KR20200054619A - Apparatus for managing growth of plants based on mass of fruits, and method thereof - Google Patents

Abstract

The present invention relates to an apparatus for managing growth of plants based on the weight of fruits, and a method thereof. The apparatus for managing growth of plants according to the present invention includes: a fruit component model storage unit for storing a fruit component model defining the correlation between the weight of the fruit of a crop and the content of the components in the fruit according to the growth stage of the crop; a weight acquisition unit which acquires information on the weight of the fruit to be analyzed; a component prediction unit for predicting the content of component of the fruit to be analyzed based on the weight of the fruit to be analyzed and the fruit component model; and an information providing unit which provides growth information on the growth of the crop based on the weight of the fruit to be analyzed and the predicted content of the fruit to be analyzed. As described above, information on crop quality can be easily obtained by predicting the content of the main components of the fruit based on the weight of the crop fruit.

Description

Fruit weight-based crop growth management apparatus, and method thereof {APPARATUS FOR MANAGING GROWTH OF PLANTS BASED ON MASS OF FRUITS, AND METHOD THEREOF}

The present invention relates to a crop growth management apparatus and a method thereof, and more particularly, a crop growth management apparatus for diagnosing a growth state based on the measured growth index of a crop and managing the growth of the crop based on the diagnostic information. And the method.

Under the crisis of stagnation of agricultural productivity, reduction and aging of the rural population, and opening of the agricultural products market, smart farms incorporating ICT (Information and Communication Technology) technology into agriculture as a way to increase crop yield and quality in recent years and to reduce labor. (Smart farm) is spreading.

Smart Farm monitors the environment of cultivation facilities using Internet of Things technology, creates a suitable environment for cultivation by driving a control device, and remote management is also possible through a mobile device, thereby lowering the barrier to entry into the agricultural field and increasing productivity and efficiency. It is regarded as the next generation model that can create high added value, such as quality improvement.

Accordingly, unlike conventional agriculture, which relies on know-how or knowledge acquired through personal cultivation experience, it is gradually evolving toward analyzing and managing growth through data analysis. There is a lot to do.

For example, when nutrient solution is supplied to crops, nutrient solution components are appropriately prepared according to a recipe provided by another facility or institution. The recipes provided are tailored to the general crop sample depending on the growth period, but there are limitations because the individual growth conditions of the crop are not considered. For example, the phosphorus (P) and nitrogen (N) components of the nutrient solution components, phosphorus and nitrogen components are essential for crop growth, so it is common to supply them abundantly so as not to be insufficient.The remaining components that are not absorbed by the crop are water / soil pollution It will act as a factor that induces.

As such, the uniform nutrient solution supply based on the recipe causes environmental pollution due to excessive supply, and there is a problem that it is not economical. In addition, according to the current nutrient solution supply method based on the recipe, it is difficult to grasp even if a specific nutrient solution is insufficient in the crop, and it is difficult to reflect the component in the nutrient solution, and thus it is difficult to supply the nutrient solution optimized for crop growth.

Korean Patent Publication No. 10-2018-0110562 (2018.10.10)

Therefore, the present invention was devised to solve the above-mentioned problems of the prior art, and a crop growth management apparatus for diagnosing the growth state of the crop based on the weight of the crop fruit and using the diagnostic information to manage the growth of the crop. , And to provide a method.

The above object is a fruit component model storage unit for storing a fruit component model defining a correlation between the weight of the fruit of the crop according to the growth stage of the crop according to an aspect of the present invention and the content of the component contained in the fruit; A weight acquisition unit that acquires information on the weight of the fruit to be analyzed; A component prediction unit for predicting the component content of the fruit to be analyzed based on the weight of the fruit to be analyzed and the fruit component model; And it can be achieved by a crop growth management apparatus characterized in that it comprises an information providing unit for providing growth information regarding the growth of the crop based on the weight of the fruit to be analyzed and the component content of the predicted fruit.

Here, the fruit component model is a detailed model for each component corresponding to the type of at least one of phosphorus (P), nitrogen (N), calcium (Ca), magnesium (Mg), and potassium (K) components, respectively. It may include.

In addition, the fruit component model may include a detailed model for each flower garden corresponding to each flower garden.

Meanwhile, the weight acquisition unit may calculate the weight of the fruit to be analyzed based on the length and width of the fruit to be analyzed, which is recognized from the image in which the fruit to be analyzed is captured.

