KR102608848B1 - System for providing cad program business sales management service capable of demand forecasting - Google Patents

Abstract

A CAD program sales management service provision system that enables demand forecasting is provided. After registering each customer, a customer-specific sales report is entered and viewed, non-purchasing customers are classified, and CRM (Customer Relationship Management) for technical support is provided. ), a user terminal that performs partner management, customer management, sales management, menu management, and code management, and a storage unit that receives and stores partner and customer information from the user terminal or administrator terminal, to the customer company. A management department that manages the sales progress status by designating it as awaiting approval, unable to proceed, in progress, completed, or failed; a customer that assigns the user terminal of the user in charge for CRM when a request for technical support is entered from the customer's terminal It includes a management service providing server including a demand forecasting unit that performs demand forecasting using a pre-built demand forecasting model based on accumulated sales data and then transmits it to the user terminal.

Description

A CD program sales management service provision system capable of demand forecasting {SYSTEM FOR PROVIDING CAD PROGRAM BUSINESS SALES MANAGEMENT SERVICE CAPABLE OF DEMAND FORECASTING}

The present invention relates to a CAD program sales management service provision system capable of demand forecasting. It provides a system that can provide a guide to inter-company transactions through demand forecasting when performing sales management for selling CAD programs.

In all activities of a company aimed at pursuing profit, various information such as sales and purchases is continuously generated. The information generated in this way is, at a small scale, an element for the CEO to evaluate the performance of salespeople, and at a large scale, it becomes reliable data that allows him to directly view the overall market situation, so it needs to be managed efficiently. Companies have manually recorded various information generated in the process of calculating the company's profits through sales and the contents of the company's operation and management in ledgers. Although these records are obtained directly from the field and are highly reliable data, the data As the amount increases, the efficiency of management further decreases and it becomes a simple record, and its usability gradually decreases. As PCs become widespread, most companies are choosing enterprise resource planning (ERP) that utilizes PCs to store this information.

At this time, a method of performing demand forecasting or making sales proposals through demand forecasting to effectively carry out sales activities was researched and developed. In this regard, Korea Patent Publication No. 2017-0088116 (published on August 1, 2017), which is a prior art, and Korean Patent No. 10-0722956 (announced on May 30, 2007), which stores customer, product, and order data in ERP and generates demand forecast values based on ERP, product master, inventory, and sales. Based on the information required for demand forecasting corresponding to the information, the recommended order quantity for each product is created through the demand forecast model. When the manufacturer modifies and confirms the recommended order quantity information, an order proposal is created and sent to the distributor, so that the distributor and the manufacturer Configurations that establish strategic partnerships and effectively support the supply chain management (Vender Managed Inventory) process are disclosed.

However, in the former case, it is disclosed that demand forecast values are generated based on ERP, but the exact method of predicting demand is not described, and in the latter case, only the structure of adjusting supply and demand in supply chain management is disclosed. Just do it. Prediction is a series of tasks that measure the scale and effect of future events under controllable conditions when faced with an uncertain situation. If you want to predict the market, you are predicting future demand, such as product size, quality of service, period, or location required by a specific market. Forecasting is the science of the request or need to find out in advance what will happen in the future. The goal is to obtain an answer to this question using systematic and systematic tools. Demand forecasting is one of the most important factors in all corporate activities. It measures the size of target market demand, and determines the production scale, production time, and production scale of products that meet market demand. It affects almost all areas of corporate activities, including the supply and demand of factories and personnel required for production, and marketing costs. Accordingly, research and development of a system that can perform demand forecasting based on sales management programs is required.

In one embodiment of the present invention, when performing management for sales of a CAD program, registering and managing customer companies and partner companies, and performing B2B (Business to Business) demand forecasting, not only quantitative demand forecasting but also qualitative demand forecasting It enables predictions to be made, and by classifying trading companies into new and existing customers to perform demand forecasting, it helps to classify purchase demand according to the life cycle of corporate customers and conduct sales, and helps B2B companies We can provide a CAD program sales management service provision system that can predict demand and provide management services so that business activities can be continued considering the characteristics of transactions between businesses. However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means for achieving the above-mentioned technical task, an embodiment of the present invention registers each customer, then inputs and searches a report for each customer, classifies non-purchasing customers, and provides CRM for technical support. A user terminal that performs (Customer Relationship Management), an administrator terminal that performs partner management, customer management, sales management, menu management, and code management, and a store that registers and stores partner and customer information from the user terminal or administrator terminal. Management department, which designates and manages the business progress status for the customer as one of waiting for approval, unable to proceed, in progress, completed, and failed; the user terminal of the user in charge for CRM when a request for technical support is entered from the customer's terminal. It includes a management service providing server including a customer department that allocates and a demand forecasting department that performs demand forecasting using a demand forecasting model established based on accumulated sales data and then delivers it to the user terminal.

According to one of the means for solving the problems of the present invention described above, when performing management for sales of a CAD program, registering and managing customer companies and partner companies, and quantitative demand when predicting B2B (Business to Business) demand. It allows you to perform qualitative demand forecasting as well as forecasting. By classifying business partners into new and existing customers and performing demand forecasting, you can classify purchase demand according to the life cycle of corporate customers and conduct sales. We can provide management services to help businesses continue their business activities, taking into account the characteristics of transactions between B2B companies.

1 is a diagram illustrating a CAD program sales management service provision system capable of demand forecasting according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a management service providing server included in the system of FIG. 1.
Figures 3 and 4 are diagrams for explaining an embodiment in which a CAD program sales management service capable of predicting demand is implemented according to an embodiment of the present invention.
Figure 5 is an operation flowchart illustrating a method of providing a CAD program sales management service capable of predicting demand according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this does not mean excluding other components unless specifically stated to the contrary, but may further include other components, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The terms "about", "substantially", etc. used throughout the specification are used to mean at or close to that value when manufacturing and material tolerances inherent in the stated meaning are presented, and are used to enhance the understanding of the present invention. Precise or absolute figures are used to assist in preventing unscrupulous infringers from taking unfair advantage of stated disclosures. The term “step of” or “step of” as used throughout the specification of the present invention does not mean “step for.”

