KR102586532B1 - Method, device and system for providing online sales platform service for agricultural and fishery product based on forecast of price volatility - Google Patents

Abstract

According to one embodiment, a method of providing an online sales platform service for agricultural and fisheries products based on price volatility prediction, performed by an apparatus, includes the steps of: receiving a request for prediction of price volatility of a first food in a first period from a manager terminal; Confirming the production volume of the first food by period based on the production volume information of the first food, and confirming the sales volume of the first food by period based on the sales volume information of the first food; When the production area of the first food is confirmed to be a first area, checking weather conditions for each period of the first area and weather forecast conditions for the first period based on weather information of the first area; Generating a first matching result by matching the production volume of the first food for each period, weather conditions for each period in the first region, and weather forecast conditions for the first period; Applying the first matching result to the first artificial intelligence model, based on the output of the first artificial intelligence model, setting the production volume of the first food expected to be produced in the first period as the first production volume step; Generating a second matching result by matching sales volume of the first food by period, weather conditions of the first region by period, and weather forecast conditions of the first period; Applying the second matching result to a second artificial intelligence model, based on the output of the second artificial intelligence model, setting the sales volume of the first food expected to be sold in the first period as the first sales volume. step; calculating a surplus inventory amount by subtracting the first sales volume from the first production volume; Confirming that the reference price of the first food is set to the first price; predicting price volatility of the first food such that the price of the first food will be maintained at the first price in the first period when it is confirmed that the spare stock amount is within a preset reference stock amount range; If it is confirmed that the free stock amount is outside the standard stock amount range and less than the minimum value of the standard stock amount range, the first weight is set to a higher value as the free stock amount is smaller within the range from 100% to 150%, and the first weight is set to a higher value. A second price is calculated as a value multiplied by 1 price and the first weight, and the price of the first food is expected to change from the first price to the second price in the first period, and the price of the first food is predicting volatility; If it is confirmed that the free stock amount is outside the standard stock amount range and is greater than the maximum value of the standard stock amount range, the second weight is set to a lower value as the free stock amount is greater within the range from 50% to 100%, and the second weight is set to a lower value. A third price is calculated by multiplying the 1 price and the second weight, and the price of the first food is expected to change from the first price to the third price in the first period, and the price of the first food is predicting volatility; A method of providing an online sales platform service for agricultural and marine products based on price volatility prediction is provided, including transmitting a result of predicting the price volatility of the first food to the manager terminal.

Description

Method, device and system for providing online sales platform service for agricultural and marine products based on prediction of price volatility {METHOD, DEVICE AND SYSTEM FOR PROVIDING ONLINE SALES PLATFORM SERVICE FOR AGRICULTURAL AND FISHERY PRODUCT BASED ON FORECAST OF PRICE VOLATILITY}

The embodiments below relate to technology for providing an online sales platform service for agricultural and fishery products based on prediction of price volatility.

The production volume of agricultural and fisheries foods may fluctuate from period to period due to the influence of seasons, climate, etc., and sales volume may fluctuate from period to period due to the influence of seasons, holidays, etc.

In other words, because the production volume and sales volume of agricultural and fishery foods are not fixed for each period and continuously fluctuate, it is difficult to determine the sales price for the food.

Accordingly, the demand for predicting the production and sales volume of agricultural and fishery foods and, through this, the price volatility of agricultural and fishery foods is increasing, and research on related technologies is required.

Korean Patent Publication No. 10-2023-0029017 Korean Patent Publication No. 10-2023-0075678 Korean Patent Publication No. 10-2022-0151453 Korean Patent No. 10-2199620

According to one embodiment, the purpose is to provide a method, device, and system for providing an online sales platform service for agricultural and marine products based on prediction of price volatility.

The object of the present invention is not limited to the object mentioned above, and other objects not mentioned can be clearly understood from the description below.

According to one embodiment, a method of providing an online sales platform service for agricultural and fisheries products based on price volatility prediction, performed by an apparatus, includes the steps of: receiving a request for prediction of price volatility of a first food in a first period from a manager terminal; Confirming the production volume of the first food by period based on the production volume information of the first food, and confirming the sales volume of the first food by period based on the sales volume information of the first food; When the production area of the first food is confirmed to be a first area, checking weather conditions for each period of the first area and weather forecast conditions for the first period based on weather information of the first area; Generating a first matching result by matching the production volume of the first food for each period, weather conditions for each period in the first region, and weather forecast conditions for the first period; Applying the first matching result to the first artificial intelligence model, based on the output of the first artificial intelligence model, setting the production volume of the first food expected to be produced in the first period as the first production volume step; Generating a second matching result by matching sales volume of the first food by period, weather conditions of the first region by period, and weather forecast conditions of the first period; Applying the second matching result to a second artificial intelligence model, based on the output of the second artificial intelligence model, setting the sales volume of the first food expected to be sold in the first period as the first sales volume. step; calculating a surplus inventory amount by subtracting the first sales volume from the first production volume; Confirming that the reference price of the first food is set to the first price; predicting price volatility of the first food such that the price of the first food will be maintained at the first price in the first period when it is confirmed that the spare stock amount is within a preset reference stock amount range; If it is confirmed that the free stock amount is outside the standard stock amount range and less than the minimum value of the standard stock amount range, the first weight is set to a higher value as the free stock amount is smaller within the range from 100% to 150%, and the first weight is set to a higher value. A second price is calculated as a value multiplied by 1 price and the first weight, and the price of the first food is expected to change from the first price to the second price in the first period, and the price of the first food is predicting volatility; If it is confirmed that the free stock amount is outside the standard stock amount range and is greater than the maximum value of the standard stock amount range, the second weight is set to a lower value as the free stock amount is greater within the range from 50% to 100%, and the second weight is set to a lower value. A third price is calculated by multiplying the 1 price and the second weight, and the price of the first food is expected to change from the first price to the third price in the first period, and the price of the first food is predicting volatility; A method of providing an online sales platform service for agricultural and marine products based on price volatility prediction is provided, including transmitting a result of predicting the price volatility of the first food to the manager terminal.

The method of providing an agricultural and fishery food online sales platform service based on the prediction of price volatility determines, based on weather information of the first region, whether a period of bad weather adversely affecting production of the first food is included during the first period. Analyzing step; If it is determined that the first period does not include a period of inclement weather, setting the first ratio to 100%; If it is confirmed that a period of bad weather is included in the first period, the bad weather period within the first period is set as a 1-1 period, the number of days of the first period is set to a first number, and the number of days in the first period is set to a first number. -1 setting the number of days in the period to a second number; calculating a second ratio as a value obtained by dividing the second numerical value by the first numerical value, and setting the first ratio as a value obtained by adding 100% and the second ratio; Based on the schedule information of the first period, analyzing whether a period that has a positive impact on sales of the first food is included in the first period; If it is confirmed that the stock period is not included in the first period, setting a third ratio to 100%; If it is confirmed that the main period is included in the first period, the main period within the first period is set as the 1-2 period, the number of days of the first period is set to a first number, and the first period is set to a first number. -2 setting the number of days in the period to a third number; calculating a fourth ratio as a value obtained by dividing the third value by the first value, and setting the third ratio as a value obtained by adding 100% and the fourth ratio; And when the first ratio and the third ratio are respectively set, the fifth ratio is calculated as a value multiplied by the first ratio and the third ratio, and the fifth ratio is calculated as the ratio of the first food in the first period. A step of setting a price adjustment ratio to adjust price volatility may be further included.

The step of predicting the price volatility of the first food such that the price of the first food will be maintained at the first price in the first period includes calculating the fourth price as a product of the first price and the fifth ratio. Calculating; calculating a difference between the first price and the fourth price as a first difference price; If the first difference price is confirmed to be lower than a preset first reference price, predicting the price volatility of the first food such that the price of the first food will be maintained at the first price in the first period. ; and if the first difference price is confirmed to be higher than the first reference price, the price of the first food product will change from the first price to the fourth price in the first period, It may include the step of predicting volatility.

Predicting the price volatility of the first food such that the price of the first food will change from the first price to the second price in the first period includes multiplying the second price and the fifth ratio. calculating a fifth price from the value; calculating a difference between the second price and the fifth price as a second difference price; If the second difference price is confirmed to be lower than the preset second reference price, the price of the first food will change from the first price to the second price in the first period, and the price of the first food will change from the first price to the second price. predicting volatility; and if the second difference price is confirmed to be higher than the second reference price, the price of the first food product will change from the first price to the fifth price in the first period, It may include the step of predicting volatility.

