WO2016188384A1 - 智能种植管理方法和智能种植设备 - Google Patents

智能种植管理方法和智能种植设备 Download PDF

Info

Publication number
WO2016188384A1
WO2016188384A1 PCT/CN2016/082958 CN2016082958W WO2016188384A1 WO 2016188384 A1 WO2016188384 A1 WO 2016188384A1 CN 2016082958 W CN2016082958 W CN 2016082958W WO 2016188384 A1 WO2016188384 A1 WO 2016188384A1
Authority
WO
WIPO (PCT)
Prior art keywords
planting
information
plant
condition information
intelligent
Prior art date
Application number
PCT/CN2016/082958
Other languages
English (en)
French (fr)
Inventor
徐吉祥
Original Assignee
徐吉祥
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 徐吉祥 filed Critical 徐吉祥
Priority to EP16799272.6A priority Critical patent/EP3330905A4/en
Priority to JP2018513711A priority patent/JP2018517220A/ja
Priority to CA2987319A priority patent/CA2987319A1/en
Priority to AU2016266460A priority patent/AU2016266460B2/en
Priority to RU2017145656A priority patent/RU2688234C1/ru
Priority to US15/576,899 priority patent/US10966377B2/en
Publication of WO2016188384A1 publication Critical patent/WO2016188384A1/zh

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01GHORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
    • A01G7/00Botany in general
    • A01G7/06Treatment of growing trees or plants, e.g. for preventing decay of wood, for tingeing flowers or wood, for prolonging the life of plants
    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01CPLANTING; SOWING; FERTILISING
    • A01C21/00Methods of fertilising, sowing or planting
    • A01C21/005Following a specific plan, e.g. pattern
    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01CPLANTING; SOWING; FERTILISING
    • A01C21/00Methods of fertilising, sowing or planting
    • A01C21/007Determining fertilization requirements
    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01GHORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
    • A01G25/00Watering gardens, fields, sports grounds or the like
    • A01G25/16Control of watering
    • A01G25/165Cyclic operations, timing systems, timing valves, impulse operations
    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01GHORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
    • A01G25/00Watering gardens, fields, sports grounds or the like
    • A01G25/16Control of watering
    • A01G25/167Control by humidity of the soil itself or of devices simulating soil or of the atmosphere; Soil humidity sensors
    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01GHORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
    • A01G7/00Botany in general
    • A01G7/02Treatment of plants with carbon dioxide
    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01GHORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
    • A01G7/00Botany in general
    • A01G7/04Electric or magnetic or acoustic treatment of plants for promoting growth
    • A01G7/045Electric or magnetic or acoustic treatment of plants for promoting growth with electric lighting
    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01GHORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
    • A01G9/00Cultivation in receptacles, forcing-frames or greenhouses; Edging for beds, lawn or the like
    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01GHORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
    • A01G9/00Cultivation in receptacles, forcing-frames or greenhouses; Edging for beds, lawn or the like
    • A01G9/20Forcing-frames; Lights, i.e. glass panels covering the forcing-frames
    • AHUMAN NECESSITIES
    • A01AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01GHORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
    • A01G9/00Cultivation in receptacles, forcing-frames or greenhouses; Edging for beds, lawn or the like
    • A01G9/24Devices or systems for heating, ventilating, regulating temperature, illuminating, or watering, in greenhouses, forcing-frames, or the like
    • A01G9/249Lighting means
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00Computing arrangements based on specific mathematical models
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/06Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02Agriculture; Fishing; Forestry; Mining
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P60/00Technologies relating to agriculture, livestock or agroalimentary industries
    • Y02P60/14Measures for saving energy, e.g. in green houses

