of areas according to the roof area characteristic information, and obtaining the partition maintenance adjustment coefficient, specifically includes the following steps: According to the sunshine duration and the orientation, the roof is divided into several areas, and the illumination intensity coefficient of each area is obtained; According to the shading condition and the partition illumination intensity coefficient, a partition maintenance adjustment coefficient is determined, and the partition maintenance adjustment coefficient is used to perform regional adjustment on the overall maintenance parameter information.

[0012] By adopting the above technical scheme, in the same roof space, there are significant differences in lighting conditions between the unobstructed area facing south and the area facing north blocked by adjacent buildings. If unified maintenance parameters are used, it will lead to insufficient water supply in the area with sufficient light and water accumulation in the area with insufficient light. This application firstly considers the two key factors of orientation and sunshine duration to divide the roof into regions and quantify the light intensity coefficient. Then, the obstruction situation is used as a correction parameter combined with the light intensity coefficient to establish a zoned maintenance adjustment coefficient, thereby realizing the regional adjustment of the overall maintenance parameters and improving the growth adaptability and maintenance effect of plants in different regions.

[0013] Optionally, according to the abnormal warning and data collection instructions, obtaining partition adjustment parameter information specifically includes the following steps: According to the abnormal warning and data collection instructions, obtain the partition environmental monitoring data and the partition plant growth status data; Obtaining abnormal cause analysis based on the sub-area environmental monitoring data and sub-area plant growth status data in combination with the growth difference value; According to the abnormal cause analysis and the overall maintenance parameter information, the type of maintenance parameter to be adjusted and the adjustment range are determined, and the partition adjustment parameter information is generated.

[0014] By adopting the above technical solution, the present application first synchronously collects environmental monitoring data and plant growth status data after the abnormal warning is triggered, and then correlates the real-time data with the growth difference value to identify the cause of the abnormality. Finally, based on the comparison between the abnormal cause and the overall maintenance parameters, the type of parameters that need to be adjusted and the specific adjustment range are determined, thereby improving the efficiency of solving abnormal problems and the ability to optimize maintenance plans.

[0015] Optionally, triggering a maintenance plan adjustment instruction according to the partition adjustment parameter information specifically includes the following steps: Extracting a maintenance adjustment type from the partition adjustment parameter information, wherein the maintenance adjustment type includes irrigation adjustment, fertilization adjustment and pruning adjustment; For irrigation adjustment, the adjustment values ​​of irrigation water volume and irrigation duration are calculated based on soil moisture monitoring data; For fertilization adjustment, determine the adjustment value of fertilizer ratio and fertilizer amount according to soil nutrient monitoring data; For pruning adjustment, the adjustment values ​​of pruning height and pruning range are determined according to the plant growth density data; Compare each adjustment value with the plant tolerance range, generate a corresponding execution instruction sequence, and trigger the maintenance plan adjustment instruction.

[0016] By adopting the above technical scheme, the existing roof greening maintenance adjustment scheme is too simplistic. For example, when adjusting the irrigation amount, the water consumption is increased or decreased based on experience only, without considering the actual soil moisture content and plant tolerance, which leads to new problems after the adjustment and even causes plant damage. This application first subdivides the maintenance adjustment types into three aspects: irrigation, fertilization and pruning, and then introduces corresponding special monitoring data as the basis for adjustment, such as soil moisture content, nutrient content and growth density, and calculates each adjustment value based on this. Finally, the safety of the adjustment scheme is ensured by comparing with the plant tolerance range, thereby improving the accuracy and safety of maintenance adjustments and reducing the probability of secondary damage caused by improper adjustments.

