WO2020140958A1 - 农机作业分析模型生成方法、模型、分析方法及管理方法 - Google Patents
农机作业分析模型生成方法、模型、分析方法及管理方法 Download PDFInfo
- Publication number
- WO2020140958A1 WO2020140958A1 PCT/CN2020/070174 CN2020070174W WO2020140958A1 WO 2020140958 A1 WO2020140958 A1 WO 2020140958A1 CN 2020070174 W CN2020070174 W CN 2020070174W WO 2020140958 A1 WO2020140958 A1 WO 2020140958A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- agricultural machinery
- type
- plant variety
- machinery operation
- plant
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000004458 analytical method Methods 0.000 title claims abstract description 54
- 238000007726 management method Methods 0.000 title claims abstract description 9
- 241000196324 Embryophyta Species 0.000 claims abstract description 110
- 230000012010 growth Effects 0.000 claims abstract description 51
- 238000010801 machine learning Methods 0.000 claims abstract description 5
- 238000002360 preparation method Methods 0.000 claims description 32
- 230000004720 fertilization Effects 0.000 claims description 31
- 238000009331 sowing Methods 0.000 claims description 31
- 238000003973 irrigation Methods 0.000 claims description 22
- 230000002262 irrigation Effects 0.000 claims description 22
- 239000003337 fertilizer Substances 0.000 claims description 18
- 238000003306 harvesting Methods 0.000 claims description 16
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 14
- 239000003814 drug Substances 0.000 claims description 12
- 239000002689 soil Substances 0.000 claims description 6
- 238000005507 spraying Methods 0.000 claims description 6
- 230000008635 plant growth Effects 0.000 claims description 5
- 230000035558 fertility Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 230000035606 childbirth Effects 0.000 claims description 3
- 238000010899 nucleation Methods 0.000 claims description 3
- 235000021048 nutrient requirements Nutrition 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000003971 tillage Methods 0.000 description 2
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Definitions
- the invention relates to the field of agricultural intelligence, in particular to a method, model, analysis method and management method for agricultural machinery operation analysis models.
- agricultural machinery operation services as agricultural services include land preparation (including flat land, overturned land, rotary tillage), sowing, fertilization, plant protection, irrigation and harvesting.
- Agricultural machinery operation services also tend to be more professional.
- the invention provides a generation method, a model, an analysis method and a management method of an agricultural machinery operation analysis model, which has the characteristics of facilitating the realization of intelligent agricultural machinery operation.
- the method includes,
- Collect plant variety planting area data including but not limited to plant growth habits in the planting area and the type of agricultural machinery required throughout the growing period;
- the plant varieties include more than two types of varieties; each type of plant variety includes at least one planting area data;
- the growth habit includes the growth characteristics corresponding to each growth stage; the growth characteristics include, but are not limited to, one or more of the required water requirements, nutrient requirements, and growth height parameters;
- the whole growth period includes the period corresponding to each growth stage
- the types of agricultural machinery operations include but are not limited to one or more of land preparation, seeding, fertilization, plant protection, irrigation and harvesting;
- machine learning is performed to generate a plant variety full growth period agricultural machinery operation analysis model; the farm machine operation analysis model can obtain the current possible needs based on the plant variety, planting area, and the current growth period Types of agricultural machinery operations.
- the collected plant variety planting area data also includes the best sowing time and/or local meteorological conditions.
- the method also includes obtaining the current status of soil fertility based on plant growth characteristics and historical fertilization.
- the method further includes that, when the required type of agricultural machinery operation is fertilization, a specific fertilization method and fertilizer variety are obtained according to the current growing period.
- the method further includes that, when the type of agricultural machinery required is land preparation, the depth required for land preparation is obtained according to the plant variety.
- the method further includes that, when the required type of agricultural machinery operation is sowing, the type of agricultural machinery and the sowing method to be adopted are obtained according to plant varieties.
- the method further includes that, when the required type of agricultural machinery operation is harvesting, the type of agricultural machinery and the harvesting method to be adopted are obtained according to plant varieties.
- the method further includes, when the required type of agricultural machinery operation is irrigation, a specific embodiment of irrigation is given according to the water demand of the plant variety during the current growth period and/or the local meteorological conditions within the set time period.
- the method further includes:
- the agricultural machinery type and the corresponding operation index are obtained according to the plant variety, and the operation index includes the depth of the required land preparation and the driving speed of the vehicle;
- the operation index includes the spacing between the planting rows, the average amount of seed used per acre and the driving speed of the vehicle; For fertilization, the type of agricultural machinery and the corresponding operation index are obtained according to the current growing period.
- the operation index includes the rate of fertilizer spreading, the average amount of fertilizer used per acre of land, and the speed of vehicles;
- the type of agricultural machinery and the corresponding operation index are obtained according to the plant variety, and the operation index includes the spraying rate of the medicament, the average amount of medicine per acre and the driving speed of the vehicle;
- the agricultural machinery type and the corresponding operation index are obtained according to the plant variety, and the operation index includes the vehicle running speed.
