WO2018076517A1 - 灌溉装置的控制方法和控制装置 - Google Patents

灌溉装置的控制方法和控制装置 Download PDF

Info

Publication number
WO2018076517A1
WO2018076517A1 PCT/CN2016/111607 CN2016111607W WO2018076517A1 WO 2018076517 A1 WO2018076517 A1 WO 2018076517A1 CN 2016111607 W CN2016111607 W CN 2016111607W WO 2018076517 A1 WO2018076517 A1 WO 2018076517A1
Authority
WO
WIPO (PCT)
Prior art keywords
irrigation
decision
decision model
data
irrigation device
Prior art date
Application number
PCT/CN2016/111607
Other languages
English (en)
French (fr)
Inventor
王刚
Original Assignee
深圳前海弘稼科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳前海弘稼科技有限公司 filed Critical 深圳前海弘稼科技有限公司
Publication of WO2018076517A1 publication Critical patent/WO2018076517A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
    • A01G25/00—Watering gardens, fields, sports grounds or the like
    • A01G25/16—Control of watering
    • A01G25/167—Control by humidity of the soil itself or of devices simulating soil or of the atmosphere; Soil humidity sensors

Definitions

  • the present invention relates to the field of agricultural irrigation technology, and in particular to a method of controlling an irrigation device and a control device for an irrigation device.
  • the irrigation device is started to irrigate the plants to meet the water demand of the plants.
  • management is required to regularly check the soil conditions, which is more troublesome to manage.
  • the manager needs to manually start the irrigation device for irrigation.
  • the invention is based on the above problems, and proposes a new technical solution, which can intelligently start the irrigation device for irrigation, avoiding the manual startup by the management personnel, thereby reducing the workload of the management personnel.
  • the first aspect of the present invention provides a method for controlling an irrigation device, comprising: obtaining irrigation decision data, constructing an irrigation decision model according to the irrigation decision data; acquiring current planting parameters, according to the irrigation decision model Obtaining an irrigation result that matches the current planting parameter; and determining whether to activate the irrigation device for irrigation based on the irrigation result.
  • an irrigation decision model is constructed to intelligently determine whether to start the irrigation device according to the irrigation decision model, thereby preventing the manager from regularly going to the site to check the growth of the plant, and avoiding the manager determining according to his own experience. Whether to start the irrigation device, so that the control of the irrigation device is more intelligent, reducing the workload of the manager.
  • the step of constructing the irrigation decision model according to the irrigation decision data specifically includes: converting the irrigation decision data into a data structure according to a preset rule; according to the data structure, Constructing the irrigation decision model.
  • the irrigation decision model is constructed by converting the irrigation decision data into a computer-recognizable data structure to facilitate the computer to recognize the data structure, and the irrigation decision model constructed is also computer-recognizable.
  • the irrigation decision model is constructed using a decision tree algorithm.
  • the decision tree algorithm can be used to ensure that the constructed irrigation decision model is relatively simple, and the decision tree algorithm is robust to noise data.
  • the method further comprises: controlling a water flow rate of the irrigation device when performing irrigation according to the current planting parameter.
  • the water flow rate during irrigation is controlled according to current planting parameters, for example, the current air temperature is within the first temperature range, and the soil moisture is within the first humidity range, at which time the plant's demand for water is compared. If the water is large, the current flow of the irrigation device will be relatively large. The current air temperature is in the second temperature range and the soil moisture is in the second humidity range. At this time, the plant needs less water, then the irrigation The water flow rate of the irrigation device is relatively small, thus meeting the actual needs of plants.
  • current planting parameters for example, the current air temperature is within the first temperature range, and the soil moisture is within the first humidity range, at which time the plant's demand for water is compared. If the water is large, the current flow of the irrigation device will be relatively large. The current air temperature is in the second temperature range and the soil moisture is in the second humidity range. At this time, the plant needs less water, then the irrigation The water flow rate of the irrigation device is relatively small, thus meeting the actual needs of plants.
  • the current planting parameter comprises a combination of one or more of the following: current time, weather condition, air temperature, soil moisture.
  • a second aspect of the present invention provides a control device for an irrigation device, comprising: a building unit for acquiring irrigation decision data, constructing an irrigation decision model according to the irrigation decision data; and acquiring a unit for acquiring current planting parameters, And obtaining, according to the irrigation decision model, an irrigation result matching the current planting parameter; and determining unit, configured to determine whether to start the irrigation device for irrigation according to the irrigation result.
  • an irrigation decision model is constructed to intelligently determine whether to start the irrigation device according to the irrigation decision model, thereby preventing the manager from regularly going to the site to check the growth of the plant, and avoiding the manager determining according to his own experience. Whether to start the irrigation device, from The control of the irrigation device is made more intelligent, reducing the workload of the manager.
  • the building unit includes: a converting subunit, configured to convert the irrigation decision data into a data structure according to a preset rule; and construct a subunit for constructing according to the data structure The irrigation decision model.
  • the irrigation decision model is constructed by converting the irrigation decision data into a computer-recognizable data structure to facilitate the computer to recognize the data structure, and the irrigation decision model constructed is also computer-recognizable.
  • the building unit is specifically configured to construct the irrigation decision model using a decision tree algorithm.
  • the decision tree algorithm can be used to ensure that the constructed irrigation decision model is relatively simple, and the decision tree algorithm is robust to noise data.
