TWI619086B - Market research and analysis system - Google Patents

Abstract

The object of the present invention is to enable high-precision market research and analysis. The market survey and analysis system 1 includes: a waveform generating means for waveformizing customer data stored in a database; a means for calculating a difference between points of at least two or more waveforms generated by the waveform generating means; Means to generate at least two or more waveform line angle differences; means to determine whether the difference between the points is within a threshold; means to determine whether the difference between the line angles is within a threshold; to calculate the difference between the points Means for the ratio within the threshold; means for calculating the ratio of the difference between the line angles within the threshold; and calculating at least two based on the ratio of the difference between the points within the threshold and the difference between the line angles within the threshold Means of approximation of the above waveforms.

Description

Market research and analysis system

The present invention relates to a market survey and analysis system, and is particularly used to calculate data used to provide advertisements that meet customers' hobbies and intentions.

In order to promote the purchase of goods and services for customers who can obtain credit card, credit card, marketing network subscribers, customer account registrants, etc., and can provide customers with advertisements, The so-called recommendation system is used to present advertisements to customers. The advertisement promotion refers to the issuance of gift coupons such as POS terminals, the sending of emails with advertisements as content, and the customization of member login screens on websites. customize) display of advertisements, direct mail advertisements to customers (Direct Mail), etc. Previously, all types of gift certificates, advertisements, etc. were provided to customers. However, from the viewpoint of efficiency and cost reduction of advertising, if the advertisement is only provided to customers who have hobbies and intentions suitable for a specific advertisement, the advertising effect will be large. It can effectively provide advertisements. Therefore, a market survey, analysis system, or recommendation system for extracting target customers who provide specific advertisements is proposed. For example, there are a recommendation system that extracts advertisements that are presented based on customer attributes and purchase history (Patent Documents 1, 3, and 4), and a service ticket issuance system that extracts service tickets that are presented based on customer attributes and purchase history (Patent Document 2). Wait. These market research, analysis systems, or recommendation systems use member customer attributes and purchase history as profiles for advertisement extraction, and combine them with external factors such as weather or traffic information to extract the correspondence with specific advertisements. Member customers, and the benchmark for drawing is fixed.

[Previous Technical Literature]

[Patent Literature]

[Patent Document 1] Japanese Patent Laid-Open No. 2010-211687

[Patent Document 2] Japanese Patent Laid-Open No. 2009-163533

[Patent Document 3] Japanese Patent Laid-Open No. 2012-247926

[Patent Document 4] Japanese Patent Laid-Open No. 2004-70504

[Patent Document 5] Japanese Patent Laid-Open No. 2012-190061

The above-mentioned conventional market survey, analysis system or recommendation system also estimates the customer's preferences and intentions, and can even provide advertisements based on the customer's preferences and intentions. However, companies want to correctly analyze consumer preferences, intentions, or stores, products, services, and regional offices at the stage of various business activities, such as product development, store planning, advertising planning, advertisement provision, or selection of advertisement provision methods. Has characteristics that contribute to corporate activities. Therefore, an object of the present invention is to provide a system capable of realizing accurate market research and analysis and market research, and capable of providing market research and analysis results to an affiliated enterprise as a user of the analysis system in an easily understandable form.

The market survey and analysis system of the present invention is characterized by: a waveform generating means for wavy customer data stored in a database; and a means for calculating a difference between points of at least two or more waveforms generated by the waveform generating means; Means for calculating a difference between line segment angles of at least two or more waveforms generated by the waveform generating means; means for determining whether the difference between the points is within a threshold value; means for determining whether the difference between the line segment angles is within a threshold value; calculating the above Means for calculating the ratio of the difference between the points within the threshold; calculating the ratio of the difference between the point angles within the threshold; and based on the ratio of the difference between the points between the threshold value and the difference between the line angle Means for calculating the approximate degree of at least two waveforms.

