KR20230052454A - System and method for providing guide information for crops - Google Patents

Abstract

A method of providing crop cultivation guide information is disclosed. The method for providing crop cultivation guide information according to the present invention includes a learning step in which the machine learning module learns about crop cultivation conditions and yield; an input step in which the server receives information about a selected cultivation area from a user terminal; a score calculation step in which the machine learning module calculates a score for at least one or more crops based on data on crop cultivation conditions in the cultivation area; and a score information providing step of providing a score for each crop to the user terminal.

Description

Crop cultivation guide information provision system and method for providing crop cultivation guide information {System and method for providing guide information for crops}

The present invention relates to a crop cultivation guide information providing system and a crop cultivation guide information providing method.

Even those who do not grow crops commercially are given the opportunity to grow crops using weekend farms or private vegetable gardens.

However, there is a practical limit to the types of crops that can be cultivated, since knowledge and experience are inevitably lacking unless one is a person who grows crops as a business. Therefore, those who do not grow crops commercially tend to grow crops that are well known to the public and easy to grow, such as lettuce, pepper, and corn, compared to various crops.

Crops that have been cultivated a lot in the past and have a lot of data information such as cultivation conditions are good for individuals to grow as a hobby, but there is a problem that hobbies are limited because there is inevitably a limit to crop selection.

On the other hand, even if crops are grown, it is difficult for individuals to respond to environmental changes such as weather and climate change.

The technical problem to be solved by the present invention is to provide information helpful in selecting crops to be grown among various crops, while providing continuous guide information to control the cultivation performance of crops in the process of growing the crops. will be.

In order to solve the above technical problem, in the method for providing crop cultivation guide information according to an embodiment of the present invention, a server including a machine learning module provides crop cultivation guide information to a user terminal, and the machine learning module determines conditions for crop cultivation. A learning step of performing learning about output and yield; an input step in which the server receives information about a selected cultivation area from a user terminal; a score calculation step in which the machine learning module calculates a score for at least one or more crops based on data on crop cultivation conditions in the cultivation area; and a score information providing step of providing a score for each crop to the user terminal, wherein the score for the crop is calculated according to the learning result of the machine learning module, and the machine learning module calculates the yield per area in the past. It can be set to be the highest score when the cultivation conditions of the region with the highest number are entered as data.

In one embodiment of the present invention, the cultivation conditions include information on weather prediction, and the server compares the cultivation conditions in the region where the yield per area was the highest in the past with the cultivation conditions in the selected cultivation region to control among the cultivation conditions. generating cultivation condition improvement information including information instructing to adjust possible variables; and transmitting, by the server, the improvement information to the user terminal.

In one embodiment of the present invention, the step of updating the information on the weather prediction by the server; Includes information instructing the server to adjust controllable variables among the cultivation conditions by comparing the cultivation conditions of the region where yield per area was highest in the past with the cultivation conditions including the updated weather prediction information in the selected cultivation region Generating the cultivation condition update information to; The server may further include transmitting the update information to the user terminal.

In one embodiment of the present invention, the scoring step may include: inputting, by the server, cultivation condition data for the cultivation area to the machine learning module; Receiving information about controllable variables from a user terminal; adjusting, by the server, data on the cultivation conditions by reflecting the received controllable variables; and calculating, by the machine learning module, a score for each crop for the cultivation area based on the adjusted data.

In order to solve the above technical problem, a crop cultivation guide information providing system according to an embodiment of the present invention includes a database for storing data related to cultivation conditions; and a server that receives the database and information and provides crop cultivation guide information, wherein the server includes: a communication unit that receives information about a selected cultivation area from a user terminal; a control unit extracting information on cultivation conditions from the database for the selected cultivation area and inputting the information to the machine learning module; And a machine learning module that performs learning on the cultivation conditions and yield of the crop and calculates a score for at least one crop based on the data on the cultivation conditions input with respect to the cultivation area. The score for is calculated according to the learning result of the machine learning module, and the machine learning module is set to have the highest score when the cultivation conditions of the region where the yield per area was the highest in the past are input as data, and the communication unit is set to obtain the highest score for each crop. A score for may be transmitted to the user terminal.

The present invention has the effect of providing information helpful in selecting crops to be cultivated among various crops.

The present invention has the effect of providing continuous guide information to control the cultivation performance of the selected crop.