  • the method further includes: a control unit, configured to control water of the irrigation device during irrigation according to the current planting parameter flow.
  • the water flow rate during irrigation is controlled according to current planting parameters, for example, the current air temperature is within the first temperature range, and the soil moisture is within the first humidity range, at which time the plant's demand for water is compared. If the water is large, the current flow of the irrigation device will be relatively large. The current air temperature is in the second temperature range and the soil moisture is in the second humidity range. At this time, the plant needs less water, then the irrigation The water flow rate of the irrigation device is relatively small, thus meeting the actual needs of plants.
  • current planting parameters for example, the current air temperature is within the first temperature range, and the soil moisture is within the first humidity range, at which time the plant's demand for water is compared. If the water is large, the current flow of the irrigation device will be relatively large. The current air temperature is in the second temperature range and the soil moisture is in the second humidity range. At this time, the plant needs less water, then the irrigation The water flow rate of the irrigation device is relatively small, thus meeting the actual needs of plants.
  • the current planting parameter comprises a combination of one or more of the following: current time, weather condition, air temperature, soil moisture.
  • the irrigation device can be intelligently activated for irrigation, and the manual startup of the management personnel is avoided, thereby reducing the workload of the management personnel.
  • FIG. 1 is a flow chart showing a control method of an irrigation apparatus according to an embodiment of the present invention
  • FIG. 2 shows a schematic structure of a control device of an irrigation device according to an embodiment of the present invention.
  • FIG. 1 is a flow chart showing a control method of an irrigation apparatus according to an embodiment of the present invention.
  • a method of controlling an irrigation apparatus includes:
  • Step 102 Acquire irrigation decision data, and construct an irrigation decision model according to the irrigation decision data.
  • Step 104 Acquire current planting parameters, and obtain irrigation results that match the current planting parameters according to the irrigation decision model.
  • Step 106 Determine, according to the irrigation result, whether to start the irrigation device for irrigation.
  • the irrigation device is activated for irrigation, and if the irrigation result is not irrigation, the irrigation device is not activated.
  • an irrigation decision model is constructed to intelligently determine whether to start the irrigation device according to the irrigation decision model, thereby preventing the manager from regularly going to the site to check the growth of the plant, and avoiding the manager determining according to his own experience. Whether to start the irrigation device, so that the control of the irrigation device is more intelligent, reducing the workload of the manager.
  • the step of constructing the irrigation decision model according to the irrigation decision data specifically includes: converting the irrigation decision data into a data structure according to a preset rule; according to the data structure, Constructing the irrigation decision model.
  • the irrigation decision model is constructed by converting the irrigation decision data into a computer-recognizable data structure to facilitate the computer to recognize the data structure, and the irrigation decision model constructed is also computer-recognizable.
  • the irrigation decision data is the data input by the user according to his needs.
  • Table 1 shows irrigation decision data.
  • the setting value is 0, the cloudy setting is 1, the irrigation setting is 1, the irrigation is set to 0, the data structure is in the format, the irrigation result is 1: time 2: the weather), and the irrigation decision data is converted. Into the following data structure.
  • the current weather is fine
  • the current time is 9:35
  • the current weather and current time are converted into a computer-recognizable data structure of 1:9.35 2:0.
  • the current The weather matches the current time with an irrigation result of 1, ie irrigation.
  • the irrigation decision model is constructed using a decision tree algorithm.
  • the decision tree algorithm can be used to ensure that the constructed irrigation decision model is relatively simple, and the decision tree algorithm is robust to noise data.
  • the decision tree algorithm is a method of approximating the value of discrete functions. It is a typical classification method. First, the data is processed. The inductive algorithm is used to generate readable rules and decision trees, and then the new data is analyzed by decision. The upper decision tree is the process of classifying data through a series of rules. Decision tree algorithms include ID3 algorithm, ID5 algorithm, and CART algorithm.
  • the method further comprises: controlling a water flow rate of the irrigation device when performing irrigation according to the current planting parameter.
  • the water flow rate during irrigation is controlled according to current planting parameters, for example, the current air temperature is within the first temperature range, and the soil moisture is within the first humidity range, at which time the plant's demand for water is compared. If the water is large, the current flow of the irrigation device will be relatively large. The current air temperature is in the second temperature range and the soil moisture is in the second humidity range. At this time, the plant needs less water, then the irrigation The water flow rate of the irrigation device is relatively small, thus meeting the actual needs of plants.
  • current planting parameters for example, the current air temperature is within the first temperature range, and the soil moisture is within the first humidity range, at which time the plant's demand for water is compared. If the water is large, the current flow of the irrigation device will be relatively large. The current air temperature is in the second temperature range and the soil moisture is in the second humidity range. At this time, the plant needs less water, then the irrigation The water flow rate of the irrigation device is relatively small, thus meeting the actual needs of plants.
  • the current planting parameter includes one of the following or A variety of combinations: current time, weather conditions, air temperature, soil moisture.
  • the irrigation decision model If in the irrigation decision model, the weather is fine at 9:00 in the morning, the air temperature is greater than 25 ° C, and the soil moisture is less than 10%.