Predicting the price volatility of the first food product such that the price of the first food product will change from the first price to the third price in the first period includes multiplying the third price and the fifth ratio. calculating a sixth price from the value; calculating the difference between the third price and the sixth price as a third difference price; If the third difference price is confirmed to be lower than the preset third reference price, the price of the first food will change from the first price to the third price in the first period, and the price of the first food will change from the first price to the third price. predicting volatility; If the third difference price is confirmed to be higher than the third reference price, calculating the difference between the first price and the sixth price as a fourth difference price; If the fourth difference price is confirmed to be lower than the third reference price, predicting price volatility of the first food such that the price of the first food will be maintained at the first price in the first period; and if the fourth difference price is confirmed to be higher than the third reference price, the price of the first food product will change from the first price to the sixth price in the first period, It may include the step of predicting volatility.

According to one embodiment, by predicting the production and sales volume of agricultural and fishery foods and predicting the price volatility of agricultural and fishery foods based on the prediction results for production and sales volume, when selling agricultural and fishery foods online, the sales price is determined by period. It has the effect of helping to make automatic decisions.

Meanwhile, the effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below.

1 is a diagram schematically showing the configuration of a system according to an embodiment.
Figure 2 is a flow chart for explaining the process of predicting the production and sales volume of food and calculating spare inventory through the predicted production and sales volume according to an embodiment.
Figure 3 is a flow chart to explain the process of predicting price volatility of food according to one embodiment.
Figure 4 is a flowchart for explaining the process of setting a price adjustment ratio in consideration of weather and items according to an embodiment.
5 shows that the price of the first food will be maintained at the first price in the first period according to an embodiment, and when the price volatility of the first food is predicted, the price volatility of the first food is adjusted according to the price adjustment ratio. This is a flowchart to explain the process.
Figure 6 shows that the price of the first food will change from the first price to the second price in a first period according to an embodiment, and when the price volatility of the first food is predicted, the price of the first food is changed according to the price adjustment ratio. This is a flow chart to explain the process of adjusting price volatility.
Figure 7 shows that the price of the first food will change from the first price to the third price in the first period according to an embodiment, and when the price volatility of the first food is predicted, the price of the first food is changed according to the price adjustment ratio. This is a flow chart to explain the process of adjusting price volatility.
Figure 8 is a flow chart to explain the process of providing a notification service for securing additional food according to an embodiment.
Figure 9 is a flowchart for explaining a process for providing a notification service about the amount of food stocked by day according to an embodiment.
Figure 10 is a flowchart for explaining the process of inspecting a box packaging food according to one embodiment.
FIG. 11 is a flowchart illustrating a process for providing a notification service regarding which process requires inspection when the first box is classified as a defective box according to an embodiment.
Figure 12 is an exemplary diagram of the configuration of a device according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the attached drawings. However, various changes can be made to the embodiments, so the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents, or substitutes for the embodiments are included in the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Terms such as first or second may be used to describe various components, but these terms should be interpreted only for the purpose of distinguishing one component from another component. For example, a first component may be named a second component, and similarly, the second component may also be named a first component.

When a component is referred to as being “connected” to another component, it should be understood that it may be directly connected or connected to the other component, but that other components may exist in between.

The terms used in the examples are for descriptive purposes only and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by a person of ordinary skill in the technical field to which the embodiments belong. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and unless explicitly defined in the present application, should not be interpreted in an ideal or excessively formal sense. No.

In addition, when describing with reference to the accompanying drawings, identical components will be assigned the same reference numerals regardless of the reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiments, if it is determined that detailed descriptions of related known technologies may unnecessarily obscure the gist of the embodiments, the detailed descriptions are omitted.

Embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

In an embodiment, an artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, it is a system in which machines learn and make decisions on their own. As artificial intelligence systems are used, recognition rates improve and sellers' tastes can be more accurately understood, and existing rule-based smart systems are gradually being replaced by deep learning-based artificial intelligence systems.

Artificial intelligence technology consists of machine learning and element technologies using machine learning. Machine learning is an algorithmic technology that classifies/learns the characteristics of input data on its own, and elemental technology is a technology that mimics the functions of the human brain such as cognition and judgment by utilizing machine learning algorithms such as deep learning, including linguistic understanding and visual It consists of technical areas such as understanding, reasoning/prediction, knowledge expression, and motion control.

The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding is a technology that recognizes and applies/processes human language/characters and includes natural language processing, machine translation, conversation systems, question and answer, and voice recognition/synthesis. Visual understanding is a technology that recognizes and processes objects like human vision, and includes object recognition, object tracking, image search, person recognition, scene understanding, spatial understanding, and image improvement. Inferential prediction is a technology that judges information to make logical inferences and predictions, and includes knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendations. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and includes knowledge construction (data creation/classification) and knowledge management (data utilization). Motion control is a technology that controls the autonomous driving of vehicles and the movement of robots, and includes motion control (navigation, collision, driving), operation control (behavior control), etc.

Generally, in order to apply machine learning algorithms to real life, learning is performed using a trial and error method due to the nature of the basic methodology of machine learning. In particular, deep learning requires hundreds of thousands of iterations. It is impossible to execute this in an actual physical external environment, so instead, the actual physical external environment is virtually implemented on a computer and learning is performed through simulation.

1 is a diagram schematically showing the configuration of a system according to an embodiment.

Referring to FIG. 1, a system according to one embodiment may include an administrator terminal 100 and a device 200.

First, the administrator terminal 100 and the device 200 can be connected through a communication network, and the communication network is configured regardless of the communication mode, such as wired or wireless, so that communication between servers and between servers and terminals is performed. It can be implemented in various forms.

The manager terminal 100 may be implemented as a computing device with a communication function, for example, but is not limited to a mobile phone, desktop PC, laptop PC, tablet PC, smartphone, etc., and is not limited to external It can also be implemented as various types of communication devices that can be connected to a server.

The administrator terminal 100 may be configured to perform all or part of the calculation function, storage/reference function, input/output function, and control function of a typical computer. The administrator terminal 100 may be configured to communicate with the device 200 wired or wirelessly.

The administrator terminal 100 is connected to a web page operated by a person or organization providing services using the device 200, or an application developed and distributed by a person or organization providing services using the device 200. Can be installed. The administrator terminal 100 may be linked to the device 200 through a web page or application.

The device 200 may be its own server owned by a person or organization that provides services using the device 200, a cloud server, or a p2p (peer-to-peer) set of distributed nodes. It may be possible. The device 200 may be configured to perform all or part of the calculation function, storage/reference function, input/output function, and control function of a typical computer. The device 200 may be equipped with at least one artificial intelligence model that performs an inference function.

The device 200 may be configured to communicate wired or wirelessly with the administrator terminal 100, control the operation of the administrator terminal 100, and control what information to display on the screen of the administrator terminal 100. .

The device 200 can provide a platform service for selling agricultural and fishery products online, and can be implemented as a server that provides the platform service.

Meanwhile, for convenience of explanation, only the manager terminal 100 is shown in FIG. 1, but the number of terminals may vary depending on the embodiment. As long as the processing capacity of the device 200 allows, the number of terminals is not particularly limited.

According to one embodiment, the device 200 can predict the production and sales volume of food based on artificial intelligence.

In the present invention, artificial intelligence (AI) refers to technology that imitates human learning ability, reasoning ability, perception ability, etc. and implements this with a computer, and includes concepts such as machine learning and symbolic logic. may include. Machine Learning (ML) is an algorithmic technology that classifies or learns the characteristics of input data on its own. Artificial intelligence technology is a machine learning algorithm that analyzes input data, learns the results of the analysis, and makes judgments or predictions based on the results of the learning. Additionally, technologies that mimic the functions of the human brain, such as cognition and judgment, using machine learning algorithms can also be understood as the category of artificial intelligence. For example, technical fields such as verbal understanding, visual understanding, reasoning/prediction, knowledge representation, and motion control may be included.

Machine learning can refer to the process of training a neural network model using experience processing data. Machine learning can mean that computer software improves its own data processing capabilities. A neural network model is built by modeling the correlation between data, and the correlation can be expressed by a plurality of parameters. A neural network model extracts and analyzes features from given data to derive correlations between data. Repeating this process to optimize the parameters of the neural network model can be called machine learning. For example, a neural network model can learn the mapping (correlation) between input and output for data given as input-output pairs. Alternatively, a neural network model may learn the relationships by deriving regularities between given data even when only input data is given.