1 shows a crop cultivation guide information providing system according to an embodiment of the present invention.
2 shows a crop cultivation guide information providing method according to an embodiment of the present invention.
Figure 3 shows the detailed steps of the learning step regarding crop cultivation conditions and performance in the crop cultivation guide information providing method according to an embodiment of the present invention.
4 is a schematic diagram of machine learning in the crop cultivation guide information providing method according to an embodiment of the present invention.
Figure 5 shows the detailed steps of the score calculation step in the crop cultivation guide information providing method according to an embodiment of the present invention.
Figure 6 shows the detailed steps of the score calculation step according to another embodiment of the present invention.
Figure 7 shows the detailed steps of the score calculation step according to another embodiment of the present invention.
8 shows detailed steps of the cultivation condition improvement step in the crop cultivation guide information providing method according to an embodiment of the present invention.

Since the present invention can apply various transformations and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail in the detailed description. However, it should be understood that this is not intended to limit the present invention to specific embodiments, and includes all transformations, equivalents, and substitutes included in the spirit and scope of the present invention.

In describing the present invention, if it is determined that a detailed description of related known technologies may obscure the gist of the present invention, the detailed description will be omitted.

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

1 shows a crop cultivation guide information providing system according to an embodiment of the present invention.

Referring to FIG. 1 , a crop cultivation guide information providing system according to an embodiment of the present invention includes a server 100 and a database 150.

The server 100 may be either a server in which a service provider directly holds a device or a cloud server, and the server 100 includes a plurality of physically or logically separated terminals for providing information processing. It may be included, and it may be distributed and installed in various places or provided in the form of using a cloud service for storing and processing information.

The server 100 may include a communication unit 110, a control unit 120, a storage unit 130, and a machine learning module.

The communication unit 110 may transmit/receive information by communicating with the user terminal 200, the database 150, and the information providing institution 300, respectively.

The storage unit 130 may store necessary information to provide convenience in information processing. For example, the storage unit 130 may store and update information about users, information about crops selected by each user, and information about applications that can be installed in the user terminal 200 .

Also, the storage unit 130 may store learning results of the machine learning module 140 .

The control unit 120 may control the communication unit 110, the storage unit 130, and the machine learning module 140, and perform calculations related to service provision.

The control unit 120 may include a processor capable of arithmetic processing.

The machine learning module 140 may perform machine learning. The machine learning module 140 may perform machine learning and provide information about the result to the control unit 120 .

The machine learning module 140 may calculate a result related to input information based on machine learning. Information on the calculated result may be provided to the control unit 120 .

The database 150 may transmit and receive information to and from the server 100 and may provide previously stored information to the server 100 .

The server 100 may provide information obtained from the information providing agency 300 to the database 150 to be stored.

The database 150 may be configured as a separate device from the server 100, but may also be included as one component of the server 100.

Data for each region may be stored in the database 150 with respect to a specific region. For example, with respect to a specific region, past weather, climate data, soil data, and crop yield data may be stored.

Data stored in the database 150 may be conditioned data based on the yield of each crop. Specifically, it may be data on soil conditions (for example, moisture contained in the soil) and meteorological conditions from the time a specific crop is planted to the time it is harvested, and data on variables that can be processed.

For example, data on soil conditions could be the amount of nitrogen, phosphorus and potash fertilizers.

For example, data related to meteorological conditions may include temperature, precipitation, humidity, and amount of sunlight.

Prediction data related to cultivation conditions may be stored in the database 150 . For example, weather prediction data for each region may be stored. Since weather forecast data is data that changes with time, weather forecast data stored in the database 150 may be updated according to a set period. The server 100 may periodically collect weather forecast data from the information providing agency 300 and provide the weather forecast data to the database 150 to update the weather forecast data.

The user terminal 200 may be connected to the server 100 through a wired/wireless network, communicate with the server 100 to transmit necessary information, and receive guide information related to crop cultivation.

The user terminal 200 may be, for example, any one of a smartphone, a tablet PC, a notebook, and a desktop PC, and may perform the above functions even if they are not the same. If there is, it is not limited to the above embodiment.

The user terminal 200 may include a communication means for transmitting and receiving information with the server 100, a control means for controlling the terminal, a storage means for storing information, and a display means for displaying information.

The information providing agency 300 may retain information on soil classified by region, information on past weather and climate, and information on yield by crop.

The information providing agency 300 may provide the above information to the server 100 upon request.

The information providing institution 300 may be composed of an information providing service server that holds at least one or more of the above information.

