KR20140131088A - Method for providing recommended item, storage medium recording program and device therefor - Google Patents

Abstract

Disclosed are a method for providing a recommended item,and a recording medium and a recording apparatus recording a program for the same. Particularly, the method of the present invention collects user log data related with a web site from a terminal connected to the web site through script inserted into the web site and calculates recommendation result as to one or more recommended items related with each source item servicing in the web site using a recommendation algorithm on the basis of the user log data. The method of the present invention also extracts a recommended item list requested in the recommendation result in response to the recommended item list received from a web server of the web site and then transmits the recommended item list to the web server.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for providing a recommendation item,

The present invention relates to a recommendation item providing method, and more particularly, to a recommendation item providing method for recommending another item related to an item serviced by a web site, and a recording medium and an apparatus recording the program therefor.

As the use of the Internet becomes popular, users can acquire contents related to various fields such as news, knowledge documents, games, and videos through the Internet. In addition, many service providers have opened shopping malls and provide users with a wide variety of goods and services.

However, since the information, goods, and services that can be acquired through the Internet are increasing exponentially, it takes a lot of time for the consumer to find the information or goods he really desires. Accordingly, various Internet sites provide a service that provides appropriate recommendation information such as related video recommendation and product recommendation to a visiting user, and some companies provide a recommendation system as a solution. However, in order to introduce such a recommendation system, a large number of servers capable of processing large amounts of data are basically required, and further development is required in order to link recommendation results to actual services.

An object of the present invention is to provide a recommendation item providing method that can be directly applied to a self service without further development in a web site providing various contents, goods or services, and a recording medium and an apparatus recording the program therefor.

It is another object of the present invention to provide a recommendation item providing method for recommending a more suitable item by reflecting feedback generated by a user to a recommendation result, and a recording medium and an apparatus recording the program therefor.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory and are not restrictive of the invention, unless further departing from the spirit and scope of the invention as defined by the appended claims. It will be possible.

According to one aspect of the present invention, there is provided a service apparatus, comprising: a communication unit for data transmission and reception; a user log data; a storage unit for storing a recommendation result; and a web site And a recommendation algorithm for recommending at least one recommendation item related to each source item served by the website using the recommendation algorithm based on the user log data, And a control unit for extracting a recommendation item list related to the requested source item from the recommendation result in response to the recommendation item list request and transmitting the extracted recommendation item list to the web server.

Preferably, the control unit can calculate a click rate for a recommendation item related to each source item through click log data and view log data for a recommendation item.

Preferably, the control unit may exclude a recommendation item in which the click rate is continuously lower than the threshold value for a predetermined period of time from the recommendation result.

Preferably, the control unit may divide the user log data into predetermined conditions or arbitrarily into a plurality of groups, and calculate recommendation results using different recommendation algorithms for each group.

Preferably, the control unit may calculate the click rate for each group through the click log data and the view log data for the recommendation item, and calculate the recommendation result using the recommendation algorithm used for the group having the highest click rate.

Preferably, when the terminal is connected through the link of the recommendation item connected to the service device, the control unit may acquire the click log data for the recommendation item through the connection URL of the terminal.

Preferably, the controller extracts user data including a predetermined parameter value from a visit URL (Uniform Resource Locator) included in the user log data, and obtains the user data as click log data for the recommendation item.

Preferably, if there is a recommendation item list request from the upper web server, the control unit may obtain view log data for the recommendation item through the recommended item list.

Preferably, the control unit may extract item information displayed on the visit URL from the visit URL (Uniform Resource Locator) included in the user log data and operation information related to the operation of the terminal on the visit URL.

Preferably, the control unit distinguishes the recommendation result for each source item and stores the recommendation result in a string including a service identifier for identifying a web site, an item identifier for the source item, and a recommendation item identifier for a recommendation item related to the source item. the value calculated by applying the hash function can be stored together with the recommendation result.

Preferably, the control unit may transmit a recommendation item list related to the requested source item in a JavaScript Object Notation (JSON) format or an iFrame format.

Preferably, the user log data may include a domain of a website, a visit URL (Uniform Resource Locator) of the terminal, a user identifier, and visit time information.

Preferably, the user identifier is generated by a web browser cookie of the terminal, and may be generated by combining any number and a generation time.