- An agricultural machinery operation analysis model which is generated using the above analysis model generation method, is characterized in that it includes,
- Parameter input interface including,
- Plant variety input and/or selection unit to input and/or select the plant variety to be analyzed currently
- Planting area input and/or selection unit to input and/or select the planting area to be analyzed currently;
- the acquisition unit during childbirth according to the input and/or selection, or according to the current date;
- Parameter output interface including,
- the agricultural machinery operation type output unit outputs the agricultural machinery operation type that may be currently needed.
- the agricultural machinery operation plan is a fertilization agricultural machinery operation plan
- specific fertilization methods and fertilizer varieties are given.
- the depth required for land preparation is given.
- the agricultural machinery operation plan is the sowing agricultural machinery operation plan
- the agricultural machinery type and sowing method to be adopted are given.
- the type of agricultural machinery and the harvesting method to be used are given.
- the type of agricultural machinery and the corresponding operation index are obtained according to the plant species, and the operation index includes the depth of the land preparation and the driving speed of the vehicle;
- the operation index includes the row spacing of the planting plant, the average amount of seed used per acre and the driving speed of the vehicle;
- the operation index includes the rate of fertilizer spreading, the average cost per acre of land, and the driving speed of vehicles;
- the operation index includes the spraying rate of the medicament, the average amount of medicine per acre and the driving speed of the vehicle;
- the agricultural machinery operation plan is plant protection
- the agricultural machinery type and the corresponding operation index are obtained according to the plant variety, and the operation index includes the vehicle driving speed.
- the method includes,
- the method also includes setting the local meteorological conditions within the time period, and combining with the water demand of the plant variety during the current growth period, and giving a specific implementation of irrigation.
- the method includes,
- the technical solution of the present invention can quickly obtain the types of agricultural machinery operations required by plant varieties during each growth period through the model, which is conducive to the intelligent development of agriculture and facilitates the realization of intelligent agricultural machinery operations.
- FIG. 1 is a schematic flowchart of a method for generating an agricultural machinery operation analysis model according to the present invention.
- FIG. 1 is a schematic flowchart of a method for generating an analysis model of agricultural machinery operations according to the present invention. As shown in FIG. 1, a method for generating an analysis model of agricultural machinery operations according to the present invention includes the following steps.
- Collect plant variety planting area data including but not limited to the plant's growing habits in the planting area and the type of agricultural machinery required throughout the growing period;
- the plant varieties include more than two types of varieties; each type of plant variety includes at least one planting area data;
- the growth habit includes the growth characteristics corresponding to each growth stage; the growth characteristics include but are not limited to one or more of the required water requirements, nutrient requirements and growth height parameters;
- the whole growth period includes the period corresponding to each growth stage
- the types of agricultural machinery operations include but are not limited to one or more of land preparation, seeding, fertilization, plant protection, irrigation and harvesting;
- the farm machinery operation analysis model can derive the current probabilities based on plant variety, planting area, and current growing period Type of agricultural machinery required.
- the types of agricultural machinery operations that the plant varieties need to adopt during each growth period are obtained.
- an analysis model of agricultural machinery operation types of crops is obtained, so that it is convenient to quickly obtain the type of agricultural machinery operations required by the plant variety during each growth period when the plant variety and planting area are only known. It is beneficial to the development of intelligent agriculture and facilitates the realization of intelligent agricultural machinery operations.
- the collected plant variety planting area data also includes the optimal sowing time and/or local meteorological conditions.
- farmers can plant according to the best sowing time, which is conducive to the growth of crops according to the best growing climate; on the other hand, farmers can plant according to the best sowing time, which is conducive to the growth period according to the current date.
- the method further includes obtaining the current status of soil fertility based on plant growth characteristics and historical fertilization.
- fertilization it can be judged whether fertilization is required, the type of fertilization and the amount of fertilization according to the current fertility status of the soil.
- the method further includes that, when the required type of agricultural machinery operation is fertilization, a specific fertilization method and fertilizer variety are obtained according to the current growing period.
- a specific fertilization method and fertilizer variety are obtained according to the current growing period.
- different types of fertilizers are required, and there are differences in fertilization methods. For example, some fertilize on the soil and some require fertilization under the soil.
- fertilizers that need to be fertilized can they be mixed and fertilized? Mix.
- the method further includes, when the required type of agricultural machinery operation is land preparation, obtaining the depth of the land preparation required according to the plant variety.
- the required depth of land preparation is different when preparing the land before sowing, some need deep cultivation, some shallow cultivation is required, you need to give the depth of the land preparation according to the crop variety, for example, at least how many Cm; the types of land preparation include flat land, overturned land, and rotary tillage.