Definitions

  • the invention relates to an intelligent planting method and an intelligent planting device, and more particularly to an internet-based intelligent planting management method and an intelligent planting device.
  • the most common smart planting is an automatic watering system that serves independent users. Since there is no specific plant variety (water plants or arid plants), planting environment (in the south or north, specific lighting conditions, etc.), the watering amount and time interval are all roughly estimated.
  • Chinese patent application publication CN102550371A proposes an automatic irrigation control system and method for a community or a villa based on the Internet of Things technology, which is composed of a control system, a regional node, a soil temperature and humidity sensor and a spray irrigation terminal.
  • a control system a regional node
  • a soil temperature and humidity sensor a soil temperature and humidity sensor
  • a spray irrigation terminal a spray irrigation terminal.
  • two indicators of temperature and humidity are monitored, and whether watering is determined according to two indicators of temperature and humidity.
  • the amount of watering per time in this technique is based on a preset fixed threshold or manual control, and does not take into account plant species, plant growth cycle, and only considers soil moisture and temperature for the environment.
  • Cipheral Patent Application Publication No. CN102868749A proposes an IoT cloud service system and service flow method for agricultural planting and breeding.
  • the planting data is collected and sent to the cloud center, and finally to the user terminal.
  • Cloud services include: agricultural information, policies and regulations, information release, information consultation, expert systems, agricultural products trading, agricultural product traceability, technical services, data mining, production monitoring, environmental monitoring and terminal management modules.
  • the problems of this technology are: it is mainly data perception and information release and acquisition services, lack of feedback control for planting itself; information one-way flow, that is, planting data collection, sent to user terminals; users initiate requests when services are needed Access to information, lack of active intelligent control capabilities; According to the perception system, information such as plant species and plant life cycle is not considered.
  • Chinese Patent Application Publication No. CN13155839A proposes an automatic watering and fertilizing system for detecting moisture and nutrients in the soil. If the content of water and nutrients is lowered, the soil is automatically watered or fertilized. However, this system simply waters and fertilizes according to pre-set values, without considering plant species, plant life cycle, and considering only soil moisture and fertilizer levels in the environment.
  • Chinese Patent Application Publication No. CN104012375A proposes an agricultural automatic sensing irrigation monitoring system that automatically irrigate plants in consideration of changes in ambient temperature, humidity and season. It uses an expert knowledge store that stores appropriate growth environment parameters for different growth stages of different crops. In addition to monitoring soil moisture, this technique also proposes to monitor physiological indicators of plants (such as leaf temperature and micro-variation of stems). However, this technique only focuses on irrigation issues and does not consider the growth cycle of plants.
  • Chinese patent application publication CN104012376A proposes an intelligent watering system, method and device based on ecological environment information, which can accurately control watering according to the growth cycle of flowers and plants.
  • this technique only focuses on watering issues.
  • Chinese Patent Application Publication No. CN104216373A proposes a smart cloud-based home water management system for automatic watering of flowers and automatic addition of water reservoirs.
  • This technology proposes cloud intelligent remote control, which is watered by manual control at the remote control end or according to a manually set water management plan.
  • the amount of watering is carried out manually or according to a manually set water management plan, without considering the plant's growth cycle, the environment and the current temperature and humidity of the soil.
  • this technology only focuses on watering issues.
  • Chinese Patent Publication CN203490529U (Application No. CN201320629665) proposes an intelligent planting device based on the Internet of Things.
  • This paper proposes an intelligent planting device for agricultural greenhouses, in which “in the form of Internet of Things, intelligent planting can be carried out. After maturity, it can also be packaged, weighed, labeled, planted in full, and traceable source of production information” .
  • the intelligent planting refers to: monitoring through the way of the Internet of Things, and remotely controlling the way to achieve artificial planting (see paragraph 0015).
  • the user can control the plant by controlling any device such as a terminal computer, a tablet terminal or a mobile phone terminal. Intelligent management and control"), reduce labor intensity, and manage food source information.
  • the remote control proposed in this technology is based on labor and cannot meet the intelligent management of large-scale distributed planting.
  • Chinese Patent Application Publication No. CN102884932A (Application No. CN2012104227706) proposes an intelligent soil culture plant growth and cultivation system based on planting expert cloud.
  • the document "provides an intelligent soil-based plant growth and cultivation system based on a planting expert cloud, including a planting expert cloud center, a communication network, and one or more intelligent planting devices” to realize “storing planting experience information” And sharing” and “planting in a way that shares resources.”
  • Planting experience information suggests soil pH, ambient light intensity, temperature, and humidity.
  • the guidance data planted in this technique uses preset values. Due to the many different factors in urban geography and family environment, the technology does not consider these different factors, and the acquisition of the collected empirical data is confusing and cannot actually guide the planting.
  • the living environment of modern cities is diverse, and the environment in which people live in the house or outdoors is also very different. Different cities have different climatic conditions, and some cities with large urban humidity are dry. Even in the same city, the planting environment in different regions or residential communities is different, and even in the same community, different planting environments, such as lighting conditions, are different.
  • the object of the present invention is to achieve intelligent management of large-scale distributed planting in different planting environments. Further, the present invention can solve the problem that an individual family wants to grow but lacks planting management experience and is difficult to obtain good returns. In addition, the present invention can also solve the problem that the individual family wants to grow but does not have time management.
  • the present invention proposes to construct an intelligent planting system and establish an intelligent planting star network by using the Internet, big data analysis, machine learning, and smart home hardware and software technologies.
  • an intelligent planting management method for controlling a planting process of a plurality of planting devices placed in different environments, the method comprising data collecting steps, classification and marking Steps and control steps, wherein:
  • the data collecting step includes: collecting planting information of the plant and environmental information of the planting device, and transmitting the same to the data processing system; collecting at predetermined time intervals Planting condition information at least one of a plurality of planting conditions, and transmitting the planting condition information to a data processing system; and collecting plant features of the plant and transmitting the plant features to a data processing system;
  • the classifying and marking step includes: classifying, based on the planting information and the environmental information, in the data processing system, and classifying the plant characteristics based on the planting devices according to preset conditions under the same category, and Comparing the plant feature scores of the plurality of planting devices, marking the planting condition information in the plant growth cycle of the planting device with high plant feature score, and storing the labeled under each category related to the plant growth cycle Planting condition information,
  • the adjusting step comprises: comparing the current planting condition information with the stored labeled planting condition information according to planting information and environmental information of each planting device, and in the case that the difference between the former and the latter exceeds a threshold value, according to the storage
  • the planting condition information and the current planting condition information are generated, and the regulation data is generated; and the regulation data is sent to each planting device to regulate the planting conditions of the respective planting devices.
  • an intelligent planting apparatus for controlling a planting process of a plurality of planting devices placed in different environments, the planting device comprising a data collecting device, a sorting and marking device, and regulation Device, where:
  • the data collecting device collects planting information of the plant and environmental information of the planting device, collects at least one planting condition information of the plurality of planting conditions at predetermined time intervals, and collects plant characteristics of the plant, and collects the collected
  • the information obtained is transmitted to the classification and marking device;
  • the classification and marking device classifies the received information based on the planting information and the environmental information, and scores based on the plant characteristics of each planting device according to preset conditions under the same category, and multiple The plant feature scores of the planting device are compared, and the planting condition information of the planting device with high plant feature score is marked in the plant growth cycle, and the labeled planting condition information under each category related to the plant growth cycle is stored. ,
  • the regulating device compares current planting condition information with stored labeled planting condition information according to planting information and environmental information of each planting device, and if the difference between the former and the latter exceeds a threshold value, according to the stored Mark planting conditions information and when Pre-planting condition information, generating regulation data, and transmitting the regulation data to each planting device to regulate the planting conditions of each planting device.
  • an intelligent planting apparatus including a client, a star network composed of a plurality of star network units, and a closed loop optimization platform, wherein
  • the client connects to the closed-loop optimization platform via the Internet to obtain information such as an early warning, a current planting situation, and can manually control each star network unit through a closed-loop optimization platform.
  • the star network unit and the closed-loop optimization platform are connected through the Internet, and each of the star network units includes a measuring device, a control device and an internet access module, wherein the measuring device measures environmental information and planting condition information of the plant planting device, and then measures The information data is transmitted to the access module, and the access module submits the information data to the closed-loop optimization platform via the Internet, and receives regulation data from the closed-loop optimization platform, and the control device is configured according to the regulation data. Controlling the planting conditions of the planting device,
  • the closed-loop optimization platform accepts information data from each star network unit, classifies the received information based on the planting information and the environmental information, and according to preset conditions, based on the respective planting devices.
  • the plant characteristics are scored, and the plant feature scores of the plurality of planting devices are compared, and the planting condition information of the planting device with high plant feature score is marked in the plant growth cycle, and each of the plant growth cycles is stored.
  • the closed-loop optimization platform compares current planting condition information with stored labeled planting condition information according to planting information and environmental information of each planting device, and when the difference between the former and the latter exceeds a threshold, according to the stored
  • the regulation data is generated by marking the planting condition information and the current planting condition information, and the regulation data is sent to each of the star network units to regulate the planting conditions of the planting devices of the respective star network units.
  • the invention is characterized in that it can be applied to large-scale distributed planting, and based on big data analysis, an intelligent optimization closed loop that is automatically executed is established. Therefore, the present invention can perform learning adjustment according to a specific planting environment, and has self-optimizing ability.
  • the invention solves the management complexity problem of large-scale distributed home planting under the premise of fully considering the urban environment, greatly reduces the personnel management and learning cost, and helps The people who lack the experience of planting can get good planting income and realize the large-scale distributed ecological agriculture of the city.
  • FIG. 1A to 1C are schematic views showing planting data collection according to an embodiment of the present invention, wherein FIG. 1A shows data confirmed by user input, FIG. 1B shows data acquired by networking, and FIG. 1C shows monitoring by sensor Data obtained;
  • Figure 2 shows that the planting data is classified and stored according to dimensions
  • FIG. 3A to 3E illustrate an evaluation model according to an embodiment of the present invention, wherein FIG. 3A illustrates a principle of creation of a model, FIG. 3B illustrates a planting evaluation index, and FIG. 3C illustrates a method for judging the rationality of the model. 3D shows abnormal data cleaning, and FIG. 3E shows an evaluation formula;
  • FIG. 4 is a diagram showing smart planting in accordance with one embodiment of the present invention.
  • FIG. 5 is a structural diagram showing the composition of a star network unit (for example, a home star network) according to an embodiment of the present invention
  • FIG. 6 is a schematic view showing the overall configuration of an intelligent planting system according to an embodiment of the present invention.
  • FIG. 7 is a schematic diagram showing an embodiment of a closed loop optimization platform in accordance with one embodiment of the present invention.
  • the intelligent planting management system of the present invention includes a data collection device, a classification and marking device, and a control device, respectively performing data collection operations, classification and marking operations, and control operations.
  • FIG. 1A-1C show schematic diagrams of planting data collection in accordance with one embodiment of the present invention.
  • the data collection method includes a user input confirmation mode (FIG. 1A), a networked acquisition mode (FIG. 1B), and a sensor monitoring mode (FIG. 1C).
  • plant Planting information From the nature of plant data, the data that needs to be collected can be divided into four categories: plant Planting information, environmental information about the planting device, planting condition information, and plant characteristics of the plants collected.
  • Plant planting information includes plant species, planting area, planting time and soil information.
  • soil information includes soil substrate type, base fertilizer type, soil matrix and base fertilizer mixing ratio, soil pH and soil conductivity. These planting information can be obtained by user input and measurement device detection.
  • Plant varieties may also include data on specific plant species, such as the distribution characteristics of the plant (eg, whether it is usually distributed in temperate or tropical regions), the morphology of the plant (including roots, stems, leaves, fruits, etc.) Morphology), the plant's required light characteristics, moisture characteristics, temperature characteristics, fertility requirements, common pests and diseases of the plant, and the like. And this part of the information data is obtained via the network based on the plant variety input by the user using the search technology.
  • distribution characteristics of the plant eg, whether it is usually distributed in temperate or tropical regions
  • the morphology of the plant including roots, stems, leaves, fruits, etc.
  • Morphology the plant's required light characteristics, moisture characteristics, temperature characteristics, fertility requirements, common pests and diseases of the plant, and the like.
  • this part of the information data is obtained via the network based on the plant variety input by the user using the search technology.
  • the above plant planting information can be collected at the beginning of planting, and does not need to be monitored at any time.
  • the environmental information data includes address information and location information.
  • the address information therein such as the residential area information of the house where the planting device is located.
  • the location information includes: in the case where the planting device is indoors, the floor on which the house is located, whether the planting device is placed in the room or closed balcony, the orientation of the room or closed balcony, the lighting of the window; or the case where the planting device is outdoors Next, the planting device is located in the courtyard, on the terrace, on the roof or on the open balcony. These environmental information can be obtained through user input. These planting environment information can be collected at the beginning of planting and does not need to be monitored at any time.
  • planting environment information may also include weather-like information, such as temperature information at the geographic location every day (eg, hourly temperature, highest temperature and lowest temperature per day, etc.), wind information, sunshine information, wind and snow fog, and the like. These environmental information are periodically acquired via the network based on the address information input by the user.
  • weather-like information such as temperature information at the geographic location every day (eg, hourly temperature, highest temperature and lowest temperature per day, etc.), wind information, sunshine information, wind and snow fog, and the like.
  • Planting conditions include rainfall, air conditions, soil conditions and lighting conditions.
  • Air conditions may include: air temperature, air humidity, ventilation, oxygen content Amount, carbon dioxide content, harmful gas content and respirable particulate matter.
  • harmful gases refer to formaldehyde, benzene, hydrazine, ammonia, volatile organic compounds and sulfur dioxide.
  • Respirable particulate matter refers to PM10, PM2.5, or both PM10 and PM2.5.
  • the soil conditions are selected from one or more of the following groups: soil pH, soil conductivity, soil temperature, and soil moisture.
  • the lighting conditions are selected from one or more of the following groups: light intensity and duration of illumination.
  • Information about these planting conditions can be obtained by various measuring devices, the measuring operation can be performed at a predetermined timing, or at predetermined time intervals, or the measured starting time can be set in other manners.
  • Plant characteristics include planting process information and harvesting plant characteristics.
  • the planting process information includes at least: germination success rate, which is based on germination number and planting area; when germination is used, it is based on germination deadline and sowing time; leaf growth health; disease, pest condition; and plant seedling height and leaf area.
  • These planting process information is obtained by user input and/or measuring equipment, for example by taking pictures and analyzing the pictures.
  • the obtaining operation of the planting process information may be performed at a predetermined timing, or at a predetermined time interval, or the starting timing of the operation may be set in other manners.
  • Harvested plant characteristics include at least: harvesting per unit of planted area; amount of fruit per unit of planted area; flowering period of the plant; and subjective evaluation of the grower, including self-evaluation of the growth process, self-evaluation of the harvest, fruit/leaf/ Evaluation of the taste of the rhizome and evaluation of the ornamental plants. These harvested plant features are obtained by user input and/or measurement equipment, such as by taking a picture and analyzing the picture.
  • the means for collecting the above two plant characteristics may further include taking a photo or a video or the like.
  • the collected planting data must be classified and stored according to a specific dimension.
  • These dimensions include, but are not limited to, address information dimensions, planting environment information, planting information, etc., see Figure 2.
  • Planting was carried out in the residence of the “Tiantongyuan” community in Beijing.
  • the planting device was placed in an indoor enclosed balcony.
  • the same soil ratio was used to grow coriander in early April, and the data in the growth cycle was used as a data set under one dimension.
  • 40 households planted coriander in the home so the planting situation was limited to the 40 people's planting data collection (as a category). If only one household has grown coriander in this dimension in the same period, and the planting data in the same area is too small, the data of similar conditions (adjacent areas or similar dimensions) are searched for the same classification, and the post-planting condition data is preferred for comparison.
  • Beijing “Huilongguan” community is a similar community of “Tiantongyuan” community because of its geographical proximity.
  • the “Huilongguan” community used the same soil ratio to grow coriander data collection in the indoor closed balcony in early April, as a similar condition.
  • the data collection is categorized. That is to say, when Tiantongyuan has a small amount of data, the data of the adjacent area can be selected for consolidation processing as the same classification.
  • the recent data is preferred in the later stage, it is preferable to compare it in the same type of data.
  • FIG. 3A to 3E illustrate an evaluation model according to an embodiment of the present invention, wherein FIG. 3A illustrates a principle of creation of a model, FIG. 3B illustrates a planting evaluation index, and FIG. 3C illustrates a method for judging the rationality of the model. 3D shows abnormal data cleaning, and FIG. 3E shows evaluation formula.
  • suitable planting conditions e.g., temperature, humidity, soil conditions
  • plant characteristics e.g., seedling height, harvested fruit, fruit/leaf/roots, etc.
  • the harvest of the plant is determined by the planting process, and the two are in a positive relationship. This is the basic principle of the entire evaluation model.
  • the present invention proposes to select plants with high scores by planting (including planting process information and harvesting plant characteristics) or scoring analysis, and collecting the plants obtained during the planting process.
  • Conditional data tagging As a preferred data
  • the planting condition data is marked to guide a new round of planting.
  • the relationship between planting conditions and plant characteristics When determining the relationship between planting conditions and plant characteristics, the following relationship can be considered: whether the influence of each planting process on the result is an additive relationship, a multiple relationship (ie, a multiplication relationship), or other relationship. The manner in which each sub-process affects the harvesting of plant characteristics.
  • the present invention proposes a new method of data acquisition or selection, that is, data evaluation of plant planting processes and harvesting conditions after analysis and processing based on a large amount of planting data.
  • plant characteristics fall into two broad categories: planting process information and harvesting plant characteristics.
  • planting process information and harvesting plant characteristics.
  • the two plant features are combined for scoring.
  • the measured growth physiological indexes include photosynthetic rate, chlorophyll content, leaf water potential, stomatal conductance, and leaf area.
  • the amount of plant growth can be expressed by the fresh weight, dry weight, length, area and diameter of the plant organs.
  • the amount of plant growth is the amount of growth accumulation, which is the actual amount of plant material at the time of measurement, which is equivalent to the plant's long phase.
  • the growth rate is the growth rate, which is equivalent to the growth of the plant, and has two expressions of absolute growth rate and relative growth rate.
  • the relative growth amount indicates the percentage of the net increase in biomass of the plant to the pre-treatment biomass within a certain period of time.
  • the measurement of traditional growth is often measured in the laboratory based on the measurement of fresh weight, dry weight, length, etc. after picking.
  • the determination of photosynthetic rate and chlorophyll content can only be determined in a laboratory environment.
  • the above indicators are targeted at the plant itself.
  • the planting process is standardized, streamlined, and the factory accumulates a large amount of data and lays a good foundation.
  • FIG. 3B shows the contents of the planting evaluation, including planting process evaluation, planting harvest evaluation, and subjective evaluation.
  • the planting process involves the sowing process, the plant growth process and the planting management process. These processes were separately evaluated in this embodiment.
  • the sowing process mainly involves germination, and the planting density (germination success rate) or the germination time can be selected as a parameter index for evaluation. These two indicators were used to evaluate the maturity of the sowing and seedling process.
  • Planting density (germination success rate) number of germination / planting area
  • the photos of the known germination time + 3 days were extracted and the number of germinations was calculated by image processing.
  • the planting area is the user confirmation data and is obtained by user input.
  • Proper planting density can be compared to historical data or recognized data. Excessive planting density affects the normal growth and development of plants, and the planting density is too small, which will affect the final harvest results.
  • Germination time germination deadline - sowing time
  • the cut-off time for planting germination was obtained by extracting a photograph of the germination duration + 3 days after sowing, and the date when no large number of sprouts appeared was used as the germination deadline.
  • plant seedling height and leaf size can be considered at the same growth time. This situation is judged by detecting picture data during planting.
  • the planting management process includes watering management, temperature control management, pest management, and interplanting and pollination management. The evaluation contents of each management process will be described in detail below.
  • watering should also consider the location of the planting device. For plants under direct sunlight, the amount of water should be large in the morning, otherwise the water will evaporate in less afternoons.
  • the temperature requirements of different stages of the plant are different.
  • the suitable temperature for sowing seeds of watermelon seeds is 20-25 degrees, and the growth temperature is 15-35 degrees. Therefore, temperature control should take into account the different needs of different stages of the plant.
  • the planting harvest characteristics refer to the harvest within a unit area of the picking period.
  • the amount of picking can be confirmed by picture comparison, and/or can be entered into the system by the user.
  • the planting harvest characteristics refer to the amount of results per unit area.
  • the amount of picking can be confirmed by picture comparison, and/or can be entered into the system by the user.
  • the planting harvest characteristics refer to the flowering period.
  • the flowering time and duration can be confirmed by comparing the pictures at different times.
  • Subjective evaluation is a self-subjective evaluation of plant growers, including: self-evaluation of the growth process, self-evaluation of the harvest, fruit/leaf taste evaluation, and/or evaluation of ornamental plants.
  • the taste score has a one-vote veto. This is because we are pursuing health and safety, not just production. For vegetables and fruits, the taste is far better than the importance of production.
  • Step 1 Pick a data set of the same/similar dimensions.
  • Step 2. Evaluate the seeding and seedling process during planting.
  • Step 3. Evaluate the growth process using growth process indicators.
  • Step 4. Use the management process indicators to evaluate the management process.
  • Step 5. Use species Plant harvesting indicators are used to evaluate harvest conditions.
  • Step 6. Compare the relevant process evaluations in the previous better planting data item by item and record the comparison results.
  • Step 7. After the indicator evaluation is completed, the overall score of the planting process is obtained by integrating the various processes and their indicators with different weighting values.
  • Step 8. Select better planting data and fit the curve of each monitoring item with the previous better planting data.
  • Step 9. The difference in value at the same time point is derived. See if the trend is consistent and whether the difference exceeds the preset value.
  • Step 11 Curve fitting with each monitoring data of the planting expert planting process during the same period (concurrent with the plant growth process).
  • Step 12. The difference in value at the same time point is derived. See if the trend is consistent and whether the difference exceeds the preset value.
  • Step 13. Find inconsistencies or markers that exceed the preset value as mutation data.
  • Step 14. If the same data is twice marked as mutated data, notify the system planting expert to perform manual intervention.
  • Step 15. Referring to the user's self-subjective evaluation, select the data with high scores for each process and comprehensive evaluation.
  • Step 16. Select the preferred planting data to add the version and add the preferred planting model.
  • Steps 8 to 14 above are the abnormal data cleaning steps, and the following describes the cleaning of the abnormal data.
  • the anomaly data is cleaned in two ways: compared to the concurrent planting expert process data, and compared to the prior preferred data.
  • Curve fitting was performed with each monitoring data of the planting expert cultivation process during the same period. At the same time point value difference, seeking. See if the trend is consistent and whether the difference exceeds the preset value. Marks that are found to be inconsistent or exceed the preset value are mutated data.
  • Process data that is twice labeled as mutated data will be removed from the preferred data set and notified to the system implant specialist for manual analysis, research, and intervention.
  • the evaluation formula is based on plant process characteristics and plant harvesting characteristics. In the embodiment of the present invention, as shown in FIG. 3E, the following evaluation formula is selected:
