KR101768637B1 - Data consignment sales and profit sharing system - Google Patents

Abstract

The present invention provides a data consignment sales and profit distribution system. A data provider automatically transmits behavior log data such as search, click, and payment in an online store using a smartphone and behavior log data such as visit to an offline store and payment in an offline store to a server through an application installed in the smartphone. When a data consumer purchases interesting data through payment, the server provides a payment amount, excluding a predetermined fee, to accounts of providers, and then, processes the purchased data to provide a visualizing service to indicate which store customers purchase data among online and offline stores depending on environmental conditions of the stores. Moreover, if the data consumer inputs a purchase condition, the system calculates the value of data corresponding to the condition through machine learning, and provides a service to predict a purchase correlation of future prediction data, which the data consumer wants to purchase, through machine-learning.

Description

DATA CONSIGNMENT SALES AND PROFIT SHARING SYSTEM [0002]

The present invention relates to a data commission sales and profit distribution system, and more particularly, to a data supplier, which supplies data using various sensors of a smart phone or a store, and when a data requester purchasing the data supplies the data, And to a data commission sales and profit distribution system that distributes revenue to data providers.

Corporate marketers want to know exactly what their marketing strategy is and how they are responding to the product they release according to their marketing strategy.

According to the traditional method, in order to know the customer's reaction to the products that are being sold in the online or offline store, the sales data for each store is collected and reflected in the statistical system to execute the analysis program or the developer can change the source of the analysis program And then the analysis program was executed after the modification. According to this method, it takes a long time to collect data as well as it is difficult to give statistics on live sales data on site due to the time taken to collect data. Also, There is a difficult problem.

In addition, even if the customer purchases the product due to advertisement, promotion, etc., the customer can not know whether he / she will come back to the store or not, and even if he / she does marketing, it is ended as a one-time event.

If you are running an online store and an offline store simultaneously, you can use real-time information for showrooming (online shopping at the lowest price after comparing products at an offline store), reverse showrooming (online comparison after shopping at an online store) There is a difficult problem to analyze.

Furthermore, to build and operate a CRM (Customer Relationship Management) system for collecting and analyzing marketing data, a lot of money is needed for data extraction, refining, DW (data warehousing) and analysis from the Legacy System, It is also opaque.

The present invention intends to propose a business structure that benefits both the supplier supplying data that can be utilized for marketing and the data consumer purchasing the same by dramatically improving the conventional marketing method.

Published Japanese Patent Application No. 10-2015-0090376 Published Japanese Patent Application No. 10-2015-0039657 Registration No. 10-1635090

SUMMARY OF THE INVENTION The present invention has been made to solve the problems of the prior art described above, and it is an object of the present invention to provide a data provider, in which an act log data such as search, click, payment at an online store using a smart phone, The log data is automatically transmitted to the server using the application installed on the smartphone. When the data consumer purchases the data of interest by the server, the server transmits the amount of the payment, excluding the predetermined fee, to the account of the data provider And a data commission sales and profit distribution system that provides the visualized service to the data consumer by processing the purchased data so that the customers can know where to buy in the online or offline store according to the environmental condition of the store. There is a purpose of.

It is another object of the present invention to provide a data commission sales and profit distribution system capable of calculating the value of data corresponding to a condition by machine learning by inputting a condition that a data consumer desires to purchase.

Furthermore, it is an object of the present invention to provide a data commission sales and profit distribution system which can provide services by predicting the purchase correlation through machine learning of future prediction data that a data consumer desires to purchase.

In order to achieve the above object, the data commission sales and profit distribution system of the present invention collects activity log data of a data provider in an online store, behavior log data of a data provider visiting an offline store, and environment data from various sensors installed in a store ; A big data storage unit for storing a large amount of data by processing log data and environment data collected by the data collection unit in real time and applying an optimized distributed storage module; A value of data corresponding to a period in which a data consumer desires to purchase is calculated by a machine learning method using online and offline activity log data of the data provider stored in the big data storage unit and environment data collected from the sensor A value calculation model generation unit for generating a data value calculation model that can be used for the data calculation; A data value calculation module for calculating a data value from a first time point to a second time point by using the data value calculation model and providing the calculated data value to a data consumer, A data sales unit for making a payment by the data consumer to an account of the data provider, excluding the predetermined fee, upon payment; And a data service unit for processing data corresponding to a period in which the data consumer desires to purchase data in the big data storage unit and providing the data as a visualized service when payment is made in the data sales unit.

