A smart city green space management method and system based on the Internet of Things
The total irrigation amount and growth information are obtained through Internet of Things technology, and the irrigation plan is determined using the growth status prediction model, which solves the problem of water waste for green space irrigation and achieves optimal growth of green space and water resource conservation.
Patent Information
- Application Number
- CN202211301784.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-12
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2042-07-12
AI Technical Summary
In urban construction, water for green space irrigation is often wasted and difficult to manage scientifically, affecting green space growth and water resource conservation.
Using the Internet of Things-based smart city green space management method and system, we use the growth status prediction model to determine the target irrigation plan, and send irrigation control instructions through the sensing network platform to achieve precise irrigation.
The scientific allocation of green space irrigation water has been achieved, ensuring the optimal growth status of green space, and at the same time saving irrigation water resources and human resources.
Smart Images

Figure CN115623974B_ABST
Abstract
Description
[0001] Description of the case
[0002] This application is a divisional application filed for the Chinese application with application date of July 12, 2022, application number 202210813721.9, and invention name “Smart city green space irrigation water distribution method and system based on the Internet of Things”. Technical Field
[0003] This specification relates to the field of irrigation water distribution, and in particular to a smart city green space management method and system based on the Internet of Things. Background Art
[0004] In urban construction, green space is an indispensable part of improving urban ecology and protecting urban environment. Scientific maintenance of green space is the key to ensure its normal growth. However, a large amount of irrigation water is often wasted in the process of maintaining green space.
[0005] Therefore, there is a need for a smart city green space management method and system based on the Internet of Things to scientifically allocate irrigation water, thereby ensuring that the green space reaches the optimal growth state while saving irrigation water resources. Summary of the invention
[0006] One or more embodiments of this specification provide a smart city green space management method based on the Internet of Things. The method includes: obtaining a preset total irrigation amount for a target area in a first time period in the future; determining multiple candidate irrigation schemes for the multiple green spaces based on the preset total irrigation amount and the first growth information corresponding to each of the multiple green spaces in the first time period, each candidate irrigation scheme including a set of candidate irrigation parameters for irrigating each of the green spaces; determining the target environment information for each of the green spaces in a second time period in the future; for each candidate irrigation scheme, based on the candidate irrigation scheme, the target environment information and the first growth information, determining through a growth condition prediction model whether the multiple green spaces should be irrigated based on the candidate irrigation scheme in the second time period. The second growth information of each of the green spaces after irrigation; based on the second growth information of each of the green spaces, determining the growth promotion value corresponding to the candidate irrigation scheme; based on the growth promotion value corresponding to each of the candidate irrigation schemes, determining the target irrigation scheme for the multiple green spaces in the first time period, the target irrigation scheme including a set of target irrigation parameters for irrigating each of the green spaces in the first time period; based on the target irrigation parameters, generating irrigation control instructions for irrigating each of the green spaces, and sending the irrigation control instructions to the irrigation object platform through the sensor network platform, the irrigation object platform being used to irrigate each of the green spaces in response to the irrigation control instructions.
[0007] One or more embodiments of the present specification provide a smart city green space management system based on the Internet of Things, the system comprising an urban management platform, a sensor network platform, an urban monitoring object platform and an irrigation object platform, wherein the urban management platform is configured to: obtain a preset total irrigation amount for a target area in a first time period in the future; determine a plurality of candidate irrigation schemes for the plurality of green spaces based on the preset total irrigation amount and first growth information corresponding to each of the plurality of green spaces in the first time period, each of the candidate irrigation schemes comprising a set of candidate irrigation parameters for irrigating each of the green spaces; determine target environmental information for each of the green spaces in a second time period in the future; for each of the candidate irrigation schemes, Based on the candidate irrigation scheme, the target environmental information and the first growth information, the second growth information of each of the green spaces after the multiple green spaces are irrigated based on the candidate irrigation scheme in the second time period is determined through a growth condition prediction model; based on the second growth information of each of the green spaces, the growth promotion value corresponding to the candidate irrigation scheme is determined; based on the growth promotion value corresponding to each of the candidate irrigation schemes, the target irrigation scheme for the multiple green spaces in the first time period is determined, the target irrigation scheme including a set of target irrigation parameters for irrigating each of the green spaces in the first time period; based on the target irrigation parameters, an irrigation control instruction for irrigating each of the green spaces is generated. The city management platform is configured to: send the irrigation control instruction to the irrigation object platform; the irrigation object platform is configured to: irrigate each of the green spaces in response to the irrigation control instruction.
[0008] One or more embodiments of the present specification provide a smart city green space management device based on the Internet of Things, the device comprising at least one processor and at least one memory, the at least one memory being used to store computer instructions; the at least one processor being used to execute at least part of the computer instructions in a method as described in any of the above embodiments.
[0009] One or more embodiments of this specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method as described in any one of the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:
[0011] Figure 1It is a schematic diagram of an application scenario of a smart city green space irrigation water distribution system based on the Internet of Things according to some embodiments of this specification;
[0012] Figure 2 is a schematic diagram of a smart city green space irrigation water distribution system based on the Internet of Things according to some embodiments of this specification;
[0013] Figure 3 is an exemplary flow chart of a method for allocating irrigation water for green space in a smart city based on the Internet of Things according to some embodiments of this specification;
[0014] Figure 4 is a schematic diagram of an image recognition model according to some embodiments of this specification;
[0015] Figure 5 is an exemplary flow chart of determining target irrigation parameters according to some embodiments of this specification;
[0016] Figure 6 is a schematic diagram of a growth status prediction model according to some embodiments of this specification;
[0017] Figure 7 is an exemplary flow chart of determining target irrigation parameters according to some embodiments of this specification;
[0018] Figure 8 is another exemplary flow chart of determining target irrigation parameters according to some embodiments of this specification;
[0019] Fig. 9 is another exemplary flow chart for determining target irrigation parameters according to some embodiments of the present specification. DETAILED DESCRIPTION
[0020] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.
[0021] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.
[0022] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprises" and "includes" only indicate the inclusion of the steps and elements that have been clearly identified. These steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.
[0023] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.
[0024] Figure 1 It is a schematic diagram of an application scenario of a smart city green space irrigation water distribution system based on the Internet of Things as shown in some embodiments of this specification.
