WO2021060771A1

WO2021060771A1 - Method for providing motion identification service for customer behavior analysis and supply chain management based on artificial intelligence and internet of things

Info

Publication number: WO2021060771A1
Application number: PCT/KR2020/012529
Authority: WO
Inventors: 허해연
Original assignee: 허해연
Priority date: 2019-09-24
Filing date: 2020-09-17
Publication date: 2021-04-01
Also published as: KR102230991B1

Abstract

Provided is a method for providing a motion identification service for customer behavior analysis and supply chain management based on artificial intelligence and Internet of things, the method comprising the steps of: receiving motion data collected via a motion scanner from at least one motion collector attached to at least one product; parsing the collected motion data to determine and extract a motion event corresponding to at least one movement type, deriving a level-of-interest identifier from the motion event, and classifying same; extracting reference data having a preconfigured similarity from big data pre-constructed in the classified level-of-interest identifier; and outputting customer behavior analysis data pre-mapped to and stored in the extracted reference data to generate customer behavior analysis data for a customer's level of interest in the at least one product.

Description

Method of providing motion identification service for analysis of customer behavior and supply chain management based on artificial intelligence and IoT

The present invention relates to a method of providing a motion identification service for analysis of customer behavior and supply chain management based on artificial intelligence and IoT, and provides a platform capable of grasping a customer's interest in a product from the movement of the product.

The Fourth Industrial Revolution refers to a technological revolution in which the boundaries between physics, digital, and biology are disappearing based on the Third Industrial Revolution, and convergence between multi-disciplinary technologies takes place. The basic mechanism of the 4th industrial revolution is superintelligence, hyperconnection, and convergence to generate big data through the Internet of Things, and artificial intelligence performs appropriate judgment and autonomous control based on the interpretation of big data to produce superintelligent products. And provide services. In the end, it is differentiated in terms of range, speed, and ripple power compared to the 3rd Industrial Revolution due to improved connectivity and automation, and innovative technological advances and industrial reorganization due to overall system changes are the main features. The 4th Industrial Revolution is based on the hyper-connectivity of IoT technology that connects things to things, people to people, and people to things.In particular, the core technologies of the 4th Industrial Revolution are applied to the flagship industries where the Korean economy has strengths. To promote this, research is being conducted on actively investing in production processes such as the Internet of Things or using big data and artificial intelligence in the science and technology field or the knowledge service industry.

At this time, a method of analyzing customer behavior by combining artificial intelligence and IoT was researched and developed. In this regard, Korean Patent Registration No. 10-1888922 (announced on August 16, 2018), which is a prior art, has Customer information management that manages the information collected by the customer information collection device and the customer information collection device installed in the store to collect data to analyze the behavioral information of entering and exiting customers, and analyzes customer behavior based on the collected information It includes an analysis information database that stores customer behavior information analyzed by the server and the customer information management server, and the customer information collection device acquires in-store images using an RGB image sensor, analyzes the in-store image, and enters by time. A video information collection unit that counts the number of people and collects video information including the number of people entering and exiting by time slot, and collecting terminal identification information and access time information corresponding to the terminal identification information and access signal strength information from a user terminal possessed by the customer. A configuration including an AP and a collection information transmitting unit for transmitting image information and terminal identification information to a customer information management server is disclosed.

However, even if you use the above-described method, just grasping the customer's movements is an accurate indication of what kind of product the customer is interested in, whether they are just looking at the product or listening to purchase a product even if they are interested. Information cannot be grasped. In addition, if the retail store located at the forefront of supply-chain management fails to grasp the exact needs or demands, product production planning or product supply and inventory management will fail. Therefore, the superintelligence, hyper-connection, and convergence made possible by artificial intelligence and IoT generate big data through IoT, and artificial intelligence performs appropriate judgment and autonomous control based on the interpretation of big data. There is a need for a method of producing products and providing services.