[0017] In a second aspect, the present application provides a data-driven intelligent roof greening construction and maintenance system, including: A greening scheme selection module, used to obtain greening scheme selection information, and obtain overall maintenance parameter information according to the greening scheme selection information; A zone division module is used to obtain roof zone characteristic information, divide the roof into several functional zones according to the roof zone characteristic information, and obtain zone maintenance adjustment coefficients; An intelligent maintenance control module, used to trigger an intelligent maintenance instruction according to the partition maintenance adjustment coefficient and the overall maintenance parameter information; A growth status monitoring module is used to obtain partition growth status detection information, compare the partition growth status detection information with preset standard growth parameters to obtain a growth difference value, compare the growth difference value with a preset change threshold value, and if the growth difference value is outside the preset change threshold range, trigger an abnormal warning and data collection instruction; A parameter adjustment module, used to obtain partition adjustment parameter information according to the abnormal warning and data collection instructions; The maintenance execution module is used to trigger the maintenance plan adjustment instruction according to the partition adjustment parameter information.

[0018] Optionally, the greening scheme selection module includes: A parameter acquisition unit, configured to extract plant variety information from the greening scheme selection information, wherein the greening scheme selection information includes plant variety, greening area and expected coverage; A database query unit, used to obtain the corresponding suitable temperature range, humidity range and light requirements according to the plant variety database; A maintenance cycle calculation unit, used to obtain a maintenance cycle according to the greening area and the expected coverage combined with the growth characteristics of the plant variety; A parameter integration unit is used to associate and integrate the suitable temperature range, humidity range, light requirements and maintenance cycle to obtain the overall maintenance parameter information, wherein the overall maintenance parameter information includes the suitable temperature range, humidity range, light requirements and maintenance cycle.

[0019] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned data-driven intelligent roof greening construction and maintenance method when executing the computer program.

[0020] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned data-driven intelligent roof greening construction and maintenance method.

[0021] In summary, the present application includes at least one of the following beneficial technical effects: 1. This application first determines the overall maintenance parameters based on the greening scheme selection information, then divides the function into different zones according to the characteristics of the roof area and sets differentiated maintenance adjustment coefficients, and performs basic maintenance through intelligent maintenance instructions; at the same time, a real-time monitoring mechanism for the growth status of each zone is established, and when an abnormality is detected, an early warning is immediately triggered and environmental data is collected to dynamically adjust the maintenance scheme; intelligent maintenance based on real-time data is realized, which improves the survival rate and growth quality of roof greening; 2. In order to solve the one-sided problems existing in the maintenance parameter setting process of the existing roof greening system, such as setting fixed irrigation parameters only according to plant varieties while ignoring the influence of greening area and expected coverage, which leads to uneven growth of ground cover plants such as clover due to improper maintenance parameter setting when planted on a large scale; this application first extracts plant variety information from the greening plan and queries the professional database to obtain basic growth parameters, then calculates the maintenance cycle using greening area and expected coverage as influencing factors, and finally establishes a complete overall maintenance parameter system through correlation and integration, and establishes a maintenance parameter determination method that considers multi-dimensional factors, thereby improving the scientificity and applicability of the maintenance plan; 3. In order to solve the problem that the existing roof greening maintenance plan fails to fully consider the periodic characteristics of plant growth, this application first determines the specific frequency of various maintenance operations during the growth period and dormancy period based on the growth characteristics and expected coverage of the plant varieties, and then integrates these differentiated parameters into the annual maintenance plan schedule to achieve periodic adjustment of maintenance measures and improve maintenance efficiency and resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a data-driven intelligent green roof construction and maintenance method according to an embodiment of the present application; Figure 2 It is a flow chart of step S100 in a data-driven intelligent green roof construction and maintenance method according to an embodiment of the present application; Figure 3 It is a flow chart of step S120 in a data-driven intelligent green roof construction and maintenance method according to an embodiment of the present application; Figure 4 It is a flow chart of step S200 in a data-driven intelligent green roof construction and maintenance method according to an embodiment of the present application; Figure 5 It is a flow chart of step S500 in a data-driven intelligent green roof construction and maintenance method according to an embodiment of the present application; Figure 6 It is a flow chart of step S600 in a data-driven intelligent green roof construction and maintenance method according to an embodiment of the present application; Figure 7This is a module schematic diagram of a data-driven intelligent roof greening construction and maintenance system according to an embodiment of the present application; Figure 8 It is a diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0024] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0025] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0026] In the first aspect, the present application provides a data-driven intelligent roof greening construction and maintenance method, referring to Figure 1 , including the following steps: S100: Obtain greening scheme selection information, and obtain overall maintenance parameter information based on the greening scheme selection information.