- the method further includes, when the required type of agricultural machinery operation is sowing, deriving the type of agricultural machinery and the sowing method to be used according to the plant variety. Different crop varieties require different types of agricultural machinery and sowing methods to be used for sowing.
- the generated analysis model should further be able to analyze the types of agricultural machinery and sowing methods used to facilitate smart operations.
- the method further includes, when the required type of agricultural machinery operation is harvesting, determining the type of agricultural machinery and the harvesting method to be used according to the plant variety. Different crop varieties require different types of agricultural machinery and sowing methods during harvesting.
- the generated analysis model should further be able to analyze the types of agricultural machinery and sowing methods used to facilitate smart operations.
- the method further includes, when the required type of agricultural machinery operation is irrigation, according to the demand for water during the current growth period of the plant variety and/or the local meteorological conditions within the set time period Specific implementation. For example, whether it needs irrigation, water quantity and irrigation time, irrigation method, etc. Different crop varieties require different water during their different growth periods, so they need to be analyzed separately; in addition, they can be combined with the latest local meteorological conditions to analyze whether irrigation is needed and how much water is poured, for example, recently If there is enough rain, no more irrigation is needed. Although there has been rain in recent days, but the amount of water is not enough, you can analyze how to irrigate and how much water to use according to the amount of rain.
- the method further includes,
- the agricultural machinery type and the corresponding operation index are obtained according to the plant variety, and the operation index includes the depth of the required land preparation and the driving speed of the vehicle;
- the operation index includes the spacing between planting rows, the average amount of seed used per acre and the driving speed of vehicles;
- the type of agricultural machinery and the corresponding operation index are obtained according to the current growing period, and the operation index includes the rate of fertilizer spreading, the average amount of fertilizer used per acre and the driving speed of vehicles;
- the type of agricultural machinery and the corresponding operation index are obtained according to the plant variety, and the operation index includes the spraying rate of the medicament, the average amount of medicine per acre and the driving speed of the vehicle;
- the agricultural machinery type and the corresponding operation index are obtained according to the plant variety, and the operation index includes the vehicle running speed.
- an agricultural machinery operation analysis model generated using the above analysis model generation method, including,
- Parameter input interface including,
- Plant variety input and/or selection unit to input and/or select the plant variety to be analyzed currently
- Planting area input and/or selection unit to input and/or select the planting area to be analyzed currently;
- the acquisition unit during childbirth according to the input and/or selection, or according to the current date;
- Parameter output interface including,
- the agricultural machinery operation type output unit outputs the agricultural machinery operation type that may be currently needed.
- the type of agricultural machinery and the corresponding operation index are obtained according to the plant variety, and the operation index includes the depth of the land preparation and the driving speed of the vehicle;
- the operation index includes the row spacing of the planting plant, the average amount of seed used per acre and the driving speed of the vehicle;
- the operation index includes the rate of fertilizer spreading, the average amount of fertilizer used per acre of land, and the speed of vehicle travel;
- the operation index includes the spraying rate of the medicament, the average amount of medicine per acre and the driving speed of the vehicle;
- the agricultural machinery operation plan is plant protection
- the agricultural machinery type and the corresponding operation index are obtained according to the plant variety, and the operation index includes the vehicle driving speed.
- an agricultural machinery operation analysis model or analysis system includes a parameter input interface and a parameter output interface, and the conditions to be input are input through the parameter input interface to obtain an output result.
- Corresponding growth period if you need to set manually, you can get it manually; if it can be obtained automatically (for example, according to local planting habits, the current date has a corresponding relationship with the growing period, so you can get the current position according to the corresponding relationship The growth period corresponding to the date), the model or system can automatically obtain the growth period after obtaining the plant variety and the corresponding planting area; if it can be set manually or automatically, it can be selected and set as needed.
- the method includes: obtaining plant species to be analyzed, planting areas, and the current or growing period to be analyzed, and analyzing using the above analysis model to obtain the type of agricultural machinery operations that may be needed currently .
- the method also includes setting the local meteorological conditions within the time period, and combining with the water demand of the plant variety during the current growth period, and giving a specific implementation of irrigation.