An embodiment of the present invention is to measure the customer's interest from the behavior of the customer who touches the product. Analyzes the behavior of the company and at the same time derives the level of interest and checks whether the level of interest leads to sales, so that the results of the established big data and the comparison and verification of errors are performed, and the balance between supply and demand within the supply chain management system is Provides a method of providing motion identification services for artificial intelligence and IoT-based customer behavior analysis and supply chain management that can achieve and ultimately optimize all resources based on real-time data and achieve cost reduction and production efficiency. I can. However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention includes the steps of receiving motion data collected via a motion scanner from at least one motion collector attached to at least one product, and the collected motion Parsing the data to determine and extract a motion event corresponding to at least one motion type, deriving and classifying an interest level identifier from the motion event, and pre-set from the big data pre-established in the classified interest level identifier. Extracting reference data having a degree of similarity, and outputting customer behavior analysis data previously mapped to and stored in the extracted reference data, and generating customer behavior analysis data on a customer's interest in at least one product. .

According to any one of the above-described problem solving means of the present invention, in order to measure the customer's interest from the behavior of the customer who touches the product, the movement of the product is measured using the Internet of Things, and a query ( Query) to analyze the customer's behavior and at the same time derive the level of interest, and to check whether the level of interest leads to sales, compare the results of the established big data and verify errors, and within the supply chain management system. A balance between supply and demand can be achieved, and ultimately, all resources can be optimized based on real-time data, resulting in cost reduction and production efficiency.

1 is a view for explaining a motion identification service providing system for artificial intelligence and IoT-based customer behavior analysis and supply chain management according to an embodiment of the present invention.

FIG. 2 is a block diagram illustrating a motion identification service providing server included in the system of FIG. 1.

3 is a view for explaining an embodiment in which a motion identification service for analysis of customer behavior and supply chain management based on artificial intelligence and IoT according to an embodiment of the present invention is implemented.

FIG. 4 is a diagram showing a process in which data is transmitted and received between components included in the motion identification service providing system for artificial intelligence and IoT-based customer behavior analysis and supply chain management of FIG. 1 according to an embodiment of the present invention to be.

5 is a flowchart illustrating a method of providing a motion identification service for analysis of customer behavior and supply chain management based on artificial intelligence and IoT according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" with another part, this includes not only "directly connected" but also "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included, and one or more other features, not excluding other components, unless specifically stated to the contrary. It is to be understood that it does not preclude the presence or addition of any number, step, action, component, part, or combination thereof.

The terms "about", "substantially", and the like, as used throughout the specification, are used in or close to the numerical value when manufacturing and material tolerances specific to the stated meaning are presented, and are used to provide an understanding of the present invention. To assist, accurate or absolute numerical values are used to prevent unreasonable use of the stated disclosure by unscrupulous infringers. As used throughout the specification of the present invention, the term "step (to)" or "step of" does not mean "step for".

In the present specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized by using two or more hardware, or two or more units may be realized by one piece of hardware.

In the present specification, some of the operations or functions described as being performed by the terminal, device, or device may be performed instead in a server connected to the terminal, device, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed by a terminal, device, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means mapping or matching the unique number of the terminal or the identification information of the individual, which is the identification data of the terminal. Can be interpreted as.

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

1 is a view for explaining a motion identification service providing system for artificial intelligence and IoT-based customer behavior analysis and supply chain management according to an embodiment of the present invention. Referring to FIG. 1, a motion identification service providing system 1 for analyzing customer behavior and supply chain management based on artificial intelligence and IoT includes at least one motion collector 100, a motion identification service providing server 300, and at least It may include one motion scanner 400, and at least one manufacturer server 500. However, since the motion identification service providing system 1 for analysis of customer behavior and supply chain management based on artificial intelligence and IoT of FIG. 1 is only an embodiment of the present invention, the present invention is limited to the interpretation of FIG. It does not become.

In this case, each component of FIG. 1 is generally connected through a network 200. For example, as shown in FIG. 1, at least one motion collector 100 may be connected to the motion identification service providing server 300 through the network 200. In addition, the motion identification service providing server 300 may be connected to at least one motion collector 100, at least one motion scanner 400, and at least one manufacturer server 500 through the network 200. In addition, the at least one motion scanner 400 may be connected to the at least one motion collector 100 and the motion identification service providing server 300 through the network 200. In addition, at least one manufacturer server 500 may be connected to the motion identification service providing server 300 through the network 200.

Here, the network refers to a connection structure in which information exchange is possible between each node, such as a plurality of terminals and servers, and examples of such networks include RF, 3rd Generation Partnership Project (3GPP) network, and Long Term (LTE). Evolution) network, 5GPP (5th Generation Partnership Project) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network) , Personal Area Network (PAN), Bluetooth (Bluetooth) network, NFC network, satellite broadcasting network, analog broadcasting network, Digital Multimedia Broadcasting (DMB) network, and the like, but are not limited thereto.

