KR102646888B1 - Electronic device predicting store profits using on deep learning-based prediction moedl and utilizing the predicted information and method thereof - Google Patents

Abstract

According to this embodiment, an electronic device that predicts profit for a store using a deep learning-based prediction model and utilizes the predicted information includes a communication interface and a processor, wherein the processor is configured to communicate through the communication interface. , first group data related to the income of the first store, second group data related to the expenditure of the first store, and third group data related to the location characteristics of the first store from the server that manages the first store. Obtaining and inputting the first group data, the second group data, and the third group data of the first store into a deep learning-based prediction model, the data obtained from the first store during a preset first period Predict first predicted revenue data, second predicted revenue data obtained from the first store during a preset second period, and third predicted revenue data obtained from the first store during a preset third period, and the dip The learning-based prediction model is based on the first group data, the second group data, and the third group data of the plurality of stores received from the server. It is learned based on first operating revenue data, second operating revenue data obtained from the plurality of stores during a preset second period, and third operating revenue data obtained from the plurality of stores during a preset third period.

Description

Electronic device and method for predicting store profits using a deep learning-based prediction model and utilizing the predicted information {ELECTRONIC DEVICE PREDICTING STORE PROFITS USING ON DEEP LEARNING-BASED PREDICTION MOEDL AND UTILIZING THE PREDICTED INFORMATION AND METHOD THEREOF}

Various embodiments of the present invention relate to an electronic device and method for predicting profits for a store using a deep learning-based prediction model and utilizing the predicted information.

Artificial intelligence (AI) refers to a technology that artificially implements some or all of human learning, reasoning, and perception abilities using computer programs. In relation to artificial intelligence (AI), machine learning refers to learning to optimize parameters with given data using a model composed of multiple parameters.

Meanwhile, Korea's civil law defines land and its fixtures as real estate among tangible objects, electricity, and other manageable natural forces. Such real estate includes apartments, officetels, land, etc., and is frequently traded in our daily lives and commercial transactions.

In addition, stores belonging to real estate are very expensive for ordinary investors to purchase, so many people had difficulty investing in stores.

Therefore, there is a need for a device for small investors in stores belonging to real estate, and research is being attempted to create a prediction model using artificial intelligence (AI) by using the relationship between various causes and prices on store profits. Although it is known, it has not yet developed to a reliable level.

U.S. Patent Publication No. 10984490 (2021.04.20.) Korean Patent Publication No. 10-2438644 (2022.08.26.)

Therefore, according to this embodiment, it is possible to provide an electronic device that predicts profits for a store using a deep learning-based prediction model and provides and manages information in real time to a plurality of operators and investors who utilize the predicted information. there is.

According to this embodiment, an electronic device that predicts profit for a store using a deep learning-based prediction model and utilizes the predicted information includes a communication interface and a processor, wherein the processor is configured to communicate through the communication interface. , first group data related to the income of the first store, second group data related to the expenditure of the first store, and third group data related to the location characteristics of the first store from the server that manages the first store. Obtaining and inputting the first group data, the second group data, and the third group data of the first store into a deep learning-based prediction model, the data obtained from the first store during a preset first period Predict first predicted revenue data, second predicted revenue data obtained from the first store during a preset second period, and third predicted revenue data obtained from the first store during a preset third period, and the dip The learning-based prediction model is based on the first group data, the second group data, and the third group data of the plurality of stores received from the server. It is learned based on first operating revenue data, second operating revenue data obtained from the plurality of stores during a preset second period, and third operating revenue data obtained from the plurality of stores during a preset third period.

The present invention predicts future sales for a specific store by analyzing a plurality of data about a specific store, and based on this, information is shared with the operator of the specific store and multiple investors, providing the effect of transparent investment.

1 shows a block diagram of an electronic device and a network according to various embodiments of the present invention.
Figure 2 is a flowchart illustrating a method of predicting profit for a store using a deep learning-based prediction model according to various embodiments.
3A to 3E are exemplary diagrams for selecting a plurality of stores for profit prediction according to various embodiments.
Figure 4 is an example diagram for selecting a plurality of times for profit prediction according to various embodiments.
Figure 5 is a flow chart for utilizing predicted store profits to an operator, according to various embodiments.
FIG. 6 is a detailed flowchart for data transmission in FIG. 5.
Figure 7 is a specific example diagram for selecting an investment style of investors according to various embodiments.
Figure 8 is a flow chart for utilizing predicted store profits to investors, according to various embodiments.
FIG. 9 is a specific flowchart for data transmission in FIG. 8.
Figure 10 is a detailed illustration of an investor's purchase or sale according to various embodiments.

Hereinafter, various embodiments of this document are described with reference to the attached drawings. The examples and terms used herein are not intended to limit the technology described in this document to specific embodiments, and should be understood to include various modifications, equivalents, and/or substitutes for the examples. In connection with the description of the drawings, similar reference numbers may be used for similar components. Singular expressions may include plural expressions, unless the context clearly indicates otherwise. In this document, expressions such as “A or B” or “at least one of A and/or B” may include all possible combinations of the items listed together. Expressions such as “first,” “second,” “first,” or “second,” can modify the corresponding components regardless of order or importance, and are used to distinguish one component from another. It is only used and does not limit the corresponding components. When a component (e.g., a first) component is said to be "connected (functionally or communicatively)" or "connected" to another (e.g., second) component, it means that the component is connected to the other component. It may be connected directly to a component or may be connected through another component (e.g., a third component).

In this document, “configured to” means “suitable for,” “having the ability to,” or “changed to,” depending on the situation, for example, in terms of hardware or software. ," can be used interchangeably with "made to," "capable of," or "designed to." In some contexts, the expression “a device configured to” may mean that the device is “capable of” working with other devices or components. For example, the phrase "processor configured (or set) to perform A, B, and C" refers to a processor dedicated to performing the operations (e.g., an embedded processor), or by executing one or more software programs stored on a memory device. , may refer to a general-purpose processor (e.g., CPU or application processor) capable of performing the corresponding operations.

Electronic devices according to various embodiments of this document may include, for example, at least one of a smartphone, tablet PC, desktop PC, laptop PC, netbook computer, workstation, and server.

1, an electronic device 101 within a network environment 100, in various embodiments, is described. The electronic device 101 may include a bus 110, a processor 120, a memory 130, an input/output interface 150, a display 160, and a communication interface 170. In some embodiments, the electronic device 101 may omit at least one of the components or may additionally include another component. The bus 110 connects the components 110 to 170 to each other and may include circuitry that transfers communication (eg, control messages or data) between the components. The processor 120 may include one or more of a central processing unit, an application processor, or a communication processor (CP). For example, the processor 120 may perform operations or data processing related to control and/or communication of at least one other component of the electronic device 101. Additionally, the processor 120 may be composed of at least one processor and may execute one or more instructions.

Memory 130 stores one or more instructions and may include volatile and/or non-volatile memory. For example, the memory 130 may store commands or data related to at least one other component of the electronic device 101. According to one embodiment, memory 130 may store software and/or program 140. Program 140 may include, for example, a kernel 141, middleware 143, an application programming interface (API) 145, and/or an application program (or “application”) 147, etc. . At least a portion of the kernel 141, middleware 143, or API 145 may be referred to as an operating system. Kernel 141 may, for example, provide system resources (e.g., middleware 143, API 145, or application program 147) used to execute operations or functions implemented in other programs (e.g., : Bus 110, processor 120, or memory 130, etc.) can be controlled or managed. In addition, the kernel 141 provides an interface for controlling or managing system resources by accessing individual components of the electronic device 101 in the middleware 143, API 145, or application program 147. You can.