The data value calculation model is characterized in that the value of the data is set to be lower as the data is older and the value of the future data is set higher.

The activity log data of the data provider in the online store includes a search activity and a settlement activity. The activity log data of the data provider that visited the offline store includes store visit and payment activities. And the data value calculation model is characterized in that a search action, a payment action, and a visit to a store are set to have a higher weight than a temperature and humidity of a store.

The data value calculation model is characterized in that the data value is calculated using a period between a first time point and a second time point when the data consumer desires to purchase, an area where the offline stores are located, and age information of the data provider.

The data value calculation model is characterized in that the longer the period from the first time point to the second time point, the higher the value of data as the number of the population of the area where the offline store is located is calculated.

The activity log data of the data provider in the online store and the behavior log data and the environment data of the data provider who visited the offline store in the corresponding period from the first time point to the second time point are analyzed and classified according to the area, And a data analyzer for analyzing whether the data provider purchases the online store or the offline store, and the data service unit provides the visualized service with the analysis result of the data analyzer.

The activity data of the data provider in the online store and the activity log data of the data provider visiting the offline store, which are stored in the big data storage unit in real time, A data streaming processing unit for analyzing the data stream in real time; And a data streaming service unit for displaying an action change of the current customers with the processing result of the data streaming processing unit as an animation.

Wherein the big data storage unit stores climate data generated and provided by a public institution, and uses the online and offline activity log data of the data provider stored in the big data storage unit and the environmental data collected from the sensor, A purchase prediction model generation unit for generating a purchase prediction model capable of predicting whether a data supplier performs a purchase action in an online store or an offline store according to an environmental factor of the store; And when a future purchase prediction request is input from the data consumer, the big data storage unit searches for the corresponding climatic data in the big data storage unit, and the retrieved climate data is applied to the purchase prediction model, And a purchase prediction service unit for predicting where the purchase is performed in the offline store.

The purchase prediction service unit receives one or more pieces of information of the age and gender of a customer who desires a purchase prediction from a data consumer and applies the purchase information to the purchase prediction model, And predicts and provides a purchase action in the shop.

And an activity index calculating unit operable to calculate an activity index in on-line and off-line using the activity log data of the data provider, wherein the data selling unit differs the data provider's account according to the activity index of the data provider do.

According to the data commission sales and profit distribution system according to the present invention, a data provider installs an app on its own smart phone, obtains revenue by providing data as an online and offline store activity, The information on purchasing behavior using the information on product marketing can be used as a basis for data sharing economy.

Data consumers are provided with forecasting analysis service for purchasing activities by machine learning, so that decision making and marketing strategy can be established in the future.

By calculating the value of data that a data consumer desires to purchase by machine learning, it is possible to measure more precisely the value by taking into consideration various variables rather than a uniform value calculation.

Furthermore, by providing various visualization services to data consumers, they can intuitively recognize and can help in marketing decision making.

1 is a service exemplary view of a data commission sales and revenue distribution system according to the present invention;
2 is a block diagram of a data commission sales and revenue distribution system according to the present invention;

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention, and how to accomplish them, will become apparent by reference to the embodiments described in detail below with reference to the accompanying drawings.

However, the present invention is not limited to the embodiments described below, but may be embodied in various other forms.

The present embodiments are provided so that the disclosure of the present invention is thoroughly disclosed and that those skilled in the art will fully understand the scope of the present invention.

And the present invention is only defined by the scope of the claims.

Thus, in some embodiments, well known components, well known operations, and well-known techniques are not specifically described to avoid an undesirable interpretation of the present invention.

In addition, throughout the specification, like reference numerals refer to like elements, and the terms (mentioned) used herein are intended to illustrate the embodiments and not to limit the invention.

In this specification, the singular forms include plural forms unless the context clearly dictates otherwise, and the constituents and acts referred to as " comprising (or comprising) " do not exclude the presence or addition of one or more other constituents and actions .

Unless defined otherwise, all terms (including technical and scientific terms) used herein may be used in a sense commonly understood by one of ordinary skill in the art to which this invention belongs.

Also, commonly used predefined terms are not ideally or excessively interpreted unless they are defined.