According to another aspect of the present invention, there is provided a method of providing a recommendation item, the service device collecting user log data related to a web site from a terminal accessing the web site through a script inserted in the web site, Calculating recommendation results of at least one recommendation item related to each source item serviced by the website using a recommendation algorithm based on user log data, and requesting a recommended item list received from the web server of the web site And extracting a recommendation item list related to the requested source item from the recommendation result and transmitting the extracted recommendation item list to the web server.

Preferably, the service device may further include calculating click-through rates for the recommendation items associated with each source item through click-log data and view log data for the recommendation item.

Preferably, the service device may further include the step of excluding the recommendation item in which the click rate is continuously lower than the threshold value for a predetermined period of time, from the recommendation result.

Preferably, the step of calculating the recommendation result may be such that the service apparatus divides the user log data into predetermined conditions or arbitrarily into a plurality of groups, and calculates recommendation results using different recommendation algorithms for each group.

Preferably, the step of calculating the recommendation result may include calculating the click rate for each group through the click log data and the view log data for the recommendation item, and calculating the recommendation result with the recommendation algorithm used for the group having the highest click rate can do.

Preferably, when the terminal is connected through a link of a recommendation item connected to the service device, the service device may further include acquiring click log data for the recommendation item through the connection URL of the terminal.

Preferably, the service device may further include extracting user data including a predetermined parameter value from a visit URL (Uniform Resource Locator) included in the user log data and obtaining the extracted user data as click log data for a recommendation item .

Preferably, if the service apparatus requests the recommendation item list of the web server, the method may further include obtaining view log data for the recommendation item through the recommendation item list.

Preferably, the user device may further include extracting item information displayed on the visit URL from a Uniform Resource Locator (URL) included in the user log data and operation information related to the operation of the terminal on the visit URL.

Preferably, the service apparatus stores the recommendation result for each source item separately, and stores the service identifier for identifying the website, the item identifier for the source item, and the recommendation item identifier for the recommendation item related to the source item, and storing the value calculated by applying the hash function together with the recommendation result.

According to the embodiment of the present invention, it is possible to directly apply to a self service without additionally developing a web site providing various contents, goods or services.

Also, according to the embodiment of the present invention, it is possible to recommend a more suitable item by providing the feedback on the recommendation result based on the click / view log data generated from the user.

The effects obtained in the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the following description .

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the technical features of the invention.
1 is a view schematically illustrating a system to which a recommendation item providing service apparatus according to an embodiment of the present invention can be applied.
2 is a diagram illustrating a configuration of a service apparatus according to an embodiment of the present invention.
3 is a diagram illustrating a recommendation item providing method according to an embodiment of the present invention.
4 is a diagram illustrating a method of collecting user log data according to an embodiment of the present invention.
5 is a diagram illustrating a method of collecting user log data according to an embodiment of the present invention.
6 is a diagram illustrating a method of providing a list of recommended items in accordance with an embodiment of the present invention.
7 is a diagram illustrating a recommendation item list provided in an iFrame format according to an embodiment of the present invention.
8 shows an example in which a recommendation item list provided in an iframe format according to an embodiment of the present invention is displayed on a web page.
9 is a diagram illustrating a method of collecting click log data according to an embodiment of the present invention.
10 is a diagram illustrating a click rate for each recommendation item according to an embodiment of the present invention.
11 is a diagram illustrating a recommendation rate for each algorithm according to an embodiment of the present invention.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following detailed description, together with the accompanying drawings, is intended to illustrate exemplary embodiments of the invention and is not intended to represent the only embodiments in which the invention may be practiced. The following detailed description includes specific details in order to provide a thorough understanding of the present invention. However, those skilled in the art will appreciate that the present invention may be practiced without these specific details.

In some instances, well-known structures and devices may be omitted or may be shown in block diagram form, centering on the core functionality of each structure and device, to avoid obscuring the concepts of the present invention.

Throughout the specification, when an element is referred to as "comprising" or " including ", it is meant that the element does not exclude other elements, do. Also, the terms " part, "" module," and " module ", etc. in the specification mean a unit for processing at least one function or operation and may be implemented by hardware or software or a combination of hardware and software have. Also, the terms " a or ", "one "," the ", and the like are synonyms in the context of describing the invention (particularly in the context of the following claims) May be used in a sense including both singular and plural, unless the context clearly dictates otherwise.