The middleware 143 may, for example, perform an intermediary role so that the API 145 or the application program 147 can communicate with the kernel 141 to exchange data. Additionally, the middleware 143 may process one or more work requests received from the application program 147 according to priority. For example, the middleware 143 may use system resources (e.g., bus 110, processor 120, or memory 130, etc.) of the electronic device 101 for at least one of the application programs 147. Priority may be assigned and the one or more work requests may be processed. The API 145 is an interface for the application 147 to control functions provided by the kernel 141 or middleware 143, for example, at least for file control, window control, image processing, or character control. Can contain one interface or function (e.g. command). The input/output interface 150, for example, transmits commands or data input from a user or other external device to other component(s) of the electronic device 101, or to other component(s) of the electronic device 101 ( Commands or data received from (fields) can be output to the user or other external devices.

Display 160 may be, for example, a liquid crystal display (LCD), a light-emitting diode (LED) display, an organic light-emitting diode (OLED) display, a microelectromechanical system (MEMS) display, or an electronic paper display. It can be included. For example, the display 160 may display various contents (e.g., text, images, videos, icons, and/or symbols, etc.) to the user. The display 160 may include a touch screen and may receive, for example, a touch, gesture, proximity, or hovering input using an electronic pen or a part of the user's body. The communication interface 170, for example, establishes communication between the electronic device 101 and an external device (e.g., the first external electronic device 102, the second external electronic device 104, or the server 106). You can. For example, the communication interface 170 may be connected to the network 162 through wireless or wired communication and communicate with an external device (eg, the second external electronic device 104 or the server 106).

Wireless communications include, for example, LTE, LTE Advance (LTE-A), code division multiple access (CDMA), wideband CDMA (WCDMA), universal mobile telecommunications system (UMTS), Wireless Broadband (WiBro), or Global GSM (GSM). It may include cellular communication using at least one of the System for Mobile Communications). According to one embodiment, wireless communication includes, for example, wireless fidelity (WiFi), Bluetooth, Bluetooth Low Energy (BLE), Zigbee, near field communication (NFC), Magnetic Secure Transmission, and radio. It may include at least one of frequency (RF) or body area network (BAN). According to one embodiment, wireless communications may include GNSS. GNSS may be, for example, Global Positioning System (GPS), Global Navigation Satellite System (Glonass), Beidou Navigation Satellite System (hereinafter “Beidou”), or Galileo, the European global satellite-based navigation system. Hereinafter, in this document, “GPS” may be used interchangeably with “GNSS.” Wired communication may include, for example, at least one of universal serial bus (USB), high definition multimedia interface (HDMI), recommended standard 232 (RS-232), power line communication, or plain old telephone service (POTS). there is. Network 162 may include at least one of a telecommunications network, for example, a computer network (e.g., a LAN or WAN), the Internet, or a telephone network.

Each of the first and second external electronic devices 102 and 104 may be of the same or different type as the electronic device 101. According to various embodiments, all or part of the operations performed on the electronic device 101 may be executed on one or more electronic devices (e.g., the electronic devices 102 and 104, or the server 106). In one embodiment, According to this, when the electronic device 101 is to perform a certain function or service automatically or upon request, the electronic device 101 performs at least some functions associated therewith instead of or in addition to executing the function or service on its own. may be requested from another device (e.g., electronic device 102, 104, or server 106). The other electronic device (e.g., electronic device 102, 104, or server 106) may request the requested function or Additional functions may be executed and the results may be transmitted to the electronic device 101. The electronic device 101 may process the received results as is or additionally to provide the requested function or service. To this end, for example, For example, cloud computing, distributed computing, or client-server computing technologies may be used.

Figure 2 is a flowchart illustrating a method of predicting profit for a store using a deep learning-based prediction model according to various embodiments.

3A to 3E are exemplary diagrams for selecting a plurality of stores for profit prediction according to various embodiments.

Figure 4 is an example diagram for selecting a plurality of times for profit prediction according to various embodiments.

In operation 201, according to various embodiments, the electronic device 101 (e.g., the processor 120 of FIG. 1) manages the first store through a communication interface (e.g., the communication interface 170 of FIG. 1). First group data related to the income of the first store (e.g., FIGS. 3D and 3E), second group data related to the expenditures of the first store, and third group data related to the location characteristics of the first store from the server. It can be obtained.

As an example, the first group data consists of data including store sales, major customer age groups, floating population, and store operating hours.

More specifically, 'store sales' is related to all income generated in the store, and in the case of cafes and restaurants, it may include income such as daily total revenue and monthly total revenue.

In addition, the 'major customer age group' is output based on the preferences of each store. In the case of cafes that have become famous through media such as influencers and YouTubers, young people are the main customers, and in the case of cafes that have become famous through media such as influencers and YouTubers, the main customer base is the younger generation, and in the case of cafes that have become famous through media such as influencers and YouTubers, In the case of stores that are operated, people in their 50s to 80s are the main customers, and the examples may not be limited.

In addition, 'Floating Population' is used to determine whether a store is easily accessible, and refers to an area close to a subway station (e.g., 1 minute away from the subway, 5 minutes away from the subway) or an area with many buildings (e.g., around Gangnam Station, (around Samsung Station) may apply, and the content may be linked to a third group.

In addition, 'store operating hours' are the total operating hours of the store per day, which may vary depending on the uniqueness of the location. Specifically, depending on the area, there may be a lot of guests mainly in the morning and lunch, and mainly in the evening. There may be many, so they may be open depending on the time.

As an example, the second group data may be composed of data including the cost of products in the store, the number of people operating the store, the presence or absence of an unmanned robot, the number of kiosks, and the store's fixed expenses.

More specifically, the 'cost of products in a store' is the cost of products for sale in the store. In the case of a cafe, it may be raw materials for drinks such as coffee beans, milk, and fruit, and in the case of a restaurant, it may be raw materials for beverages such as coffee beans, milk, and fruits. , foodstuffs such as red pepper powder may be included. These are amounts that are absolutely necessary and must be incurred as expenses compared to sales.

Additionally, ‘store operating personnel’ are all employees working at the store. In the case of cafes, this may apply to baristas and part-time workers, and in the case of restaurants, it may apply to chefs and part-time workers. These are also amounts that are absolutely necessary and must be generated because they ensure smooth operation of sales.

In addition, 'presence or absence of unmanned robots' refers to all unmanned robots operating in the store. In the case of an unmanned robot, the initial cost is very high, but it has the advantage of smoothing in-store operations by replacing part-time workers, reducing necessary payments by not hiring part-time workers, and reducing human errors.

Additionally, the ‘number of kiosks’ refers to the calculator operated in the store. In the case of kiosks, the initial cost is high, but it has the advantage of facilitating in-store sales input by replacing part-time workers, reducing necessary payments by not hiring part-time workers, and reducing human errors.

In addition, 'store fixed expenses' are expenses that must be paid at the store, for example, monthly rent for the store (excluding those who own the store building), electricity bills used in the store, gas costs, and water bills. You can take it in.

As an example, the third group data may consist of data including regional distinction for the location of the store, the location of the subway station closest to the store, the location of the store within the building, the exterior structure of the store, and the internal structure of the store.

More specifically, 'regional distinction for a store's location' refers to which region it operates. As an example, the regional range for extracting store data for learning is, as shown in FIG. 3A, in the case of a region 311 selecting a dong in the district among the regions 310 set based on the dong, the corresponding region , and in the case of an area (313) in which a plurality of dongs are selected in the district among the areas (310) set based on dongs, the corresponding area and adjacent areas may also be included.