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. Meanwhile, '~ part' is not limited to software or hardware, and '~ part' may be configured to reside in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card.

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

In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is identifying data of the terminal. It can be interpreted as

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

1 is a diagram illustrating a CAD program sales management service provision system capable of demand forecasting according to an embodiment of the present invention. Referring to FIG. 1, a CAD program sales management service providing system 1 capable of predicting demand includes at least one user terminal 100, a management service providing server 300, and at least one administrator terminal 400. can do. However, since the CAD program sales management service providing system 1 capable of demand forecasting shown in FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1.

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1, at least one user terminal 100 may be connected to the management service providing server 300 through the network 200. In addition, the management service providing server 300 may be connected to at least one user terminal 100 and at least one administrator terminal 400 through the network 200. Additionally, at least one manager terminal 400 may be connected to the management service providing server 300 through the network 200.

Here, the network refers to a connection structure that allows information exchange between each node, such as a plurality of terminals and servers. Examples of such networks include a local area network (LAN) and a wide area network (WAN). Wide Area Network, Internet (WWW: World Wide Web), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), and Wi-Fi. , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC ( It includes, but is not limited to, Near-Field Communication (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, and DMB (Digital Multimedia Broadcasting) network.

In the following, the term at least one is defined as a term including singular and plural, and even if the term at least one does not exist, each component may exist in singular or plural, and may mean singular or plural. This should be self-explanatory. In addition, whether each component is provided in singular or plural form may be changed depending on the embodiment.

At least one user terminal 100 includes sales management, sales management, planning, and data input for sales management using a web page, app page, program, or application related to a CAD program sales management service capable of predicting demand. This may be a person in charge of marketing, etc.

Here, at least one user terminal 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one user terminal 100 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

The management service providing server 300 may be a server that provides a CAD program sales management service web page, app page, program, or application capable of predicting demand. In addition, the management service providing server 300 may be a server that receives data from the user terminal 100, allows the data to be searched by the manager terminal 400, and performs demand forecasting by analyzing the input data. .

Here, the management service providing server 300 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc.

At least one manager terminal 400 may be a manager terminal that manages users, customers, and partner companies using a web page, app page, program, or application related to a CAD program sales management service capable of predicting demand.

Here, at least one manager terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one manager terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one manager terminal 400 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

Figure 2 is a block diagram for explaining the management service providing server included in the system of Figure 1, and Figures 3 and 4 show a CAD program sales management service capable of predicting demand according to an embodiment of the present invention. This drawing is for explaining one embodiment.

Referring to Figure 2, the management service providing server 300 includes a storage unit 310, a management unit 320, a customer unit 330, a demand prediction unit 340, a classification unit 350, and a life cycle consideration unit ( 360), ㅁModel Construction Department (370), License Management Department (380), Unconfirmed Customer Information Department (390), Decision-Making Department (391), Automation Department (393), Potential Customer Discovery Department (395), and Customer Satisfaction Department ( 397) may be included.

A CAD in which the management service providing server 300 or another server (not shown) operating in conjunction with an embodiment of the present invention can predict demand with at least one user terminal 100 and at least one administrator terminal 400. When transmitting a program sales management service application, program, app page, web page, etc., at least one user terminal 100 and at least one manager terminal 400 are configured to use a CAD program sales management service application capable of predicting demand. , you can install or open programs, app pages, web pages, etc. Additionally, a service program may be run on at least one user terminal 100 and at least one administrator terminal 400 using a script executed in a web browser. Here, a web browser is a program that allows the use of web (WWW: World Wide Web) services and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Netscape. , Explorer, Chrome, etc. Additionally, an application refers to an application on a terminal and includes, for example, an app running on a mobile terminal (smartphone).

Referring to FIG. 2, the storage unit 310 can receive information about partner companies and customer companies from the user terminal 100 or the manager terminal 400 and store it. The user terminal 100 can register each customer company and then input and view a report (Sales Report) for each customer company.

The management unit 320 can manage the business progress status for the customer by designating it as one of waiting for approval, unable to proceed, in progress, completed, and failed. The manager terminal 400 can perform partner management, customer management, sales management, menu management, and code management.

The customer department 330 may allocate the user terminal 100 of the user in charge for CRM when a request for technical support is input from the customer terminal (not shown) of the customer company. The user terminal 100 can classify non-purchasing customers and perform Customer Relationship Management (CRM) for technical support.

The demand forecasting unit 340 may perform demand forecasting using a previously constructed demand forecasting model based on accumulated sales data and then transmit the demand forecast to the user terminal 100. Demand forecasting techniques by use based on a qualitative demand forecasting model, demand forecasting techniques based on quantitative multiple regression analysis, new and existing demand forecasts that can be easily used, and analysis of various events experienced as a company grows and develops according to the life cycle. can do. In order to create a demand forecasting technique based on new demand and existing demand, the factors that can predict new demand are defined as the number of new corporations by industry and the company's new customer lines, and the factors that can predict existing demand are defined as the company's repurchase customer lines. can do. In addition, various events that occur depending on the company's growth and development stage can be set, such as company establishment, corporation conversion, business location relocation and expansion, employee recruitment, etc., and then a demand forecasting guide for each event can be presented. When demand forecasting for individual companies is necessary, demand forecasting methods by use, new and existing demand forecasting methods, or forecasting methods based on life cycle can be used. To predict market demand for a specific region or industry, multiple regression analysis methods can be used. there is.

B2B marketing and sales managers can be presented with new guidance measures to consider when predicting demand. The usage-specific technique identifies factors that should be looked at from the buyer's perspective rather than the seller when predicting demand for individual companies, and the multiple regression analysis technique When analyzing the B2B commercial area at a macro level, the region and company's industry and size can be considered and used as independent variables in the prediction model. The results of demand forecasting can be used as an indicator for suppliers to more efficiently allocate and use marketing and sales resources, and above all, they can serve as an objective standard for performance analysis by industry and region. As suggested by the Delphi method, the qualitative method can seek advice from corporate purchasing experts, verify validity through sample surveys, and perform demand forecasting analysis in the B2B commercial area using quantitative methods such as multiple regression analysis. You can. Each model or method is described in detail below.

