CN109145785A - The determination method and apparatus of plant-nursing mode - Google Patents
The determination method and apparatus of plant-nursing mode Download PDFInfo
- Publication number
- CN109145785A CN109145785A CN201810879413.XA CN201810879413A CN109145785A CN 109145785 A CN109145785 A CN 109145785A CN 201810879413 A CN201810879413 A CN 201810879413A CN 109145785 A CN109145785 A CN 109145785A
- Authority
- CN
- China
- Prior art keywords
- plant
- treated
- sample
- identification model
- nursing care
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/36—Indoor scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Abstract
The present invention provides a kind of determination method and apparatus of plant-nursing mode.This method comprises: obtaining the image of plant to be treated;The structure feature of the plant to be treated is extracted from described image, the structure feature includes: at least one of root, stem, leaf, flower and fruit;According to the structure feature and identification model of the plant to be treated, determine that the corresponding nursing care mode of the plant to be treated, the identification model are used to indicate the relationship between the structure feature of plant and the nursing care mode of plant.Compared to the prior art, this method eliminates the process manually consulted, and improves the efficiency for obtaining plant-nursing mode.
Description
Technical field
The present invention relates to big data technology more particularly to a kind of determination method and apparatus of plant-nursing mode.
Background technique
Plant has the effects that environment purification, reduces radiation and absorb toxic gas, therefore people are often on the ground of office
Just and occupy the plant that residence plants each shape colors.Different types of plant-nursing mode is different, and same plant is in difference
The nursing care mode of growth conditions is also different.
In the prior art, plant is obtained generally by internet searching, the method for browsing the artificial enquiries such as pertinent texts
Nursing care mode can undoubtedly have asking for inefficiency however, artificial enquiry method needs to expend a large amount of time and efforts of user
Topic.
Summary of the invention
The embodiment of the present invention provides a kind of determination method and apparatus of plant-nursing mode, obtains plant for improving user
Nursing care mode efficiency.
In a first aspect, the embodiment of the present invention provides a kind of determination method of plant-nursing mode, comprising:
Obtain the image of plant to be treated;
The structure feature of the plant to be treated is extracted from described image, the structure feature includes: root, stem, leaf, flower
At least one of with fruit;
According to the structure feature and identification model of the plant to be treated, the corresponding nursing side of the plant to be treated is determined
Formula, the identification model are used to indicate the relationship between the structure feature of plant and the nursing care mode of plant.
Optionally, the structure feature and identification model according to the plant to be treated, determines the plant to be treated
Corresponding nursing care mode, comprising:
According to the structure feature of the plant to be treated, determine the plant to be treated at long status;
Identified to described at long status using the identification model, it is determining with described at the corresponding nursing side of long status
Formula.
Optionally, the structure feature and identification model according to the plant to be treated obtains the plant to be treated
Before corresponding nursing care mode, further includes:
According to the training sample prestored, the identification model is determined.
Optionally, the training sample that the basis prestores determines the identification model, comprising:
According to the structure feature of sample each in the training sample, determine each sample at long status;
According to each sample at long status, the corresponding state feature vector of each sample is constructed;
According to the labeled nursing care mode of the state feature vector of each sample and each sample, the identification mould is determined
Type.
Optionally, described to be identified to described at long status using the identification model, it is determining and described at long status
Corresponding nursing care mode, comprising:
According to the plant to be treated at long status, the state feature vector of the plant to be treated is constructed;
The state feature vector of the plant to be treated is inputted in the identification model, is obtained with described into long status pair
The nursing care mode answered.
Optionally, the nursing care mode labeled according to the state feature vector of each sample and each sample, determines
The identification model, comprising:
Using deep learning method to the labeled nursing care mode of the state feature vector of each sample and each sample into
Row training, obtains the identification model.
Optionally, the corresponding nursing care mode of plant to be treated described in terminal display is passed through using augmented reality AR technology.
Second aspect, the present invention provide a kind of determining device of plant-nursing mode, comprising:
Module is obtained, for obtaining the image of plant to be treated;
Extraction module, for extracting the structure feature of the plant to be treated, the structure feature packet from described image
It includes: at least one of root, stem, leaf, flower and fruit;
First determining module determines described wait protect for the structure feature and identification model according to the plant to be treated
The corresponding nursing care mode of plant is managed, the identification model is used to indicate between the structure feature of plant and the nursing care mode of plant
Relationship.
