KR102604041B1 - Method, device and program of recommending cultivation conditions for increase the content active ingredients in crop - Google Patents

Abstract

The present invention relates to a method of recommending cultivation conditions for increasing the content of active ingredients in crops. By extracting and providing cultivation conditions that can increase the content of active ingredients in target crops using a recommendation model built with deep learning, the user can It has the effect of allowing more active ingredients to be obtained by cultivating the corresponding crop.

Description

{Method, device and program of recommending cultivation conditions for increase the content active ingredients in crop}

The present invention relates to a method for recommending cultivation conditions, and more specifically, to a method for recommending cultivation conditions that can increase the content of active ingredients in crops.

Various active ingredients extracted from growing crops are used in various fields such as pharmaceuticals, cosmetics, and health functional foods, and the market size is growing.

However, even in this situation where needs are increasing, the amount of crops cultivated is limited, leading to shortages and shortages of active ingredients.

Although many research papers have been written and experiments are being conducted to overcome the above situation, the technology to organize such big data and suggest cultivation conditions to users who grow crops is not currently available to the public.

Republic of Korea Patent Publication No. 10-2015-0075515, (2015.07.06)

The present invention, in order to solve the problems described above, seeks to extract and provide cultivation conditions that can increase the content of active ingredients in target crops using a recommendation model built with deep learning.

In addition, the present invention seeks to receive input of the necessary active ingredients that the user wishes to obtain from crops, and extract and provide cultivation conditions that can increase the necessary active ingredients using a recommendation model.

In addition, the present invention seeks to obtain empirical data based on the user's crop cultivation results and train it in a recommendation model.

In addition, the present invention seeks to derive and provide one or more recommended crops that can obtain a certain level or more of the required active ingredient that the user wishes to obtain.

In addition, the present invention extracts result data according to the provision of cultivation conditions for a specific crop from the target data and constructs it as a learning dataset to deep learn a recommendation model.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

A method of recommending cultivation conditions for increasing the content of active ingredients in crops according to an embodiment of the present invention to solve the above-mentioned problems includes the steps of receiving information about a target crop by a computer; And a step where the computer applies the received information on the target crop to at least one recommendation model built using deep learning, and extracts cultivation conditions for increasing the active ingredients in the target crop.

In addition, a method of recommending cultivation conditions for increasing the content of active ingredients in crops according to an embodiment of the present invention to solve the above-described problem includes the step of receiving at least one necessary active ingredient that a computer wants to obtain by cultivating crops. ; And applying the received necessary active ingredient information to at least one recommendation model built by the computer through deep learning to derive one or more recommended crops that can obtain the necessary active ingredient at a preset level or higher. .

In addition, in order to solve the above-described problem, the method of building a cultivation condition recommendation model for increasing the active ingredient content in crops according to an embodiment of the present invention is to use a computer to determine the cultivation conditions mentioned with a specific crop in the target data. detecting condition data; Detecting result data on active ingredients in the specific crop within the target data when the specific crop is grown under the detected cultivation conditions; Constructing a learning dataset based on the condition data and the result data; And it includes the step of applying and learning the learning data set to at least one recommendation model that recommends cultivation conditions for increasing active ingredients in crops.

In addition, an apparatus for recommending cultivation conditions for increasing the content of active ingredients in crops according to an embodiment of the present invention for solving the above-described problems includes a receiving unit that receives at least one necessary active ingredient to be obtained by growing crops; And a controller that applies the necessary active ingredient information to at least one recommendation model built through deep learning to derive one or more recommended crops that can obtain the necessary active ingredient at a preset level or higher.

In addition, an apparatus for recommending cultivation conditions for increasing the content of active ingredients in crops according to an embodiment of the present invention for solving the above-described problems includes a receiving unit that receives at least one necessary active ingredient to be obtained by growing crops; And a controller that applies the necessary active ingredient information to at least one recommendation model built through deep learning to derive one or more recommended crops that can obtain the necessary active ingredient at a preset level or higher.

In addition, an apparatus for building a model for recommending cultivation conditions for increasing the content of active ingredients in crops according to an embodiment of the present invention to solve the above-mentioned problems includes a data collection module that receives or searches target data; a detection unit that detects condition data for the cultivation conditions mentioned with the specific crop in the target data and detects result data for the active ingredient in the specific crop when grown under the cultivation conditions; a learning module that configures a learning dataset based on the condition data and the result data; and a controller that trains the learning data set by applying it to a recommendation model.