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

1 and 2, a data commission sales and profit distribution system 100 according to the present invention includes a data collecting unit 110, a big data storing unit 120, a value calculating model generating unit 130, A data streaming processing unit 170, a data streaming service unit 180, a purchase prediction model generating unit 190, a purchase forecasting service unit 140, and a data service unit 150. The data analysis unit 160, the data streaming processing unit 170, 200 and an activity index calculating unit 210. [

The data collection unit 110 collects activity log data of the data provider in the online store, activity log data of the data provider who visited the offline store, and environmental data from various sensors installed in the store.

For example, the activity log data of the data provider in the online store refers to the data provider's click, search, and settlement behavior in the online store of the A brand, and the activity log data of the data provider visiting the offline store is A A visit to a brand offline store, and a settlement in an offline store. Of course, the smartphone 10 of the data provider who desires to use the service must install the app after agreeing to provide his / her action information to the system 100 about search, click, .

The A-brand offline store is provided with a sensor module 20 for collecting various environmental data in a store in a kiosk or other equipment and transmitting the collected environmental data to the system 100. Various sensor modules 20 for collecting the overall data of the store environment can be integrated and installed in the Raspberry Pi. The sensor may include various sensors such as a temperature sensor, a humidity sensor, an illuminance sensor, a noise sensor, a beacon sensor, an infrared sensor, and an ultrasonic sensor. These sensors will be able to be installed by the company that operates the system in consultation with the store, and the data to be collected by the sensor is an environmental factor such as how pleasantly the A-brand store is, and the noise.

It is the collection of environmental data, since visitors to a store are likely to be affected by environmental factors to make purchases in an A-brand offline store. For example, if an A-brand in-store is pleasant, it will be long in-store and can be purchased directly, but if the A-brand in-store is loud and cold, it will eventually go home and buy it at the A-brand online store.

When it is confirmed that the app installed in the smartphone 10 of the data provider has visited the store by communicating with the beacon sensor of the store, the app of the smartphone 10 is transferred to the system 100 by the customer A And visits the brand offline store. In the case of searching and clicking on the A brand online store, the application installed in the smartphone 10 is executed in the background, and the online transaction log data of the customer is transmitted to the system 100 side.

The big data storage unit 120 processes the log data and the environment data collected by the data collecting unit 110 in real time, and stores a large amount of data by applying an optimized distributed storage module.

The big data storage unit 120 processes the collected log data in real time and stores a large amount of data at a high speed by applying a distributed storage module optimized for each data type and repetition pattern. The big data storage unit 120 stores atypical / large capacity data including online collected data and offline data, which is store data, at high speed in real time based on the Hadoop system.

The value calculation model generation unit 130 generates the value calculation model 130 by using the online and offline activity log data of the data provider stored in the big data storage unit 120 and the environment data collected from the sensor 20 of the store, A data value calculation model that can calculate the value of data corresponding to a period in which a consumer desires to purchase is created.

The value calculation model generation unit 130 can generate a data value calculation model using a machine learning method such as classification and regression tree analysis, Bayesian network and SVM.

Specifically, the data value calculation model is modeled to lower the value of data as time goes by, and to set the value of future data high. For example, if one week passes, it is halved, and after one month it drops to 25%. Data over a year old is dropped to 5%.

The data value calculation model is modeled to set the weight of the click activity, the search activity, the settlement activity, and the store visit higher than the environmental data such as the temperature, humidity, roughness, and noise of the store. For example, if the log data of clicks, searches, and store visits are set to a weight of 1, and the settlement log data of an online or offline store is set to a weight of 2, the temperature and humidity corresponding to store environmental data The weight can be set to 0.5, the illuminance and the noise to 0.2.

The data value calculation model calculates the value of the data using the period between the first point of time and the second point of time when the data consumer desires to purchase, the area where the offline store is located, and the age information of the data provider. The longer the period between the first and second points of view, the greater the population of the location where the store is located, and the greater the age at which purchasing is active, the higher the value of the data. For example, if a data consumer wants to buy 30 data from Seoul during the period from June to August corresponding to last summer, data prices will be high.

Conversely, the data value calculation model is modeled such that the shorter the period from the first point of view to the second point of view, and the lower the value of the data as the population of the area where the offline store is located is smaller. Last summer, the price of data for stores in Myeongdong area in Seoul will be much higher than the price of data for stores in Yongin area in Gyeonggi province last summer. This is because data in Seoul's Myeongdong area is highly valued in terms of companies that are data consumers.