In addition, the regional range for extracting store data for learning based on regional distinction for the corresponding location of the store is, as shown in Figure 3b, one district in the city among the regions 330 set based on the district. In the case of the selected area (331), it can be included in the corresponding area, and in the case of the area (333) in which multiple districts in each city are selected among the areas (330) set based on the city, the corresponding area and adjacent areas can be included.

In addition, the regional range for extracting store data for learning based on regional distinction for the corresponding location of the store is one city within Korea among regions 350 set based on Korea, as shown in FIG. 3C. In the case of the selected region (351), it can be included in the region, and in the case of the region (353) in which multiple cities or provinces are selected among the regions (350) set based on Korea, the region and adjacent regions can be included.

In addition, the regional range for extracting store data for learning based on regional distinction for the corresponding location of the store is within 100m based on the point point 390 in the case of the red line 371, as shown in FIG. 3D. The yellow line 373 can be set within 300m of the point 390, and the green line 375 can be set within 500m of the point 390.

In addition, the regional range for extracting store data for learning based on regional distinction for the corresponding location of the store is within 500m based on the point point 390 in the case of the green line 375, as shown in FIG. 3E. The blue line 377 can be set within 1 km from the point 390, and the purple line 379 can be set within 2 km from the point 390.

In addition, as for the 'location of the subway station closest to the store', as shown in FIG. 3D, the point point 390 can be selected as the store location, and the distance from the nearest subway station based on the store can be calculated. This can determine whether the store is easily accessible to a large floating population, and can affect sales for the store.

Additionally, the 'location of the store within the building' can be set as to whether the store is on the first floor, in the basement, or on the second or higher floor. Specifically, in the case of a store in a department store, if it is located in the basement, it is calculated as an easily accessible and inexpensive location where you can eat lightly, and if it is on a higher floor, it is calculated as a location where access is difficult and expensive but you can eat leisurely and have high-quality food. can be calculated. Also, as another example, in the case of a store located in a general building, it is easy to access if it is on the first floor, but if it is on the second floor or basement, access is slightly inconvenient, and if it is on the third floor or higher, it is not easy to access, which may affect sales. You can.

Additionally, the 'exterior structure of the store' may be a structure that is recognized as the appearance of the store. Specifically, in the case of a franchise such as Starbucks, the store can be easily recognized and is easily recognized from the outside, and in the case of a private store, the appearance can be changed to recognize that it is a unique store.

Additionally, the ‘internal structure of the store’ may be a structure recognized internally in the store. Specifically, in the case of a cafe, there must be a space for making coffee and an auxiliary space within the store, but in the case of a restaurant, there may or may not be an auxiliary space other than the kitchen within the store. As above, the internal structure of a store varies depending on the characteristics of each store, and accordingly, it can be determined whether it is easy for customers to enter.

In operation 203, the first group data, second group data, and third group data of the first store are input into a deep learning-based prediction model to generate a first predicted profit obtained by the first store during a preset first period. Data, second predicted revenue data obtained from the first store during a preset second period, and third predicted revenue data obtained from the first store during a preset third period may be predicted.

As an example, referring to FIG. 4, the electronic device 101 (e.g., the processor 120) changes the preset first period from a monthly period setting 410 to a period setting 411 according to a specific month to a specific quarter. You can control by selecting the period setting (413) and the period setting (415) according to a specific half-year. As a specific example, the electronic device 101 (e.g., processor 120) may set the period 411 according to a specific month to July, select a plurality of periods, and set the period 411 according to a specific date. You can. In addition, the electronic device 101 (e.g., processor 120) can set the period setting 411 according to a specific quarter to 3 quarters, select a plurality, and set it as a standard according to a specific date. there is. Additionally, the electronic device 101 (e.g., processor 120) may set the period setting 413 according to a specific half-year to the second half of the year or set it as a standard according to a specific date.

As an example, referring to FIG. 4 , the electronic device 101 (e.g., the processor 120) may control the preset second period by selecting the corresponding year in the annual period setting 420. As a specific example, the electronic device 101 (e.g., processor 120) can set the period 420 according to the year to 1 year, select multiple times, and set it as a standard according to a specific date. It can be. Additionally, although not shown, the electronic device 101 (e.g., processor 120) may select a specific year (e.g., 2021, 2022).

As an example, referring to FIG. 4, the electronic device 101 (e.g., the processor 120) operates the preset third period every month, every quarter, every half year, every year, from the store's opening base date. And the period setting 430 can be controlled every two years. As a specific example, the electronic device 101 (e.g., processor 120) is stored every month, every quarter, every half year, every year, and every year based on the date the store opens (e.g., May 31, 2013). At least one period setting 430 can be selected for each two years, and can be set according to the selected period.

According to various embodiments, before inputting specific lifelog data into a deep learning-based prediction model, the electronic device 101 (e.g., processor 120 of FIG. 1) stores the specific lifelog data to suit a data format for learning. Data can be preprocessed. For example, the electronic device 101 formats (e.g., channel × sampling frequency × length) of specific lifelog data (e.g., first group data, second group data, third group data, set specific period, etc.). As an input data format for a deep learning-based prediction model, it can be preprocessed to be a × b (hertz) × c (seconds).

According to various embodiments, a deep learning-based prediction model is performed during a preset first period based on the first group data, the second group data, and the third group data of a plurality of stores received from the server. First operating revenue data obtained from the plurality of stores, second operating revenue data obtained from the plurality of stores during a preset second period, and third operating revenue data obtained from the plurality of stores during a preset third period. It can be learned based on revenue data. For example, a deep learning-based prediction model, (1) first group data, second group data, and third group in a preset first period (e.g., July, August, third quarter, second half, etc.) It is possible to learn based on data, and (2) first group data, second group data, and third group data in a preset second period (e.g., 1 year, 2 years, 2018, 2020, etc.) You can learn based on (3) a preset first period (e.g. 3 months, 1 year, 3 years based on the store opening date (May 4, 2017), a specific date (December 17, 2017) etc.) can be learned based on first group data, second group data, and third group data. At this time, the electronic device 101 may preprocess the first group data, second group data, and third group data to fit the learning data format. More specifically, the deep learning-based prediction model is based on (1) first group data of multiple stores, including store sales, major customer age groups, floating population, and store operating hours; (2) cost of products in the store; , second group data across multiple stores, including store operating personnel, presence or absence of unmanned robots, number of kiosks, and store fixed expenditures, and (3) regional distinction for the corresponding location of the store, location of the subway station and building closest to the store, It can be learned based on third group data of all multiple stores, including the location of my store, the exterior structure of the store, and the internal structure of the store. In this case, the server that manages the first store input to the prediction model may be the first group data, second group data, and third group data of the first store.

According to one embodiment, the electronic device 101 acquires a result value (output data) using a prediction model to which random weights are assigned as a learning process of a prediction model for predicting the profit of the first store, and obtains This can be performed by comparing the resulting value with the labeling data of the learning data, performing backpropagation according to the error, and optimizing the weights. Specifically, learning a prediction model refers to the process of training a prediction model based on training data and labeled data or unlabeled data, so that the prediction model can determine output data with respect to input data. In other words, the prediction model forms rules for the data and makes decisions. According to one embodiment, the electronic device 101 may use multiple learning algorithms among a plurality of learning algorithms that calculate the predicted value. For example, an ensemble method can be used in a prediction model, and better prediction performance can be obtained compared to using separate learning algorithms. Training a prediction model may mean adjusting the weights of the model. According to one embodiment, as a learning method, various methods such as supervised learning, unsupervised learning, reinforcement learning, imitation learning, and federated-learning are used. Available.