In addition to this, another method for implementing the present invention, another system, and a computer-readable recording medium recording a computer program for executing the method may be further provided.

According to the present invention as described above, by extracting and providing cultivation conditions that can increase the active ingredient content in the target crop using a recommendation model built with deep learning, the user can obtain more active ingredients by cultivating the crop. It has the effect of allowing you to do so.

In addition, according to the present invention, the necessary active ingredients that the user wants to obtain from crops are input, and cultivation conditions that can increase the necessary active ingredients are extracted and provided using a recommendation model, thereby obtaining the necessary active ingredients that the user wants to obtain. It has the effect of allowing you to acquire more.

In addition, according to the present invention, there is an effect of acquiring empirical data according to the user's crop cultivation results and training the recommendation model to upgrade the recommendation model.

In addition, according to the present invention, when the user inputs the required active ingredient that he or she wishes to obtain, one or more recommended crops that can obtain a certain level or more are derived and provided, which has the effect of recommending crops for obtaining the active ingredient to the user. there is.

In addition, according to the present invention, by extracting the result data according to the provision of cultivation conditions for a specific crop from the target data, constructing this as a learning dataset and deep learning the recommendation model, artificial intelligence can be used to recommend cultivation conditions. There is an effect that can be built.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

Figure 1 is a schematic diagram of a method for recommending cultivation conditions for increasing the active ingredient content in crops according to an embodiment of the present invention.
Figure 2 is a flowchart of a method for recommending cultivation conditions for increasing the active ingredient content in crops according to an embodiment of the present invention.
Figure 3 is a diagram illustrating empirical data.
Figure 4 is a diagram illustrating steps that can be added to a method for recommending cultivation conditions for increasing the active ingredient content in crops according to an embodiment of the present invention.
Figure 5 is a flowchart of a method for recommending cultivation conditions for increasing the active ingredient content in crops according to another embodiment of the present invention.
Figure 6 is a flowchart of a method for building a cultivation conditions recommendation model for increasing the active ingredient content in crops according to an embodiment of the present invention.
Figure 7 is a diagram illustrating building a learning dataset from target data.
Figure 8 is a diagram illustrating a smart farm system using a method for recommending cultivation conditions for increasing the active ingredient content in crops according to an embodiment of the present invention.
Figure 9 is a block diagram of a device for recommending cultivation conditions for increasing active ingredients in crops according to an embodiment of the present invention.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure of the present invention is complete and to provide a general understanding of the technical field to which the present invention pertains. It is provided to fully inform the skilled person of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for describing embodiments and is not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other elements in addition to the mentioned elements. Like reference numerals refer to like elements throughout the specification, and “and/or” includes each and every combination of one or more of the referenced elements. Although “first”, “second”, etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may also be a second component within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless clearly specifically defined.

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

In the embodiments of the present invention, the active ingredient refers to an ingredient that can be obtained from crops, and more specifically, an ingredient that can be used in pharmaceuticals, cosmetics, health functional foods, etc. For example, saponin from ginseng, chlorophyll and beta-carotene from kale, policosanol and saponarin from barley sprouts, etc.

Figure 1 is a schematic diagram of a method for recommending cultivation conditions for increasing the active ingredient content in crops according to an embodiment of the present invention.

Referring to FIG. 1, a schematic description will be given of a method for recommending cultivation conditions for increasing the active ingredient content in crops according to an embodiment of the present invention.

The present invention uses a recommendation model built through deep learning, and the recommendation model is deep learned by having a computer extract effective information from target data, construct a learning dataset, and train this to the recommendation model.

At this time, the target data can be applied to any document with a certain level of reliability or higher, and representative examples include verified data such as theses, academic journals, and patent documents.

In order to verify this reliability, the data collection module 60 of the recommendation model building device 50 verifies the reliability of the target data collected by installing a reliability verification algorithm, and uses the detection unit 70 only for the target data for which verification has been completed. Valid information can be extracted through

And, when the computer receives information about the target crop from the user, it applies the information about the target crop to the recommendation model, and the recommendation model uses learned artificial intelligence to create cultivation conditions that can increase the content of active ingredients in the target crop. It is extracted.