Optionally, first determining module, comprising:
First determination unit, for the structure feature according to the plant to be treated, determine the plant to be treated at
Long status;
Identification module, for being identified to described at long status using the identification model, the determining and growth shape
The corresponding nursing care mode of state.
Optionally, described device, further includes: the second determining module, for determining the knowledge according to the training sample prestored
Other model.
Optionally, second determining module, comprising:
Second determination unit determines each sample for the structure feature according to sample each in the training sample
At long status;
Construction unit, for, at long status, constructing the corresponding state feature vector of each sample according to each sample;
Third determination unit, for the nursing side labeled according to the state feature vector of each sample and each sample
Formula determines the identification model.
Optionally, the identification module, specifically for, at long status, building is described wait protect according to the plant to be treated
Manage the state feature vector of plant;And input the state feature vector of the plant to be treated in the identification model, it obtains
With described at the corresponding nursing care mode of long status.
Optionally, the second determining module, specifically for the state feature vector using deep learning method to each sample
The nursing care mode being labeled with each sample is trained, and obtains the identification model.
Optionally, described device, further includes: display module, for passing through terminal display institute using augmented reality AR technology
State the corresponding nursing care mode of plant to be treated.
The third aspect, the present invention provide a kind of computer readable storage medium, are stored thereon with computer program, the meter
Calculation machine program realizes the determination method of above-mentioned plant-nursing mode when being executed by processor.
Fourth aspect, the present invention provide a kind of server, comprising:
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to realize above-mentioned plant-nursing mode really via the executable instruction is executed
Determine method.
The determination method of plant-nursing mode provided by the invention, by obtaining the image of plant to be treated, then from this
The structure feature of plant to be treated is extracted in image, finally according to the structure feature and identification model of the plant to be treated, really
Determine the corresponding nursing care mode of the plant to be treated and compared to the prior art eliminate the process manually consulted, improves acquisition
The efficiency of plant-nursing mode.
Detailed description of the invention
Fig. 1 is the flow chart of the embodiment one of the determination method of plant-nursing mode provided by the invention;
Fig. 2 is the flow chart of the embodiment two of the determination method of plant-nursing mode provided by the invention;
Fig. 3 is the flow chart of the embodiment three of the determination method of plant-nursing mode provided by the invention;
Fig. 4 is identification model schematic diagram provided by the invention;
Fig. 5 is the structural schematic diagram of the embodiment one of the determining device of plant-nursing mode provided by the invention;
Fig. 6 is the structural schematic diagram of the embodiment two of the determining device of plant-nursing mode provided by the invention;
Fig. 7 is the hardware structural diagram of server provided by the invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
In order to understand the nursing care mode of certain plant, in the prior art, generally by internet searching, pertinent texts are browsed
The method of equal artificial enquiries obtains the nursing care mode of the plant, however, artificial enquiry method can undoubtedly have asking for inefficiency
Topic.
The present invention provides a kind of determination method of plant-nursing mode, by obtaining the image of plant to be treated, from the figure
The structure feature that the plant to be treated is extracted as in can be obtained in conjunction with the structure feature and preparatory trained identification model
The corresponding nursing care mode of the plant to be treated.Compared to the prior art, the process manually consulted is eliminated, improves and obtains plant
The efficiency of nursing care mode.
Optionally, method provided by the invention can be executed by the processing equipment such as processor for being equipped with the terminal of corresponding software
Corresponding software code realization can also be executed corresponding software code by the processing equipment of the terminal, and combine other hardware real
Body is realized, can also be realized by server.The following examples are illustrated by executing subject of server.
How to be solved with technical solution of the specifically embodiment to technical solution of the present invention and the application below above-mentioned
Technical problem is described in detail.These specific embodiments can be combined with each other below, for the same or similar concept
Or process may repeat no more in certain embodiments.Below in conjunction with attached drawing, the embodiment of the present invention is described.
Fig. 1 is the flow chart of the embodiment one of the determination method of plant-nursing mode provided by the invention, as shown in Figure 1,
The determination method of plant-nursing mode provided in this embodiment, comprising:
S101, the image for obtaining plant to be treated.
Optionally, above-mentioned image can be obtained using the modes such as taking pictures and scan by the camera of terminal, get above-mentioned
The step of after image, which is sent to server, executes S102-S103 so as to server.