  • the irrigation conditions corresponding to the above irrigation conditions are for irrigation, and the current planting parameters meet the above irrigation. When conditions are met, it is determined that irrigation is performed and the irrigation device is automatically activated for irrigation.
  • Fig. 2 shows a schematic structural view of a control device of an irrigation device according to an embodiment of the present invention.
  • a control apparatus 200 of an irrigation apparatus includes a construction unit 202, an acquisition unit 204, and a determination unit 206.
  • the construction unit 202 is configured to acquire irrigation decision data, and construct an irrigation decision model according to the irrigation decision data; the obtaining unit 204 is configured to acquire current planting parameters, and obtain, according to the irrigation decision model, a match with the current planting parameter.
  • the irrigation result; determining unit 206 is configured to determine whether to start the irrigation device for irrigation according to the irrigation result.
  • an irrigation decision model is constructed to intelligently determine whether to start the irrigation device according to the irrigation decision model, thereby preventing the manager from regularly going to the site to check the growth of the plant, and avoiding the manager determining according to his own experience. Whether to start the irrigation device, so that the control of the irrigation device is more intelligent, reducing the workload of the manager.
  • the construction unit 202 includes: a conversion subunit 2022, configured to convert the irrigation decision data into a data structure according to a preset rule; and a construction subunit 2024, configured to use the data according to the data Structure, constructing the irrigation decision model.
  • the irrigation decision model is constructed by converting the irrigation decision data into a computer-recognizable data structure to facilitate the computer to recognize the data structure, and the irrigation decision model constructed is also computer-recognizable.
  • the constructing unit 202 is specifically configured to construct the irrigation decision model using a decision tree algorithm.
  • the decision tree algorithm can be used to ensure that the constructed irrigation decision model is relatively simple, and the decision tree algorithm is robust to noise data.
  • the method further includes: a control unit 208, configured to control the current planting parameter according to the The water flow rate of the irrigation device when it is being irrigated.
  • the water flow rate during irrigation is controlled according to current planting parameters, for example, the current air temperature is within the first temperature range, and the soil moisture is within the first humidity range, at which time the plant's demand for water is compared. If the water is large, the current flow of the irrigation device will be relatively large. The current air temperature is in the second temperature range and the soil moisture is in the second humidity range. At this time, the plant needs less water, then the irrigation The water flow rate of the irrigation device is relatively small, thus meeting the actual needs of plants.
  • current planting parameters for example, the current air temperature is within the first temperature range, and the soil moisture is within the first humidity range, at which time the plant's demand for water is compared. If the water is large, the current flow of the irrigation device will be relatively large. The current air temperature is in the second temperature range and the soil moisture is in the second humidity range. At this time, the plant needs less water, then the irrigation The water flow rate of the irrigation device is relatively small, thus meeting the actual needs of plants.
  • the current planting parameter comprises a combination of one or more of the following: current time, weather condition, air temperature, soil moisture.
  • the irrigation decision model For example, in the irrigation decision model, at 9:00 in the morning, the weather is fine, the air temperature is greater than 25 ° C, and the soil moisture is less than 10%.
  • the irrigation conditions corresponding to the above irrigation conditions are for irrigation, and the current planting parameters satisfy the above.
  • it is determined to irrigate and automatically start the irrigation device for irrigation.
  • a server in accordance with one embodiment of the present invention includes a processor, a memory, and a communication bus.
  • the processor may be a general-purpose processor, such as a central processing unit (CPU), or may be a digital signal processor (DSP), an application specific integrated circuit (ASIC), or One or more integrated circuits configured to implement embodiments of the present invention.
  • the memory may include a volatile memory (Volatile Memory), such as a random access memory (RAM); the memory may also include a non-volatile memory (Non-Volatile Memory), such as a read-only memory (Read-Only Memory). , ROM), Flash Memory, Hard Disk Drive (HDD), or Solid-State Drive (SSD); the memory may also include a combination of the above types of memories.
  • the communication bus is used to implement connection communication between the processor and the memory.
  • the communication bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus.
  • ISA Industry Standard Architecture
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the communication bus can be divided into an address bus, a data bus, a control bus, and the like.
  • the processor is used to call the program code stored in the memory, and performs the following operations:
  • Obtaining irrigation decision data constructing an irrigation decision model according to the irrigation decision data; obtaining current planting parameters, obtaining irrigation results matching the current planting parameters according to the irrigation decision model; determining whether to start according to the irrigation result Irrigation device for irrigation.
  • the processor is specifically configured to convert the irrigation decision data into a data structure according to a preset rule; and construct the irrigation decision model according to the data structure.
  • the processor constructs the irrigation decision model using a decision tree algorithm.
  • the processor is further configured to control the water flow of the irrigation device when performing irrigation according to the current planting parameter.
  • the current planting parameter comprises a combination of one or more of the following: current time, weather conditions, air temperature, soil moisture.
  • the irrigation device can be intelligently started for irrigation, and the manual startup of the management personnel is avoided, so that the irrigation of the irrigation device is more intelligent, thereby reducing the management personnel.
  • the amount of work is described in detail above with reference to the accompanying drawings.