Through this, the user provides the cultivation conditions extracted while growing the target crop, and can obtain more active ingredients even by growing the same amount of crop.

Above, a brief description has been given of the method for recommending cultivation conditions for increasing the content of active ingredients in crops according to an embodiment of the present invention. Below, a more detailed embodiment will be described with reference to other drawings.

In an embodiment of the present invention, the process of each step is performed by a computer. More specifically, the method of recommending cultivation conditions for increasing the active ingredient content in crops according to an embodiment of the present invention is a cultivation condition recommendation device 100. The method of building a cultivation condition recommendation model for increasing the active ingredient content in crops according to an embodiment of the present invention is performed by the recommendation model building device 50.

Additionally, this device may be implemented in the form of a server so that the user can access the terminal 200 and use services using the web and applications.

Figure 2 is a flowchart of a method for recommending cultivation conditions for increasing the active ingredient content in crops according to an embodiment of the present invention, and Figure 3 is a diagram illustrating empirical data.

With reference to Figures 2 and 3, a method of recommending cultivation conditions for increasing the active ingredient content in crops according to an embodiment of the present invention will be described.

First, the receiver 120 of the cultivation condition recommendation device 100 receives information about the target crop from the user. (S200)

At this time, the receiving unit 120 of the cultivation condition recommendation device 100 may receive information on the target crop directly from the user, or may be implemented in the form of a server and receive the information on the target crop input from the user's terminal 200. It may be received through the communication unit 130 and transmitted to the reception unit 120.

Target crop refers to a crop for which the user wishes to receive recommendations for growing conditions that can increase the content of active ingredients in the crop. Examples may include the crop the user wishes to grow or the crop the user is currently cultivating. there is.

Next to S200, the controller 110 of the cultivation condition recommendation device 100 applies information on the target crop to the recommendation model to extract cultivation conditions that can increase the content of the active ingredient in the target crop. (S250)

In detail, since the recommendation model is built with deep learning through various big data, if information on the target crop is applied and certain cultivation conditions are provided while cultivating the target crop, when the target crop is harvested, the active ingredients in the target crop The cultivation conditions can be extracted to determine whether the content of the active ingredient can be increased.

At this time, the cultivation conditions can be any conditions that can be provided to the crop in the process of growing the crop, and examples include cultivation environmental conditions and specific stimulation conditions.

In addition, cultivation environmental conditions can include all matters that can act as environmental factors in growing crops, such as temperature, humidity, amount of light, wind, carbon dioxide concentration in the cultivation area, soil conditions, amount and timing of moisture provision, etc. required for crop cultivation. there is.

In addition, stimulation conditions can be any element that can be provided as a stimulus to crops when growing crops, for example, stimulation by providing light of a specific wavelength, stimulation by providing light of a specific color, etc. Various stimuli can be applied to this, such as stimulating crops by playing certain music.

Additionally, if elements corresponding to the cultivation environment conditions are determined to be stimulating factors for crops, they may be overlapped and selected as stimulating factors.

In one embodiment, the recommendation model may be composed of an environmental condition recommendation model and a stimulus condition recommendation model, and the controller 110 extracts the environmental condition using the environmental condition recommendation model and the stimulus condition recommendation model using the stimulus condition recommendation model. can be extracted.

As above, in the embodiment of the present invention, the recommendation model may apply information on the target crop to extract cultivation conditions for increasing the active ingredient content in the target crop, and in addition, it may extract cultivation conditions for increasing the yield of the target crop. You may.

S250 Next, the controller 110 of the cultivation condition recommendation device 100 applies the received empirical data according to the completion of cultivation of the target crop to a recommendation model and learns it. (S300)

More specifically, the cultivation condition recommendation device 100 receives as empirical data the results of how much active ingredient is actually obtained from the target crop when the user grows the target crop under the cultivation conditions extracted in S250, and receives this as empirical data. This means reflecting the actual results by retraining the recommendation model.

At this time, empirical data refers to the results of active ingredients obtained from target crops for which cultivation has been completed.

And, in some cases, the user may have faithfully fulfilled all the cultivation conditions extracted from S250 and harvested the target crop, but may not have fulfilled all the cultivation conditions. Therefore, the empirical data may include cultivation condition performance data, which means the extent to which the cultivation conditions extracted from S250 are provided during the process of cultivating the target crop.