According to another aspect of the present invention, the present invention is characterized in that the waveform generating means generates a line chart.

The present invention is characterized in that the waveform generation means includes means for calculating the averaged customer data.

The present invention is characterized in that it has a means for selecting one or more sender data and a means for selecting one or more receiver data. The waveform generating means generates a waveform of the sender data and a waveform of the receiver data, and calculates an approximate waveform. The degree means is to calculate the approximate degree of the waveform of the receiver data corresponding to the sender data.

The invention is characterized in that it has a table creation means, and the list shows the similarity between the sender's data and the receiver's data.

The feature of the present invention is that the sender's data and the receiver's data can be selected from at least any one of the categories of customers, enterprises, stores, goods, services, and regions.

The present invention is characterized by having an estimation processing means, which calculates estimation data based on actual data stored in a database.

The invention is characterized in that discretization processing is performed on the actual data, and the estimation data is calculated based on the discretized processing actual data and using an estimation processing means.

The present invention is characterized in that the estimated data calculated by the estimation processing means is used as customer data.

The present invention is characterized in that the estimated data calculated by the estimation processing means is used to supplement missing items of actual data and create customer data.

The present invention is characterized in that the estimated data is composed of a probability value or an estimated value after threshold value judgment of the probability value.

The present invention is characterized by having a table creation means for displaying customer data in a list of customer IDs.

The present invention is characterized in that it has a recommendation means which enables an arbitrary customer ID, Related to recommended media for companies, stores, products, services, or regions that have calculated an arbitrary similarity.

The present invention is characterized in that it has recommendation means for associating the recommended media corresponding to an arbitrary company ID, store ID, product, service ID, or area ID with a customer ID that has calculated an arbitrary similarity.

The present invention is characterized in that the terminal of the headquarters has a means for selecting the data of the sender and the data of the receiver, and a means for viewing the results of market research and analysis.

According to the market survey and analysis system of the present invention, high-precision market survey and analysis can be performed.

1‧‧‧Market survey and analysis system

2‧‧‧Server

3‧‧‧ Store Terminal

4‧‧‧ internet

5, 6‧‧‧ Customer Terminal

7‧‧‧Headquarters

Fig. 1 is a schematic diagram of a system of the present invention.

Figure 2 is a flowchart of the system of the present invention.

Figure 3 is a flowchart of the system of the present invention.

FIG. 4 is an example of a data table created in the system of the present invention.

FIG. 5 is an example of a data table created in the system of the present invention.

FIG. 6 is an example of a data table created in the system of the present invention.

FIG. 7 is an example of a data table created in the system of the present invention.

Figure 8 is a flowchart of the system of the present invention.

Figure 9 is a flowchart of the system of the present invention.

FIG. 10 is an example of a chart generated in the system of the present invention.

FIG. 11 is an example of a chart generated in the system of the present invention.

FIG. 12 is an example of a chart generated in the system of the present invention.

FIG. 13 is a diagram illustrating a process of calculating an approximation in the system of the present invention.

FIG. 14 is a diagram explaining a process of calculating an approximation in the system of the present invention.

FIG. 15 is an example of a data table showing an example of use of approximation in the system of the present invention.

Figure 16 is a flowchart of the system of the present invention.

As shown in FIG. 1, the market survey and analysis system 1 of the present invention is composed of the following components: an operating company system 2, which is composed of a server and a database group under the jurisdiction of the operating company; a store terminal 3 such as a POS terminal, It is connected to the operating company system 2 in a way that can transmit information and is installed in a corporate store; shop terminals 3 such as POS terminals are connected to the operating company system 2 in a way that can transmit information through the network 4; Customer mobile terminals 5 such as mobile phones and smartphones; customer computer terminals 6 (hereinafter referred to as customer terminals 5, 6); and terminals 7 etc. installed in the headquarters of the enterprise.