An artificial intelligence learning model or neural network model may be designed to implement the human brain structure on a computer, and may include a plurality of network nodes with weights that simulate neurons of a human neural network. A plurality of network nodes may have a connection relationship with each other by simulating the synaptic activity of neurons in which neurons exchange signals through synapses. In an artificial intelligence learning model, multiple network nodes are located in layers of different depths and can exchange data according to convolutional connection relationships. The artificial intelligence learning model may be, for example, an artificial neural network model (Artificial Neural Network), a convolution neural network (CNN) model, etc. As an example, an artificial intelligence learning model may be machine-learned according to methods such as supervised learning, unsupervised learning, and reinforcement learning. Machine learning algorithms for performing machine learning include Decision Tree, Bayesian Network, Support Vector Machine, Artificial Neural Network, and Ada-boost. , Perceptron, Genetic Programming, Clustering, etc. can be used.

Among them, CNN is a type of multilayer perceptrons designed to use minimal preprocessing. CNN consists of one or several convolution layers and general artificial neural network layers on top of them, and additionally utilizes weights and pooling layers. Thanks to this structure, CNN can fully utilize input data with a two-dimensional structure. Compared to other deep learning structures, CNN shows good performance in both video and audio fields. CNNs can also be trained via standard back propagation. CNNs have the advantage of being easier to train and using fewer parameters than other feedforward artificial neural network techniques.

Convolutional networks are neural networks that contain sets of nodes with bound parameters. The increasing size of available training data and the availability of computational power, combined with algorithmic advances such as piecewise linear unit and dropout training, have led to significant improvements in many computer vision tasks. For extremely large data sets, such as those available for many tasks today, overfitting is not critical, and increasing the size of the network improves test accuracy. Optimal use of computing resources becomes a limiting factor. For this purpose, distributed, scalable implementations of deep neural networks can be used.

The device 200 can predict the price volatility of food using the results of predicting the production and sales volume of food, and transmit the prediction result of the price volatility of food to the manager terminal 100, through which, the Based on predictions of price volatility, managers can be provided with sales strategies on how to sell agricultural and marine products online. A detailed description related to this will be described later with reference to FIGS. 2 and 3.

Figure 2 is a flow chart for explaining the process of predicting the production and sales volume of food and calculating spare inventory through the predicted production and sales volume according to an embodiment.

Referring to FIG. 2, first, in step S201, the device 200 may receive a request to predict the price volatility of the first food in the first period from the manager terminal 100. Here, a request to predict the price volatility of the first food in the first period is a request to predict how the price of the first food will change in the first period.

According to one embodiment, the first period is a future period a certain period of time has passed from the present, and can be set at the request of an administrator, and can be set based on various periods such as weeks, months, and quarters.

According to one embodiment, the first food is one of the foods sold on an agricultural, fisheries and food online sales platform, and can be selected at the request of the manager.

In step S202, the device 200 may check the production volume of the first food by period based on the production volume information of the first food, and check the sales volume of the first food by period based on the sales volume information of the first food. Here, the production volume information of the first food and the sales volume information of the first food may be obtained from the database of the device 200.

That is, when the device 200 receives a request to predict the price volatility of the first food in the first period from the manager terminal 100, the device 200 searches the information stored in the database to provide production information of the first food and sales volume of the first food. Information can be obtained individually.

According to one embodiment, the production information of the first food is information indicating how much of the first food was produced by period, and how much of the first food was produced by period based on various periods such as day, week, month, quarter, etc. It may include information about production volume representing . At this time, the production volume information of the first food may only include information about the production volume within a predetermined period, for example, within the last 5 years. In addition, the production information of the first food may include only information about the production volume of the first food produced in a specific region, for example, information about the production volume of the first food produced in the first region by period. It can be included.

According to one embodiment, the sales volume information of the first food is information indicating how much the first food has been sold by period, and how much of the first food has been sold by period based on various periods such as day, week, month, and quarter. It may include information about sales volume representing . At this time, the sales volume information of the first food may only include information about the sales volume within a predetermined period, for example, within the last 5 years. In addition, the sales volume information of the first food may only include information about the sales volume of the first food sold on the agricultural and fisheries food online sales platform. For example, the sales volume of the first food by period and sold on the agricultural and fisheries food online sales platform. It may include information about.

In step S203, the device 200 may confirm that the production area of the first food is the first area. At this time, the device 200 may confirm that the production area of the first food is the first area, based on the food information of the first food. Here, food information of the first food may be obtained from the database of the device 200.

That is, the device 200 can obtain food information of the first food by querying the information stored in the database, and confirm that the production area of the first food is the first area based on the obtained food information of the first food. there is.

According to one embodiment, the food information of the first food may include food-related information such as type, name, country of origin, size, price, standard weight, packaging unit, packaging method, storage temperature, expiration date, etc. .

In step S204, the device 200 may check the weather condition for each period of the first area and the weather forecast condition for the first period based on the weather information of the first area. Here, weather information for the first region may be obtained from an external server that manages weather information. At this time, the weather conditions for each period of the first region represent the past weather conditions of the first region for each period, and can be expressed as weather conditions such as weather, precipitation, wind speed, temperature, and humidity, and the weather forecast state for the first period is the first weather condition. It represents the future weather conditions of the first period in the region and can be expressed as weather conditions such as weather, precipitation, wind speed, temperature, and humidity.

That is, when the production area of the first food is confirmed to be the first area, the device 200 may transmit a request for provision of weather information of the first area to an external server that manages weather information, and may transmit a request for provision of weather information of the first area from the external server to the first area. You can obtain weather information.

According to one embodiment, the weather information of the first region includes information recording past weather conditions indicating what the weather conditions of the first region were by period and future weather conditions indicating what the weather conditions of the first area will be by period. It may include information predicting weather conditions, and information indicating what the weather conditions were in the first region based on various periods such as daily, week, month, quarter, etc., and what the weather conditions in the first region will be. May contain predictive information. At this time, the weather information of the first region may include weather information for a predetermined period, for example, information recording weather conditions within the last 5 years and information predicting weather conditions within the next 1 year. can do.

In step S205, the device 200 may generate a first matching result by matching the production volume of the first food by period, the weather condition by period of the first region, and the weather forecast state of the first period.

In step S206, the device 200 may apply the first matching result to the first artificial intelligence model learned in advance. Here, the first artificial intelligence model predicts the production amount of food expected to be produced in a specific period after receiving the matching result of matching the production volume of a specific food by period, the weather condition by period in a specific region, and the weather forecast state of a specific period. It may be an algorithm that outputs.

In other words, the first artificial intelligence model predicts and calculates the production volume of food expected to be produced in a specific period, taking into account the production volume of food by period, weather conditions in the region where food is produced, weather forecast conditions in a specific period, etc. You can.

Specifically, the first artificial intelligence model compares the production of the first food by period with the weather conditions of the first region by period, and analyzes how much the production of the first food is affected by the weather conditions of the first region, Based on the analysis results, the production volume of the first food expected to be produced in the first period can be predicted and calculated according to the weather forecast state in the first period.

For example, the first AI model predicts that the first food will be produced in January 2023, considering the January 2022 production volume of the first food, the January 2022 weather conditions in the first region, and the weather forecast conditions in January 2023. It can be calculated by predicting the expected production volume of the first food.

In step S207, the device 200 may set the production volume of the first food expected to be produced in the first period as the first production volume, based on the output of the first artificial intelligence model.

According to one embodiment, the first artificial intelligence model is the production volume of food expected to be produced in a specific period through a matching result of matching the production volume of a specific food by period, the weather condition by period in a specific region, and the weather forecast state of a specific period. It can be learned to analyze how much this is. Through this, the first artificial intelligence model analyzes how much food production is expected to be produced in a specific period, considering the production volume of food by period, weather conditions in the area where food is produced by period, and weather forecast conditions in a specific period. You can print it out. To this end, the first artificial intelligence model may be pre-trained to analyze the production amount of food expected to be produced in a specific period.

The learning device in which learning of the first artificial intelligence model is performed may be the same device as the device 200 for predicting the production amount of food expected to be produced in a specific period using the learned first artificial intelligence model, or may be a separate device. It may be. Below, the process by which the first artificial intelligence model is learned is explained.

First, the learning device can generate input based on matching results that match the production volume of a specific food by period, weather conditions by period in a specific region, and weather forecast conditions of a specific period.

