Support device for analyzing customer lifetime value

Abstract

To provide a support device for analyzing a customer lifetime value that efficiently analyzes the customer lifetime value while complying with a personal information protection regulation even when a plurality of advertisement platforms are used in combination.SOLUTION: A support device 1 of the present invention includes: a viewing information reception unit 112 that receives data indicating behavior of viewers on each of a plurality of advertisement platforms for each customer; a behavior information reception unit 113 that receives, for each customer, data indicating behavior of an action taker in a transaction execution platform; and a statistical processing unit 114 that aggregates, on the basis of data indicating the behavior of the viewers received for each customer and data indicating the behavior of the action taker received for each customer, quantitative data and / or qualitative data related to the action taken by the customer on a web for each type of platform that the viewer first accessed from among a plurality of advertisement platforms.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a support device for customer lifetime value analysis (also simply referred to as "support device"). [Background technology]

[0002] Customer lifetime value (LTV) refers to the total profit a customer brings to a business throughout the entire period from the start of a transaction between the business and the customer to the end of the transaction. Currently, customer lifetime value is gaining importance among various businesses.

[0003] The background to this is that depending on the customer's attributes, the cost performance of the business owner changes, and so does the profit margin. Also, there is the issue of a declining birthrate and aging population, and in order for businesses to survive in developed markets, especially in Japan, it is important to not let go of existing customers once they have been acquired. Therefore, it is necessary to be aware of the behavior exhibited by customers according to their attributes and to carry out appropriate marketing.

[0004] From this perspective, businesses are placing emphasis on strategies to increase customer lifetime value in their marketing strategies, and this also applies to online marketing.

[0005] Traditionally, advertising using cookies has been emphasized in online marketing. Generally, a cookie is a mechanism that temporarily stores information about a user who accesses a web server in the browser. When a cookie is enabled, information that can identify the user specified by the web server that accessed the cookie for the first time is stored on the user's device as a cookie file.

[0006] On subsequent visits, the information stored on the user's device will be sent to the web server, allowing for smoother provision of information to the user and improving the user experience on the website.

[0007] Cookies are broadly classified into two types: first-party cookies and third-party cookies.

[0008] First-party cookies are cookies issued by the web server the user is visiting. First-party cookies may contain browsing history, login information, product information in a shopping cart on an e-commerce site, personal information, etc.

[0009] On the other hand, third-party cookies are cookies issued by websites other than the one the user is visiting. Third-party cookies are used by advertisers and others to store user information, and may be used across multiple websites.

[0010] Meanwhile, with the advancement of internet technology, personal information protection regulations have been strengthened since the latter half of the 2010s, primarily in Europe and the United States. Particularly well-known examples of such personal information protection regulations include the European Union's General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA).

[0011] These personal information protection regulations require businesses handling personal information to obtain the consent of individuals for a wide range of actions, including the acquisition, modification, transfer outside the region or to a third party, deletion, etc. As a result, there is a growing movement to impose restrictions on the use of personal information on the Internet, particularly among platform operators.

[0012] In particular, third-party cookies are subject to functional blocking in many web browsers, which has led to concerns about the accuracy of retargeting ads that use third-party cookies and the accuracy of conversion measurement.

[0013] In response to strengthened regulations on personal information, in the field of online marketing, it has become difficult to share personal information among multiple service providers, and personal information is being anonymized. As a result, analysis of customer lifetime value requires a certain degree of inference-based analysis, and in particular, tracking customer behavior across multiple advertising platforms, SNS (Social Networking Sites), etc. has become practically difficult (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0014] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-207020 Summary of the Invention [Problem to be solved by the invention]

[0015] However, many businesses are now conducting marketing that combines multiple advertising platforms, transaction execution platforms, and social media. For example, the beauty salon industry uses Hot Pepper Beauty, LINE, Facebook, and Instagram (all registered trademarks, the same applies below) in a complex manner.

[0016] For this reason, even when multiple advertising platforms and transaction execution platforms are used in combination, it is necessary to efficiently analyze customer lifetime value while complying with personal information protection regulations. [Means for solving the problem]

[0017] As a result of intensive research into solving the above-mentioned problems, the inventors have found that when an advertiser conducts advertising and transactions using a server directly or indirectly managed by the advertiser, multiple advertising platforms, and a transaction execution platform, the above-mentioned object can be achieved by receiving, in association with each other, customer behavior on the server and the behavior of viewers on the advertising platform, and customer behavior on the server and the behavior of action takers on the transaction execution platform, and aggregating quantitative data and / or qualitative data regarding customer behavior for each customer. As a result, the inventors have completed the present invention.

[0018] The present invention tracks customer behavior from an advertisement that introduced customers to the transaction execution platform through social media (e.g., LINE (registered trademark)) to a final action, such as a reservation. This allows the present invention to track the entire series of customer actions leading up to a reservation, including pre-reservation communications, such as so-called step emails, which are messages automatically sent to customers who have taken a specific action. The present invention can also provide statistics such as customer lifetime value (LTV) measured for each reservation introduction path or each service initially selected. This allows the present invention to measure new customer introduction paths, communications with new customers, and LTV for each service ordered by new customers, providing store managers with indicators for identifying key points for improving their operations. Furthermore, the present invention contributes to identifying synergistic effects resulting from the combination of introduction paths and service providers.