According to one embodiment, the revenue data of the first store may be classified into one of first predicted revenue data, second predicted revenue data, and first predicted revenue data according to the selected period and prediction model. For example, a deep learning-based prediction model recognizes the selected period (e.g., 3 months as of May 2020) as the first period and responds to the first period when the selected period (e.g., 3 months as of May 2020) is input from the external electronic device of the first store operator. The first predicted profit data may be output. In addition, the deep learning-based prediction model recognizes the selected period (e.g., all of 2021) as the second period when it is input from the external electronic device of the first store operator, and generates the second predicted profit data corresponding to the second period. can be output. In addition, the deep learning-based prediction model is used when a selected period (e.g., 1 year (May 31, 2016) based on the store opening date (May 31, 2015)) is input from the first store operator's external electronic device. , it is recognized as the third period, and third predicted profit data corresponding to the third period can be output. Additionally, the above example is just an example and can be selected and output in other ways.

According to one embodiment, a prediction model for predicting revenue for the first store may include a convolutional neural network (CNN). As a CNN structure, at least one of AlexNet, LENET, NIN, VGGNet, ResNet, WideResnet, GoogleNet, FractaNet, DenseNet, FitNet, RitResNet, HighwayNet, MobileNet, and DeeplySupervisedNet can be used. According to one embodiment, the prediction model may be implemented using a plurality of CNN structures. For example, the prediction model may use a combination of a one-dimensional CNN and a two-dimensional CNN, and may be implemented using either a GRU neural network or an LSTM neural network. In one embodiment, the one-dimensional CNN and the two-dimensional CNN are sequentially combined with a CNN layer, a ReLu layer, a pooling layer, and a dropout layer having a plurality of filters of a specific size for feature extraction. It may include a block, and may include a fully connected (FC) layer and an activation layer (eg, sigmoid, softmax, etc.). According to one embodiment, a convolution layer may extract features from input data. Additionally, the convolution layer can be composed of a filter that extracts features and an activation function that changes the value of the filter that extracts features to a non-linear value. The filter may include a function that detects whether the input data includes the feature.

According to various embodiments, the electronic device 101 may use various algorithms (eg, machine learning algorithms) and/or models for predicting profits for the first store in addition to a deep learning-based prediction model.

According to one embodiment, a prediction model for predicting revenue for the first store may be implemented including a classifier and/or regression model. In one embodiment, the prediction model may be implemented in the form of a classifier that generates auxiliary information of revenue for the first store. The classifier can perform binary classification or multiple classification. For example, a prediction model may use input data (e.g., first group data from a first store) against auxiliary information of revenue for the first store to indicate a certain type of emotional state (e.g., sales of the store, main customer age group, flow, etc.). It may be a binary classification model that predicts whether a product corresponds to one of the following: population, and store operating hours. Alternatively, the prediction model may be a multi-classification model that classifies input data into more specific classes. For example, it may be a multi-classification model that classifies the first group data of the first store into one of the store's sales, main customer age group, floating population, and store operating hours. In one embodiment, the classifier may use various types of algorithms, such as decision trees, support vector machines, and random forests. This is only an example and is not limited thereto.

According to one embodiment, a prediction model for predicting revenue for the first store may be implemented in the form of a regression model that generates auxiliary information on revenue for the first store. The regression model can derive the profit for the first store in probability form. For example, based on the first group data, second group data, and third group data, result values such as a 25% probability of loss occurring, a 65% probability of maintaining the status quo, and a 10% probability of profit generation may be derived. The type of profit derived with the highest probability may be the profit that can be generated by the operator in the future. The regression model may use various types of algorithms such as linear regression, regression tree, support vector regression, and kernel regression. This is only an example and is not limited thereto.

Figure 5 is a flow chart for utilizing predicted store profits to an operator, according to various embodiments.

FIG. 6 is a detailed flowchart for data transmission in FIG. 5.

In operation 510, a request for operating profit data of the first store managed by the operator managing the store may be received from the operator's external electronic device through a communication interface (e.g., the communication interface 170 of FIG. 1). .

As an example, an operator who operates a first store in a plurality of stores operates his or her external electronic device and stores his or her first store maintenance data and corresponding settings through a communication interface (e.g., communication interface 170 in FIG. 1). You can send a period and at the same time request a forecast for your first store's revenue.

In operation 530, the electronic device 101 (e.g., the processor 120), when any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data satisfies a preset first condition. Any one of first predicted revenue data, second predicted revenue data, and third predicted revenue data may be transmitted to the operator's external electronic device.

As an example, the electronic device 101 (e.g., the processor 120) sends any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data to the operator when the set first condition is satisfied. It is compared with the preset first store maintenance data, and as a result of the comparison, any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is satisfied to be more than the preset allowable range compared to the first store maintenance data. In this case, it can be determined that the first condition is satisfied.

More specifically, in operation s531, the electronic device 101 (e.g., processor 120), with reference to FIG. 6, any one of first predicted profit data, second predicted profit data, and third predicted profit data. may be compared with the corresponding set period selected from the external electronic device of the operator of the first store, and the profit data extracted as a result of the comparison may be compared with the first store maintenance data. Additionally, the electronic device 101 (eg, processor 120) may receive the first store maintenance data and the corresponding set period set from the server. Here, the setting period is a period selected on the electronic device of the operator of the first store, and the setting method can be set by the operator's settings, as shown in FIG. 4.

As a specific example, if the operator of the first store sets the period to March, the electronic device 101 (e.g., processor 120) recognizes it as the first period and determines the period by matching it with the first predicted profit data. .

In operation s532, the electronic device 101 (e.g., processor 120), referring to FIG. 6, first predicted profit data, second predicted profit data, and third predicted profit data determined to be the same period as the corresponding set period. Any one of the revenue data may be compared with the first store maintenance data based on the first condition. This means that, if a specific period is determined, the corresponding predicted profit data can be compared with the first store maintenance data. Here, the preset tolerance range may be set to -10% or more of the matched predicted profit data compared to the first store maintenance data.

In operation S533, the electronic device 101 (e.g., the processor 120), with reference to FIG. 6, determines whether any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is stored in the first store. If it is determined to be greater than a preset tolerance range compared to the maintained data, it may be determined that the first condition is satisfied. In addition, referring to FIG. 6, the electronic device 101 (e.g., processor 120) stores any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data of the first store operator. It can be transmitted to an external electronic device.

As a specific example, the electronic device 101 (e.g., the processor 120) sets the predicted profit data matching the preset tolerance range to -10% or more compared to the first store maintenance data, and receives the data from the operator's external electronic device. The set period received is 3 months, and profit generation of 35% of the existing profit can be set as the first store maintenance data. Based on the above, the electronic device 101 (e.g., processor 120) determines that it is the first predicted profit data, and if the profit generation of the first predicted profit data predicts 40% of the existing profit, the matched prediction Since the profit data is judged to be 5% or more compared to the first store maintenance data, it can be determined that the first condition is satisfied. This can guide the operator to determine whether to maintain that status while recognizing that the predicted profit data transmitted from the external electronic device is judged to be 5% of the first store maintenance data and is operating smoothly.

Meanwhile, in operation S532, the electronic device 101 (e.g., the processor 120) determines that, as a result of the comparison, any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is stored in the first store. If it is judged to be below the preset tolerance range compared to the maintained data, it may be determined that the first condition is not satisfied.

As a specific example, the electronic device 101 (e.g., the processor 120) sets the predicted profit data matching the preset tolerance range to -10% or more compared to the first store maintenance data and transmits it from the operator's external electronic device. If the received setting period is 1 year and the profit generation is set as the first store maintenance data at 50% of the existing profit, the electronic device 101 (e.g., processor 120) determines it to be the second predicted profit data and 2 If the profit generation of the predicted profit data predicts a 30% profit compared to the previous one, the matched predicted profit data is judged to be -20% compared to the first store maintenance data, so it can be judged that the first condition is not satisfied.