S102, the structure feature that the plant to be treated is extracted from described image, the structure feature include: root, stem,
At least one of leaf, flower and fruit.
S103, according to the structure feature and identification model of the plant to be treated, determine that the plant to be treated is corresponding
Nursing care mode, the identification model are used to indicate the relationship between the structure feature of plant and the nursing care mode of plant.
Wherein, on the basis of obtaining the structure feature of plant to be treated, the plant to be treated can be determined as follows
The corresponding nursing care mode of object:
According to the structure feature of the plant to be treated, determine the plant to be treated at long status;
Identified to described at long status using the identification model, it is determining with described at the corresponding nursing side of long status
Formula.
It is illustrated so that plant to be treated is epipremnum aureum as an example below:
Firstly, terminal camera obtains the image of the epipremnum aureum using scanning or by the way of taking pictures, then the image is sent out
Server is given, above-mentioned identification model is stored in server, after server obtains the image of above-mentioned epipremnum aureum, is mentioned from the image
The structure feature of epipremnum aureum is taken, for example has extracted the feature of the leaf of epipremnum aureum, the epipremnum aureum is then determined according to the feature of the leaf of epipremnum aureum
At long status, it is assumed that obtain epipremnum aureum it is current be at long status: blade tip curling is simultaneously withered brown;Server inputs this at long status
Identification model identifies identification model this at long status, after identifying successfully, identification model will export with it is above-mentioned at
The corresponding nursing care mode of long status.And then the nursing care mode can be returned to terminal and shown by server, so that user Ke Tong
It crosses terminal and shows that result gets the mode of nursing of the epipremnum aureum in the case where blade tip crimps and is withered brown.
Optionally, above-mentioned identification model can not only export nursing care mode corresponding with plant to be treated, can also identify
The title of plant to be treated out.For continuing above-mentioned example, server inputs identification model at long status for plant to be treated
Afterwards, identification model exports the title of also exportable plant to be treated while corresponding nursing care mode, this can be waited protecting by server
The title and nursing care mode for managing plant return to terminal and are shown, that is to say, that the content that terminal is shown both had included wait protect
The title for managing plant, also includes nursing care mode of the plant to be treated under currently at long status.It is not aware that currently in user
When scanning or shooting image in the case where what plant, the method for the present embodiment also may inform the user that the title of the plant.It improves
User experience.
The determination method of plant-nursing mode provided in this embodiment, by obtaining the image of plant to be treated, then from
The structure feature of plant to be treated is extracted in the image, finally according to the structure feature and identification model of the plant to be treated,
Determine compared to the prior art the corresponding nursing care mode of the plant to be treated eliminates the process manually consulted, improves and obtain
Take the efficiency of plant-nursing mode.
Fig. 2 is the flow chart of the embodiment two of the determination method of plant-nursing mode provided by the invention, according to
The structure feature and identification model of plant to be treated will be determined first before determining the corresponding nursing care mode of the plant to be treated
The identification model.As shown in Fig. 2, the determination method of plant-nursing mode provided in this embodiment, describes determining identification model
A kind of achievable mode, i.e., according to the training sample that prestores, determine the identification model, specifically can include:
S201, according to the structure feature of sample each in the training sample, determine each sample at long status.
S202, according to each sample at long status, construct the corresponding state feature vector of each sample.
Wherein, training sample contains the plant of each shape colors, such as: cactus, epipremnum aureum, hanging basket, money tree etc..With green
For trailing plants sample: after the image for obtaining the epipremnum aureum sample, extracting the structure feature of the epipremnum aureum sample, it is assumed that the epipremnum aureum extracted
The structure feature of sample includes the feature of stem and the feature of leaf, can be by way of artificial judgment according to the feature of the stem and leaf
Feature determine the epipremnum aureum sample at long status, it is assumed that the obtained epipremnum aureum sample at long status be stem 0.5cm, leaf margin become
It is brown, then can be at the state feature vector that long status constructs the epipremnum aureum sample according to thisThus the corresponding state feature vector of the epipremnum aureum sample has just been obtained.Accordingly
, the state feature vector that similar method obtains each sample can be used.