[0019] One aspect of the present invention is a system for providing a method of providing a service that includes: a customer behavior acquisition unit that acquires, from a server managed directly or indirectly by an advertiser, data indicating the behavior of customers who use the server; a viewing information receiving unit that receives, from a plurality of advertising platforms, data indicating the behavior of viewers of advertisements of the advertiser posted via the advertising platform, which associates the viewers with the customers; an action information receiving unit that receives, from the transaction execution platform, data indicating the behavior of action takers, which associates the action takers of payments or reservations via the transaction execution platform with the customers; and a statistical processing unit that aggregates statistics regarding the behavior of the viewers and the behavior of the action takers in the plurality of advertising platforms in association with the behavior of the customers, wherein the viewing information receiving unit receives data from the plurality of advertising platforms in association with the behavior of the customers. The action information receiving unit receives data indicating the behavior of the viewer on each of the platforms for each customer, the action information receiving unit receives data indicating the behavior of the action performer on the transaction execution platform for each customer, the statistical processing unit compiles quantitative data and / or qualitative data regarding the actions performed by the customer for each type of advertising platform that the viewer first accessed among the plurality of advertising platforms based on the data indicating the behavior of the viewer received for each customer and the data indicating the behavior of the action performer received for each customer, and the statistical processing unit combines and compiles the classification information and the statistical amount to provide a customer lifetime value analysis support device that contributes to optimizing the advertiser's marketing measures.

[0020] In the present invention, a customer lifetime value analysis support device includes a customer behavior acquisition unit, a viewing information receiving unit, and an action information receiving unit. This allows data indicating the behavior of customers using a server managed directly or indirectly by an advertiser to be acquired. Data indicating the behavior of viewers of an advertiser's advertisement posted via the advertising platform, which associates the viewer with the customer, can be received from multiple advertising platforms. Furthermore, data indicating the behavior of the action performer, which associates the action performer with the customer, can be received from a transaction execution platform.

[0021] This allows for the receipt of data on the behavior of viewers on each of multiple advertising platforms for each customer, while still complying with personal information protection regulations. Similarly, it also allows for the receipt of data on the behavior of action takers on a transaction execution platform for each customer.

[0022] In addition, in the present invention, the customer lifetime value analysis support device includes a statistical processing unit, which makes it possible to aggregate statistics on the behavior of viewers across multiple advertising platforms in association with actions taken by customers.

[0023] The statistical processing unit compiles statistics for each type of advertising platform that a viewer first accessed from among multiple advertising platforms based on the data on viewer behavior received for each customer and the data on action taker behavior received for each customer, and at that time, compiles quantitative data and / or qualitative data on the actions taken by customers on the web.

[0024] As described above, even when multiple advertising platforms are used in combination, it is possible to efficiently analyze customer lifetime value while complying with personal information protection regulations.

[0025] Furthermore, by efficiently analyzing customer lifetime value while complying with personal information protection regulations, the following secondary effects can be expected:

[0026] First, by aggregating statistics on customer behavior on the web for each type of advertising platform that a viewer first accessed, it is possible to analyze for each customer how the type of advertising platform and the content of each advertising platform affect customer behavior.

[0027] This allows you to evaluate the effectiveness of each advertising platform and conduct more effective analysis of customer lifetime value.

[0028] For example, consider a beauty salon. In the case of a beauty salon, the type of advertising platform that customers first view, also known as a landing page, can affect the occurrence of customer behavior.

[0029] By aggregating data on viewer behavior on each of multiple advertising platforms for each customer, it is possible to more accurately understand the impact that placing advertisements on a specific advertising platform has on the lifetime value of a beauty salon's customers.

[0030] In the case of a beauty salon, the probability of a customer's future actions may differ depending on the menu that the customer has reserved. For example, customers who select a haircut may have a low repeat rate.

[0031] By aggregating data on the behavior of action takers on the transaction execution platform for each customer, it is possible to more accurately understand the impact of each type of action on the lifetime value of a beauty salon customer.

[0032] In addition to the configuration of the present invention described above, by additionally adopting various configurations related to the innovation of the aggregation method, it is possible to grasp the trends in customer behavior and the impact of each advertising platform on customer lifetime value more accurately and in more detail. [Effects of the Invention]

[0033] According to the present invention, even when multiple advertising platforms and transaction execution platforms are used in combination, customer lifetime value can be analyzed efficiently while complying with personal information protection regulations. According to the present invention, by collecting and analyzing customer behavior data across multiple advertising platforms and transaction execution platforms while taking personal information protection regulations into consideration, advertisers can more accurately grasp customer lifetime value and optimize their marketing strategies. This was difficult to achieve with conventional analysis based on a single platform. [Brief explanation of the drawings]

[0034] [Figure 1] FIG. 1 is a block diagram showing an example of the hardware and software configuration of a system S according to this embodiment. [Figure 2] FIG. 2 is a main flowchart showing an example of a preferred flow of the customer lifetime value analysis process executed by the support device 1 of this embodiment. [Figure 3] FIG. 3 is a flowchart showing an example of a preferred flow of a customer lifetime value analysis process taking parallel execution into consideration. [Figure 4] FIG. 4 is a continuation of FIG. [Figure 5] FIG. 5 is a continuation of FIG. DETAILED DESCRIPTION OF THE INVENTION

[0035] Hereinafter, an example of an embodiment of the present invention will be described in detail with reference to the drawings.

[0036] <System S> FIG. 1 is a block diagram showing an example of the hardware configuration and software configuration of the system S of this embodiment. An example of a preferred embodiment of the system S of this embodiment will be described below with reference to FIG. 1. The system S of this embodiment is configured to include a support device 1. The support device 1 is capable of communicating with one or more advertiser terminals (hereinafter, sometimes simply referred to as "terminals T") via a network N.

