KR102487851B1 - Apparatus and method for measuring advertising performance based on store visit history - Google Patents

Abstract

Disclosed are an apparatus and method for measuring advertising performance based on a store visit history, which evaluates offline performance of advertisements. According to one embodiment of the present invention, the method for measuring advertising performance based on a store visit history comprises the steps of: building a database containing store visit history and location information for each of a plurality of users; selecting a target user to receive advertising information of a target store from the plurality of users on the basis of the database; providing the advertising information to a user terminal of the target user; collecting an actual visit history of the target user to the target store; and evaluating advertising performance corresponding to the advertising information on the basis of the actual visit history.

Description

Advertising performance measurement device and method based on store visit history {APPARATUS AND METHOD FOR MEASURING ADVERTISING PERFORMANCE BASED ON STORE VISIT HISTORY}

The present disclosure relates to an apparatus and method for measuring advertisement performance based on store visit history. For example, the present disclosure relates to an advertisement performance evaluation system for measuring a user's offline store visit performance according to a digital advertisement.

Companies that do business offline execute large-scale advertisements online/mobile to increase the number of visitors to their stores. Companies that do business online can easily measure how many times users who are exposed to digital advertisements visit their online sites, while offline companies have limitations in measuring store visits by people who have seen advertisements. As a result, most of them of companies had no choice but to devise advertising/marketing strategies without objectively evaluating the performance of offline advertising, which accounts for more than 60% of customer consumption.

In addition, according to overseas research cases related to this, there is no significant difference in the ratio of users accessing (clicking) the advertisement depending on the distance between the user and the target store when the mobile advertisement is exposed, while actually visiting the store after being exposed to the advertisement It has been analyzed that visit performance decreases by 18% for each mile the user and the corresponding store move away from each other.

Therefore, based on the past location recognition records and current locations of multiple users, select people with a high probability of visiting the target store for advertisement, expose the advertisement, and track whether the user who received the advertisement actually visited the store. Advertising performance for offline stores can be objectively and quantitatively evaluated, and it is expected that companies that run businesses based on offline stores will be able to utilize these evaluation results in various ways to establish advertising/marketing strategies.

On the other hand, recently, technologies for providing various services to stores or restaurants located around the user terminal by identifying the location of the user terminal have been used. In order to realize these technologies, it is necessary to accurately recognize the user's visit to the store. , Existing technology for recognizing the location of a user terminal specifies the position of a signal having the largest signal value or the highest similarity with a reference signal as the location of the user terminal based on a GPS signal, a mobile communication signal, or the like, or The similarity comparison standard value was uniformly applied to all stores, and the location of the user terminal was uniformly specified without considering the characteristics of the stores, so there was a limit to low accuracy.

In addition, the existing location recognition technology of the user terminal was only to the extent of characterizing the information that the user terminal is near a specific store or specifying the nearest store information, and accurately recognizing that the user terminal actually entered the inside of a specific store. There was a problem with not being able to do it.

The background technology of the present application is disclosed in Korean Patent Registration No. 10-1771538.

The present invention is to solve the above-mentioned problems of the prior art, and selects a user to provide an advertisement for a target store in consideration of store visit history and location information of multiple users, and the user who receives the advertisement actually visits the target store An object of the present invention is to provide a device and method for measuring advertisement performance based on a store visit history that can evaluate the offline performance of an advertisement by tracking whether or not it has been performed.

However, the technical problem to be achieved by the embodiments of the present application is not limited to the technical problems described above, and other technical problems may exist.

As a technical means for achieving the above technical problem, the method for measuring advertising performance based on store visit history according to an embodiment of the present application includes the steps of building a database including store visit history and location information of each of a plurality of users; Selecting a target user to receive advertisement information of a target store from among the plurality of users based on the database; providing the advertisement information to a user terminal of the target user; The method may include collecting a visit history and evaluating advertisement performance corresponding to the advertisement information based on the actual visit history.

In addition, the selecting step may include calculating a possibility of visiting the target store of each of the plurality of users based on the database, and a user whose visit possibility is equal to or higher than a predetermined threshold level among the plurality of users as the target user. It may include a selection step.

In addition, the collecting of the actual visit history may include receiving a terminal signal fingerprint from the user terminal, calculating a similarity between a previously secured reference signal fingerprint of the target store and the terminal signal fingerprint, and Based on the method, determining the target user's entry into the target store may be included.

In addition, the step of calculating the visit possibility includes first reference information for selecting a user having a store visit history for the target store from among the plurality of users, and a history of visiting the target store among the plurality of users. Second criterion information for selecting a user having the store visit history for a reference store previously visited by a user, third criterion information that is proximity to the current location information of each of the plurality of users and the location of the target store, and The visit possibility based on reference information including at least one of current location information of each of the plurality of users and fourth reference information that is a proximity to at least one of a residence and a place of work of a user having a history of visiting the target store. can be calculated.

In the evaluating of the advertisement performance, the actual visit history of the target user and the actual visit history of a comparison user who has not received the advertisement information may be compared.

In addition, the step of evaluating the advertisement performance may include providing the advertisement information to a first group including at least some users randomly selected from among the plurality of users, and the actual visit history of the first group and the plurality of users. Comparing the actual visit histories of a second group excluding the first group among users of the second group.