It should be understood that in above-mentioned training sample, a kind of plant may include multiple samples, such as this plant of epipremnum aureum
It may include multiple samples, but the structure feature extracted from multiple epipremnum aureum sample is different, for example extract
The feature and leaf of stem are characterized in difference, therefore the corresponding state feature vector of different epipremnum aureum samples is also different.Epipremnum aureum sample
Quantity is more, and the basic data of model training is more detailed, recognition result of the identification model obtained according to the sample to epipremnum aureum
More accurate, obtained nursing care mode accuracy also correspondinglys increase.
Optionally, the state feature vector of training sample can also include the structures such as root, stem, leaf, flower and the fruit of plant
Shape, size and color, so that identification model can identify the type of plant to be treated and title according to these information
Out.
S203, the nursing care mode being labeled according to the state feature vector of each sample and each sample, determine the knowledge
Other model.
Wherein, before model training, the nursing care mode to each sample is needed to be marked, for example, can by state feature to
Amount isEpipremnum aureum sample nursing care mode label are as follows: season of growth watering is insufficient,
Basin soil rewaters when cannot be completely dried up.
It should be understood that when the nursing care mode to sample is marked, it need to be in conjunction with the meaning of the professional of plant cultivation
See and is marked.
The state feature vector of each sample and on the basis of corresponding nursing care mode in obtaining training sample, can
The state feature vector of each sample and corresponding nursing care mode are trained using deep learning method, obtained described
Identification model.
The determination method of plant-nursing mode provided in this embodiment describes according to the training sample prestored, determines institute
A kind of achievable mode of identification model is stated, specifically: first according to the structure feature of sample each in training sample, determine
Each sample at long status;Then the corresponding state feature vector of each sample is constructed at long status according to each sample;
Nursing care mode finally labeled according to the state feature vector of each sample and each sample, determines the identification model;?
To after the identification model, it is corresponding plant to be treated can be directly obtained with the identification model according to the image of plant to be treated
Nursing care mode, it is compared to the prior art, time saving and energy saving, improve user experience degree.
Fig. 3 is the flow chart of the embodiment three of the determination method of plant-nursing mode provided by the invention.As shown in figure 3,
The determination method of plant-nursing mode provided in this embodiment is that side further can be achieved to one kind of S103 in above-described embodiment
The description of formula, S103 are specifically included:
S301, according to the structure feature of the plant to be treated, determine the plant to be treated at long status.
S302, according to the plant to be treated at long status, construct the state feature vector of the plant to be treated.
S303, the state feature vector of the plant to be treated is inputted in the identification model, is obtained and the growth
The corresponding nursing care mode of state.
Where it is assumed that the state feature vector that S302 obtains plant to be treated isShape shown in Figure 4, will obtaining
State feature vector isIt inputs in identification model, identification model can export the corresponding nursing care mode of the plant to be treated.
Athlete's state evaluating method provided in this embodiment, further includes:
S304, the corresponding nursing care mode of plant to be treated described in terminal display is passed through using augmented reality AR technology.
It wherein, can be by the image of the nursing care mode of plant to be treated and plant to be treated using augmented reality AR technology
User is showed simultaneously by terminal, further improves user experience.
The determination method of plant-nursing mode provided in this embodiment, the one kind for describing determining plant-nursing mode can be real
Existing mode, specifically: according to the plant to be treated at long status, construct the state feature of the plant to be treated to
Amount;The state feature vector of the plant to be treated is inputted in the identification model, obtain with it is described corresponding at long status
Nursing care mode.Compared to the prior art, the process manually consulted is eliminated, the efficiency for obtaining plant-nursing mode is improved.
Fig. 5 is the structural schematic diagram of the embodiment one of the determining device of plant-nursing mode provided by the invention, such as Fig. 5 institute
Show, the determining device of plant-nursing mode provided in this embodiment, comprising:
Module 501 is obtained, for obtaining the image of plant to be treated;
Extraction module 502, for extracting the structure feature of the plant to be treated, the structure feature from described image
It include: at least one of root, stem, leaf, flower and fruit;
First determining module 503, for the structure feature and identification model according to the plant to be treated, determine it is described to
The corresponding nursing care mode of plant is nursed, the identification model is used to indicate between the structure feature of plant and the nursing care mode of plant
Relationship.
The determining device of plant-nursing mode provided in this embodiment, can be used for executing the method in embodiment illustrated in fig. 1,
That the realization principle and technical effect are similar is similar for it, and details are not described herein.