Abstract

本发明提出了一种灌溉装置的控制方法和控制装置，其中，所述灌溉装置的控制方法包括：获取灌溉决策数据，根据所述灌溉决策数据，构建灌溉决策模型；获取当前种植参数，根据所述灌溉决策模型，获取与所述当前种植参数匹配的灌溉结果；根据所述灌溉结果，确定是否启动灌溉装置来进行灌溉。通过本发明的技术方案，可以智能地启动灌溉装置进行灌溉，避免了管理人员手动启动，从而减轻了管理人员的工作量。

Description

灌溉装置的控制方法和控制装置 技术领域
本发明涉及农业灌溉技术领域，具体而言，涉及一种灌溉装置的控制方法和一种灌溉装置的控制装置。
背景技术
目前，为了保证植物能够健康生长，当土壤比较干或者湿度比较低时，启动灌溉装置来对植物进行灌溉，满足植物对水分的需求。但是需要管理人员定期查看土壤情况，这样的管理就比较麻烦。而且当管理人员根据自己的工作经验确定土壤比较干时，需要管理人员手动启动灌溉装置来进行灌溉。
因此，如何智能地启动灌溉装置进行灌溉，避免用户手动启动，从而减轻管理人员的工作量成为亟待解决的技术问题。
发明内容
本发明正是基于上述问题，提出了一种新的技术方案，可以智能地启动灌溉装置进行灌溉，避免了管理人员手动启动，从而减轻了管理人员的工作量。
有鉴于此，本发明的第一方面提出了一种灌溉装置的控制方法，包括：获取灌溉决策数据，根据所述灌溉决策数据，构建灌溉决策模型；获取当前种植参数，根据所述灌溉决策模型，获取与所述当前种植参数匹配的灌溉结果；根据所述灌溉结果，确定是否启动灌溉装置来进行灌溉。
在该技术方案中，通过构建灌溉决策模型，以根据该灌溉决策模型智能地确定是否启动灌溉装置，避免了管理人员定期去现场查看植物的生长情况，以及避免了管理人员根据自己的经验来确定是否启动灌溉装置，从而使得对灌溉装置的控制更加智能化，减少了管理人员的工作量。
在上述技术方案中，优选地，所述根据所述灌溉决策数据，构建灌溉决策模型的步骤，具体包括：按照预设规则，将所述灌溉决策数据转换成数据结构；根据所述数据结构，构建所述灌溉决策模型。
在该技术方案中，通过将灌溉决策数据转换成计算机能够识别的数据结构，以方便计算机识别该数据结构来构建灌溉决策模型，而且构建出的该灌溉决策模型也是计算机能够识别的。
在上述任一技术方案中，优选地，使用决策树算法构建所述灌溉决策模型。
在该技术方案中，使用决策树算法可以保证构建的灌溉决策模型比较简单，而且决策树算法对于噪声数据具有很好的健壮性。
在上述任一技术方案中，优选地，在启动所述灌溉装置来进行灌溉的情况下，还包括：根据所述当前种植参数，控制所述灌溉装置在进行灌溉时的水流量。
在该技术方案中，根据当前种植参数控制灌溉时的水流量，例如，当前的空气温度在第一温度范围内、且土壤湿度在第一湿度范围内，此时植物对于水的需求量就比较大，则灌溉装置此次灌溉的水流量就比较大，当前的空气温度在第二温度范围内、且土壤湿度在第二湿度范围内，此时植物对于水的需求量就比较小，则灌溉装置此次灌溉的水流量就比较小，从而满足了植物的实际需求。
在上述任一技术方案中，优选地，所述当前种植参数包括以下之一或多种的组合：当前时间、天气状况、空气温度、土壤湿度。
本发明的第二方面提出了一种灌溉装置的控制装置，包括：构建单元，用于获取灌溉决策数据，根据所述灌溉决策数据，构建灌溉决策模型；获取单元，用于获取当前种植参数，根据所述灌溉决策模型，获取与所述当前种植参数匹配的灌溉结果；确定单元，用于根据所述灌溉结果，确定是否启动灌溉装置来进行灌溉。
在该技术方案中，通过构建灌溉决策模型，以根据该灌溉决策模型智能地确定是否启动灌溉装置，避免了管理人员定期去现场查看植物的生长情况，以及避免了管理人员根据自己的经验来确定是否启动灌溉装置，从 而使得对灌溉装置的控制更加智能化，减少了管理人员的工作量。
在上述技术方案中，优选地，所述构建单元包括：转换子单元，用于按照预设规则，将所述灌溉决策数据转换成数据结构；构建子单元，用于根据所述数据结构，构建所述灌溉决策模型。
在该技术方案中，通过将灌溉决策数据转换成计算机能够识别的数据结构，以方便计算机识别该数据结构来构建灌溉决策模型，而且构建出的该灌溉决策模型也是计算机能够识别的。
在上述任一技术方案中，优选地，所述构建单元具体用于，使用决策树算法构建所述灌溉决策模型。
在该技术方案中，使用决策树算法可以保证构建的灌溉决策模型比较简单，而且决策树算法对于噪声数据具有很好的健壮性。
在上述任一技术方案中，优选地，在启动所述灌溉装置来进行灌溉的情况下，还包括：控制单元，用于根据所述当前种植参数，控制所述灌溉装置在进行灌溉时的水流量。
在该技术方案中，根据当前种植参数控制灌溉时的水流量，例如，当前的空气温度在第一温度范围内、且土壤湿度在第一湿度范围内，此时植物对于水的需求量就比较大，则灌溉装置此次灌溉的水流量就比较大，当前的空气温度在第二温度范围内、且土壤湿度在第二湿度范围内，此时植物对于水的需求量就比较小，则灌溉装置此次灌溉的水流量就比较小，从而满足了植物的实际需求。
在上述任一技术方案中，优选地，所述当前种植参数包括以下之一或多种的组合：当前时间、天气状况、空气温度、土壤湿度。
通过本发明的技术方案，可以智能地启动灌溉装置进行灌溉，避免了管理人员手动启动，从而减轻了管理人员的工作量。
附图说明
图1示出了根据本发明的实施例的灌溉装置的控制方法的流程示意图；
图2示出了根据本发明的实施例的灌溉装置的控制装置的结构示意 图。
具体实施方式
为了可以更清楚地理解本发明的上述目的、特征和优点，下面结合附图和具体实施方式对本发明进行进一步的详细描述。需要说明的是，在不冲突的情况下，本申请的实施例及实施例中的特征可以相互组合。
在下面的描述中阐述了很多具体细节以便于充分理解本发明，但是，本发明还可以采用其他不同于在此描述的其他方式来实施，因此，本发明的保护范围并不受下面公开的具体实施例的限制。
图1示出了根据本发明的实施例的灌溉装置的控制方法的流程示意图。
如图1所示，根据本发明的实施例的灌溉装置的控制方法，包括：
步骤102，获取灌溉决策数据，根据所述灌溉决策数据，构建灌溉决策模型。
步骤104，获取当前种植参数，根据所述灌溉决策模型，获取与所述当前种植参数匹配的灌溉结果。