[0027] In this embodiment, the greening project planning information provided by the construction unit is collected through the interactive interface of the intelligent management platform. The system uses the expert knowledge base to analyze the input information, and combines the climate characteristics, building characteristics and other factors of the project location to generate preliminary greening plan suggestions and corresponding maintenance standard parameter sets.

[0028] Specifically, a commercial roof garden project plans to build a 1,000 square meter leisure green space, hoping to mainly use low-maintenance, drought-tolerant plants. The system recommends a plant configuration of 50% creeping grass, 30% sedum, and 20% sedum, and generates corresponding maintenance standards: irrigation frequency is once every 2 days, each water supply is 1.5L / ㎡, and the fertilization cycle is 45 days, with each application amount of 15g / ㎡.

[0029] S200, obtaining roof area characteristic information, dividing the roof into several areas according to the roof area characteristic information, and obtaining the area maintenance adjustment coefficient.

[0030] In this embodiment, a drone equipped with thermal imaging and multispectral sensors is used to scan the roof environment to obtain environmental characteristic data such as thermal distribution map, light intensity map and moisture distribution map. Based on these data, the system identifies areas with similar environmental characteristics and calculates the corresponding maintenance adjustment coefficient according to the degree of deviation of the environmental characteristics of each area.

[0031] Specifically, for example, in an 800-square-meter roof greening project, the system identified five characteristic areas by scanning the environment at different times through drones: the east sun area, the west shade area, the central transition area, the north strong wind area, and the south heat island area. Subsequently, the system calculated the maintenance adjustment coefficient of each area: first determine the environmental reference benchmark value, and use the deviation percentage between the measured data of each area and the benchmark value as the adjustment factor. Taking the east sun area as an example, the average light intensity in this area is 4400Lux (deviation +10%), the temperature is 27℃ (deviation +8%), the relative humidity is 60% (deviation -8%), and the wind speed is 2.8m / s (deviation -7%). The comprehensive calculation results in an adjustment coefficient of 0.9.

[0032] S300. Triggering intelligent maintenance instructions according to the partition maintenance adjustment coefficient and the overall maintenance parameter information.

[0033] In this embodiment, by learning historical maintenance data and plant growth feedback, an environmental factor-maintenance measure-growth effect association model is established. According to the adjustment coefficients of different regions, the maintenance parameters are automatically optimized and accurate maintenance instructions are generated.

[0034] Specifically, for the heat island area, the system found based on machine learning model analysis that the area needs additional cooling measures, so it generated differentiated maintenance instructions: increase spray cooling, adjust irrigation time (avoid the high temperature period at noon), and recommend the installation of sunshade facilities.

[0035] S400, obtain partition growth status detection information, compare the partition growth status detection information with preset standard growth parameters to obtain growth difference values, compare the growth difference values ​​with preset change thresholds, and if the growth difference values ​​are outside the preset change threshold range, trigger abnormal warnings and data collection instructions.

[0036] In this embodiment, a computer vision-based plant growth monitoring system is pre-deployed, including a fixed camera and a patrol robot. The system uses image processing technology to analyze plant growth conditions in real time, including leaf color, growth density, plant height and other indicators, and intelligently compares them with standard growth parameters in the database. In the absence of hardware conditions, the partition growth condition detection information is obtained through manual patrol records.

[0037] Specifically, for example, the system detected that the average plant height in the strong wind area was 8cm, compared with the standard parameter of 12cm, the growth difference was -33%, exceeding the preset ±20% change threshold. The system immediately started the deep monitoring program and mobilized the inspection robot to scan the area at close range to collect detailed data such as soil compactness and root growth.

[0038] S500: Obtain partition adjustment parameter information according to the abnormal warning and data collection instructions.

[0039] In this embodiment, the plant growth expert knowledge base and the environmental stress response strategy library are pre-integrated. By performing multi-dimensional analysis on abnormal data, the root cause of the problem can be quickly identified and a scientific adjustment plan can be formulated.

