KR102594165B1 - System of predicting future demand using sales volume prediction model for temperature change - Google Patents

Abstract

The present invention includes a data collection unit that collects data on changes in sales volume of products due to climate change, a data collection unit that uses the data collected to generate big data on similar product groups with matching trends, and evaluation factors that affect product demand. a data analysis unit that calculates the relationships and weights between the two and reassembles the evaluation factors; and a data analysis unit that predicts future demand for the product from data on products selected based on the data recombined in the data analysis unit and products in a similar product group to the selected product. A future demand forecasting system using a sales volume forecasting model for temperature changes that includes a demand forecasting unit is disclosed.

Description

Future demand prediction system using a sales forecast model for temperature changes { SYSTEM OF PREDICTING FUTURE DEMAND USING SALES VOLUME PREDICTION MODEL FOR TEMPERATURE CHANGE }

The present invention relates to a future demand prediction system using a sales volume prediction model for temperature changes. More specifically, a sales volume prediction model using big data analysis is used to select similar product categories affected by temperature changes and the selected products. This is about a future demand forecasting system using a sales forecast model for temperature changes that allows predicting future demand.

As the information industry develops and Internet access through smartphones becomes easier, online shopping is becoming increasingly active. In particular, the online shopping market has grown even larger over the past few years as people have avoided offline shopping due to the coronavirus pandemic.

As a result, companies can easily secure larger amounts of information, and by analyzing this information, they can efficiently predict demand, identify consumer perceptions and trends, and more accurately manage inventory and determine prices. It has been done.

Despite the use of this information, many newly launched online shopping malls are still unable to survive for long and are being closed down. In particular, shopping malls that mainly handle clothing products such as coats, jumpers, and shirts, or products that are affected by weather or temperature, such as fans, air conditioners, umbrellas, heaters, etc., can incur large losses if product sales volume is incorrectly predicted. It can also cause a company's existential crisis.

For this reason, many researchers are studying ways to analyze weather and climate information and use it for marketing.

For example, prior patents also introduce methods of using weather or climate information for marketing.

For example, in Republic of Korea Patent No. 10-2343374, ‘Artificial intelligence cosmetics sales prediction method based on weather and climate data and server using the same’ (hereinafter referred to as ‘Patent Document 1’), In a method of predicting sales of cosmetics used for skin, a technology is being developed to improve the accuracy and reliability of cosmetics sales forecasts by considering meteorological and climate data corresponding to the forecast target store.

In addition, in Republic of Korea Patent No. 10-0610644, 'Internet shopping mall operation method applying discount rate according to temperature' (hereinafter referred to as 'Patent Document 2'), in the e-commerce method using the Internet, products that have been purchased and paid for are An Internet shopping mall operation method is disclosed that applies a specified discount rate corresponding to the temperature on the date of purchase of the product and then compensates for the discount amount using the discount rate.

In addition, Republic of Korea Patent No. 10-1838393, '24-hour power demand prediction device and power demand prediction method using hourly temperature' (hereinafter referred to as 'Patent Document 3'), uses the hourly temperature forecast predicted for the next day. We are disclosing a power demand forecasting device and a power demand forecasting method that can search for past power demand with similar temperature change patterns and use it as input data to predict power demand.

However, there is a problem that it is difficult to accurately predict future demand for products using only the technology disclosed in these patent documents.

Republic of Korea Patent No. 10-1838393 ‘24-hour power demand prediction device and power demand prediction method using hourly temperature’ Republic of Korea Patent No. 10-2343374 ‘Artificial intelligence cosmetics sales prediction method based on weather and climate data and server using the same’ Republic of Korea Patent No. 10-0610644 ‘Internet shopping mall operation method applying discount rate according to temperature’

Journal of the Korean Society of Big Data, Vol. 4, No. 1, 2019, pp.29-37, 'Sales prediction model for temperature changes using big data analysis' Meteorological Administration Open Meteorological Data Portal (https://data.kma.go.kr/stcs /grnd /grndTaList.do)

The present invention was created to solve the above problems, and is a future demand prediction system using a sales volume prediction model for temperature changes that allows predicting future demand for similar products affected by temperature changes through big data analysis. The purpose is to provide.

In order to solve the above problems, the present invention includes a data collection unit that collects data on changes in sales volume of products due to climate change, and using the data collected by the data collection unit to generate big data on similar product groups with matching trends, A data analysis unit that calculates the relationships and weights of evaluation factors that affect product demand and reassembles the evaluation factors; a product selected based on the data recombined in the data analysis unit; and data on products that are similar to the selected product. A future demand forecasting system using a sales forecast model for temperature changes is disclosed, which includes a demand forecasting unit that predicts future demand for products.

According to an embodiment of the present invention, the generation of big data for the similar product group is a future demand prediction system using a sales forecast model for temperature changes, characterized in that the generation of big data for the selected product is achieved by analyzing the regression line graph of the sales volume graph according to temperature of the selected product. commences.

According to one embodiment of the present invention, whether the trends are consistent is determined by generating a confidence interval trend line graph based on the regression line graph and then temperature change based on the rate at which the regression line graph of the product to be compared deviates from the confidence interval trend line graph. We launch a future demand forecasting system using a sales volume forecasting model.

According to one embodiment of the present invention, the data analysis unit calculates the relationship between the selected evaluation elements, groups the evaluation elements based on the calculated relationship, sets the ranking of the grouped evaluation elements, and ranks the evaluation elements. Initiates a future demand prediction system using a sales forecast model for temperature changes, which is characterized by merging low-ranked evaluation factor data with high evaluation factors to create a demand forecast graph.

According to one embodiment of the present invention, the demand forecasting unit outputs demand forecast data for the product selected through the demand forecast graph, and compares demand forecast data for the selected product with similar products to generate demand forecast data for the selected product. A future demand prediction system using a sales volume prediction model for temperature changes, which is designed to compensate for changes in temperature, is disclosed.