To this end, the cultivation condition recommendation device 100 can provide an empirical data input form to the user's terminal 200 when it is confirmed that the target crop cultivated by the user has been completed, and the empirical data input form contains the target crop. It can be a form that requests input such as the amount of active ingredients obtained through cultivation and the extent to which cultivation conditions were implemented.

Figure 4 is a diagram illustrating steps that can be added to a method for recommending cultivation conditions for increasing the active ingredient content in crops according to an embodiment of the present invention.

FIG. 4 illustrates steps that may be included in other embodiments in addition to the steps described in FIG. 3, and these additional steps will be described in the following embodiments.

Next to S200, the cultivation condition recommendation device 100 may receive one or more necessary active ingredients to be obtained by cultivating the target crop from the user. (S230)

For example, assuming that there are 10 necessary active ingredients that can be obtained by cultivating Crop A, the necessary active ingredients that the user mainly wants to obtain by cultivating Crop A may be several of them.

Specifically, it is possible to obtain and use all 10 active ingredients, but among them, there may be an active ingredient that is mainly desired to be obtained, so in the embodiments of the present invention, the necessary active ingredients are those that can be obtained from the target crop by the user. It may mean the active ingredient that it is trying to acquire intensively.

In addition, the controller 110 of the cultivation condition recommendation device 100 applies the information of the target crop and the required active ingredients to the recommendation model in the cultivation condition extraction step (S250) to determine conditions for increasing the required active ingredients in the target crop. is extracted.

In this way, when S230, which inputs the necessary active ingredients, is added, the recommendation model can extract more specific and accurate cultivation conditions, and the user can use the extracted cultivation conditions to select crops with the necessary active ingredients that the user wants to obtain. It has the effect of increasing my content.

Next to S250, when the target crop is grown under the conditions extracted in S250, the calculation unit 150 of the cultivation condition recommendation device 100 may calculate and provide the expected content or expected acquisition amount of the active ingredient in the target crop. (S260)

More specifically, the calculation unit 150 calculates and provides the content of the active ingredient in the target crop and the expected acquisition amount of the active ingredient that can be obtained from the target crop when the target crop is grown under the extracted cultivation conditions. it means.

By going through this process, the cultivation condition recommendation device 100 can enable the user to faithfully implement the extracted cultivation conditions, and from the user's perspective, when receiving a reservation order, the active ingredient is selected based on the expected acquisition amount. You can also take pre-orders.

S260 Next, the calculation unit of the cultivation condition recommendation device 100 predicts possible climate change from the climate change record for the previous certain period of the cultivation location received from the user, and possible errors in the expected gain calculated using this. Range information can be added. (S270)

There are crops that can be grown without being affected by the external environment, but there are also crops that are inevitably affected by the external environment during the cultivation process, depending on the type of crop or the growing conditions of the user.

Accordingly, in an embodiment of the present invention, the cultivation condition recommendation device 100 may receive input from the user as the location of the cultivation area where the target crop is to be grown.

In addition, when information on the cultivation location of the target crop is input from the user using the recommendation model, the calculation unit 150 of the cultivation condition recommendation device 100 generates information from the climate change record for a certain period of time prior to the corresponding cultivation location as in S270. Possible climate changes can be predicted and, taking this into account, error range information can be added to the expected gain calculated in S260.

In addition, the cultivation condition recommendation device 100 may predict possible climate changes and occurrence periods based on climate change records for a certain period of time prior to the cultivation location input by the user, and may derive and provide solutions to deal with them. (S280)

As mentioned above, the processes of S270 and S280 may not be performed if the target crop is a crop that is not significantly affected by changes in the external environment, or if the user's cultivation conditions allow for cultivation independent of the external environment.

In addition, the cultivation condition recommendation device 100 can receive information from the user on equipment that can be input as the cultivation conditions for crops. Here, the equipment information may include the type and specifications of the cultivation equipment provided in the user's cultivation area, and the type and specifications of the agricultural equipment (agricultural machinery) owned by the user.

Therefore, the cultivation condition recommendation device 100 has the effect of filtering and providing cultivation conditions that can be provided while the user grows the target crop, taking the user's conditions into consideration.