Fig. 6 is the structural schematic diagram of the embodiment two of the determining device of plant-nursing mode provided by the invention, such as Fig. 6 institute
Show, the determining device of plant-nursing mode provided in this embodiment, first determining module 503, comprising:
First determination unit 601 determines the plant to be treated for the structure feature according to the plant to be treated
At long status;
Recognition unit 602, for being identified to described at long status using the identification model, the determining and growth
The corresponding nursing care mode of state.
Optionally, the determining device of plant-nursing mode provided in this embodiment, further includes:
Second determining module 603, for determining the identification model according to the training sample prestored.
Optionally, second determining module 603, comprising:
Second determination unit 604 determines each sample for the structure feature according to sample each in the training sample
At long status;
Construction unit 605, at long status, constructed according to each sample each sample corresponding state feature to
Amount;
Third determination unit 606, for the nursing labeled according to the state feature vector of each sample and each sample
Mode determines the identification model.
Optionally, the recognition unit 602, specifically for according to the plant to be treated at long status, described in building
The state feature vector of plant to be treated;And input the state feature vector of the plant to be treated in the identification model,
It obtains with described into the corresponding nursing care mode of long status.
Optionally, the second determining module 603, specifically for using deep learning method to the state feature of each sample to
The nursing care mode that amount and each sample are labeled is trained, and obtains the identification model.
Optionally, the determining device of plant-nursing mode provided in this embodiment, further includes:
Display module 607, for passing through the corresponding shield of plant to be treated described in terminal display using augmented reality AR technology
Reason mode.
The determining device of plant-nursing mode provided in this embodiment, can be used for executing in Fig. 2 or embodiment illustrated in fig. 3
Method, it is similar that the realization principle and technical effect are similar, and details are not described herein.
Fig. 7 is the hardware structural diagram of server provided by the invention.As shown in fig. 7, the server of the present embodiment can
To include:
Memory 701, for storing program instruction.
The processor 702, for being performed the method for realizing any of the above-described embodiment description in described program instruction,
Specific implementation principle can be found in above-described embodiment, and details are not described herein again for the present embodiment.
The present invention provides a kind of computer readable storage medium, is stored thereon with computer program, the computer program
The determination method of plant-nursing mode described in any of the above-described embodiment is realized when being executed by processor.
The present invention also provides a kind of program product, described program product includes computer program, and the computer program is deposited
In readable storage medium storing program for executing, at least one processor can read the computer program, institute from the readable storage medium storing program for executing for storage
Plant-nursing mode described in any of the above-described embodiment can be realized by stating when at least one processor executes the computer program
Determine method.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or logical of device or unit
Letter connection can be electrical property, mechanical or other forms.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
Equipment (can be personal computer, server or the network equipment etc.) or processor (English: processor) execute this hair
The part steps of bright each embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory
(English: Read-Only Memory, abbreviation: ROM), random access memory (English: Random Access Memory, letter
Claim: RAM), the various media that can store program code such as magnetic or disk.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (16)
1. a kind of determination method of plant-nursing mode characterized by comprising
Obtain the image of plant to be treated;
The structure feature of the plant to be treated is extracted from described image, the structure feature includes: root, stem, leaf, Hua Heguo
It is at least one of real;
According to the structure feature and identification model of the plant to be treated, the corresponding nursing care mode of the plant to be treated is determined,
The identification model is used to indicate the relationship between the structure feature of plant and the nursing care mode of plant.
2. the method according to claim 1, wherein the structure feature and knowledge according to the plant to be treated
Other model determines the corresponding nursing care mode of the plant to be treated, comprising:
According to the structure feature of the plant to be treated, determine the plant to be treated at long status;
Identified to described at long status using the identification model, it is determining with described at the corresponding nursing care mode of long status.
3. according to the method described in claim 2, it is characterized in that, the structure feature and knowledge according to the plant to be treated
Other model, before obtaining the corresponding nursing care mode of the plant to be treated, further includes:
According to the training sample prestored, the identification model is determined.
4. according to the method described in claim 3, it is characterized in that, the training sample that the basis prestores, determines the identification
Model, comprising:
According to the structure feature of sample each in the training sample, determine each sample at long status;
According to each sample at long status, the corresponding state feature vector of each sample is constructed;
According to the labeled nursing care mode of the state feature vector of each sample and each sample, the identification model is determined.