In addition, the information providing unit may provide nutrient solution guide information regarding a component amount of the nutrient solution to be supplied to the crop based on the predicted content of the fruit to be analyzed.

At this time, the fruit component model includes a detailed model for each flower garden corresponding to each flower garden, and the information providing unit is configured to set the angle according to the growth time of the crop in the prediction result according to the detailed model for each flower garden. The nutrient solution guide information may be provided by applying weights to detailed models for each room.

On the other hand, the disease information storage unit for storing the disease pattern information related to the change in the weight of the fruit according to the growth stage of the crop affected by the disease or the change in the components contained in the fruit of the diseased crop further comprises a pest information storage unit, and providing the information The department may estimate whether or not the crop is affected by comparing the weight of the fruit to be analyzed and the predicted component content of the fruit to be analyzed with the disease pattern information.

The above object is in a crop growth management method performed through a crop growth management device for managing the growth of crops according to another aspect of the present invention, the weight and weight of the fruit of the crop according to the growth stage of the crop Storing a fruit component model defining a correlation between content of contained components; Obtaining information on the weight of the fruit to be analyzed; Predicting a component content of the fruit to be analyzed based on the weight of the fruit to be analyzed and the fruit component model; And providing growth information on the growth of the crop based on the weight of the fruit to be analyzed and the predicted content of the fruit to be analyzed.

As described above, according to the present invention, it is possible to obtain information on crop quality by predicting the main component content of the fruit based on the weight of the crop fruit.

Further, according to the present invention, it is possible to supply a nutrient solution suitable for the growth state of the crop based on the predicted content of the component of the fruit. In addition, it is possible to identify early crop related diseases based on the weight of the fruit and the predicted content of the ingredients according to the growing season.

1 is a block diagram showing the configuration of a crop growth management apparatus according to an embodiment of the present invention;
Figure 2 is a reference diagram for explaining the fruit component model according to an embodiment of the present invention;
3 is a reference diagram for explaining a weight conversion process by the weight acquisition unit according to an embodiment of the present invention; And
4 is a flowchart illustrating a method for managing crop growth according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram showing the configuration of a crop growth management apparatus according to an embodiment of the present invention. 1, the crop growth management apparatus 100 according to an embodiment of the present invention includes a fruit component model storage unit 10, a disease information storage unit 20, a weight acquisition unit 30, a component prediction unit 40 ), And the information providing unit 50.

The fruit component model storage unit 10 stores a fruit component model that defines a correlation between the weight of the fruit of the crop according to the growth stage of the crop and the content of the component contained in the fruit. The fruit component model can be defined as a function that indicates the content of the component in the fruit according to the weight of the fruit, with the weight of the fruit according to the growth stage of the crop as an independent variable and the content of the component in the fruit as a dependent variable. have. Here, the weight of the fruit may be fresh weight, which is the weight before drying immediately after picking the fruit, or may be dry weight dried by drying the moisture after collection. Meanwhile, the components contained in the fruit are phosphorus (P), nitrogen (N), calcium (Ca), magnesium (Mg), potassium (K), and the like, and may vary depending on the type of fruit.

Figure 2 is a reference diagram for explaining the fruit component model according to an embodiment of the present invention, showing an example of 20 crop samples, fruit growth in a series of crop growth stages of fruit ripening and fruit ripening It is a graph showing changes in how the content (mg) of the phosphorus (P) component changes with increasing weight (g).

Referring to FIG. 2, it can be seen that although the specific change amount for the crop sample is slightly different, the content of the phosphorus (P) component of the fruit increases as the raw weight of the fruit increases.

As described above, the fruit component model is based on the correlation between the change in fruit weight and the change in the content of fruit in the growth stage of the crop, and can be modeled on the basis of the weight data of fruit for each growth stage of the individual crops and the content of the component content of the fruit. Can be. For reference, the component content of the fruit may be obtained through various known component analysis methods including an ICP (Inductively Coupled Plasma) analysis method.

On the other hand, basically, the content of the component of the fruit is a dependent variable, and the weight of each stage of fruit growth is an independent variable, but as another independent variable, a fruit component model including the cumulative supply (g) of the component through nutrient solution can be generated. . For example, a multivariate fruit component model can be generated by using the content of the phosphorus (P) component as a dependent variable and the weight of each fruit growth stage and the cumulative supply of phosphorus (P) contained in the nutrient solution as independent variables. Here, the cumulative supply amount of the specific component included in the nutrient solution means the cumulative amount of the specific component supplied as the nutrient solution to the weight of a predetermined fruit. Through this, it is possible to grasp the relationship with the weight of the fruit as well as the change in the content of each component according to the supply of the nutrient solution.