  • the weight of each process and indicator is confirmed.
  • the weight value determines the ability of each process and indicator to influence the outcome and outcome.
  • the regulatory operation is to guide the implementation of the planting using planting condition data corresponding to better plant characteristics. Regulation can be performed for one or more growing conditions.
  • Step 1 Monitor the temperature of the current planting environment (soil temperature and air temperature) every hour and upload it to the closed-loop optimization platform through the access module.
  • Step 2 The closed-loop optimization platform uses the preferred data for comparison to determine if the temperature deviates from the threshold.
  • Step 3 If there is no deviation from the threshold, end.
  • Step 4 If the threshold is deviated, the relevant regulatory information is produced, such as the regulated temperature reaches a certain value.
  • Step 5 The control system queries the access module to check whether there is regulation information.
  • Step 6 The control system downloads and obtains the regulation information, and notifies the monitoring module to adjust the temperature monitoring frequency, such as once every 5 minutes.
  • Step 7 Adjust the temperature according to the regulation information. If it is over, the water spray will cool down or shade, and if it is lower, it will heat up and raise the temperature.
  • Step 8 The monitoring module periodically transmits the temperature change to the control system.
  • Step 9 The control system compares the control objectives and determines whether the temperature control target is reached.
  • Step 10 When it is reached, stop regulation. Upload the control results to the closed-loop optimization platform. If it is not reached, continue to regulate.
  • Step 1 Monitor the humidity of the current planting environment (soil moisture and air every 4 hours) Humidity) is uploaded to the closed-loop optimization platform through the access module.
  • Step 2 The closed-loop optimization platform uses the preferred data for comparison to determine if the humidity deviates from the threshold.
  • Step 3 If there is no deviation from the threshold, end.
  • Step 4 If the threshold is deviated, production related regulatory information, such as humidity, reaches a certain value.
  • Step 5 The control system queries the access module to check whether there is regulation information.
  • Step 6 The control system downloads and obtains the regulation information, and notifies the monitoring module to adjust the humidity monitoring frequency, such as monitoring once in 30 seconds.
  • Step 7 Watering irrigation according to regulation and control information.
  • Step 8 The monitoring module periodically transmits the humidity change to the control system.
  • Step 9 The control system compares the control objectives and determines whether the humidity control target is reached.
  • Step 10 When it is reached, stop regulation. Upload the control results to the closed-loop optimization platform. If it is not reached, continue to regulate.
  • Step 1 Monitor the light intensity of the current planting environment every hour and upload it to the closed-loop optimization platform through the access module.
  • Step 2 The closed-loop optimization platform uses the preferred data for comparison to determine if the illumination intensity deviates from the threshold.
  • Step 3 If there is no deviation from the threshold, then it ends.
  • Step 4 If the threshold is deviated, the relevant regulation information is produced, for example, 2 hours of sunshade or LED fill light to a specified amount of illumination.
  • Step 5 The control system queries the access module to check whether there is regulation information.
  • Step 6 The control system downloads and obtains the regulation information, and notifies the monitoring module to adjust the frequency of the illumination monitoring, such as once every 30 minutes.
  • Step 7 LED fill light / shading treatment.
  • Step 8 The monitoring module periodically transmits the illumination intensity change and the illumination duration to the control system.
  • Step 9 The control system compares the control targets and determines whether the light control target is achieved.
  • Step 10 When it is reached, stop regulation. Upload the control results to the closed-loop optimization platform. If it is not reached, continue to regulate.
  • the soil fertility level is expressed by detecting soil conductivity.
  • Step 1 Monitor the soil conductivity of the current planting environment and upload it to the closed-loop optimization platform through the access module.
  • Step 2 The platform determines whether regulation is needed based on the current growth stage of the plant, the last detection time, and the current soil conductivity.
  • Step 3 If regulation is needed, generate regulatory information, such as how much liquid fertilizer is added to the water to adjust the soil conductivity.
  • Step 4 The control system queries the access module to check whether there is regulation information.
  • Step 5 The control system downloads and obtains the regulation information, and notifies the monitoring module to adjust the soil conductivity monitoring frequency.
  • Step 7 Mix liquid fertilizer and water according to regulatory information.
  • Step 8 When watering the next time, the fertilizer and water are watered together.
  • Step 9 The monitoring module periodically sends the soil conductivity level to the control system.
  • Step 1 Provide the corresponding pest and disease biological preparation according to the user's planting variety, and the user joins the control equipment.
  • Step 2. Monitor and obtain the picture of the pest situation in the current planting environment, and upload it to the closed-loop optimization platform through the access module.
  • Step 3 The platform identifies through image processing to confirm the occurrence of pests and generate regulatory information.
  • Step 4 The control system queries the access module to check whether there is regulation information.
  • Step 5 The control system downloads and obtains the regulation information.
  • Step 6 Mix the insecticide and water according to the regulatory information.
  • Step 7. Spray with water the next time you water it.
  • Step 8 This control measure is continuously implemented for a specified number of days, for example once a day.
  • the specific regulation time interval can be set by the user.
  • Step 9 After the specified number of days, the monitoring module uploads the picture of the pest condition to the platform, and compares the previous photos to determine the effect.
  • Step 10 If the effect is not obvious, the warning informs the user to take manual intervention.
  • the intelligent planting system of the present invention is described in detail above, and the following describes an embodiment of the smart planting apparatus of the present invention using the intelligent planting system.
  • the entire system can be powered by batteries, solar/wind and power.
  • the intelligent planting device is generally composed of a smart home star network (including a plurality of star network units), an intelligent closed-loop optimization platform, and a client.
  • the system provides four different implementation modes: expert mode, assistant mode, follow mode, and white mode.
  • the expert mode In the expert mode, 1-N environmental monitoring modules, 0-N control systems and one access module are deployed.
  • the expert mode gives the user complete control, and the experts independently control all aspects of the planting process.
  • the system is only responsible for reminders and warnings.
  • the environmental parameters When the environmental parameters are abnormal, for example, if the watering is forgotten for several consecutive days, the system alerts the expert user through the client warning, and the expert user handles it by himself.
  • Expert users can choose to configure the control system or choose not to configure the control system.
  • planting management can be remotely controlled by the client.
  • the closed-loop optimization platform records the entire planting process, saves relevant planting data and evaluates it.
  • the assistant mode In the assistant mode, 1-N environmental monitoring modules, 1-N control systems and one access module are deployed.
  • the assistant mode provides a personal assistant service for busy planters or users. The user's entire planting process is still dominated by autonomous control, and the system provides early warning reminders and occasional regulation. On weekdays, users are responsible for planting management, such as watering and fertilizing. When the user forgets to operate or the planting indicator deviates from the threshold, the system first issues an alert to remind the user. If the user does not actively control the specified time, the system automatically adjusts and notifies the user.
  • 1-N environmental monitoring modules, 1-N control systems and one access module are deployed.
  • the user selects a trusted expert user who is similar to his own planting environment through the client and grows the same planting variety as the expert user.
  • the entire planting process except for some work that must be done manually (such as sowing, pruning, harvesting, etc.) Operations such as watering, fertilizing, fill light, ventilation, etc., all automatically operate according to the data of the experts followed.
  • This method is a process in which a user follows an expert to learn to plant. In the process, the user can use the client to communicate and discuss with the expert users who follow. Users can also backtrack, mark, and add experience to the planting process data through the client.
  • 1-N environmental monitoring modules In the white mode, 1-N environmental monitoring modules, 1-N control systems and one access module are deployed. During the whole planting process, except for some work that must be manually operated, such as sowing, pruning, harvesting, etc., other operations such as watering, fertilizing, light filling, ventilation, etc. are all automatically operated according to the preferred planting data of the system. Minimize the operation of the white user.
  • Step 1 The planting user inputs the relevant user confirmation information into the closed-loop optimization model, including planting information, geographical location information, and environmental information.
  • Step 2 The monitoring module monitors plant related information and sends it to the access module and the remote control module.
  • Step 3 The access module is responsible for accessing the Internet and transmitting the information to the closed-loop optimization model.
  • Step 4 Through the access module, the remote control module sends an inquiry about whether the regulation needs to be sent to the closed-loop optimization model.
  • Step 5 The closed-loop optimization model determines whether regulation is needed based on information such as monitoring information, plant-related information, and previous regulation.
  • Step 6 If necessary, the closed-loop optimization model generates control information and transmits it to the remote control module through the access module.
  • Step 7 The remote control module adjusts the planting conditions according to the regulation information, such as watering, fertilizing, and the like.
  • Step 8 During the regulation process, the monitoring module transmits relevant information changes to the remote control module at any time.
  • Step 9 The remote control module determines whether the control target is reached. Step 10: If the control target is reached, the regulation is stopped, and the control result is transmitted to the closed-loop optimization model through the access module.
  • a satellite network unit includes three parts: an environmental monitoring, a control system, and an Internet access, and each part is connected through a low-power wireless network.
  • an environmental monitoring In one star network unit, 0 to N remote control, and 1 internet access.
  • the data collection device and the conditioning device are disposed in a separate planting environment (e.g., individual households).
  • this part can also be collectively referred to as a smart home star network, including an environment monitoring module, a control system, and an access module.
  • the access module submits data over the Internet to an intelligent closed-loop optimization platform (described below) and receives regulatory data from the intelligent closed-loop optimization platform.
  • the access module transmits regulatory data to the control system via a low-power wireless connection.
  • the control system performs watering, fill/shading, oxygen/CO 2 reduction, temperature rise, temperature rise, fertilization, ventilation, and de-worming according to the control data, and compares the environmental monitoring data in real time to see if the control target is achieved.
  • the wireless transmission module can self-organize the network and transmit the monitoring data to the control module and the access module.
  • the measuring device includes various corresponding sensors, and then the measured information data can be transmitted or uploaded to the access module through the low-power wireless transmission module, and the access module is responsible for transmitting to the closed-loop optimization platform, for example, to the closed loop described below. Optimized in the platform.
  • the monitoring module can acquire data at a specified frequency or time interval and upload it through the access module. For example, temperature, humidity, pictures, etc. upload data in hours.
  • each user internally forms a star network unit.
  • the star network unit and the closed-loop optimization platform are connected via the Internet.
  • the client connects to the closed-loop optimization platform via the Internet to obtain information such as early warning and current planting conditions, and can be optimized through closed loop.
  • the platform manually controls the authorized satellite network unit.
  • the information input by the user may also include: a default watering time period, and the like. This user-entered operation can be confirmed and directly entered by the client at the start of planting, and the entered information data can be transmitted or uploaded, for example, to the closed-loop optimization platform described below.
  • Figure 7 shows an implementation of an intelligent closed-loop optimization platform that illustrates how a closed-loop optimization platform forms a closed-loop overall process, and how to guide the planting process in a closed loop.
  • the classification and labeling module and the control module are all set in the intelligent closed-loop optimization platform.
  • the intelligent closed-loop optimization service platform (referred to as the closed-loop optimization platform) matches and selects more optimized environment comparison data and possible participation adjustments according to the environmental data (optional). Generate control data and transmit access modules over the Internet.
  • the control module is set in the intelligent closed-loop optimization platform, and the use is more Excellent planting data guides planting.
  • the closed-loop optimization platform At the beginning of the establishment of the closed-loop optimization platform, various known upper and lower limit data such as illumination and temperature are set according to the plant species, and the control data is sequentially fed back. A large amount of user input information and environmental monitoring data during the growth cycle were obtained during the first planting process. At the time of harvest, users are encouraged to use the client (WeChat/Mobile APP/PC, etc.) to take photos to share the harvest or use the system's video monitoring information. According to the user's planting area and harvest pictures, the closed-loop optimization platform performs analysis and quantification. The quantified data were compared to determine better planting data under the same environmental data, and used as the next round of regulatory guidance data. This process is automatically cycled and optimized step by step.
  • the data can be fine-tuned by agricultural experts if needed. Or select the planting data of a specific expert under the same environmental data as a comparison.
  • the environmental data, planting process and harvesting conditions are taken as input, and the machine learning algorithm is used to classify and optimize, and a better planting data model is obtained.
  • Step 7 After the user confirms the planting area and planting variety, the system determines whether there is relevant preferred planting data (planting data includes relevant data for each stage of the entire plant growth cycle). Step 2. If there is no way to turn to the expert. Step 3. If yes, use the preferred data and turn to the white mode. Step 4. Record relevant data for each stage of the plant growth cycle. Step 5. At the time of harvest, comprehensive evaluation by user picture sharing, experience sharing, self-evaluation, other people's evaluation, video monitoring information, etc. Step 6. Sort, classify, analyze, and evaluate the collected large amount of data using machine learning algorithms. Get more professional planting experts and more preferred planting data. In this process, some system user interventions can also be selected to make the selection algorithm converge more quickly. Step 7. Update the data of the closed-loop optimization model. Then when more users are planting, the system returns to step 3.
  • the closed-loop optimization platform mainly includes two functions: using better planting data to guide planting (control processing), and selecting better planting data (classification and evaluation processing) from the collected planting data.
  • the content of the invention includes the following aspects:
  • An intelligent planting management method for multiple placement in different environments The planting process in the planting device is controlled, the method comprising a data collection step, a classification and labeling step, and a regulating step, wherein:
  • the data collection step includes:
  • the sorting and marking steps include:
  • classification is performed based on the planting information and the environmental information, and under the same category, the plant characteristics based on the planting devices are scored according to preset conditions, and the plurality of planting devices are The plant characteristic scores are compared, the planting condition information of the planting feature with high plant feature score is marked in the plant growth cycle, and the labeled planting condition information under each category related to the plant growth cycle is stored,
  • the regulating steps include:
  • the current planting condition information is compared with the stored labeled planting condition information, and if the difference between the former and the latter exceeds the threshold value, the stored labeled planting condition information is used. And current planting condition information to generate regulatory data;
  • the regulation data is sent to each planting device to regulate the planting conditions of the respective planting devices.
  • the sorting and marking steps include:
  • the regulatory data is obtained based at least on one of: stored labeled planting condition information, time of the last regulatory operation, last adjusted amount, and threshold.
  • comparing the current planting condition information with the stored tagged planting condition information in the regulating step comprises:
  • the current planting condition information is fitted with the expert planting condition information of the same or similar planting time, and the difference is obtained at the same time point, and the current planting is performed if the change trend is inconsistent or the difference exceeds the preset value.
  • Condition information is marked as mutation data.
  • comparing the current planting condition information with the stored tagged planting condition information in the regulating step comprises:
  • the current planting condition information is fitted to the same or similar planting time by the labeled planting condition information, and the difference is obtained at the same time point value, and if the change trend is inconsistent or the difference exceeds the preset value, The current planting condition information is marked as mutation data.
  • Location information based on information about the house in which the plant is located including:
  • the floor where the house is located whether the planting device is placed in the room or closed balcony, the orientation of the room or closed balcony, the window lighting; or
  • the planting device is outdoors, the planting device is located in a courtyard, terrace, roof or open balcony.
  • the soil information includes a soil substrate type, a base fertilizer type, a soil base and a base fertilizer mixing ratio, a soil pH, and a soil conductivity.
  • planting process information includes one or more of the following groups:
  • Germination success rate based on the number of germination and planting area
  • Management process information including watering management, temperature control management, pest management, and inter-plant pruning management.
  • the subjective evaluation of the grower includes self-evaluation of the growth process, self-evaluation of the harvest, evaluation of the taste of the fruit/leaf, and evaluation of the ornamental plants.
  • illumination condition is selected from one or more of the group consisting of: light intensity and duration of illumination.
  • regulating operation is selected from one or more of the group consisting of watering, filling light, shading, supplementing oxygen, supplementing carbon dioxide, and reducing Temperature, elevated temperature, fertilization, increased ventilation, reduced ventilation, spraying insecticides, spraying insecticide prevention agents.
  • An intelligent planting apparatus for controlling a planting process of a plurality of planting devices placed in different environments, the smart planting device comprising a data collecting device, a sorting and marking device, and a regulating device, wherein:
  • the data collecting device collects planting information of the plant and environmental information of the planting device, collects at least one planting condition information of the plurality of planting conditions at predetermined time intervals, and collects plant characteristics of the plant, and collects the collected The information obtained is transferred to the points Class and marking device;
  • the classification and marking device classifies the received information based on the planting information and the environmental information, and scores based on the plant characteristics of each planting device according to preset conditions under the same category, and multiple The plant feature scores of the planting device are compared, and the planting condition information of the planting device with high plant feature score is marked in the plant growth cycle, and the labeled planting condition information under each category related to the plant growth cycle is stored. ,
  • the regulating device compares current planting condition information with stored labeled planting condition information according to planting information and environmental information of each planting device, and if the difference between the former and the latter exceeds a threshold value, according to the stored The planting condition information and the current planting condition information are marked, the regulation data is generated, and the regulation data is sent to each planting device to regulate the planting conditions of the respective planting devices.
  • the sorting and marking device is scored under the same category, according to preset conditions, based on the planting process information of each planting device, and the harvested plant features.
  • the regulatory data is obtained based at least on one of: stored labeled planting condition information, time of the last regulatory operation, last adjusted amount, and threshold.
  • the current planting condition information is fitted with the expert planting condition information of the same or similar planting time, and the difference is obtained at the same time point, and the current planting is performed if the change trend is inconsistent or the difference exceeds the preset value.
  • Condition information is marked as mutation data.
  • the intelligent planting apparatus of (28), wherein comparing the current planting condition information with the stored tagged planting condition information comprises:
  • the current planting condition information is fitted to the same or similar planting time by the labeled planting condition information, and the difference is obtained at the same time point value, and if the change trend is inconsistent or the difference exceeds the preset value, The current planting condition information is marked as mutation data.
  • Location information based on information about the house in which the plant is located including:
  • the floor where the house is located whether the planting device is placed in the room or closed balcony, the orientation of the room or closed balcony, the window lighting; or
  • the planting device is outdoors, the planting device is located in a courtyard, terrace, roof or open balcony.
  • the intelligent planting apparatus according to (23), wherein the planting information of the plant includes plant variety, planting area, planting time, and soil information.
  • planting process information comprises one or more of the following groups:
  • Germination success rate based on the number of germination and planting area
  • Management process information including watering management, temperature control management, pest management, and inter-plant pruning management.
  • the subjective evaluation of the grower includes self-evaluation of the growth process, self-evaluation of the harvest, evaluation of the taste of the fruit/leaf, and evaluation of the ornamental plants.
  • planting conditions include rainfall, air conditions, soil conditions, and lighting conditions.
  • air condition is selected from one or more of the group consisting of: air temperature, air humidity, ventilation, oxygen content, carbon dioxide content, and harmful Gas content and respirable particulate matter.
  • illumination condition is selected from one or more of the group consisting of: light intensity and duration of illumination.
  • the intelligent planting apparatus wherein the regulating operation is selected from one or more of the group consisting of: watering, filling light, shading, supplementing oxygen, replenishing carbon dioxide, lowering temperature Increase temperature, fertilize, increase ventilation, reduce ventilation, spray insecticides, and spray insecticide prevention agents.
  • An intelligent planting device comprising a client, a star network composed of a plurality of star network units, and a closed loop optimization platform, wherein
  • the client connects to the closed-loop optimization platform via the Internet to obtain information such as an early warning, a current planting situation, and can manually control each star network unit through a closed-loop optimization platform.
  • the star network unit and the closed-loop optimization platform are connected through the Internet, and each of the star network units includes a measuring device, a control device and an internet access module, wherein the measuring device measures environmental information and planting condition information of the plant planting device, and then measures The information data is transmitted to the access module, and the access module submits the information data to the closed-loop optimization platform via the Internet, and receives regulation data from the closed-loop optimization platform, and the control device is configured according to the regulation data. Controlling the planting conditions of the planting device,
  • the closed-loop optimization platform accepts information data from each star network unit, classifies the received information based on the planting information and the environmental information, and according to preset conditions, based on the respective planting devices.
  • the plant characteristics are scored, and the plant feature scores of the plurality of planting devices are compared, and the planting condition information of the planting device with high plant feature score is marked in the plant growth cycle, and each of the plant growth cycles is stored.
  • the closed-loop optimization platform compares current planting condition information with stored labeled planting condition information according to planting information and environmental information of each planting device, and when the difference between the former and the latter exceeds a threshold, according to the stored Generating regulatory data by marking planting condition information and current planting condition information, and transmitting the regulatory data to each
  • the star network unit regulates the planting conditions of the planting devices of the respective star network units.
  • the closed-loop optimization platform is scored under the same category, according to preset conditions, based on the planting process information of each planting device, and the harvested plant features.
  • the regulatory data is obtained based at least on one of: stored labeled planting condition information, time of the last regulatory operation, last adjusted amount, and threshold.
  • comparing the current planting condition information with the stored tagged planting condition information comprises:
  • the current planting condition information is fitted with the expert planting condition information of the same or similar planting time, and the difference is obtained at the same time point, and the current planting is performed if the change trend is inconsistent or the difference exceeds the preset value.
  • Condition information is marked as mutation data.
  • the intelligent planting device wherein the current planting is The comparison of the condition information with the stored marked planting condition information includes:
  • the current planting condition information is fitted to the same or similar planting time by the labeled planting condition information, and the difference is obtained at the same time point value, and if the change trend is inconsistent or the difference exceeds the preset value, The current planting condition information is marked as mutation data.
  • the intelligent planting device according to (45), wherein the environmental information of the planting device comprises:
  • Location information based on information about the house in which the plant is located including:
  • the floor where the house is located whether the planting device is placed in the room or closed balcony, the orientation of the room or closed balcony, the window lighting; or
  • the planting device is outdoors, the planting device is located in a courtyard, terrace, roof or open balcony.
  • the intelligent planting apparatus according to (45), wherein the planting information of the plant includes plant variety, planting area, planting time, and soil information.
  • the intelligent planting apparatus wherein the soil information includes a soil substrate type, a base fertilizer type, a soil base and a base fertilizer mixing ratio, a soil pH, and a soil conductivity.
  • planting process information comprises one or more of the following groups:
  • Germination success rate based on the number of germination and planting area
  • Management process information including watering management, temperature control management, pest management, Interplanting and pruning pollination management.
  • the subjective evaluation of the grower includes self-evaluation of the growth process, self-evaluation of the harvest, evaluation of the taste of the fruit/leaf, and evaluation of the ornamental plants.
  • planting conditions include rainfall, air conditions, soil conditions, and lighting conditions.
  • air condition is selected from one or more of the group consisting of: air temperature, air humidity, ventilation, oxygen content, carbon dioxide content, and harmful Gas content and respirable particulate matter.
  • the intelligent planting device of (59), wherein the illumination condition is selected from one or more of the group consisting of: light intensity and duration of illumination.
  • regulating operation is selected from one or more of the group consisting of: watering, filling light, shading, supplementing oxygen, supplementing carbon dioxide, lowering temperature Increase temperature, fertilize, increase ventilation, reduce ventilation, spray insecticides, and spray insecticide prevention agents.