5. according to the method described in claim 2, it is characterized in that, it is described using the identification model to it is described at long status into
Row identification, it is determining with described at the corresponding nursing care mode of long status, comprising:
According to the plant to be treated at long status, the state feature vector of the plant to be treated is constructed;
The state feature vector of the plant to be treated is inputted in the identification model, obtain with it is described corresponding at long status
Nursing care mode.
6. according to the method described in claim 3, it is characterized in that, the state feature vector according to each sample and each
The labeled nursing care mode of sample, determines the identification model, comprising:
It is instructed using the deep learning method nursing care mode labeled to the state feature vector of each sample and each sample
Practice, obtains the identification model.
7. the method according to claim 1, wherein further include:
The corresponding nursing care mode of plant to be treated described in terminal display is passed through using augmented reality AR technology.
8. a kind of determining device of plant-nursing mode characterized by comprising
Module is obtained, for obtaining the image of plant to be treated;
Extraction module, for extracting the structure feature of the plant to be treated from described image, the structure feature includes:
At least one of root, stem, leaf, flower and fruit;
First determining module determines the plant to be treated for the structure feature and identification model according to the plant to be treated
The corresponding nursing care mode of object, the identification model are used to indicate the pass between the structure feature of plant and the nursing care mode of plant
System.
9. device according to claim 8, which is characterized in that first determining module, comprising:
First determination unit determines the growth shape of the plant to be treated for the structure feature according to the plant to be treated
State;
Identification module, it is determining and described at long status pair for being identified to described at long status using the identification model
The nursing care mode answered.
10. device according to claim 9, which is characterized in that further include:
Second determining module, for determining the identification model according to the training sample prestored.
11. device according to claim 10, which is characterized in that second determining module, comprising:
Second determination unit determines the growth of each sample for the structure feature according to sample each in the training sample
State;
Construction unit, for, at long status, constructing the corresponding state feature vector of each sample according to each sample;
Third determination unit, for the nursing care mode labeled according to the state feature vector of each sample and each sample, really
The fixed identification model.
12. device according to claim 9, which is characterized in that
The identification module, specifically for, at long status, constructing the shape of the plant to be treated according to the plant to be treated
State feature vector;And input the state feature vector of the plant to be treated in the identification model, it obtains and the growth
The corresponding nursing care mode of state.
13. device according to claim 10, which is characterized in that
Second determining module, specifically for the state feature vector and each sample quilt using deep learning method to each sample
The nursing care mode of label is trained, and obtains the identification model.
14. device according to claim 8, which is characterized in that further include:
Display module, for showing the corresponding nursing care mode of the plant to be treated using augmented reality AR.
15. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Claim 1-7 described in any item methods are realized when being executed by processor.
16. a kind of server characterized by comprising
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to realize that claim 1-7 is described in any item via the executable instruction is executed
Method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810879413.XA CN109145785A (en) | 2018-08-03 | 2018-08-03 | The determination method and apparatus of plant-nursing mode |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810879413.XA CN109145785A (en) | 2018-08-03 | 2018-08-03 | The determination method and apparatus of plant-nursing mode |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109145785A true CN109145785A (en) | 2019-01-04 |
Family
ID=64791412
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810879413.XA Pending CN109145785A (en) | 2018-08-03 | 2018-08-03 | The determination method and apparatus of plant-nursing mode |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109145785A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110377961A (en) * | 2019-06-25 | 2019-10-25 | 北京百度网讯科技有限公司 | Crop growth environment control method, device, computer equipment and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102564593A (en) * | 2011-12-30 | 2012-07-11 | 河海大学常州校区 | Plant growth condition monitoring system based on compute vision and internet of things |