[0025] In some embodiments, the application scenario 100 of the smart city green space irrigation water distribution system based on the Internet of Things may include a processing device 110, a network 120, a storage device 130, a terminal 140, and a target area 150. In some embodiments, the components in the application scenario 100 may be connected and / or communicated with each other via the network 120 (e.g., wireless connection, wired connection, or a combination thereof). For example, the processing device 110 may be connected to the storage device 130 via the network 120.
[0026] The target area 150 refers to an area where irrigation water needs to be allocated. The target area 150 may include multiple green spaces. For example, green space 150-1 and green space 150-2. Green space refers to green space that is specifically used by the city to improve ecology, protect the environment, provide recreational areas for residents and beautify the landscape. In some embodiments, data required for the allocation of irrigation water for smart city green spaces based on the Internet of Things can be obtained through data acquisition devices (such as image acquisition devices, water volume monitoring devices, etc.) installed on green space 150-1 and green space 150-2. For example, historical monitoring information, historical irrigation parameters, etc.
[0027] In some embodiments, the processing device 110 can directly connect to the storage device 130 and the terminal 140 to exchange information and / or data through the network 120 to access the information and / or data. For example, the processing device 110 can obtain the historical monitoring information of the green space through the network 120. The processing device 110 can obtain the historical monitoring information, historical irrigation parameters, and historical environmental information stored in the storage device 130 through the network 120. The processing device 110 can obtain the historical monitoring information, historical irrigation parameters, and historical environmental information stored in the storage device 130 through the network 120. The processing device 110 can send irrigation control instructions to the terminal 140 through the network 120. In some embodiments, the processing device 110 can process information and / or data related to the application scenario 100 to perform one or more functions described in this specification. For example, the processing device 110 can determine the historical growth information of multiple green spaces in a historical time period based on the historical monitoring information of the green space.
[0028] It should be noted that the application scenario 100 is provided for illustrative purposes only and is not intended to limit the scope of the present application. For those of ordinary skill in the art, various modifications or variations can be made according to the description of this specification. For example, the application scenario 100 of the smart city green space irrigation water distribution system based on the Internet of Things can implement similar or different functions on other devices. However, these changes and modifications will not deviate from the scope of the present application.
[0029] Figure 2 It is a schematic diagram of a smart city green space irrigation water distribution system based on the Internet of Things according to some embodiments of this specification.
[0030] The smart city green space irrigation water distribution system 200 based on the Internet of Things can be implemented based on the Internet of Things system.
[0031] The Internet of Things system is an information processing system that includes but is not limited to user platforms, service platforms, management platforms, sensor network platforms, urban monitoring object platforms, and some or all of the object platforms. The user platform refers to a user-oriented platform that can obtain user needs and feedback information to users. The service platform refers to a platform that can provide input and output services to users. The management platform can realize the overall planning and coordination of the connection and collaboration between various functional platforms (such as sensor network platforms and object platforms). The management platform gathers information from the Internet of Things operating system and can provide perception management and control management functions for the Internet of Things operating system. The sensor network platform can connect the management platform and the object platform, and play the role of sensing information communication and controlling information communication. The object platform is a functional platform for generating perception information and executing control information.
[0032] The information processing in the IoT system can be divided into the processing flow of perception information and the processing flow of control information. Control information can be information generated based on perception information. Among them, the processing of perception information is that the object platform obtains the perception information and transmits it to the management platform through the sensor network platform. The control information is sent from the management platform to the object platform through the sensor network platform, thereby realizing the control of the corresponding object.
[0033] like Figure 2 As shown, the IoT-based smart city green space irrigation water distribution system 200 may include a user platform 210 , a service platform 220 , a city management platform 230 , a sensor network platform 240 , a city monitoring object platform 250 and an irrigation object platform 260 .
[0034] The user platform 210 can be configured as a terminal device for interacting with a user. The user platform 210 can be used to receive information input by a user, generate instructions based on the information and send them to the service platform 220, and display the information sent by the service platform 220 to the user. The user can refer to the manager or user of the smart city green space irrigation water distribution system based on the Internet of Things.
[0035] The service platform 220 may be configured as a first server and may be used to receive instructions sent by the user platform and send them to the city management platform 230 after processing, and to obtain information required by the user from the city management platform 230 and send it to the user platform 210 .
[0036] The city management platform 230 can be configured as a second server and a memory. The city management platform 230 can be used to receive instructions sent by the service platform 220 and control the operation of the irrigation object platform 260 according to the instructions, can receive and store information sent by the city monitoring object platform 250, and can also store urban green space information. Among them, the urban green space information can include the location information, area information, type information and quantity information of vegetation in the green space, etc. of each green space in the city.
[0037] The sensor network platform 240 may be configured as a communication network and gateway for the city management platform 230 to interact with the city monitoring object platform 250 and the irrigation object platform 260. For example, the city management platform 230 may obtain historical monitoring information of multiple green spaces in the target area in historical time periods from the city monitoring object platform 250 through the sensor network platform 240. The city management platform 230 may also send the irrigation control instructions to the irrigation object platform 260 through the sensor network platform 240.
[0038] The city monitoring object platform 250 can be equipped with a variety of data collection devices. The data collection devices may include but are not limited to camera equipment, temperature sensors, light sensors, wind sensors, and rainfall statistics devices. The information that the city monitoring object platform 250 can collect includes but is not limited to image information, temperature information, precipitation information, wind information, light information, etc. The collected information can be transmitted to the city management platform 230.
[0039] The irrigation object platform 260 can be configured as an intelligent irrigation device for performing irrigation operations. The irrigation object platform 260 can receive control instructions from the city management platform 230 and perform irrigation operations according to the instruction content, and can send irrigation operation related information to the city management platform 230 through the sensor network platform 240. Specifically, the irrigation operation related information may include information such as irrigation time and irrigation water volume.
[0040] It should be understood that the above platforms are only simple examples of the relevant platforms mainly involved in this specification, and do not represent the display of all relevant contents of this application. There are also some platforms and units that are not shown in this schematic diagram. Moreover, the above platforms and units are not completely independent and may be cross-involved with each other.
[0041] It should be understood that Figure 2 The system and its platform shown can be implemented in various ways. For example, in some embodiments, the system and its platform can be implemented by hardware, software or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or a dedicated design hardware. Those skilled in the art will understand that the above-mentioned methods and systems can be implemented using computer executable instructions and / or included in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its platform of this specification can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software such as executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software (for example, firmware).