步骤106，根据所述灌溉结果，确定是否启动灌溉装置来进行灌溉。
例如，若灌溉结果为进行灌溉，则启动灌溉装置来进行灌溉，若灌溉结果为不进行灌溉，则不启动灌溉装置。
在该技术方案中，通过构建灌溉决策模型，以根据该灌溉决策模型智能地确定是否启动灌溉装置，避免了管理人员定期去现场查看植物的生长情况，以及避免了管理人员根据自己的经验来确定是否启动灌溉装置，从而使得对灌溉装置的控制更加智能化，减少了管理人员的工作量。
在上述技术方案中，优选地，所述根据所述灌溉决策数据，构建灌溉决策模型的步骤，具体包括：按照预设规则，将所述灌溉决策数据转换成数据结构；根据所述数据结构，构建所述灌溉决策模型。
在该技术方案中，通过将灌溉决策数据转换成计算机能够识别的数据结构，以方便计算机识别该数据结构来构建灌溉决策模型，而且构建出的该灌溉决策模型也是计算机能够识别的。
其中，灌溉决策数据是用户根据其需求输入的数据。例如，表1示出了灌溉决策数据。
表1
时间 天气 是否灌溉(灌溉结果)
9:00 天晴 是
9:35 天晴 是
9:50 天晴 否
10:00 天晴 否
10:10 天晴 否
10:25 天晴 否
10:40 天晴 是
9:00 多云 是
9:35 多云 否
9:50 多云 是
10:00 多云 否
10:10 多云 否
按照预设规则(天晴设置值为0，多云设置值为1，灌溉设置为1，不灌溉设置为0，数据结构的格式为，灌溉结果1：时间2：天气)，将灌溉决策数据转换成以下的数据结构。
1  1:9.00   2:0
1  1:9.35   2:0
0  1:9.50   2:0
0  1:10.0   2:0
0  1:10.10  2:0
0  1:10.25  2:0
1  1:10.40  2:0
1  1:9.0    2:1
0  1:9.35   2:1
1  1:9.50   2:1
0  1:10.0   2:1
0  1:10.10  2:1
根据以上的数据结构构建出如下的灌溉决策模型。
id＝1,isLeaf＝false,predict＝0.0(prob＝0.5833333333333334),impurity＝0.9798687566511527,split＝Some(Feature＝0,threshold＝9.35,featureType＝Continuous,categories＝List()),stats＝Some(gain＝0.16859063219201986,impurity＝0.9798687566511527,left impurity＝0.8112781244591328,right impurity＝0.8112781244591328)
例如，当前天气为天晴，当前时间为9:35，此时将当前天气和当前时间转换成计算机能够识别的数据结构为1:9.35 2:0，从以上的灌溉决策模型可知，与该当前天气和当前时间匹配的灌溉结果为1，即进行灌溉。
在上述任一技术方案中，优选地，使用决策树算法构建所述灌溉决策模型。
在该技术方案中，使用决策树算法可以保证构建的灌溉决策模型比较简单，而且决策树算法对于噪声数据具有很好的健壮性。
决策树算法是一种逼近离散函数值的方法，它是一种典型的分类方法，首先对数据进行处理，利用归纳算法生成可读的规则和决策树，然后利用决策对新数据进行分析，本质上决策树是通过一系列规则对数据进行分类的过程。决策树算法包括有ID3算法、ID5算法、CART算法。
在上述任一技术方案中，优选地，在启动所述灌溉装置来进行灌溉的情况下，还包括：根据所述当前种植参数，控制所述灌溉装置在进行灌溉时的水流量。
在该技术方案中，根据当前种植参数控制灌溉时的水流量，例如，当前的空气温度在第一温度范围内、且土壤湿度在第一湿度范围内，此时植物对于水的需求量就比较大，则灌溉装置此次灌溉的水流量就比较大，当前的空气温度在第二温度范围内、且土壤湿度在第二湿度范围内，此时植物对于水的需求量就比较小，则灌溉装置此次灌溉的水流量就比较小，从而满足了植物的实际需求。
在上述任一技术方案中，优选地，所述当前种植参数包括以下之一或 多种的组合：当前时间、天气状况、空气温度、土壤湿度。
若在灌溉决策模型中，早上9:00，天气晴朗，空气温度为大于25℃，土壤湿度为小于10％，以上的灌溉条件对应的灌溉结果为进行灌溉，则在当前种植参数满足以上的灌溉条件时，确定进行灌溉，并自动启动灌溉装置进行灌溉。
图2示出了根据本发明的实施例的灌溉装置的控制装置的结构示意图。
如图2所示，根据本发明的实施例的灌溉装置的控制装置200，包括：构建单元202、获取单元204和确定单元206。
构建单元202，用于获取灌溉决策数据，根据所述灌溉决策数据，构建灌溉决策模型；获取单元204，用于获取当前种植参数，根据所述灌溉决策模型，获取与所述当前种植参数匹配的灌溉结果；确定单元206，用于根据所述灌溉结果，确定是否启动灌溉装置来进行灌溉。
在该技术方案中，通过构建灌溉决策模型，以根据该灌溉决策模型智能地确定是否启动灌溉装置，避免了管理人员定期去现场查看植物的生长情况，以及避免了管理人员根据自己的经验来确定是否启动灌溉装置，从而使得对灌溉装置的控制更加智能化，减少了管理人员的工作量。
在上述技术方案中，优选地，所述构建单元202包括：转换子单元2022，用于按照预设规则，将所述灌溉决策数据转换成数据结构；构建子单元2024，用于根据所述数据结构，构建所述灌溉决策模型。
在该技术方案中，通过将灌溉决策数据转换成计算机能够识别的数据结构，以方便计算机识别该数据结构来构建灌溉决策模型，而且构建出的该灌溉决策模型也是计算机能够识别的。
在上述任一技术方案中，优选地，所述构建单元202具体用于，使用决策树算法构建所述灌溉决策模型。
在该技术方案中，使用决策树算法可以保证构建的灌溉决策模型比较简单，而且决策树算法对于噪声数据具有很好的健壮性。
在上述任一技术方案中，优选地，在启动所述灌溉装置来进行灌溉的情况下，还包括：控制单元208，用于根据所述当前种植参数，控制所述 灌溉装置在进行灌溉时的水流量。