Also, the screening may be performed based on a pre-generated screening algorithm.

In addition, the method for measuring advertisement performance based on store visit history according to an embodiment of the present disclosure may include updating the selection algorithm based on the advertisement performance.

In addition, the method for measuring advertisement performance based on store visit history according to an embodiment of the present disclosure includes estimating activity pattern information including at least one of a visit preference, a work place, and a residence of each of the plurality of users based on the database. steps may be included.

In the selecting of the target user, the target user may be selected in consideration of the activity pattern information.

On the other hand, the advertising performance measurement device based on store visit history according to an embodiment of the present application includes a data collection unit for constructing a database including store visit history and location information of each of a plurality of users, and the plurality of stores based on the database. A selection unit for selecting a target user to receive advertisement information of a target store from among users, an advertisement providing unit for providing the advertisement information to a user terminal of the target user, and collecting a history of the target user's actual visit to the target store It may include a visit determination unit and an evaluation unit that evaluates advertisement performance corresponding to the advertisement information based on the actual visit history.

In addition, the selector may calculate a possibility of visiting the target store of each of the plurality of users based on the database, and select a user whose visit possibility is equal to or higher than a predetermined threshold level among the plurality of users as the target user. there is.

In addition, the visit determination unit receives a terminal signal fingerprint from the user terminal, calculates a similarity between a previously secured reference signal fingerprint of the target store and the terminal signal fingerprint, and based on the similarity, determines the target user's It is possible to determine the entry into the target store.

In addition, the selection unit determines first criterion information for selecting a user having a history of visiting the target store from among the plurality of users, information of a user having a history of visiting the target store among the plurality of users, and Second criterion information for selecting a user having the store visit history for a reference store, third criterion information that is a proximity between the current location information of each of the plurality of users and the location of the target store, and each of the plurality of users The possibility of the visit may be calculated based on reference information including at least one of fourth reference information, which is a proximity to at least one of a residence and a place of work of a user having a history of visiting the target store and current location information of the user. .

The evaluation unit may compare the actual visit history of the target user and the actual visit history of a comparison user who has not received the advertisement information.

In addition, the screening unit may include a pre-generated screening algorithm.

Also, the selection unit may update the selection algorithm based on the advertisement performance.

The above-described problem solving means are merely exemplary and should not be construed as intended to limit the present disclosure. In addition to the exemplary embodiments described above, additional embodiments may exist in the drawings and detailed description of the invention.

According to the above-described problem solving means of the present application, a user to be provided with an advertisement for a target store is selected in consideration of store visit histories and location information of multiple users, and it is tracked whether or not the user who received the advertisement actually visited the target store. Therefore, it is possible to provide a device and method for measuring advertisement performance based on a store visit history capable of evaluating the offline performance of an advertisement.

However, the effects obtainable herein are not limited to the effects described above, and other effects may exist.

1 is a schematic configuration diagram of an advertisement system including an advertisement performance measuring device based on a store visit history according to an embodiment of the present disclosure.
2 is a conceptual diagram illustrating a process of recognizing the location of a user terminal of a target user.
3 is a conceptual diagram for explaining a signal fingerprint.
4 is a schematic configuration diagram of an advertisement performance measuring device based on store visit history according to an embodiment of the present disclosure.
5 is an operational flowchart of a method for measuring advertisement performance based on a store visit history according to an embodiment of the present disclosure.
6 is a detailed operational flowchart of a process of collecting actual visit history of a target user.

Hereinafter, embodiments of the present application will be described in detail so that those skilled in the art can easily practice with reference to the accompanying drawings. However, the present disclosure may be implemented in many different forms and is not limited to the embodiments described herein. And in order to clearly describe the present application in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the present specification, when a part is said to be “connected” to another part, it is not only “directly connected”, but also “electrically connected” or “indirectly connected” with another element in between. "Including cases where

Throughout the present specification, when a member is referred to as being “on,” “above,” “on top of,” “below,” “below,” or “below” another member, this means that a member is located in relation to another member. This includes not only the case of contact but also the case of another member between the two members.

Throughout the present specification, when a certain component is said to "include", it means that it may further include other components without excluding other components unless otherwise stated.

The present disclosure relates to an apparatus and method for measuring advertisement performance based on store visit history. For example, the present disclosure relates to an advertisement performance evaluation system for measuring a user's offline store visit performance according to a digital advertisement.

1 is a schematic configuration diagram of an advertisement system including an advertisement performance measuring device based on a store visit history according to an embodiment of the present disclosure.

Referring to FIG. 1 , the advertisement system 10 according to an embodiment of the present application includes an advertisement performance measuring device 100 (hereinafter referred to as 'advertising performance measuring device 100' based on store visit history) according to an embodiment of the present application. It may include a user terminal 200 and a signal fingerprint measuring terminal 300. In addition, although not shown in the drawing, the advertising system 10 may include a corporate terminal (not shown) of a company that operates an offline store and executes advertising/marketing through the advertising system 10 disclosed herein.

The advertisement performance measuring device 100 , the user terminal 200 , the signal fingerprint measurement terminal 300 and the enterprise terminal (not shown) may communicate with each other through the network 20 . The network 20 refers to a connection structure capable of exchanging information between nodes such as terminals and servers, and examples of such a network 20 include a 3rd Generation Partnership Project (3GPP) network and a Long LTE (LTE) network. Term Evolution (Term Evolution) network, 5G network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network) Network), wifi network, Bluetooth network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc. are included, but are not limited thereto.