As shown in the flow chart of FIG. 2, the market survey and analysis system 1 of the present invention is composed of the following means: the actual data collection and storage means, which collects actual data as a previous stage of analysis; the estimation processing means, which is based on the actual Data to calculate estimated data; waveform generation means to generate waveforms based on customer data consisting of actual data and / or estimated data; synchronization rate calculation means to calculate approximations (hereinafter referred to as synchronization rates) based on the generated waveforms ); And recommended means, which are added as needed.

(Actual data collection and storage means)

The actual data collection and storage means will be described with reference to FIGS. 1 and 4. This method is used to collect actual data of customers as a preliminary stage of market research and analysis, and store the collected actual data in a database.

Actual data collection and storage in a service point management system (not shown) constructed independently of the market survey and analysis system of the present invention, or constructed as a part of the market survey and analysis system of the present invention Means are systematically aimed at when customers Use the identifier (hereinafter, customer ID) given to the customer during registration to collect actual data and store it in the database. In addition, generally, the customer ID is an arbitrary digit number or symbol that is different for each customer. As an example, the customer ID is recorded on the service point card held by the customer, and the customer ID can be read and entered by the store terminal 3 or the customer terminals 5 and 6.

The following shows examples of actual data collection. When customers use the system At the time of recording, the basic attribute data of the customer is transmitted from the shop terminal 3 or the customer terminals 5, 6 to the operating company system 2. The operating company system 2 receives the basic attribute data, associates each customer ID with actual data, and stores it in the basic attribute database. The items of the basic attribute data include, for example, gender, age, address, characteristics of the place of residence, and characteristics of the commute destination area.

In addition, whenever a customer joins a store of an affiliated company that joins market research and analysis system 1, When shopping at a shop or an EC site, the store terminal 3 or the headquarters terminal 7 transmits information, that is, the history system data and the customer ID are transmitted to the operating company system 2 and the operating company system 2 receives the history system data and the customer ID. And each customer ID is associated with the actual data of each item related to the history data and stored in the history database. The items of the history data include, for example, use of a company, purchase of goods or services, visit time or visit time, use of a store, and the like.

It is also possible to collect research funds collected based on customer responses. material. The customer transfers information from the customer terminals 5 and 6, that is, the research department data and the customer ID are transmitted to the server of the operating company system 2. The server receives the research department data and the customer ID, and the customer ID and The actual data of each item of the research department data are associated and stored in the research department database. Examples of the research-related data items include, for example, member questionnaires and intention flags. As a member questionnaire survey item, the married, unmarried distinction, the presence or absence of children, the status of the house, the annual income, and the presence or absence of a driver's license collected by customers who are members of the system in response to the questionnaire can be listed. In addition, as the intentional flag item, traditional intentions (intentionality of favoring traditional things), innovative intentions (intentionality of innovating things), and high-level intentions (likes of high-level things) can be listed to distinguish the consciousness of customers. Intentional) and other projects, In addition, an example of establishing a phased flag according to the level of each intentionality can be cited.

Furthermore, as an example of an item that can be added, a customer Network mobile data using the mobile status of communication networks such as roads. As the items of network mobile data, the access time to the communication network, the media used, and the sites used can be listed. In addition, as an example of other items that can be added, service points given based on the purchase amount can be cited. The service points granted when a customer makes a purchase are passed from the store terminal 3 or the headquarters terminal 7 to the operating company system 2, the server receives the service points, and associates the obtained service points with the customer ID The accumulated service points stored in the place are added up, and the service points are stored in the service point database at any time. In addition, the above items are examples, and the actual data collected and stored is not limited to these items.