[0040] Specifically, for example, the system analyzed abnormal data in strong wind areas and found that: the soil was too compact, which restricted root growth; the wind speed frequently exceeded 6m / s, causing mechanical damage to plants. Based on this, it generated comprehensive adjustment suggestions: soil improvement and installation of smart wind barriers, etc.

[0041] S600: triggering a maintenance plan adjustment instruction according to the partition adjustment parameter information.

[0042] In this embodiment, the adjustment plan is converted into specific equipment control instructions and manual operation guidelines through automated maintenance equipment and an intelligent management platform, and remote control and real-time supervision are achieved through Internet of Things technology.

[0043] In one embodiment, the greening scheme selection information includes plant species, greening area and expected coverage, and the overall maintenance parameter information includes suitable temperature range, humidity range, light requirements and maintenance cycle; Figure 2 In step S100, greening scheme selection information is obtained, and overall maintenance parameter information is obtained according to the greening scheme selection information, which specifically includes the following steps: S110, extracting plant variety information from the greening plan selection information, and obtaining corresponding suitable temperature range, humidity range and light requirements according to the plant variety database.

[0044] In this embodiment, the system pre-builds a multi-dimensional plant variety database, which not only contains the basic physiological characteristics of plants, but also integrates the actual planting data and growth performance of different climate regions. Through machine learning algorithms, the system can quickly match the optimal growth parameter range according to plant variety information, improving the accuracy and adaptability of parameter acquisition.

[0045] S120. Obtain a maintenance cycle based on the greening area and expected coverage combined with the growth characteristics of the plant varieties.

[0046] In this embodiment, the system analyzes the growth rate, tillering ability and coverage expansion characteristics of the plants, combines the greening area and expected coverage requirements, and calculates the maintenance cycle and key time nodes required to achieve the expected effect.

[0047] Specifically, in a project with a total area of ​​200 square meters and an expected coverage of 90%, the system analyzed the characteristics of each grass species in the mixed sowing plan: the growth rate of bermudagrass is 0.8cm / day, the tillering cycle is 12 days, the growth rate of Bermuda grass is 0.7cm / day, the tillering cycle is 14 days, and the growth rate of ryegrass is 1.0cm / day, the tillering cycle is 10 days. Through growth simulation calculations, it was determined that it would take 45 days to achieve basic coverage and 90 days to achieve the expected coverage. Based on this, a maintenance cycle divided into three stages was formulated: in the early stage, for example, 1-30 days, focus on promoting germination and growth, in the middle stage, strengthen tillering expansion, and in the later stage, optimize coverage density.

[0048] S130, associating and integrating the suitable temperature range, humidity range, light requirements and maintenance cycle to obtain overall maintenance parameter information.

[0049] In this embodiment, the optimal overall maintenance parameter combination is generated by analyzing the mutual influence relationship between various growth parameters.

[0050] In one embodiment, the maintenance cycle includes a growth period maintenance cycle and a dormancy period maintenance cycle, referring to Figure 3 In step S120, the maintenance cycle is obtained according to the greening area and the expected coverage, combined with the growth characteristics of the plant species, which specifically includes the following steps: S121. Obtain the growing period maintenance cycle and the dormant period maintenance cycle according to the growth characteristics and expected coverage of the plant variety.

[0051] Among them, the maintenance cycle during the growing period includes the irrigation frequency during the growing period, the fertilization frequency during the growing period, and the pruning frequency during the growing period; the maintenance cycle during the dormant period includes the irrigation frequency during the dormant period, the fertilization frequency during the dormant period, and the pruning frequency during the dormant period.

[0052] In this embodiment, the system pre-establishes a seasonal plant growth cycle management model, and based on the physiological rhythm and phenological characteristics of plants, the maintenance cycle is subdivided into two main stages: the growth period and the dormancy period. By analyzing the correlation between historical meteorological data and plant growth data, the time point of plant growth state transition is predicted, and the maintenance parameters are dynamically adjusted accordingly.