According to one embodiment of the present invention, the ranking of the evaluation factors is higher as the difference between the maximum and minimum values of the data within the set range range is larger, and the data analysis unit determines the evaluation factor with the highest ranking (rank 1). Utilize a sales forecast model for temperature changes, which is characterized by multiplying the data of other evaluation factors except by a conversion factor to match the change in data with the first-ranked data, and then correcting the data so that the evaluation factors have the same value in the first section. A future demand forecasting system is launched.

According to one embodiment of the present invention, the data analysis unit estimates the polynomial trend line of the evaluation factors and then creates a differential graph of the polynomial trend line to determine the location of the inflection point, and data of the evaluation factors based on the location of the inflection point. We initiate a future demand forecasting system using a sales forecast model for temperature changes, which is characterized by merging to create a demand forecast graph.

According to one embodiment of the present invention, the demand forecasting unit predicts future demand based on the ratio of the value of the first-ranking evaluation factor predicted by the demand forecast graph and the value of the recently measured first-ranking evaluation factor. We are launching a future demand forecasting system using a sales forecast model for temperature changes.

According to one embodiment of the present invention, the demand forecast graph is a temperature change characterized in that it is drawn as a polynomial trend line from the section immediately before the inflection point to the section after the recently measured section among the data of the merged first-ranked evaluation element. We launch a future demand forecasting system using a sales volume forecasting model.

According to an embodiment of the present invention, the demand forecast graph is a polynomial trend line of order of adding 1 to the number of inflection points of the second-ranked evaluation factor. A future demand forecasting system using a sales forecast model for temperature changes. commences.

According to the present invention, it is possible to more accurately analyze the future demand for the product group by selecting a product category that is greatly influenced by temperature or climate using big data analysis.

In addition, it is possible to collect more data for demand forecasting by classifying product categories with similar fluctuation trends due to temperature or climate into one product group, thereby improving the reliability of analysis.

In addition, it becomes possible to more accurately predict the rate of change in demand by ranking multiple factors that affect demand and merging the rate of change of low-ranked factors with the rate of change of high-ranked factors.

Figure 1 is a diagram illustrating the structure of a future demand prediction system using a sales volume prediction model for temperature changes according to an embodiment of the present invention.
Figure 2 is a diagram showing the trend of temperature change at regular intervals.
Figure 3 is a diagram showing an example of data on non-standardized products.
Figure 4 is a diagram showing an example of standardized data on a specific product.
Figure 5 is a flowchart explaining a method of classifying similar products into similar product groups to predict future demand for products.
Figure 6 is a flowchart showing the process of calculating the correlation between product sales and temperature changes.
Figure 7 is a diagram explaining a method of generating a sales trend graph and confidence interval for product a according to temperature changes.
Figure 8a is a diagram explaining a method of generating a sales trend graph of product b.
Figure 8b is a diagram explaining a method of comparing the tendencies of product a and product b.
Figure 9a is a diagram explaining a method of generating a sales trend graph of product c.
Figure 9b is a diagram explaining a method of comparing the tendencies of product a and product c.
Figure 10 is a diagram explaining a method of selecting a similar product group based on tendency comparison.
Figure 11 is a flowchart explaining a method for analyzing consumption patterns and predicting future demand according to an embodiment of the present invention.
Figure 12 is a flowchart for specifically explaining the 'step of recombining evaluation elements' shown in Figure 11.
Figure 13 is a flow chart to specifically explain the 'step of predicting product demand' shown in Figure 11.
FIG. 14 is a flowchart for specifically explaining the 'step of generating a demand forecast graph' shown in FIG. 11.
Figure 15a is a diagram explaining the step of creating an original graph to create a demand forecast graph.
Figure 15b is a diagram illustrating the step of generating an initial value matching graph according to magnification conversion to generate a demand forecast graph.
FIG. 15C is a diagram illustrating the steps of generating an increase and initial value correction graph to create a demand forecast graph.
Figure 15d is a diagram explaining the step of creating a polynomial trend line graph to create a demand forecast graph.
Figure 15e is a diagram explaining the step of creating a differential graph of a polynomial trend line to create a demand forecast graph.
Figure 15f is a diagram explaining the step of creating a first merge graph to create a demand forecast graph.
Figure 15g is a diagram explaining the step of creating a secondary merge graph to create a demand forecast graph.
Figure 15h is a diagram explaining the step of creating a 3rd merge graph to create a demand forecast graph.
Figure 15i is a diagram explaining a method of predicting future demand through a trend prediction graph.
Figure 16 is a diagram showing an example of reporting based on future demand forecast results.

Hereinafter, the present invention will be described in more detail with reference to the drawings. In this specification, the same or similar reference numbers are assigned to the same or similar components even in different embodiments, and the description is replaced with the first description. As used herein, singular expressions include plural expressions unless the context clearly dictates otherwise.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

The terms used in this specification are merely used to describe specific embodiments and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as “comprise” or “have” are intended to indicate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

In addition, terms such as "... unit", "... unit", and "... module" used in the specification refer to a unit that processes at least one function or operation, which is hardware or software or hardware and It can be implemented through a combination of software.

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

Figure 1 is a diagram illustrating the structure of a future demand prediction system using a sales volume prediction model for temperature changes according to an embodiment of the present invention.

Referring to Figure 1, a future demand prediction system using a sales prediction model for temperature changes can be connected to shopping malls, blogs, cafes, Korea Meteorological Administration sites, etc. through a server.

The server collects data from the Internet sites and stores it in a database, and the system uses information processed from the collected data to predict future demand for products and provides it to users.

The Internet site may include a shopping mall site (11), a blog site (12), a cafe site (13), a Korea Meteorological Administration site (14), etc.

Users who receive future demand forecast data may be individual users, corporate users, and server or system administrators.

The collected data is classified into items such as site name, product URL, product name, product category, image, price, product description, review, inquiry, and collection time and stored in the database.

The demand forecasting system may include a data collection department, a data analysis department, a demand forecasting department, and a management department. These 'parts' are only divided to explain the function of the demand forecasting system and may not be separated in terms of hardware.

The data collection unit may include a communication module 111 and a database 112.