[0042] It should be noted that the above description of the candidate item display and determination system and its platform is only for convenience of description and does not limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the various platforms or form a subsystem to connect with other platforms without deviating from this principle. In some embodiments, Figure 2 The user platform, service platform, city management platform, sensor network platform, city monitoring object platform and object platform disclosed in the specification can be different platforms in one system, or one platform can realize the functions of two or more platforms. For example, each platform can share a storage module, or each platform can have its own storage module. Such variations are all within the protection scope of this specification.
[0043] Figure 3 This is an exemplary flow chart of a method for allocating irrigation water for green space in a smart city based on the Internet of Things according to some embodiments of this specification. Figure 3 As shown, process 300 may include the following steps:
[0044] Step 310: The city management platform obtains historical monitoring information of multiple green spaces in the target area during historical time periods from the city monitoring object platform via the sensor network platform.
[0045] The target area may refer to a certain area covered by the smart city green space irrigation water distribution system based on the Internet of Things. For example, the target area may be the entire city. For another example, the target area may be an administrative district or area within the city.
[0046] The historical time period may refer to a period of time before the time point when the green space is irrigated. The length of the historical time period may be preset. The historical time period may include multiple time points, and the time intervals between the multiple time points may be preset.
[0047] Historical monitoring information may be monitoring information of green space at multiple time points within a historical time period. Historical monitoring information may include image information, video information, etc. of green space within a historical time period. Historical monitoring information may include other information, such as type information and quantity information of vegetation in green space within a historical time period. In some embodiments, historical monitoring information may be a sequence based on time, which may include monitoring information at multiple time points within a historical time period. Historical monitoring information may be obtained in a variety of ways. For example, image information, video information, etc. within a historical time period may be obtained by photographing multiple green spaces in the target area using a camera configured by the urban monitoring object platform; type information and quantity information of vegetation may be obtained from the memory of the urban management platform.
[0048] Step 320: The city management platform determines historical growth information of the plurality of green spaces within a historical time period based on the historical monitoring information of the plurality of green spaces.
[0049] Historical growth information may refer to information about the growth of vegetation in a green space within a historical time period. Historical growth information may be represented by a historical growth score. The historical growth score may be a score within a preset range, and the higher the score, the better the growth condition of the green space. For example, the historical growth score may be a score between 0 and 100. In some embodiments, the historical growth information may be a sequence based on time, and the sequence may include environmental information at multiple time points within the historical time period. When the historical growth information is represented by a historical growth score, the historical growth information may be a sequence of historical growth scores at multiple time points within the historical time period.
[0050] In some embodiments, historical monitoring information of multiple green areas may be analyzed to determine historical growth information of the multiple green areas within a historical time period.
[0051] In some embodiments, the city management platform can process the historical monitoring information based on the image recognition model to determine the historical growth scores of multiple green spaces in the historical time period. Figure 4 And the corresponding instructions will not be repeated here.
[0052] Step 330: The urban management platform determines the target irrigation parameters for each green space in the first time period in the future based on the historical growth information.
[0053] The first time period may refer to a fixed length of time in the future. The length of the first time period may be preset. For example, the first time period may be one week in the future.
[0054] The target irrigation parameters may refer to the operation parameters when irrigating each green space. The target irrigation parameters may include one or more of the irrigation water volume, irrigation method, and irrigation time. The irrigation method includes but is not limited to drip irrigation, sprinkler irrigation, and the like.
[0055] In some embodiments, modeling can be performed or various data analysis algorithms, such as regression analysis, discriminant analysis, etc., can be used to analyze and process historical growth information to obtain target irrigation parameters for each green space in the first time period in the future.
[0056] In some embodiments, for each green space, the city management platform can obtain the historical irrigation parameters of the green space in the historical time period through the irrigation object platform and the historical environmental information of the green space in the historical time period through the city monitoring object platform; based on the historical growth information, historical irrigation parameters and historical environmental information, determine the first growth information of the green space in the first time period through the growth status prediction model; based on the first growth information corresponding to each piece of green space, determine the target irrigation parameters of each piece of green space in the first time period. For more information about the above embodiments, see Figure 5 and its corresponding description.
[0057] Step 340: The urban management platform generates irrigation control instructions for irrigating each green space based on the target irrigation parameters.
[0058] The irrigation control instruction may refer to an instruction for controlling the irrigation equipment to irrigate the green space. The urban management platform may generate corresponding irrigation control instructions based on the target irrigation parameters of each green space.
[0059] Step 350: The city management platform sends the irrigation control instruction to the irrigation object platform through the sensor network platform, and the irrigation object platform is used to irrigate each green space in response to the irrigation control instruction.
[0060] Figure 4 It is a schematic diagram of an image recognition model according to some embodiments of this specification.
[0061] In some embodiments, the image recognition model can process the historical monitoring information of a green space to determine the historical growth information of the green space in the historical time period. Figure 4 As shown, the image recognition model 420 may include a first feature extraction layer 420-1 and a score determination layer 420-2 connected in sequence. The input of the image recognition model 420 may include historical monitoring information 410 of a certain green space in a historical time period, and the output may include a historical growth score 430 of the green space in a historical time period.
[0062] In some embodiments, the first feature extraction layer can process the historical monitoring information of a green space in a historical time period to determine the historical image feature vector of the green space in the historical time period. When the historical monitoring information is image information, the features in the image information (for example, the color and height of the vegetation, etc.) can be extracted to determine the historical image feature vector of the green space in the historical time period. Each dimension of the historical image feature vector can correspond to an image feature. The first feature extraction layer can be a convolutional neural network model. Figure 4 As shown, the input of the first feature extraction layer 420 - 1 may be historical monitoring information 410 of a certain green space in a historical time period, and the output may be a historical image feature vector 421 of the green space.
[0063] In some embodiments, the scoring determination layer can process the historical image feature vector of a green space in the historical time period to determine the historical growth score of the green space in the historical time period. The scoring determination layer can be a deep neural network model. Figure 4 As shown, the input of the score determination layer 420 - 2 may be a historical image feature vector 421 of a certain green space, and the output may be a historical growth score 430 of the green space in a historical period of time.