In one embodiment, S270 receives information about the cultivation location of the target crop after the provision step, predicts possible climate changes from the climate change record for a previous certain period of the cultivation location, and predicts the predicted climate change. It may consist of adding a possible error range to the expected acquisition amount calculated based on it.

Figure 5 is a flowchart of a method for recommending cultivation conditions for increasing the active ingredient content in crops according to another embodiment of the present invention.

In the embodiment described through FIGS. 1 to 4, the target crop was first input and cultivation conditions that could increase the active ingredients that could be obtained by cultivating the target crop were extracted.

In Figure 5, an embodiment will be described in which the necessary active ingredients to be obtained by cultivating crops are first received, and crops from which a certain amount of the necessary active ingredients can be obtained are recommended and provided.

This can be helpful for users who want to obtain a specific active ingredient but do not know what crops to grow.

First, the cultivation condition recommendation device 100 receives information on one or more necessary active ingredients that the user wishes to obtain by growing crops. (S400)

Then, the controller 110 of the cultivation condition recommendation device 100 applies the necessary active ingredient information to the recommendation model to derive one or more recommended crops that can obtain a certain level or more of the necessary active ingredient. (S470)

Through this process, the user can select and grow crops from the recommended crops derived from S470 and obtain the necessary active ingredients.

In one embodiment, after S470, when at least one recommended crop is selected from the recommended crops by the user, the controller 110 of the cultivation condition recommendation device 100 applies the information on the selected recommended crop to the recommendation model to select the selected recommended crop. Cultivation conditions that can increase the content of the necessary active ingredients can be extracted and provided. (S500)

At this time, the recommendation model may extract cultivation conditions that can increase the content of the active ingredient in the selected recommended crop, but since the recommended crop is recommended based on the required active ingredient input from the user, the content of the required active ingredient is increased. It is desirable to extract and provide possible cultivation conditions.

In one embodiment, following S400, a user condition input step (S430) may be further included including information on the location of the crop cultivation site from the user and information on equipment owned by the user that can be used as cultivation conditions when growing the crop.

In addition, when S430 is further included, the controller 110 of the cultivation condition recommendation device 100 inputs the necessary active ingredient information and user condition information into the recommendation model, so that the necessary active ingredient can be obtained at a certain level or more, and the user One or more recommended crops that can be grown are derived and provided.

At this time, being able to obtain a certain level or more of the required active ingredient means the content of the required active ingredient in the crop.

This is because even if the controller 110 uses a recommendation model to derive and provide recommended crops that can obtain a certain level or more of the necessary active ingredients, crops that cannot be grown due to the user's cultivation conditions may be included, so enter the user's conditions. The purpose is to derive and recommend only crops that the user can grow.

S430 receives information about the location of the cultivation area of the target crop, receives information about equipment available within the cultivation conditions, derives cultivation environment information about the location of the cultivation location, and based on the cultivation environment information and equipment information It may consist of filtering the available cultivation conditions among the cultivation conditions.

The recommendation model used in the method of recommending cultivation conditions for increasing the active ingredient content in crops according to another embodiment of the present invention described above is deep learned by inputting a learning dataset in the following manner.

The detection unit 70 of the recommendation model building device 50 detects condition data for the cultivation conditions mentioned with the specific crop in the target data, and provides the cultivation conditions detected in the target data, thereby detecting the active ingredients in the specific crop. Detect result data for at least one of the content or the obtained amount.

Then, the recommendation model building device 50 constructs a learning data set based on condition data detected for a specific crop in the target data and detected result data according to the detected cultivation conditions.

When the learning data set is configured in this way, the controller 110 of the recommendation model building device 50 applies the learning data set to the recommendation model and trains it.

The structure of the learning data set has been briefly described above, and the method of building a model for recommending cultivation conditions to increase the content of active ingredients in crops will be explained in more detail below with reference to other figures.

Figure 6 is a flowchart of a method for building a cultivation conditions recommendation model for increasing the active ingredient content in crops according to an embodiment of the present invention.

Figure 7 is a diagram illustrating building a learning dataset from target data.

With reference to FIGS. 6 and 7, a method of constructing a cultivation conditions recommendation model for increasing the active ingredient content in crops according to an embodiment of the present invention will be described.

Before explaining the embodiment, the recommendation model building device 50 includes a data collection module 60, and the data collection module 60 collects target data for extracting effective information.