In operation s534, the electronic device 101 (e.g., the processor 120) selects any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data for which the first condition is determined to be unsatisfied to a preset value. It may be compared with the first store maintenance data based on the 1-1 condition, which determines the value to be below an acceptable range or above a preset risk range. Here, below the preset tolerance range or above the preset risk range, the matched predicted profit data may be set to -10% or less to -50& or more compared to the first store maintenance data.

In operation S535, the electronic device 101 (e.g., processor 120), with reference to FIG. 6, any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is If it is determined to be below a preset tolerance range or above a preset risk range compared to the first store maintenance data, it may be determined that the above 1-1 condition is satisfied. In addition, referring to FIG. 6, the electronic device 101 (e.g., processor 120) may generate any one of first predicted profit data, the second predicted profit data, and the third predicted profit data, and the first predicted profit data. The predicted profit and items of the second store, which are in a similar industry to the store and can be obtained more than the preset profit data of the first store, may be transmitted to an external electronic device of the operator of the first store.

As a specific example, the electronic device 101 (e.g., processor 120) matches predicted profit data that is below a preset tolerance range or above a preset risk range by -10% or less to -50% of the first store maintenance data. Set as above, the set period received from the operator's external electronic device is 1 year, the set period received from the operator's external electronic device is 1 year, and profit generation is 50% of the existing profit as the first store maintenance data. You can set it. Based on the above, the electronic device 101 (e.g., processor 120) determines the second predicted profit data, and if the profit generation of the second predicted profit data predicts 30% of the existing profit, the matched prediction Since the profit data is judged to be -20% compared to the first store maintenance data, it can be determined that condition 1-1 is satisfied. This means that the predicted profit data transmitted from the operator's external electronic device is judged to be -20% compared to the first store maintenance data, and while it is identified that some operations are unreasonable or have other problems, it is a business similar to the first store and operates smoothly. You can provide guidance on how to overcome the situation by benchmarking or referencing the second store in progress.

Meanwhile, in operation S534, the electronic device 101 (e.g., the processor 120) determines that, as a result of the comparison, any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is the first store If it is judged to be below the preset risk range compared to the maintenance data, it can be judged that condition 1-1 is not satisfied.

As a specific example, the electronic device 101 (e.g., processor 120) matches predicted profit data that is below a preset tolerance range or above a preset risk range by -10% or less to -50% of the first store maintenance data. If set as above, the setting period transmitted from the operator's external electronic device is 1 year, and the profit generation can be set to 50% of the existing profit as the first store maintenance data. Based on the above, the electronic device 101 (e.g., processor 120) determines the second predicted profit data, and if the profit generation of the second predicted profit data predicts -10% profit compared to the previous one, the matched Since the predicted profit data is judged to be -60% compared to the first store maintenance data, it can be judged that condition 1-1 is not satisfied.

In operation S536, the electronic device 101 (e.g., the processor 120), with reference to FIG. 6, any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data. If it is judged to be below a preset risk range compared to the first store maintenance data, it may be determined that the above 1-1 condition is not satisfied. In addition, referring to FIG. 6, the electronic device 101 (e.g., processor 120) is in a different industry from the first store and is adjacent to the first store, and can obtain more than the first store maintenance data set. 3 The predicted profits and items of the store may be transmitted to an external electronic device of the operator of the first store.

As a specific example, the electronic device 101 (e.g., processor 120) matches predicted profit data that is below a preset tolerance range or above a preset risk range by -10% or less to -50% of the first store maintenance data. If set as above, the setting period transmitted from the operator's external electronic device is 1 year, and the profit generation can be set to 50% of the existing profit as the first store maintenance data. Based on the above, the electronic device 101 (e.g., processor 120) determines the second predicted profit data, and if the profit generation of the second predicted profit data predicts -10% profit compared to the previous one, the matched Since the predicted profit data is judged to be -60% compared to the first store maintenance data, it can be judged that condition 1-1 is not satisfied. This means that the predicted profit data transmitted from the operator's external electronic device is judged to be -60% compared to the first store maintenance data, making operation very difficult or very wrong, making operation impossible, and operating the business even though it is a different industry from the first store. By benchmarking or referring to third-party stores that run the business smoothly, we can guide you to completely change your operation method.

Figure 7 is a specific example diagram for selecting an investment style of investors according to various embodiments.

Figure 8 is a flow chart for utilizing predicted store profits to investors, according to various embodiments.

FIG. 9 is a specific flowchart for data transmission in FIG. 8.

As an example, the electronic device 101 (e.g., the processor 120), as shown in FIG. 7, includes ultra-stable style data 611, stable style data 613, neutral style data 615, It consists of growth style data 617 and hyper-growth style data 619, and can request selection data 630 of the investment style data 610 through an external electronic device of a plurality of investors, and selection data 630 ) can be set to transmit from the server. Additionally, its investment style may change.

More specifically, the 'ultra-stable style data 611', as shown in FIG. 7, is a form in which the investment style data 610 is used among a plurality of investors who do not want a loss of principal instead of wanting a very small return on investment. Therefore, the margin of error compared to profit is very small. As an example, the principal return of the ultra-stable style data 611 may be set to a minimum of -2% and a maximum of 5%, and the error range of the ultra-stable style data 611 may be set to ±0% to 2.5%.

In addition, as shown in FIG. 7, 'stable style data 613' is a form in which a plurality of investors who want a small return on investment, but can invest even if a very small loss of principal occurs, compares the return to return. The margin of error is also small. As an example, the principal return of the stable style data 613 can be set to a minimum of -10% and a maximum of 20%, and the error range of the stable style data 613 can be set to ±2.5% to 7%.

In addition, as shown in FIG. 7, 'neutral style data 615' allows multiple investors to invest even if the loss of principal is reduced to some extent instead of seeking an appropriate return on investment. As an example, the principal return of the neutral style data 615 is a minimum of -35% and a maximum of 50%, and the error range of the neutral style data 615 can be set to ±5% to 10%.

In addition, as shown in FIG. 7, 'growth style data 617' refers to a plurality of investors who pursue investment returns rather than the original investment amount and invest a significant portion, taking into account the possibility of losses. You can. As an example, the principal return of the growth style data 617 is a minimum of -60% and a maximum of 80%, and the error range of the growth style data 617 can be set to ±10% to 20%.

In addition, as shown in FIG. 7, 'hyper-growth style data 619' may want as much profit as possible even if there is a possibility of losing the entire investment principal among multiple investors. As an example, the principal return of the hyper-growth style data 619 is a minimum of -100% and a maximum of 120%, and the error range of the hyper-growth style data 619 can be set to ±25% to 40%.

In operation 710, a request for operating profit data of the first store managed by the investor investing in the store may be received from the investor's external electronic device through a communication interface (e.g., the communication interface 170 of FIG. 1). .

As an example, an investor investing in a first store among a plurality of stores operates his/her external electronic device and records the profits of the first store in which the investor invested through a communication interface (e.g., communication interface 170 in FIG. 1). You can request a prediction.

In operation 730, the electronic device 101 (e.g., the processor 120) when any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data satisfies a preset second condition. Any one of first predicted profit data, second predicted profit data, and third predicted profit data may be transmitted to the investor's external electronic device.

As an example, the electronic device 101 (e.g., the processor 120) receives any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data from the investor when the set second condition is satisfied. Compared to the set investment style data 630, it is compared to determine whether it is greater than or equal to a preset allowable range, and as a result of the comparison, any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is within the preset allowable range compared to the investment style data. If the above is satisfied, it can be determined that the second condition is satisfied.