CN104376496A (en) * | 2014-12-10 | 2015-02-25 | 绵阳青山森腾信息科技有限公司 | Wireless inquiry system convenient in agricultural product disease inquiring |
CN204423437U (en) * | 2014-12-10 | 2015-06-24 | 绵阳青山森腾信息科技有限公司 | There is the agriculture real-time advisory system of wisdom wireless network |
CN106682658A (en) * | 2017-03-14 | 2017-05-17 | 湖南威达科技有限公司 | APP (Application) for domestically raising Chinese herbaceous peony flowers based on big data and image identification |
CN107330887A (en) * | 2017-07-11 | 2017-11-07 | 重庆邮电大学 | A kind of crop pest control scheme commending system based on deep learning |
CN206627796U (en) * | 2017-03-17 | 2017-11-10 | 广东石油化工学院 | Flowerpot intelligent monitoring device |
CN107742290A (en) * | 2017-10-18 | 2018-02-27 | 成都东谷利农农业科技有限公司 | Plant disease identifies method for early warning and device |
-
2018
- 2018-08-03 CN CN201810879413.XA patent/CN109145785A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102564593A (en) * | 2011-12-30 | 2012-07-11 | 河海大学常州校区 | Plant growth condition monitoring system based on compute vision and internet of things |
CN104376496A (en) * | 2014-12-10 | 2015-02-25 | 绵阳青山森腾信息科技有限公司 | Wireless inquiry system convenient in agricultural product disease inquiring |
CN204423437U (en) * | 2014-12-10 | 2015-06-24 | 绵阳青山森腾信息科技有限公司 | There is the agriculture real-time advisory system of wisdom wireless network |
CN106682658A (en) * | 2017-03-14 | 2017-05-17 | 湖南威达科技有限公司 | APP (Application) for domestically raising Chinese herbaceous peony flowers based on big data and image identification |
CN206627796U (en) * | 2017-03-17 | 2017-11-10 | 广东石油化工学院 | Flowerpot intelligent monitoring device |
CN107330887A (en) * | 2017-07-11 | 2017-11-07 | 重庆邮电大学 | A kind of crop pest control scheme commending system based on deep learning |
CN107742290A (en) * | 2017-10-18 | 2018-02-27 | 成都东谷利农农业科技有限公司 | Plant disease identifies method for early warning and device |
Non-Patent Citations (1)
Title |
---|
刘鹏 等: "基于深度学习的园林智能浇灌系统", 《湖北汽车工业学院学报》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110377961A (en) * | 2019-06-25 | 2019-10-25 | 北京百度网讯科技有限公司 | Crop growth environment control method, device, computer equipment and storage medium |
CN110377961B (en) * | 2019-06-25 | 2023-04-28 | 北京百度网讯科技有限公司 | Crop growth environment control method, device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Larson et al. | Current perspectives and the future of domestication studies | |
Wang et al. | Ancient pinnate leaf mimesis among lacewings | |
Pathirana et al. | Management and utilization of plant genetic resources for a sustainable agriculture | |
Hao et al. | Pollen grain size associated with pollinator feeding strategy | |
CN108009147B (en) | Electronic book cover generation method, electronic device and computer storage medium | |
CN110348907A (en) | A kind of orientation method and device of advertisement crowd | |
CN107590811A (en) | Landscape image processing method, device and computing device based on scene cut | |
CN105447566B (en) | Training device, training method and detection device | |
Boyne et al. | Variation in leaf structure of the invasive Madeira vine (Anredera cordifolia, Basellaceae) at different light levels | |
Zhou et al. | Icdar 2015 text reading in the wild competition | |
CN109145785A (en) | The determination method and apparatus of plant-nursing mode | |
CN106844412A (en) | A kind of human face data collection method and device | |
Heikkinen et al. | Assemblages of spiders on models of semi-arid shrubs | |
Zhang et al. | Pollen morphology of different species of Iris barbata and its systematic significance with scanning electron microscopy methods | |
CN106294584B (en) | The training method and device of order models | |
CN106611027B (en) | Website precedence data treating method and apparatus | |
CN107767391A (en) | Landscape image processing method, device, computing device and computer-readable storage medium | |
CN103544141B (en) | Meaningful text string extracting method and system in binary data | |
Li et al. | Fruit consumption and seed dispersal by birds in native vs. ex situ individuals of the endangered Chinese yew, Taxus chinensis | |
CN107220299A (en) | Picture retrieval method and device | |
CN103810278B (en) | The web page processing method and device of terminal | |
Hyman et al. | Cassava and overcoming the challenges of global climatic change: report of the second scientific conference of the Global Cassava Partnership for the 21st century | |
Robles et al. | Woodpeckers as model organisms in a changing world. Foreword to the 7th International Woodpecker Conference Proceedings | |
Wang et al. | Weed25: a weed database for machine learning | |
AM et al. | MedChecker-An Ensembled Deep-Learning-based Classification Model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190104 |
|
RJ01 | Rejection of invention patent application after publication |