At this time, the data collection module 60 can directly input target data or input a URL, and includes a target data search algorithm to search documents on the web and select documents that meet the requirements of target data as target data. It may be possible.

At this time, the target data can be applied to any document with a certain level of reliability or higher, and representative examples include verified data such as theses, academic journals, and patent documents.

In order to verify this reliability, the data collection module 60 of the recommendation model building device 50 verifies the reliability of the target data collected by installing a reliability verification algorithm, and uses the detection unit 70 only for the target data for which verification has been completed. Valid information can be extracted through

In this way, when the target data is confirmed, the detection unit 70 of the recommendation model building device 50 detects condition data for the cultivation conditions of a specific crop within the target data. (S100)

More specifically, the names of various crops are stored in the database 140, and the detection unit 70 searches the target data to detect whether there is a mention of a specific crop.

In addition, when the detection unit 70 detects that there is a mention of a specific crop in the target data, it detects whether the target data contains information about the cultivation conditions of the specific crop (condition data) along with a mention of the specific crop. .

Next to S100, the detection unit 70 detects result data according to the provision of the cultivation conditions detected in S100 within the target data. (S130)

Through this, ① the detection unit 70 determines whether there is a mention of a specific crop in the target data, ② if so, whether there is a mention of providing specific cultivation conditions to a specific crop, and ③ the result data when providing specific cultivation conditions to a specific crop. A total of 3 types of content are detected in the target data to see if there is any mention of .

Next, after S130, the learning module 80 constructs a learning data set based on condition data for cultivation conditions detected for a specific crop and detected result data corresponding to the detected cultivation conditions. (S150)

Next to S150, the controller 110 trains the recommendation model by applying the learning data set to the recommendation model. (S170)

At this time, the result data may correspond to data such as the amount of change in the content of the active ingredient in a specific crop, the expected change in content, the amount of active ingredient obtained, or the expected amount of acquired active ingredient in the specific crop when the corresponding cultivation conditions are provided to the specific crop.

In this process, the detection unit 70 may or may not reflect the predicted content change and the expected acquisition amount of the active ingredient in the learning data set depending on the reliability of the target data.

Additionally, as described above, the cultivation conditions (condition data) detected by the detection unit 70 in S130 may include cultivation environmental conditions for crops and specific stimulus conditions.

In addition, in the method of building a cultivation condition recommendation model for increasing the active ingredient content in crops according to an embodiment of the present invention, the target data may be verified data such as papers, academic journals, patent documents, etc., as mentioned above. , In addition, data such as voice data, video data, etc. can be selected as target data as long as reliability is guaranteed.

In order to detect such voice data and image data, the detector 70 may apply technologies such as voice recognition technology and image recognition technology.

Figure 8 is a diagram illustrating a smart farm system using a method for recommending cultivation conditions for increasing the active ingredient content in crops according to an embodiment of the present invention.

Cultivation conditions extracted using the method of recommending cultivation conditions for increasing the active ingredient content in crops described above can be provided to the smart farm through the communication unit 130, and the smart farm provides various cultivation conditions established in the cultivation area. The device can be automatically controlled according to the received cultivation conditions to provide cultivation conditions to the crops being grown.

Figure 9 is a block diagram of a device for recommending cultivation conditions for increasing active ingredients in crops according to an embodiment of the present invention.

Referring to Figure 9, the device for recommending cultivation conditions for increasing active ingredients in crops according to an embodiment of the present invention includes a controller 110, a communication unit 130, a receiver 120, a database 140, and a calculation unit ( 150), and the recommendation model may be composed of an environmental condition recommendation model and a stimulus condition recommendation model.

In addition, the cultivation condition recommendation model building device 50 for increasing the active ingredient content in crops may be included as a component of the cultivation condition recommendation device 100, as shown in FIG. 9, or may be configured as a separate component. .

The recommendation model building device 50 includes a data collection module 60, a detection unit 70, and a learning module 80.

However, in some embodiments, the cultivation condition recommendation device 100 and the recommendation model building device 50 may include fewer or more components than the components shown in FIG. 9 .

When information on the target crop is received through the receiver 120, the controller 110 applies the information on the target crop to a recommendation model to extract cultivation conditions that can increase the content of the active ingredient in the target crop.

At this time, the recommendation model is built using deep learning, and when information on the target crop is input, cultivation conditions that can increase the content of active ingredients in the target crop can be extracted.