In the following, the term'at least one' is defined as a term including the singular number and the plural number, and even if the term'at least one' does not exist, each component may exist in the singular or plural, and may mean the singular or plural. It will be self-evident. In addition, it will be possible to change according to the embodiment that each component is provided in the singular or plural.

The at least one motion collector 100 may be a device that detects motion using a web page, an app page, a program, or an application related to a motion identification service for analyzing customer behavior and supply chain management based on artificial intelligence and IoT. The at least one motion collector 100 may be a device that is attached or mounted on a product and collects information such as shaking, impact, movement pattern, direction, and number of times of the product. Further, the at least one motion collector 100 may be a device that is connected to the motion scanner 500 by wire or wirelessly and transmits the collected motion data to the motion scanner 500. In addition, according to an embodiment implemented as active or passive when transmitting the collected information, it may be a device that transmits motion data in real time or periodically when a request is received by the motion scanner 500. In addition, the at least one motion collector 100 may be a device that transmits an identification code of a product together when transmitting motion data to the motion scanner 500, or may be a device that may be interpolated into the product in a wearable form. In addition, at least one motion collector 100 may have a built-in motion sensor, but any sensor capable of detecting the above-described type of motion may be used.

The motion identification service providing server 300 may be a server that provides a motion identification service web page, an app page, a program, or an application for analysis of customer behavior and supply chain management based on artificial intelligence and IoT. Then, the motion identification service providing server 300 inputs the motion data collected from the motion collector 100 via the motion scanner 400 as a query to pre-built big data, and identifies the motion from the type of motion data. And, it may be a server that extracts the degree of interest in the product of the customer according to the type and classification of the movement. In addition, the motion identification service providing server 300 may be a server for verifying an error in the extracted interest level by linking the extracted interest level and purchase availability data and relearning big data. In this case, the motion identification service providing server 300 may allow the motion scanner 400 to run the process of classifying motion data, but is not limited thereto, and based on computing resources and networking resources of the motion scanner 400 It may be a server that distributes or allocates running processes.

Here, the motion identification service providing server 300 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like.

The at least one motion scanner 400 receives motion data from the motion collector 100 using a web page, app page, program or application related to a motion identification service for analyzing customer behavior and supply chain management based on artificial intelligence and IoT. It may be a device that collects and transmits it to the motion identification service providing server 300. In this case, the at least one motion scanner 400 may be a device that classifies the collected motion data into an artificial intelligence algorithm when the networking resource and the computing resource satisfy a preset reference value as described above.

Here, the at least one motion scanner 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like. In this case, the at least one motion scanner 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one motion scanner 400, for example, as a wireless communication device that is guaranteed portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) All types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs may be included.

At least one manufacturer server 500 is from the motion identification service providing server 300 using a web page, app page, program or application related to motion identification service for analyzing customer behavior and supply chain management based on artificial intelligence and IoT. It may be a server that collects interest level data and is used for smart factory or logistics or inventory management. Here, the at least one manufacturer server 500 may be a server that adjusts the amount of production and distribution using supply chain management and determines the amount of production, order amount, distribution amount, etc. by predicting demand.

Here, the at least one manufacturer server 500 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like. At this time, the at least one manufacturer server 500 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one manufacturer server 500, for example, as a wireless communication device that is guaranteed portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) All types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs may be included.

2 is a block diagram illustrating a motion identification service providing server included in the system of FIG. 1, and FIG. 3 is a block diagram for analyzing customer behavior and supply chain management based on artificial intelligence and IoT according to an embodiment of the present invention. A diagram for explaining an embodiment in which a motion identification service is implemented.

2, the motion identification service providing server 300 includes a receiving unit 310, a classification unit 320, an extraction unit 330, a generation unit 340, a supply management unit 350, and a big data conversion unit ( 360).