[0053] Specifically, taking bermudagrass as an example, the system determines detailed maintenance frequency parameters based on its growth characteristics and the expected coverage requirement of 90%. The maintenance cycle during the growth period includes increased irrigation frequency, fertilization frequency, and pruning frequency; while the frequency is reduced during the dormant period.

[0054] S122. Determine the annual maintenance schedule based on the growth period maintenance cycle and the dormancy period maintenance cycle.

[0055] In this embodiment, a detailed maintenance schedule is automatically generated according to maintenance requirements in different periods.

[0056] In one embodiment, the roof area feature information includes orientation, sunshine duration and shading conditions. Figure 4 In step S200, the roof area characteristic information is obtained, the roof is divided into several areas according to the roof area characteristic information, and the partition maintenance adjustment coefficient is obtained, which specifically includes the following steps: S210: Divide the roof into several areas according to the sunshine duration and direction, and obtain the light intensity coefficient of the area.

[0057] In this embodiment, the system uses lighting simulation analysis technology, combined with the building information model, to construct a dynamic model of roof lighting throughout the year. According to the geographical location, building orientation and surrounding environment, the system calculates the changes in light intensity of each area of ​​the roof in different seasons and at different times, providing a scientific basis for regional division.

[0058] S220. Determine a partition maintenance adjustment coefficient according to the shading condition and the partition illumination intensity coefficient. The partition maintenance adjustment coefficient is used to make regional adjustments to the overall maintenance parameter information.

[0059] In this embodiment, the system calculates the maintenance adjustment coefficient by analyzing the influence of the obstructions around the building on the illumination and combining the acquired partition illumination intensity coefficient. The system adopts a weighted calculation model, taking into account factors such as the height, distance and projection angle of the obstruction, and corrects the illumination intensity coefficient to finally obtain the maintenance adjustment coefficient for each area.

[0060] In one embodiment, referring to Figure 5 In step S500, according to the abnormal warning and data collection instructions, the partition adjustment parameter information is obtained, which specifically includes the following steps: S510. Obtaining sub-area environmental monitoring data and sub-area plant growth status data according to abnormal warning and data collection instructions.

[0061] In this embodiment, the system collects real-time environmental and growth status data through an environmental sensor network and plant growth monitoring equipment deployed in various areas of the roof.

[0062] Specifically, when the system receives an early warning of abnormal plant growth in the southwest region, it immediately starts an intensive monitoring mode for the area. For example, environmental monitoring equipment collects data every 30 minutes, and plant growth monitoring equipment collects morphological characteristics three times a day.

[0063] S520. Obtain abnormal cause analysis based on the partitioned environmental monitoring data and the partitioned plant growth status data in combination with the growth difference value.

[0064] In this embodiment, the system establishes a plant growth abnormality pattern library by analyzing historical data, which can quickly match current abnormal phenomena with known problem patterns. The system uses a decision tree algorithm to locate the main and secondary factors causing growth differences by analyzing the correlation between environmental factors and growth status.

[0065] S530. According to the abnormal cause analysis and the overall maintenance parameter information, determine the type of maintenance parameter to be adjusted and the adjustment range, and generate partition adjustment parameter information.

[0066] In this embodiment, the system automatically calculates the optimal adjustment plan for each maintenance parameter based on the abnormal cause analysis results and the plant physiological demand model, and dynamically determines the priority and adjustment range of the parameter adjustment according to the severity of the abnormality and the interaction between environmental factors.

[0067] Specifically, for example, in response to the abnormal growth in the southwest region, the system generated a zoning adjustment parameter plan: first adjust the fertilization strategy, then optimize irrigation parameters, adjust pruning frequency, and so on.

[0068] In one embodiment, referring to Figure 6 In step S600, the maintenance plan adjustment instruction is triggered according to the partition adjustment parameter information, which specifically includes the following steps: S610: Extracting maintenance adjustment types from the partition adjustment parameter information, where the maintenance adjustment types include irrigation adjustment, fertilization adjustment, and pruning adjustment.

[0069] S620: For irrigation adjustment, calculate the adjustment values ​​of irrigation water volume and irrigation duration according to the soil moisture monitoring data.