The type of fruit in the fruit ingredient model is not limited to a specific type such as tomato, strawberry, and melon, but can be divided into detailed models according to the type of fruit, such as the tomato fruit ingredient model, strawberry fruit ingredient model, and melon fruit ingredient model. Even types can be subdivided according to varieties. For example, in the case of tomatoes, fruit composition models for each variety may be generated according to tomato varieties, such as Deiros, Defness, Dabol, and Dotaerang (Momotaro).

In addition, the fruit component model may be subdivided according to the kind of component contained in the fruit. For example, a detailed model for each component may be included in response to components such as phosphorus (P), nitrogen (N), calcium (Ca), magnesium (Mg), and potassium (K), respectively. It may vary depending on the type of fruit. This reflects that the main ingredients for fruit quality may differ depending on the type of fruit.

On the other hand, the fruit component model can generate a fruit component model based on the data for the entire flowerpot, regardless of the flowerpot, but the fruit component model for one set flowerpot can be applied as a representative fruit component model for the crop. Of course. For example, when generating a fruit component model for a tomato crop, there are approximately 40 flower pots in one individual, wherein the tomato fruit component is based on fruit weight data and fruit component content data obtained in the entire flower pot. Although a model can be generated, the tomato fruit component model is generated based on the weight data and fruit component content data of fruit obtained from the sixth plant in a plurality of tomato crop individuals by applying the sixth flower garden with the most favorable growth conditions. You may.

Meanwhile, a fruit component model may be generated for each room based on the fruit data in each room. For example, when a fruit component model is generated by collecting fruit weight data and fruit component content data obtained from the same sixth flower in a plurality of tomato crop individuals, the fruit component model for the sixth flower is derived. Or, in the case of tomatoes, it is known that 1 ~ 10 flower gardens between spring and summer, 11 ~ 25 flower gardens from summer to autumn, and the remaining flower gardens appear from 26 flower gardens after that. You may be able to create a component model.

As described above, the fruit component model collects the data set of the weight value (g) of fruit according to the growth stage collected during the growth process of the crop, the cumulative supply amount (g) of the specific component through the nutrient solution, and the specific component content (mg) of the fruit. It can be modeled as a basis. At this time, the specific data collection method, such as how to collect and model data from the whole room or the number of fruits from the number of rooms, considers the model to be created, and the model accuracy verification process. It can be determined experimentally.

The fruit component model can be generated by analyzing the correlation with the content of each component of the fruit as a dependent variable, and the weight and the cumulative supply amount of a specific component through nutrient solution as the independent variable. Based on the collected data, various statistical analysis such as regression analysis, multivariate analysis, or machine learning by various algorithms such as neural network, support vector machine (SVM), and deep learning A fruit component model can be generated by analyzing the correlation between independent and dependent variables using various analysis tools. The fruit component model may take the form of an n-th order polynomial function, for example, but of course, it may take a different function form according to an analysis method or an analysis result.

The disease information storage unit 20 stores disease pattern information regarding a change in fruit weight according to a growth stage of a crop affected by various diseases or a change in a component contained in a fruit of the crop affected by the disease. Here, the type of the pest and the pattern of the pest may be changed according to the type of crop.

The pest pattern information is based on the fact that, when a crop disease occurs, changes in the weight of the fruit or the components contained in the fruit may appear different from the normal fruit. For example, umbilical rot disease, which is one of the diseases of tomato crops, is a disease that begins to rot in the area where the flower hangs, and because the stomach rots, it shows less weight than normal fruits and tends to show less calcium (Ca) component among fruits. . Umbilical rot disease can be identified with the naked eye because the rotten state is exposed to the outside, but there is a problem in that it is difficult to initially identify with the naked eye.

The disease pattern information can be constructed experimentally based on the difference in weight and composition of the diseased fruit compared to the normal fruit displayed at the growth stage through the sample of the diseased disease. Such pest pattern information can be usefully used to identify the relevant pests of crops early.

The weight acquisition unit 30 acquires information about the weight of the fruit to be analyzed. Here, the fruit to be analyzed means a fruit to be analyzed using a fruit component model pre-built in the fruit component model storage unit 10.

The weight acquisition unit 30 may directly receive information regarding the weight of the fruit to be analyzed from the user. For example, a user may directly receive input through a user interface (not shown) provided for user input, such as a keyboard or mouse, or communicate with a user terminal (not shown) capable of communication carried by the user to receive information regarding weight. Can be.