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Environmental Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Software Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Soil Sciences (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Forests & Forestry (AREA)
  • Ecology (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Botany (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Development Economics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Medical Informatics (AREA)
  • Water Supply & Treatment (AREA)
  • Health & Medical Sciences (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Animal Husbandry (AREA)
  • Mining & Mineral Resources (AREA)
  • General Health & Medical Sciences (AREA)
  • Agronomy & Crop Science (AREA)

Abstract

一种智能种植管理方法和设备,针对多个放置于不同环境的种植装置中的植物种植过程进行控制,包括数据采集、分类及标记以及调控步骤。采集的数据包括:植物的种植信息和种植装置所处环境信息、种植条件信息、植物特征。将所采集数据分类,在同一类别下,按照预设条件,对各种植装置的植物特征进行评分及比较,将植物特征评分高的种植装置在植物生长周期内的各种植条件信息进行标记存储。根据各种植装置的种植信息和环境信息,将当前种植条件信息与存储的经标记种植条件信息比较,二者之差值超过阈值时,依据存储的经标记种植条件信息和当前种植条件信息生成调控数据,以对各种植装置的该种植条件进行调控。

Description

智能种植管理方法和智能种植设备 技术领域
本发明涉及一种智能种植方法和一种智能种植设备,更具体地说,本发明涉及基于互联网的智能种植管理方法和智能种植设备。
背景技术
对植物种植进行智能管理一直是农业领域的关注热点,对此人们进行了多种技术改进和尝试。
最常见的智能种植为自动浇水系统,服务于独立用户。由于没有基于具体的植物品种(喜水植物还是干旱植物)、种植环境(处于南方还是北方,具体采光情况等)进行判断,浇水量和时间间隔全凭粗略的估计。
中国专利申请公开CN102550371A提出了一种基于物联网技术的小区或别墅用自动灌溉控制系统及方法,由控制系统、区域节点、土壤温湿度传感器和喷淋灌溉终端组成。在该技术中,监测温湿度两项指标,并依据温湿度两项指标决定是否浇水。然而,这种技术中每次浇水量的多少均依据预先设置固定的阈值或者进行人工控制,并且没有考虑植物种类、植物生长周期,对于所处环境的情况仅考虑了土壤的水分和温度。
中国专利申请公开CN102868749A提出了一种农业种植、饲养的物联网云服务系统及服务流程方法。其中将种植数据采集后发送至云中心,最后至用户终端。云服务包括:农业资讯、政策法规、信息发布、信息咨询、专家系统、农产品交易、农产品溯源、技术服务、数据挖掘、生产监控、环境监控及终端管理的模块。该技术存在的问题是:其主要是数据感知和信息发布与获取服务,缺少对于种植本身的反馈控制;信息单向流动,即种植数据采集后,发送至用户终端;用户需要服务时主动发起请求获取信息,缺少主动的智能调控能力;数 据感知系统没有考虑植物种类、植物生命周期等信息。
中国专利申请公开CN13155839A提出一种自动浇水施肥系统,检测土壤中的水分和营养物质,如果水分和营养物质的含量降低了,就会自动为土壤进行浇水或施肥。然而,此系统简单地依据预先设定值进行浇水施肥,没有考虑植物种类、植物生命周期,对所处环境仅考虑了土壤水分和肥料水平。
中国专利申请公开CN104012375A提出一种农业自动感知灌溉监控系统,综合考虑环境温度、湿度及季节的变化,自动对植物进行浇灌。其采用了专家知识存储器,其中存储着不同作物不同生长阶段相对应的适宜的生长环境参数。此技术在监测土壤湿度之外,还提出监测植物的生理指标(如叶片温度、茎秆微变化)。然而,此技术仅关注灌溉问题,没有考虑植物所处的生长周期情况。
中国专利申请公开CN104012376A提出一种基于生态环境信息的智能浇花系统、方法及其装置,可以根据花草的生长周期精确控制浇水。然而,此技术仅关注了浇水问题。
中国专利申请公开CN104216373A提出一种基于智能云的家庭水管理系统,用来实现对花卉的自动浇水和对储水器的自动添加。此技术提出了云智能远程控制,通过远程控制端人工控制或依据人工设置的水管理计划进行浇水。然而,关于浇水量的多少是由人工控制或者依据人工设置的水管理计划进行,没有考虑植物的生长周期、所处环境及当前土壤的温湿度情况。此外,此技术仅关注了浇水问题。
中国专利公开CN203490529U(申请号CN201320629665)提出了一种基于物联网的智能种植装置。该文献针对农业大棚提出了一种智能种植装置,其中“通过物联网的形式,可以进行智能化的种植,成熟后还可以进行打包、称重、贴标、全程种植、生产信息可追溯源头”。所说的智能种植是指:通过物联网的方式进行监控,远程控制的方式实现人工种植(见0015段“使用者即可通过控制终端电脑、平板电脑终端或手机终端任意一个设备对种植物进行智能管理和控制”),减少劳动强度,进行食品来源信息管理。然而,此技术中提出的远程控制基于人工,无法满足大规模分布式的种植的智能管理。
中国专利申请公开CN102884932A(申请号CN2012104227706)提出了一种基于种植专家云的智能型土培植物生长栽培系统。具体而言,该文献“提供一种基于种植专家云的智能型土培植物生长栽培系统,包括种植专家云中心、通信网络和一个或多个智能种植装置”,实现“对种植经验信息进行存储和共享”以及“以共享资源的方式实现种植”。种植经验信息提出了土壤ph值、环境光照强度、温度、湿度。然而,此技术中种植的指导数据使用的是预设值。由于城市地理和家庭环境方面存在诸多不同因素,该技术没有考虑这些不同因素,采集上传的经验数据混乱无法实际指导种植。
现代城市的居住环境多种多样,导致人们在居室或户外的种植环境也有很大不同。不同城市气候条件不同,有的城市湿度大有的城市干燥。即使同一城市,在不同地区或居住小区的种植环境也不相同,甚至同一小区内,不同楼层、朝向的种植环境例如光照条件也不相同。
这些现有技术提出的种植指导是基于预设值进行的,显然不能“因材施教”,不能根据具体种植环境进行调整,指导的效果可想而知。
发明内容
基于现有技术存在的上述问题,本发明的目的是实现在不同种植环境下大规模分布式种植的智能管理。进一步,本发明能够解决个人家庭想种却缺乏种植管理经验、难以获得良好收益的问题。此外,本发明还能解决个人家庭想种却没有时间管理的问题。
为了实现上述目的,本发明提出利用互联网、大数据分析、机器学习以及智能家居软硬件技术,构建智能种植系统,建立智能种植星网。
为实现上述目的,根据本发明的一个方面,提供一种智能种植管理方法,其针对多个放置于不同环境下的种植装置中的植物种植过程进行控制,该方法包括数据采集步骤、分类及标记步骤以及调控步骤,其中:
所述数据采集步骤包括:采集植物的种植信息和该种植装置所处的环境信息,并将其传送到数据处理系统;以预定时间间隔,采集 多种种植条件中的至少一种种植条件信息,并将该种植条件信息传送到数据处理系统;以及,采集植物的植物特征,并将该植物特征传送到数据处理系统;
所述分类及标记步骤包括:在数据处理系统中,基于所述种植信息和所述环境信息进行分类,在同一类别下,按照预设条件,基于各个种植装置的所述植物特征进行评分,并将多个种植装置的植物特征评分进行比较,将植物特征评分高的种植装置在植物生长周期内的各个种植条件信息进行标记,以及,存储与该植物生长周期相关的各类别下的经标记的种植条件信息,
所述调控步骤包括:根据各个种植装置的种植信息和环境信息,将当前的种植条件信息与存储的经标记种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,依据存储的经标记种植条件信息和当前种植条件信息,生成调控数据;以及,将该调控数据发送至各个种植装置,以对各个种植装置的该种植条件进行调控操作。
根据本发明的另一方面,提供一种智能种植设备,其对多个放置于不同环境下的种植装置中的植物种植过程进行控制,该智能种植设备包括数据采集装置、分类及标记装置以及调控装置,其中:
所述数据采集装置采集植物的种植信息和该种植装置所处的环境信息,以预定时间间隔采集多种种植条件中的至少一种种植条件信息,以及,采集植物的植物特征,并将所采集到的信息传送到所述分类及标记装置;
所述分类及标记装置基于所述种植信息和所述环境信息将收到的信息进行分类,在同一类别下,按照预设条件,基于各个种植装置的所述植物特征进行评分,并将多个种植装置的植物特征评分进行比较,将植物特征评分高的种植装置在植物生长周期内的各个种植条件信息进行标记,以及,存储与该植物生长周期相关的各类别下的经标记的种植条件信息,
所述调控装置根据各个种植装置的种植信息和环境信息,将当前的种植条件信息与存储的经标记种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,依据存储的经标记种植条件信息和当 前种植条件信息,生成调控数据,以及,将该调控数据发送至各个种植装置,以对各个种植装置的该种植条件进行调控操作。
根据本发明的又一方面,提供一种智能种植设备,包括客户端、由多个星网单元构成的星网、和闭环优化平台,其中,
所述客户端通过互联网连接到所述闭环优化平台,获取预警、当前种植情况等信息,并且可以通过闭环优化平台手工控制各星网单元,
所述星网单元与闭环优化平台通过互联网连接,各星网单元包括测量装置、控制装置和互联网接入模块,其中,所述测量装置测量植物种植装置的环境信息和种植条件信息,然后将测量的信息数据传送给所述接入模块,所述接入模块通过互联网将所述信息数据提交给所述闭环优化平台,并接收来自闭环优化平台的调控数据,所述控制装置根据所述调控数据控制所述种植装置的种植条件,
所述闭环优化平台接受来自各星网单元的信息数据,基于所述种植信息和所述环境信息将收到的信息进行分类,在同一类别下,按照预设条件,基于各个种植装置的所述植物特征进行评分,并将多个种植装置的植物特征评分进行比较,将植物特征评分高的种植装置在植物生长周期内的各个种植条件信息进行标记,以及,存储与该植物生长周期相关的各类别下的经标记的种植条件信息,
所述闭环优化平台根据各个种植装置的种植信息和环境信息,将当前的种植条件信息与存储的经标记种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,依据存储的经标记种植条件信息和当前种植条件信息,生成调控数据,以及,将该调控数据发送至各个星网单元,以对各个星网单元的种植装置的该种植条件进行调控操作。
本发明特点是能够应用于大规模分布式种植,并基于大数据分析,建立起自动执行的智能优化闭环。因此,本发明能够根据具体的种植环境进行学习调整,具备自我优化能力。
本发明在充分考虑城市环境的前提下,解决了大规模的分散型家庭种植的管理复杂性问题,极大的降低了人员管理和学习成本,帮 助缺乏种植经验的人员获得良好的种植收益,使城市大规模分布式生态农业得以实现。
附图说明
下面参考附图进行说明,附图中:
图1A至图1C是示出根据本发明一个实施例的种植数据收集的示意图,其中图1A示出通过用户输入确认的数据,图1B示出通过联网获取的数据,图1C示出通过传感器监测获得的数据;
图2示出将种植数据依据维度进行分类存储;
图3A至图3E示出根据本发明一种实施例的评价模型,其中,图3A示出创建模型的思路原则,图3B示出种植评价指标,图3C示出模型合理性的判断方法,图3D示出异常数据清理,图3E示出评价公式;
图4是示出根据本发明一个实施例的智能种植;
图5是示出根据本发明一个实施例的一个星网单元(例如家庭星网)的组成的结构图;
图6是示出根据本发明一个实施例的智能种植系统整体构成的概略图;以及
图7是示出根据本发明一个实施例的闭环优化平台实施方式的示意图。
具体实施方式
下面参考附图具体说明本发明的具体实施方式。
如前文总体说明的,本发明的智能种植管理系统包括数据采集装置、分类及标记装置、调控装置,分别执行数据采集操作、分类及标记操作、调控操作。
[数据采集操作]
图1A至图1C示出根据本发明一个实施例的种植数据收集的示意图。在本实施例中,数据收集方法包括用户输入确认方式(图1A)、联网获取方式(图1B)、以及传感器监测方式(图1C)。
从植物数据的性质来看,需要采集的数据可以分为四类:植物的 种植信息,该种植装置所处的环境信息,种植条件信息,和所采集植物的植物特征。
(1)植物的种植信息采集
植物的种植信息包括植物品种、种植面积、种植时间和土壤信息。其中,土壤信息包括土壤基质种类、底肥种类、土壤基质与底肥混合比例、土壤酸碱度和土壤导电率。这些植物种植信息可以通过用户输入和测量设备检测而获取。
植物品种还可以包括特定植物种类的相关数据,例如:该种植物的分布地带特性(例如其通常分布于温带地区还是热带地区),该种植物的形态(包括根、茎、叶、果等的形态),该种植物所需光照特性、水分特性、温度特性、肥力需求,该种植物的常见病虫害,等等。而这部分信息数据基于用户输入的植物品种使用搜索技术经由联网获取。
另外,上述植物种植信息在种植开始时获取收集即可,不需要随时监控。
(2)种植装置所处的环境信息采集
环境信息数据包括地址信息和位置信息。其中的地址信息,例如种植装置所处房屋的居住小区信息。位置信息包括:在种植装置处于室内的情况下,房屋所处楼层,种植装置是置于房间内还是封闭阳台,所处房间或封闭阳台的朝向,窗户采光情况;或者在种植装置处于室外的情况下,种植装置是位于院落、露台、屋顶还是开放阳台。这些环境信息可以通过用户输入获取。这些种植环境信息在种植开始时获取收集即可,不需要随时监控。
此外,种植环境信息还可以包括天气类信息,例如:每天该地理位置处的温度信息(例如每小时的温度、每天的最高温和最低温等)、风力信息、日照信息、风雨雪雾等。这些环境信息基于用户输入的地址信息经由联网定期获取。
(3)种植条件采集
种植条件包括降雨量、空气条件、土壤条件和光照条件。
空气条件可以包括:空气温度、空气湿度、通风情况、氧气含 量、二氧化碳含量、有害气体含量和可吸入颗粒物等。其中有害气体指的是甲醛、苯、氡、氨、挥发性有机化合物和二氧化硫等。可吸入颗粒物指的是PM10、PM2.5、或者PM10和PM2.5二者。
土壤条件选自下述群组中的一种或多种:土壤酸碱度、土壤导电率、土壤温度和土壤湿度。
光照条件选自下述群组中的一种或多种:光照强度和光照时长。
关于这些种植条件的信息可以通过各种测量设备得到,测量操作可以在预定定时进行,或者以预定时间间隔进行,或者按照其他方式设定测量的启动时刻。
(4)植物特征采集
植物特征包括种植过程信息和收获植物特征。
种植过程信息至少包括:发芽成功率,其基于发芽数和种植面积;发芽用时,其基于发芽截止时刻和播种时刻;叶子生长健康情况;病害、虫害情况;以及植物的株苗高度和叶子面积。这些种植过程信息通过用户输入和/或测量设备获得,例如通过拍照并对图片分析处理而获得。种植过程信息的获取操作可以在预定定时进行,或者以预定时间间隔进行,或者按照其他方式设定此操作的启动时刻。
收获植物特征至少包括:单位种植面积的收获情况;单位种植面积内的果实量;植物的花期;以及种植者的主观评价,包括生长过程的自我评价、收获情况的自我评价、果实/叶菜/根茎的口感评价、观赏植物的评价。这些收获植物特征通过用户输入和/或测量设备获得,例如通过拍照并对图片分析处理而获得。
另外,采集上述两种植物特征的手段还可以包括拍摄照片或者视频等。
[分类及评价标记操作]
1.数据的分类及存储操作
由于生命科学本身的复杂性,植物种植过程中收集到的各类数据(例如温度、湿度、光照等数据)只有在相同/相似维度(即相同/相似环境)下进行比较评测才有意义,并且只有这样才能实际地进一步去 指导种植。
因此,采集到的种植数据必须依据特定的维度进行分类存储。这些维度包括但不局限于:地址信息维度、种植环境信息、种植信息等,请参见图2。
下面具体举例说明。在北京“天通苑”小区的居所内进行种植,种植装置放置于室内封闭式阳台中,采用相同土壤配比,在4月初种植香菜,其生长周期内的数据作为一个维度下的数据集合。同期有40户在居所中种植香菜,那么种植情况评比限制在这40人的种植数据集合(作为一个类别)内进行。如果同期此维度下只有一户居所种植香菜,同一区域种植数据太少时,则寻找类似条件(临近区域或类似维度)的数据进行合并处理作为同一归类,后期种植条件数据优选时进行评比优选。例如,北京“回龙观”小区因其地理位置临近而作为“天通苑”小区的相似小区,该“回龙观”小区在室内封闭式阳台中4月初采用相同土壤配比种植香菜的数据集合,作为类似条件的数据集合进行归类。也就是说,天通苑数据少时,可选择临近区域的数据进行合并处理,作为同一归类。后期近期数据优选时,是在同类数据中进行评比优选的。
2.数据的评价分析操作
图3A至图3E示出根据本发明一种实施例的评价模型,其中,图3A示出创建模型的思路原则,图3B示出种植评价指标,图3C示出模型合理性的判断方法,图3D示出异常数据清理,图3E示出评价公式。
本领域技术人员已知,合适的种植条件(例如温度、湿度、土壤条件)会导致获得具备更好植物特征(例如株苗高度、收获果实量、果实/叶菜/根茎的口感等)的植物。因此,如果种出的植物具备优良的植物特征,则可以说明在其种植过程中的种植条件是适当的。
类似于产品质量由制造工艺过程决定的关系,植物的收获由种植过程决定,二者是正相关系。这是整个评价模型的基础原则。
因此,如图3A所示,本发明提出,通过对植物特征(包括种植过程信息和收获植物特征)进行评价或者说评分分析,挑选出评分高的植物,将该植物种植过程中采集获取的种植条件数据进行标记(作 为优选数据)并存储,然后,在下一轮植物种植时,用经标记的该植物种植条件数据指导新一轮的种植。
确定种植条件与植物特征之间关系时,可以考虑如下关系:各个种植子过程对于结果的影响是否为累加关系、还是倍数关系(即乘法关系)、或是其他关系。各个子过程对于收获植物特征的影响方式。
那么,如何评价植物种植过程和收获情况,如何构建两者之间的关系,是进行数据评价的关键。关于这一点,本发明提出了新的数据获取或者说挑选方法,即,基于大量种植数据进行分析处理后进行植物种植过程和收获情况的数据评价。