Specifically, the learning device may perform a preprocessing process on matching results that match the production volume of a specific food by period, weather conditions by period in a specific region, and weather forecast conditions of a specific period. The pre-processed matching result can be used as an input to the first artificial intelligence model, or the input can be generated through normal processing to remove unnecessary information.

Next, the learning device can apply input to the first artificial intelligence model. The first artificial intelligence model may be an artificial neural network learned according to reinforcement learning. The first artificial intelligence model may be a Q-Network, DQN (Depp Q-Network), or relational network (RL) structure suitable for outputting abstract inference through reinforcement learning.

The first artificial intelligence model learned according to reinforcement learning can be updated and optimized by reflecting the evaluation of various rewards.

For example, the first compensation compares the production of the first food by period with the weather condition of the first region by period, and if it is analyzed that the production of the first food increased when the weather condition of the first region was in the first state, If it is analyzed that the production of the first food has increased as the weather condition in the first period in the region is predicted to have a higher probability of being the first condition, the compensation value can be higher, and the second compensation can be calculated based on the period-specific production of the first food and the first food. If it is analyzed that the production of the first food decreased when the weather conditions in the first region were in the second state by comparing the weather conditions by period in the region, there is a high probability that the weather conditions in the first period in the first region were in the second state. If the analysis predicts that the production of the first food decreases, the compensation value may increase. Here, the first state and the second state can be set through meteorological conditions such as weather, precipitation, wind speed, temperature, and humidity.

Next, the learning device may obtain an output from the first artificial intelligence model. The output of the first artificial intelligence model may be information about the production volume of food expected to be produced in a specific period. At this time, the first artificial intelligence model analyzes the production volume of food expected to be produced in a specific period through matching results that match the production volume of specific food by period, weather conditions by period in a specific region, and weather forecast conditions in a specific period, You can output information about the production volume of food expected to be produced in a specific period.

Next, the learning device may evaluate the output of the first artificial intelligence model and pay a reward. At this time, the evaluation of the output can be divided into first compensation, second compensation, etc.

For example, the learning device compares the periodical production of the first food with the periodical weather condition of the first region, and if it is analyzed that the production of the first food increased when the weather condition of the first region was in the first state, the first region If it is analyzed that the higher the probability that the weather condition in the first period in the region is the first condition, the production of the first food increases, more first compensation is awarded, and the production of the first food by period and the weather condition by period in the first region are analyzed as In comparison, if it is analyzed that the production of the first food decreases when the weather condition in the first region is in the second state, the higher the probability that the weather condition in the first period in the first region is the second state, the higher the production of the first food. If we analyze this decrease, we can award more secondary rewards.

Next, the learning device may update the first artificial intelligence model based on the evaluation.

Specifically, the learning device specifies the first artificial intelligence model to maximize the expected value of the sum of rewards in an environment that analyzes the amount of food expected to be produced in a specific period. The first artificial intelligence model can be updated through the process of optimizing the policy that determines the actions to be taken in the states.

For example, if there is no problem with the result of analyzing the production volume of the first food expected to be produced in the first period as the first production volume, the learning device provides information indicating that there is no problem with the analysis of the first production volume. Generating first learning data comprising, and applying the first learning data to the first artificial intelligence model, to produce first food expected to be produced in another period having a weather prediction state similar to that of the first period. When analyzing production volume, the first artificial intelligence model can be updated through the process of training the first artificial intelligence model to have a value similar to the first production volume.

Meanwhile, the process of optimizing the policy can be accomplished through estimating the maximum expected value of the sum of rewards or the maximum value of the Q-function, or estimating the minimum value of the loss function of the Q-function. Estimation of the minimum value of the loss function can be done through stochastic gradient descent (SGD), etc. The process of optimizing the policy is not limited to this, and various optimization algorithms used in reinforcement learning can be used.

The learning device can gradually update the first artificial intelligence model by repeating the learning process of the first artificial intelligence model described above. Through this, the learning device is a first artificial device that outputs the production volume of food expected to be produced in a specific period through matching results that match the production volume of a specific food by period, weather conditions by period in a specific region, and weather forecast conditions in a specific period. Intelligence models can be trained.

In other words, when the learning device analyzes the production volume of food expected to be produced in a specific period through the matching result of matching the production volume of a specific food by period, the weather condition by period in a specific region, and the weather forecast state of a specific period, the first The first artificial intelligence model can be learned by adjusting the analysis standard by reflecting reinforcement learning through compensation or second compensation.

In step S208, the device 200 may generate a second matching result by matching the sales volume of the first food by period, the weather condition by period of the first region, and the weather forecast state of the first period.

In step S209, the device 200 may apply the second matching result to the second artificial intelligence model learned in advance. Here, the second artificial intelligence model predicts the sales volume of food expected to be sold in a specific period after receiving the matching result of matching the sales volume of a specific food by period, the weather condition by period in a specific region, and the weather forecast state of a specific period. It may be an algorithm that outputs.

In other words, the second artificial intelligence model predicts and calculates the sales volume of food expected to be sold in a specific period, taking into account the sales volume of food by period, weather conditions in the area where food is sold, weather forecast conditions in a specific period, etc. You can.

Specifically, the second artificial intelligence model compares the sales volume of the first food by period with the weather conditions of the first region by period, and analyzes how much the sales volume of the first food is affected by the weather conditions of the first region, Based on the analysis results, the sales volume of the first food expected to be sold in the first period can be predicted and calculated according to the weather forecast state in the first period.

For example, the second AI model predicts that the first food will be sold in January 2023, considering the January 2022 sales volume of the first food, the January 2022 weather conditions in the first region, and the weather forecast status in January 2023. It can be calculated by predicting the expected sales volume of the first food.

In step S210, the device 200 may set the sales volume of the first food expected to be sold in the first period as the first sales volume, based on the output of the second artificial intelligence model.

According to one embodiment, the second artificial intelligence model is the sales volume of food expected to be sold in a specific period through a matching result of matching the sales volume of a specific food by period, the weather condition by period of a specific region, and the weather forecast state of a specific period. It can be learned to analyze how much this is. Through this, the second artificial intelligence model analyzes how much food is expected to be sold in a specific period, considering the sales volume of food by period, the weather conditions of the area where food is sold by period, and the weather forecast status of a specific period. You can print it out. To this end, the second artificial intelligence model may be pre-trained to analyze the sales volume of food expected to be sold in a specific period.

The learning device in which learning of the second artificial intelligence model is performed may be the same device as the device 200 for predicting the sales volume of food expected to be sold in a specific period using the learned second artificial intelligence model, or may be a separate device. It may be. Below, the process by which the second artificial intelligence model is learned is explained.

First, the learning device can generate input based on matching results that match the sales volume of a specific food by period, weather conditions by period in a specific region, and weather forecast conditions of a specific period.

Specifically, the learning device may perform a preprocessing process on matching results that match the sales volume of a specific food by period, weather conditions by period in a specific region, and weather forecast conditions of a specific period. The pre-processed matching result can be used as an input to the second artificial intelligence model, or the input can be generated through normal processing to remove unnecessary information.

Next, the learning device can apply input to the second artificial intelligence model. The second artificial intelligence model may be an artificial neural network learned according to reinforcement learning. The second artificial intelligence model may be a Q-Network, DQN (Depp Q-Network), or relational network (RL) structure suitable for outputting abstract inference through reinforcement learning.

The second artificial intelligence model learned according to reinforcement learning can be updated and optimized by reflecting the evaluation of various rewards.

For example, the third compensation compares the sales volume of the first food by period with the weather condition of the first region by period, and if it is analyzed that the sales volume of the first food increased when the weather condition of the first region was in the third state, The higher the probability that the weather condition in the first period in region 1 is predicted to be the third condition, the higher the compensation value can be if it is analyzed that the sales volume of the first food has increased, and the fourth compensation can be calculated by dividing the sales volume of the first food by period and the 1st food by period. By comparing the weather conditions for each period in the region, if it is analyzed that the sales volume of the first food decreased when the weather condition in the first region was in the fourth state, there is a high probability that the weather condition in the first period in the first region was in the fourth state. The more it is predicted that the sales volume of the first food decreases, the higher the compensation value can be. Here, the third state and fourth state can be set through meteorological conditions such as weather, precipitation, wind speed, temperature, and humidity.

Next, the learning device can obtain an output from the second artificial intelligence model. The output of the second artificial intelligence model may be information about the sales volume of food expected to be sold in a specific period. At this time, the second artificial intelligence model analyzes the sales volume of food expected to be sold in a specific period through matching results that match the sales volume of a specific food by period, weather conditions by period in a specific region, and weather forecast conditions in a specific period, You can output information about the sales volume of food expected to be sold in a specific period.