The environmental condition recommendation model can extract environmental conditions that can increase the content of active ingredients in the target crop when information on the target crop is applied.

The stimulation condition recommendation model can extract stimulation conditions that can increase the content of active ingredients in the target crop when information on the target crop is applied.

The communication unit 130 includes wired and wireless communication functions, communicates with the user's terminal 200 to exchange various information, and when linked to a smart farm system, provides cultivation conditions extracted from the smart farm.

The receiving unit 120 receives information about the target crop from the user terminal 200.

The database 140 may store various types of information such as target crop information and user conditions input from the user, and may also store empirical data based on crop cultivation results input and received from the user.

In addition, various data necessary for the cultivation condition recommendation device 100 may be stored.

The calculation unit 150 calculates the expected acquisition amount (expected content) of the active ingredient in the target crop when the target crop is grown under the cultivation conditions extracted through the recommendation model.

The data collection module 60 of the recommendation model building device 50 collects target data for extracting valid information, can receive target data directly or a URL, and includes a target data search algorithm to retrieve documents on the web. You can also search and select documents that meet the requirements of the target data as the target data.

The detection unit 70 detects information about the cultivation conditions of a specific crop in the target data and detects result data according to the provision of cultivation conditions detected in the target data.

The learning module 80 constructs a learning data set based on condition data for cultivation conditions detected in the target data through the detection unit 70 and detected result data corresponding to the cultivation conditions.

Then, the controller 110 trains the recommendation model by applying the learning data set constructed through the learning module 80 to the recommendation model.

The device for recommending cultivation conditions for increasing the active ingredient content in crops according to the embodiment of the present invention described above is a method and category of the invention for recommending cultivation conditions for increasing the active ingredient content in crops described through FIGS. 1 to 8 However, since the content is the same, redundant explanations and examples should be omitted.

The method according to an embodiment of the present invention described above may be implemented as a program (or application) and stored in a medium in order to be executed in conjunction with a server, which is hardware.

The above-mentioned program is C, C++, JAVA, machine language, etc. that can be read by the processor (CPU) of the computer through the device interface of the computer in order for the computer to read the program and execute the methods implemented in the program. It may include code coded in a computer language. These codes may include functional codes related to functions that define the necessary functions for executing the methods, and include control codes related to execution procedures necessary for the computer's processor to execute the functions according to predetermined procedures. can do. In addition, these codes may further include memory reference-related codes that indicate at which location (address address) in the computer's internal or external memory additional information or media required for the computer's processor to execute the above functions should be referenced. there is. In addition, if the computer's processor needs to communicate with any other remote computer or server to execute the above functions, the code uses the computer's communication module to determine how to communicate with any other remote computer or server. It may further include communication-related codes regarding whether communication should be performed and what information or media should be transmitted and received during communication.

The storage medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, examples of the storage medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc., but are not limited thereto. That is, the program may be stored in various recording media on various servers that the computer can access or on various recording media on the user's computer. Additionally, the medium may be distributed to computer systems connected to a network, and computer-readable code may be stored in a distributed manner.

The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. The software module may be RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, hard disk, removable disk, CD-ROM, or It may reside on any type of computer-readable recording medium well known in the art to which the present invention pertains.

Above, embodiments of the present invention have been described with reference to the attached drawings, but those skilled in the art will understand that the present invention can be implemented in other specific forms without changing its technical idea or essential features. You will be able to understand it. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive.

50: Recommendation model building device
60: data acquisition module
70: detection unit
80: Learning module
100: Cultivation conditions recommendation device
110: controller
120: Receiving unit
130: Department of Communications
140: database
200: terminal

Claims (19)