[0037] [Support device 1] The support device 1 realizes each software component shown in FIG. 1 using hardware components such as a control unit 11, a memory unit 12, and a communication unit 13. Then, the support device 1 receives, using each software component, the behavior of customers on the advertiser server and the behavior of viewers or action takers on the advertising platform or transaction execution platform, in association with each other. "Customers" are also referred to as "users." Then, for each customer, a customer lifetime value analysis process is executed to compile quantitative data and / or qualitative data related to the actions performed by the customer. The type of the support device 1 is not particularly limited. The type of the support device 1 may be, for example, various server devices, cloud servers, etc.

[0038] In this embodiment, the term "advertising platform" refers to a virtual space on the Internet that displays a group of content and is operated by an operator different from the advertiser, and that can display advertisements. Taking the example of a beauty salon, more specific examples include social networking sites such as Hot Pepper Beauty, Facebook, and Instagram.

[0039] In this embodiment, the "transaction execution platform" refers to a virtual space on the Internet that displays a group of content, is operated by an operator different from the advertiser, and allows customers to execute transactions they desire. In the case of a beauty salon, a more specific example would be LINE.

[0040] [Control unit 11] The control unit 11 includes a central processing unit (CPU), a random access memory (RAM), a read only memory (ROM), and the like.

[0041] The control unit 11 cooperates with the storage unit 12 and / or the communication unit 13 as necessary. The control unit 11 then realizes software components of the program of this embodiment executed by the support device 1, such as an advertiser server registration unit, a platform registration unit, a display command unit, a data management unit, a customer behavior acquisition unit 111, a browsing information receiving unit 112, an action information receiving unit 113, a statistical processing unit 114, and a content generation unit 115. Details of each software component will be explained later through the flow of the customer lifetime value analysis process executed by the support device 1 of this embodiment.

[0042] [Storage section 12] The memory unit 12 is a device in which data and / or files are stored, and includes a storage unit that stores data non-temporarily using a hard disk, a semiconductor memory, a recording medium, a memory card, or the like.

[0043] The storage unit 12 stores programs executed by the microcomputer, a database 121, and the like.

[0044] Various data are stored for each advertiser or in association with the identification information of a specific advertiser in this database 121. Specific examples of such data include a series of information related to the advertiser server, a series of information related to the advertising platform, information indicating customer behavior on the advertiser server, information indicating viewer behavior on the advertising platform, and information obtained by statistically processing such information.

[0045] [Communications Section 13] The communication unit 13 is not particularly limited as long as it connects the support device 1 to the network N and enables communication with the terminal T, etc. An example of the communication unit 13 is a network card compatible with the Ethernet standard.

[0046] [Network N] The type of the network N is not particularly limited as long as it allows the support device 1 and the terminal T to communicate with each other. The type of the network N is, for example, the Internet, a mobile phone network, a wireless LAN, or the like.

[0047] [Terminal T] There is no particular limitation on the type of terminal T. The terminal T may be, for example, a personal computer, a laptop computer, a smartphone, a tablet terminal, or the like.

[0048] The terminal T is operated by the advertiser and transmits commands to the support device 1 via the communication unit 13. For example, the terminal T commands the support device 1 to register information about the advertiser server. The terminal T may also command the support device 1 to register information about the advertising platform.

[0049] Furthermore, when terminal T instructs the support device 1 via the communication unit 13 to display data regarding customer lifetime value, the control unit 11 instructs terminal T via the display command unit to display data regarding customer lifetime value.

[0050] [Main flowchart of customer lifetime value analysis process] 2 is a main flowchart showing an example of a preferred flow of the customer lifetime value analysis process executed by the support device 1 of this embodiment. The following describes an example of a preferred flow of the customer lifetime value analysis process executed by the support device 1 of this embodiment, with reference to FIG. 2.

[0051] First, as part of the customer lifetime value analysis process, the support device 1 receives the behavior of customers in the advertiser server in association with the behavior of viewers or action takers in the advertising platform or the transaction execution platform. Then, it executes a series of processes to tally quantitative data and / or qualitative data related to the actions shown by each customer. Steps S1 to S8 are an example of this process.

[0052] [Step S1: Register the advertiser server] When a command is received from terminal T, control unit 11 cooperates with memory unit 12 and communication unit 13 to register information relating to a server directly or indirectly managed by an advertiser (hereinafter also referred to as "advertiser server"). Note that when no command is received from terminal T, step S1 may be skipped and the process may proceed to step S2 or step S3.

[0053] The advertiser server registration unit instructs the display command unit to display the registration form on terminal T. Note that, unless otherwise specified below, any "registration form" does not have to be a single form, and may be divided into multiple forms.

[0054] The advertiser server registration unit may receive the address (URL: Uniform Resource Locator) of the advertiser server, information about the content, and information about the API (Application Programming Interface) provided by the advertiser server as needed, via the communication unit 13. Then, this information is stored in the database 121 via the data management unit.

[0055] The information about the API includes an API key issued by the advertiser server, an API secret key, an API access token, the name of the service provider of the advertiser server, and authentication information for logging in to the advertiser server.

[0056] The advertiser server registration unit may also receive the content itself provided by the advertiser. In this case, the advertiser server may be configured so that when a customer attempts to access a web page on the advertiser server, the customer is automatically redirected to a web page managed by the support device 1.

[0057] At this time, the advertiser server registration unit may receive setting information related to the forwarding service via the communication unit 13. At this time, the advertiser server registration unit may register various setting information, such as registering only a part of the address assigned to the advertiser server.

[0058] At the end of step S1, the control unit 11 moves the process to step S2.

[0059] [Step S2: Register your platform] When a command is received from terminal T, control unit 11 executes registration of information relating to the advertising platform and the transaction execution platform in cooperation with memory unit 12 and communication unit 13. Note that when no command is received from terminal T, step S2 may be skipped and the process may proceed to step S3.