- the method includes,
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Animal Husbandry (AREA)
- General Health & Medical Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Agronomy & Crop Science (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Cultivation Of Plants (AREA)
Abstract
本发明提供了一种农机作业分析模型生成方法、模型、分析方法及管理方法,分析模型生成方法中,搜集植物品种种植区域数据,包括但不仅限于植物在该种植区域的生长习性和在整个生育期间需要的农机作业类型;根据植物品种种植区域数据,进行机器学习,生成植物品种全生育期农机作业分析模型;所述农机作业分析模型能够根据植物品种,种植区域,以及当前所处于的生育期间,得出当前可能需要的农机作业类型。与现有技术相比,本发明技术方案能够快速通过模型得出植物品种在各生育期间,需要的农机作业类型,有利于农业智能化发展,便于实现智能化农机作业。
Description
相关申请的交叉引用
本申请要求于2019年01月03日提交中国专利局,申请号为2019100056283,发明名称为“一种农机作业分析模型生成方法、模型、分析方法及管理方法”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本发明涉及农业智能化领域,特别涉及一种农机作业分析模型生成方法、模型、分析方法及管理方法。
随着农业智能化的发展,农业经营越来越大片经营化,农机作业服务作为农业服务,包括整地(包括平地、翻地、旋耕)、播种、施肥、植保、灌溉和收割等,需要的农机作业服务也越来越趋向于专业服务化,为了能够促进农机现代化,农业现代化智能化的发展,需要能够快得出植物品种在各生育期间,需要的农机作业类型,从而有利于农业智能化发展,便于实现智能化农机作业。
发明内容
本发明提供了一种农机作业分析模型生成方法、模型、分析方法及管理方法,具有便于实现智能化农机作业的特点。
根据本发明提供的一种农机作业分析模型生成方法,方法包括,
搜集植物品种种植区域数据,包括但不仅限于植物在该种植区域的生长习性和在整个生育期间需要的农机作业类型;
所述植物品种包括两类以上的品种;每类植物品种包括至少一个种植区域数据;
所述生长习性包括在各个生长阶段所对应的生育特性;所述生育特性包括 但不限于所需要的水分需求、养分需求和生长高度参数中的一种或几种;
所述整个生育期间包括各个生长阶段所对应的时期;
所述农机作业类型包括但不限于整地、播种、施肥、植保、灌溉和收割中的一种或几种;
根据植物品种种植区域数据,进行机器学习,生成植物品种全生育期农机作业分析模型;所述农机作业分析模型能够根据植物品种,种植区域,以及当前所处于的生育期间,得出当前可能需要的农机作业类型。
所搜集的植物品种种植区域数据还包括最佳播种时期和/或当地的气象条件。
所述方法还包括,根据植物生育特性和历史施肥情况,得出当前土壤的肥力现状。
所述方法还包括,当需要的农机作业类型为施肥时,根据当前的生育期间,得出具体的施肥方式和肥料品种。
所述方法还包括,当需要的农机作业类型为整地时,根据植物品种得出需要整地的深度。
所述方法还包括,当需要的农机作业类型为播种时,根据植物品种得出需要采用的农机类型及播种方式。
所述方法还包括,当需要的农机作业类型为收割时,根据植物品种得出需要采用的农机类型及收割方式。
所述方法还包括,当需要的农机作业类型为灌溉时,根据植物品种当前生育期间对水分的需求和/或设置时间段内当地的气象条件给出灌溉的具体实施方案。
可选的,所述方法还包括:
当需要的农机作业类型为整地时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括需要整地的深度和车辆行驶速率;
当需要的农机作业类型为播种时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括播种株行间距、每亩地平均用种量和车辆行驶速率; 当需要的农机作业类型为施肥时,根据当前的生育期间得出农机类型和对应的作业指标,该作业指标包括撒肥速率、每亩地平均用肥量和车辆行驶速率;
当需要的农机作业类型为植保时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括药剂喷洒速率、每亩地平均用药量和车辆行驶速率;
当需要的农机作业类型为植保时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括车辆行驶速率。
一种农机作业分析模型,采用上述分析模型生成方法生成,其特征在于,包括,
参数输入接口,包括,
植物品种输入和/或选择单元,输入和/或选择当前需要分析的植物品种;
种植区域输入和/或选择单元,输入和/或选择当前需要分析的种植区域;
生育期间获取单元,根据输入和/或选择获取,或根据当前所处的日期自动获取;
参数输出接口,包括,
农机作业类型输出单元,输出当前可能需要的农机作业类型。
还包括农机作业方案输出单元,根据农机作业类型及植物品种给出农机作业方案;所述农机作业方案包括但不仅限于整地、播种、施肥、植保、收割和灌溉的农机作业方案。
当农机作业方案为施肥的农机作业方案时,给出具体的施肥方式和肥料品种。
当农机作业方案为整地的农机作业方案时,给出需要整地的深度。
当农机作业方案为播种的农机作业方案时,给出需要采用的农机类型及播种方式。
当农机作业方案为收割的农机作业方案时,给出需要采用的农机类型及收割方式。