[0064] In some embodiments, the image recognition model can be determined by jointly training the first feature extraction layer and the score determination layer. The training sample can include sample monitoring information of the sample green space in the sample time period, and the label of the training sample can be the growth information of the sample time period. The label can be obtained by manually annotating the sample monitoring information of the sample green space in the sample time period. It should be understood that the vegetation type of the sample green space and the green space to be predicted should be the same or the same major category, such as the vegetation type of the sample green space and the green space to be predicted are both ryegrass. Multiple training samples are input into the initial first feature extraction layer, and the output of the initial first feature extraction layer is input into the initial score determination layer. A loss function is constructed based on the output and label of the initial score determination layer. And the parameters of the initial first feature extraction layer and the initial score determination layer are iteratively updated based on the loss function until the preset conditions are met, and the training ends. The parameters in the first feature extraction layer and the score determination layer can be determined to obtain a trained image recognition model. The preset conditions may include but are not limited to the convergence of the loss function, the loss function value is less than the preset value, or the number of training iterations reaches a threshold.
[0065] In some embodiments of this specification, the image recognition model can be used to determine the historical growth information of each green space in the historical time period, thereby reducing the cost of manual judgment and improving processing efficiency. In some other embodiments of this specification, the multi-layer structure of the image recognition model can be used to process different data separately, further improving the accuracy of the calculation results of the image recognition model.
[0066] Figure 5 FIG. 1 is an exemplary flow chart of determining target irrigation parameters according to some embodiments of the present specification. Figure 5 As shown, process 500 may include the following steps:
[0067] Step 510, for each green space, the city management platform obtains the historical irrigation parameters of the green space in the historical time period through the irrigation object platform and obtains the historical environmental information of the green space in the historical time period through the city monitoring object platform.
[0068] The historical irrigation parameters refer to the irrigation parameters of the green space in the historical time period. As an example only, the historical irrigation parameters may be the irrigation parameters of a green space irrigated in the previous month. The historical irrigation parameters include: the irrigation frequency is 3 days / time, and the average irrigation water volume is 9-10 tons / mu each time. In some embodiments, the historical irrigation parameters may be a sequence based on time, and the sequence may include the irrigation parameters of multiple time points in the historical time period.
[0069] Historical irrigation parameters can be obtained through the irrigation object platform. For example, the city management platform can obtain historical irrigation parameters from the historical data of the irrigation object platform.
[0070] Historical environmental information refers to environmental information of green space in historical time periods. For example, historical environmental information may include rainfall, temperature, humidity, light intensity, wind speed, etc. in the historical time period of the area where the green space is located. In some embodiments, the historical environmental information may be a sequence based on time, and the sequence may include environmental information at multiple time points in the historical time period.
[0071] The historical environment information can be obtained through the city monitoring object platform. For example, the city monitoring object platform can obtain the historical environment information from the historical data according to the needs of the city management platform.
[0072] Step 520: The urban management platform determines the first growth information of the green space in the first time period through a growth condition prediction model based on the historical growth information, historical irrigation parameters, and historical environmental information.
[0073] The first growth information may refer to the growth information of the green space in a first time period in the future. Similar to the historical growth information, the first growth information may be represented by a first growth score. As an example only, the first growth score may also be a score in the range of 0 to 100.
[0074] In some embodiments, the growth status prediction model can process the growth information, irrigation parameters, and environmental information of a green space in a certain time period to determine the first growth information in the next time period corresponding to the time period.
[0075] The growth status prediction model can be used to determine the first growth information of the green space in the first time period. The growth prediction model can include but is not limited to a combination of one or more of a convolutional neural network and a deep neural network.
[0076] For each green space, the growth condition prediction model can process the historical growth information, historical irrigation parameters and historical environmental information to determine the first growth information of the green space in the first time period. The growth condition prediction model may include but is not limited to a combination of one or more of a convolutional neural network model and a deep neural network model. The input of the growth condition prediction model may include the historical growth information, historical irrigation parameters and historical environmental information of a green space. Among them, the historical growth information, historical irrigation parameters and historical environmental information can all be sequences based on time. The output of the growth condition prediction model may include the first growth information of the green space in the first time period.
[0077] In some embodiments, the growth condition prediction model can be obtained by training. The initial growth condition prediction model can be trained based on multiple sets of labeled training samples. The training samples may include sample growth information, sample irrigation parameters, and sample environmental information of the sample green space in the first sample time period. The label may be the growth information of the sample green space in the second sample time period, wherein the first sample time period is earlier than the second sample time period. The label may be obtained by manually annotating the sample monitoring information of the sample green space in the second sample time period, or by processing the sample monitoring information through the aforementioned image recognition model. It should be understood that the vegetation type of the sample green space and the green space to be predicted should be the same or the same major category. Multiple training samples are input into the initial growth condition prediction model. A loss function is constructed based on the output and label of the initial growth condition prediction model, and the parameters of the initial growth condition prediction model are iteratively updated based on the loss function. When the trained model meets the preset conditions, the training ends and the trained growth condition prediction model is obtained. The preset conditions may include but are not limited to the convergence of the loss function, the loss function value is less than the preset value, or the number of training iterations reaches a threshold.
[0078] In some embodiments, the growth condition prediction model can also be a custom model. Figure 6 As shown, the growth condition prediction model 650 may include a second feature extraction layer 650-1, a third feature extraction layer 650-2, a fourth feature extraction layer 650-3, and a growth prediction layer 650-4.
[0079] In some embodiments, the second feature extraction layer can process the historical growth information to determine the growth sequence characteristics of the green space in the historical time period. The second feature extraction layer can be a deep neural network model. Figure 6 As shown, the input of the second feature extraction layer 650-1 may be the historical growth information 610, and the output of the second feature extraction layer 650-1 may be the growth sequence feature 651. The growth sequence feature may refer to a sequence feature obtained after feature extraction of the historical growth information.
[0080] In some embodiments, the third feature extraction layer can process historical irrigation parameters to determine the irrigation sequence characteristics of the green space in the historical time period. The third feature extraction layer can be a deep neural network model. Figure 6 As shown, the input of the third feature extraction layer 650-2 may be the historical irrigation parameter 620, and the output of the third feature extraction layer 650-2 may be the irrigation sequence feature 652. The irrigation sequence feature may refer to a sequence feature obtained after feature extraction of the historical irrigation parameter.