在该技术方案中，根据当前种植参数控制灌溉时的水流量，例如，当前的空气温度在第一温度范围内、且土壤湿度在第一湿度范围内，此时植物对于水的需求量就比较大，则灌溉装置此次灌溉的水流量就比较大，当前的空气温度在第二温度范围内、且土壤湿度在第二湿度范围内，此时植物对于水的需求量就比较小，则灌溉装置此次灌溉的水流量就比较小，从而满足了植物的实际需求。
在上述任一技术方案中，优选地，所述当前种植参数包括以下之一或多种的组合：当前时间、天气状况、空气温度、土壤湿度。
例如，在灌溉决策模型中，早上9:00，天气晴朗，空气温度为大于25℃，土壤湿度为小于10％，以上的灌溉条件对应的灌溉结果为进行灌溉，则在当前种植参数满足以上的灌溉条件时，确定进行灌溉，并自动启动灌溉装置进行灌溉。
根据本发明的一个实施例的服务器，包括处理器、存储器和通信总线。
处理器可以是通用处理器，例如中央处理器(Central Processing Unit，CPU)，还可以是数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)，或者是被配置成实施本发明实施例的一个或多个集成电路。存储器，用于存储程序代码，并将该程序代码传输给处理器。存储器可以包括易失性存储器(Volatile Memory)，例如随机存取存储器(Random Access Memory，RAM)；存储器也可以包括非易失性存储器(Non-Volatile Memory)，例如只读存储器(Read-Only Memory，ROM)、快闪存储器(Flash Memory)、硬盘(Hard Disk Drive，HDD)或固态硬盘(Solid-State Drive，SSD)；存储器还可以包括上述种类的存储器的组合。通信总线用于实现处理器和存储器之间的连接通信。通信总线可以是工业标准体系结构(Industry Standard Architecture，ISA)总线、外部设备互连(Peripheral Component Interconnect，PCI)总线或扩展标准体系结构(Extended Industry Standard Architecture，EISA)总线等。该通信总线可以分为地址总线、数据总线、控制总线等。
其中，处理器用于调用存储器存储的程序代码，执行如下操作：
获取灌溉决策数据，根据所述灌溉决策数据，构建灌溉决策模型；获取当前种植参数，根据所述灌溉决策模型，获取与所述当前种植参数匹配的灌溉结果；根据所述灌溉结果，确定是否启动灌溉装置来进行灌溉。
优选地，处理器具体用于，按照预设规则，将所述灌溉决策数据转换成数据结构；根据所述数据结构，构建所述灌溉决策模型。
优选地，处理器使用决策树算法构建所述灌溉决策模型。
优选地，在启动所述灌溉装置来进行灌溉的情况下，处理器还用于，根据所述当前种植参数，控制所述灌溉装置在进行灌溉时的水流量。
优选地，所述当前种植参数包括以下之一或多种的组合：当前时间、天气状况、空气温度、土壤湿度。
以上结合附图详细说明了本发明的技术方案，通过本发明的技术方案，可以智能地启动灌溉装置进行灌溉，避免了管理人员手动启动，使得灌溉装置的灌溉更加智能化，从而减轻了管理人员的工作量。
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种灌溉装置的控制方法，其特征在于，包括：
    获取灌溉决策数据，根据所述灌溉决策数据，构建灌溉决策模型；
    获取当前种植参数，根据所述灌溉决策模型，获取与所述当前种植参数匹配的灌溉结果；
    根据所述灌溉结果，确定是否启动灌溉装置来进行灌溉。
  2. 根据权利要求1所述的灌溉装置的控制方法，其特征在于，所述根据所述灌溉决策数据，构建灌溉决策模型的步骤，具体包括：
    按照预设规则，将所述灌溉决策数据转换成数据结构；
    根据所述数据结构，构建所述灌溉决策模型。
  3. 根据权利要求1所述的灌溉装置的控制方法，其特征在于，
    使用决策树算法构建所述灌溉决策模型。
  4. 根据权利要求1至3中任一项所述的灌溉装置的控制方法，其特征在于，在启动所述灌溉装置来进行灌溉的情况下，还包括：
    根据所述当前种植参数，控制所述灌溉装置在进行灌溉时的水流量。
  5. 根据权利要求1至3中任一项所述的灌溉装置的控制方法，其特征在于，
    所述当前种植参数包括以下之一或多种的组合：当前时间、天气状况、空气温度、土壤湿度。
  6. 一种灌溉装置的控制装置，其特征在于，包括：
    构建单元，用于获取灌溉决策数据，根据所述灌溉决策数据，构建灌溉决策模型；
    获取单元，用于获取当前种植参数，根据所述灌溉决策模型，获取与所述当前种植参数匹配的灌溉结果；
    确定单元，用于根据所述灌溉结果，确定是否启动灌溉装置来进行灌溉。
  7. 根据权利要求6所述的灌溉装置的控制装置，其特征在于，所述构建单元包括：
    转换子单元，用于按照预设规则，将所述灌溉决策数据转换成数据结构；
    构建子单元，用于根据所述数据结构，构建所述灌溉决策模型。
  8. 根据权利要求6所述的灌溉装置的控制装置，其特征在于，
    所述构建单元具体用于，使用决策树算法构建所述灌溉决策模型。
  9. 根据权利要求6至8中任一项所述的灌溉装置的控制装置，其特征在于，在启动所述灌溉装置来进行灌溉的情况下，还包括：
    控制单元，用于根据所述当前种植参数，控制所述灌溉装置在进行灌溉时的水流量。
  10. 根据权利要求6至8中任一项所述的灌溉装置的控制装置，其特征在于，
    所述当前种植参数包括以下之一或多种的组合：当前时间、天气状况、空气温度、土壤湿度。
PCT/CN2016/111607 2016-10-28 2016-12-23 灌溉装置的控制方法和控制装置 WO2018076517A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610974304.7 2016-10-28
CN201610974304.7A CN106489687A (zh) 2016-10-28 2016-10-28 灌溉装置的控制方法和控制装置

