KR20220081019A - System for predicting sale of merchandise by using parcel delivery service information - Google Patents

Abstract

The present invention provides an e-commerce server 110 that generates order information and courier transportation information by performing e-commerce, and performs inventory management on behalf of logistics services according to order information and courier transportation information, and product category from order information Internal data of sales status by region, sales status by region, return status, and sales status by company are extracted and generated, and the delivery status of courier companies, production status of manufacturers, export/import performance by product, sales data by product, consumption data by age, and consumption by period are generated from the delivery information. Fulfillment server 120, which extracts and generates external data of consumption propensity and SNS trend by propensity and weather, stores internal data and external data to build a data warehouse for pre-processing, A sales volume prediction unit 130, and a sales volume prediction unit 130 that analyze the correlation between weather and SNS trend variables and product sales to derive product sales forecast values for each region, product, age, period, weather, and SNS trend ), including the display unit 140 that processes and visualizes the product sales forecast value derived by A prediction system is disclosed.

Description

Sales forecasting system using courier transportation information {SYSTEM FOR PREDICTING SALE OF MERCHANDISE BY USING PARCEL DELIVERY SERVICE INFORMATION}

The present invention relates to a sales prediction system using parcel delivery information that can minimize malicious inventory by using parcel delivery information corresponding to invoice information as basic information and predicting sales by region, product, and period through an analysis algorithm. .

As is well known, inventory management is a very important factor in the e-commerce of small quantity sales of multiple products. In the fulfillment system, if the storage period is long, continuous storage costs occur. There are aspects that are difficult to maintain.

In addition, it is often the case that inventory is incinerated or stored for a long time in a warehouse despite fixed costs to observe the time of sale. In other words, inventory is discarded to enhance brand value, but not resold to inventory purchasers.

Accordingly, the occurrence of embodied stock is inevitable, and thus costs are inevitably incurred even when incineration of embodied stock or long-term storage in a warehouse.

Therefore, there is a need for a technology capable of reducing costs due to malicious inventory by minimizing the occurrence of consolidation inventory by building a forecasting system that can accurately perform demand forecasting, that is, sales forecasting for a product.

Korean Patent Publication No. 10-1872223 (Internet-based sales forecast information providing device, 2018.08.02) Korean Patent Publication No. 10-2077279 (Logistics management system operation method, 2020.02.13)

The technical task to be achieved by the spirit of the present invention is that it is possible to minimize malicious inventory by using courier transportation information corresponding to invoice information as basic information and predicting sales by region, product and period through an analysis algorithm. To provide a sales forecasting system using

In order to achieve the above object, the present invention provides an e-commerce server that generates order information and courier delivery information by performing an electronic commerce transaction; In accordance with the order information from the e-commerce server and the courier delivery information, inventory management is integrated by acting on behalf of the logistics service of warehousing, storage, packaging, shipment, and return of goods, and the sales status by product category from the order information Internal data of sales status by region, return status, and sales status by company are extracted and generated, and from the above courier delivery information, delivery status of courier companies, production status of manufacturers, import/export performance by product, sales data by product, consumption data by age, consumption propensity and weather by period A fulfillment server that extracts and generates external data of each consumption propensity and SNS trend; By storing the internal data and the external data, a data warehouse is built and pre-processed, and the correlation between region, product, age, period, weather, SNS trend variables, and product sales is analyzed by region, product, age, and period. and a sales volume prediction unit that derives product sales forecast values for each weather and SNS trend; and a display unit that processes and visualizes the product sales forecast value derived by the sales volume prediction unit; including, using courier transportation information corresponding to invoice information to predict sales by region, product and period, using courier transportation information It provides a sales forecasting system.

Here, the sales volume predicting unit may derive a valid variable of the analyzed correlation and apply an analysis algorithm to derive the product sales forecast value.

In addition, time series analysis, regression analysis, or random forest may be applied to the analysis algorithm.

In addition, the sales volume prediction unit, the total or province-by-year sales volume trend analysis, product sourcing ratio analysis to sales volume, sales volume decrease over the past 3 years, sales volume by region, product sourcing status by product category, and product category It is possible to derive the purchase status, the purchase status by region, the status by age and income, the purchase trend by product category, and the predicted product sales volume of the purchase trend in a specific region.

In addition, the courier delivery information may include invoice information, delivery address, product, and quantity.

According to the present invention, it is possible to minimize malicious inventory by using the parcel delivery information corresponding to the invoice information as basic information and predicting the sales by region, product, and period through an analysis algorithm.

1 shows a schematic configuration diagram of a sales prediction system using parcel delivery information according to an embodiment of the present invention.
2 is an example of the display of the predicted product sales volume by the display unit of the sales prediction system using the parcel delivery information of FIG. 1, respectively.

Advantages and features of the present invention, and a method of achieving them, will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in a variety of different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the technical field to which the present invention belongs It is provided to fully inform the possessor of the scope of the invention, and the present invention is only defined by the scope of the claims.

With reference to the accompanying drawings will be described in detail for the implementation of the present invention. Irrespective of the drawings, like reference numbers refer to like elements, and "and/or" includes each and every combination of one or more of the recited items.

The terminology used herein is for the purpose of describing the embodiments, and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components.

Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used with the meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless clearly defined in particular.