Next, the learning device can evaluate the output of the second artificial intelligence model and pay a reward. At this time, the evaluation of the output can be divided into third compensation, fourth compensation, etc.

For example, the learning device compares the sales volume of the first food by period with the weather condition of the first region by period, and if it is analyzed that the sales volume of the first food increased when the weather state of the first region is in the third state, the first food If it is analyzed that the higher the probability that the weather condition in the first period is the third condition in the region, the sales volume of the first food increases, more third compensation is awarded, and the sales volume of the first food by period and the weather condition by period in the first region are analyzed. In comparison, if it is analyzed that the sales volume of the first food decreases when the weather condition in the first region is the fourth state, the higher the probability that the weather condition in the first period in the first region is the fourth state, the higher the sales volume of the first food. If we analyze this decrease, we can award more fourth rewards.

Next, the learning device may update the second artificial intelligence model based on the evaluation.

Specifically, the learning device specifies the second artificial intelligence model to maximize the expected value of the sum of rewards in an environment that analyzes the sales volume of food expected to be sold in a specific period. The second artificial intelligence model can be updated through the process of optimizing the policy that determines the actions to be taken in the states.

For example, if there is no problem with the result of analyzing the sales volume of the first food expected to be sold in the first period as the first sales volume, the learning device provides information indicating that there is no problem with the analysis of the first sales volume. Generate first learning data including, and apply the first learning data to the second artificial intelligence model to produce first food expected to be sold in another period having a weather forecast state similar to the weather forecast state of the first period. When analyzing sales volume, the second artificial intelligence model can be updated through the process of training the second artificial intelligence model to have a value similar to the first sales volume.

Meanwhile, the process of optimizing the policy can be accomplished through estimating the maximum expected value of the sum of rewards or the maximum value of the Q-function, or estimating the minimum value of the loss function of the Q-function. Estimation of the minimum value of the loss function can be done through stochastic gradient descent (SGD), etc. The process of optimizing the policy is not limited to this, and various optimization algorithms used in reinforcement learning can be used.

The learning device can gradually update the second artificial intelligence model by repeating the learning process of the second artificial intelligence model described above. Through this, the learning device is a second artificial device that outputs the sales volume of food expected to be sold in a specific period through matching results that match the sales volume of a specific food by period, weather conditions by period in a specific region, and weather forecast conditions of a specific period. Intelligence models can be trained.

In other words, when the learning device analyzes the sales volume of food expected to be sold in a specific period through the matching result of matching the sales volume of a specific food by period, weather conditions by period in a specific region, and weather forecast status of a specific period, the third A second artificial intelligence model can be learned by adjusting the analysis standard by reflecting reinforcement learning through compensation or fourth compensation.

In step S211, the device 200 may calculate the spare inventory amount by subtracting the first sales volume from the first production volume.

Figure 3 is a flow chart to explain the process of predicting price volatility of food according to one embodiment.

According to one embodiment, each step shown in FIG. 3 may be performed after step S211.

Referring to FIG. 3, first, in step S301, the device 200 can confirm that the reference price of the first food is set to the first price. At this time, the device 200 may confirm that the standard price of the first food is set to the first price based on the food information of the first food. Here, the food price of the first food may be set at the request of the manager, or may be set as the average sales price of the first food during a predetermined period.

In step S302, the device 200 may check whether the spare inventory amount is within the standard inventory range. Here, the standard inventory range may be set differently depending on the embodiment.

If it is confirmed in step S302 that the spare stock amount is included within the standard inventory range, in step S303, the device 200 determines that the price of the first food will be maintained at the first price in the first period, and the price volatility of the first food can be predicted.

For example, when the standard inventory range is set from 100 to 200, the device 200 determines that if the spare inventory is confirmed to be 150, the price of the first food will be maintained at the first price in the first period, The price volatility of the first food product can be predicted.

If it is confirmed in step S302 that the free inventory amount is outside the standard inventory range, in step S304, the device 200 may check whether the free inventory amount is less than the minimum value of the standard inventory range.

If it is confirmed in step S304 that the amount of free inventory is less than the minimum value of the standard inventory range, in step S305, the device 200 may set the first weight to a higher value as the amount of free stock decreases. At this time, the first weight can be set within a range from 100% to 150%.

For example, if the standard inventory range is set from 100 to 200, the device 200 can set the first weight to 110% when the free stock amount is confirmed to be 90, and when the free stock amount is confirmed to be 80. , the first weight can be set to 120%.

In step S306, the device 200 may calculate the second price as the product of the first price and the first weight.

In step S307, the device 200 may predict the price volatility of the first food, such that the price of the first food will change from the first price to the second price in the first period.

That is, if the device 200 determines that the free stock amount is outside the standard stock amount range and is less than the minimum value of the standard stock amount range, the device 200 sets the first weight to a higher value as the free stock amount is smaller within the range from 100% to 150%. , calculating the second price as the product of the first price and the first weight, and predicting the price volatility of the first food such that the price of the first food will change from the first price to the second price in the first period. , if the amount of spare inventory is below a certain level, the price of the first food will fluctuate to a price higher than the reference price in the first period, and the price volatility of the first food can be predicted.

On the other hand, if it is confirmed in step S304 that the free stock amount is more than the minimum value of the standard stock amount range, the free stock amount is outside the standard stock amount range, so it can be confirmed that the free stock amount is more than the maximum value of the standard stock amount range. If it is confirmed that this standard inventory amount is greater than the maximum value of the range, in step S308, the device 200 may set the second weight to a lower value as the free inventory amount increases. At this time, the second weight can be set within a range from 50% to 100%.

For example, if the standard inventory range is set from 100 to 200, the device 200 can set the second weight to 90% when the free stock amount is confirmed to be 210, and when the free stock amount is confirmed to be 220. , the second weight can be set to 80%.

In step S309, the device 200 may calculate the third price as the product of the first price and the second weight.

In step S310, the device 200 may predict the price volatility of the first food, such that the price of the first food will change from the first price to the third price in the first period.

That is, if the device 200 determines that the free stock amount is outside the standard stock amount range and is greater than the maximum value of the standard stock amount range, the device 200 sets the second weight to a lower value as the free stock amount increases within the range from 50% to 100%. , calculating the third price as the product of the first price and the second weight, and predicting the price volatility of the first food such that the price of the first food will change from the first price to the third price in the first period. , if the amount of spare inventory is greater than a certain level, the price of the first food will fluctuate to a price lower than the reference price in the first period, and the price volatility of the first food can be predicted.

If the price volatility of the first food is predicted through any one of steps S303, S307, and S310, in step S311, the device 200 reports the result of predicting the price volatility of the first food to the manager terminal 100. It can be sent to .

When the first period begins, the device 200 may automatically set the sales price of the first food based on a result of predicting the price volatility of the first food.

Figure 4 is a flowchart for explaining the process of setting a price adjustment ratio in consideration of weather and items according to an embodiment.

According to one embodiment, each step shown in FIG. 4 may be performed after step S211.

Referring to FIG. 4, first, in step S401, the device 200 analyzes whether a period of bad weather adversely affecting the production of the first food is included during the first period, based on weather information of the first region. You can. Here, the bad weather period may refer to a period in which weather that has a negative impact on food production activities, such as heavy rain, storms, typhoons, hail, heavy snow, and showers, is predicted.

For example, when heavy rain has a negative effect on the production of the first food, the device 200 may analyze whether days on which the weather is predicted to be heavy rain are included in the first period.

In step S402, the device 200 may check whether the bad weather period that adversely affects the production of the first food is included in the first period as a result of analyzing whether the bad weather period that adversely affects the production of the first food is included.

If it is confirmed in step S402 that the inclement weather period is not included in the first period, in step S407, the device 200 may set the first ratio to 100%.

If it is confirmed in step S402 that the bad weather period is included in the first period, in step S403, the device 200 may set the bad weather period within the first period as the 1-1 period.

In step S404, the device 200 may set the number of days in the first period as a first value and the number of days in the 1-1 period as a second value.

In step S405, the device 200 may calculate the second ratio by dividing the second value by the first value.

In step S406, the device 200 may set the first ratio to a value obtained by adding 100% and the second ratio.