At this time, the user will be able to input data regarding raw weight or dry weight. If the user inputs the raw weight data of the fruit, and the fruit component model takes a function form of the content of the component contained in the fruit according to the dry weight of the fruit, the weight acquisition unit 30 converts the input raw weight to the dry weight. Conversion processing must be performed.

Figure 3 is a reference diagram for explaining the weight conversion process by the weight acquisition unit 30 according to an embodiment of the present invention, shows a graph showing the relationship between the raw weight and dry weight of the fruit.

As shown in the graph of FIG. 3, the weight acquisition unit 30 stores data on the correlation between the raw weight and the dry weight of the fruit, and converts the weight input from the user to match the weight format of the fruit component model based on this. Processing can be performed.

On the other hand, without directly receiving the weight data from the user, the weight acquisition unit 30 recognizes length information such as the width, height and width (thickness) of the fruit from the image of the fruit to be analyzed and analyzes it based on this. You can also calculate the raw weight of the fruit.

Here, the image of the fruit to be analyzed is photographed by the user using a user terminal including a camera, and the user terminal is transmitted to the weight acquisition unit 30 through communication or the user directly inputs the image captured through the user interface unit May be implemented. Meanwhile, since there are various known image recognition algorithms for recognizing the size or length of an object in an image, a detailed description thereof will be omitted for simplicity. The weight acquisition unit 30 may be equipped with an algorithm for recognizing the length of the object, etc. in the input image, and calculating the raw weight from the length (horizontal, vertical, and thickness). At this time, as described above, when the fruit component model is a dry weight based function, a process for converting the calculated raw weight to dry weight can be performed.

The component prediction unit 40 predicts the component content of the fruit to be analyzed by applying the weight value of the fruit obtained through the weight acquisition unit 30 and the user input to the fruit component model. At this time, the user can input information about the growth stage of the crop together, and when the fruit component model includes the cumulative supply amount of ingredients through nutrient solution as another independent variable, the component prediction unit 40 is used to supply nutrient solution from the user. Additional information can be received. Alternatively, the nutrient solution cumulative supply amount information may be implemented to be received through communication from a separate nutrient solution control device (not shown) that controls or manages the nutrient solution supply amount.

Meanwhile, the component prediction unit 40 may select a fruit component model to be applied among a plurality of fruit component models based on a user input or the like. For example, the user may directly select a model to be applied among a fruit component model for each fruit, a fruit component model for each flower room, and a fruit component model for each component, or input information necessary for selection. Alternatively, the component prediction unit 40 may automatically select the fruit component model to be performed for prediction based on the analysis target fruit image input from the user. For example, the component prediction unit 40 may be equipped with various image processing algorithms to determine what error the image is related to, and also, by considering the current date and the location of the analysis target error in the image, the number of It is also possible to select one of the fruit component models for each room by judging whether it is the fruit or not.

The information providing unit 50 is based on the weight of the fruit obtained through the weight acquisition unit 30 and the component content of the fruit to be analyzed predicted through the component prediction unit 40 to grow the crop containing the fruit to be analyzed. Provide growth information. Here, the growth information includes fruit quality information and whether or not the crop is affected.

First, the information providing unit 50 may provide information about the quality of the fruit based on the weight of the fruit and the content of each component predicted through the fruit component model for each component. To this end, the information providing unit 50 classifies the fruit quality for each growth stage into a predetermined grade, stores a data table defining the weight of the fruit corresponding to each quality grade and the content data of each component, and based on this Quality information can be provided. In addition, in order to improve the quality of the fruit in the current state, it may be possible to provide information on which component is insufficient or which component is excessive. The user can use it to adjust the composition of the ingredients of the nutrient solution supplied to the crop based on this, and it can also be used as basic information to select high-quality quality in advance.

In addition, the information providing unit 50 estimates whether the crop is diseased by comparing the weight of the fruit to be analyzed and the component content of the predicted fruit to be analyzed with the disease pattern information stored in the disease information storage unit 20. At this time, the information providing unit 50 may estimate using the information on the growth stage of the crop input from the user together. For example, the information providing unit 50 may estimate that there is a disease when the weight of the fruit is lighter than that of the growth stage or the content of a specific component is lower than the normal fruit in the growth stage. In the case of tomatoes, it can be determined that belly rot is suspected when the weight is low or the calcium component is predicted less than the fruit of the same growth period.