The role of demand forecasting is to provide information for corporate decision-making in an uncertain business environment. Demand forecasting is the most important input data for planning and management decision-making models related to production, inventory, and sales. Currently, various statistical methods are used as forecasting methods needed for planning, and various forecasting programs based on statistical methodology have been developed, but there are not many cases in which complete forecast results can be obtained. Despite these uncertain conditions, forecasts are used as an important part of business planning, and most companies use forecasts in various areas such as production, sales, human resources, and finance. In particular, companies must support price setting, promotion strategies, production management, material management, and human resources planning based on demand forecasts, so they can improve profitability by managing them monthly, weekly, and daily according to the period of need. Referring to Figure 3(a), demand forecasting can be largely divided into long-term demand forecasting and short-term demand forecasting. In the long term, it includes process design and production capacity to secure production capacity, and in the short term, it includes production planning, sales management, and inventory management.

<Demand forecasting process>

The demand forecasting process is a process of predicting the timing, scope, or results of events that will occur in the uncertain future in an uncertain future. In other words, forecasting involves estimating future demand for the size, timing, and quality of products or services to be put on the market. Therefore, the forecasting process can be said to be essential to a company's management activities because it must provide a logical basis that must be applied to make uncertain situations predictable. In corporate management, process design and production system planning involve establishing mid- to long-term plans regarding the size and form of products or services to be put on the market, and system operation includes product inventory levels, manpower supply and demand plans, raw material repurchase plans, etc. This refers to the establishment of short-term plans such as manufacturing plans and financial plans. For this reason, forecasting can help corporate managers eliminate some uncertain factors and engage in more effective management activities in order to improve an uncertain situation into a controllable situation. In this respect, the forecasting process can be said to be the starting stage and most important element of management decision-making. In general, the prediction process can be explained in the following five steps.

First, the reason, purpose, and timing for forecasting must be determined. Once these matters are determined, it is possible to determine how accurate the desired prediction is. In other words, it is possible to determine all matters necessary for prediction, such as information, personnel, and systems necessary to meet the desired prediction accuracy. Second, mid- to long-term forecasts are less accurate than short-term forecasts. Therefore, you must decide on the time you want to forecast or the forecast period. Third, a forecasting technique must be determined. Of course, since there are various forecasting techniques, it is possible to use several forecasting techniques and then decide on the optimal forecasting technique, but since the cost and time involved must be taken into account, a decision must be made as best as possible for the situation. Fourth, the forecasting process is supported by securing and analyzing the necessary data so that designated forecasting techniques can be used. It also makes assumptions necessary for prediction. Fifth, the prediction results must be checked to see if the prediction was successful. If the forecast result differs from the actual, the problem is checked step by step, including selection of forecast method, data collection, and assumptions, and corrected to produce a revised forecast result.

The basic steps of prediction activity are as shown in Figure 3(b). To succeed in forecasting activities, you must fundamentally understand the purpose of forecasting. For example, a financial manager in charge of investment in production facilities needs to forecast market demand and sales for at least 4 to 5 years. This is because investing in production facilities is a long-term task, and if it is not supported by stable sales, the need for investment in production facilities is meaningless, so investment cannot be made properly. In general, forecasts should be quantified, and investment costs, sales, profits, etc. of production facilities should be forecast in monetary units. On the other hand, it is important to know the exact timing for investment schedules and raw material supply and demand periods, so they should be expressed in appropriate timing rather than monetary units.

<Selection and application of demand forecasting techniques>

Forecasting is essential for rational decision making. By predicting the future, you can purchase raw materials that meet demand, produce and sell them appropriately, minimize inventory, and reduce costs by eliminating unnecessary elements in each sector. Since various forecasting methods have been studied to find a method that suits each environment, individual companies must select and apply a method that suits their situation. If you do not accurately diagnose the situation you are facing and use the appropriate method, you will not be able to obtain the desired prediction results. Table 1 below is a table comparing the application fields of each prediction technique. The forecasting technique must be decided by considering the following factors: first, availability of materials needed for forecasting, second, expected level of accuracy desired for forecasting, third, cost to be used for forecasting, and fourth, short-term, mid-term, and long-term forecasting. The length of the period, fifth, the time required for analysis and prediction, and sixth, the complexity of factors affecting the forecast.

division Forecasting technique Application field expense qualitative
method -Delphi method
-market research
-Data leakage and life cycle analysis -Used for long-term forecasting
-Same as above
-Same as above -middle
-go
-middle causal
prediction method -Regression analysis
-Econometric model -Apply to short-term and mid-term forecasts of existing products and services
-Same as above -middle
-go time series
analyze -Moving average method
-Exponential smoothing method
-Least squares method -Short-term forecast of production and business activities
-Same as above
-Same as above -I
-I
-I

Among the six items to consider when making a forecast, forecast accuracy and forecast cost are important to consider. Decisions required at each stage of the product life cycle, such as product introduction, growth, and maturity, have different characteristics and require different information for each stage. The above matters are expressed graphically as shown in Figure 3(c). In Figure 3(c), the decision making and appropriate forecasting techniques at each stage of the product life cycle are summarized. Step-by-step management, such as product introduction, growth, and maturity, cannot be solved by applying a single forecasting method. For example, schedule management and inventory management for product introduction require short-term forecasts, and production management, marketing, and sales management, such as process selection at the factory location, require both short-term and mid- to long-term forecasts. The demand forecasting method is Various methods can be applied depending on the situation, but in general, many methods can be used to predict the future by analyzing past experiences and characteristic factors. Looking at the time series forecasting method, it is used to make short-term future predictions based on past performance. In addition, since the predicted reasons can be analyzed through a causal model, the time series forecasting method performs predictions by deriving seasonal characteristics and trend factors when analyzing time series data. The demand forecasting process can be shown as shown in Figure 3(d).