The information providing agency 300 may be composed of one server, but may be composed of two or more servers each managed by two or more organizations that manage and record different information.

2 shows a crop cultivation guide information providing method according to an embodiment of the present invention.

Hereinafter, a description of the operation of the crop cultivation guide information providing system will be replaced by a description of a method of providing crop cultivation guide information using the server 100 and the database 150 as the main subjects.

In addition, it will be understood that the operation of the server 100 can be performed by the operations of the sub-components even if the sub-components of the server 100 are not specifically mentioned below.

Referring to FIG. 2, in step S210, the machine learning module 140 learns about crop cultivation conditions and performance.

Figure 3 shows the learning step for crop cultivation conditions and performance in detailed steps.

Here, it is assumed that the data on past cultivation conditions have been secured in advance by the information providing agency 300 or the server 100 manager's input.

In step S211, the control unit 120 selects data on past cultivation conditions from the database and inputs them to the machine learning module 140.

Cultivation condition data may include soil information, past weather, and past climate information for a specific region.

In step S213, the control unit 120 selects past yields for crops and inputs them to the machine learning module 140.

The above-mentioned cultivation conditions and yield can be extracted by region for all crops to be learned.

Crops to be learned must have a history of cultivation and production in at least one region.

In step S215, the controller 120 assigns weights to variables related to machine learning.

Weighting can be directly input based on expertise.

In step S217, the machine learning module performs machine learning based on the input data on cultivation conditions and data on yield.

Machine learning in step S217 aims to predict the yield of a specific crop under specific cultivation conditions. In the machine learning in an embodiment of the present invention, a criterion for a result value may be set so that a specific crop obtains the highest score (eg, 100 points) under the cultivation conditions of a region where the yield per unit area was the highest in the past.

4 shows a schematic diagram of machine learning according to an embodiment of the present invention.

Referring to FIG. 4 , learning data for machine learning are data on past cultivation conditions of each crop for each region and past yield data. The machine learning module 140 learns the relationship between past cultivation condition data and past yield data.

The machine learning algorithm can select any one of known machine learning methods such as ANN, DNN, CNN, RNN, DLP, and MLP. However, not only known methods but also machine learning algorithms to be improved or developed in the future can be used as long as they are suitable for the conditions of the present invention.

The machine learning module 140 that has undergone machine learning receives data (In) about new cultivation conditions for a specific crop in a specific region as an input, and calculates a score as output data (Out).

For the score, the cultivation condition with the highest yield per area in the past for a specific crop is set as the highest score (100 points), and the closer the condition is, the closer the score (for example, 90 points) to the highest score can be calculated.

Referring back to FIG. 2 , in step S220 , the machine learning module 140 receives information about the cultivation area.

Information about the cultivation area may be input according to a set criterion (eg, all areas). In this case, the input subject may be the control unit 120, which is a component of the server 100.

Information about the cultivation area may be input from the user terminal 200 . In this case, being input may mean that information about the cultivation area is received through communication with the user terminal 200 . The user may input information about the cultivation area through a program provided with an input interface such as an application installed in the user terminal 200 . The application may control the user terminal 200 to transmit input information to the server 100 .

In step S230, a score for each crop for the cultivation area is calculated.

For example, the scores for lettuce, onion, and corn in Namyangju, Gyeonggi-do can be calculated as 75 points, 80 points, and 88 points, respectively.

On the other hand, the cultivation area may be set more subdivided or wider than the administrative district depending on the setting.

5 to 7 show detailed steps of the score calculation step according to different embodiments of the present invention.

Referring to FIG. 5 , in step S231, the server 100 inputs cultivation condition data for the cultivation area to the machine learning module 140. The server 100 may read cultivation condition data updated to the latest date in the current database 150 and input the data to the machine learning module 140 . Cultivation condition data may include soil data and meteorological prediction data.

In step S233, the machine learning module 140 calculates a score for each crop for the cultivation area.

The cultivation area may be, for example, an area selected by the user.

The machine learning module 140 may calculate scores based on data on cultivation conditions in a growing region for all crops having data.

The score of each crop can be expressed as a relative value to the highest score (100 points).

In step S235, the server 100 may transmit and provide score information of each crop to the user terminal 200 through the communication unit 110.

The embodiment shown in FIG. 6 will be described as follows.

Referring to FIG. 6 , in step S331, cultivation condition data for the cultivation area is input.

The user may select crops to be grown by referring to the scores of the crops listed in the region desired to be grown. Since this step is the same as described in step S231 above, a detailed description thereof will be omitted.