More specifically, in operation s731, the electronic device 101 (e.g., processor 120), with reference to FIG. 9, any one of first predicted profit data, second predicted profit data, and third predicted profit data. The set period selected from the external electronic device of the first store investor may be compared, and the profit data extracted as a result of the comparison may be compared with the selected investment style data 630. Additionally, the electronic device 101 (eg, processor 120) may receive the corresponding set period. Here, the corresponding setting period is a period selected on the investor's external electronic device at the first store, and the setting method can be set by the investor's settings, as shown in FIG. 4. As a specific example, if the investor in the first store sets the period to March, the electronic device 101 (e.g., processor 120) recognizes it as the first period and makes a decision by matching it with the first predicted profit data. .

In operation s732, the electronic device 101 (e.g., processor 120), with reference to FIG. 9, first predicted profit data, second predicted profit data, and third predicted profit data determined to be the same period as the corresponding set period. Any one of the return data may be compared with the investment style data 630 based on the second condition. This means that, if a specific period is determined, the corresponding predicted profit data and investment style data 630 can be compared. Here, the investment style data 630 may be set to ‘stable style data 613’.

In operation s733, the electronic device 101 (e.g., the processor 120), with reference to FIG. 9, selects one of the first predicted return data, the second predicted return data, and the third predicted return data as investment style data. If it is judged to be above the range of investment style data (630) compared to (630), it can be judged that the second condition is satisfied. Additionally, with reference to FIG. 9 , the electronic device 101 (e.g., the processor 120) sends any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data to the first store investor or It can be transmitted to an external electronic device of the person planning to invest in the first store.

As a specific example, the electronic device 101 (e.g., processor 120) receives investment style data 630 matching a preset tolerance range as stable style data 613, and if the investor's set period is 3 months, , the electronic device 101 (e.g., processor 120) determines that the first predicted profit data is the first predicted profit data, and if the profit generation of the first predicted profit data predicts a 15% profit compared to the existing one, the matched investment style data 630 It can be determined that the second condition is satisfied. This guides the investor to make an investment decision based on that status while recognizing that the investment style data 630 transmitted from the investor's external electronic device determines that the profit of the first store maintenance data is 15% and is operating smoothly. can do.

Meanwhile, in operation S732, the electronic device 101 (e.g., the processor 120) determines that, as a result of the comparison, any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is investment style data. If it is judged to be below the investment style data (630) range compared to (630), the second condition can be judged to be unsatisfied.

As a specific example, the electronic device 101 (e.g., the processor 120) sets the range of the investment style data 630 to the stable style data 613, and the setting period transmitted from the investor's external electronic device is 1 year. It can be set to . Based on the above, the electronic device 101 (e.g., the processor 120) determines the second predicted profit data and sets the second condition if the profit generation of the second predicted profit data predicts -20% profit compared to the previous one. can be judged as unsatisfactory.

In operation S734, the electronic device 101 (e.g., the processor 120) may transmit an investment style change option to the investor's external electronic device set with the investment style data 630 for which the second condition is determined to be unsatisfied, Changed investment style data 630 may be received from the investor's external electronic device. Here, the electronic device 101 (e.g., the processor 120) may transmit the investment style data 630, including information about the range of possible selections, to the investor's external electronic device. Afterwards, the investor can change the investment style data 630 through his or her external electronic device. Finally, the investor's external electronic device may transmit the changed investment style data 630 to the electronic device 101 via a communication interface (e.g., the communication interface 170).

In operation S736, the electronic device 101 (e.g., processor 120), referring to FIG. 9, first predicted profit data, second predicted profit data, and third predicted profit data determined to be the same period as the corresponding set period. Any one of the profit data may be compared with the changed investment style data 630 based on the second condition. Here, the changed investment style data 630 may be set to neutral style data 615. Thereafter, in operation s733, the electronic device 101 (e.g., processor 120), referring to FIG. 9, determines that any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data has changed. If it is determined that the changed investment style data (630) is above the range compared to the investment style data (630), it can be determined that the second condition is satisfied. The contents of this are the same as those of S733 written at the top, so they are omitted.

Meanwhile, in operation S735, the electronic device 101 (e.g., processor 120) does not receive the changed investment style data 630 from the investor's external electronic device, or the electronic device 101 (e.g., : Processor 120) determines that, as a result of the comparison, any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data has a range of investment style data 630 compared with the investment style data 630. If it is judged as below, it can be judged that the second condition is not satisfied.

As a specific example, the electronic device 101 (e.g., processor 120) sets the range of the changed investment style data 630 to neutral style data 615, and sets the set period transmitted from the investor's external electronic device to the neutral style data 615. It can be set to 1 year. Based on the above, the electronic device 101 (e.g., processor 120) determines the second predicted profit data and sets the second condition if the profit generation of the second predicted profit data predicts -50% profit compared to the previous one. can be judged as unsatisfactory.

In operation S737, referring to FIG. 9, the electronic device 101 (e.g., the processor 120) does not receive the changed investment style data 630 from the investor's external electronic device or, as a result of comparison, the first If any one of the predicted profit data, the second predicted profit data, and the third predicted profit data is judged to be below the range of the changed investment style data (630) compared to the changed investment style data (630), the second condition is determined to be unsatisfied. Therefore, data may not be transmitted to the investor's external electronic device. This is evidence that the investment in the store in question was not appropriate for the investor, or that the allowable range set by change was evidence. Nevertheless, it is judged to be more risky, so investors can prevent losses.

Figure 10 is a detailed illustration of an investor's purchase or sale according to various embodiments.

First, the electronic device 101 (eg, processor 120) may ensure that the entire stake of the first store is comprised of a plurality of tokens generated based on blockchain. As an example, the electronic device 101 (e.g., the processor 120) stores the entire stake of the first store in 100 plural tokens, 50 of which are distributed to the external electronic device of the operator 830, and the remaining 50 are distributed to the plural tokens. It may be shared on the external electronic devices of existing investors 870.

In operation S801, referring to FIG. 10, the electronic device 101 (e.g., the processor 120) provides the maximum token data available for purchase to the external electronic device of the new investor 850 that has confirmed at least one predicted profit data. can do. Here, the total number of tokens is 100, the number of tokens held in the external electronic devices of the operator 830 is 50, the minimum held token ratio is 25%, and the number of tokens available for sale among the external electronic devices of the plurality of existing investors 870 is 30. Assuming there are 55 tokens, the electronic device 101 (e.g., processor 120) may set the maximum number of tokens available for purchase to 55 and share the information with the external electronic device of the new investor 850.

In operation S803, the electronic device 101 (e.g., the processor 120), referring to FIG. 10, may receive at least one token purchase request signal from the external electronic device of the new investor 850. As a specific example, the electronic device 101 (e.g., the processor 120) may request the purchase of 20 tokens from the external electronic device of the new investor 850.

In operation S805, the electronic device 101 (eg, processor 120), referring to FIG. 10, may provide at least one token in response to a purchase request. As a specific example, the electronic device 101 (e.g., the processor 120) transfers the token from the external electronic device of the plurality of existing investors 870 that requested the transaction with the highest priority to the external electronic device of the new investor 850. (e.g., 20 tokens) can be transmitted, and if there is no corresponding sale request, the token held by the operator (830) can be transmitted (e.g., 20 tokens) to the external electronic device of the new investor (850). In addition, the electronic device 101 (e.g., processor 120) transfers some tokens (e.g., 10 tokens) from the external electronic device of a plurality of existing investors 870 to the external electronic device of the new investor 850. , some tokens (e.g., 10) may be transferred from an external electronic device of the operator 830.