The specific terminology used in the following description is provided to aid understanding of the present invention, and the use of such specific terminology may be changed into other forms without departing from the technical idea of the present invention.

Hereinafter, as a result recommended to the user in the present invention, various kinds of goods or services that can be distributed through a wired / wireless network, contents such as characters, sounds, images, moving pictures and the like, And will be collectively referred to as an " item " for convenience of explanation.

1 is a view schematically illustrating a system to which a recommendation item providing service apparatus according to an embodiment of the present invention can be applied.

1, a system to which a recommendation item providing service apparatus according to an embodiment of the present invention can be applied includes a plurality of terminals 10, a web server 20, a service apparatus 30, and a network 40 Lt; / RTI >

The terminal 10 refers to a device available for the user to exchange information with the web server 20 and / or the service device 30 via the network 40, and to display such information or receive information from the user. In particular, in the present invention, the terminal 30 can access the web server 20 and receive various information about items and a list of recommended items provided by the service device 30. [ Here, the recommendation item means a list of one or more recommendation items related to a specific item, and can be generated based on the user log data collected from the web server 20 and / or the terminal 10 by the service device 30 .

In addition, the terminal 10 may transmit the selection information for the item selected by the user to the web server 20 so as to use the selected item (for example, purchase, store cart, download, delivery to another terminal, etc.) Various functions can be performed. In addition, the terminal 10 may perform a function of transmitting user log data to the service device 30, and a detailed description thereof will be described later. Preferably, the terminal 10 can transmit and receive information to and from the web server 20 and / or the service device 30 through a web browser stored therein, but the present invention is not limited thereto.

As shown in FIG. 1, the terminal described in this specification can be implemented in various forms. For example, a mobile phone, a smart phone, a laptop computer, a digital broadcasting terminal, a tablet PC, a PDA (personal digital assistant), a portable multimedia player (PMP) A fixed terminal such as a smart TV, a set-top box, a desktop computer or the like may be used as well as a mobile terminal of the present invention and a terminal capable of transmitting / The apparatus is also applicable to the terminal of the present invention.

The web server 20 collectively refers to servers of service providers that provide various services on the web, and is not limited to physically specific servers or servers that provide specific services. In particular, in the present invention, the web server 20 provides the above-described item and various information about the item to the terminal 10 connected to the web server 20, and transmits the information to the terminal 10 And can provide a recommendation item list for the selected item from the service device 30 to the terminal 10. In addition, the web server 20 may perform a function of transmitting user log data to the service device 30, and a detailed description thereof will be described later.

The service device 30 is a device that provides a recommendation item list for various items provided by the web server 20 to the web server 20. In particular, in the present invention, the service apparatus 30 collects and processes user log data from the terminal 10 and / or the web server 20, calculates a recommendation item list corresponding to each item, . Here, the user log data means a set of information indicating a history such as which terminal 10 (i.e., a user) has performed an operation on an item and at what web server.

In addition, the service device 30 collects view log data and / or click log data from the terminal 10 and / or the web server 20 or from the collected user log data, It is possible to provide a recommendation item list in which the feedback is reflected according to the user's visit or operation. Here, view log data refers to a set of information indicating a history that a web page displaying a specific item is provided to the terminal 10 by accessing the web server 20 of the terminal 10 (i.e., a user) do. The click log data is stored in the recommended item list by the terminal 10 (that is, the user) clicking on a recommended item list provided to the web server 20 by the service apparatus 30 Means a set of information indicating a history in which a web page displaying a recommendation item clicked through a link (e.g., a hyperlink or a hot link) is provided to the terminal 10.

The service device 30 may be implemented as a collection of various devices to support the above-described operations. A storage server for storing and managing log data (for example, user log, view log, click log data), a collection server for collecting log data, a clustering server for converting or processing log data, An API (Application Program Interface) server for calculating a recommendation item list and providing a recommended item list to a web server, a feedback processing server for modifying a recommendation item list based on the feedback result or selecting a recommendation algorithm, and the like . In addition, each module performing the function corresponding to the above-described operation may be implemented in one service device 30. [ Hereinafter, for ease of explanation, it is assumed that the service device 30 is implemented.