The motion identification service providing server 300 according to an embodiment of the present invention or another server (not shown) operating in conjunction with at least one motion collector 100, at least one motion scanner 400, and at least one When transmitting a motion identification service application, program, app page, web page, etc. for artificial intelligence and IoT-based customer behavior analysis and supply chain management to the manufacturer server 500, at least one motion collector 100, at least one The motion scanner 400, and at least one manufacturer server 500, install or open a motion identification service application, program, app page, web page, etc. for analyzing customer behavior and supply chain management based on artificial intelligence and IoT. I can. In addition, a service program may be driven in at least one motion collector 100, at least one motion scanner 400, and at least one manufacturer server 500 by using a script executed in a web browser. Here, the web browser is a program that enables you to use the web (WWW: world wide web) service, which means a program that receives and displays hypertext described in HTML (hyper text mark-up language). For example, Netscape , Explorer, chrome, etc. In addition, the application refers to an application on the terminal, and includes, for example, an app running on a mobile terminal (smart phone).

Referring to FIG. 2, the receiving unit 310 may receive motion data collected via the motion scanner 400 from at least one motion collector 100 attached to at least one product. In this case, the motion data may vary, such as vector data including the direction and size of the motion, the number of times, the frequency, and the applied impact, but are not limited to those listed. In addition, the motion data may be time-series synchronized data, and may serve as input data capable of grasping a step-by-step behavior and interest or preference of customer behavior analysis using motion data arranged in a time axis.

The classifier 320 may parse the collected motion data to determine and extract a motion event corresponding to at least one motion type, and classify it by deriving an interest level identifier from the motion event. For example, whether there is a movement of the product at the first level, if there is, whether there is movement or only grabbing the product at the second level, and if there is movement, the number or frequency of the product is turned over or moved at the third level. After grasping what happens, frequency, pattern, and direction, it is possible to collect and analyze whether or not worn at the fourth level, walked while wearing, or jumped through the contact sensor. For example, in the case of shoes, if you like them, try wearing them, or walking or running while wearing them. In order to grasp such details, synchronization of a time axis such as a time stamp is required as described above. In this case, a 6-axis motion sensor including three acceleration axes and three gyroscope axes may be used, but the use of a three-axis motion sensor or a motion sensor other than that is not excluded.

The classification unit 320 parses the collected motion data to determine and extract a motion event corresponding to at least one motion type, and when classifying by deriving an identifier of the degree of interest from the motion event, at least one motion type The motion event corresponding to may be an event classified based on at least one or a combination of at least one of the number of times, direction, pattern, applied impact, frequency, period, intensity, and size of the at least one product has been moved. However, it will be obvious that any one is possible if it is not limited to the listed factors and is for grasping motion or motion.

The extraction unit 330 may extract reference data having a preset similarity from big data pre-established in an identifier of the classified interest degree. For example, if the time series data of A-B-C-D is collected as motion data of the "A" product, and as a result of analyzing the time series data of A-B-C-D, you have the interest of group Z (Cluster), the identifier of the classified interest is Z. At this time, if there is a cluster similar to or having the same degree of interest as Z in the big data already constructed with Z, the corresponding cluster is extracted as reference data. Since the reference data has already been established, information such as the reason for the actions of A-B-C-D, patterns, analysis, and interest may be mapped and stored as metadata. Therefore, by entering Z as a query, information on the interest level of Z can be found, and ultimately, the level of interest in the "A" product can be mapped and stored so that it can be used for supply chain management in the future.

As described above, the generation unit 340 may output customer behavior analysis data that is previously mapped to and stored in the extracted reference data to generate customer behavior analysis data regarding a customer's interest in at least one product.

The supply management unit 350 outputs customer behavior analysis data that is previously mapped and stored to the reference data extracted from the generation unit 340, and generates customer behavior analysis data on the customer's interest in at least one product, By inputting customer behavior analysis data into Supply Chain Management, at least one type of sales volume prediction simulation can be driven. One data is not meaningful for calculating statistics, but when these data are collected and calculated as statistics, data that is meaningful for supply chain management can be extracted. In the case of using what size and which product the customer is interested in, and the correlation between the customer behavior analysis data and sales, it can be useful for demand, supply, and inventory management.