The user terminal 200 is, for example, a smart phone (Smartphone), a smart pad (SmartPad), a tablet PC, etc. and PCS (Personal Communication System), GSM (Global System for Mobile communication), PDC (Personal Digital Cellular), PHS ( Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal It may be any kind of wireless communication device, such as

In addition, referring to FIG. 1 , a user terminal 200 is a user terminal 201 possessed (possessed) by a target user selected to provide advertisement information of a target store by the advertisement performance measuring device 100 and It can be classified as a user terminal 202 possessed (possessed) by a user who has not received advertisement information (in other words, a user other than the target user).

Meanwhile, the advertisement performance measuring device 100 may refer to an advertisement service server built to operate the advertisement system 10 disclosed herein. In other words, the advertisement performance measurement device 100 disclosed herein may be the same server as the advertisement service server that provides store advertisement information to consumers and provides evaluation results for the advertisement performance.

The advertisement performance measuring device 100 may build a database 101 including store visit histories and location information of each of a plurality of users. For example, the advertisement performance measuring device 100 includes a plurality of users (eg, a user who has subscribed to a service platform provided by the advertisement system 10 or installed an application operated by the advertisement system 10 on a terminal) Each store visit history, past location information, current location information, etc. may be collected from the user terminal 200 of each of a plurality of users.

For example, the advertisement performance measurement apparatus 100 may receive the device identifier of the user terminal 200, store information visited by time (units), and latitude/longitude information by time (units).

In addition, according to an embodiment of the present application, the advertisement performance measurement apparatus 100 estimates activity pattern information including at least one of a visit preference, a work place, and a residence of each of a plurality of users based on the built database 101. can do.

On the other hand, according to an embodiment of the present application, the store visit history collected by the advertisement performance measuring device 100 to build the database 101 is collected based on the signal fingerprint-based store visit determination method described in detail below. it could be In other words, according to an embodiment of the present application, the store visit history collection process for constructing the database 101 and the actual visit history collection process including whether or not the target user receiving the advertisement information actually visited the target store signal It may be performed similarly based on fingerprints.

In addition, the advertisement performance measuring device 100 uses the advertisement information of a target store among a plurality of users based on the built database 101 and location information of an offline store (hereinafter referred to as a 'target store') corresponding to the advertisement information. It is possible to select a target user to receive.

In detail, the advertisement performance measurement apparatus 100 may calculate a possibility of each of a plurality of users visiting a target store based on the built database 101 .

According to an embodiment of the present application, the advertisement performance measuring device 100 includes first criterion information for selecting a user having a store visit history for a target store among a plurality of users, and a history of visiting the target store among a plurality of users. Second criterion information for selecting a user having a store visit history for a reference store previously visited by the user, third criterion information that is proximity to the target store location and current location information of each of a plurality of users, and a plurality of users. The possibility of visiting may be calculated based on reference information including at least one of fourth reference information, which is a proximity to at least one of a residence and a place of work of a user having a history of visiting the target store and respective current location information.

Exemplarily, the advertisement performance measurement device 100 provides a first score according to first reference information, a second score according to second reference information, a third score according to third reference information, and a fourth reference score for each of a plurality of users. The fourth score according to the information is calculated as a digitized score, and the possibility of visiting the target store obtained by synthesizing the first to fourth scores (eg, digitizing a representative value through arithmetic average, weighted average, etc.) is calculated for each user it may be computational.

More specifically, in relation to the first reference information, the number of visits to the target store, the elapsed period from the last visit, the average interval between visits to the target store, the time spent visiting the target store and staying in the target store, Users with more purchase details (amount, number of times, etc.) may have a higher first score, but the first score calculation method is not limited thereto.

In addition, with respect to the second criterion information, the number of visits to the reference store that a user who has a history of visiting the target store has already visited, the elapsed period from the last visit, the average interval between visits to the reference store, and reference by visiting the reference store The second score may be evaluated higher for users with more time spent in the store and purchase history (amount, number of times, etc.) at the reference store, but the second score calculation method is not limited thereto.

In addition, in relation to the third reference information, the third score may be evaluated higher as the location of the target store is closer to the current location.

In addition, in relation to the fourth criterion information, the fourth score is evaluated higher for a user whose residence and current location have a history of visiting the target store, and the work place and current location of the user who has a history of visiting the target store exist. The closer the user is, the higher the fourth score may be. In addition, in this regard, according to an embodiment of the present application, the degree of influence on the fourth score among the proximity to the residence of users with a history of visiting the target store and the proximity to the workplace of users with a history of visiting the target store ( Proximity with a high weight) may be individually set for each piece of advertisement information based on the type of industry of the target store and the type of product/service corresponding to the advertisement information. For example, in the case of offline stores in industries that users are likely to visit near their residences, such as discount marts, the weight for proximity to their residence is set high, while stationery/printing companies, etc. In the case of an offline store of a business that is highly likely to be visited in the vicinity, a weight for the place of work may be set high and the fourth score may be calculated.