<Demand forecasting technique>

The composition of time series forecasting methods can generally include trends, cycles, seasonal variations, and irregular fluctuations. Trends can be said to be long-term fluctuation factors that affect time series data due to the effects of technological development, changes in consumer tastes, economic changes such as population changes, inflation, and increased unemployment rates. Cycle is a time series component that circulates in cycles of 2, 5, or 10 years, and becomes a factor of mid- to long-term fluctuations, such as the business cycle. Seasonal changes are changes that occur every year and are effects that appear on a monthly or quarterly basis. Irregular changes refer to factors that are difficult to predict, such as natural disasters. There are two ways to explain why the above-mentioned changes occur. First, it is a method of establishing a causal relationship between cause and effect, finding variables that cause change, and explaining the main factors of that change. This is an econometric approach that creates an econometric model based on economic theory and explains the factors of change. Second, it is a method that attempts to explain changes based on information obtained through probabilistic analysis without establishing causal relationships from the beginning. At this time, in one embodiment of the present invention, a hybrid model combining a quantitative demand forecasting model and a qualitative demand forecasting model is used, which will be described later in the model building unit 370. Of course, it is obvious that in addition to the hybrid model, the quantitative demand forecasting model and qualitative demand forecasting model described above can be used.

The classification unit 350 can apply a demand forecasting model by dividing customers into new customers and existing customers. The life cycle consideration department 360 may determine the purchase demand that occurs according to the corporate life cycle of the customer company through demand forecasting and then guide the purchase demand to the user terminal 100. New Demand & Existing Demand and Customer LifeTime Value can be considered. From the perspective of a B2B company, new demand and existing demand are the new demand from new customers and existing transactions. This is to classify and predict repurchase demand from customers who have been using the service. New demand is the demand from customers who have not done business with us yet, and existing demand is repurchase demand. When a company with multiple product lines sells a variety of products, repurchase demand can be divided into cases where the products are the same and cases where the products are different. In the case of IT products, rather than purchasing the product because it is broken, it is often replaced or upgraded because the performance of the product has deteriorated due to technological advancement. Therefore, even if you repurchase the same product line, you are purchasing a product with improved performance, so it can be called up-selling. Purchasing a different product is called cross-selling or cross-selling, such as purchasing a printer after purchasing a computer. . New demand and existing demand can be widely used when classifying corporate demand, and can also be used when predicting demand for products used when a new building is built or when an existing building is rebuilt through remodeling. Customer lifetime value refers to the various events that occur from the time an individual is born until he or she becomes an adult. For example, just as an individual purchases an IT product at the time of entering and graduating from school, getting married, or buying a house, a business also develops a company, recruits employees, etc. This refers to a method of predicting demand that occurs during the construction and relocation of a business, corporate conversion, and business expansion. This customer lifetime value has been mainly studied for products or markets targeting individuals, but it can be applied to companies and used to predict demand.

<Measurement and control of prediction error>

이며, 평균절대오차(Mean Absolute Deviation, MAD)는

이다. It is very rare for predictions and reality to match exactly. Since there is always room for error, efforts should be made to minimize such error. When making predictions using some time-series data, a method that generates a small error among various prediction methods should be applied. Of course, there is no way to reduce errors in any environment, and a method suitable for each environment must be found and applied. The method for measuring error is as follows. If the prediction is Y', the actual is Y, and the period is n, the mean deviation is mean error =

and the Mean Absolute Deviation (MAD) is

am.

Before making a prediction, no one wants or expects to get inaccurate results. However, if an error occurs, the cause of the error must be identified. We need to understand why actual demand forecasts are different and find ways to reduce errors in future forecasts. One way to check whether the prediction was good is to use the tracking signal (TS). The tracking signal measures how well the prediction matches reality, and is the average error divided by the mean absolute error (MAD). A negative (-) tracking indicator value means that the prediction is smaller than the reality, and a positive (+) tracking indicator value means that the prediction is larger than the actual. For tracking indicator values between -1 and 1, the smaller the value, the better, and it is desirable for the indicator to stay near O, which is the balance of yin and yang. At this time, the types of prediction errors are shown in Table 2 below.

Types of prediction errors detail Cumulative Forecasting Error (CFE) -A means to measure the bias of predictions
-If it continues to increase, it indicates that actual demand is being underestimated. Mean Average Error (MAE) -The sum of the differences between the actual value and the predicted value divided by the number of periods.
-Used to measure the direction of prediction error Mean Absolute Deviation (MAD) -Prediction error measurement means to prevent positive (+) errors from canceling out negative (-) errors.
-Take the absolute value of the error so that all errors are non-negative. Mean Square Error (MSE) -Calculate the average of the squares of each error so that all errors are non-negative. Mean Absolute Percent Error -Evaluate forecast error proportionally considering the size of demand
- Only the absolute value of each error rate is used and only the width of the error is considered.

When building a demand forecasting model, the model building unit 370 may build a hybrid model that mixes a qualitative demand forecasting model and a quantitative demand forecasting model. Demand forecasting methods can be divided into a variety of methods depending on the target or purpose of forecasting, but are generally divided into qualitative forecasting methods and quantitative forecasting methods. Qualitative forecasting methods are predictions based on subjective judgment, including the Delphi Method, Jury of Executive Opinion, Life-Cycle Analysis, Historical Analogy, and Committee Consensus Method. (Panel Consensus), Market Research, etc. Qualitative methods are methods used when launching a new product or entering a new market when there is no or insufficient past data and it is difficult to predict the future. The accuracy and reliability may be somewhat lower than quantitative methods. Quantitative forecasting methods are divided into causal forecasting methods and time series forecasting methods and use mathematical models and data. The causal forecasting method is a method of predicting demand using a causal model that mathematically finds and predicts causal relationships between causes and results. A representative example is the regression analysis method. Time series forecasting methods predict future trends using past data and include the Exponential Smoothing Method, Box-Jenkins Model, and Moving Average Method. The qualitative forecasting methods used in the demand forecasting technique are shown in Table 3, and the quantitative forecasting methods are shown in Tables 4 and 5.