(Estimated processing method)

Next, the estimation processing means will be described with reference to FIGS. 1 to 7. Use actual data collection and storage methods to store basic attribute data, history data, research data, network action data, service point data and other actual data in the basic attribute database, history data database, research data database, And other databases, and updated at any time. However, the collection and storage of actual data is not carried out for all items. For example, if you use the form creation method to create a performance data form as shown in Figure 4, the actual data will be displayed in a state associated with the customer ID. However, at this time, the items of the basic attribute data that have not been entered, and the store that the customer has not purchased Certain items, such as history-related items, or research-related items that have not responded to the questionnaire, may become missing information for a variety of reasons. In addition, some actual data may include prominent data that are not suitable as a basis for market research and analysis due to erroneous input by customers or stores. Therefore, in the estimation process, the estimated data is calculated based on the actual data, and the customer data is used to create and process the customer data that is the basis of market research and analysis.

If the operating company system 2 operates the estimation processing means, the estimation processing means will benefit. Probability inference algorithm, based on the actual data stored in the basic attribute database, research database, history database, points database, and other databases, etc., to estimate each item The data is estimated and processed. As an example of the probability inference algorithm, various methods such as a Bayesian Network, a Neural Network, and a Random Forest can be listed, but are not limited thereto.

Referring to Fig. 5, a first embodiment of the estimation process is shown. Figure 5 shows the estimates The processing means performs a probability inference and calculates a complete table of estimated data. The estimated data is composed of an estimated value obtained by using a threshold value to judge the probability value of the inferred result. The server of the operating company system 2 is based on the actual data of the items of other customers that have actual data close to the customer of the estimation target among the actual data of the project as the basis, and based on the probability inference algorithm, The corresponding probability of the data of each project is estimated. For example, when estimating the married probability of customer A (customer ID is 10001), the server of the operating company system 2 is based on actual data with other items (for example, gender data, age data, address data, history data) Etc.), the actual data of the item "the difference between married and unmarried" of other customers with actual data close to customer A, and calculate the probability of getting married for customer A (for example, the probability of getting married is 70% ). Similarly, when the history of customer A (e.g., ID 100001) is estimated to be the probability of purchasing "products" of company A in the data, the server of operating company system 2 is based on actual data with other items (e.g., , Gender data, age data, address data, history data), actual data of other customers' company A's "dish" items in actual data close to customer A, and calculate the purchased product "dish" The probability value (for example, the probability of purchasing the item "dish" is 10%). Furthermore, in terms of the nature of the project, for items whose actual information should be expressed as YES or NO, or 100% or 0% (such as the difference between married and unmarried), an estimation process can also be added. The estimation process is for the following The estimated value is judged. As for the estimated value, if the probability value is above the threshold value, it is YES, if it is below the threshold value, it is NO. Similarly, if it is above the threshold value, it is 100%, and if it is below the threshold value, it is 0. %. In addition, the threshold is variable. For example, when the threshold value of the inferred result of the married probability value of the customer A (for example, the married probability value is 70%) is set to 50%, the estimated value of the "married" of the customer A is calculated. to In the example of the complete data table shown in FIG. 5, after only estimating the missing items of actual data or performing the estimating processing on all items, only the missing items of actual data are associated with the estimated data. , And the actual data and the estimated data composed of the estimated values are used as customer data, but it can also be calculated only by the estimated data by estimating the processing of all items and associating all the items with the estimated data. Customer information.

In addition, at the stage of collecting and storing actual data, in order to exclude outstanding data, also For example, the value of the actual data may be rounded off, or the degree may be differentiated, and the discretization processing may be performed in various ways. After the discretized actual data is prepared, the discretized actual data is estimated. That is, the actual data used as the basis for the estimation process may be the collected actual data or the discretized actual data.

Referring to Fig. 6, a second embodiment of the estimation process is shown. Figure 6 shows a complete table of the probability inferences made by the estimation processing method, and the probability value of the inferred result is directly used as the estimated data, and the estimated data composed of the probability values is used to supplement the missing parts of the actual data. At this time, customer data composed of actual data and estimated data is calculated, and the estimated data is composed of probability values.