On the other hand, the weight of each of the above-mentioned first to fourth standard information (in other words, the ratio of the first to fourth scores considered in finally predicting each user's visit possibility) is It may be set according to each advertisement information by reflecting needs. In this regard, the advertisement performance measuring device 100 determines the matters that the company preferentially considers among the first to fourth standard information, which are criteria for selecting a target user to receive advertisement information through a company terminal (not shown). A visit possibility of each user may be calculated by requesting ranking information, and considering the ranking information provided from an enterprise terminal (not shown).

In addition, according to an embodiment of the present application, the advertisement performance measuring device 100 receives advertisement information including advertisement characteristic information, data collected in the database 101, and activity pattern information derived for each user as input. A pre-generated screening algorithm may be provided to calculate and output the possibility of each user visiting the target store.

In addition, according to an embodiment of the present application, the selection algorithm of the advertisement performance measuring device 100 is updated (updated) based on the result of evaluating the advertisement performance based on the store visit history, which will be described later, thereby inducing actual customer visits to offline stores. It can be continuously optimized to select possible advertisement recipients (target users) with high accuracy. For example, the selection algorithm of the advertisement performance measurement device 100 may be updated (updated) in a way of adjusting the weight of each of the aforementioned reference information based on the advertisement performance evaluation result, but the update method of the selection algorithm is based on this. but not limited to

On the other hand, the advertisement performance measurement device 100 provides content information of advertisements to be executed by the company from a company terminal (not shown), operation time information of offline stores (advertisement target stores) operated by the company, promotion according to the advertisement (benefit) ) information, type information of products/services to be advertised, and type information of the target company, advertisement characteristic information including a wide range of information can be obtained.

In this regard, the advertisement performance measuring device 100 may calculate the possibility of each of a plurality of users visiting the target store in more detail by considering the advertisement characteristic information and the activity pattern information through analysis of the database 101. there is.

In addition, the advertisement performance measurement apparatus 100 may select a user having a probability of visiting the calculated target store equal to or higher than a predetermined threshold level among a plurality of users as a target user.

For example, the advertisement performance measurement apparatus 100 may select a user whose calculated visit probability is greater than or equal to a preset threshold value as a target user. As another example, the advertisement performance measuring device 100, when the number of target users to receive advertisement information is set in advance, ranks the possibility of visiting a plurality of users, and selects a user with a high ranking corresponding to the number of users as the target user. However, it is not limited thereto, and a method of finally specifying a target user to receive advertisement information based on each user's visit possibility can be widely applied in various ways.

The advertisement performance measurement device 100 may provide advertisement information to the user terminal 201 of the target user. For example, advertisement information in various formats, such as SNS-based feed advertisements, application-based real-time push notifications, and text messages, may be provided to the user terminal 201 of the target user. In addition, according to an embodiment of the present application, the advertisement performance measuring device 100 may provide advertisement information including reference information corresponding to the main cause for which the target user's visit possibility is highly evaluated when providing advertisement information. can For example, in the case of a target user selected based on the third criterion information, the advertisement performance measuring device 100 'advertisement for a store close to the current location'. In the case of target users selected based on the first criterion information, 'This is an advertisement for a store you have visited before.' The advertisement information may be processed so that a visit inducement phrase such as such is included in the advertisement information.

Also, the advertisement performance measuring device 100 may collect a history of actual visits to target stores by the target user after the point at which advertisement information is provided to the target user.

Specifically, the advertisement performance measuring device 100 may determine a history of actual visits to the target store based on the signal fingerprint. Hereinafter, referring to FIGS. 2 and 3 , the concept of signal fingerprint and a store visit determination technique using signal fingerprint will be described.

2 is a conceptual diagram for explaining a process of recognizing the location of a user terminal of a target user, and FIG. 3 is a conceptual diagram for explaining a signal fingerprint.

Referring to FIGS. 2 and 3 , the advertisement performance measuring device 100 may receive a plurality of reference signal fingerprints 11 from a plurality of signal fingerprint measuring terminals 300 . Also, the terminal signal fingerprint 21 may be received from the user terminal 200 . Each of the reference signal fingerprint 11 and the terminal signal fingerprint 21 may include a Basic Service Set IDentifier (BSSID) of a neighboring access point and Received Signal Strength (RSS) of a signal transmitted from the access point. In addition, the reference signal fingerprint 11 and the terminal signal fingerprint 21 may include Media Access Control (MAC) addresses of nearby Bluetooth communication devices (not shown).

More specifically, the signal fingerprint measuring terminal 300 and the user terminal 200 may receive identification information from an external device such as a nearby access point or a Bluetooth communication device. The identification information may include a MAC address of a Bluetooth communication device or a BSSID of an access point. MAC address and BSSID are unique identification values of a Bluetooth communication device and an access point, respectively, and may have a length of 48 bits. Specifically, the MAC address may mean an address used by a Bluetooth communication device in a MAC layer, and the BSSID may mean an identifier for identifying a basic service set (BSS), which is a basic building block in a WiFi system.

In addition, the signal fingerprint measuring terminal 300 and the user terminal 200 may obtain a beacon signal periodically broadcast by a Bluetooth communication device or an access point, and decode identification information from the obtained beacon signal. Alternatively, the signal fingerprint measuring terminal 300 and the user terminal 200 transmit a probe request frame for discovering a Bluetooth communication device or access point, and then receive a response from the Bluetooth communication device or access point in response thereto. Identification information may be decoded from the probe response frame.