在判断相同或类似条件下哪些植物特征数据是更优的选择过程中,由于大数据分析涉及大量的数据,优选过程需要尽可能少的人工参与,更多的数据分析是使用信息技术自动化进行的。
如前文所述,植物特征分为两大类:种植过程信息和收获植物特征。在本实施例中,将这两种植物特征综合进行评分。
常测生长生理指标有光合速率,叶绿素含量,叶水势,气孔导度,叶面积等指标。
植物生长量可以由植物器官的鲜重、干重、长度、面积和直径等表示。植物生长积量是生长积累的数量,即是植物材料在测定时的实际数量,它相当于植物的长相。生长速率是表示生长的快慢,相当于植物的长势,有绝对生长速率和相对生长速率两种表示。相对生长量表示的是一定时间内、植物净增加生物量占处理前生物量的百分数。
传统生长量的测量往往是采摘后在试验室基于鲜重、干重、长度等的测量对比评测。光合速率、叶绿素含量的测定只能在实验室环境下测定。上面这些指标评测目标为植物本身情况。而我们还需要对于人参与其中的种植过程进行评测,对于多株植物形成种群的相互影响考虑在内,构建植物生长过程与收获情况的正相关系,进而得出过程与收获的联系,为实现种植过程标准化,流程化,工厂化积累大量数据,打下良好基础。
图3B示出种植评价的内容,包括种植过程评价、种植收获评价、主观评价。
2.1种植过程评价
种植过程涉及播种过程、植物生长过程和种植管理过程。在本实施例中对这些过程分别进行评价。
2.1.1播种过程评价
播种过程主要涉及发芽情况,可以选择种植密度(发芽成功率)或发芽用时作为参数指标进行评价。使用这两个指标来评价播种育苗过程的成熟度。
种植密度(发芽成功率)=发芽数/种植面积
提取播种公认发芽时长+3天的照片,通过图片处理计算得出发芽数。种植面积为用户确认数据,通过用户输入方式获取。
恰当的种植密度可以与历史数据或公认数据进行对比。种植密度过大会影响植物正常的生长发育,种植密度过小会影响最后的收获成果。
发芽用时=发芽截止时间-播种时间
种植发芽的截止时间通过下述方式获取:提取播种后公认发芽时长+3天的照片,在无大批新芽出现时的日期作为发芽截止时间。
2.1.2生长过程评价
植物叶子生长情况,是否出现过叶子蔫黄、枯萎、株苗死亡的情况,出现次数,涉及株苗数量等。此情况通过检测种植过程中的图片数据进行判断。
种植过程中是否发生过虫害情况,出现次数。此情况通过检测种植过程中的图片数据进行判断。
对于植物的长势,可以考虑在相同生长时间植物的株苗高度和叶面大小。此情况通过检测种植过程中的图片数据进行判断。
对于果树,可以考虑结出果实所需的历时长短。
另外,还可以考虑在生长过程是否出现超出种植数据阈值的情况。
2.1.3种植管理过程评价
种植管理过程包括浇水管理、温控管理、病虫害管理、间苗剪枝授粉管理等。下面详细进行说明各管理过程的评价内容。
(1)浇水管理评价
众所周知,植物对浇水量的需求因植物种类不同而不同,水量过多或过少都不利于植物生长。
因此,不同植物类型采用不同的浇水策略,例如:一些喜湿润的花卉如杜鹃、山茶、含笑、栀子、米兰等,可以考虑按照“见干见湿”的原则浇水,即,出现栽培介质表层发白的情况就进行浇水,浇至湿润即可;对于兰花、腊梅、天竺葵等喜干怕涝的盆花,可以考虑按照“干透浇透”原则浇水,即,在栽培介质干了的情况下,进行浇水;对于五针松、黑松和旱生植物,可以考虑按照“宁干勿湿”的原则浇水,即,在栽培介质干透了的情况下,进行浇水,并且注意不要出现积水的情况。
关于浇水量,要注意植株是否出现过根部变黑腐烂(浇水过多),植株是否出现干枯现象(浇水过少),植株的土壤湿度、空气湿度是否超过阈值。
另外,需要对浇水时间进行合理选择。通常情况下,浇水应在植物生长活动时进行,但要避开烈日曝晒,所以,一般来说,冬季应在上午9-10时以后浇水,夏季应在清晨8时之前和下午5时以后浇水。
另外,浇水还要考虑种植装置的布置位置,对处在阳光直射下的植物,早上浇水量要大,否则在阳光照射下持续不到下午水分就蒸发了。
(2)温控管理评价
植物不同阶段温度需求不同,如西瓜种子播种适宜温度为20-25度,生长温度15-35度。因此,温度的控制要考虑植物的不同阶段需求不同。
夏日温度过高时,需要及时进行降温处理,例如喷洒降温或遮阳。
冬季温度过低时,需要及时进行加热保温处理。
(3)病害、虫害管理
是否出现过病害、虫害,出现次数。叶面、果实是否受到病害、虫害影响。是否进行过病害、虫害预防操作,例如喷洒虫害预防剂(如能防治煤污病、腐烂病及其他病菌孢子的萌发的姜水)等。病害、虫害出现后是否及时处理,如喷洒除虫剂(如杀灭蚜虫的花椒水)等。
(4)间苗剪枝授粉管理
播种后种植密度大时,需要进行间苗处理,并需要注意间苗处理是否达到或接近植物种植的间距推荐标准。另外,在植物生长过程中需要进行剪枝及授粉管理,需要留意是否出现需要修剪的枝条,如果出现则需要进行修剪,并要注意修剪是否合理。在需要授粉时,是否进行了授粉。
2.2种植收获评价
对于叶菜,其种植收获特征指的是采摘期单位面积内的收获情况。可以通过图片对比确认采摘量,和/或,可以通过用户采摘称重录入系统。
对于果实,其种植收获特征指的是单位面积内的结果量。可以通过图片对比确认采摘量,和/或,可以通过用户采摘称重录入系统。
对于观赏植物,其种植收获特征指的是花期情况。可以通过不同时间的图片对比,确认开花时间及历时长短。
2.3主观评价
主观评价是植物种植者的自我主观评价,包括:对生长过程的自我评价,对收获情况的自我评价,果实/叶菜的口感评价,和/或,观赏植物的评价。
2.4模型合理性评判
需要确定一个评价标准以确保和检验所构建模型是否合理可用。在本实施例中,如图3C所示,模型合理性评判原则如下:
·单株情况,相同条件下,过程与收获是正相函数。
·种群生长时,相同条件下,过程与收获依然是正相函数。
·口味评分具有一票否决权。这是因为,我们追求的是健康安全,而不仅仅是产量。对于蔬菜水果来说,口味的好坏远远超过产量的重要性。
2.5评价步骤
步骤1.选取一个相同/类似维度的数据集合。步骤2.对种植中的播种育苗过程进行评价。步骤3.使用生长过程指标对生长过程进行评价。步骤4.使用管理过程指标对管理过程进行评价。步骤5.使用种 植收获指标对收获情况进行评价。步骤6.与之前更优种植数据中的相关过程评价逐项进行对比,并记录对比结果。步骤7.指标评价完成后,使用不同加权值综合各个过程及其指标得出种植过程的整体评分。步骤8.挑选更优种植数据,与之前更优种植数据的各个监测项曲线拟合。步骤9.同一时间点值求差,求导。看变化趋势是否一致,差值是否超过预设值。步骤10.发现不一致或超过预设值的标记为突变数据。步骤11.与同期(植物生长过程的同期)种植专家种植过程的各个监测数据进行曲线拟合。步骤12.同一时间点值求差,求导。看变化趋势是否一致,差值是否超过预设值。步骤13.发现不一致或超过预设值的标记为突变数据。步骤14.同一数据如果经过二次标记为突变数据则通知系统种植专家进行人工干预处理。步骤15.参考用户自我主观评测,选取各个过程及综合评测分数都高的数据。步骤16.挑选的更优种植数据添加版本,加入优选种植模型。
上面的步骤8至步骤14为异常数据清理步骤,下面具体说明异常数据的清理。
如图3D所示,在本实施例中,使用两种方式清理异常数据:与同期种植专家过程数据对比,以及,与之前优选数据进行对比。
与同期种植专家种植过程的各个监测数据进行曲线拟合。同一时间点值求差、求导。看变化趋势是否一致,差值是否超过预设值。发现不一致或超过预设值的标记为突变数据。
与之前优选数据进行对比时,挑选更优种植数据,与之前更优种植数据的各个监测项曲线拟合。同一时间点值求差、求导。看变化趋势是否一致,差值是否超过预设值。发现不一致或超过预设值的标记为突变数据。
两次被标记为突变数据的过程数据将被从优选数据集合中剔除,并通知系统种植专家进行人工分析,研究,干预。
2.6公式
评价公式基于植物过程特征和植物收获特征,在本发明实施例中,如图3E所示,选择如下评价公式:
综合评分=(过程权重*(播种权重*播种指标评分+施肥权重*施肥 指标评分+管理权重*管理过程评分+病虫害权重*病虫害过程评分+采摘权重*采摘过程评分)+收获权重*(主观权重*主观评分+客观权重*客观评分))口味评分
其中,通过大量实验,确认各个过程、指标的权重。权重值确定各个过程和指标对于收获和结果的影响能力。
[调控操作]
调控操作是使用与更优植物特征对应的种植条件数据指导种植的实施。调控可以针对一种或多种种植条件进行。
具体的种植条件在前文数据采集部分已经进行了具体说明,下面说明几种种植条件的调控方法。
1.温度调控
步骤1.监测每小时获取当前种植环境的温度(土壤温度和空气温度),通过接入模块上传至闭环优化平台。
步骤2.闭环优化平台使用优选数据进行对比,确定温度是否偏离阈值。
步骤3.如果没有偏离阀值,结束。
步骤4.如果偏离阈值,生产相关调控信息,如调控温度到达某个值。
步骤5.控制系统通过接入模块查询是否存在调控信息。
步骤6.控制系统下载获取调控信息,并通知监测模块调整温度监测频度,如5分钟一次。
步骤7.依据调控信息调控温度。超过则喷水降温或遮阳,低于则加热提升温度。
步骤8.监测模块周期性将温度变化发送控制系统。
步骤9.控制系统对比调控目标,判断是否达到温度调控目标。
步骤10.达到,则停止调控。将调控结果上传至闭环优化平台。没有达到,则继续调控。
2.湿度调控
步骤1.监测每4小时获取当前种植环境的湿度(土壤湿度和空气 湿度),通过接入模块上传至闭环优化平台。
步骤2.闭环优化平台使用优选数据进行对比,确定湿度是否偏离阈值。
步骤3.如果没有偏离阀值,结束。
步骤4.如果偏离阈值,生产相关调控信息,如湿度到达某个值。
步骤5.控制系统通过接入模块查询是否存在调控信息。
步骤6.控制系统下载获取调控信息,并通知监测模块调整湿度监测频度,如30秒监测一次。
步骤7.依据调控信息调控进行浇水灌溉。
步骤8.监测模块周期性将湿度变化发送控制系统。
步骤9.控制系统对比调控目标,判断是否达到湿度调控目标。
步骤10.达到,则停止调控。将调控结果上传至闭环优化平台。没有达到,则继续调控。
3.光照强度调控
步骤1.监测每小时获取当前种植环境的光照强度,通过接入模块上传至闭环优化平台。
步骤2.闭环优化平台使用优选数据进行对比,确定光照强度是否偏离阈值。
步骤3.如果没有偏离阀值,则结束。
步骤4.如果偏离阈值,生产相关调控信息,例如:遮阳2小时或LED补光至指定光照量等。
步骤5.控制系统通过接入模块查询是否存在调控信息。
步骤6.控制系统下载获取调控信息,并通知监测模块调整光照监测频度,如30分钟一次。
步骤7.依据调控信息调控进行LED补光/遮阳处理。
步骤8.监测模块周期性将光照强度变化及光照时长发送控制系统。
步骤9.控制系统对比调控目标,判断是否达到光照调控目标。
步骤10.达到,则停止调控。将调控结果上传至闭环优化平台。没有达到,则继续调控。
4.土壤肥力调控
本实施例中,通过检测土壤导电率来表示土壤肥力水平。
步骤1.监测获取当前种植环境的土壤导电率,通过接入模块上传至闭环优化平台。
步骤2.平台依据植物当前生长阶段、上次检测时间、当前土壤导电率判断是否需要调控。
步骤3.如果需要调控,生成调控信息,如添加多少液肥至水中,以调整土壤导电率。
步骤4.控制系统通过接入模块查询是否存在调控信息。
步骤5.控制系统下载获取调控信息,并通知监测模块调整土壤导电率监测频度。
步骤7.依据调控信息混合液肥和水。
步骤8.下次浇水时,肥和水一起浇灌。
步骤9.监测模块周期性将土壤导电率水平发送控制系统。
5.除虫调控
步骤1.依据用户种植品种提供相应的病虫生物制剂,用户加入控制设备。
步骤2.监测获取当前种植环境的虫害情况图片,通过接入模块上传至闭环优化平台。
步骤3.平台通过图片处理识别,确认发生虫害,生成调控信息。
步骤4.控制系统通过接入模块查询是否存在调控信息。
步骤5.控制系统下载获取调控信息。
步骤6.依据调控信息混合除虫制剂和水。
步骤7.下次浇水时,和水一起喷洒。
步骤8.此调控措施连续实施指定天数,例如每天一次。具体的调控时间间隔可以由用户设定。
步骤9.指定天数后监测模块将虫害情况图片上传至平台,对比之前照片判断效果。
步骤10.如果效果不明显,预警通知用户采取人工干预措施。
上面详细描述了本发明智能种植系统,下面说明本发明采用该智能种植系统的智能种植设备构成实施例。整个系统可以采用电池、太阳能/风能、电源三种方式提供能源。
根据本实施例,智能种植设备总体上由智能家居星网(包括多个星网单元)、智能闭环优化平台、客户端三部分构成。
当前已有的自动浇花或种植系统往往是依据已经设好的固定操作来进行控制。然而不同的用户有不同的行为习惯。有人喜欢更多的自我控制,万事尽在掌握的感觉;有人喜欢有个贴身助手时刻提醒一下自己;有人喜欢听从专家的意见;有人就是希望事情越简单越好。
为了满足更多用户的需求,让更多的人用起来,更好的形成规模效应,系统提供了四种不同的实施模式:专家模式,助手模式,跟随模式,小白模式。
专家模式中,部署1-N个环境监测模块,0-N个控制系统及一个接入模块。专家模式给予用户完全的控制,专家自主控制种植过程的各个方面细节,系统仅负责提醒和预警。当环境参数异常时,例如连续多日忘记浇水时,系统通过客户端预警提醒专家用户,由专家用户自行处理。专家用户可以选择配置控制系统,也可以选择不配置控制系统。配置控制系统的情况下,种植管理可以通过客户端远程控制。闭环优化平台记录整个种植过程,保存相关种植数据并进行评价。
助手模式中,部署1-N个环境监测模块,1-N个控制系统及一个接入模块。助手模式为工作繁忙的种植专家或用户提供贴身助手服务。用户的整个种植过程中仍旧是以自主控制为主,系统提供预警提醒醒和偶尔的调控。平日,用户自主的进行种植管理,如浇水,施肥等。当用户忘记操作或者种植指标偏离阀值时,系统首先发出预警,提醒用户。指定时间内用户没有主动调控的话,则系统自动调控并通知用户。
跟随模式中,部署1-N个环境监测模块,1-N个控制系统及一个接入模块。种植开始时,用户通过客户端选择与自己种植环境类似的信赖的专家用户,并种植与该专家用户相同的种植品种。整个种植过程除一些必须手工操作的工作(如播种、剪枝、收获等)以外,其他 操作如浇水、施肥、补光、通风等,全部自动地依据所跟随专家的数据进行操作。使得用户的操作最小化。这种方式是一种用户跟随专家学习种植的过程。过程中,用户可以和跟随的专家用户随时使用客户端进行交流讨论学习。用户也可以通过客户端将种植过程数据进行回溯、标记、添加心得体会。
小白模式中,部署1-N个环境监测模块,1-N个控制系统及一个接入模块。整个种植过程中,除一些必须手工操作的工作如播种、剪枝、收获等以外,其他操作如浇水、施肥、补光、通风等操作全部自动地依据系统优选的种植数据进行操作。使得小白用户的操作最小化。
请参见图4,其中描述了智能种植的概要过程。步骤1:种植用户将相关用户确认信息输入到闭环优化模型,包括种植信息、地理位置信息、环境信息等。步骤2:监测模块监测植物相关信息,并将其发送给接入模块和远控控制模块。步骤3:接入模块负责接入互联网,并将信息传送给闭环优化模型。步骤4:通过接入模块,远程控制模块将是否需要调控的询问发送给闭环优化模型。步骤5:闭环优化模型根据监测信息、植物相关信息、上次调控情况等信息,判断是否需要调控。步骤6:如果需要,闭环优化模型生成调控信息,通过接入模块将其传送给远程控制模块。步骤7:远程控制模块依据调控信息进行植物种植条件的调节,如浇水、施肥等。步骤8:调控过程中,监测模块随时将相关信息变化传送给远程控制模块。步骤9:远程控制模块判断是否达到调控目标。步骤10:如果达到调控目标后,停止调控,并将调控结果通过接入模块传送给闭环优化模型。
如图5所示,一个星网单元包括环境监测、控制系统、互联网接入三部分,各部分之间通过低功耗无线网络连接。系统实施时,一个星网单元中环境监测有1至N个,远程控制有0至N个,互联网接入有1个。
在本发明的一种具体实施例中,数据采集装置和调控装置设置于单独种植环境(例如各个家庭)中。在本发明中,也可以将这部分统称为智能家居星网,包括环境监测模块、控制系统、接入模块三部分。
接入模块通过互联网将数据提交给智能闭环优化平台(下文描 述),并接收来自智能闭环优化平台的调控数据。接入模块通过低功耗无线连接将调控数据传输给控制系统。控制系统依据调控数据进行浇水、补光/遮阳、补氧/CO2、降温、升温、施肥、通风、除虫等操作,并实时对比环境监测数据看是否达到调控目标。无线传输模块可自组网,并将监测数据传输给控制模块和接入模块。
测量设备包括各种对应的传感器,然后测量的信息数据可以通过低功耗无线传输模块进行传送或上传给接入模块,接入模块负责传送给闭环优化平台中,例如传到下文所说明的闭环优化平台中。监测模块可以按照指定频度或时间间隔获取数据并将通过接入模块将其上传。例如,温度、湿度、图片等以小时为频度上传数据。
如图6所示,每个用户内部组成一个星网单元,星网单元与闭环优化平台通过互联网连接,客户端通过互联网连接到闭环优化平台获得预警、当前种植情况等信息,并且可以通过闭环优化平台手工控制经授权的星网单元。
用户使用客户端可以实现如下功能:
·全程种植指导(包括自动化的业务流程指导和人工指导)。
·实时远程观看植物的环境数据。
·接收预警信息,人工干预提示。
·拍照上传植物照片,分享种植乐趣、反馈收获情况。
·人工强制调整植物环境数据:浇水、补光等等。
·查询植物相关知识库。
通过用户输入的信息还可以包括:默认浇水时间段等。这种用户输入的操作可以通过客户端在种植开始时确认并直接输入,然后输入的信息数据可以传送或上传,例如传到下文所说明的闭环优化平台中。
图7示出了智能闭环优化平台的实施方式,说明闭环优化平台是如何形成闭环的整体过程,在闭环中如何指导种植的过程。分类及标记模块和调控模块都设置于智能闭环优化平台中,该智能闭环优化服务平台(简称闭环优化平台)依据环境数据,匹配、挑选更加优化的环境对比数据和用户可能的参与调整(可选项)生成调控数据,通过互联网传送接入模块。调控模块设置于智能闭环优化平台中,使用更 优种植数据指导种植。
闭环优化平台建立之初依据植物品种设置了光照、温度等已知的各种上、下限数据,并依次反馈调控数据。第一次种植过程中获取了大量的用户输入信息和生长周期中的环境监测数据。收获时,鼓励用户使用客户端(微信/手机APP/PC等)拍照分享收获情况或使用系统的视频监测信息。依据用户种植面积及收获图片,闭环优化平台进行分析处理量化。量化后的数据进行对比判定同样环境数据下收获更好的种植数据,并作为下一轮的调控指导数据。这个过程自动的循环并逐步优化。
当然,在需要的情况下,也可由农业专家对数据进行判定微调。或者选定特定专家在同样环境数据下的种植数据作为对比数。
闭环优化平台的自动优化过程中以环境数据、种植过程、收获情况为输入,采用机器学习算法进行归类优选,得出更优的种植数据模型。
参见图7,在步骤1.用户确认种植面积及种植品种后,系统判断是否有相关优选种植数据(种植数据包括整个植物生长周期内每个阶段的相关数据)。步骤2.如果没有转向专家方式。步骤3.如果有,使用优选数据,转向小白方式。步骤4.记录整个植物生长周期内各个阶段的相关数据。步骤5.收获时,通过用户图片分享、心得分享、自我评价、其他人评价、视频监测信息等情况,综合评比。步骤6.通过对收集到的大量数据采用机器学习算法进行整理、归类、分析、评比。从中获取更专业的种植专家,更优选的种植数据。这个过程中也可以选择部分的系统用户干预措施,使得选择算法更加快速收敛。步骤7.更新闭环优化模型的数据。然后当更多用户种植时,系统返回到步骤3。