qualitative
Forecasting technique Delphi method market research method life cycle
analogy expert judgment explanation The survey results from experts are compiled and the results are fed back to the experts for reinvestigation. How to repeat this to get an accurate prediction Panels, questionnaires, test markets, opinion polls, etc. to collect data on the market A method used when similar items enter the market, assuming that the product gradually moves through the stages of introduction, growth, maturity, and decline. A method of making predictions based on their experiences, intuition, etc. through interviews with individual experts or groups Usage Long-term sales forecast through production facility investment or production capacity expansion, technology forecast to determine the timing of technological innovation Total company sales forecast, sales by product, sales forecast for individual items, etc. Long-term sales forecast for production capacity or facility planning Forecast of total sales and individual product sales accuracy short-term Fair-Excellent extremely good poorness poor-average mid term Fair-Excellent Good Average - Good poor-average long time Fair-Excellent commonly poor-average poor-average Turning point prediction Average - Good Average - Good poor-average poor-average expense Medium-high height commonly lowness

time series
Forecasting technique moving average method Exponential smoothing method repair method Box-Jenkins method explanation Forecast by arithmetic mean or weighted average over a certain number of periods Similar to the moving average method, but with exponentially greater weighting on recent data
give value
Easy to computerize
And predict multi-item
Suitable for. Linear or non-linear models, trend models, polynomial models, log-linear models, Fourier series models, etc. tailored to time series data by regression analysis methods. Determine the basic time series using the autocorrelation method and form an optimal model. Approximately 60 data points are required. Usage Short- to mid-term forecasting for inventory, production, and schedule planning, multiple items can be predicted Same as moving average method Same as moving average method, but only applies to a small number of items Because it costs a lot, it is limited to products that require extremely accurate short-term forecasts. accuracy short-term poor-good Fair-Excellent extremely good Extremely Good-Excellent mid term poorness poor-good Average - Good Average - Good long time extremely poor extremely poor extremely poor extremely poor Turning point prediction poorness poorness poorness poorness expense lowness lowness Low-Medium Low-Medium

causal prediction method regression model econometrics
Model input output
Model simulation
Model explanation Defines demand as a function of external or internal variables that cause demand fluctuations. Obtain the optimal regression line using the least squares method. A system of interdependent regression equations that describe a portion of economic activity Forecast using a matrix model that represents the flow between all sectors of the economy, predicting the input required to produce the required output. Simulation of the distribution system showing changes in products sold and movement over time, reflecting the impact of the distribution pipeline Usage Short- and medium-term forecasting for overall production planning or inventory planning for a small number of items. Useful when there is a strong causal relationship Sales forecast by product for short/mid-term planning Company or national sales forecasts by industry sector Company sales forecast by major product group accuracy short-term Good - Very Good Extremely Good - Excellent Not applicable extremely good mid term Good - Very Good extremely good Good - Very Good Good - Very Good long time poorness Good Good - Very Good Good Turning point prediction extremely good Great commonly Good expense commonly height extremely high height

<Qualitative techniques>

Qualitative techniques or qualitative techniques predict demand based on an individual's subjective judgment or the opinions of several people, and are mainly used for mid- to long-term forecasting. This method is used when data accumulated from the past cannot predict the future or when there is no past data. When there is no or sufficient historical data, such as when launching a new product, it is better to use standard techniques. These types include the Delphi method, market research method, historical analogy method, and expert opinion method.

<Delphi method>

The Delphi Method, named after the famous Delphi oracle in Greece, is a method of obtaining forecasts by selecting a group of experts on the subject to be predicted, then issuing questionnaires to these experts and repeatedly collecting their opinions. Looking at it step by step, the first step is to collect opinions by individually sending questionnaires for predictions to experts. In the second step, the person performing the prediction collects and organizes the answers to obtain statistical values such as mean, median, and standard deviation. In the third step, we inform the experts of these results and ask their opinions again on the given questions. At this time, each expert can revise his or her previous opinion. After organizing the second answers, they are notified of the results and asked again for their opinions on the given question. Finally, this process continues from 4 to 6 until a sufficient consensus is reached among experts, and the results from the final round are used as the forecast. The advantage of the Delphi method is that since responding experts answer questionnaires or predictions without meeting each other face-to-face, it can avoid the tendency for opinions to be distorted by some influential people, which is a disadvantage that occurs when a group meets. It is possible to exclude concerns about mutual influence or compromise without following . The downside is that the survey compiler cannot understand and summarize as accurately as if he or she were to conduct a face-to-face survey with experts, and combining the opinions of experts can greatly influence his or her predictions, and is expensive. .

To make the Delphi method successful, the following criteria must be set and implemented. First, sufficient relevant information must be provided so that experts can make comprehensive and rational decisions. Second, you must ask questions that middle managers can answer. Third, you should not demand excessive accuracy. Fourth, conceptual definitions related to the investigation must be equally communicated to experts so that the investigation can proceed smoothly. Lastly, all experts participating in the survey must be informed that only fair and correct predictions can lead to efficient decision making when sharing the survey results with the entire organization and have a significant impact on sales.

<Market research method>

Market research is a method of establishing a hypothesis about what you want to research in the market and then verifying the established hypothesis by surveying customers' opinions using various methods such as questionnaires, direct interviews, telephone surveys, and sending prototypes. Among qualitative techniques, market research has the advantage of being relatively accurate in its predictions. On the other hand, it has the disadvantage of requiring significant cost and time.

<Historical analogy>

Historical analogy is a method of inferring demand when there is no past data, such as the launch of a new product, by analyzing how similar existing products were introduced into the market, grew, and then how demand grew as they went through a maturity period.

<Expert Opinion Method>

It is a method that synthesizes the opinions of experts in the field about the situation facing a company and uses it to predict demand. It is based on the idea that group discussions can predict demand better than individual opinions. It is a method of using the opinions of academics or sales experts with specialized knowledge about a company's situation to predict demand, and is based on the assumption that group discussion will be able to make better predictions than the opinions of one person. The advantage is that predictions can be made in a relatively short period of time and at a low cost compared to other research techniques. The disadvantage is that it is the least accurate among qualitative techniques and there is a risk of being influenced by members with strong persuasiveness.

<Quantitative techniques>

<Time series prediction method>

Time series forecasting is a technique that predicts future demand by identifying changes over time using past data or trends. Because it predicts the future based on past data, the characteristics of time series forecasting start from the assumption that the demand generated from past time series patterns will repeat the same pattern in the future. Therefore, it is difficult to apply it to products that did not exist in the past or to new products. Based on this basic concept, forecasters who need short-term future demand have an accurate basis for predicting future demand by analyzing patterns of past demand that affect future demand. A time series has a certain pattern, and this pattern consists of trend (T: Trend), seasonal variation (S: Seasonal Variation), cyclical element (C: Cyclical Element), and irregular or random variation (R: Irregular or Random Variation). do. In time series analysis, demand Y is analyzed as a complex action of four factors and an additive or multiplicative model is designed.