In addition, the signal fingerprint measuring terminal 300 and the user terminal 200 may measure the received signal strength (RSS) of each device based on the frame received from the Bluetooth communication device and the access point.

In addition, the reference signal fingerprint 11 and the terminal signal fingerprint 21 may include a BSSID of an adjacent access point and radio signal strength information of a signal transmitted from the access point as one set, and each of a plurality of access points It may include a plurality of corresponding sets. The BSSID included in the reference signal fingerprint 11 and the terminal signal fingerprint 21 may be different from each other according to the access point adjacent to the signal fingerprint measurement terminal 300 and the user terminal 200 .

The advertisement performance measurement device 100 may store the reference signal fingerprint 11 received from the signal fingerprint measurement terminal 300 in a fingerprint database. Exemplarily, the advertisement performance measuring device 100 links a plurality of store-specific reference signal fingerprints collected by the signal fingerprint measuring terminal 300 from each of a plurality of stores with information on each store (eg, a business name) to a fingerprint database. can be stored in

Also, the advertisement performance measurement apparatus 100 may calculate a similarity between the terminal signal fingerprint 21 received from the user terminal 200 and the stored reference signal fingerprint 11 . The similarity calculation may use various metrics for calculating the similarity between two vectors. As an example of computing vector similarity, Cosine Similarity, Tanimoto Coefficient Similarity, Euclidean Distance, Correlation, Chebyshev distance, Mahalanobis distance, Manhattan distance or Hamming distance can be used. Since the calculation of the similarity between signals may be applied in various ways as well as the above-described method, a detailed description thereof will be omitted.

On the other hand, since the advertising performance measurement device 100 calculates the similarity between the reference signal fingerprint 11 for each store stored in the fingerprint database and the terminal signal fingerprint 21, the similarity calculation result is the stored reference signal fingerprint 11 ) can be derived in correspondence with the number of

Also, the advertisement performance measuring device 100 may determine whether the user terminal 200 is inside or outside the target store based on the derived similarity. In this case, the advertisement performance measuring device 100 may preset a reference value for determining the inside or outside of the store. For example, the advertisement performance measurement apparatus 100 may set a plurality of reference values for each store based on the reference signal fingerprint 11 for each store. As an example of setting the reference value, the advertisement performance measuring device 100 may set the reference value based on the wireless signal strength included in the terminal signal fingerprint 21 and the wireless signal strength included in the reference signal fingerprint 11.

Describing another example of setting the reference value, the advertisement performance measuring device 100 may receive an internal signal fingerprint collected from one area inside the store and an external signal fingerprint collected from one area outside the store. The internal signal fingerprint and the external signal fingerprint may be signal fingerprints different from the reference signal fingerprint 11 . For example, the internal signal fingerprint is a signal fingerprint measured at a position very close to the door in the interior of the store (eg, a position where half of the straight line distance between the center of the store and the door is away from the door to the inside of the store), The external signal fingerprint may be a signal fingerprint measured at a position very close to the door of the store (eg, a position where half of the straight line distance between the center of the store and the door is away from the door to the outside of the store). Exemplarily, the internal signal fingerprint and the external signal fingerprint may be collected by the signal fingerprint measurement terminal 300 . The advertisement performance measurement apparatus 100 may calculate an internal similarity between the terminal signal fingerprint 21 and the internal signal fingerprint and an external similarity between the terminal signal fingerprint 21 and the external signal fingerprint. In addition, the advertisement performance measuring device 100 may set any one of values between internal similarity and external similarity as a reference value. For example, when the internal similarity is 0.8 and the external similarity is 0.6, an average value of 0.7 may be set as a reference value. In this way, the reference value for recognizing the inside of the store is more accurately set by using the signal fingerprint measured at a position very close to the door among the inside of the store and the signal fingerprint measured at a position very close to the door among the outside of the store. can be set

Describing another example of setting the reference value, the advertisement performance measuring device 100 includes a reference signal fingerprint 11 and a terminal signal fingerprint 21 corresponding to the case where it is determined that the user terminal 200 is inside the store. The degree of similarity between them can be recorded. For example, the advertising performance measuring device 100 may repeat the recording of the similarity each time it is determined that one or more different user terminals 200 are inside the store.

In addition, the advertisement performance measurement apparatus 100 may average the top n similarities among the recorded similarities and set a reference value by considering the average of the similarities and the store characteristic coefficient. Illustratively, the advertisement performance measurement apparatus 100 may set a reference value by subtracting a store characteristic coefficient from the average of the similarities. The store characteristic coefficient may be set based on at least one of the size of the store, the material of the outer wall, the interior, and the type and performance of the access point provided in the store, and may be used to set a reference value by reflecting the characteristics of the store. For example, the store characteristic coefficient may have a smaller value as the size of the store increases.

In this way, based on a specific store, a reference value is generated by considering the average value of the top n values of the similarity between the reference signal fingerprint and the terminal signal fingerprint when it is determined that the store is inside the corresponding store and the store characteristic coefficient of the corresponding store, It is possible to more accurately determine whether the user terminal 200 is located in a corresponding store.