Publications (1)

Publication Number Publication Date
WO2018076517A1 true WO2018076517A1 (zh) 2018-05-03

Family

ID=58323147

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/111607 WO2018076517A1 (zh) 2016-10-28 2016-12-23 灌溉装置的控制方法和控制装置

Country Status (2)

Country Link
CN (1) CN106489687A (zh)
WO (1) WO2018076517A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111369093A (zh) * 2018-12-26 2020-07-03 天云融创数据科技（北京）有限公司 基于机器学习的灌溉方法和装置

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107896949A (zh) * 2017-11-20 2018-04-13 深圳春沐源控股有限公司 一种水肥灌溉自动控制方法及系统
CN109526701B (zh) * 2019-01-23 2021-02-19 中国联合网络通信集团有限公司 滴灌控制方法及装置
CN112352523B (zh) * 2020-09-09 2022-10-04 安徽农业大学 一种基于智能决策的茶园水肥灌溉控制方法和系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110015793A1 (en) * 2009-07-17 2011-01-20 Rain Bird Corporation Variable Initialization Time in the Charging of Energy Reserves in an Irrigation Control System
CN104460582A (zh) * 2014-09-29 2015-03-25 贵州省水利科学研究院 一种基于模糊控制的物联网智能灌溉施肥控制方法及系统
CN104866970A (zh) * 2015-05-26 2015-08-26 徐吉祥 智能种植管理方法和智能种植设备
CN105638392A (zh) * 2015-12-29 2016-06-08 刘震 一种农业微芯片控制灌溉决策合理灌溉装置
CN105684838A (zh) * 2015-10-28 2016-06-22 广西慧云信息技术有限公司 一种根据环境参数对植物进行轮流灌溉的系统和方法