The communication module 111 may include one or more modules that enable wired/wireless communication between the demand forecasting system and the server.

The database 112 stores data collected by the demand forecasting system and data collected, analyzed, and processed by the data analysis unit 120, demand forecasting unit 130, and management unit 140.

The data collection unit 110 may collect data using a web crawler method.

A web crawler is a computer program that explores the World Wide Web in an organized, automated manner. In general, the work performed by web crawlers is called web crawling or spidering. Many sites, such as search engines, perform web crawling to keep data up to date. Web crawlers are used to create copies of all pages of the visited site, and search engines index these pages to quickly search them. Crawlers are also used for automatic maintenance tasks on websites, such as link checking and HTML code verification, and to collect certain types of information about web pages, such as automatic email collection.

A web crawler is a form of bot or software agent. Web crawlers usually start with a list of URLs, called seeds, and update the URL list by recognizing all hyperlinks on the page. The updated URL list is revisited recursively.

The operating structure of a search engine, a computer program with the ability to search the World Wide Web in an organized and automated manner, operates in three stages: Web crawling, indexing, and searching.

First, the web crawling process copies every page of a site. This is done by giving priority to the most recent data. Additionally, the indexing process collects, stores, and analyzes data to enable accurate and fast retrieval. Finally, the extraction process extracts titles, topics, etc. that contain words that make up the search term.

Search is performed through this series of processes. The search ability of a search engine is determined by the relevance between search terms and data. Among the numerous searched web pages, there are pages that are relatively more relevant to the search keyword, and the search engine continuously provides feedback through indexing and analysis of the priority values of the most relevant results. Adjust to

The data analysis unit 120 analyzes the data collected by the data collection unit 110 and edits or processes it into a form that can be utilized by users.

For example, the data analysis unit 120 selects evaluation elements that are related to each other within big data, calculates the relationship and weight of the evaluation elements, groups the evaluation elements according to the relationship, or adjusts the weights of the evaluation elements. By performing tasks such as arranging, big data can be processed into a form that is meaningful to users.

In particular, in the present invention, a temperature change analysis module may be included in the data analysis unit to analyze data on product sales volume according to temperature change.

The temperature change analysis module analyzes data on annual temperature or climate change and analyzes the relationship between temperature/climate change data and product sales.

Referring to Figure 2, there are some differences in the daily maximum and minimum temperatures, but when analyzed on a yearly basis, it can be seen that a pattern is formed within a certain temperature range.

In other words, it can be inferred that if the consumption patterns of consumers are confirmed by analyzing past temperature/climate change trends, it will be possible to predict sales volume at a specific point in the future. Hereinafter, the term 'climate' is used to include all of these factors related to meteorological phenomena, unless specifically limited to specific categories such as temperature, humidity, weather, and precipitation.

Going one step further from this data analysis, the temperature change analysis module analyzes the sales volume trends of individual products and then analyzes the correlation between products.

For example, products such as scarves, scarves, gloves, and fans are products that are affected by weather or climate. However, the sales trends for ‘shawls, scarves, gloves’ and ‘fans’ are opposite. In other words, as the temperature rises, sales of ‘fans’ increase, but sales of ‘shawls, scarves, and gloves’ decrease. Conversely, when the temperature drops, sales of 'shawls, scarves, and gloves' increase, but sales of 'fans' decrease.

However, if you look specifically, you can see that the trends do not match even within ‘shawls, gloves, and scarves.’ All three products show a trend of increasing sales when the temperature drops, but sales of 'shawls and gloves' are highest when the weather is cold in winter, but sales of 'scarves' are higher when the weather is cool in spring or fall.

The temperature change analysis module compares trends for each product and groups similar products into the same group. The reclassification method of the temperature change analysis module will be described in more detail below with reference to FIGS. 7 to 10.

The demand prediction unit 130 creates a future demand prediction mechanism based on the data analyzed by the data analysis unit 120 and predicts the future demand of consumers for a specific product.

The management unit 140 manages the overall operation of the demand forecasting system.

For example, it is possible for the system to manage the overall operation of collecting and storing data, analyzing data, and predicting demand.

Additionally, the management unit 140 can set users' permission to access data or change data.

Additionally, the management unit 140 may manage and change a mechanism for predicting future demand in the present invention.

Figure 3 is a diagram showing an example of data on non-standardized products, and Figure 4 is a diagram showing an example of data on a specific standardized product.

Referring to Figures 3 and 4, the system collects unstructured raw data from Internet sites and stores it in a database. Raw data may be missing some of the information needed for analysis or may contain information that is unnecessary for analysis.

The system can exclude unnecessary information from the collected information and additionally collect insufficient information using a web crawler method. The data collected in this way is standardized and used for demand analysis.

For example, the system can collect information about products, information about weather or climate, sales price and sales volume data, etc. separately and then bundle them together. Referring to Figure 3, the system can collect information such as product image (a), product name (b), seller (c), product material/product classification/characteristics (d), etc., see Figure 7. This allows you to collect data on average temperature changes for the period you want to analyze and product sales volume data according to temperature changes. The system analyzes the correlation between these separately collected data and reorganizes them into one standardized data.

Referring to Figure 4, temperature/climate and product sales quantity during a specific period are standardized.

More specifically, in the example of Figure 4, the period is limited to December 1, 2021 to December 8, 2021, and the weather (average temperature, minimum temperature, maximum temperature, precipitation) and sales information (average It shows the results of organizing the sales price, total sales quantity, and total sales price into one table. Here, the system formats the accumulated data from December 1, 2021 to December 8, 2021 in comma-separated values (CSV) format and stores it in the database.

According to Figure 4, it can be seen that the quantity of wool coats sold, sales price, average temperature, minimum temperature, maximum temperature, precipitation, etc. are rearranged regularly. The system formalizes the data collected in this way so that it can be used to predict sales volume.

Figure 5 is a flowchart explaining a method of classifying similar products into similar product groups to predict future demand for products, and Figure 6 is a flowchart showing the process of calculating the correlation between product sales and temperature changes.