The terminal 10, the web server 20, and the service device 30 transmit and receive various information related to each other through the network 40, and various types of networks can be used for the network 40 at this time. For example, wireless communication methods such as 3G wireless communication, 4th generation mobile communication, WLAN (Wireless LAN), Wi-Fi, WiBro, Wimax, HSDPA (High Speed Downlink Packet Access) (Ethernet), xDSL (ADSL, VDSL), Hybrid Fiber Coaxial Cable (HFC), Fiber to the Curb (FTTC), and Fiber To The Home (FTTH) It is possible. In addition to the above-described communication methods, other widely known or later-developed communication methods may be included.

2 is a diagram illustrating a configuration of a service apparatus according to an embodiment of the present invention.

The configuration of the service device 30 shown in FIG. 2 shows functional elements that are functionally distinguished, and any one or more configurations may be physically integrated with each other.

2, the service device 30 according to an embodiment of the present invention may include a communication unit 210, a control unit 220, and a storage unit 230. The communication unit 210, the control unit 220 and the storage unit 230 constituting the service device 30 may be functionally connected to perform the functions according to the present invention.

More specifically, the communication unit 210 may include one or more modules that enable wired / wireless communication with one or more terminals 10 and / or the web server 20. In particular, in the present invention, the communication unit 210 may receive user log data from one or more terminals 10 and / or the web server 20. [ Also, the communication unit 210 can receive the recommended item list request message from the web server 20, and can transmit the recommended item list to the web server 20 in response to the recommended item list request message. Upon receiving a connection request from the terminal 10 by clicking a recommendation item on the web page provided by the web server 20, a redirect URL (Uniform Resource Locator) is assigned to the corresponding terminal 10 Lt; / RTI >

The control unit 220 is configured to perform overall control of the service device 30 and controls the flow of signals for performing functions of the communication unit 210 and the storage unit 250. At this time, the control unit 220 may include an operating system (OS), an application program, and a process unit for driving each configuration, for example, a central processing unit (CPU).

Particularly, in the present invention, the control unit 220 includes a data collecting unit 221, a data processing unit 222, a recommendation calculating unit 223, a recommendation result providing unit 224, and a feedback processing unit 225 .

The data collection unit 221 may collect the user log data from the terminal 10 and / or the web server 20 and store the collected user log data in the storage unit 230.

The data processing unit 222 extracts data necessary for calculation in order to calculate a recommendation item from the user log data collected and stored by the data collection unit 221, converts the extracted data into a data format suitable for calculation, And store the user log data in the storage unit 230. [ In addition, the recommendation calculation unit 223 performs a function of storing a recommendation result, which is calculated and stored in the database 230, into a format for providing the recommendation result to the web server 20 via the Internet .

The recommendation calculation unit 223 calculates recommendation items from the converted user log data processed by the data processing unit 222 by using various recommendation algorithms and stores the recommendation calculation results obtained by calculating the recommendation items in the storage unit 230 Can be performed.

Upon receiving the recommendation item list request message for a specific item from the Web server 20, the recommendation result provider 224 extracts a recommendation item list for the item from the recommendation result of the storage unit 230, To the mobile terminal. In addition, deletion of recommended items from recommendation result (or list of recommended items), addition of new recommendation items to recommendation result list (or recommended item list), addition of additional information to recommendation result list And to post-process the recommendation result (or recommended item list).

The feedback processor 225 collects the click log data and / or the view log data, and reprocesses the recommendation result (or the recommended item list) based on the collected click log data and / or the view log data, ) Can perform a function of determining a recommendation algorithm to be used in the recommendation calculation.

First, in order to collect click log data, the feedback processing unit 225 receives a connection request from the terminal 10 by clicking a recommendation item of a user on a web page provided by the web server 20, And stores the URL in the storage unit 230, and can transmit a redirect URL to the corresponding terminal 10 requested to be connected. Alternatively, the feedback processing unit 225 may extract data having a specific parameter or format from the user log data and store the extracted data in the storage unit 230 as click log data.