For example, if the first period is set from June 1 to June 30, the device 200 predicts from June 1 to June 30 based on weather information in the first region. As a result of checking the weather, if it is confirmed that the weather in Region 1 is bad from June 1st to June 3rd, it can be set as Period 1-1 from June 1st to June 3rd. The number of days in the period is confirmed to be 30 days, so the first number can be set to 30, and the number of days in the 1-1 period is confirmed to be 3 days, so the second number can be set to 3, and 10% calculated through “3 / 30” can be calculated as the second ratio, and 110% calculated through “100% + 10%” can be calculated as the first ratio.

That is, the device 200 may set the first ratio to a higher value as the bad weather period is longer, in order to adjust the price of food to a higher price in consideration of the reduced production, because the production of food decreases during the bad weather period. there is.

Meanwhile, in step S408, the device 200 may analyze whether a period that has a positive impact on sales of the first food is included in the first period based on schedule information of the first period. Here, the main period may refer to a period that includes schedules that have a positive impact on food sales activities, such as public holidays, holidays, vacations, and vacation seasons.

For example, if a public holiday has a positive effect on sales of the first food, the device 200 may analyze whether a day set as a public holiday is included in the first period.

According to one embodiment, schedule information for the first period may be obtained from the database of the device 200 and may include information related to schedules set for each date.

That is, the device 200 searches the information stored in the database to obtain schedule information for the first period, and based on the obtained schedule information for the first period, provides information that positively affects sales of the first food during the first period. It is possible to analyze whether or not a period of time is included.

In step S409, the device 200 analyzes whether a period that has a positive effect on sales of the first food is included in the first period, and as a result, it can be confirmed whether the period is included in the first period. .

If it is confirmed in step S409 that the main period is not included in the first period, the device 200 may set the third ratio to 100% in step S414.

If it is confirmed in step S409 that the main period is included in the first period, in step S410, the device 200 may set the main period as the 1-2 period within the first period.

In step S411, the device 200 may set the number of days in the first period as a first value and the number of days in the 1-2 period as a third value.

In step S412, the device 200 may calculate the fourth ratio by dividing the third value by the first value.

In step S413, the device 200 may set the third ratio to the value obtained by adding 100% and the fourth ratio.

For example, if the first period is set from June 1 to June 30, the device 200 selects the dates from June 1 to June 30 based on the schedule information of the first period. As a result of checking the schedule set for each period, if it is confirmed that the schedule is from June 1 to June 6, the period from June 1 to June 6 can be set as the 1st and 2nd period, and the 1st period is The number of days in period 1-2 is confirmed to be 30 days, so the first number can be set to 30. The number of days in period 1-2 is confirmed to be 6 days, so the third number can be set to 6, and the 20% calculated through “6 / 30” is set to 30. It can be calculated as the fourth ratio, and 120% calculated through “100% + 20%” can be calculated as the third ratio.

That is, the device 200 may set the third ratio to a higher value as the selling period is longer, in order to adjust the price of food to a higher price in consideration of the increased sales volume, since the sales volume of food increases during the selling period. there is.

In step S415, when the first ratio and the third ratio are respectively set, the device 200 may calculate the fifth ratio as a value obtained by multiplying the first ratio and the third ratio. At this time, the first ratio may be set through step S406 or S407, and the third ratio may be set through step S413 or S414.

In step S416, the device 200 may set the fifth ratio as a price adjustment ratio for adjusting the price volatility of the first food in the first period.

According to one embodiment, through step S303, when the price of the first food is predicted to be maintained at the first price in the first period and the price volatility of the first food is predicted, the fifth ratio is applied to determine the price of the first food. Price volatility can be adjusted. A detailed description regarding this will be provided later with reference to FIG. 5 .

According to one embodiment, in step S307, when the price volatility of the first food is predicted to change from the first price to the second price in the first period, the fifth ratio is applied The price volatility of the first food can be adjusted. A detailed description regarding this will be provided later with reference to FIG. 6 .

According to one embodiment, through step S310, when the price volatility of the first food is predicted to change from the first price to the third price in the first period, the fifth ratio is applied The price volatility of the first food can be adjusted. A detailed description regarding this will be provided later with reference to FIG. 7 .

5 shows that the price of the first food will be maintained at the first price in the first period according to an embodiment, and when the price volatility of the first food is predicted, the price volatility of the first food is adjusted according to the price adjustment ratio. This is a flowchart to explain the process.

Referring to FIG. 5, first, in step S501, the device 200 may calculate the fourth price as the product of the first price and the fifth ratio.

In step S502, the device 200 may calculate the difference between the first price and the fourth price as the first difference price.

For example, if the first price is 100 won and the fifth ratio is 110%, the device 200 calculates 110 won calculated through “100 The calculated 10 won can be calculated as the first difference price.

In step S503, the device 200 may check whether the first difference price is lower than the first reference price. Here, the first reference price may be set differently depending on the embodiment.

If the first difference price is confirmed to be lower than the first reference price in step S503, in step S504, the device 200 determines that the price of the first food will be maintained at the first price in the first period, and that the price of the first food will be maintained at the first price. Volatility can be predicted.

If it is confirmed in step S503 that the first difference price is higher than the first reference price, in step S505, the device 200 determines that the price of the first food will change from the first price to the fourth price in the first period. , the price volatility of the first food can be predicted.

Figure 6 shows that the price of the first food will change from the first price to the second price in a first period according to an embodiment, and when the price volatility of the first food is predicted, the price of the first food is changed according to the price adjustment ratio. This is a flow chart to explain the process of adjusting price volatility.

Referring to FIG. 6, first, in step S601, the device 200 may calculate the fifth price as the product of the second price and the fifth ratio.

In step S602, the device 200 may calculate the difference between the second price and the fifth price as the second difference price.

For example, if the first price is 100 won, the second price is 110 won, and the fifth ratio is 110%, the device 200 calculates 121 won calculated through “110 , 11 won calculated through “21 - 110” can be calculated as the second difference price.

In step S603, the device 200 may check whether the second difference price is lower than the second reference price. Here, the second reference price may be set differently depending on the embodiment.

If the second difference price is confirmed to be lower than the second reference price in step S603, in step S604, the device 200 determines that the price of the first food will change from the first price to the second price in the first period, 1 Food price volatility can be predicted.

If it is confirmed in step S603 that the second difference price is higher than the second reference price, in step S605, the device 200 determines that the price of the first food will change from the first price to the fifth price in the first period. , the price volatility of the first food can be predicted.

Figure 7 shows that the price of the first food will change from the first price to the third price in the first period according to an embodiment, and when the price volatility of the first food is predicted, the price of the first food is changed according to the price adjustment ratio. This is a flow chart to explain the process of adjusting price volatility.

Referring to FIG. 7, first, in step S701, the device 200 may calculate the sixth price as the product of the third price and the fifth ratio.

In step S702, the device 200 may calculate the difference between the third price and the sixth price as the third difference price.

For example, if the first price is 100 won, the third price is 90 won, and the fifth ratio is 110%, the device 200 calculates 99 won calculated through “90 , 9 won calculated through “-90” can be calculated as the third difference price.

In step S703, the device 200 may check whether the third difference price is lower than the third reference price. Here, the third reference price may be set differently depending on the embodiment.

If the third difference price is confirmed to be lower than the third reference price in step S703, in step S704, the device 200 determines that the price of the first food will change from the first price to the third price in the first period, 1 Food price volatility can be predicted.

If it is confirmed in step S703 that the third difference price is higher rather than lower than the third reference price, in step S705, the device 200 may calculate the difference between the first price and the sixth price as the fourth difference price.

For example, if the first price is 100 won, the third price is 90 won, and the fifth ratio is 110%, the device 200 calculates 99 won calculated through “90 , 9 won calculated through “-90” can be calculated as the third difference price, and if the third standard price is set to 5 won, the third difference price is confirmed to be higher than the third standard price, 1 won calculated through “-99” can be calculated as the fourth difference price.

In step S706, the device 200 may check whether the fourth difference price is lower than the third reference price.

If the fourth difference price is confirmed to be lower than the third reference price in step S706, in step S707, the device 200 determines that the price of the first food will be maintained at the first price in the first period, and that the price of the first food will be maintained at the first price. Volatility can be predicted.

If it is confirmed in step S706 that the fourth difference price is higher than the third reference price, in step S708, the device 200 determines that the price of the first food will change from the first price to the sixth price in the first period. , the price volatility of the first food can be predicted.

Figure 8 is a flow chart to explain the process of providing a notification service for securing additional food according to an embodiment.

According to one embodiment, each step shown in FIG. 8 may be performed after step S311.

Referring to FIG. 8, first, in step S801, the device 200 may check whether the first production volume is less than the first sales volume.