Referring to Figure 5, the method of classifying similar products into similar product groups includes selecting products with large seasonal sales changes (S10) and analyzing the sales volume of each selected product according to temperature (S20). Wow, it includes a step (S30) to classify products that have a high correlation between temperature changes and sales volume.

In the step (S10) of selecting products with large changes in sales depending on the season, the data collection department collects a list of products affected by temperature, humidity, weather, fine dust levels, etc. through the server and stores it in the database. In this process, climate information for a specific period can be collected from the Korea Meteorological Administration site, and sales volume increase/decrease trends and changes in the number of reviews or comments can be collected and compared from sites such as shopping malls, blogs, and cafes.

According to another embodiment of the present invention, the data collection unit can collect not only domestic climate information but also foreign climate information. Through this, it is also possible to predict future demand for products that are widely sold abroad.

In the step (S20) of analyzing the sales volume of each selected product according to the temperature, the individual sales volume of the products collected in step S10 according to the climate (or temperature) is analyzed.

Specifically, step S20 may include a big data collection step (S21), a data standardization step (S22), a big data analysis and sales volume prediction step (S23), and a forecast and actual sales volume error analysis step (S24). there is.

In the big data collection step (S21), the data collection department collects unstructured raw data from Internet sites and stores it in a database.

In the data standardization step (S22), as shown in FIG. 4, the information necessary for predicting future demand is rearranged to fit a certain format. Referring to Figure 4, it can be seen that the quantity of wool coats sold, sales price, average temperature, minimum temperature, maximum temperature, precipitation, etc. are organized in a table.

In the big data analysis and sales volume prediction step (S23), the temperature change analysis module uses the standardized data to determine sales volume trends for each product and groups products showing similar trends into the same product group. When predicting future demand for a specific product, the system also utilizes data from other products within the same product group.

After forming a group of similar products, the system selects evaluation factors. The demand forecasting unit creates a product demand forecast graph using the selected evaluation factors. According to an embodiment of the present invention, the demand forecasting graph may use a polynomial graph merging method. This will be described in detail with reference to FIGS. 11 to 16 below.

In the prediction and actual sales volume error analysis step (S24), the formula for demand forecasting is corrected by comparing future demand forecast data and actual sales volume data.

Hereinafter, a method for creating a pool of similar product groups will be described with reference to FIGS. 7 to 10.

Figure 7 is a diagram explaining a method of generating a sales trend graph and confidence interval for product a according to temperature changes.

In the present invention, big data analysis can utilize the analysis technique disclosed in Non-Patent Document 1. Since other analysis techniques may be used in big data analysis, it is not the core content of the present invention, but the analysis technique of Non-Patent Document 1 is briefly summarized for understanding of the invention.

According to the above analysis technique, a matrix sequentially representing the average temperature value of the temperature data collected during the period to be analyzed, regardless of the size of the value, can be expressed as the formula below.

Here, N represents the number of collected average temperature values.

The sales volume ( SV ) according to the temperature ( t ) of a specific product category (category, c ) is expressed by the determinant below.

)은 분석기간 동안 특정 상품의 판매량의 평균값들로 이루어진 행렬이다. Sales volume for the average temperature of a specific product (

) is a matrix consisting of the average values of the sales volume of a specific product during the analysis period.

The average value of the nth value can be expressed as the equation below.

Here, c is the product category index for data standardization and classification, t is the temperature, and K is the number of years during the analysis period.

In order to express the calculated matrices in a graph, the obtained sales volume values can be organized in ascending order according to the average temperature value and expressed as follows.

Here, s represents the index of the temperature matrix in which the element values of the temperature matrix are sorted in ascending order and has the same date index value as the sales volume of products sold at that temperature.

The error rate can be expressed as follows.

Here, the superscript a is a symbol representing actual sales volume, and Z represents the number of data samples used in the analysis.

The system first generates a sales graph 200 according to temperature as shown in (a) of FIG. 7 and a regression line graph 201 using the 'stat_smooth' function of the R program.

Afterwards, the system generates an upper confidence interval trend graph 202a and a lower confidence interval trend graph 202b as shown in (b) of FIG. 7 based on the regression line graph 201. The confidence interval trend graphs 202a and 202b can be used to determine similar product groups.

Referring to FIGS. 8A to 9B, a specific mechanism by which the system determines similar product groups will be described.

Figure 8a is a diagram explaining a method of generating a sales trend graph of product b, Figure 8b is a diagram explaining a method of comparing the trends of product a and product b, and Figure 9a is a diagram explaining a method of generating a sales trend graph of product c. This is a diagram explaining a method, and Figure 9b is a diagram explaining a method of comparing the tendencies of product a and product c.

As explained in Figure 7, the system draws a regression line graph and a confidence interval trend graph based on sales volume data according to temperature of product a and then compares the trends of product a and other products.

Referring to FIG. 8A, the system generates a sales volume graph 300 and a regression line graph 301 according to the temperature of product b. The sales volume graph (300) is indicated with a black solid line, and the regression line graph (301) is indicated with a blue dotted line.

The system extracts the regression line graph 301 and synthesizes it into the graph of product a.

Referring to FIG. 8B, the regression line graph 301 of product b is placed between the upper confidence interval trend graph 202a and the lower confidence interval trend graph 202b of product a. For products with matching tendencies, most of the regression line graph is placed between the upper and lower confidence interval trend graphs, and for products with inconsistent tendencies, the regression line graph is placed outside the confidence interval trend graph.

According to one embodiment of the present invention, whether the trends are consistent can be determined by the ratio of the area (B) where the regression line graph deviates from the confidence interval trend graph to the area (A) between the confidence interval trend graphs.

For example, referring to Figure 8b, the regression line graph 301 of product b is placed between the upper confidence interval trend graph 202a and the lower confidence interval trend graph 202b in most sections, and some upper confidence interval graphs in the rightmost section. The confidence interval deviates from the upper side of the trend graph 202a. In this case, the area (B) between the regression line graph 301 and the upper confidence interval trend graph 202a is less than 1/20 of the area (A) between the upper and lower confidence interval trend graphs. The system determines that the trends match when the area ratio becomes smaller than the predetermined ratio.