For example, by adding a product interest index to information such as production volume by size, product type, organized marketing budget, presence or absence of similar products, the commercial district where the store is located, and the total sales of the previous year/month store, Periodic sales can also be predicted. First, when a product arrives at the store, the motion collector 100 and the motion scanner 400 according to an embodiment of the present invention collect and transmit motion data to collect motion data from the motion identification service providing server 300. To be there. For example, assuming that a customer touches a product as A, when looking upside down or taking a closer look, B, and C when wearing, the measurement of interest is weighted by A, B, and C. It may be possible by differently giving phosphorus X, Y, and Z. That is, when using the correlation between motion data and sales data, X, Y, and Z may be determined from calculating the minimum value of the cost function. Interest is AX + BY + CZ, A, B, and C are set to a value of 0 to 1, and the difference between the calculated interest and the actual sales data is divided into 1 for the case of interest and 0 for the case of not being sold. You can find the weight that minimizes the cost function to minimize. Of course, the above-described method is different from the actual algorithm and is a simplified calculation method for better understanding, and the actual algorithm may be different. When calculating the degree of interest in this way, it is possible to calculate the sales possibility of a product by store, weather, quarter, and size, and update or relearn big data based on the calculated sales possibility. The actual sales and profits are calculated using the sales forecast in the updated big data, and the sales and profits are actually and forecasted using an algorithm aimed at narrowing the gap by comparing sales and profits when all products are sold. You can close the gap between the data. In this way, if the error between the simulated value and the actual value is reduced by using the continuous device, the accuracy of the algorithm may increase with more data as time passes.

In the case of performing error verification and authentication in this way, the error part and the cause of the error in the generated prediction data can be identified, the identified error part and the cause of the error are updated in big data, and then the pattern of the error is discovered and the error rate is classified. In order to predict, deep learning using an artificial neural network can be performed, and the data derived from deep learning can be reflected in big data. Group characteristics can be defined through clustering or pattern analysis, and the relationship between motion data and degree of interest can be grasped through data having conflicting predicted values that do not fit the defined characteristics. The identified data is filtered out when it is refined, and if there is a relationship that gives different motions or erroneous results, the motion data can be filtered. Likewise, such a case can be excluded from raw data, because if the data is mixed and big data is constructed, there is a high probability that an error occurs when the group's characteristics are misaligned or when a query is made. In addition, data types can be classified as follows depending on whether the accumulation of past history is meaningful, and the range of data to be managed or provided can be determined accordingly. Accordingly, motion data can be classified into historical data, previous data, and current data. At this time, for historical data, all historical data recorded in the past are meaningful items, and for previous data, all historical values for the data are not required, but the value of the previous point is meaning. Is an item. Present type data is a data item that has no significant influence on past history information. In other words, it is data that is stored for items whose current value is more important than the data generated at the past time.

The big data conversion unit 360, before receiving the motion data collected via the motion scanner 400 from the at least one motion collector 100 attached to the at least one product at the receiving unit 310, Motion data of at least one motion collector 100 attached to at least one product may be collected from at least one motion scanner 400 located in a store. In addition, the big data conversion unit 360 may store raw data including collected motion data in parallel and distributed, and store unstructured data, structured data, and semi-structured data included in the stored raw data. Semi-structured data can be refined, and pre-processing including classification as meta data can be performed. In addition, the big data conversion unit 360 performs data mining on the preprocessed data, divides it into a training dataset and a test dataset, and performs learning with at least one kind of artificial intelligence algorithm. And build big data learned with at least one kind of artificial intelligence algorithm.

Here, in data mining, classification (Classification), which predicts a class of new data by learning a training data set with a known class by searching for an intrinsic relationship between preprocessed data, or clustering that group data based on similarity without class information ( Clustering). Of course, there may be various other mining methods, and may be mined differently according to the type of big data to be collected and stored or the type of query to be requested later. The big data constructed in this way may be verified through deep learning or machine learning of artificial neural networks. Here, artificial neural network deep learning may be useful when analyzing vector data such as motion data. At this time, at least one artificial intelligence algorithm may include machine learning, and machine learning, supervised learning, semi-supervised learning, unsupervised learning, And reinforcement learning (Reinforcement Learning) may include any one or a combination of at least one.

At this time, the artificial neural network may use a CNN (Convolutional neural network) structure, which is a network structure using a convolutional layer and is suitable for image processing. Because it can. In addition, text mining is a technology that aims to extract and process useful information from non/semi-structured text data based on natural language processing technology. Through text mining technology, meaningful information can be extracted from a vast bundle of texts, linkages with other information can be grasped, and the results can be obtained beyond finding a category of text or simply searching for information. Using this, in the motion identification service according to an embodiment of the present invention, large-capacity language resources and statistical and regular algorithms may be used to analyze an identifier or natural language input as a query and discover hidden information therein. In addition, cluster analysis can be used to finally discover a group of similar characteristics while combining objects with similar characteristics.