It relates to a method of recommending cultivation conditions for increasing the content of active ingredients in crops performed by a cultivation condition recommendation device,
Receiving, by the cultivation condition recommendation device, information on a target crop through a receiver;
Extracting cultivation conditions for increasing the content of active ingredients in the target crop by applying, by the cultivation condition recommendation device, information on the received target crop to at least one recommendation model built by deep learning through a controller; and
Receiving, by the cultivation condition recommendation device, information about the location of the cultivation area of the target crop through the receiver;
Receiving, by the cultivation condition recommendation device, information on equipment available for input into the cultivation conditions through the receiver;
The cultivation condition recommendation device deriving cultivation environment information about the cultivation location; and
A step of filtering, by the cultivation condition recommendation device, available cultivation conditions among the cultivation conditions based on the cultivation environment information and the equipment information,
The equipment information includes the type and specifications of equipment that can be used under the cultivation conditions,
After the extraction step, when the cultivation condition recommendation device cultivates the target crop under the extracted cultivation conditions through a calculation unit, calculating and providing an expected acquisition amount of the active ingredient that can be obtained from the target crop. Contains more,
Predicting, by the cultivation condition recommendation device, a climate change that may occur from a climate change record for a previous predetermined period of time at the cultivation location through a calculation unit; and
The cultivation condition recommendation device further includes a step of adding information on a possible error range to the calculated expected gain amount based on the predicted climate change through a calculation unit,
After the extraction step, the cultivation condition recommendation device receives empirical data according to completion of cultivation of the target crop through a receiver;
Further comprising the step of the cultivation condition recommendation device training the at least one recommendation model using the received empirical data through a controller,
The above empirical data is,
Containing active ingredient results obtained from the target crop for which cultivation has been completed and cultivation condition performance data indicating the extent to which the extracted cultivation conditions were provided in the process of cultivating the target crop,
How to recommend growing conditions to increase the content of active ingredients in crops.
According to paragraph 1,
After receiving information on the target crop, the cultivation condition recommendation device further includes a step of receiving at least one necessary active ingredient to be obtained from the target crop through a receiving unit,
The extraction step is,
A method of recommending cultivation conditions for increasing the content of active ingredients in crops, wherein the cultivation condition recommendation device extracts the cultivation conditions by applying information on the target crop and the required active ingredients to the recommendation model through a controller.

delete delete According to paragraph 1,
The cultivation condition recommendation device predicts when the climate change will occur from a climate change record for a certain period of time prior to the cultivation location, and provides a solution to cope with the predicted climate change, further comprising:
How to recommend growing conditions to increase the content of active ingredients in crops.
delete delete delete delete delete delete According to paragraph 1,
The recommended model includes a deep learning model using a learning dataset,
The learning data set is,
Contains condition data on the cultivation conditions mentioned with a specific crop in the target data, and result data on the content or acquisition amount of the active ingredient in the specific crop when the specific crop is grown under the cultivation conditions in the target data. doing,
How to recommend growing conditions to increase the content of active ingredients in crops.
According to paragraph 1,
The cultivation conditions include at least one of cultivation environmental conditions and specific stimulation conditions for crops,
How to recommend growing conditions to increase the content of active ingredients in crops.
delete delete In the device for recommending cultivation conditions for increasing the content of active ingredients in crops,
A receiving unit that receives information about the target crop;
It includes a controller that extracts cultivation conditions that can increase the content of active ingredients in the target crop by applying information on the target crop to a recommendation model,
The controller is,
The cultivation condition recommendation device receives information about the location of the cultivation area of the target crop through the receiver,
The cultivation condition recommendation device receives information on equipment that can be input to the cultivation conditions through the receiver,
The cultivation condition recommendation device derives cultivation environment information for the cultivation location, filters available cultivation conditions among the cultivation conditions based on the cultivation environment information and the equipment information,
The equipment information includes the type and specifications of equipment that can be used under the cultivation conditions,
The cultivation condition recommendation device calculates and provides an expected acquisition amount of the active ingredient that can be obtained from the target crop when the target crop is grown under the extracted cultivation conditions,
The cultivation condition recommendation device predicts possible climate changes from climate change records for a certain period of time prior to the cultivation location,
The cultivation condition recommendation device adds information on the possible error range to the calculated expected gain based on the predicted climate change,
The cultivation condition recommendation device receives empirical data according to completion of cultivation of the target crop through the receiver,
The cultivation condition recommendation device trains the recommendation model using the received empirical data,
The above empirical data is,
Containing active ingredient results obtained from the target crop for which cultivation has been completed and cultivation condition performance data indicating the extent to which the extracted cultivation conditions were provided in the process of cultivating the target crop,
Cultivation conditions recommendation device.
delete delete A recording medium combined with a computer, which is hardware, and equipped with a program for executing the method of recommending cultivation conditions for increasing the content of active ingredients in crops according to paragraph 1.