The ratio of the area for determining the tendency can be defined as the error rate defined in Equation 8.

Likewise, referring to FIG. 9A, the system generates a sales volume graph 400 and a regression line graph 401 according to the temperature of product c. The sales volume graph (400) is indicated with a black solid line, and the regression line graph (401) is indicated with a green dotted line.

The system extracts the regression line graph 401 and synthesizes it into the graph of product a.

Referring to FIG. 9B, the regression line graph 401 of product c is placed between the upper confidence interval trend graph 202a and the lower confidence interval trend graph 202b of product a.

Since the regression line graph 401 of product c is placed between the upper confidence interval trend graph 202a and the lower confidence interval trend graph 202b in the entire period, the system can determine that the tendency of product c is consistent with product a. .

The system selects a group of similar products based on the tendency judgment described above.

Figure 10 is a diagram explaining a method of selecting a similar product group based on tendency comparison.

Referring to Figure 10, scarves and yellow dust masks are classified into Group A, ice cream, fans and air conditioners are classified into Group B, rice, apples and hiking gear are classified into Group C, and hand warmers, scarves and gloves are classified into Group D. .

Scarves, scarves, and gloves are products that are affected by climate, but the trends are not consistent. Specifically, all three products are consistent in that sales increase when the temperature drops, but sales of 'shawls and gloves' are high when the weather is cold in winter, while sales of 'scarves' are high when the weather is cool in spring or fall. . Therefore, when a graph of sales volume according to climate is drawn up, the trends for 'shawls, gloves' and 'scarves' do not match.

When predicting future demand for products belonging to a similar product group, the system can generate big data using data from other products in the product group. In this way, the amount of data can be significantly increased, thereby improving the accuracy of future demand forecasts.

After securing big data on similar product groups in the manner described above, the system calculates the relationship between evaluation factors and predicts future demand using a synthetic trend line correction method.

The future demand prediction method will be described in detail with reference to FIGS. 11 to 16.

Figure 11 is a flowchart explaining a method for analyzing consumption patterns and predicting future demand according to an embodiment of the present invention, and Figures 12 to 14 are flowcharts explaining this in more detail.

Specifically, Figure 12 specifically explains the 'step of recombining evaluation factors', Figure 13 specifically explains the 'step of predicting product demand', and Figure 14 shows 'the step of generating a demand forecast graph'. Explain in detail.

Referring to FIG. 11, the consumption pattern analysis and future demand prediction method includes a step of selecting evaluation factors (S100), a step of collecting data on the evaluation factors (S200), and calculating the relationship and weight of the evaluation factors to determine the evaluation factors. It includes a step of recombining them (S300) and a step of predicting demand for the product (S400).

The order of selecting evaluation factors (S100) and collecting data on evaluation factors (S200) may be changed. In other words, the system can select specific evaluation factors and then collect data on those evaluation factors, or select evaluation factors from data already collected and extract data on the evaluation factors.

Evaluation factors may include sales volume, number of views, number of likes, number of comments, number or content of reviews, rating, number or content of hashtags, etc.

In the step of collecting data on evaluation factors (S200), the system collects data through the data collection unit 110. As described above, the data collection unit 110 can generate big data by collecting data using a web crawler method and storing it in a database.

In the step (S300) of recombining the evaluation factors by calculating the relationships and weights of the evaluation factors, the data on the evaluation factors selected and collected in steps S100 and S200 are analyzed and processed into a form that can be used for demand forecasting.

According to one embodiment of the present invention, the step of recombining evaluation elements (S300) includes calculating the relationship between the evaluation elements (S310), grouping the evaluation elements according to the relationship (S320), and evaluating within the group. A step of arranging elements according to weight (S330), a step of graphing and displaying the rate of change of evaluation factors (S430), and merging the graph of evaluation factors with low weight into the graph of evaluation factors with high weight to create a demand forecast graph. It may include a step of generating (S350), etc.

In the step of calculating the relationship between evaluation factors (S310), trends between evaluation factors are analyzed. For example, if sales volume increases when the number of views or comments for a specific product increases, it can be determined that the number of views and comments has a high relationship with sales volume. Additionally, if a specific evaluation factor increases but the change in sales volume is minimal, it can be determined that the relationship between the specific evaluation factor and sales volume is low.

In the step of grouping evaluation elements according to their relationship (S320), evaluation elements with a high degree of relationship can be grouped into one group. For example, among evaluation factors, you can create groups with a high degree of relationship and conduct analysis for each group.

In the step of arranging the evaluation elements within the group according to weight (S330), the base data is selected among the evaluation element data within the group, weights are assigned to each data, and the data are arranged according to ranking.

The criteria for selecting base data can be accomplished in various ways.

According to an embodiment of the present invention, the evaluation factor with the largest change within the measurement interval is selected as the base data, and other evaluation factors are multiplied by a conversion factor to match the change range. This will be described in more detail below with reference to FIG. 15C.

In the step of graphing and displaying the rate of change of evaluation factors (S340), the data collected and analyzed in previous steps are displayed in a graph.

For example, the system can graph the numerical values of evaluation factors, such as the graphs shown in FIGS. 15A to 15I. Additionally, the system can generate a polynomial trend line graph of the numerical graphs of these evaluation factors, create a differential graph of the polynomial trend line graphs, and then check the inflection point value of the polynomial trend line graph. Using the slope or inflection point values of the graphs identified in this way, the rate of change, trend of change, correlation of change, etc. of the evaluation factors can be confirmed.

In the step (S350) of creating a demand forecast graph by merging the graph of the evaluation element with a high weight with the graph of the evaluation element with a low weight, the scale of the graphs is scaled by setting the comparison standard for the evaluation elements and then calculating the conversion factor. It merges graphs using polynomial trend line graphs, differential graphs, inflection point data, etc., and creates a demand forecast graph.