The information providing unit 50 provides the user with the suspected pest name and countermeasure information together when the crop is presumed to have a pest, so that the user can accurately check whether the disease is present, add certain ingredients to the nutrient solution, or change environmental conditions It can help you take the necessary steps to cure the disease, such as prescribing. For example, when it is estimated that the tomato crop has umbilical rot, the information providing unit 50 makes the calcium (Ca) component higher in the nutrient component and the nitrogen (N), magnesium (Mg) component amount lower in the drainage concentration. The nutrient solution guide information can be generated to increase the absorption rate of the calcium (Ca) component.

Meanwhile, the information providing unit 50 may provide nutrient solution guide information regarding the amount of the nutrient solution to be supplied to the crop based on the component content of the fruit to be analyzed predicted through the component prediction unit 40.

For example, when a specific component is smaller than a predetermined reference value compared to a normal fruit, fruit quality can be improved by providing guide information to further include the component in the nutrient solution. In addition, by comparing the nutrient information input from the user and the predicted component content of the fruit, when it is determined that the supplied component is excessive compared to the component content of the fruit, guide information for reducing the component can be provided. Through this, it is possible to promote economic efficiency and at the same time reduce water / soil pollution caused by residual phosphorus (P) and nitrogen (N) components not absorbed by the crop. As described above, in order to provide the nutrient solution guide information, the information providing unit 50 may store reference information on the proper amount of the component of the nutrient solution to be supplied according to the content of the fruit.

On the other hand, as a result of performing prediction by applying the analysis object fruits belonging to different room to the fruit component models of the corresponding room, it can be assumed that the results for each room are differently derived. For example, as a result of prediction according to the fruit composition model of the fifth flower, it was found that a specific ingredient was insufficient, but in the sixth flower, when it is determined that the ingredient is suitable, there is a problem as to which standard the nutrient solution guide information is provided. Occurs.

As described above, when the prediction conclusions for each flower garden are differently derived or conflict with each other, the information providing unit 50 may use the prediction result according to the fruit ingredient model for each flower garden for the fruit ingredient model for each flower garden according to the growth period of the crop. Nutrient guide information may be provided by applying a weight.

To this end, the information providing unit 50 may store weight information for a fruit component model for each flower growing season. Based on this, by adding more weights to the fruit component model corresponding to a flower plant that is more important for crop growth in the current state according to the growth time, and to assigning less weight to a fruit component model corresponding to a flower plant that is relatively insignificant, It is possible to generate nutrient guide information by focusing relatively on a high- importance painting room at the corresponding growth period.

Growth information and nutrient solution guide information generated through the information providing unit 50 may be provided to a user through a display means such as a monitor or transmitted to a user terminal.

4 is a flowchart illustrating a method for managing crop growth according to an embodiment of the present invention. Hereinafter, with reference to FIG. 4, the organic operation of each component of the above-described crop growth management apparatus 100 will be described.

First, it is premised to construct a database in which a fruit ingredient model is stored, which defines a correlation between the weight of the fruit of the crop according to the growth stage of the crop and the content of the ingredients contained in the fruit (S10). It is as described above that the fruit ingredient model may be modeled by including the cumulative supply amount of ingredients through nutrient solution as another independent variable in addition to the ingredient content of the fruit. Through this, it is possible to grasp the relationship between the nutrient solution supply and the content of each component as well as the weight of the fruit.

As described above, the fruit component model may be subdivided into fruit models, fruit varieties, each component, and each detail model. The fruit component model is used to predict the content of the fruit to be analyzed as described below. Looking at the above process, first, information about the weight of the fruit to be analyzed is obtained (S20). At this time, the user may directly input the weight value of the fruit, or when the user inputs a captured image of the fruit to be analyzed, the length and width of the fruit may be recognized through image processing to calculate the weight value of the fruit. . On the other hand, as described above, it is possible to undergo a data conversion process between raw weight and dry weight according to the format of the fruit component model and the obtained weight data. Depending on the independent variable of the fruit composition model, the user can also input nutrient solution information supplied to the crop, if necessary.

Subsequently, a step of predicting the component content of the fruit to be analyzed is applied by applying the obtained weight of the fruit to be analyzed to the fruit component model (S30). At this time, a suitable model can be selected and applied from the detailed model of the fruit component model based on the fruit type, variety, and plant information to which the fruit to be analyzed belongs.