[0060] The platform registration unit instructs the terminal T via the display command unit to display the registration form.

[0061] The platform registration unit may receive information regarding the addresses of the advertising platform and the transaction execution platform, information regarding content, and, if necessary, information regarding APIs provided by the advertising platform and the transaction execution platform, via the communication unit 13. Then, this information is stored in the database 121 via the data management unit. At this time, the platform registration unit may register various setting information, such as registering only a portion of the addresses assigned to the advertising platform and the transaction execution platform.

[0062] Information about the API includes the API key issued by the advertising platform and the transaction execution platform, the API secret key, the API access token, the names of the service providers of the advertising platform and the transaction execution platform, and authentication information for logging in to the advertising platform and the transaction execution platform.

[0063] Regarding APIs provided by advertising platforms, Facebook offers an API called CPAI (Conversion Application Programming Interface). Other advertising platforms (e.g., Instagram) also offer APIs with similar functions. Furthermore, transaction execution platforms, such as LINE, offer APIs with functions similar to CAPI. These APIs, including CAPI, can receive data indicating customer behavior on the advertiser's server (hereinafter also referred to as "customer behavior data") and transmit data indicating the behavior of viewers of the advertiser's advertisements posted via the advertising platform, associating them with customers (hereinafter also referred to as "viewing information data"). Furthermore, by receiving customer behavior data, they can transmit data indicating the actions of action performers on the transaction execution platform (hereinafter also referred to as "action information data"). Action execution data includes pre-reservation communications, such as so-called step emails, which are messages automatically sent to customers who have taken a specific action.

[0064] The platform registration unit may be divided into an advertising platform registration unit and a transaction execution platform registration unit. In this case, the display command unit commands terminal T to separately display a registration form for the advertising platform and a registration form for the transaction execution platform. The advertising platform registration unit then registers various information related to the advertising platform. The transaction execution platform registration unit also registers various information related to the transaction execution platform.

[0065] At the end of step S2, the control unit 11 moves the process to step S3.

[0066] [Step S3: Obtain customer behavior data] When a command is received from the terminal T, the control unit 11 cooperates with the memory unit 12 and the communication unit 13 to execute the customer behavior acquisition unit 111. The customer behavior acquisition unit 111 acquires, from the advertiser server, data on the behavior of customers who use the server. Note that if the customer behavior data has already been acquired at this point, step S3 may be skipped and the process may proceed to step S4.

[0067] Here, the customer behavior data includes classification information (for example, type, item, person in charge, store, region, etc.) associated with the sale and / or provision of goods and / or services selected and / or purchased by the customer.

[0068] By obtaining this data indicating customer behavior, including, for example, classification information, from the advertiser server, the advertiser can analyze, for each customer, the impact that the advertisement had on the customer and the customer's behavior as a result.

[0069] In addition, in order to enable analysis related to type, item, person in charge, store, or region, the above classification information can be, more specifically, at least one selected from the group consisting of identification information related to the type and item of the product or service, identification information of the person in charge who sold and provided the product or service, and identification information of the store and region where the product or service was sold or provided.

[0070] Let's take a beauty salon as an example of this classification information. Beauty salons are a place where competition is relatively fierce among businesses, and each business actively advertises and promotes. In addition, there are a certain number of customers who frequently change salons. Therefore, by obtaining the above data showing the behavior of each customer, it becomes possible to more accurately analyze customer lifetime value.

[0071] Taking a beauty salon as an example, the type of service related to the classification information refers to the menu of services such as haircut, color, damage care, and hair quality improvement. The identification information of the person in charge related to the classification information refers to the name of the hairdresser or barber. The identification information of the store and area that provided the service related to the classification information refers to the branch name and address, as well as the name of the area or administrative district where they are located.

[0072] In the case of a beauty salon, customer lifetime value may vary depending on the menu. It may also vary depending on the hairdresser or barber in charge. Customer behavior may differ depending on the region, which may affect customer lifetime value. Therefore, acquiring this information as classification information can lead to a more accurate analysis of customer lifetime value. Furthermore, acquiring this information as classification information allows for even more accurate analysis, including combination with the advertising platform from which customers are coming. Using classification information, customer behavior can be analyzed by advertising platform, product / service type, and initial menu selection, enabling the development of more detailed marketing strategies. Furthermore, combining classification information with statistics can provide insights that directly lead to advertising optimization and product / service improvement.

[0073] At the end of step S3, the control unit 11 moves the process to step S4.

[0074] [Step S4: Receive browsing information data] When a command is received from the terminal T, the control unit 11 cooperates with the storage unit 12 and the communication unit 13 to execute the browsing information receiving unit 112. The browsing information receiving unit 112 is capable of receiving browsing information data from a plurality of advertising platforms.

[0075] Then, in step S4, the browsing information receiving unit 112 receives browsing information data for each customer in each of the multiple advertising platforms.

[0076] This allows us to understand the behavior of each viewer on multiple advertising platforms for each customer, thereby obtaining data that can be analyzed to determine which advertising platform a customer accessed and which resulted in various actions.

[0077] Take a beauty salon for example. In the case of a beauty salon, the occurrence rate of customer behavior can vary depending on the type of advertising platform that customers first view, also known as a landing page. For example, it is known that customers who first view a specific advertising platform have a low rate of repeat visits after visiting the salon.

[0078] By being able to understand the behavior of viewers on each of multiple advertising platforms for each customer, it is also possible to analyze the behavior of customers who first viewed a particular advertising platform for each advertising platform.

[0079] At the end of step S4, the control unit 11 moves the process to step S5.