To this end, the step of generating a demand forecast graph by merging the graph of evaluation factors with low weight with the graph of evaluation factors with high weight (S350) includes the step of expressing the data of evaluation factors as a time series graph (S351), and the step of creating a time series graph. A step of converting to a polynomial trend line (S352), a step of creating a differential graph of the polynomial trend line (S353), a step of combining the polynomial trend line of evaluation factor A and the trend line of evaluation factor B after the inflection point occurs (S355), , may include a step of creating a demand forecast graph based on the synthetic trend line (S356), etc.

In the step of predicting product demand (S400), the demand forecast graph generated in step S300 is used to predict future demand for a specific product.

The step of predicting demand for a product (S400) includes outputting demand forecast data for the selected product through a demand forecast graph (S410), comparing demand forecast data for the selected product and similar products (S420), and It may include a step of correcting product demand forecast data (S430).

The steps described above do not necessarily have to be performed in the order listed. Additionally, it is possible to omit certain steps or include other steps as needed.

Figure 13 is a diagram showing examples of fields in which BAFP according to the present invention can be utilized. Referring to Figure 13, variable data classification methods and correlation weight adjustment methods for collecting necessary information from third-party homepages can be implemented in various ways.

For example, figures extracted through 1) analysis of distribution by time, day of the week, and season, 2) analysis of changes in rise and fall, 3) analysis of sporadic sudden changes, 4) analysis of sales distribution, 5) analysis of market share, etc. Based on this, an automatic reporting evaluation of the overall item can be provided through different visual analysis.

Below, the method for predicting product demand in this system will be described in detail through specific examples. In the following embodiment, in order to predict future sales volume or future demand for a product, demand prediction is made using 'number of likes', 'number of comments', 'rating average', and 'number of views' data among relevant evaluation factors. Let's look at how to create a graph.

Referring to Table 1 below, you can see changes in the number of likes, comments, rating averages, and views related to a specific product. In Table 1, the sections were divided into 12 sections and the numerical values were recorded. In the embodiment of the present invention, 1 section is defined in units of 1 month, but there is no need to limit 1 section to 1 month, and if necessary, the section can be defined or investigated in units of 1 day, 1 week, 1 month, etc. It is also possible to extend or shorten the period.

In one embodiment of the present invention, it is preferable to use only evaluation factors belonging to one task, but it is also possible to use the total sum of the same evaluation factors belonging to different tasks or to use their average value.

For example, it is desirable to analyze future demand using the number of likes, number of comments, average rating, and number of views collected through the Naver Shopping site, but if necessary, the number of likes on the Naver Shopping, Coupang, and G Market sites It is also possible to collect and analyze the number of comments, average rating, number of views, or data corresponding to these data.

Figure 15a expresses the numerical values listed in Table 1 as a line graph.

Referring to Table 1 and Figure 15a, the lowest number of likes is recorded at 15 in the first survey section (section 1), and the highest number is recorded at 31 in section 6. The difference between the lowest and highest number of likes is 16.

The lowest number of comments is recorded as 8 in section 1, and the maximum number is recorded as 16 in section 4. The difference between the lowest and highest number of comments is 8.

The lowest rating average is recorded at 4.5 points in section 1, and the lowest value is recorded at 4.8 points in section 4. The difference between the lowest and highest rating average is 0.3 points.

The lowest number of views is recorded at 66 in section 2, and the highest number is recorded at 81 in section 7. The difference between the lowest and highest number of views is 15.

Because the change values of the evaluation factors are different, it is difficult to directly compare them. Therefore, in the present invention, the rate of change of the evaluation factors is checked after the evaluation factors are multiplied by the conversion factor to match the change range.

In this embodiment, the evaluation factor with the largest change is selected as the base data. Other evaluation factors are multiplied by weight values (conversion factors) to match the change range of the evaluation factors corresponding to the base data. Table 1 below lists the conversion factor values for each evaluation element.

Evaluation factors range of change conversion factor number of likes 16 One number of comments 9 1.778 Rating average 0.3 53.333 views 15 1.0667

Figure 15b is a diagram illustrating the step of creating an initial value matching graph according to magnification conversion to create a demand forecast graph, and Figure 15c is a diagram explaining the step of generating a rise range and initial value correction graph to create a demand forecast graph. This is a drawing. The system of the present invention converts the magnification of the collected data as shown in Figures 15b and 15c, compares them, and then compares them by matching the increase.

Referring to Figure 15b, the system multiplies each evaluation factor by a specific value to match the initial value. For example, the initial value of the number of comments is 8, so multiply it by 1.875 to convert it to 15, the initial value of the rating average is 4.5, so multiply it by 3.333 to convert it to 15, and the initial value of the number of views is 67, so multiply it by 0.224 to convert it to 15. do.

By converting in this way, it is possible to check the change trends of each evaluation element after a specific point in time (initial value). However, in this case, it is only possible to identify trends in evaluation factors, but it is difficult to synthesize evaluation factor graphs. Therefore, it is necessary to match the range of changes in evaluation factors.

Referring to Figure 15c, the system multiplies each evaluation factor by the conversion factor calculated in Table 1 to generate data as shown in Table 3 below.

Afterwards, the system performs correction to match the initial value so that changes in evaluation factors after the initial value can be confirmed. At this time, the amount of change must be kept the same, so at this stage, the initial value is matched through sum or difference.

Table 4 below shows data where the initial value is set to 15 by adding or subtracting specific values from the number of comments, average rating, and number of views data in Table 2 above.

If you draw a graph using the data in Table 4, you can obtain a graph like Figure 15c.

Figure 15d is a diagram explaining the step of creating a polynomial trend line graph to create a demand forecast graph.

When the trend line graph of each evaluation element graph in FIG. 15C is drawn, it is as shown in FIG. 15D. In Figure 15d, for convenience, the 6th order polynomial trend line graph of each evaluation factor is checked.

According to this, the 6th-order polynomial trend line formula for the number of likes is as in Equation 7 below, the 6th-order polynomial trend line formula for the number of comments is as in Equation 8 below, and the 6th-order polynomial trend line formula for the rating average is as in Equation 9 below. , the 6th order polynomial trend line formula for the number of views is as Equation 10 below.