当农机作业方案为灌溉的农机作业方案时,给出灌溉的具体实施方案。
可选的,当农机作业方案为整地时,根据植物品种得出农机类型和对应的 作业指标,该作业指标包括需要整地的深度和车辆行驶速率;
当农机作业方案为播种时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括播种株行间距、每亩地平均用种量和车辆行驶速率;
当农机作业方案为施肥时,根据当前的生育期间得出农机类型和对应的作业指标,该作业指标包括撒肥速率、每亩地平均用费量和车辆行驶速率;
当农机作业方案为植保时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括药剂喷洒速率、每亩地平均用药量和车辆行驶速率;
当农机作业方案为植保时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括车辆行驶速率。
根据本发明提供的一种农机作业分析方法,方法包括,
获取需要分析的植物品种、种植区域及当前或所需要分析的生育期间,采用上述分析模型进行分析,得出当前可能需要的农机作业类型。
所述方法还包括,设置时间段内当地的气象条件,结合植物品种当前生育期间对水分的需求,给出灌溉的具体实施方案。
根据本发明提供的一种农机作业管理方法,方法包括,
根据上述农机作业分析方法给出的农机作业标准,上传到农机作业的监控终端;采集实际农机作业的技术指标数据,并将所述指标数据与作业标准进行对比,如果对比数据偏差超过设定阈值,则认为农机作业不符合要求。
与现有技术相比,本发明技术方案能够快速通过模型得出植物品种在各生育期间,需要的农机作业类型,有利于农业智能化发展,便于实现智能化农机作业。
构成本发明的一部分的附图用来提供对本发明的进一步理解,使得本发明的其它特征、目的和优点变得更明显。本发明的示意性实施例附图及其说明用于解释本发明,并不构成对本发明的不当限定。在附图中:
图1是根据本发明的农机作业分析模型生成方法的流程示意图。
为了使本发明的目的、技术方案及优点更加清楚明白,以下结合实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本发明,并不用于限定本发明。
本说明书(包括摘要)中公开的任一特征,除非特别叙述,均可被其他等效或者具有类似目的的替代特征加以替换。即,除非特别叙述,每个特征只是一系列等效或类似特征中的一个例子而已。
图1是根据本发明的农机作业分析模型生成方法的流程示意图,如图1所示,根据本发明提供的一种农机作业分析模型生成方法,方法包括如下步骤,
100,搜集植物品种种植区域数据,包括但不仅限于植物在该种植区域的生长习性和在整个生育期间需要的农机作业类型;
所述植物品种包括两类以上的品种;每类植物品种包括至少一个种植区域数据;
所述生长习性包括在各个生长阶段所对应的生育特性;所述生育特性包括但不限于所需要的水分需求、养分需求和生长高度参数中的一种或几种;
所述整个生育期间包括各个生长阶段所对应的时期;
所述农机作业类型包括但不限于整地、播种、施肥、植保、灌溉和收割中的一种或几种;
200,根据植物品种种植区域数据,进行机器学习,生成植物品种全生育期农机作业分析模型;所述农机作业分析模型能够根据植物品种,种植区域,以及当前所处于的生育期间,得出当前可能需要的农机作业类型。
在本发明方案中,通过搜集大量的植物品种区域数据,通过对生长习性和在整个生育期间可能采用的农机作业类型进行分析,得出植物品种在各个生育期间需要采用的农机作业类型。通过大量的数据机器学习,得到农作物的农机作业类型分析模型,从而便于在仅知道植物品种和种植区域的情况下,能够快速通过模型得出该植物品种在各生育期间,需要的农机作业类型,有利于农业 智能化发展,便于实现智能化农机作业。
作为本发明的一种实施方式,所搜集的植物品种种植区域数据还包括最佳播种时期和/或当地的气象条件。一方面农户能够根据最佳的播种时期进行种植,有利于农作物的按照最佳的生长气候规律进行生长;另一方面农户根据最佳播种时期进行种植,有利于根据当前日期所处于的生育期进行判断可能需要的农机作业类型。
作为本发明的一种实施方式,所述方法还包括,根据植物生育特性和历史施肥情况,得出当前土壤的肥力现状。在需要施肥时,能够根据当前土壤的肥力现状来判断是否需要施肥,施肥的种类及施肥量。
作为本发明的一种实施方式,所述方法还包括,当需要的农机作业类型为施肥时,根据当前的生育期间,得出具体的施肥方式和肥料品种。农作物不同的生育期间,所需要的肥料品种不同,施肥方式也存在区别,例如有的是土上施肥,有的需要土下施肥,当需要施肥的肥料品种有两种以上时,是否可以混合施肥,如何进行混合。
作为本发明的一种实施方式,所述方法还包括,当需要的农机作业类型为整地时,根据植物品种得出需要整地的深度。针对不同的农作物品种,播种前整地时,需要的整地深度并不相同,有的需要深耕,有的浅耕就可以了,需要根据农作物品种,给出整地的深度,例如整地审查至少要达到多少厘米;整地的类型包括平地、翻地、旋耕。
作为本发明的一种实施方式,所述方法还包括,当需要的农机作业类型为播种时,根据植物品种得出需要采用的农机类型及播种方式。不同的农作物品种,其需播种时要采用的农机类型和播种方式有所不同,生成的分析模型应当进一步能够分析出采用的农机类型和播种方式以更方便智能作业。
作为本发明的一种实施方式,所述方法还包括,当需要的农机作业类型为收割时,根据植物品种得出需要采用的农机类型及收割方式。不同的农作物品种,收割时,其需要采用的农机类型和播种方式有所不同,生成的分析模型应当进一步能够分析出采用的农机类型和播种方式以更方便智能作业。