Meanwhile, the at least one motion collector 100 may be a device that includes at least one type of motion sensor and detects the motion of at least one product on which the at least one motion collector 100 is mounted. In addition, the motion scanner 400 may be a device that is connected to at least one motion collector 100 through a wired or wireless network and collects at least one product identification code and motion data from the at least one motion collector 100. have. In addition, the at least one motion collector 100 and the motion scanner 400 may be based on the Internet of Things. Here, the motion collector 100 may be composed of an IC chip capable of calculation, a wired or wireless rechargeable power supply, an internal memory, a motion sensor, a Bluetooth capable of wireless communication, NFC, RFID, and the like. Motion sensors can collect and record data on changes in product movement and direction, geomagnetic sensors measure speed and distance, and measure angles of movement, such as speed, direction, and rotation of objects. Can be grasped. In addition, the motion collector 100 may collect information on when and how long it has occurred with a timestamp function, and the recorded information may have a form of raw data or a form in which an identifier is tagged with an artificial intelligence algorithm. Raw data is recorded in the memory, and in the case of the active type, data can be transmitted by itself, and in the case of the passive type, it can be provided in the form of a response (Ack) only when a reading signal exists (Req).

The motion scanner 400 is a component capable of reading or scanning a two-dimensional identification code or a three-dimensional identification code including, for example, an IC chip capable of calculation, a wired/wireless rechargeable power supply, an internal memory, a motion sensor, a barcode or a QR code. Alternatively, it may be a device and a portable device including a wireless communication component or device. The motion scanner 400 may be a device that is interlocked or paired with the motion collector 100 and transmits the collected motion data to the motion identification service providing server 300. For example, it may be similar to a barcode scanner connected to a point of sale (POS). In addition, the motion scanner 400 may independently drive the artificial intelligence algorithm or identify raw data when the networking resource or the computing resource of the motion scanner 400 satisfies a preset condition. . In addition, as a pairing method between the motion scanner 400 and the motion collector 100, a method of reading data by scanning or reading the motion collector 100 through the motion scanner 400 may be used, or the motion collector 100 When) is made of an active element, a method of collecting output signals and data may be used, but is not limited to those described above.

In the fashion market, it is common for product planning, production, and delivery to proceed on a seasonal basis, and it is virtually impossible to predict what will be fashionable after one season in a world where customer demand is constantly changing. However, if designers produce random products based on the subjective judgment of designers, the cost will inevitably increase due to overflowing inventory. Therefore, when using the method according to an embodiment of the present invention instead of predicting a product that will be popular in the future, it is possible to establish a strategy for rapidly producing and supplying products like fast food by tracking trends of products sold at a current popularity. In addition, in the case of a transnational group, it is possible to build an optimal inventory distribution system that can maximize profits by analyzing big data on sales and inventory in stores around the world in real time. After analyzing data in real time to understand customer demand, it becomes possible to produce products that customers want. Rather than displaying and selling planned products in the second or first quarter, it will be possible to launch and display in each store based on real-time analysis of popular products by utilizing big data analysis on store inventory and sales. .

Hereinafter, an operation process according to the configuration of the motion identification service providing server of FIG. 2 will be described in detail with reference to FIG. 3 as an example. However, it will be apparent that the embodiment is only any one of various embodiments of the present invention, and is not limited thereto.

Referring to FIG. 3A, (a) the motion identification service providing server 300 collects motion data collected from the motion collector 100 through the motion scanner 400, and (b) data preprocessing, analysis, and event classification Through the process, satisfaction is calculated, and errors or errors are verified by comparing the satisfaction with previously stored big data. In addition, it is transmitted to the manufacturer server 500 as shown in FIG. 3B so that it can be used in the system of supply chain management. For example, the motion identification service providing server 300 may provide a user interface to a terminal such as a manufacturer server 500 or a POS of each store, and may provide a scenario capable of outputting data tailored to the user's needs. . For example, through the product code, men's shoes that have been worn in all stores over the past 24 hours can be listed based on the number of times they are worn. Or search for all product movements that took place the previous day in a store. The user interface may have differences in presentation methods and graphics depending on the needs of the company and department to use.