Looking at Figure 15d and the above equations, each graph is similar to each other, but repeats increases and decreases at different points. In other words, the evaluation factors show similar trends overall, but if you look at them in detail, some factors tend to increase at a specific point in time, while other factors tend to decrease.

In the present invention, future demand is predicted by reflecting the influence of these interrelated evaluation factors on different evaluation factors.

Specifically, the evaluation factor that has the greatest impact on demand is set as the base data, and then the growth rate of the next-ranked evaluation factor is reflected. In this way, if a trend line is drawn sequentially reflecting the growth rates of all evaluation factors, the overall trend can be predicted more accurately than predicting using only one piece of data.

To do this, it is necessary to check when the rate of change changes from positive to negative in each graph and when the rate of change changes from negative to positive. The point at which the rate of change changes from positive to negative (or the point at which the rate of change changes from negative to positive) is a critical point when the interest of consumers changes rapidly, so this needs to be reflected in the demand forecast.

Figure 15e is a diagram explaining the step of creating a differential graph of a polynomial trend line to create a demand forecast graph. The system analyzes the polynomial differential graph to identify the inflection points of the trend line.

The differential trend line formula for the number of likes is shown in Equation 11 below, the differential trend line formula for the number of comments is shown in Equation 12 below, the differential trend line formula for the rating average is shown in Equation 13 below, and the differential trend line formula for the number of views is shown below. It is the same as equation 14.

Referring to Equations 11 to 14 and FIG. 15e, the inflection points of each graph are shown in Table 5 below.

Evaluation factors inflection point number of likes 5.678 (decrease) number of comments 4.802 (decrease), 9.133 (increase) Rating average 10.651 (increase) views 6.512 (decrease)

Figure 15f is a diagram explaining the step of creating a first merge graph to create a demand forecast graph. According to one embodiment of the present invention, the system generates a first merge graph using the inflection point data confirmed above. Referring to Figure 15b, the system sets the weight ranking in the following order: number of likes (1st), number of comments (2nd), number of views (3rd), and average rating (4th). In the first merge graph, a graph is created by merging the 4th-ranked data with the 3rd-ranked data.

As can be seen in Table 4 above, the 4th rank rating average data shows a significant change after 10.651. Specifically, it can be seen that the rate of change in the rating average changes from minus (decrease trend) to plus (increase trend) at 10.651. This change in the rating average trend may reflect the change in the number of third-ranked views or affect the change in the number of views, so the system reflects the rating average data in the number of views graph for the section after 10.651.

Since the purpose of this embodiment is to generate a final trend prediction graph, it is important to identify the changing trend of the graph. For this purpose, in this embodiment, the trend line is corrected by calculating the average value of the 3rd and 4th priority data in the section after 10.651.

The first merge graph reflecting this is shown in Figure 15f.

Referring to Figure 15f, it can be seen that the decline rate in the graph after the first merge decreased compared to the view count graph before the first merge. In other words, it can be seen that the predicted value for future demand has increased when rating average data is reflected compared to when predicting future demand using only view count data.

Even when interpreted qualitatively, if buyers' evaluations of a specific product have improved, the number of consumers who choose the product after seeing the rating reviews will increase, which can lead to an increase in the number of likes. Therefore, the first merged data is used before merging. It can be thought that it is more accurate than the data.

Figure 15g is a diagram explaining the step of creating a secondary merge graph to create a demand forecast graph. According to one embodiment of the present invention, the system creates a secondary merge graph using the primary merge data generated above.

The secondary merge graph creates a graph by merging the primary merge data with the secondary comment count data.

As can be seen in Table 4 above, the 3rd ranking view count data undergoes a significant change after 6.510. Specifically, it can be seen that the rate of change in the number of views changes from plus (increasing trend) to minus (decreasing trend) at 6.510. This change in the trend in the number of views may pre-reflect the change in the number of second-ranked comments or affect the change in the number of comments, so the system reflects the number of views data in the number of comments graph for the section after 6.510. For more accurate predictions, it is desirable that the view count data reflected at this time is data corrected by the 4th priority data (the 1st merged data generated earlier).

The secondary merge graph reflecting this is shown in Figure 15g.

Referring to Figure 15g, it can be seen that the amount of change in the number of comments graph after the secondary merge has decreased compared to the graph of the number of comments before the secondary merge. In other words, when predicting future demand using only the number of comments data, demand is expected to increase rapidly, but when forecasting by reflecting the number of views and average rating data, future demand is expected to increase slowly.

Even when interpreted qualitatively, if the number of comments has recently increased but the number of views has turned to a downward trend, it is not desirable to expect demand to increase rapidly in the future. In other words, from a qualitative perspective, it can be confirmed that predicting future demand through secondary merged data will be more accurate than predicting demand based only on the number of comments.

Figure 15h is a diagram explaining the step of creating a 3rd merge graph to create a demand forecast graph. According to one embodiment of the present invention, the system generates a tertiary merge graph using the secondary merge data generated above.

The 3rd merge graph creates a graph by merging the 1st rank like count data with the 2nd merge data.

As can be seen in Table 5 above, the data on the number of second-ranked comments shows significant changes in the values of 4.802 and 9.133. Specifically, it can be seen that the rate of change in the number of comments changes from plus (increasing trend) to minus (decreasing trend) at 4.802, and from minus (decreasing trend) to plus (increasing trend) at 9.133.

Since this change in the trend of the number of comments may pre-reflect the change in the number of first-ranked likes or affect the change in the number of likes, the system reflects the number of comments data in the number of likes graph for the interval after 4.802 and 9.133. For more accurate predictions, it is desirable that the comment count data reflected at this time is data corrected by the 3rd and 4th ranking data (secondary merged data generated earlier).

The third merge graph reflecting this is shown in Figure 15h.

Referring to Figure 15h, it can be seen that the graph of the number of likes after the third merge shows a decreasing trend compared to the graph of the number of likes before the third merge. In other words, when predicting future demand using only data on the number of likes, demand is expected to decrease, but when predicting by reflecting the number of comments, number of views, and average rating data, it can be expected that future demand will trend upward.