作为本发明的一种实施方式,所述方法还包括,当需要的农机作业类型为灌溉时,根据植物品种当前生育期间对水分的需求和/或设置时间段内当地的气象条件给出灌溉的具体实施方案。如,是否需要灌溉,水量及灌溉时间,灌溉方式等。不同的农作物品种,在其不同的生育期间,需要的水分有所不同,因此需要分别分析;另外,能够结合当地的最近的气象条件来分析是否需要灌溉,浇多少水,例如,最近每天都在下雨,水量充足,则不需要再灌溉,虽然最近几天有下雨,但是水量不充足,则可以根据下雨的水量情况,分析需要如何灌溉,浇多少水。
作为本发明的一种实施方式,所述方法还包括,
当需要的农机作业类型为整地时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括需要整地的深度和车辆行驶速率;
当需要的农机作业类型为播种时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括播种株行间距、每亩地平均用种量和车辆行驶速率;
当需要的农机作业类型为施肥时,根据当前的生育期间得出农机类型和对应的作业指标,该作业指标包括撒肥速率、每亩地平均用肥量和车辆行驶速率;
当需要的农机作业类型为植保时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括药剂喷洒速率、每亩地平均用药量和车辆行驶速率;
当需要的农机作业类型为植保时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括车辆行驶速率。
根据本发明提供的一种农机作业分析模型,采用上述分析模型生成方法生成,包括,
参数输入接口,包括,
植物品种输入和/或选择单元,输入和/或选择当前需要分析的植物品种;
种植区域输入和/或选择单元,输入和/或选择当前需要分析的种植区域;
生育期间获取单元,根据输入和/或选择获取,或根据当前所处的日期自动获取;
参数输出接口,包括,
农机作业类型输出单元,输出当前可能需要的农机作业类型。
本发明技术方案提出的农机作业分析模型,
还包括农机作业方案输出单元,根据农机作业类型及植物品种给出农机作业方案;所述农机作业方案包括但不仅限于整地、播种、施肥、植保、收割和灌溉的农机作业方案。
可选的,当农机作业方案为整地时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括需要整地的深度和车辆行驶速率;
当农机作业方案为播种时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括播种株行间距、每亩地平均用种量和车辆行驶速率;
当农机作业方案为施肥时,根据当前的生育期间得出农机类型和对应的作业指标,该作业指标包括撒肥速率、每亩地平均用肥量和车辆行驶速率;
当农机作业方案为植保时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括药剂喷洒速率、每亩地平均用药量和车辆行驶速率;
当农机作业方案为植保时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括车辆行驶速率。
根据本发明提供的一种农机作业分析模型或者说分析系统,包括参数输入接口和参数输出接口,将需要输入的条件通过参数输入接口输入,获得输出的结果。对应生育期间,如果需要手动设置,则通过手动设置获取;如果能自动获得(例如,根据当地的种植习惯,当前所处的日期与生育期间有对应关系,因此能够根据对应关系,得出当前所处日期对应的生育期间),则模型或系统能够在获取植物品种和对应的种植区域后,自动获得生育期间;如果既能够手动设置又能够自动获得,则可以根据需要进行选择设置。
根据本发明提供的一种农机作业分析方法,方法包括,获取需要分析的植物品种、种植区域及当前或所需要分析的生育期间,采用上述分析模型进行分析,得出当前可能需要的农机作业类型。
所述方法还包括,设置时间段内当地的气象条件,结合植物品种当前生育期间对水分的需求,给出灌溉的具体实施方案。
根据本发明提供的一种农机作业管理方法,方法包括,
根据上述农机作业分析方法给出的农机作业标准,上传到农机作业的监控终端;采集实际农机作业的技术指标数据,并将所述指标数据与作业标准进行对比,如果对比数据偏差超过设定阈值,则认为农机作业不符合要求。针对农作物生育特性和作业需求,制定农机作业标准,上传到农机作业的监控终端上,指导农机手开展农机作业,同时采集农机作业的技术指标数据,并将这些数据与当前农作物的生长发育特性和作业标准进行比对,作为一种具体方案,如果比对数据偏差超过5%,即认为作业不符合要求。
Claims (12)
- 一种农机作业分析模型生成方法,方法包括,搜集植物品种种植区域数据,包括但不仅限于植物在该种植区域的生长习性和在整个生育期间需要的农机作业类型;所述植物品种包括两类以上的品种;每类植物品种包括至少一个种植区域数据;所述生长习性包括在各个生长阶段所对应的生育特性;所述生育特性包括但不限于所需要的水分需求、养分需求和生长高度参数中的一种或几种;所述整个生育期间包括各个生长阶段所对应的时期;所述农机作业类型包括但不限于整地、播种、施肥、植保、灌溉和收割中的一种或几种;根据植物品种种植区域数据,进行机器学习,生成植物品种全生育期农机作业分析模型;所述农机作业分析模型能够根据植物品种,种植区域,以及当前所处于的生育期间,得出当前可能需要的农机作业类型。
- 根据权利要求1所述的农机作业分析模型生成方法,所搜集的植物品种种植区域数据还包括最佳播种时期和/或当地的气象条件。
- 根据权利要求1所述的农机作业分析模型生成方法,所述方法还包括,根据植物生育特性和历史施肥情况,得出当前土壤的肥力现状。