[0081] In some embodiments, the fourth feature extraction layer can process the historical environmental information to determine the environmental sequence characteristics of the green space in the historical time period. The fourth feature extraction layer can be a deep neural network model. Figure 6 As shown, the input of the fourth feature extraction layer 650-3 may be historical environment information 630, and the output of the fourth feature extraction layer 650-3 may be environment sequence features 653. The environment sequence features may refer to sequence features obtained after feature extraction of historical environment information.
[0082] In some embodiments, the growth prediction layer can process the growth sequence characteristics, irrigation sequence characteristics, and environmental sequence characteristics to determine the first growth information of the green space in the first time period. The growth prediction layer can be a long short-term memory network model. Figure 6 As shown, the input of the growth prediction layer 650 - 4 may include growth sequence features 651 , irrigation sequence features 652 , and environment sequence features 653 , and the output of the growth prediction layer 650 - 4 may include first growth information 660 of the green space in a first time period.
[0083] In some embodiments, the second feature extraction layer, the third feature extraction layer, the fourth feature extraction layer and the growth prediction layer can be obtained by joint training. The training sample includes the sample growth information, sample irrigation parameters and sample environmental information of the sample green space in the third sample time period. The label can be the growth information of the sample green space in the fourth sample time period, and the third sample time period is earlier than the fourth sample time period. Among them, the label can be obtained by manually annotating the sample monitoring information of the sample green space in the fourth sample time period, or by processing the sample monitoring information through the aforementioned image recognition model. It should be understood that the vegetation types of the sample green space and the green space to be predicted should be the same or the same major category, such as the vegetation types of the sample green space and the green space to be predicted are both ryegrass. The sample growth information in the training sample is input into the initial second feature extraction layer, the sample irrigation parameters in the training sample are input into the initial third feature extraction layer, and the sample environmental information in the training sample is input into the initial fourth feature extraction layer. Then the outputs of the initial second feature extraction layer, the initial third feature extraction layer and the initial fourth feature extraction layer are input into the initial growth prediction layer, and a loss function is constructed based on the output and label of the initial growth prediction layer. Iteratively update the parameters of each layer in the initial growth condition prediction model based on the loss function until the preset conditions are met to obtain a trained growth condition prediction model. The preset conditions may include but are not limited to loss function convergence, loss function value is less than a preset value, or the number of training iterations reaches a threshold.
[0084] like Figure 6 As shown, the growth condition prediction model 650 may further include a first feature extraction layer 650 - 5 .
[0085] In some embodiments, the first feature extraction layer can process the historical monitoring information to determine the historical image feature vectors of multiple green spaces. Figure 6 As shown, the input of the first feature extraction layer 650 - 5 may be the historical monitoring information 640 , and the output of the first feature extraction layer 650 - 5 may be the historical image feature vector 654 .
[0086] The growth prediction layer 650 - 4 may process the growth sequence feature 651 , the irrigation sequence feature 652 , the environment sequence feature 653 , and the historical image feature vector 654 to determine the first growth information 660 of the green space in the first time period.
[0087] In some embodiments, the parameters of the first feature extraction layer can be obtained by performing transfer learning on the first feature extraction layer in the trained image recognition model. Figure 4 and its related description.
[0088] Step 530: The urban management platform determines the target irrigation parameters for each green space in the first time period based on the first growth information corresponding to each green space.
[0089] In some embodiments, modeling can be performed or various data analysis algorithms, such as regression analysis, discriminant analysis, etc., can be used to analyze and process the first growth information corresponding to each green space to determine the target irrigation parameters of each green space in the first time period.
[0090] In some embodiments, the city management platform can obtain the preset total irrigation volume of the target area in the first time period. Based on the preset total irrigation volume and the first growth information of each green space, combined with a preset algorithm, the target irrigation parameter corresponding to each green space is determined. For more information about the above embodiments, please refer to Figure 7 and its related description.
[0091] In some embodiments, the urban management platform can also obtain the preset total irrigation amount of the target area within the first time period; based on the preset total irrigation amount and the first growth information corresponding to each green space, determine multiple candidate irrigation schemes for multiple green spaces, each candidate irrigation scheme includes a set of candidate irrigation parameters for irrigating each green space; determine the target environmental information of each green space in the second time period in the future; for each candidate irrigation scheme, based on the candidate irrigation scheme, the target environmental information and the first growth information, determine the second growth information of each green space after the multiple green spaces are irrigated based on the candidate irrigation scheme in the second time period through a growth condition prediction model; based on the second growth information of each green space, determine the growth promotion value corresponding to the candidate irrigation scheme; based on the growth promotion value corresponding to each candidate irrigation scheme, determine the target irrigation scheme for the multiple green spaces, the target irrigation scheme includes a set of target irrigation parameters for irrigating each green space in the first time period. For more information about the above embodiments, please refer to Fig. 9 and its related description.
[0092] Some embodiments of this specification can accurately predict the growth of green land through models based on historical data of green land, so as to determine more scientific target irrigation parameters, save irrigation water resources and human resources responsible for irrigation while ensuring the normal growth of green land.
[0093] Figure 7 FIG. 1 is an exemplary flow chart of determining target irrigation parameters according to some embodiments of the present specification. Figure 7 As shown, process 700 may include the following steps:
[0094] Step 710: The city management platform obtains a preset total irrigation amount for the target area within a first time period.
[0095] The preset total irrigation volume refers to the total amount of water available for irrigation operations in the target area during the first time period.
[0096] The preset total irrigation amount can be obtained from the database of the city management platform. For example, the preset total irrigation amount in the database of the city management platform can be updated regularly (e.g., daily, weekly, etc.) according to known conditions. When there is a data request for obtaining the preset total irrigation amount, the latest preset total irrigation amount can be retrieved for subsequent processing.
[0097] Step 720: The urban management platform determines the target irrigation parameters corresponding to each green space based on the preset total irrigation amount and the first growth information of each green space in combination with a preset algorithm.
[0098] In some embodiments, the city management platform may use various preset algorithms to analyze and process the preset irrigation amount and the first growth information of each green space to determine the target irrigation parameters corresponding to each green space. For example, the preset algorithms may include regression analysis, discriminant analysis, etc.