Referring to Fig. 7, a third embodiment of the estimation process is shown. FIG. 7 shows a complete table in which the estimation processing method performs probability inference and calculates the probability value of the inferred result as the estimated data directly, and uses the estimated data composed of the probability value to fill in all the items. At this time, the customer data for which all items are composed of estimated data is calculated, and the estimated data is composed of probability values.

In addition, as required, the form creation means is a complete form that is displayed so that each item of the list is associated with the customer data, as shown in FIGS. 5 to 7. In this way, a complete form with no blank columns associated with the customer data and the list can be provided in a visible manner.

(Waveform generation means)

The waveform generation means will be described with reference to FIGS. 8 to 12. Waveform generation means Means to draw data on a chart and make it waveform.

When the operating company system 2 operates the waveform generation means, the waveform generation means advances. A line drawing process (S1) of drawing customer data of each item corresponding to a category on the vertical axis is performed, and a waveform generating process (S2) of performing line charting is performed. For example, when the waveform of customer A is generated, as shown in FIG. 10, the horizontal axis is set as items, and the vertical axis is set as customer data (%), and each item related to customer A (for example, annual income level, smoking rate , Car ownership rate), and make it waveform. Thereby, the nature of the customer A is represented by a waveform. Similarly, it can also show the waveform of customer B.

In another form of the waveform generation method, the horizontal axis is set as an item, and the vertical axis is set as an item. For the customer data (%), the average value of the customer data of each item is calculated, a drawing process of drawing the averaged customer data is performed, and a waveform generation process of performing line charting is performed. For example, as shown in FIG. 11, when generating the waveform of the product G, set the horizontal axis as the item, and the vertical axis as the customer data (%), and calculate the customer's division with the historical data of the purchased product G. The average value of the customer data of each item is plotted and waveformized by averaging the customer data corresponding to each item of the product G (for example, annual income level, smoking rate, and car ownership rate). For example, the drawing process of the item "Smoking rate" of the product G is to calculate the average smoking rate of all purchasers of the product G or the customer data of the specific purchasers belonging to the specific layer such as gender and age, and for the item "Smoking "Ratio" uses the average value as customer data. After doing this for all projects, waveforms are generated. Thereby, the buyer layer of the product G is represented by a waveform. As shown in FIG. 12, the drawing process of the item “Advanced Intent” in Store A and Store B is to calculate the customer data of all users in the store A, or specific users belonging to a specific layer such as gender and age. The average value of the high-level intention, and the average value is plotted as the customer data for the item "high-level intention". After doing this for all projects, waveforms are generated. In addition, such waveform generation processing can of course be performed for customers, products, and stores, and can also be performed for analysis objects in various fields such as enterprises, regions, and ages. Figures 10 to 12 show the generation of two waveforms. Example, but it is also possible to generate 1 waveform and 3 or more waveforms. In addition, the line chart is suitable for calculating the synchronization rate described later, but other types of charts such as a curve chart, a function chart, a scatter chart, an area chart, and a radar chart can also be generated.

As shown in Figure 9, in order to compare multiple data, the sender data can be selected in advance And recipient information. Here, the so-called sender data refers to the average value of the member customer group based on attributes, intentions, purchase tendency, etc. used to calculate the approximation, that is, the synchronization rate; the so-called receiver data refers to the use of The average value of the target group to determine the synchronization rate with the sender's data, according to the target person or attribute, intention, purchase tendency, etc. For example, as shown in FIGS. 9 and 10, in order to compare the waveforms of customer data of customer A and customer B, the customer A (customer ID) is selected in the sender data, and the customer is selected in the receiver data. B (customer ID) (S1), and the server of the operating company system 2 extracts customer data (S2) corresponding to the customer ID of customer A and customer B (S2), and draws the customer data of customer A and customer B ( For example, a drawing process (S3) of annual income level rate, smoking rate, and car ownership rate is performed to perform waveform generation processing (S4) of graphing a line with each drawing.