In step S333, the server 100 may receive controllable variables.

A user may input controllable variables through the user terminal 200 . An application installed in the user terminal 200 may control the user terminal 200 to provide information on controllable variables to the server 100 .

Controllable variables may refer to variables that can be adjusted by a user among data on cultivation conditions.

For example, the user may adjust at least one of the cultivation temperature and the amount of light by using artificial means such as designing a greenhouse and operating an air conditioner.

For example, users can control the amount of precipitation by spraying water on the land they are cultivating.

For example, the user may adjust the amount of light using a shield such as a black cloth.

For example, the user can control conditions regarding the soil using nitrogen, phosphoric acid, and potash fertilizers.

In addition to the controllable variables, the user can also input a range of controllable variables. For example, if the cultivation temperature can be controlled within the range of 5°C, that value can be entered.

The server 100 receives information about controllable variables and their ranges through the communication unit 110, and these information may be input to the machine learning module 140 as it is or processed.

In step S335, the server 100 may adjust cultivation condition data. Here, adjusting the cultivation condition data may mean changing controllable variables among the variables related to the cultivation conditions according to the setting.

Cultivation condition data can be adjusted differently depending on settings. For example, if the user inputs the temperature as adjustable in the range of 5°C, the server 100 may adjust the temperature as close as possible to the optimal temperature condition. For example, if the temperature data before adjustment is 20°C and the optimum temperature condition is 30°C, the temperature data may be adjusted to 25°C. For example, if the temperature data before adjustment is 20°C and the optimum temperature condition is 23°C, the temperature data may be adjusted to 23°C.

In step S337, the machine learning module 140 calculates a score for each crop for the cultivation area. The difference between this step and the aforementioned step S233 is that the score for each crop was calculated based on the adjusted cultivation condition data.

In step S339, the server 100 may transmit and provide score information of each crop to the user terminal 200 through the communication unit 110.

The user may select crops to be grown by referring to the scores of the crops listed in the region desired to be grown. The user may be provided with a crop score list adjusted to the user by inputting information about variables that the user can directly control.

Compared to crop cultivation in a natural state where no action is taken, the user is provided with a prediction ranking when the user actively intervenes, so that the user can select a crop that is expected to produce a higher yield when managed by the user.

The embodiment shown in FIG. 7 will be described as follows.

Referring to FIG. 7 , steps S431 to S433 correspond to steps S231 to 237 illustrated in FIG. 5 , respectively. Steps S444 to S447 correspond to steps S333 to S339, respectively.

The embodiment shown in FIG. 7 provides the user terminal 200 with information on the score for each crop based on the data before adjustment, receives (receives) the adjusted data, adjusts the score for each crop, and adjusts the score for each crop. It can be described as providing information.

According to the embodiment of FIG. 7 , the user selects crops to be grown by comparing the scores for each crop when no action is taken to change the cultivation conditions and the score for each crop when there is an active action to take a change on the cultivation conditions. We can help you choose.

8 shows detailed steps of the cultivation condition improvement step in the crop cultivation guide information providing method according to an embodiment of the present invention.

Referring to FIG. 8 , in step S251, the server 100 generates cultivation condition improvement information.

Improvement information on cultivation conditions may be generated for a specific crop set by the user to be cultivated in a specific region.

The improvement information of cultivation conditions compares the data on the past cultivation conditions (hereinafter referred to as 'optimal conditions') of the area where the crops were most produced in the past and the data on the cultivation conditions in the area selected by the user to determine the cultivation conditions. It may be improvement information about controllable variables to be close to the optimal condition.

For example, when the temperature of a specific region is 23°C and the optimal condition is 25°C, the improvement information may be information including “raise the temperature by 2°C”.

In step S253, the server 100 may provide the generated improvement information to the user by transmitting it to the user terminal 200.

The server 100 may provide guidance information on how to effectively control variables related to cultivation conditions together with improvement information. Such guide information may be prepared or secured in advance by an administrator of the server 100 and stored in the storage unit 130 .

In step S257, the server 100 inputs cultivation condition update data.

Cultivation condition update data means that data on cultivation conditions is updated in response to changes in the prediction of environmental factors related to cultivation conditions.

For example, the precipitation on October 5 predicted on August 5 may be different from the precipitation on October 5 predicted on September 5. Therefore, it is necessary to update the data by setting an update cycle according to the passage of time.