[0070] S630: For fertilization adjustment, determine the fertilizer ratio and fertilizer amount adjustment value according to the soil nutrient monitoring data.

[0071] S640: For pruning adjustment, determine adjustment values ​​of pruning height and pruning range according to plant growth density data.

[0072] S650: Compare each adjustment value with the plant tolerance range, generate a corresponding execution instruction sequence, and trigger a maintenance plan adjustment instruction.

[0073] In this embodiment, the system pre-establishes a plant tolerance assessment system, which includes a database of physiological characteristics of various plants, to assess whether the adjustment parameters exceed the adaptation range of the plants.

[0074] Specifically, for example, the system compares the calculated adjustment values ​​with the tolerance range of Bermuda grass: irrigation adjustment value -20% (tolerance range ±30%), fertilization adjustment value +20% (tolerance range ±25%), pruning adjustment value -12.5% ​​(tolerance range ±15%). If they are all within the safe range, an execution instruction sequence is generated and executed one by one in order of priority, and the plant response is monitored in real time during the execution process.

[0075] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0076] On the second aspect, the present application provides a data-driven intelligent roof greening construction and maintenance system. The data-driven intelligent roof greening construction and maintenance system of the present application is described below in combination with the above-mentioned data-driven intelligent roof greening construction and maintenance method.

[0077] Reference Figure 7 , a data-driven intelligent green roof construction and maintenance system, including: A greening scheme selection module is used to obtain greening scheme selection information, and obtain overall maintenance parameter information based on the greening scheme selection information; The area division module is used to obtain the characteristic information of the roof area, divide the roof into several functional areas according to the characteristic information of the roof area, and obtain the maintenance adjustment coefficient of the partition; Intelligent maintenance control module, used to trigger intelligent maintenance instructions according to the partition maintenance adjustment coefficient and overall maintenance parameter information; The growth status monitoring module is used to obtain the partition growth status detection information, compare the partition growth status detection information with the preset standard growth parameters, obtain the growth difference value, compare the growth difference value with the preset change threshold value, and trigger an abnormal warning and data collection instruction if the growth difference value is outside the preset change threshold range; The parameter adjustment module is used to obtain the partition adjustment parameter information according to the abnormal warning and data collection instructions; The maintenance execution module is used to trigger maintenance plan adjustment instructions based on partition adjustment parameter information.

[0078] In one embodiment, the greening scheme selection module includes: A parameter acquisition unit, used to extract plant variety information from greening scheme selection information, wherein the greening scheme selection information includes plant variety, greening area and expected coverage; A database query unit, used to obtain the corresponding suitable temperature range, humidity range and light requirements according to the plant variety database; A maintenance cycle calculation unit is used to obtain the maintenance cycle according to the greening area and the expected coverage combined with the growth characteristics of the plant varieties; The parameter integration unit is used to associate and integrate the suitable temperature range, humidity range, light requirements and maintenance cycle to obtain overall maintenance parameter information, wherein the overall maintenance parameter information includes the suitable temperature range, humidity range, light requirements and maintenance cycle.

[0079] In one embodiment, the maintenance cycle calculation unit includes: A cycle distinguishing unit is used to obtain a growing period maintenance cycle and a dormant period maintenance cycle according to the growth characteristics and expected coverage of the plant variety, wherein the growing period maintenance cycle includes the growing period irrigation frequency, the growing period fertilization frequency and the growing period pruning frequency, and the dormant period maintenance cycle includes the dormant period irrigation frequency, the dormant period fertilization frequency and the dormant period pruning frequency; The timetable generating unit is used to determine the annual maintenance plan timetable according to the growing period maintenance cycle and the dormant period maintenance cycle.

[0080] In one embodiment, the region division module includes: A light analysis unit is used to divide the roof into several areas according to the sunshine duration and orientation, and obtain the light intensity coefficient of each area, wherein the characteristic information of the roof area includes orientation, sunshine duration and shading; The coefficient adjustment unit is used to determine the partition maintenance adjustment coefficient according to the shading situation and the partition light intensity coefficient. The partition maintenance adjustment coefficient is used to make regional adjustments to the overall maintenance parameter information.