- 根据权利要求1到3之一所述的农机作业分析模型生成方法,所述方法还包括但不限于如下方法的一种或几种,当需要的农机作业类型为施肥时,根据当前的生育期间,得出具体的施肥方式和肥料品种;当需要的农机作业类型为整地时,根据植物品种得出需要整地的深度;当需要的农机作业类型为播种时,根据植物品种得出需要采用的农机类型及播种方式;当需要的农机作业类型为收割时,根据植物品种得出需要采用的农机类型及收割方式;当需要的农机作业类型为灌溉时,根据植物品种当前生育期间对水分的需 求和/或设置时间段内当地的气象条件给出灌溉的具体实施方案。
- 根据权利要求1到3之一所述的农机作业分析模型生成方法,所述方法还包括但不限于如下方法的一种或几种,当需要的农机作业类型为整地时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括需要整地的深度和车辆行驶速率;当需要的农机作业类型为播种时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括播种株行间距、每亩地平均用种量和车辆行驶速率;当需要的农机作业类型为施肥时,根据当前的生育期间得出农机类型和对应的作业指标,该作业指标包括撒肥速率、每亩地平均用肥量和车辆行驶速率;当需要的农机作业类型为植保时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括药剂喷洒速率、每亩地平均用药量和车辆行驶速率;当需要的农机作业类型为植保时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括车辆行驶速率。
- 一种农机作业分析模型,采用权利要求1到5之一所述的分析模型生成方法生成,其特征在于,包括,参数输入接口,包括,植物品种输入和/或选择单元,输入和/或选择当前需要分析的植物品种;种植区域输入和/或选择单元,输入和/或选择当前需要分析的种植区域;生育期间获取单元,根据输入和/或选择获取,或根据当前所处的日期自动获取;参数输出接口,包括,农机作业类型输出单元,输出当前可能需要的农机作业类型。
- 根据权利要求6所述的农机作业分析模型,其特征在于,还包括农机作业方案输出单元,根据农机作业类型及植物品种给出农机作业方案;所述农机作业方案包括但不仅限于整地、播种、施肥、植保、收割和灌溉的农机作业方案。
- 根据权利要求7所述的农机作业分析模型,其特征在于,当农机作业方案为施肥的农机作业方案时,给出具体的施肥方式和肥料品种;当农机作业方案为整地的农机作业方案时,给出需要整地的深度;当农机作业方案为播种的农机作业方案时,给出需要采用的农机类型及播种方式;当农机作业方案为收割的农机作业方案时,给出需要采用的农机类型及收割方式;当农机作业方案为灌溉的农机作业方案时,给出灌溉的具体实施方案。
- 根据权利要求7所述的农机作业分析模型,其特征在于,当农机作业方案为整地时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括需要整地的深度和车辆行驶速率;当农机作业方案为播种时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括播种株行间距、每亩地平均用种量和车辆行驶速率;当农机作业方案为施肥时,根据当前的生育期间得出农机类型和对应的作业指标,该作业指标包括撒肥速率、每亩地平均用肥量和车辆行驶速率;当农机作业方案为植保时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括药剂喷洒速率、每亩地平均用药量和车辆行驶速率;当农机作业方案为植保时,根据植物品种得出农机类型和对应的作业指标,该作业指标包括车辆行驶速率。
- 一种农机作业分析方法,方法包括,获取需要分析的植物品种、种植区域及当前或所需要分析的生育期间,采用权利要求6到9之一所述的分析模型进行分析,得出当前可能需要的农机作业类型。
- 根据权利要求10所述的农机作业分析方法,所述方法还包括,设置时间段内当地的气象条件,结合植物品种当前生育期间对水分的需求,给出灌溉的具体实施方案。
- 一种农机作业管理方法,方法包括,根据权利要求10或11所述的农机作业分析方法给出的农机作业标准,上传到农机作业的监控终端;采集实际农机作业的技术指标数据,并将所述指标数据与作业标准进行对比,如果对比数据偏差超过设定阈值,则认为农机作业不符合要求。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910005628.3A CN109829626A (zh) | 2019-01-03 | 2019-01-03 | 一种农机作业分析模型生成方法、模型、分析方法及管理方法 |
CN201910005628.3 | 2019-01-03 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020140958A1 true WO2020140958A1 (zh) | 2020-07-09 |
Family
ID=66860148
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/070174 WO2020140958A1 (zh) | 2019-01-03 | 2020-01-03 | 农机作业分析模型生成方法、模型、分析方法及管理方法 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109829626A (zh) |
WO (1) | WO2020140958A1 (zh) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109829626A (zh) * | 2019-01-03 | 2019-05-31 | 固安京蓝云科技有限公司 | 一种农机作业分析模型生成方法、模型、分析方法及管理方法 |