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120036091A1 (en) * 2006-06-12 2012-02-09 Cook Kenneth W System and method for automated, range-based irrigation
CN101953287B (zh) * 2010-08-25 2012-11-21 中国农业大学 基于多数据的作物需水检测系统
CN102487788A (zh) * 2011-12-15 2012-06-13 南京成风大气信息技术有限公司 基于气象信息服务的智能喷灌排放控制系统
CN104429829A (zh) * 2013-09-15 2015-03-25 南京大五教育科技有限公司 稻田智能灌溉系统
CN103838144B (zh) * 2013-12-30 2016-09-21 广西卡西亚科技有限公司 基于物联网土壤分析的甘蔗精细种植滴灌建模控制方法
CN104472314A (zh) * 2015-01-12 2015-04-01 中央民族大学 一种灌溉方法及装置及系统
CN104904569B (zh) * 2015-05-25 2018-02-13 华南农业大学 一种基于动态含水量估计的智能灌溉调控系统及方法
CN105389663B (zh) * 2015-11-20 2020-10-09 天津市农业技术推广站 一种农田灌溉智能决策系统和方法
CN105892287B (zh) * 2016-05-09 2018-12-18 河海大学常州校区 基于模糊判决的农作物灌溉策略及决策系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110015793A1 (en) * 2009-07-17 2011-01-20 Rain Bird Corporation Variable Initialization Time in the Charging of Energy Reserves in an Irrigation Control System
CN104460582A (zh) * 2014-09-29 2015-03-25 贵州省水利科学研究院 一种基于模糊控制的物联网智能灌溉施肥控制方法及系统
CN104866970A (zh) * 2015-05-26 2015-08-26 徐吉祥 智能种植管理方法和智能种植设备
CN105684838A (zh) * 2015-10-28 2016-06-22 广西慧云信息技术有限公司 一种根据环境参数对植物进行轮流灌溉的系统和方法
CN105638392A (zh) * 2015-12-29 2016-06-08 刘震 一种农业微芯片控制灌溉决策合理灌溉装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111369093A (zh) * 2018-12-26 2020-07-03 天云融创数据科技（北京）有限公司 基于机器学习的灌溉方法和装置
CN111369093B (zh) * 2018-12-26 2023-09-29 天云融创数据科技（北京）有限公司 基于机器学习的灌溉方法和装置

Also Published As

Publication number Publication date
CN106489687A (zh) 2017-03-15

Similar Documents

Publication Publication Date Title
WO2018076517A1 (zh) 灌溉装置的控制方法和控制装置
CN109543295B (zh) 数值天气预报的气象要素数据处理方法及装置
US20180121821A1 (en) Methods and systems of forecasting the drying of an agricultural crop
Saputra et al. System design and implementation automation system of expert system on hydroponics nutrients control using forward chaining method
WO2017106962A1 (en) System and method for real-time water management
WO2019227369A1 (zh) 植物生长智能控制系统、方法、电子终端及可读存储介质
CN110909679A (zh) 冬小麦历史种植区的休耕轮作信息遥感识别方法及系统
WO2016121432A1 (ja) 技能承継支援装置、技能承継支援方法、及びコンピュータ読み取り可能な記録媒体
CN113342098A (zh) 一种多用途养殖场环境智能控制方法及系统
WO2020186875A1 (zh) 用于农作物的实际耗水量处理方法及装置、服务器
CN112001242A (zh) 一种智能园艺管理方法和装置
CN110989703A (zh) 调节香薰浓度的方法、装置、电子设备和计算机可读介质
AU2017100206A4 (en) Quantitative water irrigation method and apparatus
Garg et al. A proposed method to determine yield response factors of different crops under deficit irrigation using inverse formulation approach
LU102457B1 (en) Irrigation method, device, system and readable storage medium of crop
CN116990490B (zh) 一种基于物联网的土壤水分动态监测系统及方法
JP6612503B2 (ja) 潅水装置及び潅水システム
WO2019085429A1 (zh) 种植任务生成方法、装置、电子设备及存储介质
CN112836903A (zh) 病虫害风险预测方法
CN111061323A (zh) 一种温室大棚的温湿度智能控制系统
CN108171417B (zh) 种植任务调整方法、电子设备及存储介质
Pawar et al. Weekly rainfall variability and probability analysis for Solapur in respect of crop planning
JPWO2018151196A1 (ja) 作物生育の推定装置、作物生育の推定方法、プログラム、および記録媒体
CN114938770B (zh) 一种灌溉控制方法、装置、系统、设备及介质
CN106790418B (zh) 一种反馈方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16920202

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 26.09.2019)

122 Ep: pct application non-entry in european phase

Ref document number: 16920202

Country of ref document: EP

Kind code of ref document: A1