For details that are not explained about the method of providing motion identification services for artificial intelligence and IoT-based customer behavior analysis and supply chain management of Figs. 2 and 3, artificial intelligence and IoT-based customer behavior analysis and The description of the method for providing a motion identification service for supply chain management will be omitted since it is the same as the description or can be easily inferred from the description.

FIG. 4 is a diagram showing a process in which data is transmitted and received between components included in the motion identification service providing system for artificial intelligence and IoT-based customer behavior analysis and supply chain management of FIG. 1 according to an embodiment of the present invention to be. Hereinafter, an example of a process in which data is transmitted/received between components will be described with reference to FIG. 4, but the present application is not limitedly interpreted as such an embodiment. It is obvious to those skilled in the art that the process of transmitting and receiving data may be changed.

Referring to FIG. 4, the motion identification service providing server 300 collects motion data and sales data generated in at least one store, performs preprocessing (S4100), and uses data analysis and artificial intelligence algorithms to provide big data. Modeling is performed to generate output data for the query input afterwards by constructing. Among at least one artificial intelligence algorithm, modeling may be performed using an algorithm with high predictability and no errors, but the use of multiple artificial intelligence algorithms together or in combination is not excluded.

At this time, the motion identification service providing server 300, when the motion collector 100 and the motion scanner 400 are interlocked to collect motion data (S4300 to S4500), parses the motion data and extracts an identifier (S4600), By creating a query with an identifier (S4610), extracting an event for a similar motion that is an answer to the query (S4630), classifying motion data (S4700), and calculating the degree of interest (S4800) to perform statistical processing. (S4900). At this time, the correlation between the calculated interest and the actually sold data can be calculated as a function to extract errors or perform further verification, and after verification is completed, the big data is updated and retraining is performed to further lower errors. May be. Then, the statistically processed data is transmitted to at least one manufacturer server 500 so that the manufacturer server 500 can reconstruct or visualize desired data to be used (S4920).

The order between the above-described steps S4100 to S4920 is only an example and is not limited thereto. That is, the order of the above-described steps (S4100 to S4920) may be mutually changed, and some of the steps may be executed or deleted at the same time.

For the unexplained matters that are not described about the method of providing motion identification services for the analysis of artificial intelligence and IoT-based customer behavior and supply chain management of FIG. 4, the analysis of artificial intelligence and IoT-based customer behavior and The description of the method for providing a motion identification service for supply chain management will be omitted since it is the same as the description or can be easily inferred from the description.

5 is a flowchart illustrating a method of providing a motion identification service for analysis of customer behavior and supply chain management based on artificial intelligence and IoT according to an embodiment of the present invention. Referring to FIG. 5, the motion identification service providing server receives motion data collected via a motion scanner from at least one motion collector attached to at least one product (S5100).

Then, the motion identification service providing server determines and extracts a motion event corresponding to at least one motion type by parsing the collected motion data, and classifies and derives an interest level identifier from the motion event (S5200).

In addition, the motion identification service providing server extracts reference data having a preset similarity from big data previously established in the classified interest level identifier (S5300), and outputs customer behavior analysis data previously mapped to the extracted reference data and stored. Thus, customer behavior analysis data on the customer's interest in at least one product is generated (S5400).

For the unexplained matters that are not explained about the method of providing motion identification services for the analysis of artificial intelligence and IoT-based customer behavior and supply chain management of FIG. 5, the analysis of artificial intelligence and IoT-based customer behavior and The description of the method for providing a motion identification service for supply chain management will be omitted since it is the same as the description or can be easily inferred from the description.

The method of providing motion identification service for analysis of customer behavior and supply chain management based on artificial intelligence and IoT according to an embodiment described with reference to FIG. 5 is an instruction executable by a computer such as an application or program module executed by a computer. It may be implemented in the form of a recording medium including a. Computer-readable media can be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Further, the computer-readable medium may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The above-described method for providing motion identification service for artificial intelligence and IoT-based customer behavior analysis and supply chain management according to an embodiment of the present invention includes an application basically installed on a terminal (this is a platform or operating system basically installed on the terminal, etc.). It can be executed by an application (that is, a program) directly installed on the master terminal through an application providing server such as an application store server, an application, or a web server related to the service. It can also be executed. In this sense, the method for providing motion identification service for artificial intelligence and IoT-based customer behavior analysis and supply chain management according to an embodiment of the present invention described above is basically an application installed in a terminal or directly installed by a user (i.e., Program) and recorded on a computer-readable recording medium such as a terminal.