In order to collect view log data, the feedback processor 225 may receive the recommended item list request message from the web server 20 and store it in the database 230 as view log data .

2, the data collecting unit 221, the data processing unit 222, the recommendation calculating unit 223, the recommendation result providing unit 224, and the feedback processing unit 225 are shown as respective blocks. However, May be integrated into one device, and some or all of them may be implemented in physically different devices as described above. Further, a plurality of devices performing the same function may be implemented in parallel.

The storage unit 230 is a means for storing data and programs necessary for operation of the service device 30 and basically stores an operating program to be executed by the service device 30 and an application program. In particular, in the present invention, the storage unit 230 stores the user log data collected by the data collection unit 241, the converted user log data processed by the data processing unit 222 and the recommendation result, ) And the view log data and the click log data collected by the feedback collecting unit 245. [0213] FIG.

The storage unit 250 may be implemented by various storage means. For example, the storage unit 250 may be a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD A random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM) , A magnetic memory, a magnetic disk, or an optical disk. The storage unit 250 may be inside or outside the control unit 220, and may be connected to the control unit 220 by various well-known means.

Hereinafter, for the sake of clarity, the user log data processed by the data processing unit 222 is distinguished from the 'user log data' collected by the data collecting unit 221 and is referred to as 'converted user log data'. The result calculated by the recommendation calculation unit 223 is referred to as a 'recommended calculation result', and the recommended calculation result processed by the data processing unit 222 is referred to as a 'recommended result'. Also, the recommendation result provided by the recommendation result providing unit 224 regarding the specific item requested by the web server 20 from the recommendation result is referred to as a 'recommendation item list'. That is, the recommendation result includes a recommended item list recommended for all items.

Hereinafter, an operation for providing a recommendation item in the service apparatus 30 will be described with reference to FIG.

3 is a diagram illustrating a recommendation item providing method according to an embodiment of the present invention.

Referring to FIG. 3, the service device 30 may collect the above-described user log data from the terminal 10 and / or the web server 20 (S301). Here, the service device 30 can collect user log data from the terminal 10 and / or the web server 20 in a synchronous (i.e., real-time collection) or asynchronously (for example, And can collect user log data continuously from the terminal 10 and / or the web server 20 regardless of the collection method.

In step S303, the service device 30 extracts data necessary for recommendation calculation in order to calculate a recommendation item from the user log data collected in step S301, and converts the extracted data into a data format suitable for recommendation calculation and stores it. If the format of the user log data collected from the plurality of terminals 10 and / or the plurality of web servers 20 is the same in step S301 and is suitable for the recommended item calculation, the service device 30 performs the data conversion step It may not be performed, that is, step S303 may be omitted.

The service device 30 can calculate a recommendation item using various recommended algorithms using the user log data converted in S303, and store the recommendation calculation result (S305). Here, the service device 30 can calculate a recommendation item for each recommendation algorithm for every item. In addition, the user log data can be divided into a plurality of groups according to a certain criterion, and a recommendation item can be calculated using different recommendation algorithms for each group. The time at which the service device 30 calculates the recommendation item may be the same as or not the same as the time at which the user log data is collected in step S301, and may be calculated with a certain period.

The service device 30 may convert the recommended calculation result calculated in step S305 into a data format suitable for providing to the web server 20 via the Internet (S307). As described above, if the service device 30 does not perform the data conversion step in step S303, step S307 may also be omitted.

The service device 30 performs post-processing on the calculated recommendation result (or recommendation item list), and provides the recommendation item list to the web server 20 that collected the user log data (S309). At this time, the service apparatus 30 provides the recommendation item list to the web server 20 with a predetermined period, or the service apparatus 30 requests the recommended item list for the specific item from the web server 20, To the web server 20, a recommended list of recommended items.

The service device 30 may collect the feedback of the user and reflect it in the recommendation (S311). That is, the service device 30 reprocesses the recommendation result (or recommendation item list) based on the collected click log data and / or view log data (branching to step S309) (Refer to step S305) (S311).

Hereinafter, each step described in the example of FIG. 3 will be described in more detail.

The service device 30 (in particular, the data collecting unit 221) may collect the above-described user log data from the terminal 10 and / or the web server 20 (S301).