The advertisement performance measuring device 100 may determine the position of the user terminal 200 by setting a reference value in the above-described manner and comparing the similarity between each reference signal fingerprint and the terminal signal fingerprint and the reference value. The advertisement performance measuring device 100 may determine that the user terminal 200 is inside the store when the similarity is greater than or equal to a reference value associated with a specific store.

The user terminal 200 may generate a terminal signal fingerprint 21 including signals transmitted from a plurality of access points 31, 41, and 51 adjacent to each other. For convenience of description, it is assumed that the plurality of access points 31 , 41 , and 51 are respectively provided in the plurality of stores 30 , 40 , and 50 , but the present invention is not limited thereto. The advertisement performance measurement device 100 may receive signals transmitted from access points 31, 41, and 51 inside each store 30, 40, and 50, and collect a reference signal fingerprint 11 from the received signal. there is. For example, the reference signal fingerprint collected at the store 40 may include the BSSID and respective strength information received from the access points 31 and 41, and the reference signal fingerprint collected at the store 30 is the access point It may include the BSSID received from (31, 41, 51) and each strength information, and in this way, reference signal fingerprints of each store may be different from each other according to the network environment of each store.

Also, referring to FIG. 3 , the reference signal fingerprint 11 may include a plurality of sets consisting of a BSSID of one access point and radio signal strength information between the store and the access point. The reference signal fingerprint 11 is a BSSID 610 of an access point 41 provided in a store 40 and a wireless signal strength information 611 between the signal fingerprint measurement terminal 300 and the access point a 41 ) as one set (a set). Similarly, BSSID 620 of b access point 31 of b store 30 and b set having b wireless signal strength information 621 and BSSID 630 of c access point 51 of c store 50 It may include c sets with c radio signal strength information 631 .

The terminal signal fingerprint 21 may have the same form as the reference signal fingerprint 11 described with reference to FIG. 3 except that it is wireless signal strength information between the user terminal 200 and the access point, so duplicate descriptions are omitted.

According to an embodiment of the present application, since each store has different characteristics such as the size of the store and the thickness of the wall, and the type of access point adjacent to each store and the performance of each access point may be different, the reference collected for each store is different. Each signal fingerprint may be configured as a set having different BSSIDs and different wireless signal strength information. In addition, the terminal signal fingerprint 21 may have a collected BSSID and wireless signal strength depending on the location of the user terminal 200 or the surrounding environment as well as the characteristics of the store and access point described above.

In summary, the advertisement performance measuring device 100 receives the terminal signal fingerprint 21 from the user terminal 201 of the target user, and obtains the reference signal fingerprint 11 and the terminal previously secured for the target store corresponding to the advertisement information. The similarity of the signal fingerprint 21 may be calculated to determine whether the target user enters the target store.

In addition, similarly, the advertisement performance measurement apparatus 100 detects a terminal signal fingerprint 21 from the user terminal 202 of the user even for a user who has not received advertisement information among a plurality of users (in other words, a user other than the target user). It is possible to determine entry into the inside of the target store by receiving and calculating the similarity between the previously secured reference signal fingerprint 11 and the terminal signal fingerprint 21 for the target store corresponding to the advertisement information.

In this regard, the advertisement performance measuring device 100 may evaluate advertisement performance corresponding to advertisement information based on the actual visit history of the target user.

According to an embodiment of the present disclosure, the advertisement performance measuring device 100 may compare an actual visit history of a target user and an actual visit history of a comparison user who has not received advertisement information. In other words, the advertisement performance measuring device 100 determines that the target user's visit rate calculated based on the target user's actual visit history is higher than the visit rate calculated based on the actual visit history of the comparison user who has not received the advertisement information. The more calculated, the more users who visited the target store after checking the corresponding advertisement, so it can be evaluated that the effect of the advertisement is excellent.

In this regard, according to an embodiment of the present application, the advertisement performance measurement device 100 transmits service fee information charged according to the provision of advertisement service to a corporate terminal (not shown), but records actual visits through the above-described evaluation process. In terms of service fee information corresponding to advertisement information determined to have excellent advertisement performance, a fee may be variably determined so that a higher cost is set.

As another example, the advertisement performance measuring device 100 provides advertisement information for a first group including at least some users randomly selected from among a plurality of users, and then records actual visits of target users selected through the above-described screening algorithm. The reference result of comparing the actual visit history of the comparison user, who is a control group who has not received the advertisement information, with the reference result (for example, the result of subtracting the visit ratio of the comparison user from the visit ratio of the target user) and the first group randomly provided with advertisements. The comparison result of comparing the actual visit history and the actual visit history of the second group excluding the first group among the plurality of users (for example, the result of subtracting the visit ratio of the second group from the visit ratio of the first group) By comparison, the effectiveness of screening algorithms can be evaluated.

At this time, the advertisement performance measurement device 100 calculates the higher the reference result (difference in visitation ratio between the target user and the comparison user) compared to the control result (difference in visitation ratio between the user who viewed the random advertisement and the user who did not provide the advertisement), the higher the target user It can be understood that the screening algorithm is in a more optimized state. In other words, if the difference between the reference result and the comparison result is insignificant or the comparison result is computed higher than the reference result, the advertisement performance measurement device 100 may determine that the target user selection algorithm needs to be updated (updated).