① Gradually changing over a long period of time is called a trend. Stocks, prices, population, income, weather, etc. sometimes show small fluctuations up and down, but when viewed from a long-term perspective, they show a steady rise, decline, or stagnation. ② The phenomenon in which demand fluctuates over a long period of time, usually over a year, showing some kind of wave, is called cyclical fluctuation. Typical examples of cyclical fluctuations include economic fluctuations and stock price fluctuations, which are caused by various political, economic, and social environmental variables, making it difficult to predict the future. A person who predicts such cyclical fluctuations must determine what phase of the cycle the current point is in and adjust the forecast according to the results. ③ Repetitive demand fluctuations, usually with a period of 1, are called seasonal fluctuations. Seasonal fluctuations occur due to natural or artificial factors such as climate change or customary systems. Because seasonal fluctuations are more regular than cyclical fluctuations, it is relatively easy to predict future demand. ④ Irregular fluctuations are called random fluctuations. Even if the three factors - cycle, season, and trend - are perfectly understood and predicted, some forecast errors are bound to occur. This is because irregular accidental factors exist in addition to factors that are continuously considered. Random fluctuations are random fluctuations that appear irregularly and cannot be predicted, so they are also called residuals, meaning the remainder after excluding trends, cycles, and seasonal fluctuations.

<Moving average method>

The moving average method is a method of forecasting by averaging demand over a certain period of time. Moving averages are commonly used in the stock market, and long-term (120 days), medium-term (60 days), and short-term (5, 20 days) methods use the moving average method. It is an easy-to-use method among time series forecasting methods and is used for stable short-term forecasting. Since time series always contain some unpredictable random fluctuations, by analyzing the average value of the time series using the moving average method, the part where random fluctuations appear is removed to reveal the correct part of the time series. There is a simple moving average method that gives equal weight to all past demand and a weighted moving average method that gives weight to recent demand.

<Simple moving average method>

The Simple Moving Average method assigns the same weight to all past demand and is a demand forecast suitable for cases where there is little seasonal variation, no rapid increase or decrease, and only random fluctuations are particularly large. In the simple moving average method, random fluctuations are eliminated by using a moving average. The simple moving average method uses the simple average of actual demand for a certain period before the forecast period as the future forecast. In other words, if the actual demand for period t is At, the forecast value for period t is Ft, and the moving average period is N, then Ft in the simple moving average method is as follows.

<Weighted moving average method>

The weighted moving average method is a technique designed under the assumption that recently generated data acts more closely on predicted future demand. It is believed that recent data has greater potential for future predictions than older data, and relatively greater weight is given to recent data. If there is a trend in the recent data and this trend appears prominently in the recent data, a high weight is given to the recent data to respond to future demand changes. The weighted moving average method can change the influence of past data more than the simple moving average method, but it has the disadvantage of being inconvenient to use and expensive. The forecast value using the weighted moving average method can be calculated as follows.

At this time, Ft is the demand forecast for period t, At is the actual award for period t, and Wt is the weight given to period t.

<Exponential smoothing method>

Exponential smoothing, which is used for corporate inventory management and production planning, is a frequently used forecasting technique for short-term demand. It is a technique in which the target period is extended and utilized indefinitely to all periods of past time series data, and the weight is applied more as it approaches the period to be predicted, and progressively lessened at a certain rate as it gets further away. The advantages of the exponential smoothing method are that first, the accuracy is very high, second, it is easy to create a forecast model, third, the application principles of the model are easy to understand, fourth, the calculation method to obtain the predicted value is simple, and fifth, among the past data, Since it is only partially used, the required data storage requirements are small. Sixth, it is easy to test whether the prediction model is accurate.

<Simple exponential smoothing method>

The method of assigning greater weight to recent data and giving less weight to past performance values as they are further away from the present is similar to the weighted moving average method. However, the weighted moving average method only uses performance for a certain period from the present, while the simple exponential smoothing method uses current data. All past section performances are used.

In other words, this month's forecast is the delivery forecast + smoothing constant (delivery actual value - delivery forecast).

<Exponential smoothing method reflecting trends>

The simple exponential smoothing method can make accurate predictions when there is no upward or downward trend in demand in the time series. However, if there is a trend, the trend change during the forecast period must be reflected in order to forecast as close to actual demand as possible. In other words, realistic demand can be predicted by reflecting trends in forecasts obtained using the exponential smoothing method.

<Winters Model>

The Winters Model was designed to reflect both trend factors and seasonal factors. This technique is a method of predicting sales by specifying the value for each element under the assumption that sales are comprised of basic sales volume, seasonal factors, and linear elements.

<Regression Analysis>

Regression analysis is a technique that attempts to analyze social phenomena in terms of functional relationships between independent variables that influence them and dependent variables that are influenced by them. In this way, it is used to analyze the causes of many unknown problems by analyzing and predicting functional relationships between variables through data analysis. If there is one independent variable, it is called simple regression analysis. If there are two or more independent variables, it is called multiple regression analysis. Additionally, regression analysis can be divided into linear regression analysis and nonlinear regression analysis depending on the form of the regression equation.

<Simple regression analysis>

Simple regression analysis, which sees a relationship between one independent variable and a dependent variable, is the most easily used linear model. The basic formula is as follows:

<Multiple regression analysis>

In simple regression analysis, there is only one variable that has influence, but in the real world, various variables have a complex influence, and this aspect often needs to be studied. Looking at economic indicators, there are many variables that affect exports and imports, such as interest rates, exchange rates, and each country's economic situation. The technique that can be used in these cases is multiple regression. In other words, multiple regression analysis refers to linear regression analysis used when there are multiple independent variables. Both multiple regression analysis and simple regression analysis can be said to be linear regression analysis, and the relationship between independent variables and dependent variables may be linear or interactive.