[0099] In some embodiments, the urban management platform can determine multiple candidate irrigation schemes for multiple green spaces based on a preset total irrigation volume and the first growth information corresponding to each green space, each candidate irrigation scheme including a set of candidate irrigation parameters for irrigating each green space; for each candidate irrigation scheme, perform at least one round of iterative updates on the candidate irrigation scheme through a preset algorithm to determine the growth promotion value of the candidate irrigation scheme in a second time period in the future; based on the growth promotion value corresponding to each candidate irrigation scheme, determine the target irrigation scheme for multiple green spaces, the target irrigation scheme including a set of target irrigation parameters for irrigating each green space in the first time period. For more information about the above embodiments, see Figure 8 and its related description.
[0100] Some embodiments of the present specification may allocate the planned preset total amount of irrigation water more scientifically based on the preset total amount of irrigation and the first growth information of each green space.
[0101] Figure 8 FIG. 4 is another exemplary flow chart for determining target irrigation parameters according to some embodiments of the present specification. Figure 8 As shown, process 800 may include the following steps:
[0102] Step 810, the urban management platform determines multiple candidate irrigation schemes for multiple green spaces based on a preset total irrigation amount and the first growth information corresponding to each green space, each candidate irrigation scheme including a set of candidate irrigation parameters for irrigating each green space.
[0103] The candidate irrigation scheme may refer to a candidate scheme for irrigating multiple green spaces in the target area. The candidate irrigation scheme may include candidate irrigation parameters for each green space. It should be understood that the total amount of water used by the candidate irrigation parameters for each green space in each candidate irrigation scheme should not exceed the preset total irrigation amount. The candidate irrigation parameters may refer to the irrigation parameters allocated to each green space in the target area in the candidate irrigation scheme. For example, the first irrigation parameter of a green space may include an irrigation water volume of 2 tons / mu.
[0104] In some embodiments, the city management platform can analyze and process the preset total irrigation amount and the first growth information corresponding to each green space to determine multiple candidate irrigation schemes. For example, the preset total irrigation amount can be allocated based on the area ratio of each green space to determine the initial irrigation water volume of each green space. The irrigation water volume is adjusted based on multiple adjustment values corresponding to the first growth information of each green space to determine the irrigation water volume of each green space. Then, based on the irrigation water volume of each green space and the preset irrigation rules of each green space, multiple candidate irrigation parameters of each green space are determined. For example, based on the area of a green space, it is preliminarily determined that the initial irrigation water volume of the green space in the next three days is 2 tons. The first growth information of the green space is 85 points. According to the preset corresponding relationship, the adjustment value corresponding to the first growth information can be determined to be -0.10 tons, -0.15 tons and -0.20 tons. Based on the irrigation water volume of the green space in the next three days being 1.90 tons, 1.85 tons and 1.80 tons respectively, the irrigation water volume is allocated according to the irrigation rules of the green space, and multiple candidate irrigation parameters of the green space can be determined. In some embodiments, multiple candidate irrigation parameters for each green space may be combined to determine multiple candidate irrigation plans.
[0105] For another example, the urban management platform can also determine the historical irrigation plans corresponding to the time periods for each green space that are similar to the current preset total irrigation amount and the first growth information corresponding to each green space based on historical data, and use the aforementioned historical irrigation plans as candidate irrigation plans.
[0106] In step 820, the urban management platform uses a preset algorithm to perform at least one round of iterative updates on multiple candidate irrigation plans until preset conditions are met. The multiple candidate irrigation plans after iterative updates converge into a target irrigation plan, which includes a set of target irrigation parameters for irrigating each green space in a first time period.
[0107] In some embodiments, the urban management platform can perform at least one round of iterative updates on each candidate irrigation scheme through a preset algorithm; for each iteratively updated candidate irrigation scheme, the growth promotion value corresponding to the iteratively updated candidate irrigation scheme is determined based on the iteratively updated candidate irrigation scheme. Among them, the growth promotion value can represent the total growth information of all green spaces in the target area in the second time period in the future. The growth promotion value can be determined based on the second growth information and represented as the sum of the second growth scores. The second growth information can represent the growth information of the green space in the second time period in the future. Similar to the historical growth information, the second growth information can also be represented by the second growth score. For example, the second growth score can be a score of 0 to 100. In some embodiments, the iteratively updated candidate irrigation scheme can be processed based on the growth condition prediction model to determine the growth promotion value corresponding to the iteratively updated candidate irrigation scheme. For more information on determining the growth promotion value corresponding to the iteratively updated candidate irrigation scheme, please refer to Fig. 9 and its related description.
[0108] For each candidate irrigation scheme, during the iterative update of the candidate irrigation scheme, the candidate irrigation parameters in the candidate irrigation scheme may correspond to a multidimensional increment, wherein the multidimensional increment may refer to the adjustment range of the irrigation water volume of each green space included in the candidate irrigation scheme in each iteration.
[0109] In the first round of iteration, the initial candidate irrigation scheme can be updated based on the initial multidimensional increment to obtain an updated candidate irrigation scheme. The updated candidate irrigation scheme is determined as the candidate irrigation scheme to be processed, and the initial multidimensional increment is determined as the multidimensional increment to be processed in the next round. The initial multidimensional increment can be a system default value, an experience value, a manually preset value, etc. set according to actual needs, or any combination thereof.
[0110] In some embodiments, the initial candidate irrigation scheme can be obtained by initializing the vector. The exemplary process of initializing the vector is as follows: for a number of green spaces (assuming the number is D), the number of initial candidate irrigation schemes can be set to N. At this time, the dimension of each initial candidate irrigation scheme is D (each dimension corresponds to the amount of irrigation water for a green space), and the vector corresponding to the i-th initial candidate irrigation scheme is It can be expressed as:
[0111]
[0112] The vectors corresponding to the N initial candidate irrigation schemes It can be expressed as:
[0113]
[0114] Wherein, 0 is an identifier (representing the 0th round of iteration, i.e., the initial value before the iteration starts), and i is the number of the candidate irrigation scheme, where i≤N.
[0115] In each subsequent round of iteration, the multidimensional increment to be processed in that round is updated to obtain an updated multidimensional increment. The candidate irrigation scheme to be processed is updated based on the updated multidimensional increment to obtain an updated candidate irrigation scheme. The updated candidate irrigation scheme is determined as the candidate irrigation scheme to be processed in the next round, and the updated multidimensional increment is determined as the multidimensional increment to be processed in the next round.