If it is determined in step S801 that the first production volume is less than the first sales volume, in step S802, the device 200 secures sufficient inventory with the first food produced in the first region when selling the first food during the first period. It can be judged that it was not done.

In step S803, the device 200 may calculate a first difference amount, which is the difference between the first production volume and the first sales volume.

In step S804, the device 200 may transmit a notification message to the manager terminal 100 indicating that additional securing of the first food in the first difference amount is required in a region other than the first region.

Meanwhile, if it is confirmed in step S801 that the first production volume is not less but more than the first sales volume, in step S805, the device 200 selects the first food produced in the first region when selling the first food during the first period. It can be judged that there is sufficient inventory.

In step S806, the device 200 may transmit a notification message to the manager terminal 100 indicating that additional securing of the first food is not necessary.

When the device 200 transmits a notification message indicating that additional securing of the first food is not necessary to the manager terminal 100, based on the result of predicting the price volatility of the first food, within the first production volume A notification message informing the user how much stock of the first food should be secured by day can be further sent. A detailed description regarding this will be provided later with reference to FIG. 9 .

Figure 9 is a flowchart for explaining a process for providing a notification service about the amount of food stocked by day according to an embodiment.

Referring to FIG. 9 , first, in step S901, the device 200 may calculate the first quantity, which is the average daily sales quantity of the first food, as the value obtained by dividing the first sales quantity by the first numerical value.

In step S902, the device 200 may confirm that, as a result of predicting the price volatility of the first food, the price of the first food is predicted to be maintained in the first period.

That is, if the price volatility of the first food is predicted to be maintained at the first price in the first period through step S303, the device 200 determines that the price of the first food in the first period will be maintained at the first price. It can be confirmed that it is predicted to be maintained.

In step S903, if the price of the first food is predicted to be maintained in the first period as a result of predicting the price volatility of the first food, the device 200 increases the inventory amount of the first food on the first date to the first You can set it as the quantity, and set the stock quantity of the first food on the second date as the first quantity. Here, the first date is the start date of the first period and the second date is a date after the first date within the first period.

That is, when the price of the first food is predicted to be maintained in the first period as a result of predicting the price volatility of the first food, the device 200 secures the stock of the first food in a constant quantity for each day. You can set the inventory amount of the first food.

Meanwhile, in step S904, the device 200 may confirm that, as a result of predicting the price volatility of the first food, the price of the first food is predicted to increase by a sixth rate in the first period. That is, if the price volatility of the first food is predicted to change from the first price to the second price in the first period through step S307, the device 200 determines the first price and the second price. By comparing the prices, the sixth ratio is calculated, and it can be confirmed that the price of the first food is predicted to increase by the sixth ratio in the first period. At this time, the sixth ratio can be calculated through the formula “(second price - first price) / (first price)”. For example, if the first price is 100 won and the second price is 110 won, the device 200 may calculate 10% calculated through “(110 - 100) / 100)” as the sixth ratio.

In step S905, when the device 200 predicts the price volatility of the first food and predicts that the price of the first food will increase by the sixth ratio in the first period, the value obtained by multiplying the first quantity and the sixth ratio The second quantity can be calculated.

In step S906, the device 200 may calculate the third quantity by adding the first quantity and the second quantity, and calculate the fourth quantity by subtracting the second quantity from the first quantity.

In step S907, the device 200 may set the secured stock quantity of the first food on the first date as the third quantity, and set the secured stock quantity of the first food on the second date as the fourth quantity.

For example, if the first quantity is 100 and the price of the first food is predicted to rise by 10% in the first period, the device 200 uses 10 calculated through “100 , calculate 110 items calculated through “+ 10” as the third quantity, calculate 90 items calculated through “- 10” as the fourth quantity, and then stock the first food on the first date. The secured quantity can be set to 110, and the stock secured quantity of the first food on the second date can be set to 90.

That is, if the device 200 predicts the price volatility of the first food and predicts that the price of the first food will rise in the first period, the device 200 secures a larger quantity of inventory at an early date and gradually reduces the stock. In order to secure the quantity in stock, the stock quantity of the first food by date can be set.

Meanwhile, in step S908, the device 200 may confirm that, as a result of predicting the price volatility of the first food, the price of the first food is predicted to decrease by the seventh percentage in the first period. That is, if the price volatility of the first food is predicted to change from the first price to the third price in the first period through step S310, the device 200 changes the first price and the third price. By comparing the prices, the seventh ratio is calculated, and it can be confirmed that the price of the first food is predicted to fall by the seventh ratio in the first period. At this time, the 7th ratio can be calculated through the formula “(1st price - 3rd price) / (1st price)”. For example, if the first price is 100 won and the third price is 90 won, the device 200 can calculate 10% calculated through “(100 - 90) / 100)” as the seventh ratio.

In step S909, when the device 200 predicts the price volatility of the first food and predicts that the price of the first food will fall by the seventh ratio in the first period, the value obtained by multiplying the first quantity and the seventh ratio The fifth quantity can be calculated.

In step S910, the device 200 may calculate the sixth quantity by subtracting the fifth quantity from the first quantity, and calculate the seventh quantity by adding the first quantity and the fifth quantity.

In step S911, the device 200 may set the secured inventory quantity of the first food on the first date to the sixth quantity, and set the secured inventory quantity of the first food to the seventh quantity on the second date.

For example, if the first quantity is 100 and the price of the first food is predicted to drop by 10% in the first period, the device 200 uses 10 calculated through “100 , 90 items calculated through “100 - 10” are calculated as the 6th quantity, and 110 items calculated through “100 + 10” are calculated as the 7th quantity, and then the 1st food on the 1st date. The stock quantity of can be set to 90, and the stock quantity of the first food can be set to 110 on the second date.

That is, when the device 200 predicts the price volatility of the first food and predicts that the price of the first food will fall in the first period, the device 200 secures a smaller quantity of inventory at an early date and gradually increases the price of the first food. In order to secure the quantity in stock, the stock quantity of the first food by date can be set.

If the stock amount of the first food by date is set through any one of steps S903, S907, and S911, in step S912, the device 200 sends a notification message about the stock amount of the first food by date to the manager terminal ( 100).

Figure 10 is a flowchart for explaining the process of inspecting a box packaging food according to one embodiment.

Referring to FIG. 10 , first, in step S1001, the device 200 may confirm the first number of packaging units of the first food based on the food information of the first food. At this time, the packaging unit is a unit for packaging food into one box, and may refer to the number set for bundle sale.

In step S1002, the device 200 may receive information about the weight of the first box from the weight meter. At this time, the first box is one of the boxes in which the first food is packaged according to the packaging unit of the first food. For example, when the packaging unit of the first food is 5, the first box is a box containing and packaging the 5 first foods.

Specifically, the weight meter may measure the weight of the first box to generate information about the weight of the first box, and when the weight of the first box is measured by the weight meter, the device 200 receives the weight of the first box from the weight meter. Information about the weight of the first box may be received. To this end, the device 200 may be configured to communicate wired or wirelessly with a weight measuring device.

In step S1003, the device 200 may confirm the weight of the first box as the first weight based on information about the weight of the first box.

Meanwhile, in step S1004, the device 200 may confirm that the reference weight of one first food item is the first weight. At this time, the device 200 may confirm that the reference weight of the first food is set to the first weight based on the food information of the first food.

In step S1005, the device 200 may calculate the second weight as a value obtained by multiplying the first weight and the first number.

For example, if the first weight is 10g and the first number is 5, the device 200 may calculate 50g calculated through “10

In step S1106, the device 200 may check whether the first weight is heavier than the second weight.

If the first weight is confirmed to be heavier than the second weight in step S1106, the device 200 may classify the first box as a normal box in step S1007.

In step S1008, when the first box is classified as a normal box, the device 200 may transmit a notification message that the first box can be shipped to the manager terminal 100.

If it is confirmed in step S1006 that the first weight is lighter than the second weight, in step S1009, the device 200 may classify the first box as a defective box.

In step S1010, when the first box is classified as a defective box, the device 200 may transmit a notification message requiring repackaging of the first box to the manager terminal 100.

When transmitting a notification message that the first box needs to be repackaged to the manager terminal 100, the device 200 may further transmit a notification message indicating which process requires inspection. A detailed description regarding this will be provided later with reference to FIG. 11 .

FIG. 11 is a flowchart illustrating a process for providing a notification service regarding which process requires inspection when the first box is classified as a defective box according to an embodiment.