闭环优化平台主要包括两部分功能:使用更优种植数据指导种植(调控处理),以及,从收集到的种植数据中选取更优的种植数据(分类及评价处理)。
本发明的内容包括以下方面:
(1)一种智能种植管理方法,其针对多个放置于不同环境下的 种植装置中的植物种植过程进行控制,该方法包括数据采集步骤、分类及标记步骤以及调控步骤,其中:
所述数据采集步骤包括:
采集植物的种植信息和该种植装置所处的环境信息,并将其传送到数据处理系统;
以预定时间间隔,采集多种种植条件中的至少一种种植条件信息,并将该种植条件信息传送到数据处理系统;以及
采集植物的植物特征,并将该植物特征传送到数据处理系统;
所述分类及标记步骤包括:
在所述数据处理系统中,基于所述种植信息和所述环境信息进行分类,在同一类别下,按照预设条件,基于各个种植装置的所述植物特征进行评分,并将多个种植装置的植物特征评分进行比较,将植物特征评分高的种植装置在植物生长周期内的各个种植条件信息进行标记,以及,存储与该植物生长周期相关的各类别下的经标记的种植条件信息,
所述调控步骤包括:
根据各个种植装置的种植信息和环境信息,将当前的种植条件信息与存储的经标记种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,依据存储的经标记种植条件信息和当前种植条件信息,生成调控数据;以及
将该调控数据发送至各个种植装置,以对各个种植装置的该种植条件进行调控操作。
(2)根据(1)所述的智能种植管理方法,其中,
采集植物的植物特征包括:
在植物生长周期的过程中,采集植物的各阶段的种植过程信息;以及
在收获后,采集收获植物特征,以及
所述分类及标记步骤包括:
在同一类别下,按照预设条件,基于各个种植装置的所述 种植过程信息和所述收获植物特征进行评分。
(3)根据(1)所述的智能种植管理方法,其中,获取当前植物生长周期下的多个种植装置的植物特征评分,将其与存储的评分高的种植装置的植物特征评分进行比较,在前者高于后者的情况下,将当前植物特征评分高的种植装置的各个种植条件信息进行标记,以及,存储与当前植物生长周期相关的各类别下的经标记的种植条件信息。
(4)根据(1)所述的智能种植管理方法,其中,在第一个植物生长周期,将采集的当前种植条件信息与预设的种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,选取预设的种植条件信息,生成调控数据,以及,将该调控数据发送至各个种植装置,以对各个种植装置的该种植条件进行控制。
(5)根据(1)所述的智能种植管理方法,其中,
所述调控数据至少基于下述之一获得:存储的经标记种植条件信息、最末次调控操作的时间、末次调控量以及阈值。
(6)根据(1)所述的智能种植管理方法,其中,所述分类及标记步骤包括清理异常数据。
(7)根据(6)所述的智能种植管理方法,其中,所述调控步骤中将当前的种植条件信息与存储的经标记种植条件信息进行比较包括:
将当前的种植条件信息与相同或相似种植时间的专家种植条件信息进行曲线拟合,同一时间点值求差、求导,在变化趋势不一致或者差值超过预设值的情况下,将当前种植条件信息标记为突变数据。
(8)根据(6)所述的智能种植管理方法,其中,所述调控步骤中将当前的种植条件信息与存储的经标记种植条件信息进行比较包括:
将当前的种植条件信息与相同或相似种植时间的存储经标记种植条件信息进行曲线拟合,同一时间点值求差、求导,在变化趋势不一致或者差值超过预设值的情况下,将当前种植条件信息标记为突变数据。
(9)根据(6)所述的智能种植管理方法,其中,将两次标记为突变数据的种植条件信息剔除,并通知系统种植专家进行人工分析、研究和干预。
(10)根据(1)所述的智能种植管理方法,其中,所述种植装置所处的环境信息包括:
地址信息,其基于种植装置所处房屋的居住小区信息;
位置信息,其基于种植装置所处房屋的信息,包括:
在种植装置处于室内的情况下,房屋所处楼层,种植装置是置于房间内还是封闭阳台,所处房间或封闭阳台的朝向,窗户采光情况;或者
在种植装置处于室外的情况下,种植装置是位于院落、露台、屋顶还是开放阳台。
(11)根据(1)所述的智能种植管理方法,其中,所述植物的种植信息包括植物品种、种植面积、种植时间和土壤信息。
(12)根据(11)所述的智能种植管理方法,其中,所述土壤信息包括土壤基质种类、底肥种类、土壤基质与底肥混合比例、土壤酸碱度和土壤导电率。
(13)根据(2)所述的智能种植管理方法,其中,所述种植过程信息包括下述群组中的一种或多种:
发芽成功率,其基于发芽数和种植面积;
发芽用时,其基于发芽截止时刻和播种时刻;
叶子生长健康情况;
病害、虫害情况;
植物的株苗高度和叶子面积;以及
管理过程的信息,包括包括浇水管理、温控管理、病虫害管理、间苗剪枝授粉管理等。
(14)根据(2)所述的智能种植管理方法,其中,所述收获植物特征包括下述群组中的一种或多种:
单位种植面积的收获情况;
单位种植面积内的果实量;
植物的花期;以及
种植者的主观评价,包括生长过程的自我评价、收获情况的自我评价、果实/叶菜的口感评价、观赏植物的评价。
(15)根据(1)所述的智能种植管理方法,其中,所述种植条件包括降雨量、空气条件、土壤条件和光照条件。
(16)根据(15)所述的智能种植管理方法,其中,所述空气条件选自下述群组中的一种或多种:空气温度、空气湿度、通风情况、氧气含量、二氧化碳含量、有害气体含量和可吸入颗粒物。
(17)根据(16)所述的智能种植管理方法,其中,所述有害气体为下述群组中的一种或多种:甲醛、苯、氡、氨、挥发性有机化合物和二氧化硫。
(18)根据(16)所述的智能种植管理方法,其中,所述可吸入颗粒物为PM10、PM2.5、或者PM10和PM2.5二者。
(19)根据(15)所述的智能种植管理方法,其中,所述土壤条件选自下述群组中的一种或多种:土壤酸碱度、土壤导电率、土壤温度和土壤湿度。
(20)根据(15)所述的智能种植管理方法,其中,所述光照条件选自下述群组中的一种或多种:光照强度和光照时长。
(21)根据(1)所述的智能种植管理方法,其中,采集所述植物特征还包括拍摄照片或者视频。
(22)根据(1)所述的智能种植管理方法,其中,所述调控操作选自下述群组中的一种或多种:浇水、补光、遮阳、补充氧气、补充二氧化碳、降低温度、升高温度、施肥、增加通风量、减少通风量、喷洒除虫剂、喷洒虫害预防剂。
(23)一种智能种植设备,其对多个放置于不同环境下的种植装置中的植物种植过程进行控制,该智能种植设备包括数据采集装置、分类及标记装置以及调控装置,其中:
所述数据采集装置采集植物的种植信息和该种植装置所处的环境信息,以预定时间间隔采集多种种植条件中的至少一种种植条件信息,以及,采集植物的植物特征,并将所采集到的信息传送到所述分 类及标记装置;
所述分类及标记装置基于所述种植信息和所述环境信息将收到的信息进行分类,在同一类别下,按照预设条件,基于各个种植装置的所述植物特征进行评分,并将多个种植装置的植物特征评分进行比较,将植物特征评分高的种植装置在植物生长周期内的各个种植条件信息进行标记,以及,存储与该植物生长周期相关的各类别下的经标记的种植条件信息,
所述调控装置根据各个种植装置的种植信息和环境信息,将当前的种植条件信息与存储的经标记种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,依据存储的经标记种植条件信息和当前种植条件信息,生成调控数据,以及,将该调控数据发送至各个种植装置,以对各个种植装置的该种植条件进行调控操作。
(24)根据(23)所述的智能种植设备,其中,
采集植物的植物特征包括:
在植物生长周期的过程中,采集植物的各阶段的种植过程信息;以及
在收获后,采集收获植物特征,以及
所述分类及标记装置在同一类别下、按照预设条件、基于各个种植装置的所述种植过程信息和所述收获植物特征进行评分。
(25)根据(23)所述的智能种植设备,其中,获取当前植物生长周期下的多个种植装置的植物特征评分,将其与存储的评分高的种植装置的植物特征评分进行比较,在前者高于后者的情况下,将当前植物特征评分高的种植装置的各个种植条件信息进行标记,以及,存储与当前植物生长周期相关的各类别下的经标记的种植条件信息。
(26)根据(23)所述的智能种植设备,其中,在第一个植物生长周期,将采集的当前种植条件信息与预设的种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,选取预设的种植条件信息,生成调控数据,以及,将该调控数据发送至各个种植装置,以对各个种植装置的该种植条件进行控制。
(27)根据(23)所述的智能种植设备,其中,
所述调控数据至少基于下述之一获得:存储的经标记种植条件信息、最末次调控操作的时间、末次调控量以及阈值。
(28)根据(23)所述的智能种植设备,其中,所述分类及标记装置清理异常数据。
(29)根据(28)所述的智能种植设备,其中,将当前的种植条件信息与存储的经标记种植条件信息进行比较包括:
将当前的种植条件信息与相同或相似种植时间的专家种植条件信息进行曲线拟合,同一时间点值求差、求导,在变化趋势不一致或者差值超过预设值的情况下,将当前种植条件信息标记为突变数据。
(30)根据(28)所述的智能种植设备,其中,将当前的种植条件信息与存储的经标记种植条件信息进行比较包括:
将当前的种植条件信息与相同或相似种植时间的存储经标记种植条件信息进行曲线拟合,同一时间点值求差、求导,在变化趋势不一致或者差值超过预设值的情况下,将当前种植条件信息标记为突变数据。
(31)根据(28)所述的智能种植设备,其中,将两次标记为突变数据的种植条件信息剔除,并通知系统种植专家进行人工分析、研究和干预。
(32)根据(23)所述的智能种植设备,其中,所述种植装置所处的环境信息包括:
地址信息,其基于种植装置所处房屋的居住小区信息;
位置信息,其基于种植装置所处房屋的信息,包括:
在种植装置处于室内的情况下,房屋所处楼层,种植装置是置于房间内还是封闭阳台,所处房间或封闭阳台的朝向,窗户采光情况;或者
在种植装置处于室外的情况下,种植装置是位于院落、露台、屋顶还是开放阳台。
(33)根据(23)所述的智能种植设备,其中,所述植物的种植信息包括植物品种、种植面积、种植时间和土壤信息。
(34)根据(33)所述的智能种植设备,其中,所述土壤信息 包括土壤基质种类、底肥种类、土壤基质与底肥混合比例、土壤酸碱度和土壤导电率。
(35)根据(24)所述的智能种植设备,其中,所述种植过程信息包括下述群组中的一种或多种:
发芽成功率,其基于发芽数和种植面积;
发芽用时,其基于发芽截止时刻和播种时刻;
叶子生长健康情况;
病害、虫害情况;
植物的株苗高度和叶子面积;以及
管理过程的信息,包括包括浇水管理、温控管理、病虫害管理、间苗剪枝授粉管理等。
(36)根据(24)所述的智能种植设备,其中,所述收获植物特征包括下述群组中的一种或多种:
单位种植面积的收获情况;
单位种植面积内的果实量;
植物的花期;以及
种植者的主观评价,包括生长过程的自我评价、收获情况的自我评价、果实/叶菜的口感评价、观赏植物的评价。
(37)根据(23)所述的智能种植设备,其中,所述种植条件包括降雨量、空气条件、土壤条件和光照条件。
(38)根据(37)所述的智能种植设备,其中,所述空气条件选自下述群组中的一种或多种:空气温度、空气湿度、通风情况、氧气含量、二氧化碳含量、有害气体含量和可吸入颗粒物。
(39)根据(38)所述的智能种植设备,其中,所述有害气体为下述群组中的一种或多种:甲醛、苯、氡、氨、挥发性有机化合物和二氧化硫。
(40)根据(38)所述的智能种植设备,其中,所述可吸入颗粒物为PM10、PM2.5、或者PM10和PM2.5二者。
(41)根据(37)所述的智能种植设备,其中,所述土壤条件选自下述群组中的一种或多种:土壤酸碱度、土壤导电率、土壤温度 和土壤湿度。
(42)根据(37)所述的智能种植设备,其中,所述光照条件选自下述群组中的一种或多种:光照强度和光照时长。
(43)根据(23)所述的智能种植设备,其中,采集所述植物特征还包括拍摄照片或者视频。
(44)根据(23)所述的智能种植设备,其中,所述调控操作选自下述群组中的一种或多种:浇水、补光、遮阳、补充氧气、补充二氧化碳、降低温度、升高温度、施肥、增加通风量、减少通风量、喷洒除虫剂、喷洒虫害预防剂。
(45)一种智能种植设备,包括客户端、由多个星网单元构成的星网、和闭环优化平台,其中,
所述客户端通过互联网连接到所述闭环优化平台,获取预警、当前种植情况等信息,并且可以通过闭环优化平台手工控制各星网单元,
所述星网单元与闭环优化平台通过互联网连接,各星网单元包括测量装置、控制装置和互联网接入模块,其中,所述测量装置测量植物种植装置的环境信息和种植条件信息,然后将测量的信息数据传送给所述接入模块,所述接入模块通过互联网将所述信息数据提交给所述闭环优化平台,并接收来自闭环优化平台的调控数据,所述控制装置根据所述调控数据控制所述种植装置的种植条件,
所述闭环优化平台接受来自各星网单元的信息数据,基于所述种植信息和所述环境信息将收到的信息进行分类,在同一类别下,按照预设条件,基于各个种植装置的所述植物特征进行评分,并将多个种植装置的植物特征评分进行比较,将植物特征评分高的种植装置在植物生长周期内的各个种植条件信息进行标记,以及,存储与该植物生长周期相关的各类别下的经标记的种植条件信息,
所述闭环优化平台根据各个种植装置的种植信息和环境信息,将当前的种植条件信息与存储的经标记种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,依据存储的经标记种植条件信息和当前种植条件信息,生成调控数据,以及,将该调控数据发送至各 个星网单元,以对各个星网单元的种植装置的该种植条件进行调控操作。
(46)根据(45)所述的智能种植设备,其中,
采集植物的植物特征包括:
在植物生长周期的过程中,采集植物的各阶段的种植过程信息;以及
在收获后,采集收获植物特征,以及
所述闭环优化平台在同一类别下、按照预设条件、基于各个种植装置的所述种植过程信息和所述收获植物特征进行评分。
(47)根据(45)所述的智能种植设备,其中,获取当前植物生长周期下的多个种植装置的植物特征评分,将其与存储的评分高的种植装置的植物特征评分进行比较,在前者高于后者的情况下,将当前植物特征评分高的种植装置的各个种植条件信息进行标记,以及,存储与当前植物生长周期相关的各类别下的经标记的种植条件信息。
(48)根据(45)所述的智能种植设备,其中,在第一个植物生长周期,所述闭环优化平台将采集的当前种植条件信息与预设的种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,选取预设的种植条件信息,生成调控数据,以及,将该调控数据发送至各个种植装置,以对各个种植装置的该种植条件进行控制。
(49)根据(45)所述的智能种植设备,其中,
所述调控数据至少基于下述之一获得:存储的经标记种植条件信息、最末次调控操作的时间、末次调控量以及阈值。
(50)根据(45)所述的智能种植设备,其中,所述闭环优化平台清理异常数据。
(51)根据(50)所述的智能种植设备,其中,将当前的种植条件信息与存储的经标记种植条件信息进行比较包括:
将当前的种植条件信息与相同或相似种植时间的专家种植条件信息进行曲线拟合,同一时间点值求差、求导,在变化趋势不一致或者差值超过预设值的情况下,将当前种植条件信息标记为突变数据。
(52)根据(50)所述的智能种植设备,其中,将当前的种植 条件信息与存储的经标记种植条件信息进行比较包括:
将当前的种植条件信息与相同或相似种植时间的存储经标记种植条件信息进行曲线拟合,同一时间点值求差、求导,在变化趋势不一致或者差值超过预设值的情况下,将当前种植条件信息标记为突变数据。
(53)根据(50)所述的智能种植设备,其中,将两次标记为突变数据的种植条件信息剔除,并通知系统种植专家进行人工分析、研究和干预。
(54)根据(45)所述的智能种植设备,其中,所述种植装置所处的环境信息包括:
地址信息,其基于种植装置所处房屋的居住小区信息;
位置信息,其基于种植装置所处房屋的信息,包括:
在种植装置处于室内的情况下,房屋所处楼层,种植装置是置于房间内还是封闭阳台,所处房间或封闭阳台的朝向,窗户采光情况;或者
在种植装置处于室外的情况下,种植装置是位于院落、露台、屋顶还是开放阳台。
(55)根据(45)所述的智能种植设备,其中,所述植物的种植信息包括植物品种、种植面积、种植时间和土壤信息。
(56)根据(55)所述的智能种植设备,其中,所述土壤信息包括土壤基质种类、底肥种类、土壤基质与底肥混合比例、土壤酸碱度和土壤导电率。
(57)根据(46)所述的智能种植设备,其中,所述种植过程信息包括下述群组中的一种或多种:
发芽成功率,其基于发芽数和种植面积;
发芽用时,其基于发芽截止时刻和播种时刻;
叶子生长健康情况;
病害、虫害情况;
植物的株苗高度和叶子面积;以及
管理过程的信息,包括包括浇水管理、温控管理、病虫害管理、 间苗剪枝授粉管理等。
(58)根据(46)所述的智能种植设备,其中,所述收获植物特征包括下述群组中的一种或多种:
单位种植面积的收获情况;
单位种植面积内的果实量;
植物的花期;以及
种植者的主观评价,包括生长过程的自我评价、收获情况的自我评价、果实/叶菜的口感评价、观赏植物的评价。
(59)根据(45)所述的智能种植设备,其中,所述种植条件包括降雨量、空气条件、土壤条件和光照条件。
(60)根据(59)所述的智能种植设备,其中,所述空气条件选自下述群组中的一种或多种:空气温度、空气湿度、通风情况、氧气含量、二氧化碳含量、有害气体含量和可吸入颗粒物。
(61)根据(60)所述的智能种植设备,其中,所述有害气体为下述群组中的一种或多种:甲醛、苯、氡、氨、挥发性有机化合物和二氧化硫。
(62)根据(60)所述的智能种植设备,其中,所述可吸入颗粒物为PM10、PM2.5、或者PM10和PM2.5二者。
(63)根据(59)所述的智能种植设备,其中,所述土壤条件选自下述群组中的一种或多种:土壤酸碱度、土壤导电率、土壤温度和土壤湿度。
(64)根据(59)所述的智能种植设备,其中,所述光照条件选自下述群组中的一种或多种:光照强度和光照时长。
(65)根据(45)所述的智能种植设备,其中,采集所述植物特征还包括拍摄照片或者视频。
(66)根据(45)所述的智能种植设备,其中,所述调控操作选自下述群组中的一种或多种:浇水、补光、遮阳、补充氧气、补充二氧化碳、降低温度、升高温度、施肥、增加通风量、减少通风量、喷洒除虫剂、喷洒虫害预防剂。
虽然本发明结合优选实施例进行说明,但应当理解的是,本发明并不局限于本文所给出的实施例,而是可以在所附权利要求的范围内进行多种修改及等效置换。