Based on the predicted fruit ingredient content, weight data of the fruit obtained in step S20, and information on the growth stage of the crop, the quality information of the fruit, information on whether the crop is diseased, and nutrient guide information are generated and provided (S40). Here, the crop disease information may be provided by estimating the presence or absence of a pest by comparing the pest pattern information stored in the pest information storage unit 20 with the weight of the fruit to be analyzed and the predicted component content of the fruit to be analyzed.

At this time, since it can be difficult to judge that the analysis result for one analysis target fruit is the entire result for the crop object containing the analysis target fruit, it is possible to synthesize the growth information of the crop by combining the prediction results for two or more analysis target fruits. It may be possible to generate nutrient guide information.

As described above, the growth information provided through the crop growth management apparatus 100 and the crop growth management method according to the present invention, nutrient solution guide information, and the like are combined with appropriate nutrient solution necessary for harvesting fruit having a quality desired by the user. It can be used as basic information, and it is expected that it can be usefully used to create an environment to heal the disease by identifying the disease early or to take countermeasures.

The crop growth management method according to the present invention can be implemented with various recording media such as a magnetic storage medium, an optical reading medium, and a digital storage medium by writing a program executable on a computer.

The contents described above are only one embodiment for implementing the crop growth management apparatus and method according to the present invention, and the present invention is not limited to the above-described embodiments, as claimed in the claims below. Anyone who has ordinary knowledge in the field to which the present invention pertains without departing from the gist of the present invention will have the technical spirit of the present invention to the extent that various changes can be implemented.

The terms used in the above embodiments are only used to describe specific embodiments, and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as “include” or “have” are intended to indicate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, one or more other features. It should be understood that the existence or addition possibilities of fields or numbers, steps, operations, components, parts or combinations thereof are not excluded in advance.

10: fruit component model storage unit 20: pest pattern storage unit
30: weight acquisition unit 40: component prediction unit
50: Information provision department

Claims (8)

Fruit component model storage unit for storing a fruit component model defining a correlation between the weight of the fruit of the crop and the content of the components in the fruit according to the growth stage of the crop;
A weight acquisition unit that acquires information on the weight of the fruit to be analyzed;
A component prediction unit for predicting the component content of the fruit to be analyzed based on the weight of the fruit to be analyzed and the fruit component model; And
And an information providing unit providing growth information regarding the growth of the crop based on the weight of the fruit to be analyzed and the predicted content of the fruit to be analyzed.
According to claim 1,
The fruit component model includes a detailed model for each component corresponding to a type of at least one of phosphorus (P), nitrogen (N), calcium (Ca), magnesium (Mg), and potassium (K) components, respectively. Crop growth management device, characterized in that.
According to claim 1,
The fruit component model, crop growth management apparatus, characterized in that it comprises a detailed model for each flower garden corresponding to each flower garden.
According to claim 1,
The weight acquisition unit,
Crop growth management apparatus, characterized in that for calculating the weight of the fruit to be analyzed on the basis of the length and width of the fruit to be analyzed, which is recognized from the image of the fruit to be analyzed.
According to claim 1,
The information providing unit,
Crop growth management apparatus characterized in that it provides nutrient solution guide information on the amount of nutrients to be supplied to the crop based on the predicted component content of the analysis target fruit.
The method of claim 5,
The fruit component model includes a detailed model for each flower garden corresponding to each flower garden,
The information provision unit, crop growth characterized in that to provide the nutrient guide information by applying a weight for each of the detailed models set in advance according to the growth period of the crop to the prediction results according to the detailed model for each flower garden Management device.
According to claim 1,
Further comprising a disease information storage unit for storing the disease pattern information on the change in the weight of the fruit according to the growth stage of the crop affected by the disease or the change in the components contained in the fruit of the crop affected by the disease,
The information providing unit, crop growth management apparatus, characterized in that for estimating whether or not the disease related to the crop by comparing the weight of the fruit to be analyzed and the predicted component content of the fruit to be analyzed with the disease pattern information.
In the crop growth management method performed through the crop growth management device for managing the growth of the crop,
Storing a fruit component model defining a correlation between the weight of the fruit of the crop and the content of the component contained in the fruit according to the growth stage of the crop;
Obtaining information on the weight of the fruit to be analyzed;
Predicting a component content of the fruit to be analyzed based on the weight of the fruit to be analyzed and the fruit component model; And
And providing growth information regarding the growth of the crop based on the weight of the fruit to be analyzed and the predicted content of the fruit to be analyzed.

Images