[0080] [Step S5: Receive action information data] When a command is received from the terminal T, the control unit 11 operates the action information receiving unit 113 in cooperation with the storage unit 12 and the communication unit 13. The action information receiving unit 113 is capable of receiving action information data from the transaction execution platform.

[0081] Then, in step S5, the action information receiving unit 113 receives action information data in the transaction execution platform for each client.

[0082] This allows the actions of the action takers on the trading execution platform to be understood for each customer, thereby providing data that can be used to analyze what actions the customer has taken on the trading execution platform.

[0083] Take a beauty salon, for example. Some beauty salons use transaction platforms like LINE, which allow them to make reservations, make payments, earn points, and order products and services. For example, customers who view ads on advertising platforms like Facebook may be invited to LINE to make reservations. Alternatively, customers may make reservations directly through a reservation site like Hot Pepper Beauty, a registered trademark of Hot Pepper. By examining these referral channels, it is possible to calculate statistics related to LTV, such as repeat customer rates, for each referral channel. Additionally, by calculating statistics for each staff member responsible for providing services for each referral channel, it is possible to identify the performance of staff members by referral channel, such as identifying specific staff members with high repeat customer rates on Hot Pepper, which generally has a low repeat customer rate.

[0084] By understanding the behavior of traders on the trade execution platform for each customer, it becomes possible to analyze the behavior of action takers on the action execution platform for each customer.It also becomes possible to analyze customer lifetime value according to the type of action.

[0085] At the end of step S5, the control unit 11 moves the process to step S6.

[0086] [Step S6: Aggregate statistics] When a command is received from the terminal T, the control unit 11 cooperates with the storage unit 12 and the communication unit 13 to execute the statistical processing unit 114. The statistical processing unit 114 is capable of aggregating statistics on the behavior of viewers and the behavior of action performers in multiple advertising platforms in association with customer behavior.

[0087] In step S6, the statistical processing unit 114 compiles quantitative data and / or qualitative data regarding the actions shown by customers for each type of advertising platform that the viewer first accessed from among multiple advertising platforms, based on the browsing information data received for each customer in step S4 and the action information data received for each customer.

[0088] Here, quantitative data can include the frequency, absolute number, occurrence rate, etc. of each action item described below. For example, it can include the number of clicks on a specific link, the number of clicks per user, the number of clicks per day, the number of clicks per number of times a specific page is viewed, etc.

[0089] Furthermore, the qualitative data may include data relating to specific types of actions, such as pressing a purchase button, pressing a payment button, pressing a reservation button, etc.

[0090] Therefore, "aggregating statistics on viewer behavior and action performer behavior on multiple advertising platforms in association with customer behavior" includes the following aggregations. For example, aggregation of the number of reservations made by viewers who clicked on a link in a specific advertising platform as action performers. It also includes analyzing whether the most common action taken by viewers who viewed a specific advertising platform as action performers was clicking a purchase button or a reservation button.

[0091] By aggregating quantitative and / or qualitative data regarding the actions taken by customers for each type of advertising platform that a viewer first accessed, it is possible to analyze for each customer how the type of advertising platform and the content of each advertising platform affect the actions taken by the customer.

[0092] This allows you to evaluate the effectiveness of each advertising platform and conduct more effective analysis of customer lifetime value.

[0093] Take a beauty salon as an example. As mentioned above, in the case of a beauty salon, the occurrence rate of customer behavior can vary depending on the type of advertising platform that customers first view, also known as a landing page. For example, it is known that customers who first view a specific advertising platform have a low rate of repeat visits after visiting the salon.

[0094] By aggregating quantitative and / or qualitative data on the behavior of viewers and the behavior of action takers on each of multiple advertising platforms for each customer, it is possible to more accurately grasp the impact on the lifetime value of customers of a beauty salon due to the placement of advertisements, etc. on a specific advertising platform. It is also possible to more accurately grasp the impact on customer lifetime value according to the actions taken by customers of a beauty salon.

[0095] In addition, when aggregating the quantitative data and / or qualitative data, the statistical processing unit 114 may aggregate the quantitative data and / or qualitative data for a predetermined period and analyze changes and increases / decreases in the quantitative data and / or qualitative data over multiple predetermined periods.

[0096] For example, the predetermined period may be a predetermined time ranging from one hour to several hours, or may be a period ranging from one day to several days, or may be a period of one week, 28 days, one month, or one year.

[0097] Furthermore, when tabulating the quantitative data and / or qualitative data, the statistical processing unit 114 may further tabulate the quantitative data and / or qualitative data for each piece of classification information described in step S3.

[0098] By adopting these configurations, it is possible to gain a more accurate and detailed understanding of customer behavior trends and the impact of each advertising platform on customer lifetime value.

[0099] At the end of step S6, the control unit 11 moves the process to step S7.

[0100] [Step S7: Calculate content statistics] When receiving an instruction from the terminal T, the control unit 11 further executes the statistical processing unit 114 in cooperation with the storage unit 12 and the communication unit 13. In step S7, the statistical processing unit 114 further compiles quantitative data and / or qualitative data regarding actions shown by customers for each piece of content on an advertising platform viewed by the viewer among multiple advertising platforms, based on the viewing information data and action information data received for each customer.

[0101] This allows for detailed analysis of what actions customers took in response to the type and content of specific content posted on the advertising platform, making it easier to conduct detailed analysis of customer lifetime value according to the status of content on the advertising platform.