Claims (30)

  1. 一种智能种植管理方法,其针对多个放置于不同环境下的种植装置中的植物种植过程进行控制,该方法包括数据采集步骤、分类及标记步骤以及调控步骤,其中:
    所述数据采集步骤包括:
    采集植物的种植信息和该种植装置所处的环境信息,并将其传送到数据处理系统;
    以预定时间间隔,采集多种种植条件中的至少一种种植条件信息,并将该种植条件信息传送到数据处理系统;以及
    采集植物的植物特征,并将该植物特征传送到数据处理系统;
    所述分类及标记步骤包括:
    在所述数据处理系统中,基于所述种植信息和所述环境信息进行分类,在同一类别下,按照预设条件,基于各个种植装置的所述植物特征进行评分,并将多个种植装置的植物特征评分进行比较,将植物特征评分高的种植装置在植物生长周期内的各个种植条件信息进行标记,以及,存储与该植物生长周期相关的各类别下的经标记的种植条件信息,
    所述调控步骤包括:
    根据各个种植装置的种植信息和环境信息,将当前的种植条件信息与存储的经标记种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,依据存储的经标记种植条件信息和当前种植条件信息,生成调控数据;以及
    将该调控数据发送至各个种植装置,以对各个种植装置的该种植条件进行调控操作。
  2. 根据权利要求1所述的智能种植管理方法,其中,
    采集植物的植物特征包括:
    在植物生长周期的过程中,采集植物的各阶段的种植过程 信息;以及
    在收获后,采集收获植物特征,以及
    所述分类及标记步骤包括:
    在同一类别下,按照预设条件,基于各个种植装置的所述种植过程信息和所述收获植物特征进行评分。
  3. 根据权利要求1所述的智能种植管理方法,其中,获取当前植物生长周期下的多个种植装置的植物特征评分,将其与存储的评分高的种植装置的植物特征评分进行比较,在前者高于后者的情况下,将当前植物特征评分高的种植装置的各个种植条件信息进行标记,以及,存储与当前植物生长周期相关的各类别下的经标记的种植条件信息。
  4. 根据权利要求1所述的智能种植管理方法,其中,在第一个植物生长周期,将采集的当前种植条件信息与预设的种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,选取预设的种植条件信息,生成调控数据,以及,将该调控数据发送至各个种植装置,以对各个种植装置的该种植条件进行控制。
  5. 根据权利要求1所述的智能种植管理方法,其中,
    所述调控数据至少基于下述之一获得:存储的经标记种植条件信息、最末次调控操作的时间、末次调控量以及阈值。
  6. 根据权利要求1所述的智能种植管理方法,其中,所述分类及标记步骤包括清理异常数据。
  7. 根据权利要求6所述的智能种植管理方法,其中,所述调控步骤中将当前的种植条件信息与存储的经标记种植条件信息进行比较包括:
    将当前的种植条件信息与相同或相似种植时间的专家种植条件 信息进行曲线拟合,同一时间点值求差、求导,在变化趋势不一致或者差值超过预设值的情况下,将当前种植条件信息标记为突变数据。
  8. 根据权利要求6所述的智能种植管理方法,其中,所述调控步骤中将当前的种植条件信息与存储的经标记种植条件信息进行比较包括:
    将当前的种植条件信息与相同或相似种植时间的存储经标记种植条件信息进行曲线拟合,同一时间点值求差、求导,在变化趋势不一致或者差值超过预设值的情况下,将当前种植条件信息标记为突变数据。
  9. 根据权利要求6所述的智能种植管理方法,其中,将两次标记为突变数据的种植条件信息剔除,并通知系统种植专家进行人工分析、研究和干预。
  10. 根据权利要求1所述的智能种植管理方法,其中,所述种植装置所处的环境信息包括:
    地址信息,其基于种植装置所处房屋的居住小区信息;
    位置信息,其基于种植装置所处房屋的信息,包括:
    在种植装置处于室内的情况下,房屋所处楼层,种植装置是置于房间内还是封闭阳台,所处房间或封闭阳台的朝向,窗户采光情况;或者
    在种植装置处于室外的情况下,种植装置是位于院落、露台、屋顶还是开放阳台。
  11. 根据权利要求1所述的智能种植管理方法,其中,所述植物的种植信息包括植物品种、种植面积、种植时间和土壤信息。
  12. 根据权利要求11所述的智能种植管理方法,其中,所述土壤信息包括土壤基质种类、底肥种类、土壤基质与底肥混合比例、土 壤酸碱度和土壤导电率。
  13. 根据权利要求2所述的智能种植管理方法,其中,所述种植过程信息包括下述群组中的一种或多种:
    发芽成功率,其基于发芽数和种植面积;
    发芽用时,其基于发芽截止时刻和播种时刻;
    叶子生长健康情况;
    病害、虫害情况;
    植物的株苗高度和叶子面积;以及
    管理过程的信息,包括包括浇水管理、温控管理、病虫害管理、间苗剪枝授粉管理等。
  14. 根据权利要求2所述的智能种植管理方法,其中,所述收获植物特征包括下述群组中的一种或多种:
    单位种植面积的收获情况;
    单位种植面积内的果实量;
    植物的花期;以及
    种植者的主观评价,包括生长过程的自我评价、收获情况的自我评价、果实/叶菜的口感评价、观赏植物的评价。
  15. 根据权利要求1所述的智能种植管理方法,其中,所述种植条件包括降雨量、空气条件、土壤条件和光照条件。
  16. 根据权利要求15所述的智能种植管理方法,其中,所述空气条件选自下述群组中的一种或多种:空气温度、空气湿度、通风情况、氧气含量、二氧化碳含量、有害气体含量和可吸入颗粒物。
  17. 根据权利要求16所述的智能种植管理方法,其中,所述有害气体为下述群组中的一种或多种:甲醛、苯、氡、氨、挥发性有机化合物和二氧化硫。
  18. 根据权利要求16所述的智能种植管理方法,其中,所述可吸入颗粒物为PM10、PM2.5、或者PM10和PM2.5二者。
  19. 根据权利要求15所述的智能种植管理方法,其中,所述土壤条件选自下述群组中的一种或多种:土壤酸碱度、土壤导电率、土壤温度和土壤湿度。
  20. 根据权利要求15所述的智能种植管理方法,其中,所述光照条件选自下述群组中的一种或多种:光照强度和光照时长。
  21. 根据权利要求1所述的智能种植管理方法,其中,采集所述植物特征还包括拍摄照片或者视频。
  22. 根据权利要求1所述的智能种植管理方法,其中,所述调控操作选自下述群组中的一种或多种:浇水、补光、遮阳、补充氧气、补充二氧化碳、降低温度、升高温度、施肥、增加通风量、减少通风量、喷洒除虫剂、喷洒虫害预防剂。
  23. 一种智能种植设备,其对多个放置于不同环境下的种植装置中的植物种植过程进行控制,该智能种植设备包括数据采集装置、分类及标记装置以及调控装置,其中:
    所述数据采集装置采集植物的种植信息和该种植装置所处的环境信息,以预定时间间隔采集多种种植条件中的至少一种种植条件信息,以及,采集植物的植物特征,并将所采集到的信息传送到所述分类及标记装置;
    所述分类及标记装置基于所述种植信息和所述环境信息将收到的信息进行分类,在同一类别下,按照预设条件,基于各个种植装置的所述植物特征进行评分,并将多个种植装置的植物特征评分进行比较,将植物特征评分高的种植装置在植物生长周期内的各个种植条件 信息进行标记,以及,存储与该植物生长周期相关的各类别下的经标记的种植条件信息,
    所述调控装置根据各个种植装置的种植信息和环境信息,将当前的种植条件信息与存储的经标记种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,依据存储的经标记种植条件信息和当前种植条件信息,生成调控数据,以及,将该调控数据发送至各个种植装置,以对各个种植装置的该种植条件进行调控操作。
  24. 根据权利要求23所述的智能种植设备,其中,
    采集植物的植物特征包括:
    在植物生长周期的过程中,采集植物的各阶段的种植过程信息;以及
    在收获后,采集收获植物特征,以及
    所述分类及标记装置在同一类别下、按照预设条件、基于各个种植装置的所述种植过程信息和所述收获植物特征进行评分。
  25. 根据权利要求23所述的智能种植设备,其中,获取当前植物生长周期下的多个种植装置的植物特征评分,将其与存储的评分高的种植装置的植物特征评分进行比较,在前者高于后者的情况下,将当前植物特征评分高的种植装置的各个种植条件信息进行标记,以及,存储与当前植物生长周期相关的各类别下的经标记的种植条件信息。
  26. 根据权利要求23所述的智能种植设备,其中,在第一个植物生长周期,将采集的当前种植条件信息与预设的种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,选取预设的种植条件信息,生成调控数据,以及,将该调控数据发送至各个种植装置,以对各个种植装置的该种植条件进行控制。
  27. 一种智能种植设备,包括客户端、由多个星网单元构成的星 网、和闭环优化平台,其中,
    所述客户端通过互联网连接到所述闭环优化平台,获取预警、当前种植情况等信息,并且可以通过闭环优化平台手工控制各星网单元,
    所述星网单元与闭环优化平台通过互联网连接,各星网单元包括测量装置、控制装置和互联网接入模块,其中,所述测量装置测量植物种植装置的环境信息和种植条件信息,然后将测量的信息数据传送给所述接入模块,所述接入模块通过互联网将所述信息数据提交给所述闭环优化平台,并接收来自闭环优化平台的调控数据,所述控制装置根据所述调控数据控制所述种植装置的种植条件,
    所述闭环优化平台接受来自各星网单元的信息数据,基于所述种植信息和所述环境信息将收到的信息进行分类,在同一类别下,按照预设条件,基于各个种植装置的所述植物特征进行评分,并将多个种植装置的植物特征评分进行比较,将植物特征评分高的种植装置在植物生长周期内的各个种植条件信息进行标记,以及,存储与该植物生长周期相关的各类别下的经标记的种植条件信息,
    所述闭环优化平台根据各个种植装置的种植信息和环境信息,将当前的种植条件信息与存储的经标记种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,依据存储的经标记种植条件信息和当前种植条件信息,生成调控数据,以及,将该调控数据发送至各个星网单元,以对各个星网单元的种植装置的该种植条件进行调控操作。
  28. 根据权利要求27所述的智能种植设备,其中,
    采集植物的植物特征包括:
    在植物生长周期的过程中,采集植物的各阶段的种植过程信息;以及
    在收获后,采集收获植物特征,以及
    所述闭环优化平台在同一类别下、按照预设条件、基于各个种植装置的所述种植过程信息和所述收获植物特征进行评分。
  29. 根据权利要求27所述的智能种植设备,其中,获取当前植物生长周期下的多个种植装置的植物特征评分,将其与存储的评分高的种植装置的植物特征评分进行比较,在前者高于后者的情况下,将当前植物特征评分高的种植装置的各个种植条件信息进行标记,以及,存储与当前植物生长周期相关的各类别下的经标记的种植条件信息。
  30. 根据权利要求27所述的智能种植设备,其中,在第一个植物生长周期,所述闭环优化平台将采集的当前种植条件信息与预设的种植条件信息进行比较,在前者与后者之差值超过阈值的情况下,选取预设的种植条件信息,生成调控数据,以及,将该调控数据发送至各个种植装置,以对各个种植装置的该种植条件进行控制。
PCT/CN2016/082958 2015-05-26 2016-05-23 智能种植管理方法和智能种植设备 WO2016188384A1 (zh)

Priority Applications (6)

Application Number Priority Date Filing Date Title
EP16799272.6A EP3330905A4 (en) 2015-05-26 2016-05-23 INTELLIGENT CULTURE MANAGEMENT METHOD AND INTELLIGENT CULTURE DEVICE
JP2018513711A JP2018517220A (ja) 2015-05-26 2016-05-23 インテリジェント栽培管理方法及びインテリジェント栽培設備
CA2987319A CA2987319A1 (en) 2015-05-26 2016-05-23 An intelligent planting management method and intelligent planting apparatus
AU2016266460A AU2016266460B2 (en) 2015-05-26 2016-05-23 Intelligent growing management method and intelligent growing device
RU2017145656A RU2688234C1 (ru) 2015-05-26 2016-05-23 Способ интеллектуального управления выращиванием и интеллектуальное устройство для выращивания
US15/576,899 US10966377B2 (en) 2015-05-26 2016-05-23 Intelligent growing management method and intelligent growing device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510277815.9 2015-05-26
CN201510277815.9A CN104866970B (zh) 2015-05-26 2015-05-26 智能种植管理方法和智能种植设备

Publications (1)

Publication Number Publication Date
WO2016188384A1 true WO2016188384A1 (zh) 2016-12-01

Family

ID=53912790

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/082958 WO2016188384A1 (zh) 2015-05-26 2016-05-23 智能种植管理方法和智能种植设备

Country Status (8)

Country Link
US (1) US10966377B2 (zh)
EP (1) EP3330905A4 (zh)
JP (1) JP2018517220A (zh)
CN (1) CN104866970B (zh)
AU (1) AU2016266460B2 (zh)
CA (1) CA2987319A1 (zh)
RU (1) RU2688234C1 (zh)
WO (1) WO2016188384A1 (zh)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106709811A (zh) * 2016-12-08 2017-05-24 党兴仁 一种蔬菜生长管理方法及系统
WO2018196167A1 (zh) * 2017-04-28 2018-11-01 深圳前海弘稼科技有限公司 温室大棚的控制方法、控制装置和服务器
CN111488369A (zh) * 2020-04-01 2020-08-04 黑龙江省农业科学院农业遥感与信息研究所 一种农业科技咨询服务平台
JP2020522988A (ja) * 2017-06-14 2020-08-06 グロー ソリューションズ テック エルエルシー 成長ポッドにおける植物の重量を管理するためのシステムおよび方法
JP2020522991A (ja) * 2017-06-14 2020-08-06 グロー ソリューションズ テック エルエルシー 成長ポッド内の植物体に関する収穫タイミングを決定するためのシステムおよび方法
JP2020523980A (ja) * 2017-06-14 2020-08-13 グロー ソリューションズ テック エルエルシー 成長ポッドをプログラムするためのシステムおよび方法
JP2020527328A (ja) * 2017-06-14 2020-09-10 グロー ソリューションズ テック エルエルシー 成長ポッドにおける自己学習のためのシステムおよび方法
WO2020227812A1 (en) * 2019-05-13 2020-11-19 CO2 GRO Inc. Control of pathogens by foliar spraying with co2-infused water
CN112293077A (zh) * 2020-11-11 2021-02-02 四川省农业科学院园艺研究所 一种缩短蜡梅育种年限的方法
CN113111672A (zh) * 2021-04-13 2021-07-13 中国科学院东北地理与农业生态研究所 一种真湿地植物的判定方法
CN116502962A (zh) * 2023-06-29 2023-07-28 乐番农业科技(北京)有限公司 一种植物种质资源智能管理方法和系统
CN116824380A (zh) * 2023-08-30 2023-09-29 山东孟子居生态农业股份有限公司 一种智慧农业云平台监控系统