4 is a schematic configuration diagram of an advertisement performance measuring device based on store visit history according to an embodiment of the present disclosure.

Referring to FIG. 4 , the advertisement performance measuring device 100 may include a data collection unit 110, a selection unit 120, an advertisement providing unit 130, a visit determination unit 140, and an evaluation unit 150. there is.

The data collection unit 110 may build a database 101 including store visit histories and location information of each of a plurality of users.

In addition, the data collection unit 110 may estimate activity pattern information including at least one of a visit preference, a work place, and a residence of each of a plurality of users based on the information collected in the database 101 .

The selection unit 120 may select a target user to receive advertisement information of a target store from among a plurality of users based on the built database 101 .

Specifically, the selection unit 120 may calculate the possibility of each of a plurality of users visiting the target store based on the built database 101 . In addition, the selection unit 120 may select a user whose calculated visit probability is equal to or higher than a preset threshold level among a plurality of users as a target user to receive advertisement information.

In addition, the selection unit 120 may perform selection of a target user based on a pre-generated selection algorithm, but may update the selection algorithm based on advertisement performance derived by the evaluation unit 150 .

Also, according to an embodiment of the present disclosure, the selection unit 120 may select a target user in consideration of activity pattern information estimated for each of a plurality of users.

The advertisement provider 130 may provide advertisement information to the user terminal 201 of the target user.

The visit determination unit 140 may collect a history of actual visits to target stores by the target user.

Specifically, the visit determination unit 140 receives the terminal signal fingerprint 21 from the user terminal 200, and the similarity between the previously secured reference signal fingerprint 11 for the target store and the received terminal signal fingerprint 21 can be computed.

Also, the visit determining unit 140 may determine whether the target user enters the target store based on the calculated similarity.

The evaluation unit 150 may evaluate advertisement performance corresponding to advertisement information based on the collected actual visit history.

In detail, the evaluator 150 may evaluate the advertisement performance by comparing the target user's actual visit history to the target store and the actual visit history of the comparison user who has not received advertisement information about the target store.

As another example, the evaluation unit 150 provides advertisement information for a first group including at least some users randomly selected from among a plurality of users through the advertisement providing unit 130, and the actual visit history of the first group and the plurality of users. Advertising performance may be evaluated by comparing actual visit histories of a second group (a group that has not received advertisement information of a target store), excluding the first group, among users of the target store.

Hereinafter, based on the details described above, the operation flow of the present application will be briefly reviewed.

5 is an operational flowchart of a method for measuring advertisement performance based on a store visit history according to an embodiment of the present disclosure.

The advertisement performance measuring method based on store visit history shown in FIG. 5 may be performed by the previously described advertisement performance measurement apparatus 100 . Therefore, even if omitted below, the description of the advertisement performance measurement device 100 can be equally applied to the description of the advertisement performance measurement method based on the store visit history.

Referring to FIG. 5 , in step S11 , the data collection unit 110 may build a database 101 including store visit histories and location information of each of a plurality of users.

Next, in step S12, the selection unit 120 may select a target user to receive advertisement information of a target store from among a plurality of users based on the database 101 built in step S11.

Next, in step S13, the advertisement provider 130 may provide advertisement information to the user terminal 201 of the target user.

Next, in step S14, the visit determining unit 140 may collect a history of actual visits to the target store by the target user.

Next, in step S15 , the evaluation unit 150 may evaluate advertisement performance corresponding to the corresponding advertisement information provided to the target user based on the target user's actual visit history to the target store.

Next, in step S16, the selection unit 120 may update (update) a pre-generated selection algorithm to select a target user based on the advertisement performance evaluated in step S15.

In the foregoing description, steps S11 to S16 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present application. Also, some steps may be omitted if necessary, and the order of steps may be changed.

6 is a detailed operational flowchart of a process of collecting actual visit history of a target user.

The process of collecting the actual visit history of the target user shown in FIG. 6 may be performed by the visit determining unit 140 of the advertisement performance measuring device 100 described above. Therefore, even if omitted below, the description of the advertisement performance measuring device 100 can be equally applied to the description of FIG. 6 .

Referring to FIG. 6 , in step S141 , the visit determination unit 140 may receive the terminal signal fingerprint 21 from the user terminal 201 of the target user.

Next, in step S142, the visit determining unit 140 may calculate a similarity between the reference signal fingerprint 11 previously secured for the target store and the terminal signal fingerprint 21 received from the user terminal 201 of the target user. there is.

Next, in step S143, the visit determination unit 140 may determine whether the target user enters the target store based on the calculated similarity.

In the foregoing description, steps S141 to S143 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present application. Also, some steps may be omitted if necessary, and the order of steps may be changed.

A method for measuring advertisement performance based on store visit history according to an embodiment of the present disclosure may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the medium may be those specially designed and configured for the present invention or those known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to act as one or more software modules to perform the operations of the present invention, and vice versa.

In addition, the above-described advertisement performance measurement method based on store visit history may be implemented in the form of a computer program or application stored in a recording medium and executed by a computer.

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

The scope of the present application is indicated by the following claims rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof should be construed as being included in the scope of the present application.