[0116] In some embodiments, updating the multidimensional increment to be processed can be achieved by updating the increment element to be processed. The increment element is an element of each dimension of the multidimensional increment, and the multidimensional increment can include multiple increment elements. There can be a corresponding relationship between each green space in the candidate irrigation scheme to be processed and each increment element. The increment element can be used to characterize the adjustment range of the irrigation water volume of the corresponding green space.
[0117] In some embodiments, the incremental element to be processed can be updated based on the current loss in the previous round, and the updated incremental element can be used as the incremental element to be processed in the next round. The current loss in the previous round can be determined based on the difference between the candidate irrigation water element obtained in the previous round and the effect of the historical optimal candidate irrigation parameter.
[0118] For example, after the k+1th iteration, the updated incremental element can be calculated by the following formula (1):
[0119]
[0120] Where i represents the number of the candidate irrigation scheme, where i≤N; d represents the number of the green space, where d≤D. k represents the number of iterations, where k≥0. It represents the incremental element to be processed after the kth iteration of the i-th candidate irrigation scheme. represents the i-th candidate irrigation scheme obtained after the k-th iteration. ω represents the inertia weight constant. c1 represents the individual learning factor, and c2 represents the group learning factor. r1 and r2 are arbitrary values in the interval [0,1], which are used to increase the randomness of the search. is the value of the optimal solution of the ith candidate irrigation scheme in the dth green space after the kth iteration. The optimal solution at this time can refer to the irrigation water volume set of each green space corresponding to the candidate irrigation scheme when the growth promotion value of a candidate irrigation scheme after the kth iteration is the maximum value among the multiple growth promotion values corresponding to the previous iterations (i.e., the individual historical optimal solution). is the value of the optimal solution of all N candidate irrigation schemes in the iterations after the kth round of iterations in the dth green space. The optimal solution at this time may refer to the irrigation water volume set of each green space corresponding to the candidate irrigation scheme with the maximum growth promotion value among the aforementioned multiple candidate irrigation schemes with the maximum growth promotion value in the iterations after the kth round of iterations (i.e., the group historical optimal solution).
[0121] The aforementioned inertia weight constant ω, individual learning factor c1, group learning factor c2, and random constants r1 and r2 may be system default values, empirical values, artificially preset values, etc. set according to actual needs, or any combination thereof.
[0122] In some embodiments, the maximum absolute value of the increment element in each iteration can be v max , which means the maximum adjustment range of irrigation water volume for each green space. In the k+1th iteration, the multidimensional increment V i It can be expressed as (v i1 ,v i2 ,…,v iD The vector of multidimensional increments corresponding to the N candidate irrigation schemes can be expressed as ((v 11 ,v 12 ,…,v 1D ),(v 21 ,v 22 ,…,v 2D ),…,(v N1 ,v N2 ,…,v ND )). Any increment in the vector can be negative, but its absolute value is no greater than v. max .
[0123] In some embodiments, each candidate irrigation scheme to be processed may be updated based on the incremental element in the updated multidimensional increment. For example, after the k+1th iteration, the updated candidate irrigation scheme may be calculated by the following formula (2):
[0124]
[0125] For example, after the first iteration, the updated i-th candidate irrigation scheme can be calculated by the following formula (3):
[0126]
[0127] The vector expression corresponding to the N updated candidate irrigation schemes can be calculated by the following formula (4):
[0128]
[0129] In some embodiments, in each round of iterative updating of candidate irrigation schemes, the total irrigation water volume Q of all green spaces (i.e., the sum of vector values of all dimensions) may be subject to constraints:
[0130] Q = ∑(X id )=(X i1 +X i2 +X i3 ,…,X iD )≤S
[0131] Wherein, S can be the preset total irrigation amount.
[0132] In some embodiments, if after a certain iteration, the total irrigation water volume Q corresponding to the candidate irrigation parameters in a candidate irrigation scheme is greater than S, the irrigation water volume of each green space in the candidate irrigation scheme can be reduced by a proportion (S / Q). The corresponding total irrigation volume is:
[0133]
[0134] Then which is reduced to:
[0135]
[0136] In some embodiments, the candidate irrigation schemes may be continuously iterated and updated through the preset algorithm until a preset condition is met and the iterative update ends. The preset condition may be that a preset value is reached, or that the ratio of the growth promotion value obtained by the algorithm to the preset theoretical maximum growth promotion value is greater than a threshold.
[0137] After the iterative update is completed, the multiple candidate irrigation schemes after the iterative update can converge into a target irrigation scheme. The target irrigation scheme includes a set of target irrigation parameters for irrigating each green space in the first time period. At this time, the growth promotion value corresponding to the target irrigation scheme should be the maximum value of the growth promotion values corresponding to the multiple candidate irrigation schemes updated in previous iterative updates.
[0138] Some embodiments of this specification can continuously update multiple candidate irrigation schemes in an iterative manner and continuously optimize the candidate irrigation schemes, thereby determining the target irrigation scheme with the greatest growth promotion value, while saving irrigation water and further enabling the green space to achieve the best growth condition.
[0139] Fig. 9 FIG. 1 is another exemplary flow chart for determining target irrigation parameters according to some embodiments of the present specification. Fig. 9 As shown, process 900 may include the following steps:
[0140] Step 910: The city management platform obtains a preset total irrigation amount for the target area within a first time period.
[0141] Step 920, the urban management platform determines multiple candidate irrigation schemes for the multiple green spaces based on the preset total irrigation amount and the first growth information corresponding to each green space, each candidate irrigation scheme including a set of candidate irrigation parameters for irrigating each green space.
[0142] Step 930: The city management platform determines the target environmental information of each green space in the second future time period.
[0143] The target environmental information may refer to environmental information in the second time period in the future. Similar to the historical environmental information, the target environmental information may include the rainfall, temperature, humidity, light intensity, wind speed, etc. of the area where the green space is located in the second time period. The urban management platform may obtain the target environmental information through the sensor network platform.
[0144] Step 940, for each candidate irrigation scheme, the urban management platform determines, based on the candidate irrigation scheme, the target environment information and the first growth information, the second growth information of each green space after the multiple green spaces are irrigated with the candidate irrigation scheme within a second time period through a growth condition prediction model.
[0145] For each candidate irrigation plan, the irrigation parameters corresponding to a green space in the candidate irrigation plan, the target environment information of the green space and the first growth information of the green space can be input into the growth condition prediction model, and the output of the growth condition prediction model can be the second growth information of the green space.