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that other specific forms can be easily modified without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative and non-limiting in all respects. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

The embodiments for the implementation of the invention have been described together in the best mode for the implementation of the above invention.

The present invention relates to a method of providing motion identification services for analysis of customer behavior and supply chain management based on artificial intelligence and IoT. By measuring the movement of the customer and inputting it as a query to the previously established big data, analyzing the customer's behavior, deriving the degree of interest, and comparing the result of the previously established big data by checking whether or not the degree of interest leads to sales. And errors are verified, and a balance between supply and demand can be achieved within the supply chain management system. Ultimately, all resources can be optimized based on real-time data, and cost reduction and production efficiency can be achieved. have.

Claims

In the motion identification service providing method executed in the motion identification service providing server,

Receiving motion data collected via a motion scanner from at least one motion collector attached to the at least one product;

Parsing the collected motion data to determine and extract a motion event corresponding to at least one motion type, and deriving and classifying an interest level identifier from the motion event;

Extracting reference data having a preset similarity from big data pre-established in the classified interest level identifier; And

Generating customer behavior analysis data on a customer's interest in the at least one product by outputting customer behavior analysis data previously mapped to the extracted reference data and stored;

A method of providing motion identification services for analysis of customer behavior and supply chain management based on artificial intelligence and IoT, including a.
The method of claim 1,

After the step of generating customer behavior analysis data on the customer's interest in the at least one product by outputting the customer behavior analysis data previously mapped and stored in the extracted reference data,

Inputting the customer behavior analysis data to supply chain management and driving at least one type of sales volume prediction simulation;

That further comprises a motion identification service providing method for artificial intelligence and IoT-based customer behavior analysis and supply chain management.
The method of claim 1,

The at least one motion collector,

A device that detects the motion of at least one product equipped with the at least one motion collector, including at least one kind of motion sensor, and motion identification for customer behavior analysis and supply chain management based on artificial intelligence and IoT How to provide the service.
The method of claim 1,

The motion scanner,

It is a device that is connected to the at least one motion collector through a wired or wireless network and collects the identification code and motion data of the at least one product from the at least one motion collector, artificial intelligence and IoT-based customer behavior analysis and A method of providing motion identification services for supply chain management.
The method of claim 1,

Prior to the step of receiving motion data collected via a motion scanner from at least one motion collector attached to the at least one product,

Collecting motion data of at least one motion collector attached to at least one product from at least one motion scanner located in at least one store;

Storing raw data including the collected motion data in parallel and distributed;

Refining unstructured data, structured data, and semi-structured data included in the stored raw data, and performing pre-processing including classification as metadata;

Performing data mining on the preprocessed data, dividing it into a training dataset and a test dataset, and performing learning using at least one kind of artificial intelligence algorithm;

Building big data learned by the at least one kind of artificial intelligence algorithm;

That further comprises a motion identification service providing method for artificial intelligence and IoT-based customer behavior analysis and supply chain management.
The method of claim 5,

In the data mining, classification (Classification) for predicting a class of new data by learning a training data set with a known class by searching for an intrinsic relationship between the preprocessed data, or clustering that group data based on similarity without class information ( Clustering), artificial intelligence and IoT-based customer behavior analysis and a method of providing a motion identification service for supply chain management.
The method of claim 5,

The at least one artificial intelligence algorithm includes machine learning,

The machine learning includes any one or a combination of at least one of supervised learning, semi-supervised learning, unsupervised learning, and reinforcement learning. , A method of providing motion identification services for analysis of customer behavior and supply chain management based on artificial intelligence and IoT.
The method of claim 1,

In the step of parsing the collected motion data to determine and extract motion events corresponding to at least one motion type, and deriving and classifying an interest level identifier from the motion event,

The motion event corresponding to the at least one movement type is classified based on at least one or at least one combination of the number, direction, pattern, applied impact, frequency, period, intensity, and size of the at least one product movement. A method of providing motion identification services for analysis of customer behavior and supply chain management based on artificial intelligence and IoT, which is an event that has been completed
The method of claim 1,

The at least one motion collector and the motion scanner are based on the Internet of Things, artificial intelligence and IoT-based motion identification service providing method for customer behavior analysis and supply chain management.
A computer-readable recording medium on which a program for executing the method of any one of claims 1 to 9 is recorded.