<Demand forecasting using hybrid model>

Qualitative forecasting is a useful method for predicting important events or changes that will occur in the future, so it is used to predict new technologies or develop new products. Quantitative forecasting uses mathematical models and data to determine cause and effect in a mathematical manner. It is used to find causal relationships and predict demand. Today, companies use a variety of methods to predict future demand, using both qualitative and quantitative methods to fit each environment. The demand forecasting method using a hybrid model assumes factors that predict the demand of the target to be predicted in a qualitative way and then predicts demand in a quantitative way. Since this is the same as described in the classification unit 350 and the life cycle consideration unit 360, detailed description will be omitted.

The license management unit 380 may allow the user terminal 100 to manage the expiration of a license (Enterprise Agreement) for a CAD program installed on each customer company terminal.

The unconfirmed customer information unit 390 may transmit guidance to the user terminal 100 in the order in which the scheduled purchase date approaches when the customer terminal expresses the intention to purchase and then inputs the scheduled purchase date.

The decision-making unit 391 can accumulate and analyze maintenance events received from customer terminals, extract new functions to be added in response to maintenance events, and then determine whether to research and develop new functions through demand forecasting for new functions. there is. Predictive CAD program development methods can be used. This allows the program construction process to be effectively improved by predicting in advance the impact of the new purpose and effect of the CAD program on sales volume and inductively proposing a CAD program profile that maximizes demand. This model predicts the Demand Variation Index using the CAD program differentiation index, which refers to the degree of change in the CAD program's features. The Gaussian Process Regression technique is used for prediction, and a lecture profile that maximizes sales can be derived from the initial sales volume predicted in this way. Through this predicted initial sales volume, a CAD program profile that maximizes sales volume is derived. During the creation of a prediction model, the results of the KANO model, which measures customer satisfaction by function, can be used as weights to create a highly complete prediction model that reflects consumer data. This can dramatically solve the expert-dependent development process pointed out in the CAD program development methodology and increase the reliability and objectivity of the prediction model.

The automation unit 393 can process the quotation requested from the customer's terminal or the invoice provided to the customer's terminal through RPA (Robotic Process Automation).

The potential customer discovery unit 395 may extract the industry group and industry type that uses the CAD program and then market the CAD program to at least one company corresponding to the industry group and industry category.

The customer satisfaction department 397 collects and analyzes the satisfaction of customer terminals with implicit and explicit intent, lists the customer companies with the lowest analyzed satisfaction, and assigns them to provide promotions to the user terminal 100. You can. At this time, the way to distinguish implicit intention and explicit intention is to collect keystrokes or mouse events for customers' clicks or avoidance in shopping malls in recent collaborative filtering, and this can be used in B2B relationships as well, and based on this, This allows you to provide promotions or perform maintenance management by first contacting customers with low satisfaction levels.

Hereinafter, the operation process according to the configuration of the management service providing server of FIG. 2 described above will be described in detail using FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

The main screen of the sales program according to an embodiment of the present invention may be as shown in Figure 4a, and on this screen, the number of possible business registrations for each product is summarized and displayed in a dashboard. When selecting Wait for Approval on this screen, a list of people waiting for approval is output as shown in FIG. 4b, and when selecting Business Complete on this screen, a list of people who have completed business is output as shown in FIG. 4c. If you press 10 days before the due date, a list of approaching due dates will be displayed, as shown in Figure 4d. Customer information can be registered as shown in Figure 4e, and when the Sales inquiry item in the Sales Report is selected, a screen as shown in Figure 4f is displayed. As shown in Figure 4g, potential customers who have done business but have not yet purchased, that is, non-purchasing customers, can be managed separately, and the results of technical support inquiries as shown in Figure 4h and technical support requests as shown in Figure 4i can be entered and confirmed. You can.

Starting from Figure 4j, it is the manager screen. As shown in Figures 4j to 4m, the manager can perform partner management, company management, partner employee registration, and customer management. As shown in Figure 4m, each sales company can be managed through sales request management, sales history inquiry, etc. Cause: It allows users to check which company and at what stage of business they are currently conducting. Bulletin boards, data rooms, and notices can be managed as shown in Figure 4o, menu management can be performed as shown in Figure 4p, and groups for each partner can be managed as shown in Figure 4q. As shown in Figure 4r, the integrated code can be created, added, deleted, changed, etc.

Matters that are not explained regarding the method of providing the CAD program sales management service capable of predicting demand in FIGS. 2 to 4 are the same as those previously explained in FIG. 1 regarding the method of providing the sales management service of the CAD program capable of predicting demand. Since it is the same or can be easily inferred from the explained content, the description below will be omitted.

FIG. 5 is a diagram illustrating a process in which data is transmitted and received between components included in the CAD program sales management service providing system capable of predicting demand shown in FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of the process of transmitting and receiving data between each component will be described with reference to FIG. 5, but the present application is not limited to this embodiment, and the process shown in FIG. 5 according to the various embodiments described above It is obvious to those skilled in the art that the process of transmitting and receiving data can be changed.

Referring to FIG. 5, the management service providing server receives information on partner companies and customer companies from a user terminal or an administrator terminal and stores it (S5100).

In addition, the management service providing server manages the business progress status for the customer by designating it as one of waiting for approval, unable to proceed, in progress, completed, and failed (S5200), and when a request for technical support is entered from the customer terminal of the customer, the CRM For this purpose, the user terminal of the user in charge is assigned (S5300).

In addition, the management service providing server performs demand forecasting using a previously constructed demand forecasting model based on accumulated sales data and then transmits the demand forecast to the user terminal (S5400).

The sequence between the above-described steps (S5100 to S5400) is only an example and is not limited thereto. That is, the order between the above-described steps (S5100 to S5400) may change, and some of the steps may be executed simultaneously or deleted.

Matters that are not explained about the method of providing the CAD program sales management service capable of predicting demand as shown in FIG. 5 are explained in detail with respect to the method of providing the CAD program sales management service capable of predicting demand through FIGS. 1 to 4. Since it is the same or can be easily inferred from the explained content, the description below will be omitted.