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

The sales prediction system using courier transportation information according to an embodiment of the present invention performs an e-commerce transaction to generate order information and parcel transportation information, the e-commerce server 110, and provides logistics services according to order information and parcel transportation information to integrate inventory management, extract and create internal data of sales status by product category, region, return status, and sales status by company from order information Fulfillment server 120 that extracts and generates external data of import and export performance, sales data by product, consumption data by age, consumption propensity by period, consumption propensity by weather, and SNS trend, and stores internal data and external data to create a data warehouse Construct and pre-process, and analyze the correlation between region, product, age, period, weather, SNS trend variables, and product sales to derive product sales forecasts by region, product, age, period, weather, and SNS trend, The sales volume prediction unit 130, and the display unit 140 that processes and visualizes the product sales forecast value derived by the sales volume prediction unit 130, using the parcel delivery information corresponding to the invoice information, and by region and product The main point is to forecast sales by period.

Hereinafter, with reference to FIGS. 1 and 2 , the configuration of the sales prediction system using the above-described courier transportation information will be described in detail.

First, the e-commerce server (electronic commerce server) 110 is composed of a plurality of each performs an e-commerce, generates order information and courier delivery information for the sale product, and transmits it to the fulfillment server (120).

Here, the order information may include product category, product name, product volume, product weight, sales place, delivery address, and orderer information.

Meanwhile, the courier delivery information may include invoice information, a delivery address, a product, and a quantity.

Next, the fulfillment server 120 performs inventory management by acting on behalf of the logistics service of warehousing, storage, packaging, shipment, and return of goods according to the order information and courier delivery information from the e-commerce server 110 .

In addition, the fulfillment server 120 extracts and generates internal data of the sales status by product category, the sales status by region, the return status, and the sales status by e-commerce company from the order information, and the delivery status of the courier company and the manufacturer's production from the courier delivery information External data of the current status, import and export performance by product, sales data by product, consumption data by age, consumption propensity by period, consumption propensity by weather, and SNS trend are extracted and generated, and transmitted to the sales volume prediction unit 130 .

Next, the sales volume prediction unit 130 stores internal data and external data to build a data warehouse (DW) to create a dataset, and performs preprocessing to process missing data and error data, and By analyzing the correlation between product, age, period, weather, SNS trend variables, and product sales, product sales forecasts are derived by region, product, age, period, weather, and SNS trend.

For example, the sales volume prediction unit 130 analyzes the correlation between the aforementioned variables and product sales to derive a valid variable showing a meaningful correlation with product sales, and applies an analysis algorithm to derive a product sales forecast value. have.

Here, the analysis algorithm includes time series analysis, which is a model that statistically analyzes changes at regular intervals according to the passage of time, and regression analysis or cluster analysis, which is a model that predicts how much the result changes according to changes in the independent variable, which is an effective variable. As a kind, a random forest, which is a model that analyzes combining multiple decision trees, can be applied.

In addition, the sales volume prediction unit 130, as illustrated in Figure 2, the total or province-by-year sales volume trend analysis, sales volume to product sourcing ratio analysis, the sales volume decrease over the last three years, the sales volume by region, Display unit 140 by deriving the product sourcing status by product category, purchase status by product category, purchase status by region, status by age and income, purchase trend by product category, and product sales forecast for specific region purchase trend It can be provided through visualization.

Next, the display unit 140 processes and visualizes the product sales forecast value derived by the sales volume prediction unit 130 and provides it to the user.

Therefore, by the configuration of the sales prediction system using the parcel delivery information as described above, the delivery delivery information corresponding to the invoice information is used as basic information, and sales by region, product and period are predicted through an analysis algorithm, and malicious inventory is reduced. can be minimized

Although embodiments of the present invention have been described with reference to the above and the accompanying drawings, those of ordinary skill in the art to which the present invention pertains can practice the present invention in other specific forms without changing its technical spirit or essential features. You can understand that there is Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

110: e-commerce server 120: fulfillment server
130: sales volume prediction unit 140: display unit

Claims (5)

an e-commerce server that performs e-commerce to generate order information and courier delivery information;
In accordance with the order information from the e-commerce server and the courier delivery information, inventory management is integrated by acting on behalf of the logistics service of warehousing, storage, packaging, shipment, and return of goods, and the sales status by product category from the order information Internal data of sales status by region, return status, and sales status by company are extracted and generated, and from the above courier company delivery status and manufacturer production status, import/export performance by product, sales data by product, consumption data by age, consumption propensity and weather by period A fulfillment server that extracts and generates external data of each consumption propensity and SNS trend;
By storing the internal data and the external data, a data warehouse is built and pre-processed, and the correlation between region, product, age, period, weather, SNS trend variables, and product sales is analyzed by region, product, age, and period. and a sales volume prediction unit that derives product sales forecast values for each weather and SNS trend; and
A display unit that processes and visualizes the product sales forecast value derived by the sales volume prediction unit; Including, using courier transportation information corresponding to invoice information to predict sales by region, product, and period, sales using courier transportation information prediction system.
According to claim 1,
The sales volume prediction unit, a sales prediction system using courier transport information, characterized in that deriving the predicted value of the product sales volume by deriving a valid variable of the analyzed correlation and applying an analysis algorithm.
3. The method of claim 2,
A sales prediction system using courier transport information, characterized in that time series analysis, regression analysis or random forest is applied to the analysis algorithm.
According to claim 1,
The sales volume forecasting unit, the total or province-by-year sales trend analysis, product sourcing ratio analysis to sales volume, sales volume decrease over the past 3 years, sales volume by region, product sourcing status by product category, and purchase status by product category And, a sales forecasting system using courier transport information, characterized in that the purchase status by region, the status by age and income, and the purchase trend by product category and the product sales forecast value of the purchase trend in a specific region are derived.
According to claim 1,
The parcel delivery information is a sales prediction system using delivery delivery information, characterized in that it includes invoice information, delivery address, product, and quantity.

Images