[0146] Step 950: The urban management platform determines the growth promotion value corresponding to the candidate irrigation scheme based on the second growth information of each green space.
[0147] In step 960, the urban management platform determines target irrigation plans for the plurality of green spaces based on the growth promotion value corresponding to each candidate irrigation plan.
[0148] The urban management platform can determine the candidate irrigation plan corresponding to the greatest growth promotion value as the target irrigation plan.
[0149] In some embodiments of the present specification, multiple candidate irrigation schemes are compared through a growth condition prediction model, and from a longer-term future time period, a candidate irrigation scheme with greater growth promotion value is determined as a target irrigation scheme. While ensuring the normal growth of the green space, more scientific target irrigation parameters can be determined to avoid waste of resources.
[0150] It should be noted that the above description of each process is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to each process under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.
[0151] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.
[0152] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.
[0153] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.
[0154] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.
[0155] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values is as accurate as possible within the feasible range.
[0156] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.
[0157] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.
Claims
1. A smart city green space management method based on the Internet of Things, characterized in that: The method is executed by the city management platform and includes: Obtaining the preset total irrigation amount of the target area in the first future time period; Determine, based on the preset total irrigation amount and the first growth information corresponding to each of the plurality of green spaces in the first time period, a plurality of candidate irrigation schemes for the plurality of green spaces, each of the candidate irrigation schemes comprising a set of candidate irrigation parameters for irrigating each of the green spaces; Determining target environmental information for each piece of green land in a second future time period; For each of the candidate irrigation schemes, based on the candidate irrigation scheme, the target environment information and the first growth information, determining, by a growth condition prediction model, second growth information of each of the green spaces after the plurality of green spaces are irrigated based on the candidate irrigation scheme within the second time period; Determining the growth promotion value corresponding to the candidate irrigation scheme based on the second growth information of each piece of the green space; Determining a target irrigation scheme for the plurality of green spaces in the first time period based on the growth promotion value corresponding to each of the candidate irrigation schemes, the target irrigation scheme comprising a set of target irrigation parameters for irrigating each of the green spaces in the first time period; Based on the target irrigation parameters, an irrigation control instruction for irrigating each of the green spaces is generated, and the irrigation control instruction is sent to the irrigation object platform through the sensor network platform. The irrigation object platform is used to irrigate each of the green spaces in response to the irrigation control instruction.
2. The method according to claim 1, characterized in that The growth condition prediction model is obtained by training an initial growth condition prediction model based on multiple groups of labeled training samples, the training samples include sample growth information, sample irrigation parameters and sample environmental information of the sample green space in a first sample time period, the label is the sample growth information of the sample green space in a second sample time period, and the first sample time period is earlier than the second sample time period.
3. The method according to claim 1, characterized in that Determining the first growth information of each piece of the green space in the first time period includes: For each of the green areas, Acquire historical irrigation parameters of the green space in a historical period through the irrigation object platform, and acquire historical environmental information and historical monitoring information of the green space in the historical period through the city monitoring object platform; Determining historical growth information of the green space within the historical time period based on the historical monitoring information of the green space; Based on the historical growth information, the historical irrigation parameters and the historical environmental information, the first growth information of the green space in the first time period is determined by the growth condition prediction model.
4. The method according to claim 3, characterized in that The historical growth information, the historical irrigation parameters and the historical environmental information are all sequences based on time.
5. The method according to claim 3, characterized in that The determining, based on the historical monitoring information of the green space, the historical growth information of the green space within the historical time period comprises: The historical monitoring information of the green space is processed based on an image recognition model to determine the historical growth information of the green space in the historical time period.
6. The method according to claim 5, characterized in that The historical monitoring information includes image information, and the image recognition model includes a first feature extraction layer and a score determination layer connected in sequence. The first feature extraction layer processes the historical monitoring information of the green space to determine a historical image feature vector; the score determination layer processes the historical image feature vector to determine a historical growth score of the green space, and the historical growth score is used to characterize the historical growth information.
7. The method according to claim 6, characterized in that The growth condition prediction model includes a second feature extraction layer, a third feature extraction layer, a fourth feature extraction layer and a growth prediction layer; the second feature extraction layer processes the historical growth information to determine the growth sequence characteristics of the green space in the historical time period; the third feature extraction layer processes the historical irrigation parameters to determine the irrigation sequence characteristics of the green space in the historical time period; the fourth feature extraction layer processes the historical environmental information to determine the environmental sequence characteristics of the green space in the historical time period; the growth prediction layer processes the growth sequence characteristics, the irrigation sequence characteristics and the environmental sequence characteristics to determine the first growth information of the green space.
8. A smart city green space management system based on the Internet of Things, characterized in that: The system includes a city management platform, a sensor network platform, a city monitoring object platform and an irrigation object platform, wherein: The city management platform is configured as follows: Obtaining the preset total irrigation amount of the target area in the first future time period; Determine, based on the preset total irrigation amount and the first growth information corresponding to each of the plurality of green spaces in the first time period, a plurality of candidate irrigation schemes for the plurality of green spaces, each of the candidate irrigation schemes comprising a set of candidate irrigation parameters for irrigating each of the green spaces; Determining target environmental information for each piece of green land in a second future time period; For each of the candidate irrigation schemes, based on the candidate irrigation scheme, the target environment information and the first growth information, determining, by a growth condition prediction model, second growth information of each of the green spaces after the plurality of green spaces are irrigated based on the candidate irrigation scheme within the second time period; Determining the growth promotion value corresponding to the candidate irrigation scheme based on the second growth information of each piece of the green space; Determining a target irrigation scheme for the plurality of green spaces in the first time period based on the growth promotion value corresponding to each of the candidate irrigation schemes, the target irrigation scheme comprising a set of target irrigation parameters for irrigating each of the green spaces in the first time period; Based on the target irrigation parameters, generating an irrigation control instruction for irrigating each piece of the green space; The city management platform is configured as follows: Sending the irrigation control instruction to the irrigation object platform; The irrigation object platform is configured as follows: Each of the green spaces is irrigated in response to the irrigation control instruction.
9. A smart city green space management device based on the Internet of Things, characterized in that: The apparatus comprises at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least part of the computer instructions to implement the method as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.