When interpreted qualitatively, if the number of likes is still decreasing, but all other evaluation factors (number of comments, rating average, number of views) are trending upward, it is desirable to expect that the number of likes will also trend upward in the future. . In other words, from a qualitative perspective, it can be confirmed that predicting future demand through 3rd merged data will be more accurate than predicting demand based only on the number of likes.

Figure 15h is a diagram explaining a method of predicting future demand through a trend prediction graph.

The system creates a third merge graph in the manner described above and then creates a trend prediction graph based on it.

In the trend prediction graph, the trend prediction graph is created using data from the section just before the inflection point (4 sections) to the most recent section (12 sections), and the value 2 sections later than the most recent section is predicted.

The trend prediction graph is created as a polynomial trend line graph, and the degree of the polynomial is '(number of inflection points of the second-ranked data) + 1'. Since the number of inflection points refers to the number of x values at which the differential value of the graph becomes 0, it is desirable that the degree of the graph be '(number of inflection points of the second-ranked data) + 1', which is the value obtained by integrating this.

Therefore, in this embodiment, the trend prediction graph is composed of a third-order polynomial trend line graph, and according to this third-order polynomial trend line graph, the y value in the 14th section is approximately 26.

The system uses these demand forecast results to present reporting results to users.

Figure 16 is a diagram showing an example of reporting based on demand forecast results.

In Figure 16, the up/down degree values are calculated as (value of predicted section/value of recent section).

In this example, the value of the predicted section (section 14) is 26, and the value of the most recent section (section 12) is 20.3, so the up/down degree value is about 1.28.

Referring to Figure 16, the system provides the user with a report that 'This item is suitable for the trend but requires a cautious approach due to its weak growth potential' corresponding to the up/down degree value of 1.28.

The analysis example reporting comment shown in FIG. 16 is only an example to explain the present invention, and it is possible to change the specific text as needed.

According to at least one embodiment of the present invention discussed above, it is possible to more accurately analyze the future demand for the product group by selecting a product category that is greatly influenced by temperature or climate using big data analysis, and By classifying product categories with similar fluctuating trends into one product group, it becomes possible to collect more data for demand forecasting, thereby improving the reliability of analysis. Multiple factors affecting demand can be ranked and low By merging the rate of change of ranking factors with the rate of change of high ranking factors, quantitative and qualitative improvements can be expected compared to the prior art, such as making it possible to more accurately predict the rate of change in demand.

The embodiments described in this specification and the accompanying drawings merely illustratively illustrate some of the technical ideas included in the present invention. Accordingly, the embodiments disclosed in this specification are not intended to limit the technical idea of the present invention, but rather to explain it, and therefore, it is obvious that the scope of the technical idea of the present invention is not limited by these embodiments. All modifications and specific embodiments that can be easily inferred by a person skilled in the art within the scope of the technical idea included in the specification and drawings of the present invention should be construed as being included in the scope of the present invention.

11: Shopping mall site
12: Blog site
13: Cafe site
14: Meteorological Administration site
50: server
100: Demand forecasting system
110: data collection unit
111: communication module
112: database
120: Data analysis department
121: Temperature change analysis module
130: Demand forecasting department
140: Management Department

Claims (10)

A data collection department that collects data on changes in product sales due to climate change;
A data analysis unit that generates big data on similar product groups with similar trends using the data collected by the data collection unit, calculates the relationship and weight of the evaluation factors that affect product demand, and reassembles the evaluation factors; and
A demand forecasting unit that predicts future demand for the product from the data of the product selected based on the data recombined in the data analysis unit and the data of products corresponding to a similar product group to the selected product,
The data analysis unit,
Calculate the relationship between the selected evaluation elements, group the evaluation elements based on the calculated relationship, set the ranking of the grouped evaluation elements, and merge the evaluation element data of different rankings to create a demand forecast graph. order,
The demand forecasting department,
It is formed to output demand forecast data for the selected product through the demand forecast graph, and compare demand forecast data for the selected product with similar products to correct demand forecast data for the selected product,
The ranking of the evaluation factors is higher as the difference between the maximum and minimum values of the data within the set range is larger,
The data analysis unit multiplies the data of other evaluation elements except for the highest ranking (1st rank) evaluation factor by a conversion factor to match the change range of the data with the 1st rank data, and then converts the data so that the evaluation elements have the same value in the first section. Correction
A future demand prediction system using a sales forecast model for temperature changes. According to paragraph 1,
The generation of big data for the similar product groups is,
A future demand prediction system using a sales volume prediction model for temperature changes, which is achieved by analyzing the regression line graph of the sales volume graph according to the temperature of the selected product. According to paragraph 2,
Whether the above trends are consistent,
A future demand prediction system that generates a confidence interval trend line graph based on the regression line graph and then utilizes a sales volume prediction model for temperature changes based on the rate at which the regression line graph of the product to be compared deviates from the confidence interval trend line graph. delete delete delete According to paragraph 1,
The data analysis unit,
After estimating the polynomial trend line of the evaluation factors, creating a differential graph of the polynomial trend line to determine the location of the inflection point, and merging the data of the evaluation factors based on the location of the inflection point to create a demand forecast graph. Future demand forecasting system using a sales forecast model for temperature changes. In clause 7,
The demand forecasting department,
Future demand using a sales forecast model for temperature changes, characterized in that future demand is predicted based on the ratio of the value of the first-ranked evaluation factor predicted by the demand forecast graph and the value of the recently measured first-ranked evaluation factor. Prediction system. According to clause 8,
The demand forecast graph is,
A future demand prediction system using a sales volume prediction model for temperature changes, characterized in that among the data of the merged first-ranked evaluation factors, a polynomial trend line is drawn from the section immediately before the inflection point to the section after the recently measured section. According to clause 9,
The demand forecast graph is,
A future demand forecasting system using a sales forecast model for temperature changes, characterized as a polynomial trend line of the order of adding 1 to the number of inflection points of the second-ranked evaluation factor.

Images