[0081] In one embodiment, the parameter adjustment module includes: A data acquisition unit, used to obtain the partition environment monitoring data and the partition plant growth status data according to the abnormal warning and data collection instructions; A cause analysis unit is used to obtain abnormal cause analysis based on the partition environment monitoring data and the partition plant growth status data combined with the growth difference value; The parameter generation unit is used to determine the type and adjustment range of maintenance parameters that need to be adjusted based on the abnormal cause analysis and the overall maintenance parameter information, and generate partition adjustment parameter information.

[0082] In one embodiment, the maintenance execution module includes: A type identification unit, used for extracting the maintenance adjustment type from the partition adjustment parameter information, where the maintenance adjustment type includes irrigation adjustment, fertilization adjustment and pruning adjustment; An irrigation adjustment unit is used to calculate the adjustment value of irrigation water volume and irrigation duration according to the soil moisture monitoring data; A fertilization adjustment unit is used to determine the adjustment value of fertilizer ratio and fertilizer amount according to soil nutrient monitoring data; A pruning adjustment unit, used to determine adjustment values ​​of pruning height and pruning range according to plant growth density data; The instruction generation unit is used to compare various adjustment values ​​with the plant tolerance range, generate corresponding execution instruction sequences, and trigger maintenance plan adjustment instructions.

[0083] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The electronic device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a data-driven intelligent roof greening construction and maintenance method is implemented.

[0084] Those skilled in the art will understand that Figure 8 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0085] In one embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0086] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0087] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A data-driven intelligent green roof construction and maintenance method, characterized in that: The steps include: Obtaining greening scheme selection information, and obtaining overall maintenance parameter information according to the greening scheme selection information; Acquire roof area characteristic information, divide the roof into several areas according to the roof area characteristic information, and obtain the area maintenance adjustment coefficient; triggering intelligent maintenance instructions according to the partition maintenance adjustment coefficient and the overall maintenance parameter information; Acquire partition growth status detection information, compare the partition growth status detection information with preset standard growth parameters to obtain a growth difference value, compare the growth difference value with a preset change threshold value, and if the growth difference value is outside the preset change threshold range, trigger an abnormal warning and data collection instruction; According to the abnormal warning and data collection instructions, obtain partition adjustment parameter information; According to the partition adjustment parameter information, a maintenance plan adjustment instruction is triggered.

2. The data-driven intelligent green roof construction and maintenance method according to claim 1 is characterized in that: The greening scheme selection information includes plant varieties, greening areas and expected coverage, and the overall maintenance parameter information includes suitable temperature range, humidity range, light requirements and maintenance cycle; obtaining the greening scheme selection information, and obtaining the overall maintenance parameter information according to the greening scheme selection information, specifically includes the following steps: Extract plant variety information from the greening scheme selection information, and obtain corresponding suitable temperature range, humidity range and light requirements according to the plant variety database; Obtaining a maintenance period according to the greening area and the expected coverage combined with the growth characteristics of the plant varieties; The suitable temperature range, humidity range, light requirement and curing period are correlated and integrated to obtain the overall curing parameter information.

3. The data-driven intelligent green roof construction and maintenance method according to claim 2 is characterized in that: The maintenance cycle includes a growth period maintenance cycle and a dormancy period maintenance cycle. The maintenance cycle is obtained according to the greening area and the expected coverage, combined with the growth characteristics of the plant variety, and specifically includes the following steps: According to the growth characteristics and expected coverage of the plant variety, the growing period maintenance cycle and the dormant period maintenance cycle are obtained, wherein the growing period maintenance cycle includes the growing period irrigation frequency, the growing period fertilization frequency and the growing period pruning frequency, and the dormant period maintenance cycle includes the dormant period irrigation frequency, the dormant period fertilization frequency and the dormant period pruning frequency; An annual maintenance plan schedule is determined based on the growth period maintenance cycle and the dormancy period maintenance cycle.