CN113848870A (zh) * | 2020-06-10 | 2021-12-28 | 广州极飞科技股份有限公司 | 无人车的播种控制方法、装置、终端设备、无人车和介质 |
CN115755739A (zh) * | 2022-12-15 | 2023-03-07 | 苏州大域无疆航空科技有限公司 | 基于深度学习的农机运行监控系统 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107945042A (zh) * | 2017-11-29 | 2018-04-20 | 上海华维节水灌溉股份有限公司 | 一种作物生长灌溉决策控制系统 |
CN109829626A (zh) * | 2019-01-03 | 2019-05-31 | 固安京蓝云科技有限公司 | 一种农机作业分析模型生成方法、模型、分析方法及管理方法 |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103077474A (zh) * | 2011-10-25 | 2013-05-01 | 孙华英 | 一种地图软件辅助的农业信息管理方法 |
CN104571095A (zh) * | 2015-01-16 | 2015-04-29 | 江苏农牧科技职业学院 | 一种农机发动机无线诊断装置及系统 |
CN108510107B (zh) * | 2018-03-07 | 2022-04-15 | 深圳远佳智慧科技有限公司 | 一种农业种植指导方法、电子设备及存储介质 |
CN108805666A (zh) * | 2018-05-29 | 2018-11-13 | 安徽农业大学 | 基于物联云的农机设备共享系统及方法 |
-
2019
- 2019-01-03 CN CN201910005628.3A patent/CN109829626A/zh active Pending
-
2020
- 2020-01-03 WO PCT/CN2020/070174 patent/WO2020140958A1/zh active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107945042A (zh) * | 2017-11-29 | 2018-04-20 | 上海华维节水灌溉股份有限公司 | 一种作物生长灌溉决策控制系统 |
CN109829626A (zh) * | 2019-01-03 | 2019-05-31 | 固安京蓝云科技有限公司 | 一种农机作业分析模型生成方法、模型、分析方法及管理方法 |
Also Published As
Publication number | Publication date |
---|---|
CN109829626A (zh) | 2019-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020140958A1 (zh) | 农机作业分析模型生成方法、模型、分析方法及管理方法 | |
CN105830710B (zh) | 一种糖料甘蔗绿色可持续高产种植方法 | |
CN103503659B (zh) | 玉米高产种植方法 | |
CN102986405B (zh) | 一种马铃薯-水稻复种模式的种植方法 | |
CN105960862B (zh) | 一种玉米大垄双行深耕分层式施肥播种机 | |
CN103797926B (zh) | 水旱轮作中稻草还田复种方法 | |
CN106386114A (zh) | 一种油菜育苗移栽方法 | |
CN105660102A (zh) | 一种窝播留苗移栽两用的油菜种植方法 | |
CN103053302A (zh) | 一种适用甜瓜露地简约栽培的机械化种植模式 | |
CN104823625A (zh) | 一种甘蔗种植全程机械化生产模式 | |
CN106508391A (zh) | 设施番茄种植管理方法 | |
CN102948363B (zh) | 一种杂交水稻的制种方法 | |
CN106941907A (zh) | 全膜双垄沟播玉米二茬免耕种植冬油菜的方法 | |
CN106613227A (zh) | 一种饲草作物与粮食作物的轮作种植方法 | |
CN104082026A (zh) | 一种在甘蔗地套种西瓜的方法 | |
CN105393789A (zh) | 大麦玉米大豆三熟制秸秆还田种植方法 | |
CN109819956A (zh) | 一种农药喷洒植保作业分析模型及分析方法 | |
CN104054482A (zh) | 在早春时间甘蔗地套种西瓜的方法 | |
CN105580623A (zh) | 油菜玉米大豆三熟制秸秆还田种植方法 | |
CN104604521B (zh) | 一种在蔗田上栽培双孢蘑菇的方法 | |
CN110490757A (zh) | 一种基于智能农业技术的水稻生产运营平台及运营方法 | |
CN105900677A (zh) | 二比空双株玉米密植栽培方法 | |
CN105766354A (zh) | 一种朝鲜蓟套种大豆栽培技术 | |
CN110150072A (zh) | 一种烤烟、丹参轮作高效种植模式的研究方法 | |
CN105191596A (zh) | 一种机采棉环保栽培方法 |
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: 20735975 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20735975 Country of ref document: EP Kind code of ref document: A1 |