As shown in FIG. 11, when customer A is selected in the sender profile, When the product G is selected from the data, the server of the operating company system 2 calculates the customer data of the customer A and the averaged customer data of the customer who has purchased the product G, and generates a waveform of the customer A and the product G.

Also, as shown in FIG. 12, when the store A is selected in the sender profile, the store A When store B is selected from the data, the server of the operating company system 2 extracts the averaged customer data of customers who have visited store A and the averaged customers of customers who have come to store B. Data to generate waveforms for store A and store B. The selection of the sender's data and the receiver's data can be selected in any of the following ways, that is, the customer-to-customer, business-to-business, product-to-commodity, regional-to-regional characteristics are selected from the same category, such as customer-to-company Products and shops are selected from different categories according to the characteristics of the area. Customers, companies, shops, goods, services, and districts can be selected. Various categories such as domain characteristics are selected as objects, and the combination of the categories is arbitrary. By generating the waveform in this way, the characteristics of the comparison target can be visually confirmed.

(Synchronization rate calculation method)

A description will be given of a synchronization rate calculation means as a means for calculating the approximation with reference to FIGS. 13 and 14. The so-called synchronization rate refers to the similarity of at least two or more waveforms generated by the waveform generation means. The synchronization rate is based on a means for calculating a difference between points of at least two or more waveforms generated by the waveform generating means, and a means for calculating a difference of line segment angles of at least two or more waveforms generated by the waveform generating means. Means for determining whether the difference between the points is within a threshold, means for determining whether the difference between the line segment angles is within a threshold, means for calculating a ratio of the difference between the points within a threshold, and calculating a ratio of the difference between the line angles within a threshold And the ratio of the difference between the points within the threshold and the ratio of the difference between the line segment angles within the threshold.

As shown in Figures 8, 9, 13, and 14, if the operating company system 2 uses the same The step rate calculation means operates, and the synchronization rate calculation means calculates a difference (probability difference) between the distances between the points of each drawing of the two or more waveforms generated by the waveform generation means described above (S4). In addition, the synchronization rate calculation means calculates the difference between the angles of each line and the line of the line chart (difference in line segment angles) (S5). In addition, a threshold judgment is performed to determine whether the calculated probability difference and the line segment angle are within the threshold (S6), and the ratio of the variables within the threshold to the whole, that is, the coincidence rate of the points and the coincidence rate of the waveform is calculated. The result of adding the coincidence rate to the coincidence rate of the waveform is divided by 2 to calculate the synchronization rate (S7).

Here, the term refers to the probability of the difference between a value representing a distance corresponding to the point of rendering to the difference between the probability values of the vertical axis, if the reference 13, is for example, when plotted item of sender information items X ₁ A (E.g., annual income level) where the probability is X ₁ A% (e.g., 75%), and the probability of the item X ₁ (annual income level) of the item of the recipient's data B is X ₁ B% (e.g., 73%) , Perform the calculation of X ₁ A% (75%)-X ₁ B% (73%) = probability difference Y ₁ % (2%), repeat the calculation for the points corresponding to all the items of X ₁ ~ X _n , Calculate the probability difference Y ₁ ~ Y _n . Then, when the value of the probability difference is at a threshold (for example, ± 5%), it is determined that the points are consistent, and when it is outside the threshold, the points are determined to be inconsistent. Furthermore, a coincidence rate is calculated for all points of calculation results.

The difference between the line segment angles refers to the difference between the angles of the lines of the line chart. If referring to FIG. 13, the line segment angle difference θ = θ ₁ -θ ₂ = tan _-1 D / C-tan- ₁ D '/ The calculation of C is repeated for lines corresponding to all items between X ₁ to X _n . Then, when the difference value of the line segment angle is within a threshold (for example, ± 3 °), it is determined that the waveforms are consistent, and when it is outside the threshold, the waveforms are determined to be inconsistent. Furthermore, the coincidence rate of waveforms for all calculation results is calculated.