The server 100 may receive data that can be obtained from the information providing institution 300 among data on cultivation conditions at every possible cycle and store them in the database 150 .

The server 100 can update the database 150 as soon as the data is secured (for example, as newly input by a manager) for data input other than the information providing institution 300 among data related to cultivation conditions. .

In step S257, the server 100 may generate cultivation condition update information. Here, the cultivation condition update information is cultivated by comparing the data on the past cultivation conditions (hereinafter referred to as 'optimal conditions') of the area where the crop has been most produced in the past and the data on the updated cultivation conditions in the area selected by the user. It may be update information about controllable variables so that the condition is close to the optimal condition.

For example, when the temperature of a specific region is 20°C and the optimum condition is 25°C, the improvement information includes “raise the temperature by 5°C”, but if the temperature of the updated data is 23°C, the update information is “raise the temperature by 5°C”. It may be information including “raised by 2°C”.

In an embodiment of the present invention, improvement information is provided when cultivation of the selected crop is started and update information is continuously provided when cultivation is continued, so that the user can enjoy cultivation of the selected crop close to optimal conditions.

Meanwhile, the server 100 may provide additional information related to cultivation to the user terminal 200 . For example, the server 100 may provide the user terminal 200 with information about diseases and pests that may occur under specific temperature, humidity, and precipitation conditions. For example, the server 100 may provide the user terminal 200 with information on meteorological disasters such as storm, frost, drought, and heavy snow in advance. The server 100 may provide information on a preparation method together with the provision of the above information. Through this, the user is provided with a guide on cultivation as well as information on diseases and pests and meteorological disasters, so that the user can prepare in advance.

Terms used in this application are only used to describe specific embodiments, and are not intended to limit the present invention. In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

100: server
110: communication department
120: control unit
130: storage unit
140: machine learning module
150: database
200: user terminal
300: information provider

Claims (5)

A method in which a server including a machine learning module provides crop cultivation guide information to a user terminal,
A learning step in which the machine learning module learns about crop cultivation conditions and yield;
an input step in which the server receives information about a selected cultivation area from a user terminal;
a score calculation step in which the machine learning module calculates a score for at least one or more crops based on data on crop cultivation conditions in the cultivation area; and
Including; providing score information for providing a score for each crop to the user terminal;
The score for the crop is calculated according to the learning result of the machine learning module,
The method of providing crop cultivation guide information, characterized in that the machine learning module is set to obtain the highest score when the cultivation conditions of the region where the yield per area was the highest in the past are input as data.
According to claim 1,
The cultivation conditions include information on weather forecasting,
generating, by the server, cultivation condition improvement information including information instructing controllable variables among the cultivation conditions to be adjusted by comparing the cultivation conditions in the selected cultivation region with the cultivation conditions in the region where yield per area was highest in the past; and
The method of providing crop cultivation guide information, characterized in that it further comprises; transmitting, by the server, the improvement information to the user terminal.
According to claim 2,
updating, by the server, weather prediction information;
Includes information instructing the server to adjust controllable variables among the cultivation conditions by comparing the cultivation conditions of the region where yield per area was highest in the past with the cultivation conditions including the updated weather prediction information in the selected cultivation region Generating the cultivation condition update information to;
The method of providing crop cultivation guide information, characterized in that it further comprises; transmitting, by the server, the update information to the user terminal.
According to claim 1,
In the scoring step,
the server inputting cultivation condition data for the cultivation area to the machine learning module;
Receiving information about controllable variables from a user terminal;
adjusting, by the server, data on the cultivation conditions by reflecting the received controllable variables; and
The method of providing crop cultivation guide information comprising the step of calculating, by the machine learning module, a score for each crop for the cultivation area based on the adjusted data.
a database for storing data related to cultivation conditions; and
A server that receives the database and information and provides crop cultivation guide information;
The server,
Communication unit for receiving information about the cultivation area selected from the user terminal;
a control unit extracting information on cultivation conditions from the database for the selected cultivation area and inputting the information to the machine learning module; and
A machine learning module that performs learning on the cultivation conditions and yield of crops and calculates a score for at least one crop based on the data on the cultivation conditions input with respect to the cultivation area;
The score for the crop is calculated according to the learning result of the machine learning module,
The machine learning module is set to have the highest score when the cultivation conditions of the region where the yield per area was the highest in the past are input as data,
The system for providing crop cultivation guide information, characterized in that the communication unit transmits the score for each crop to the user terminal.

Images