[0102] (About statistics) The statistics compiled by the statistical processing unit 114 include various indicators calculated based on the received browsing information data and / or action information data, such as the new next reservation rate, existing next reservation rate, actual repeat rate, actual LTV value, predicted LTV value, and store purchase rate. These various indicators preferably include the number of inquiries. Furthermore, these various indicators are preferably aggregated in association with the content on the advertising platform that the viewer first viewed, as well as one or more of the above-mentioned classification information, the content of communication on the SNS, the first service used, the person who provided the service, the store where the service was provided, and the time when the service was provided. Furthermore, these various indicators are preferably designed to facilitate comparison of actual values ​​and predicted values. The following is an example of an indicator designed in this way.

[0103] The new next reservation rate is the percentage of new customers who have made a next reservation. The existing next reservation rate is the percentage of existing customers who have made a next reservation. By aggregating the new next reservation rate and the existing next reservation rate, the support device 1 can provide an indicator of whether services, etc. are being provided as specified. In order to align the periods that form the unit of management indicators and make them easier to consider, it is preferable that these next reservation rates be aggregated in units of periods that are aligned with other management indicators (for example, the period from the beginning of the month to the end of the month).

[0104] The actual repeat rate is the actual repeat rate excluding customers who canceled after making a reservation. By aggregating the actual repeat rate, the support device 1 can provide an indicator of whether or not a system is in place that makes it less likely for cancellations to occur after a reservation.

[0105] The actual LTV value is an index calculated using the formula: "average store visit cost per visit for a specified period (e.g., the past 365 days) × average store visit frequency for the specified period ÷ (1 - actual repeat rate for the specified period)." The predicted LTV value is an index calculated using the formula: "average store visit cost per visit for a specific period (e.g., the past 30 days) × (average store visit frequency for the specified period ÷ specified store visit cycle (e.g., 30 days)) ÷ (1 - average next reservation rate for the specified period)." A comparison between the actual LTV value and the predicted LTV value provides an index indicating whether service-related measures (e.g., price changes, service procedure changes, etc.) are having the expected impact on LTV. Therefore, by aggregating the actual LTV value and the predicted LTV value, the support device 1 can provide an index indicating whether service-related measures are having the expected impact on LTV through this comparison. Specifically, the actual LTV value is calculated based on data that is constantly updated daily. On the other hand, the predicted LTV value is a predicted LTV value based on the store visit cycle set, etc., on the management screen. By calculating these, the support device 1 can provide an index that can be used to confirm whether the predicted LTV value will actually increase as expected relative to the actual LTV value when measures such as increasing the unit price or improving the manual for next reservations are implemented, by comparing these. The actual LTV value is the actual measurement of customer lifetime value based on past performance data, and is an index that indicates the current customer value. On the other hand, the predicted LTV value is the predicted value of future customer lifetime value based on current customer behavior data, and is an index that predicts changes in customer value due to measures. By comparing the two, the effectiveness of the measures can be grasped more accurately.

[0106] The store purchase rate (store sales ratio) is an index related to store sales, which is the sales of products at the store that provides the service, and is calculated by the formula "store sales / total sales." By aggregating the store sales ratio, the support device 1 can provide an index of whether the service, etc. related to the sales of products is being provided as specified.

[0107] The support device 1 of this embodiment includes a configuration for aggregating the above-mentioned indices designed to facilitate comparison between actual and predicted values. This allows the support device 1 to visualize the impact of measures on revenue, making it easier to present the effectiveness of management guidance to the manager. Furthermore, the support device 1 provides the manager with indices for identifying key points for improving store management by measuring new customer acquisition routes, communication with new customers, and the LTV for each service ordered by new customers. This allows the support device 1 to provide an index for identifying the synergistic effect of combining acquisition routes and service providers.

[0108] For example, consider a beauty salon. Assume that the advertising platform used by the beauty salon contains videos showing the treatment process and photos of hair after the treatment. Processing by the statistical processing unit 114 makes it possible to analyze which of the customers who viewed the videos and the photos led to a reservation at the beauty salon. This makes it possible to analyze the impact of the videos and photos on customer behavior and customer lifetime value.

[0109] At the end of step S7, the control unit 11 moves the process to step S8.

[0110] [Step S8: Generate content] When a command is received from the terminal T, the control unit 11 cooperates with the storage unit 12 and the communication unit 13 to further execute the content generation unit 115. The content generation unit 115 is capable of generating content to be posted on the advertising platform, and is equipped with a large-scale language model and generative artificial intelligence (AI) as necessary.

[0111] The content generation unit 115 generates content that can realize the customer's action desired by the advertiser based on the correlation between the content of information displayed in the content on the advertising platform viewed by the viewer and the quantitative and / or qualitative data regarding the customer's action aggregated for each content. In this case, the large-scale language model and the generation AI may be machine-learned based on the action information data and statistics obtained in step S7.

[0112] This allows each piece of content to incorporate content characteristics that tend to facilitate customer behavior desired by the advertiser, such as making a reservation at a beauty salon. This allows business owners to improve the efficiency of their marketing. Finally, the control unit 11 returns the customer lifetime value analysis process to step S1, and repeats the processes from step S1 to step S8.

[0113] In this embodiment, step S7 or step S8 may be skipped. In this case, the customer lifetime value analysis process may return to step S1 upon completion of step S6 or step S7. The execution order of steps S1 to S8 is not limited to the above-described flow. Some of steps S1 to S8 may be executed in parallel. FIG. 3 is a flowchart showing an example of a preferred flow of the customer lifetime value analysis process taking parallel execution into consideration. FIG. 4 is a diagram continuing from FIG. 3. FIG. 5 is a diagram continuing from FIG. 4. In the example shown in FIGS. 3 to 5, steps S1 and S2 related to registering the advertiser server and the platform are executed as needed, and steps S3 to S5 related to receiving / acquiring data are executed in parallel and / or in any order, followed by step S6 related to compiling statistics. Thereafter, steps S7 to S8 related to generating content are executed sequentially as needed. This allows the support device 1 to execute processes that do not have a dependency on each other in execution order in parallel and / or in any order, thereby achieving rapid and efficient execution of the customer lifetime value analysis process. By executing steps S3 to S5 in parallel, the data can be acquired more efficiently, and the overall processing speed can be increased. In addition, by executing steps S7 and S8 sequentially, optimal content can be generated based on the aggregation results.