In addition, according to the coincidence rate of the points and the coincidence rate of the waveforms obtained by the above calculation, the synchronization rate = (the coincidence rate of the points + the coincidence rate of the waveform) / 2 is used to calculate the approximate degree of the waveform, that is, the synchronization rate. In addition, the value of the threshold value can be set as a variable condition.

In addition, for charts other than line charts, such as a curve chart or a function chart, the difference between the probability difference and the line angle can be calculated based on the distance between arbitrary points of the curve, the distance between any points of the connection, and the angle of the connection. Furthermore, the waveform can be differentiated and the probability difference and the difference of the line angle can be calculated. In this way, the difference between the probability difference and the line segment angle can be obtained by using various calculation methods corresponding to each graph.

As shown in FIG. 15, the operating company system 2 may add a means of creating a list of synchronization rates of receiver data with respect to sender data. In the example of the list shown in FIG. 15, for the store A of the sender profile, the synchronization rate of the store B to the store L of the receiver profile is shown.

In this way, through the estimation processing means, waveform generation means, and synchronization rate calculation means, the synchronization rate, i.e., the approximation degree, between the customer-to-customer, business-to-business, and store-to-store equivalent categories, or the customer-to-business, customer-to-store, Customer-to-product, customer-to-region, business-to-product, store-to-product, and store-to-area synchronization rates, which are similarity degrees, and visualize the approximation, of course, can make the system helpful For the customer's recommendation operation, this system can also perform a variety of purposes such as analysis of items of the company or store, analysis of branch area, etc. 查 分析。 Check analysis.

(Recommended)

A description will be given of a recommended means as a means that can be additionally provided in the market survey and analysis system 1 of the present invention. The recommendation means is a means for providing a recommendation medium to customers who log in to the market research and analysis system 1. Examples of recommended media include gift vouchers issued by store terminals 3, etc .; advertisement-based emails sent from headquarters terminal 7 and server 2 to customer terminals 5, 6; membership login screens displayed on websites, etc. Customized advertising; direct mail advertising to customers, etc.

As shown in FIG. 16, if the server of the operating company system 2 operates the recommendation means, The recommendation means extracts the customer ID of the customer corresponding to the arbitrary synchronization rate with respect to the sender data (for example, store A). Then, the recommendation means uses a variety of output means, etc., to provide the extracted customer with a recommendation medium for store A corresponding to the sender's profile. As the output means of the recommendation media, there are various output means such as issuing a gift certificate of the store A to the store terminal 3 and the like corresponding to the customer ID of the extracted customer, and an e-mail address corresponding to the customer ID of the extracted customer Send an email containing the advertisement of shop A as the content; display the customized advertisement of shop A on the member login screen corresponding to the customer ID of the extracted customer; or, the address corresponding to the customer ID of the extracted customer Printed in the direct mail advertisement of shop A as the recipient.

Also, as another example of the recommendation means, the operating company system 2 The sender information (for example, customer A) extracts the enterprise ID of the company corresponding to the arbitrary synchronization rate, the store ID of the store corresponding to the arbitrary synchronization rate, or the product or service ID corresponding to the arbitrary synchronization rate. Next, the recommendation means utilizes various output means and the like to provide the extracted company, store, or recommendation media corresponding to the product or service to the customer ID of the customer A. As the output means of the recommendation media, there are various output means such as: issuing the extracted gift certificate of a company, a store, or a product or a service to the store terminal 3 and the like corresponding to the customer ID of the customer A; and issuing the customer ID to the customer A of the customer A Corresponding e-mail address sent to the extracted company, store, or product or service The advertisement is a content email; on the member login screen corresponding to the customer ID of customer A, the customized advertisement of the extracted company, store, or product or service is displayed; or, the customized advertisement corresponding to the customer ID of customer A is displayed The address is printed as the addressee in the direct mail advertisement of the selected company, store, or product or service.