In operation S807, the electronic device 101 (eg, processor 120), referring to FIG. 10, may inform existing investors of token purchase information and total token ratio data. As a specific example, the electronic device 101 (e.g., the processor 120) receives information that the external electronic device of the new investor 850 traded the corresponding token from the external electronic devices of the plurality of existing investors who requested the transaction with the highest priority, or Information on the sale and purchase of tokens held by the operator (830) by the external electronic device of the new investor (850) and the total number of tokens purchased by the external electronic device of the new investor (850) (e.g., 20) when there is no corresponding sale request. The corresponding information can be transmitted to the external electronic device of the operator 830 and the external electronic device of all of the plurality of existing investors 870, respectively.

In operation S809, the electronic device 101 (eg, processor 120), referring to FIG. 10, may change from a new investor 850 to one of a plurality of existing investors 870. As a specific example, the electronic device 101 (e.g., the processor 120) may change the information of the new investor 850 to the external electronic device information of one of the plurality of existing investors 870.

In operation S811, the electronic device 101 (e.g., processor 120), referring to FIG. 10, sells and sells tokens from the external electronic device of a plurality of existing investors 870 to the external electronic device of the operator 830. You can. As a specific example, the electronic device 101 (e.g., processor 120) operates the corresponding tokens (e.g., 15) from an external electronic device of one of the plurality of existing investors 870 that requested the transaction with the highest priority. A delivery request can be made to an external electronic device of (830), or the corresponding tokens (e.g., 8, 5, 2) can be received from a plurality of external electronic devices among the plurality of existing investors (870) who requested the sale with the highest priority. ) can be requested to be delivered to the external electronic device of the operator 830.

In operation S813, the electronic device 101 (e.g., processor 120), referring to FIG. 10, may purchase tokens of the external electronic device of a plurality of existing investors 870 from the external electronic device of the operator 830. there is. As a specific example, the electronic device 101 (e.g., the processor 120) transfers the token from the external electronic device of the plurality of existing investors 870 that requested the transaction with the highest priority to the external electronic device of the operator 830. Can be transmitted, and 15 tokens can be transmitted to the external electronic device of the operator 830. At this time, the electronic device 101 (e.g., processor 120) may transmit (e.g., 15) information from an external electronic device of one of a plurality of existing investors 870 to the external electronic device of the operator 830, It can be delivered from external electronic devices of multiple investors (e.g. 8, 5, 2).

In operation S813, the electronic device 101 (e.g., processor 120), referring to FIG. 10, may inform a plurality of existing investors 830 of token sale information and total token ratio data. As a specific example, the electronic device 101 (e.g., the processor 120) contains information on which the external electronic device of the operator 850 bought and sold the corresponding token and the total number of tokens purchased by the external electronic device of the operator 830 ( For example, 15), the corresponding information can be transmitted to the external electronic device of the operator 830 and to the external electronic device of all of the plurality of existing investors 870. In addition, the electronic device 101 (e.g., processor 120) may exclude the external electronic device of at least one existing investor 870 who does not hold tokens from the plurality of existing investors 870 during the transaction process. there is.

According to this embodiment, an electronic device that predicts profit for a store using a deep learning-based prediction model and utilizes the predicted information includes a communication interface and a processor, wherein the processor is configured to communicate through the communication interface. , first group data related to the income of the first store, second group data related to the expenditure of the first store, and third group data related to the location characteristics of the first store from the server that manages the first store. Obtaining and inputting the first group data, the second group data, and the third group data of the first store into a deep learning-based prediction model, the data obtained from the first store during a preset first period Predict first predicted revenue data, second predicted revenue data obtained from the first store during a preset second period, and third predicted revenue data obtained from the first store during a preset third period, and the dip The learning-based prediction model is based on the first group data, the second group data, and the third group data of the plurality of stores received from the server. It is learned based on first operating revenue data, second operating revenue data obtained from the plurality of stores during a preset second period, and third operating revenue data obtained from the plurality of stores during a preset third period.

In the electronic device according to this embodiment, the first group data consists of data including store sales, major customer age groups, floating population, and store operating hours, and the second group data includes the cost of products in the store. , consists of data including store operating personnel, presence or absence of unmanned robots, number of kiosks, and store fixed expenses, and the third group data includes regional distinction for the corresponding location of the store, location of the subway station closest to the store, and within the building. It consists of data including the location of the store, the exterior structure of the store, and the internal structure of the store.

In the electronic device according to this embodiment, in the third group data, the regional distinction for the corresponding location of the store is divided into a dong unit, a district unit, a city unit, or a radius of 100 m, 300 m, or 100 m, based on a specific area. Distinguish between distances set in 500m, 1km, and 2km units.

In the electronic device according to this embodiment, the preset first period is comprised of every month, every quarter, and every half year, and the preset second period is comprised of every year, every two years, and every two years. The preset third period is composed of every month, every quarter, every half year, every year, and every two years from the store's opening base date.

In the electronic device according to this embodiment, the processor receives, through the communication interface, a request for operation profit data of a first store managed by an operator who manages the store from an external electronic device of the operator, and 1 If any one of the predicted profit data, the second predicted profit data, and the third predicted profit data satisfies a preset first condition, the first predicted profit data and the second forecast are transmitted to an external electronic device of the operator. Transmitting any one of revenue data and the third predicted revenue data, and one of the first predicted revenue data, the second predicted revenue data, and the third predicted revenue data satisfies a preset second condition. In this case, each of the plurality of investors transmits one of the first predicted profit data, the second predicted profit data, and the third predicted profit data to an external electronic device.

When the set first condition is satisfied, the electronic device according to this embodiment receives any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data from the operator. Comparison is made with the set first store maintenance data, and as a result of the comparison, any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is within a preset tolerance range compared to the first store maintenance data. If the above is satisfied, it is determined that the first condition is satisfied, and the processor receives the set first store maintenance data and the corresponding set period from the server, and the set period is the first predicted profit. data, the second predicted profit data, and the third predicted profit data, and the first predicted profit data, the second predicted profit data, which are determined to be the same period as the corresponding set period, and Any one of the third predicted revenue data is compared with the first store maintenance data based on the first condition, and as a result of the comparison, the first predicted revenue data, the second predicted revenue data, and the third prediction If any one of the revenue data is determined to be greater than a preset allowable range compared to the first store maintenance data, the first condition is determined to be satisfied, and the first predicted revenue data, the second predicted revenue data, and the Any one of the third predicted profit data is transmitted to the external electronic device of the first store operator.

In the electronic device according to this embodiment, as a result of the comparison, the processor compares any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data with the first store maintenance data. If it is determined to be below the preset acceptable range, the first condition is determined to be unsatisfied, and any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is below the preset acceptable range. or compared with the first store maintenance data based on the 1-1 condition that is determined to be a value above a preset risk range, and as a result of the comparison, any one of the second predicted profit data and the third predicted profit data If the value is determined to be below the preset tolerance range or above the preset risk range compared to the first store maintenance data, it is determined that the first condition is satisfied, and the first predicted profit data of the first store, Any one of the second predicted profit data and the third predicted profit data, and the predicted profit and items of the second store that are in a similar industry to the first store and can be obtained more than the preset first store profit data. As a result of transmission to the external electronic device of the operator of the first store and comparison, any one value of the first predicted profit data, the second predicted profit data, and the third predicted profit data is the first store maintenance data. If it is determined that the value is below the preset risk range, it is determined that the condition 1-1 is unsatisfied, and it is a different industry from the first store and is adjacent to the first store, and is obtained more than the set first store maintenance data. It is set to transmit the predicted profits and items of the third store to the external electronic device of the operator of the first store.