Referring to FIG. 11, first, in step S1101, the device 200 can check the weight of each first food item in the first box.

That is, before the first box is packaged, the weight of the first food may be individually measured by a weigher, and the device 200 may measure the weight of each of the first foods in the first box. You can check the weight of each first food item within.

Specifically, when the first food is individually located in the measurement section before the first box is packaged, the weight meter can measure the weight of each first food and generate information about the weight of each first food, When the weight of each of the first foods in the first box is measured by the weigher, the device 200 receives information about the weight of each first food from the weigher, and based on the received information, the first box You can check the weight of each first food item within.

In step S1102, when the weight of each of the first foods in the first box is confirmed, the device 200 determines the average weight of the first foods in the first box through the weight of each of the first foods in the first box. It can be calculated as the second weight.

In step S1103, the device 200 may check whether the first weight is heavier than the second weight.

If the first weight is confirmed to be heavier than the second weight in step S1103, the device 200 may determine that there is a problem with the first food in the first box in step S1104.

In step S1105, if it is determined that there is a problem with the first food in the first box, the device 200 may transmit a notification message requiring inspection of the selection process of the first food to the manager terminal 100.

If it is confirmed in step S1003 that the first weight is lighter and not heavier than the second weight, in step S1106, the device 200 may determine that there is no problem with the first food in the first box.

In step S1107, if it is determined that there is no problem with the first food in the first box, the device 200 may transmit a notification message requiring inspection of the packaging process of the first food to the manager terminal 100.

Figure 12 is an exemplary diagram of the configuration of a device according to an embodiment.

Device 200 according to one embodiment includes a processor 210 and memory 220. The processor 210 may include at least one device described above with reference to FIGS. 1 to 11 or may perform at least one method described above with reference to FIGS. 1 to 11 . A person or organization using the device 200 may provide services related to some or all of the methods described above with reference to FIGS. 1 to 11 .

The memory 220 may store information related to the methods described above or store a program in which methods described later are implemented. Memory 220 may be volatile memory or non-volatile memory.

The processor 210 can execute programs and control the device 200. The code of the program executed by the processor 210 may be stored in the memory 220. The device 200 is connected to an external device (eg, a personal computer or a network) through an input/output device (not shown) and can exchange data through wired or wireless communication.

The device 200 may be used to learn an artificial intelligence model or use a learned artificial intelligence model. Memory 220 may include a learning or learned artificial intelligence model. The processor 210 may learn or execute the algorithm of the artificial intelligence model stored in the memory 220. The learning device that trains the artificial intelligence model and the device 200 that uses the learned artificial intelligence model may be the same or may be separate.

The embodiments described above may be implemented with hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, and a field programmable gate (FPGA). It may be implemented using one or more general-purpose or special-purpose computers, such as an array, programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may execute an operating system (OS) and one or more software applications that run on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

Although the embodiments have been described with limited drawings as described above, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the following claims.

Claims (3)

In a method of providing an online sales platform service for agricultural and marine products based on price volatility prediction, performed by a device,
Receiving a request for prediction of price volatility of a first food in a first period from a manager terminal;
Confirming the production volume of the first food by period based on the production volume information of the first food, and confirming the sales volume of the first food by period based on the sales volume information of the first food;
When the production area of the first food is confirmed to be a first area, checking weather conditions for each period of the first area and weather forecast conditions for the first period based on weather information of the first area;
Generating a first matching result by matching the production volume of the first food for each period, weather conditions for each period in the first region, and weather forecast conditions for the first period;
Applying the first matching result to the first artificial intelligence model, based on the output of the first artificial intelligence model, setting the production volume of the first food expected to be produced in the first period as the first production volume step;
Generating a second matching result by matching sales volume of the first food by period, weather conditions of the first region by period, and weather forecast conditions of the first period;
Applying the second matching result to a second artificial intelligence model, based on the output of the second artificial intelligence model, setting the sales volume of the first food expected to be sold in the first period as the first sales volume. step;
calculating a surplus inventory amount by subtracting the first sales volume from the first production volume;
Confirming that the reference price of the first food is set to the first price;
predicting price volatility of the first food such that the price of the first food will be maintained at the first price in the first period when it is confirmed that the spare stock amount is within a preset reference stock amount range;
If it is confirmed that the free stock amount is outside the standard stock amount range and less than the minimum value of the standard stock amount range, the first weight is set to a higher value as the free stock amount is smaller within the range from 100% to 150%, and the first weight is set to a higher value. A second price is calculated as a value multiplied by 1 price and the first weight, and the price of the first food is expected to change from the first price to the second price in the first period, and the price of the first food is predicting volatility;
If it is confirmed that the free stock amount is outside the standard stock amount range and is greater than the maximum value of the standard stock amount range, the second weight is set to a lower value as the free stock amount is greater within the range from 50% to 100%, and the second weight is set to a lower value. A third price is calculated by multiplying the 1 price and the second weight, and the price of the first food is expected to change from the first price to the third price in the first period, and the price of the first food is predicting volatility; and
A step of transmitting the result of predicting the price volatility of the first food to the manager terminal,
Analyzing, based on weather information of the first region, whether a period of bad weather adversely affecting production of the first food is included during the first period;
If it is determined that the first period does not include a period of inclement weather, setting the first ratio to 100%;
If it is confirmed that a period of bad weather is included in the first period, the bad weather period within the first period is set as a 1-1 period, the number of days of the first period is set to a first number, and the number of days in the first period is set to a first number. -1 setting the number of days in the period to a second number;
calculating a second ratio as a value obtained by dividing the second numerical value by the first numerical value, and setting the first ratio as a value obtained by adding 100% and the second ratio;
Based on the schedule information of the first period, analyzing whether a period that has a positive effect on sales of the first food is included in the first period;
If it is confirmed that the stock period is not included in the first period, setting a third ratio to 100%;
If it is confirmed that the main period is included in the first period, the main period within the first period is set as the 1-2 period, the number of days of the first period is set to a first number, and the first period is set to a first number. -2 setting the number of days in the period to a third number;
calculating a fourth ratio as a value obtained by dividing the third value by the first value, and setting the third ratio as a value obtained by adding 100% and the fourth ratio; and
When the first ratio and the third ratio are respectively set, the fifth ratio is calculated by multiplying the first ratio and the third ratio, and the fifth ratio is calculated as the price of the first food in the first period. Further comprising setting a price adjustment rate to adjust volatility,
Method of providing online sales platform service for agricultural and marine products based on prediction of price volatility. delete According to paragraph 1,
The step of predicting the price volatility of the first food such that the price of the first food will be maintained at the first price in the first period includes,
calculating a fourth price by multiplying the first price and the fifth ratio;
calculating a difference between the first price and the fourth price as a first difference price;
If the first difference price is confirmed to be lower than a preset first reference price, predicting the price volatility of the first food such that the price of the first food will be maintained at the first price in the first period. ; and
If the first difference price is confirmed to be higher than the first reference price, the price of the first food product will change from the first price to the fourth price in the first period, such that the price volatility of the first food product Including the step of predicting,
The step of predicting the price volatility of the first food such that the price of the first food will change from the first price to the second price in the first period includes,
calculating a fifth price by multiplying the second price and the fifth ratio;
calculating a difference between the second price and the fifth price as a second difference price;
If the second difference price is confirmed to be lower than the preset second reference price, the price of the first food will change from the first price to the second price in the first period, and the price of the first food will change from the first price to the second price. predicting volatility; and
If the second difference price is confirmed to be higher than the second reference price, the price of the first food product will change from the first price to the fifth price in the first period, such that the price volatility of the first food product Including the step of predicting,
The step of predicting the price volatility of the first food such that the price of the first food will change from the first price to the third price in the first period includes,
calculating a sixth price by multiplying the third price and the fifth ratio;
calculating the difference between the third price and the sixth price as a third difference price;
If the third difference price is confirmed to be lower than the preset third reference price, the price of the first food will change from the first price to the third price in the first period, and the price of the first food will change from the first price to the third price. predicting volatility;
If the third difference price is confirmed to be higher than the third reference price, calculating the difference between the first price and the sixth price as a fourth difference price;
If the fourth difference price is confirmed to be lower than the third reference price, predicting price volatility of the first food such that the price of the first food will be maintained at the first price in the first period; and
If the fourth difference price is confirmed to be higher than the third reference price, the price of the first food product will change from the first price to the sixth price in the first period, such that the price volatility of the first food product Including the step of predicting,
Method of providing online sales platform service for agricultural and marine products based on prediction of price volatility.