The method of providing a CAD program sales management service capable of predicting demand according to an embodiment described with reference to FIG. 5 is provided in the form of a recording medium containing instructions executable by a computer, such as an application or program module executed by a computer. can also be implemented. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include all computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

The method of providing a CAD program sales management service capable of predicting demand according to an embodiment of the present invention described above includes applications installed by default on a terminal (this may include programs included in the platform or operating system, etc., which are installed by default on the terminal). ), and may also be executed by an application (i.e. program) installed by the user directly on the master terminal through an application providing server such as an application store server, an application, or a web server related to the service. In this sense, the method of providing a CAD program sales management service capable of predicting demand according to an embodiment of the present invention described above is implemented as an application (i.e., program) installed by default on the terminal or directly installed by the user, and is installed in the terminal, etc. It can be recorded on a computer-readable recording medium.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

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

Claims (10)

A user terminal that registers each customer, then inputs and searches sales reports for each customer, classifies non-purchasing customers, and performs CRM (Customer Relationship Management) for technical support;
An administrator terminal that performs partner management, customer management, sales management, menu management, and code management; and
A storage unit that registers and stores information on partner companies and customer companies from the user terminal or manager terminal, a management unit that manages the business progress status for the customer company by designating it as one of waiting for approval, unable to proceed, in progress, completed, and failed, When a request for technical support is entered from a customer terminal of a customer company, the customer department allocates the user terminal of the user in charge for CRM, performs demand forecasting using a demand forecasting model established based on accumulated sales data, and then sends the user terminal to the customer terminal. A demand forecasting unit that transmits the information to the customer company, a division department that divides the customer into new customers and existing customers and applies a demand forecasting model, and predicts the purchase demand that occurs according to the customer's corporate life cycle of the customer's terminal. A management service providing server including a life cycle consideration unit that guides the user terminal after identification, and a model construction unit that builds a hybrid model that mixes a qualitative demand forecast model and a quantitative demand forecast model when building the demand forecast model;
Including,
The demand forecasting department,
When performing the above demand forecasting, the first demand forecasting technique, which is a demand forecasting technique for each usage based on a qualitative demand forecasting model, the second demand forecasting technique, which is a demand forecasting technique based on quantitative multiple regression analysis, new demand and existing demand. Using the 3rd demand forecasting technique, which is a demand forecasting technique according to the company's growth and development, and the 4th demand forecasting technique, which is a life cycle-based demand forecasting technique that analyzes multiple events that occur as a company grows and develops according to the company life cycle. However,
In order to create the third demand forecasting technique, the factors that can predict new demand are defined to include the number of new corporations by industry and the company's new customer lines, and the factors that can predict existing demand are defined as the company's repurchase customer lines,
After setting the plurality of events as company establishment, corporate conversion, business relocation, business expansion, and employee recruitment, a demand forecasting guide for each event is presented,
When demand forecasting for an individual company is necessary, use the first demand forecasting technique, the third demand forecasting technique, or the fourth demand forecasting technique,
When predicting market demand for a specific region or industry, the second demand forecasting technique above is used.
When predicting demand through the hybrid model, assume factors that predict demand for the target to be predicted using a qualitative demand forecasting model, then predict demand using a quantitative demand forecasting model,
The results of the demand forecasting by the demand forecasting department shall be used as an indicator for distributing and using marketing and sales resources to suppliers, and as an objective standard for performance analysis by industry and region of the organization,
The new demand refers to the demand from customers who have not transacted, and the existing demand refers to the repurchase demand, which is the repurchase demand from customers who have previously transacted,
The model building department,
In relation to the above quantitative demand forecasting model, as a time series forecasting method that predicts future trends using past data, among the moving average methods, the simple moving average method, which gives equal weight to all past demands, and the weighted moving average method, which gives weight to recent demand, are used. do,
The simple moving average method is,
It is applied to demand forecasting when there are no seasonal fluctuations, no rapid increase or decrease trends, and only random fluctuations, which are irregular fluctuations, exist. The simple average of the actual demand for a certain period before the forecast period is used as the future forecast value, and the following Equation 1 is satisfied,
[Equation 1]

In Equation 1 above, Ft represents the demand forecast for period t, At represents the actual demand during period t, and N represents the moving average period,
The weighted moving average method is,
The more recent data is given a relatively greater weight compared to past data, it is possible to respond to future demand changes, the influence of past data can be changed, and Equation 2 below is satisfied,
[Equation 2]

In Equation 2 above, Ft represents the demand forecast for period t, At represents the actual demand for period t, and Wt represents the weight given to period t. A CAD program sales management service provision system capable of predicting demand.
delete delete delete According to claim 1,
The management service providing server is,
a license management unit that manages the expiration of a license (Enterprise Agreement) for a CAD program installed on each customer terminal in the user terminal;
A CAD program sales management service provision system capable of predicting demand, further comprising:
According to claim 1,
The management service providing server is,
An unconfirmed customer information unit that transmits guidance to the user terminal in the order in which the scheduled purchase date approaches when the customer terminal announces the intention to purchase and then enters the expected purchase date;
A CAD program sales management service provision system capable of predicting demand, further comprising:
According to claim 1,
The management service providing server is,
a decision-making unit that accumulates and analyzes maintenance events received from the customer terminal, extracts new functions to be added in response to the maintenance events, and then determines whether to research and develop the new functions through demand forecasting for the new functions;
A CAD program sales management service provision system capable of predicting demand, further comprising:
According to claim 1,
The management service providing server is,
An automation unit that processes the quotation requested from the customer terminal or the invoice provided to the customer terminal through RPA (Robotic Process Automation);
A CAD program sales management service provision system capable of predicting demand, further comprising:
According to claim 1,
The management service providing server is,
a potential customer discovery unit that extracts industries and industries using the CAD program and then markets the CAD program to at least one company corresponding to the industry and industry;
A CAD program sales management service provision system capable of predicting demand, further comprising:
According to claim 1,
The management service providing server is,
a customer satisfaction unit that collects and analyzes the satisfaction level of the customer terminal through implicit and explicit intent, then lists the customer enterprise with the lowest analyzed satisfaction level and assigns it to provide a promotion to the user terminal;
A CAD program sales management service provision system capable of predicting demand, further comprising:

Images