4. The data-driven intelligent green roof construction and maintenance method according to claim 1 is characterized in that: The roof area characteristic information includes orientation, sunshine duration and shading conditions; obtaining the roof area characteristic information, dividing the roof into several areas according to the roof area characteristic information, and obtaining the partition maintenance adjustment coefficient, specifically includes the following steps: According to the sunshine duration and the orientation, the roof is divided into several areas, and the illumination intensity coefficient of each area is obtained; According to the shading condition and the partition illumination intensity coefficient, a partition maintenance adjustment coefficient is determined, and the partition maintenance adjustment coefficient is used to perform regional adjustment on the overall maintenance parameter information.

5. The data-driven intelligent green roof construction and maintenance method according to claim 1 is characterized in that: According to the abnormal warning and data collection instructions, the partition adjustment parameter information is obtained, which specifically includes the following steps: According to the abnormal warning and data collection instructions, obtain the partition environmental monitoring data and the partition plant growth status data; Obtaining abnormal cause analysis based on the sub-area environmental monitoring data and sub-area plant growth status data in combination with the growth difference value; According to the abnormal cause analysis and the overall maintenance parameter information, the type of maintenance parameter to be adjusted and the adjustment range are determined, and the partition adjustment parameter information is generated.

6. The data-driven intelligent green roof construction and maintenance method according to claim 1 is characterized in that: According to the partition adjustment parameter information, a maintenance plan adjustment instruction is triggered, which specifically includes the following steps: Extracting a maintenance adjustment type from the partition adjustment parameter information, wherein the maintenance adjustment type includes irrigation adjustment, fertilization adjustment and pruning adjustment; For irrigation adjustment, the adjustment values ​​of irrigation water volume and irrigation duration are calculated based on soil moisture monitoring data; For fertilization adjustment, determine the adjustment value of fertilizer ratio and fertilizer amount according to soil nutrient monitoring data; For pruning adjustment, the adjustment values ​​of pruning height and pruning range are determined according to the plant growth density data; Compare each adjustment value with the plant tolerance range, generate a corresponding execution instruction sequence, and trigger the maintenance plan adjustment instruction.

7. A data-driven intelligent green roof construction and maintenance system, characterized in that: include: A greening scheme selection module, used to obtain greening scheme selection information, and obtain overall maintenance parameter information according to the greening scheme selection information; A zone division module is used to obtain roof zone characteristic information, divide the roof into several functional zones according to the roof zone characteristic information, and obtain zone maintenance adjustment coefficients; An intelligent maintenance control module, used to trigger an intelligent maintenance instruction according to the partition maintenance adjustment coefficient and the overall maintenance parameter information; A growth status monitoring module is used to obtain partition growth status detection information, compare the partition growth status detection information with preset standard growth parameters to obtain a growth difference value, compare the growth difference value with a preset change threshold value, and if the growth difference value is outside the preset change threshold range, trigger an abnormal warning and data collection instruction; A parameter adjustment module, used to obtain partition adjustment parameter information according to the abnormal warning and data collection instructions; The maintenance execution module is used to trigger the maintenance plan adjustment instruction according to the partition adjustment parameter information.

8. The data-driven intelligent green roof construction and maintenance system according to claim 7 is characterized in that: The greening scheme selection module includes: A parameter acquisition unit, configured to extract plant variety information from the greening scheme selection information, wherein the greening scheme selection information includes plant variety, greening area and expected coverage; A database query unit, used to obtain the corresponding suitable temperature range, humidity range and light requirements according to the plant variety database; A maintenance cycle calculation unit, used to obtain a maintenance cycle according to the greening area and the expected coverage combined with the growth characteristics of the plant variety; A parameter integration unit is used to associate and integrate the suitable temperature range, humidity range, light requirements and maintenance cycle to obtain the overall maintenance parameter information, wherein the overall maintenance parameter information includes the suitable temperature range, humidity range, light requirements and maintenance cycle.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the data-driven intelligent roof greening construction and maintenance method described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the data-driven intelligent roof greening construction and maintenance method described in any one of claims 1 to 6 are implemented.

Images