10: Advertising system
100: Advertising performance measurement device based on store visit history
110: data collection unit
120: selection unit
130: advertisement providing unit
140: visit determination unit
150: evaluation unit
101: database
200: user terminal
300: signal fingerprint measurement terminal
11: reference signal fingerprint
21: terminal signal fingerprint
20: Network
30, 40, 50: store

Claims (15)

In the advertising performance measurement method based on the store visit history performed by the advertising performance measuring device,
Building a database including store visit history and location information of each of a plurality of users;
selecting a target user to receive advertisement information of a target store from among the plurality of users based on the database;
providing the advertisement information to a user terminal of the target user;
collecting actual visit histories for the target store of the target user and a comparison user who has not received the advertisement information, respectively; and
Evaluating advertisement performance corresponding to the advertisement information based on the actual visit history;
including,
The screening step is characterized in that it is performed based on a pre-generated screening algorithm,
Evaluating the advertising performance,
deriving a reference result of comparing the actual visit history of the target user and the actual visit history of the comparison user;
providing the advertisement information to a first group including at least some users randomly selected from among the plurality of users;
deriving a comparison result by comparing the actual visit history of the first group and the actual visit history of a second group excluding the first group among the plurality of users; and
Comparing the reference result and the comparison result with each other to determine whether the selection algorithm needs to be updated;
including,
Updating the selection algorithm based on the determined update necessity state;
Which further includes
How to measure advertising performance. According to claim 1,
In the selection step,
calculating a possibility of each of the plurality of users visiting the target store based on the database; and
Selecting a user whose visit possibility is equal to or higher than a predetermined threshold level among the plurality of users as the target user;
To include, advertising performance measurement method. According to claim 1,
The step of collecting the actual visit history,
receiving a terminal signal fingerprint from the user terminal;
calculating a similarity between a previously secured reference signal fingerprint of the target store and the terminal signal fingerprint; and
determining entry of the target user into the target store based on the degree of similarity;
To include, advertising performance measurement method. According to claim 2,
The step of calculating the visit possibility,
first reference information for selecting a user having a store visit history for the target store from among the plurality of users;
second reference information for selecting a user having a history of visiting the store for a reference store previously visited by a user having a history of visiting the target store from among the plurality of users;
third reference information, which is proximity between the current location information of each of the plurality of users and the location of the target store; and
The visit possibility based on reference information including at least one of current location information of each of the plurality of users and fourth reference information that is a proximity to at least one of a residence and a place of work of a user having a history of visiting the target store. To calculate, advertising performance measurement method. According to claim 1,
Evaluating the advertising performance,
and comparing the actual visit history of the target user and the actual visit history of a comparison user who has not received the advertisement information. delete delete According to claim 1,
estimating activity pattern information including at least one of a visit preference, a work place, and a residence of each of the plurality of users based on the database;
Including more,
The step of selecting the target user,
Selecting the target user in consideration of the activity pattern information, advertising performance measurement method. In the advertisement performance measuring device based on store visit history,
a data collection unit that builds a database including store visit history and location information of each of a plurality of users;
a selection unit for selecting a target user to receive advertisement information of a target store from among the plurality of users based on the database;
an advertisement providing unit providing the advertisement information to a user terminal of the target user;
a visit determination unit which collects actual visit histories of the target store of the target user and the comparison user who has not received the advertisement information, respectively; and
an evaluation unit that evaluates advertisement performance corresponding to the advertisement information based on the actual visit history;
including,
The selection unit,
Characterized in that it is performed based on a pre-generated screening algorithm,
The evaluation unit,
A reference result is derived by comparing the actual visit history of the target user and the actual visit history of the comparison user, and the advertisement information is provided to a first group including at least some users randomly selected from among the plurality of users. and derives a comparison result by comparing the actual visit history of the first group and the actual visit history of a second group excluding the first group among the plurality of users, and comparing the reference result and the comparison result with each other. to determine the need to update the selection algorithm,
The selection unit,
Updating the selection algorithm based on the determined update necessity state;
Advertising performance measurement device. According to claim 9,
The selection unit,
Based on the database, calculating the possibility of visiting the target store of each of the plurality of users, and selecting a user whose visit possibility is equal to or higher than a predetermined threshold level among the plurality of users as the target user. . According to claim 9,
The visiting judgment unit,
Receives a terminal signal fingerprint from the user terminal, calculates a similarity between a previously secured reference signal fingerprint of the target store and the terminal signal fingerprint, and based on the similarity, the target user enters the target store Which is to determine, advertising performance measuring device. According to claim 10,
The selection unit,
first reference information for selecting a user having a store visit history for the target store from among the plurality of users;
second reference information for selecting a user having a history of visiting the store for a reference store previously visited by a user having a history of visiting the target store from among the plurality of users;
third reference information, which is proximity between the current location information of each of the plurality of users and the location of the target store; and
The visit possibility based on reference information including at least one of current location information of each of the plurality of users and fourth reference information that is a proximity to at least one of a residence and a place of work of a user having a history of visiting the target store. Which is to calculate, advertising performance measuring device. According to claim 9,
The evaluation unit,
and comparing the actual visit history of the target user and the actual visit history of a comparison user who has not received the advertisement information. delete A computer-readable recording medium recording a program for executing the method according to any one of claims 1 to 5 and 8 in a computer.

Images