In summary, the algorithm applied to the data value computation model will reflect Equation 1:

Data value = (intrinsic value of data corresponding to click, search, settlement, location and environment data of data provider + data processing value corresponding to age, store location, data collection period of data provider) - (Equation 1)

When the data sales unit 140 receives a desired period of data purchase from the data consumer from the first time point to the second time point, the data sales unit 140 calculates the data value from the first time point to the second time point using the data value calculation model, And the data consumer pays the amount of the data provider's account excluding the predetermined fee at the time of payment. Of course, the account information of the registered data provider will be stored in the big data.

The data service unit 150 processes data corresponding to a period in which the data consumer desires to purchase data in the big data storage unit 120 when payment is made in the data sales unit 140, and provides the processed data as a visualized service. Referring to FIG. 1, the data visualization service screen 30 is an example of a service screen provided by a data consumer as a basis for condition search. The visualization service will be provided to the smartphone or PC of the data consumer.

When payment is made in the data sales department 140, the data analysis unit 160 reads the activity log data of the data provider in the online store during the corresponding period from the first time point to the second time point, Analyze log data and environmental data to analyze where data providers are purchasing, either online or offline, depending on region, age, and environmental factors. The data service unit 150 provides the visualized service with the analysis result of the data analysis unit 160. [ This service is to provide the data obtained by querying the big data with the condition search formula of the data consumer who wants to purchase as a visualized service. This is the most basic service.

The data streaming processing unit 170 reads the activity log data of the data provider in the online store and the activity log data of the data provider that visited the offline store, which are stored in real time in the big data storage unit 120, Or in-store shops.

The data streaming service unit 180 animates the behavior changes of the current customers with the processing result of the data streaming processing unit 170. [ This service is to show live data on-site. Referring to FIG. 1, a data streaming service screen 40 displays a screen in which a human-shaped animation moves by region. In other words, it shows how people are buying in what area.

The big data storage unit 120 stores climate data generated and provided by a public authority. Generally, public agencies generate and provide climate data to those in need. And to store and utilize the climate prediction data for next year downloaded from a public institution in the big data storage unit 120. [

The purchase prediction model generation unit 190 generates a purchase prediction model by using the online and offline activity log data of the data provider stored in the big data storage unit 120 and the environmental data collected from the sensor, Create a purchase forecasting model that can predict where a data provider will buy from an online store or an offline store.

The purchase prediction model generation unit 190 can generate a purchase prediction model using a machine learning method such as a classification and regression tree analysis, a Bayesian network, and a support vector machine (SVM).

For example, if A-brand stores in Seoul's Myeong-dong area are comfortable in the summer, customers tend to be more likely to buy in-store stores. If A-brand stores are somewhat hot and crowded, The tendency to make purchases in online stores rather than in stores will be highly predicted.

The purchase prediction service unit 200 searches the big data storage unit 120 for climate data at a corresponding point in time when a future purchase prediction request is input from a data consumer and applies the retrieved climate data to the purchase prediction model At that point in time, we anticipate and provide customers where they will be purchasing online or in-store.

Specifically, the purchase prediction service unit 200 receives one or more pieces of information of the age and gender of a customer who desires to purchase prediction from a data consumer, applies it to the purchase prediction model, In the online store or in the offline store.

For example, if a data consumer receives information from a 50-year-old woman, Seoul Gangnam area, and so on next spring, she applies the forecast data to the forecasting model, It will show you what kind of purchasing you see in your offline store.

In addition, when data from a data consumer is input in the spring of next year, 20's female, Seoul Gangnam area, etc., Which will show you what kind of purchase you are looking for. Of course, the results of buying predictions for 20s and 50s may be different. Referring to FIG. 1, the data purchase forecast service screen 50 shows a future purchase prediction result corresponding to a time point desired by the data consumer.

The activity index calculating unit 210 calculates the activity indexes on-line and off-line using the activity log data of the data provider. The data sales unit 140 will pay the account of the data provider differently according to the activity index of the data supplier. For example, even for data providers subscribed to the service at the same time, more revenue will be allocated to those who have a lot of activities such as online store search, click, payment, offline store visit, and settlement.

According to the present invention, a data provider installs an app on its own smartphone, obtains revenue by providing data as an activity in online and offline stores, and a data consumer acquires purchase behavior information using actual customer behavior data in product marketing This will enable us to lay the foundations for a data-sharing economy.

In addition, data consumers are provided with forecasting analysis services for purchasing activities by machine learning, so that it is possible to establish corporate decision making and marketing strategies in the future.