In addition, in order to use the market survey and analysis system of the present invention, the affiliate company issues a login ID and password that can access the operating company system 2 and provides a browser for displaying market survey and analysis results, so that they can join as desired. The terminal 7 of the headquarters of the enterprise of the system uses the login ID and password to access the server of the operating company system 2 and can choose to enter the sender and receiver information, and can view the information obtained by the above-mentioned survey and analysis system 1. Market research and analysis results (customer information table, waveform chart, synchronization rate list, etc.).

Thus, according to the market survey and analysis system 1, it is possible to provide a system that can perform high-precision market surveys and analysis, and can provide the market survey and analysis results to the affiliated companies that are users of the market survey and analysis system in an easy-to-understand form. .

1‧‧‧Market survey and analysis system

2‧‧‧Server

3‧‧‧ Store Terminal

4‧‧‧ internet

5, 6‧‧‧ Customer Terminal

7‧‧‧Headquarters

Claims (15)

A market survey and analysis system, comprising: a waveform generating means for waveformizing customer data stored in a database; a means for calculating a difference between points of at least two or more waveforms generated by the waveform generating means; Means for determining the difference between line segment angles of at least two waveforms generated by the waveform generating means; means for determining whether the difference between the points is within a threshold; means for determining whether the difference between the line angles is within a threshold; calculating the points Means for calculating the ratio of the difference between the thresholds within the threshold; means for calculating the ratio of the difference between the line segment angles within the threshold; and based on the ratio of the difference between the points within the threshold and the difference between the line angles within the threshold Means for calculating the approximation of at least two waveforms. For example, the market survey and analysis system for item 1 of the patent application scope, in which the waveform generation means generates a line chart. For example, the market survey and analysis system of the first or second patent application scope, wherein the waveform generation means has a means for calculating the averaged customer data. For example, if the market survey and analysis system of the first or second patent application scope includes a means for selecting one or more sender materials and a means for selecting one or more receiver data, the waveform generation means generates the sender. The waveform of the data and the waveform of the receiver's data. The means for calculating the similarity of the waveform is to calculate the similarity of the waveform of the receiver's data corresponding to the sender's data. For example, the market survey and analysis system of the first or second scope of the patent application has a form creation method, and the list shows the similarity between the sender's data and the receiver's data. If you apply for the market survey and analysis system of item 1 or item 2, the sender's information and receiver's information can be selected from at least one of customers, enterprises, stores, goods, services, and regions. If you apply for the market survey and analysis system of item 1 or item 2, in which It has estimation processing means, which calculates estimation data based on the actual data stored in the database. If you apply for the market survey and analysis system of the first or second patent scope, the actual data is discretized, and the estimated data is calculated based on the discretized actual data and the estimation processing means. If you apply for the market survey and analysis system in the first or second scope of the patent, the estimated data calculated by the estimated processing means is used as customer data. For example, if you apply for the market survey and analysis system for item 1 or item 2 of the patent scope, the estimated data calculated by the estimated processing method will supplement the missing items of the actual data and create customer data. For example, the market survey and analysis system for item 7 of the scope of patent application, wherein the estimated data is composed of the probability value or the estimated value after threshold value judgment of the probability value. For example, the market survey and analysis system of the first or second patent application scope has a form creation method that displays customer data for a list of customer IDs. For example, the market survey and analysis system of the first or second patent application scope has a recommendation method that recommends any customer ID to a company, store, product, service, or area that has calculated any similarity. Media association. For example, the market survey and analysis system for item 1 or 2 of the scope of patent application, which has a recommendation method, which uses the recommended media corresponding to any company ID, store ID, product, service ID or area ID to calculate Customer IDs with arbitrary similarity are associated. For example, the market survey and analysis system of the first or second scope of the patent application, in which the terminal of the headquarters has the means for selecting the information of the sender and the receiver, and the means of viewing the results of the market survey and analysis.