[0114] [Statistical Use Step] The customer lifetime value analysis process preferably includes a statistic utilization step of increasing the customer lifetime value by utilizing the statistics compiled by the statistical processing unit 114. The following is an example of processing included in the statistic utilization step.

[0115] (Assignment step) The statistical value utilization step preferably includes a staff member assignment step of determining whether a staff member has been designated, and if no staff member has been designated, assigning the staff member with the highest evaluation (for example, the staff member with the highest actual repeat rate) to the position. The staff member assignment step may be a procedure in which, among the statistics compiled for each staff member who provided the service, the staff member with the highest actual repeat rate is preferentially proposed as a staff member for cases where no staff member has been designated. This allows the support device 1 to assign a person with a high actual repeat rate to a free customer who has not yet been assigned a staff member.

[0116] The staff member allocation step preferably includes a procedure for making the proposal based on the combination of the content on the advertising platform that the viewer first viewed and the service that the viewer used the first time, and the next reservation rate and actual repeat rate of the staff member. As a result, the support device 1 grasps the advertising inflow path and the LTV of the menu selected the first time, and further grasps the next reservation rate and actual repeat rate of the staff member, thereby supporting logically determining which staff member to assign to a customer who came from which advertisement and selected which menu based on past performance.

[0117] (Inquiry number notification step) The statistical data utilization step preferably includes an inquiry count notification step that notifies users, such as the store owner, when the number of inquiries per certain period (e.g., daily) falls below a given threshold. The number of inquiries here refers to the number of unique users, such as users who made reservations by phone or users who viewed the reservation site. The inquiry count notification step monitors the number of inquiries each day as an indicator and notifies the store owner if the number is low, thereby helping the store owner to implement measures to increase inquiries (e.g., advertising, flyers, SEO for the website, posting on social media, etc.) when there are few inquiries to begin with.

[0118] (Alert step) The statistical value utilization step preferably includes an alert step of notifying a staff member that the next reservation rate and / or existing next reservation rate for the staff member falls below a given threshold value that the statistical value is low. This allows the staff member with a low next reservation rate and / or existing next reservation rate to review the manual in accordance with the notification and reconfirm whether they are performing according to the manual. The given threshold value is determined, for example, based on the statistical value for the entire store or the entire region. By determining the given threshold value in this manner, the support device 1 can identify staff members with low statistical values ​​for the entire store or the entire region and notify them.

[0119] The alert step preferably includes a procedure for notifying the relevant staff member of a large discrepancy between the next reservation rate and the actual repeat rate. In such cases, there is concern that there will be a large number of cancellations, such as last-minute cancellations. The alert step including this procedure can assist in identifying the cause of the cancellations by providing a notification. The given threshold is determined, for example, based on the difference between the next reservation rate and the actual repeat rate for the entire store or the entire region. By determining the given threshold in this manner, the support device 1 can identify staff members with a large discrepancy for the entire store or the entire region and provide a notification.

[0120] (AI optimization step) The statistical analysis step preferably includes an AI optimization step of identifying communication content that maximizes the LTV indicated by the statistical data based on machine learning, using the content of communication on social media as an explanatory variable and the statistical data associated with the communication content as a target variable. This allows the assistance device 1 to support the design of communication by changing it over time, including at least the steps of communicating on social media before the customer visits, communicating by email, sending an email just before the customer visits, sending a thank-you email after the customer visits, sending emails until the appointment is made, sending emails after the reservation is made, sending emails for the second reservation, sending emails for the third reservation, and sending emails for the fourth reservation. The machine learning includes, for example, various types of machine learning related to neural networks. The learning model and the format of the training data are not particularly limited as long as they are related to conventionally known machine learning. This step analyzes the content of communication on social media using natural language processing to quantify customer emotions and preferences. By using these as explanatory variables and statistical data such as purchase amount and purchase frequency as target variables, the relationship between communication content and customer value can be modeled. In this case, by using deep learning, it becomes possible to capture nonlinear relationships.

[0121] The support device 1 can then use machine learning to identify when and in what order the various types of communication described above should be carried out to maximize LTV. Additionally, based on the identified data, the support device 1 can use machine learning (AI) to optimize the content of communication to maximize LTV effects during repeated visits after a reservation.

[0122] <Usage example> The following is an example of how the support device 1 of this embodiment is used.

[0123] [Database registration and update] The support device 1 stores information about the advertiser server and the advertising platform provided by the advertiser in the database 121, and updates the stored information.

[0124] [Analysis of customer lifetime value] The support device 1 acquires data indicating the behavior of customers using the advertiser server from a terminal T or the like used by a sales representative of a business (advertiser) that has a fixed-price subscription for a service that analyzes customer lifetime value.The support device 1 then receives, from the advertising platform, viewing information data that associates customers with viewers of the advertiser's advertisements posted via the advertising platform.The support device 1 also receives, from the transaction execution platform, action information data that associates action performers with customers.

[0125] At this time, browsing information data and action information data are received by using APIs, etc. By using APIs, etc., it is possible to track behavior from web advertisements (advertising platforms) to SNS (transaction execution platforms) for reservations and payments, such as LINE, and ultimately to track whether the behavior led to the desired action, such as payment or store reservation.