It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims and their equivalents. Obviously, such modifications are intended to be within the scope of the claims.

10: Smartphone
20: Sensor
30: Data visualization service screen
40: Data streaming service screen
50: Data purchase prediction service screen
100: Data Consignment Sales and Revenue Distribution System
110: Data collecting unit
120: Big data storage unit
130: Value calculation model generation unit
140: Data Sales Department
150: Data service department
160: Data analysis section
170: Data streaming processor
180: Data streaming service section
190: purchase prediction model generation unit
200: Purchase Forecast Service Department
210: activity index calculating section

Claims (10)

A data collecting unit collecting the activity log data of the data provider in the online store, the behavior log data of the data provider visiting the offline store, and environmental data from various sensors installed in the store;
A big data storage unit for processing log data and environment data collected by the data collection unit in real time and storing a large amount of data by applying a distributed storage module;
A value of data corresponding to a period in which a data consumer desires to purchase is calculated by a machine learning method using online and offline activity log data of the data provider stored in the big data storage unit and environment data collected from the sensor A value calculation model generation unit for generating a data value calculation model that can be used for the data calculation;
A data value calculation module for calculating a data value from a first time point to a second time point by using the data value calculation model and providing the calculated data value to a data consumer, A data sales unit for making a payment by the data consumer to an account of the data provider, excluding the predetermined fee, upon payment; And
And a data service unit for processing data corresponding to a period in which the data consumer desires to purchase data in the big data storage unit and providing the data as a visualized service when payment is made in the data sales unit,
The activity log data of the data provider in the online store includes a search activity and a settlement activity. The activity log data of the data provider that visited the offline store includes store visit and payment activities. Temperature, humidity, illuminance, noise,
The data value calculation model calculates the value of data using the following equation,
Data value = (intrinsic value of data corresponding to data provider's click, search, settlement, location and environmental data + data processing value corresponding to age, store location and data collection period of data provider)
Among the inherent values of the data, the payment transaction log data at the online or offline store of the data provider has the largest weight. Next, the click and search activity log data on the online and the location log data corresponding to the store visit activity are weighted And the weighting of temperature, humidity, illumination, and noise corresponding to the environmental data of the store is minimized and modeled.
The method according to claim 1,
Wherein the data value calculation model lowers the value of the data as the data is older and sets the value of the future data as a higher value.
delete The method according to claim 1,
Wherein the data value calculation model calculates a value of data using a period between a first time point and a second time point when the data consumer desires to purchase, an area where the offline store is located, and age information of the data provider, And revenue sharing system.
5. The method of claim 4,
Wherein the data value calculation model calculates the value of the data as the longer the period between the first time point and the second time point, the higher the number of the population of the area in which the offline store is located, the higher the value of the data.
The method according to claim 1,
The activity log data of the data provider in the online store and the behavior log data and the environment data of the data provider who visited the offline store in the corresponding period from the first time point to the second time point are analyzed and classified according to the area, Further comprising a data analyzer for analyzing whether the data provider is purchasing in an online store or an offline store,
Wherein the data service unit provides the visualized service with the analysis result of the data analysis unit.
The method according to claim 1,
The activity data of the data provider in the online store and the activity log data of the data provider visiting the offline store, which are stored in the big data storage unit in real time, A data streaming processing unit for analyzing the data stream in real time; And
Further comprising a data streaming service unit for displaying an action change of current customers with an animation by the processing result of the data streaming processing unit.
The method according to claim 1,
The big data storage unit stores climate data generated and provided by a public authority,
The data provider may store the online or offline activity log data of the data provider stored in the big data storage unit and the environment data collected from the sensor, A purchase prediction model generation unit for generating a purchase prediction model predictable for purchasing behavior; And
When receiving a future purchase prediction request from a data consumer, searching the big data storage unit for the corresponding climatic data and applying the retrieved climate data to the purchase prediction model, Further comprising a purchase prediction service unit that predicts and provides a purchase behavior in the store.
9. The method of claim 8,
The purchase prediction service unit receives one or more pieces of information of the age and gender of a customer who desires a purchase prediction from a data consumer and applies the purchase information to the purchase prediction model, Wherein the data providing system predicts and provides the purchase behavior in the store.
The method according to claim 1,
And an activity index calculating unit for calculating an activity index on-line and off-line using the activity log data of the data provider,
Wherein the data sales unit differentially pays the account of the data provider according to an activity index of the data supplier.

Images