If the set second condition is satisfied, the electronic device according to this embodiment receives any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data from the investor. Comparison is made to see if it is greater than a preset allowable range compared to the set investment style data, and as a result of the comparison, any one of the first predicted return data, the second predicted return data, and the third predicted return data is allowed compared to the investment style data. If the range is satisfied or more, it is determined that the second condition is satisfied, and the processor receives a preset investment style data setting value and the corresponding setting period from the server, and the corresponding setting period is the first prediction Determine whether it matches any one of revenue data, the second predicted revenue data, and the third predicted revenue data, and select among the determined first predicted revenue data, the second predicted revenue data, and the third predicted revenue data. Any one is compared with the investment style data based on the second condition, and as a result of the comparison, any one of the first predicted return data, the second predicted return data, and the third predicted return data is the investment style. If it is determined that the data exceeds a preset allowable range, any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is provided to the investor's external electronic device.

As used in this document, the term "module" or "unit" includes a unit consisting of hardware, software, or firmware, and can be used interchangeably with terms such as logic, logic block, component, or circuit, etc. there is. “Module” or “unit” may be an integrated part, a minimum unit that performs one or more functions, or a part thereof. A “module” or “unit” may be implemented mechanically or electronically, e.g., known or to be developed, application-specific integrated circuit (ASIC) chips, field-programmable circuits (FPGAs), that perform certain operations. gate arrays), or programmable logic devices, and may be executed by the processor 120. At least a portion of the device (e.g., modules or functions thereof) or method (e.g., operations) according to various embodiments includes instructions stored in a computer-readable storage medium (e.g., memory 130) in the form of a program module. It can be implemented as: When the instruction is executed by a processor (eg, processor 120), the processor may perform the function corresponding to the instruction. Computer-readable recording media include hard disks, floppy disks, magnetic media (e.g. magnetic tape), optical recording media (e.g. CD-ROM, DVD, magneto-optical media (e.g. floptical disks), built-in memory, etc. The instruction may include code created by a compiler or code that can be executed by an interpreter. A module or program module according to various embodiments includes at least one or more of the above-described components. , some parts may be omitted, or other components may be further included. Operations performed by modules, program modules or other components according to various embodiments may be executed sequentially, parallel, iteratively or heuristically, or at least Some operations may be executed in a different order, omitted, or other operations may be added.

Additionally, the embodiments disclosed in this document are presented for explanation and understanding of the disclosed technical content, and do not limit the scope of the present disclosure. Accordingly, the scope of the present disclosure should be interpreted as including all changes or various other embodiments based on the technical idea of the present disclosure.

Claims (8)

In an electronic device that predicts profits for a store using a deep learning-based prediction model and utilizes the predicted information,
a communication interface, and
Includes a processor,
The processor,
Through the communication interface, from the server managing the first store, first group data related to the income of the first store, second group data related to the expenditure of the first store, and location characteristics of the first store. obtain third group data;
A first prediction obtained from the first store during a preset first period by inputting the first group data, the second group data, and the third group data of the first store into a deep learning-based prediction model. predict revenue data, second predicted revenue data obtained from the first store during a preset second period, and third predicted revenue data obtained from the first store during a preset third period;
The deep learning-based prediction model is performed at the plurality of stores during a preset first period based on the first group data, the second group data, and the third group data of the plurality of stores received from the server. Learning based on the obtained first operating revenue data, the second operating revenue data obtained from the plurality of stores during a preset second period, and the third operating revenue data obtained from the plurality of stores during a preset third period become,
The processor,
Receiving, through the communication interface, a request for operation profit data of a first store managed by an operator managing the store from an external electronic device of the operator,
When any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data satisfies a preset first condition, the first predicted profit data, the first predicted profit data, and the third predicted profit data are transmitted to an external electronic device of the operator. 2 Transmit any one of the predicted profit data and the third predicted profit data, and one of the first predicted profit data, the second predicted profit data, and the third predicted profit data meets a preset second condition. When satisfied, each of the plurality of investors transmits any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data to an external electronic device,
Electronic devices.
According to claim 1,
The first group data is,
It consists of data including store sales, major customer age groups, floating population, and store operating hours.
The second group data is,
It consists of data including the cost of products in the store, the number of people operating the store, the presence or absence of unmanned robots, the number of kiosks, and the store's fixed expenses,
The third group data is,
Consisting of data including regional distinction for the store's location, location of the subway station closest to the store, location of the store within the building, exterior structure of the store, and internal structure of the store,
Electronic devices.
According to clause 2,
In the third group data, the regional distinction for the corresponding location of the store is,
Distinguished by dong unit, district unit, city unit, or by distance set in radii of 100m, 300m, 500m, 1km, and 2km based on a specific area.
Electronic devices.
According to claim 1,
The preset first period is,
It is organized every month, every quarter, and every half year,
The preset second period is,
Organized annually, biennially, and biennially,
The preset third period is,
Starting from the store's opening date, it is organized every month, every quarter, every half year, every year, and every two years.
Electronic devices.
delete According to claim 1,
If the first condition set above is satisfied,
Any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is compared with the first store maintenance data preset by the operator, and the result of the comparison is compared to the first store maintenance data. If any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data satisfies a preset tolerance range or more, determining that the first condition is satisfied,
The processor,
Receiving the set first store maintenance data and the corresponding set period from the server,
Determine whether the corresponding set period matches any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data,
Compare any one of the first predicted revenue data, the second predicted revenue data, and the third predicted revenue data determined to be the same period as the corresponding set period with the first store maintenance data based on the first condition. do,
As a result of the comparison, if any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is determined to be greater than a preset allowable range compared to the first store maintenance data, the first condition is judged to be satisfied,
Transmitting any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data to an external electronic device of the first store operator,
Electronic devices.
According to clause 6,
The processor,
As a result of the comparison, if any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is determined to be below a preset tolerance range compared to the first store maintenance data, the first condition judged to be unsatisfactory,
Based on the 1-1 condition for determining any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data as a value below a preset tolerance range or above a preset risk range, 1 Compare with store maintenance data,
As a result of the comparison, if any one of the second predicted profit data and the third predicted profit data is determined to be below a preset tolerance range or above a preset risk range compared to the first store maintenance data, the first -1 It is determined that the condition is satisfied, and any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data of the first store and a similar industry to the first store and a preset Transmitting predicted profits and items of the second store that can be obtained in excess of the first store profit data to an external electronic device of the operator of the first store,
As a result of the comparison, if any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is determined to be below a preset risk range compared to the first store maintenance data, the first predicted profit data 1-1 Condition is determined to be dissatisfied, and the predicted profits and items of the third store, which are in a different industry from the first store and are adjacent to the first store and can be obtained more than the set first store maintenance data, are predicted. set to be transmitted to an external electronic device of the operator of the first store,
Electronic devices.
According to claim 1,
If the second condition set above is satisfied,
Compare any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data to see if it is greater than a preset allowable range compared to the investment style data preset by the investor, and as a result of the comparison, the investment style data If any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data satisfies a preset tolerance range or more, determining that the second condition is satisfied,
The processor,
Receive the preset investment style data setting value and corresponding setting period from the server,
Determine whether the corresponding set period matches any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data,
Compare any one of the determined first predicted profit data, the second predicted profit data, and the third predicted profit data with the investment style data based on the second condition,
As a result of the comparison, if any one of the first predicted profit data, the second predicted profit data, and the third predicted profit data is determined to be greater than a preset allowable range compared to the investment style data, the first predicted profit data, Providing any one of the second predicted profit data and the third predicted profit data to the investor's external electronic device,
Electronic devices.