[0126] Then, quantitative data and / or qualitative data regarding actions taken by customers is compiled for each type of advertising platform that the viewer first accessed from among the plurality of advertising platforms.

[0127] Similarly, quantitative data and / or qualitative data regarding actions taken by customers is aggregated for each piece of content on an advertising platform that the viewer has viewed among a plurality of advertising platforms.

[0128] By aggregating various statistics in this way, it is not only possible to determine which advertising platforms are effective, but also to measure and predict at what point customers drop out if payment or reservations are not completed.In addition, by aggregating the menus selected by customers the first time for each advertising platform that served as the inflow route, it is also possible to measure and predict changes in customer lifetime value for each pattern.

[0129] This allows the support device 1 to provide more accurate analysis results of customer lifetime value, even enabling more efficient store and business operations. This is because if the effect on customer lifetime value can be measured for each advertising platform that serves as an inflow route, it becomes possible to determine which advertising platform to invest in. Also, if it is possible to determine which initial menu is likely to increase customer lifetime value, it becomes possible to optimize the content of the initial menu.

[0130] [Automatic generation of advertisements] The support device 1 generates content using a large-scale language model, generative AI, etc., based on quantitative data and / or qualitative data on customer actions for each piece of content on the advertising platform viewed by the viewer. More specifically, the content generation unit 115 generates content that enables customers to take the actions desired by the advertiser, based on the correlation between the content of information displayed in the content on the advertising platform viewed by the viewer and the quantitative data and / or qualitative data on customer actions aggregated for each piece of content. This enables effective marketing by the advertiser that takes into account the customer lifetime value.

[0131] In the explanation of this embodiment, the present invention has been described using customer behavior at a beauty salon as an example, where necessary. However, the support device of the present invention can naturally support the analysis of customer lifetime value even when advertisers are entities other than beauty salons. Examples of businesses other than beauty salons include businesses involved in the sale and provision of various products and services, such as daily necessities sales, real estate transactions, financial product brokerage, automobile sales, mobile phone service solicitation, and video streaming service solicitation. The support device of the present invention enables these businesses other than beauty salons to improve their services and marketing through the analysis and utilization of customer lifetime value. For e-commerce businesses, analyzing customer behavior on advertising platforms and their own websites can be expected to optimize advertising and improve the accuracy of product recommendations. Furthermore, for real estate businesses, analyzing customer behavior on advertising platforms and property listing sites can enable effective property proposals and sales approaches.

[0132] It should be noted that within the scope of the concept of the present invention, those skilled in the art may conceive of various modifications and alterations. Therefore, it is understood that such modifications and alterations fall within the scope of the present invention. For example, even if a person skilled in the art appropriately adds, deletes, or modifies components of the above-described embodiment, or adds, omits, or modifies the conditions of a process, such modifications are also included within the scope of the present invention as long as they maintain the gist of the present invention. [Explanation of symbols]

[0133] S System 1 Support equipment 11 Control section 111 Customer behavior acquisition department 112 Viewing information receiving unit 113 Action Information Receiving Unit 114 Statistical Processing Unit 115 Content Generation Unit 12 Storage section 121 databases 13 Communications Department N Network T-Terminal

Claims

1. a customer behavior acquisition unit that acquires data indicating the behavior of customers who use a server managed directly or indirectly by the advertiser from the server; a viewing information receiving unit that receives, from a plurality of advertising platforms, data indicating the behavior of viewers of the advertisements of the advertiser posted via the advertising platforms, which data associates the viewers with the customers; an action information receiving unit that receives, from the transaction execution platform, data indicating the behavior of an action performer, which associates the action performer of a payment or reservation via the transaction execution platform with the customer; a statistical processing unit that aggregates statistics regarding the behavior of the viewer and the behavior of the action performer in the plurality of advertising platforms in association with the behavior of the customer; Equipped with The browsing information receiving unit receives data indicating the behavior of the browser on each of the plurality of advertising platforms for each of the customers; the action information receiving unit receives data indicating the actions of the action takers in the transaction execution platform for each of the clients; the statistical processing unit, based on the data indicating the behavior of the viewer received for each of the customers and the data indicating the behavior of the action performer received for each of the customers, tallying quantitative data and / or qualitative data regarding the actions performed by the customers for each type of advertising platform that the viewer first accessed among the plurality of advertising platforms; The statistical processing unit combines and aggregates the classification information and the statistics, thereby contributing to optimization of the advertiser's marketing measures. A support device for customer lifetime value analysis.

2. The data regarding the behavior of the action performer includes classification information associated with the sale and / or provision of goods and / or services selected and / or purchased by the action performer; The support device of claim 1, wherein the statistical processing unit, when aggregating the quantitative data and / or the qualitative data regarding the actions shown by the customer for each type of advertising platform first accessed by the customer, further aggregates the quantitative data and / or the qualitative data for each classification information.

3. The support device of claim 2, wherein the classification information is at least one selected from the group consisting of identification information regarding the type and item of the product or service, identification information of the person who sold and provided the product or service, and identification information of the store and area where the product or service was sold and provided.

4. The support device described in claim 1 or 2, wherein the statistical processing unit further compiles quantitative data and / or qualitative data regarding the actions shown by the customer for each piece of content on an advertising platform viewed by the viewer among the plurality of advertising platforms based on the data regarding the viewer's behavior received for each customer.

5. Further, a content generation unit capable of generating content to be posted on the advertising platform, The support device of claim 4, wherein the content generation unit generates content that can realize the customer actions desired by the advertiser based on a correlation between the content of information displayed in the content on the advertising platform viewed by the viewer and quantitative and / or qualitative data regarding the actions shown by the customer aggregated for each content.

Images