Families Citing this family (115)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104866970B (zh) * 2015-05-26 2018-07-24 徐吉祥 智能种植管理方法和智能种植设备
CN105137940B (zh) * 2015-09-01 2017-11-03 徐州工业职业技术学院 物联网大棚农业生长监控系统
CN105163090B (zh) * 2015-09-22 2018-09-28 江苏大学 基于4g的家庭庭院智能看护装置
CN106605530B (zh) * 2015-10-27 2020-11-06 上海中医药大学 盆栽植物的自动监测与栽培方法及智能花盆
CN105635302B (zh) * 2016-01-15 2019-12-13 百度在线网络技术(北京)有限公司 对象操作方法和装置
CN105613246A (zh) * 2016-01-18 2016-06-01 王春雷 一种自动选择种植蔬菜种类的方法及装置
CN105512950A (zh) * 2016-01-21 2016-04-20 上海硅酉信息技术有限公司 一种地理信息系统
CN105700593B (zh) * 2016-02-04 2018-07-31 冯涛 一种植物种植监控系统及其方法
WO2017137914A1 (en) * 2016-02-12 2017-08-17 Tata Consultancy Services Limited Methods and systems for automated identification of agro-climatic zones
CN105867144A (zh) * 2016-04-05 2016-08-17 云上后稷(北京)科技有限公司 家居型植物工厂、远程控制方法、控制器及控制系统
CN105867492A (zh) * 2016-05-03 2016-08-17 昆明理工大学 一种大棚内智能温控培育多种植物的方法
CN106357611A (zh) * 2016-08-25 2017-01-25 深圳前海弘稼科技有限公司 一种植物信息共享方法以及装置
CN106331127A (zh) * 2016-08-30 2017-01-11 深圳前海弘稼科技有限公司 种植设备及其管理方法、装置、系统以及服务器
CN106465634A (zh) * 2016-09-05 2017-03-01 深圳市双赢伟业科技股份有限公司 基于农联网的蔬菜栽培方法及栽培系统
CN106408430A (zh) * 2016-09-26 2017-02-15 深圳前海弘稼科技有限公司 植物生长数据的记录方法和记录系统
CN106650587A (zh) * 2016-09-29 2017-05-10 深圳前海弘稼科技有限公司 种植设备的电源管理方法、电源管理装置和种植设备
CN106341491A (zh) * 2016-10-19 2017-01-18 郑州云海信息技术有限公司 业务平台、确定植物灌溉时间和水量的方法及系统
CN107980572A (zh) * 2016-10-26 2018-05-04 陈鸽 水培蔬菜的种植方法及种植控制装置
CN106489687A (zh) * 2016-10-28 2017-03-15 深圳前海弘稼科技有限公司 灌溉装置的控制方法和控制装置
CN106561347B (zh) * 2016-10-31 2019-12-03 惠州匠韵智能科技有限公司 一种基于机器学习的植物智能培育系统及方法
CN106651149A (zh) * 2016-12-01 2017-05-10 厦门迈信物联科技股份有限公司 一种植物生长行为分析方法
EP3340130A1 (en) * 2016-12-23 2018-06-27 Hexagon Technology Center GmbH Method for prediction of soil and/or plant condition
CN106649827A (zh) * 2016-12-29 2017-05-10 深圳前海弘稼科技有限公司 一种种植提醒方法、服务器及系统
CN106650679A (zh) * 2016-12-29 2017-05-10 深圳前海弘稼科技有限公司 种植设备控制方法、种植设备控制装置和服务器
US10554510B2 (en) * 2017-02-22 2020-02-04 Red Hat, Inc. Enabling additional metrics in a monitoring system to diagnose problems
CN106875285A (zh) * 2017-02-28 2017-06-20 河源弘稼农业科技有限公司 植物数据处理方法、植物数据处理装置和服务器
CN107066563A (zh) * 2017-03-31 2017-08-18 深圳前海弘稼科技有限公司 模拟植物种植的方法及系统
CN107292756A (zh) * 2017-04-13 2017-10-24 重庆光电信息研究院有限公司 基于气象大数据的人工智能学习方法及种植设备
CN107169107B (zh) * 2017-05-18 2021-02-02 广州市拓狗信息科技有限公司 一种基于大数据分析的水产养殖辅助方法及系统
CN107241403A (zh) * 2017-05-31 2017-10-10 深圳前海弘稼科技有限公司 推送方法及推送装置、服务器、设备和可读存储介质
CN107222549A (zh) * 2017-06-23 2017-09-29 深圳天谷智慧科技有限公司 一种教育微农场管理方法及系统
CN107483566A (zh) * 2017-08-02 2017-12-15 深圳市盛路物联通讯技术有限公司 一种基于物联网的城市绿化的方法及装置
CN107357935B (zh) * 2017-08-15 2020-02-07 杭州萌橙科技有限公司 基于程序云的智能种植设备控制方法
CN107390753B (zh) * 2017-08-29 2019-07-30 贵州省岚林阳环保能源科技有限责任公司 基于物联网云平台的智能植物生长环境调节装置与方法
CN107390754B (zh) * 2017-08-29 2019-07-30 贵州省岚林阳环保能源科技有限责任公司 基于物联网云平台的智能植物生长环境调节系统与方法
CN107527245A (zh) * 2017-08-31 2017-12-29 深圳前海弘稼科技有限公司 虚拟种植方法和虚拟种植系统
CN107450449A (zh) * 2017-09-14 2017-12-08 广东工业大学 一种农业监控系统
CN107844102B (zh) * 2017-09-29 2020-11-24 深圳春沐源控股有限公司 一种生产计划管理的方法及系统
CN107844089A (zh) * 2017-10-31 2018-03-27 深圳春沐源控股有限公司 一种种植预警的方法、系统及种植管理系统
CN107908689A (zh) * 2017-10-31 2018-04-13 江西省农业科学院农业经济与信息研究所 一种烟叶生长环境数据采集装置及其方法
CN107711453A (zh) * 2017-11-06 2018-02-23 无锡七百二十度科技有限公司 一种基于物联网的农田灌溉方法
CN108074236B (zh) * 2017-12-27 2020-05-19 Oppo广东移动通信有限公司 植物浇灌提醒方法、装置、设备及存储介质
CN108416517A (zh) * 2018-02-26 2018-08-17 深圳春沐源控股有限公司 无损鉴别方法及装置和无损鉴别系统
CN110309933A (zh) * 2018-03-23 2019-10-08 广州极飞科技有限公司 植株种植数据测量方法、作业路线规划方法及装置、系统
CN108564217B (zh) * 2018-04-16 2021-12-17 浙江工业大学 一种基于改进型混合粒子群算法的间作作物种植模式优化方法
CN108719004A (zh) * 2018-05-01 2018-11-02 沈建国 避免重复浇灌的农业用浇灌装置
CN108541565B (zh) * 2018-05-01 2020-11-06 舒城县利民农民专业合作社 避免重复浇灌的农业用浇灌装置
CN108782186A (zh) * 2018-05-08 2018-11-13 句容市宝启电子科技有限公司 绿化带智能养护方法
US11483981B1 (en) * 2018-05-14 2022-11-01 Crop One Holdings, Inc. Systems and methods for providing a low energy use farm
WO2019237200A1 (en) * 2018-06-12 2019-12-19 Paige Growth Technologies Inc. Precision agriculture system and related methods
CN109150958A (zh) * 2018-06-30 2019-01-04 湖北海纳天鹰科技发展有限公司 一种通用型NBIoT网络信息处理方法和装置
CN108934613B (zh) * 2018-09-25 2021-08-06 邻家健康科技(厦门)有限公司 一种太阳能光伏蔬菜种植大棚自动喷灌系统
CN109463260A (zh) * 2018-09-29 2019-03-15 广州绿桦环保科技有限公司 一种植物养护系统
CN109523751A (zh) * 2018-09-30 2019-03-26 康美中药材数据信息服务有限公司 一种药材生产土壤环境预警方法、电子设备和存储介质
CN110009522B (zh) * 2018-10-12 2021-06-08 贵州自留地科技有限责任公司 一种农业信息动态获取系统
US11676244B2 (en) 2018-10-19 2023-06-13 Mineral Earth Sciences Llc Crop yield prediction at field-level and pixel-level
KR102200314B1 (ko) * 2018-11-30 2021-01-08 주식회사 웨이브쓰리디 드론을 이용한 농작물 모니터링 시스템
TWI703529B (zh) * 2018-12-27 2020-09-01 蜂巢數據科技股份有限公司 作物生長階段計算方法及電腦程式產品
CN109767347B (zh) * 2018-12-29 2021-01-26 山东丰信农业服务连锁有限公司 一种基于互联网及智能的农业种植管理系统
CN109673280A (zh) * 2019-01-10 2019-04-26 珠海格力电器股份有限公司 基于微波雷达的栽培方法、装置、设备及处理器
CN109673318A (zh) * 2019-01-18 2019-04-26 王继民 一种智能健康种植系统
CN109600887A (zh) * 2019-01-28 2019-04-09 汇云时代科技(深圳)有限公司 一种日光模拟控制器
CN110111263B (zh) * 2019-03-29 2021-08-27 中国地质大学(武汉) 一种基于图像处理的烤烟种植指导系统
RU2723189C1 (ru) * 2019-06-21 2020-06-09 Автономная некоммерческая образовательная организация высшего образования "Сколковский институт науки и технологий" Способ автоматического подбора оптимальных параметров выращивания растений на основе методов машинного обучения
CN110335167B (zh) * 2019-06-25 2022-07-08 华侨大学 一种植物种植信息采集分析系统
CN110488690A (zh) * 2019-08-05 2019-11-22 安徽众星电气科技有限公司 一种工厂化石斛生态园自动化控制系统
CN110672815A (zh) * 2019-08-30 2020-01-10 安徽中科智能感知产业技术研究院有限责任公司 一种农业土壤数据传感器的检测方法及设备
CN110674186A (zh) * 2019-09-19 2020-01-10 云南农业大学 一种植物工厂数据处理方法
CN110766563A (zh) * 2019-10-22 2020-02-07 湖州灵粮生态农业有限公司 一种植物生长管理系统
CN110679452B (zh) * 2019-11-13 2024-05-28 福建天成宝得智能科技有限公司 基于射频组网技术的低功耗智能灌溉系统
CN110956381A (zh) * 2019-11-22 2020-04-03 黑龙江省农业科学院农业遥感与信息研究所 一种远程农业信息智能分析系统及农业环境调控方法
CN111062699A (zh) * 2019-12-23 2020-04-24 内蒙古自治区生物技术研究院 一种农作物全生长周期智能服务模型的构建方法及系统
CN111026208A (zh) * 2019-12-30 2020-04-17 滁州联润生态农业发展有限公司 一种苗木栽培园林综合管理操作系统
CN111436296A (zh) * 2020-01-08 2020-07-24 乐凯拜伦灯光有限公司 一种用于植物生长和发育的人工智能生长方法
US11382260B2 (en) * 2020-02-03 2022-07-12 International Business Machines Corporation Estimation of crop type and/or sowing date
WO2021166558A1 (ja) * 2020-02-17 2021-08-26 パナソニックIpマネジメント株式会社 環境条件抽出システム、環境条件抽出方法及びプログラム
WO2021165716A1 (en) * 2020-02-18 2021-08-26 Ivry Gad System and method for indoor harvesting of fresh produce
CN111507857A (zh) * 2020-04-22 2020-08-07 青岛逸景数字科技有限公司 一种基于物联网技术的数字化农业种植系统和方法
CN111639904A (zh) * 2020-05-09 2020-09-08 广州海睿信息科技有限公司 基于物联网的果蔬种植管理系统
CN111480554A (zh) * 2020-06-04 2020-08-04 宁夏大学 农田灌区水肥气热药一体化智能灌溉系统
CN111752192A (zh) * 2020-06-10 2020-10-09 元谋县果然好农业科技有限公司 一种葡萄生理情况在线监控系统
CN113875514B (zh) 2020-07-03 2023-02-03 株式会社理光 栽培方法、信息处理方法、控制方法、信息处理装置及控制装置
US11666004B2 (en) 2020-10-02 2023-06-06 Ecoation Innovative Solutions Inc. System and method for testing plant genotype and phenotype expressions under varying growing and environmental conditions
US20220104437A1 (en) * 2020-10-02 2022-04-07 Ecoation Innovative Solutions Inc. Reduction of time of day variations in plant-related data measurements
US20220107297A1 (en) * 2020-10-02 2022-04-07 Ecoation Innovative Solutions Inc. Platform for real-time identification and resolution of spatial production anomalies in agriculture
CN112119840A (zh) * 2020-10-10 2020-12-25 紫云县惠农种植养殖农民专业合作社 一种吉祥草的种植方法
CN112230696B (zh) * 2020-10-14 2022-01-28 王峰 一种出菇车间智能控制温湿度均衡分布设备及其使用方法
RU2758768C1 (ru) * 2020-12-10 2021-11-01 Сергей Борисович Огнивцев Способ управления продукционными и технологическими процессами выращивания сельскохозяйственных культур
CN112997862B (zh) * 2021-04-13 2023-06-23 湖南创新佳农科技有限公司 一种智慧农业智能灌溉装置及其灌溉方法
CN113155188A (zh) * 2021-04-15 2021-07-23 浙江天演维真网络科技股份有限公司 一种基于大数据和作物生长环境模型的趋势分析方法
CN112816357B (zh) * 2021-04-17 2021-07-02 潍坊创科种苗有限公司 称重法监测西瓜生长成熟度的装置
CN113475360A (zh) * 2021-05-17 2021-10-08 中国长江三峡集团有限公司 一种消落带植被自动喷灌系统及施工方法
CN113179925B (zh) * 2021-05-25 2023-06-16 赵钧一 一种新型垂直绿化墙灌溉系统
CN113406075B (zh) * 2021-06-08 2024-06-25 内蒙古工业大学 植物生长环境的设置方法和植物生长监测装置
CN113435566B (zh) * 2021-06-22 2022-04-12 布瑞克农业大数据科技集团有限公司 一种农场作物施肥的方法、系统、装置及存储介质
CN113557905A (zh) * 2021-07-30 2021-10-29 福建省林业科学研究院 一种香榧智能栽培方法
CN113933299B (zh) * 2021-10-12 2022-10-14 一鼎(福建)生态园林建设有限公司 基于物联网的果蔬种植管理系统
CN113884138B (zh) * 2021-10-14 2022-05-17 一鼎(福建)生态园林建设有限公司 基于大数据的种植智能监控系统
CN114467636A (zh) * 2021-12-22 2022-05-13 贵州省生物研究所 一种基于智慧网络的温湿度感应恒定浇灌菇、苗装置
CN114546006B (zh) * 2022-02-15 2022-12-23 中国热带农业科学院热带作物品种资源研究所 一种腰果仓储环境的智能控制方法及系统
CN114519538B (zh) * 2022-03-03 2024-03-26 济宁市任城区双瑞家庭农场 一种有效控制营养物质循环利用的多营养层次养殖系统
CN114568265B (zh) * 2022-03-22 2023-07-18 武汉鸿榛园林绿化工程有限公司 一种基于人工智能的园林绿化维护智能监测管理系统
CN114600751A (zh) * 2022-03-23 2022-06-10 西安建筑科技大学 一种基于计算机视觉监测的灌溉系统及方法
CN114707952B (zh) * 2022-03-23 2024-06-21 浙江大学 一种智慧种植监控方法及系统
CN115226516B (zh) * 2022-07-07 2023-09-26 西北农林科技大学 一种设施光与二氧化碳环境协同调控方法
CN115437431A (zh) * 2022-08-23 2022-12-06 芜湖市新城园林建设有限公司 基于互联网技术应用的园林管控方法及系统
CN115796624B (zh) * 2023-02-13 2023-04-04 广东省木链网科技股份有限公司 一种基于碳中和目标的环保植树管理平台
CN116503200B (zh) * 2023-05-05 2024-05-24 四川省农业科学院园艺研究所 一种基于数据分析的国兰栽培环境实时监管系统
CN116578047B (zh) * 2023-05-11 2024-04-30 江苏里下河地区农业科学研究所 一种用于辣椒生产的精细化智能控制方法及系统
CN116664333B (zh) * 2023-08-02 2023-11-14 贵州通利数字科技有限公司 基于物联网的信息资源系统
CN116757510B (zh) * 2023-08-21 2023-10-27 贵州正易科技有限公司 一种园林绿化工程项目智能管理系统
CN116776129B (zh) * 2023-08-22 2023-10-31 贵州中昂科技有限公司 一种多源农业数据的采集管理方法
CN117215351A (zh) * 2023-09-16 2023-12-12 张家港泽诺科技有限公司 一种食用菌种植环境智能监测预警系统
CN117178862B (zh) * 2023-11-08 2024-02-02 四川嘉陵江桐子壕航电开发有限公司 一种园林浇灌信息采集监控方法
CN117541177A (zh) * 2023-11-09 2024-02-09 南京邮电大学 一种基于大数据的智慧农业监控管理方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070289207A1 (en) * 2005-12-21 2007-12-20 May George A Expert system for controlling plant growth in a contained environment
CN102014165A (zh) * 2010-08-12 2011-04-13 北京天地互连信息技术有限公司 远程农业信息智能分析系统及农业环境调控方法
CN103336517A (zh) * 2013-07-02 2013-10-02 周庆芬 一种智能农业综合管理系统
CN104186186A (zh) * 2014-09-12 2014-12-10 吴慧 一种农作物的大棚种植系统
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

Family Cites Families (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
SU988241A1 (ru) * 1981-03-06 1983-01-15 Агрофизический Научно-Исследовательский Институт Всесоюзной Ордена Ленина Академии Сельскохозяйственных Наук Им.В.И.Ленина Устройство дл выращивани растений
RU2091009C1 (ru) * 1993-07-08 1997-09-27 Беркович Юлий Александрович Установка для конвейерного выращивания растений и ее вариант
RU78400U1 (ru) * 2008-04-21 2008-11-27 Министерство сельского хозяйства Российской Федерации Федеральное государственное образовательное учреждение высшего профессионального образования "Челябинский государственный агроинженерный университет" (ФГОУ ВПО ЧГАУ) Установка для выращивания растений
CN101286060A (zh) * 2008-05-16 2008-10-15 昆明理工大学 基于决策支持的控制植物生长环境的方法
MY151175A (en) * 2009-01-22 2014-04-30 Mimos Berhad A device for controlling and profiling field conditions and a method therefor
US8056284B2 (en) 2010-01-20 2011-11-15 Wen Hua He Auto-irrigating case
CN201594181U (zh) * 2010-02-09 2010-09-29 高明亮 一种植物生长环境智能控制装置
KR20120075526A (ko) * 2010-11-22 2012-07-09 (주)홈시큐넷 시설재배장의 원격 관리시스템
JP5861256B2 (ja) 2011-01-25 2016-02-16 富士通株式会社 農作業支援方法及び農作業支援装置
MX337904B (es) * 2011-06-27 2016-03-28 Basf Plant Science Co Gmbh Dispositivo de exploracion para explorar epecimienes de planta.
CN102498891B (zh) * 2011-11-08 2013-07-03 山东大学 一种湿地植被恢复物种筛选方法
CN102550371A (zh) * 2011-11-15 2012-07-11 无锡科技职业学院 基于物联网技术的小区或别墅用自动灌溉控制系统及方法
JP5525554B2 (ja) * 2012-02-16 2014-06-18 株式会社Nttドコモ 栽培支援装置、栽培支援システム、栽培支援方法及びプログラム
CN102868749A (zh) * 2012-09-20 2013-01-09 张晋 一种农业种植、饲养的物联网云服务系统及服务流程方法
CN102884932B (zh) * 2012-10-29 2014-02-19 江苏物联网研究发展中心 基于种植专家云的智能型土培植物生长栽培系统
CN103814752B (zh) * 2012-11-19 2016-10-05 美新微纳传感系统有限公司 一种冬虫夏草智能养殖系统
JP5972846B2 (ja) 2013-10-01 2016-08-17 ネポン株式会社 農用機器制御方法、プログラム、システム、および装置
CN203490529U (zh) * 2013-10-12 2014-03-19 郑州航空工业管理学院 一种基于物联网的智能种植装置
CN104012375A (zh) * 2014-05-07 2014-09-03 娄志 一种农业自动感知灌溉监控系统
JP2014193174A (ja) 2014-05-22 2014-10-09 Casio Comput Co Ltd 植物管理装置及びプログラム
CN104012376B (zh) * 2014-06-12 2017-06-20 张和暄 基于生态环境信息的智能浇花系统、方法及其装置
CN104216373A (zh) * 2014-09-03 2014-12-17 太原理工大学 基于智能云的家庭水管理系统
CN104267699A (zh) * 2014-09-30 2015-01-07 常州机电职业技术学院 一种基于物联网技术的农业大棚智能控制装置及其工作方法
CN104331109A (zh) * 2014-10-28 2015-02-04 许祥洪 温室智能控制方法及温室智能控制系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070289207A1 (en) * 2005-12-21 2007-12-20 May George A Expert system for controlling plant growth in a contained environment
CN102014165A (zh) * 2010-08-12 2011-04-13 北京天地互连信息技术有限公司 远程农业信息智能分析系统及农业环境调控方法
CN103336517A (zh) * 2013-07-02 2013-10-02 周庆芬 一种智能农业综合管理系统
CN104186186A (zh) * 2014-09-12 2014-12-10 吴慧 一种农作物的大棚种植系统
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

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3330905A4 *

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106709811A (zh) * 2016-12-08 2017-05-24 党兴仁 一种蔬菜生长管理方法及系统
WO2018196167A1 (zh) * 2017-04-28 2018-11-01 深圳前海弘稼科技有限公司 温室大棚的控制方法、控制装置和服务器
JP2020527328A (ja) * 2017-06-14 2020-09-10 グロー ソリューションズ テック エルエルシー 成長ポッドにおける自己学習のためのシステムおよび方法
JP2020522988A (ja) * 2017-06-14 2020-08-06 グロー ソリューションズ テック エルエルシー 成長ポッドにおける植物の重量を管理するためのシステムおよび方法
JP2020522991A (ja) * 2017-06-14 2020-08-06 グロー ソリューションズ テック エルエルシー 成長ポッド内の植物体に関する収穫タイミングを決定するためのシステムおよび方法
JP2020523980A (ja) * 2017-06-14 2020-08-13 グロー ソリューションズ テック エルエルシー 成長ポッドをプログラムするためのシステムおよび方法
WO2020227812A1 (en) * 2019-05-13 2020-11-19 CO2 GRO Inc. Control of pathogens by foliar spraying with co2-infused water
CN111488369A (zh) * 2020-04-01 2020-08-04 黑龙江省农业科学院农业遥感与信息研究所 一种农业科技咨询服务平台
CN112293077A (zh) * 2020-11-11 2021-02-02 四川省农业科学院园艺研究所 一种缩短蜡梅育种年限的方法
CN113111672A (zh) * 2021-04-13 2021-07-13 中国科学院东北地理与农业生态研究所 一种真湿地植物的判定方法
CN116502962A (zh) * 2023-06-29 2023-07-28 乐番农业科技(北京)有限公司 一种植物种质资源智能管理方法和系统
CN116502962B (zh) * 2023-06-29 2023-11-07 乐番农业科技(北京)有限公司 一种植物种质资源智能管理方法和系统
CN116824380A (zh) * 2023-08-30 2023-09-29 山东孟子居生态农业股份有限公司 一种智慧农业云平台监控系统
CN116824380B (zh) * 2023-08-30 2023-11-28 山东孟子居生态农业股份有限公司 一种智慧农业云平台监控系统

Also Published As

Publication number Publication date
CN104866970A (zh) 2015-08-26
CN104866970B (zh) 2018-07-24
AU2016266460B2 (en) 2019-11-07
US20180146626A1 (en) 2018-05-31
JP2018517220A (ja) 2018-06-28
RU2688234C1 (ru) 2019-05-21
EP3330905A1 (en) 2018-06-06
AU2016266460A1 (en) 2018-01-25
US10966377B2 (en) 2021-04-06
CA2987319A1 (en) 2016-12-01
EP3330905A4 (en) 2019-05-08

Similar Documents

Publication Publication Date Title
WO2016188384A1 (zh) 智能种植管理方法和智能种植设备
JP4876439B2 (ja) 植物育成情報の提供方法
KR20200029657A (ko) 작물 이미지 빅데이터를 이용한 영농 자동화 시스템
CN105700593B (zh) 一种植物种植监控系统及其方法
US20150164009A1 (en) System and method for garden monitoring and management
CN110771442A (zh) 基于物联网的农业种植方法和系统
CN105045321A (zh) 基于物联网应用设计的云平台综合管理方法
KR101893822B1 (ko) 벼의 생육시기에 따라 논의 담수 수위가 조절되는 용수자동화 관리시스템
CN205883318U (zh) 一种农业物联网远程监测与控制系统
CN108650321A (zh) 一种智能菜园控制系统及其控制方法
Mithunesh et al. Aeroponic based controlled environment based farming system
KR20220082952A (ko) 작물 이미지 빅데이터를 이용한 영농 자동화 시스템
CN111176238B (zh) Aipa智慧决策型精准农业系统
KR20230004218A (ko) 시설재배 복합환경 제어 시스템
WO2019237421A1 (zh) 一种无人机植保服务定制系统及方法
US20230153926A1 (en) Automated Plant Probe System and Method
JP2004298069A (ja) 植物育成システムおよびこれを用いた植物育成情報サービス
CN115486358A (zh) 一种多年生牧草滴灌自动化灌溉管理决策控制系统
CN111670733B (zh) 一种阳台植物种植系统
CN115471354A (zh) 一种植物的自动化种植系统及方法
JP2004298068A (ja) 植物育成システムおよびこれを用いた植物育成サービス、ならびに植物育成装置
CN214708748U (zh) 农作物精准营养灌溉管控系统
JP4645248B2 (ja) 植物育成情報の提供方法
KR102321137B1 (ko) 생물의 최적 생육조건 데이터 수집/제공 시스템 및 방법
Soniya et al. IoT-Based Framework For Smart Agriculture

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: 16799272

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2987319

Country of ref document: CA

Ref document number: 2018513711

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2017145656

Country of ref document: RU

WWE Wipo information: entry into national phase

Ref document number: 2016799272

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 15576899

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2016266460

Country of ref document: AU

Date of ref document: 20160523

Kind code of ref document: A