As described above, the user log data means a set of information indicating what kind of user performed what kind of behavior, what kind of item, what kind of web server, and what kind of item. In addition, the user log data includes information for identifying a browser mounted on the terminal 10 used by the user, information for limiting exposure to a specific user with respect to other items, (ID) identifier information, and the like.

Table 1 illustrates information that may be included in the user log data according to the present invention.

User identification information Product identification information Motion identification information Occurrence time User A Item 2 shopping basket 20XX-YY-ZZ aa: bb: cc User B Item 3 purchase 20XX-YY-ZZ aa: bb: cc User B Item 5 visit 20XX-YY-ZZ aa: bb: cc

The service device 30 may use the following method to collect such user log data.

First, the service device 30 can acquire and acquire user log data by accessing the web server 20, or can receive and acquire user log data transmitted from the web server 20, .

4 is a diagram illustrating a method of collecting user log data according to an embodiment of the present invention.

4, when the terminal 10 accesses the web server 20 and performs a specific operation, the web server 20 transmits the access path information of the web page including the user log data to the service device 30 to inform the service device 30 that the specific operation has been performed To the service device 30 (S401). Here, the web server 20 can transmit a connection request message to the service device 30 using the POST HTTP protocol.

Upon receiving the connection request message from the web server 20, the service device 30 accesses the web server 20 based on the access path information of the web page included in the connection request message, Data is extracted and acquired (S403). Here, the service device 30 can extract user log data from the web server 20 using the GET HTTP protocol.

Next, the service device 30 stores the acquired user log data (S405).

4, the user log data related to the operation of the user terminal 10 connected to the web server 20 in the web server 20 is transmitted to the service device 30 via the TCP / IP protocol Thereby obtaining user log data at the service device 30. [

Next, the service apparatus 30 may insert a script into a web site served by the web server 20 and acquire user log data from the user terminal 10 through the inserted script. This will be described below with reference to FIG.

5 is a diagram illustrating a method of collecting user log data according to an embodiment of the present invention.

Referring to FIG. 5, the service device 30 may insert a script into a web site provided by the web server 20 (S501). For example, the service apparatus 30 inserts a script such as "<script src = http: //collector.recopick.com/plugin.js> </ script>" into the web page provided by the web server 20 can do.

Thereafter, when the terminal 10 accesses the web server 20 (S503) and visits the web page provided by the web server 20, the script inserted in the web page is executed (S505). The log data for the user can be automatically transmitted to the service apparatus 30 by the script (S507). For example, when the above-described script is executed in the web browser installed in the terminal 10, the URL information of the web page visited by the terminal 10, the visit time, the values for the parameters included in the script, To the device (30).

The information collected by the service device 30 from the terminal 10 using the above-described script is as follows.

- UID (User IDentifier) generated based on web browser cookie

- User's visit URL information

- Information about the user's visit reference (Referrer)

- Connection time information

- About the user agent of the web browser

- Other Meta Information

The user identifier (UID) means a value for distinguishing a user. When the terminal 10 executes the script, the terminal 10 firstly determines whether the user identifier value is stored in the cookie of the web browser. If the user identifier is stored, (30). On the other hand, if the user identifier is not stored in the cookie of the web browser, information that can identify the user is generated by combining an arbitrary numerical value and the generation time (for example, 33619442.1366005959274), and transmits the generated information to the service device 30 .

The visit URL information means URL information of a corresponding web page of the connected web server 20. [ The referrer information refers to the URL information of the web page previously visited when the user visited the corresponding web page of the web server 20 through the link. The connection time information refers to time information that the terminal 10 visited on the web page of the web server 20. [ The user agent information of the web browser means information for distinguishing the web browser used by the terminal 10 when accessing the web server 20. For example, this information may be information for identifying whether the web browser used in the terminal 10 is a web browser for a mobile device or a web browser for a desktop. Such information may be collected by a web browser installed in the terminal 10 and transmitted to the service device 30 synchronously or asynchronously.

The meta information means other additional information that should be considered when the service apparatus 30 calculates a recommendation item. For example, the meta information may be a web site operated by the web server, Information about whether or not the information or item requires adult authentication, and the like. If the script embedded in the web page of the web server 20 has a format requiring meta information, the meta information is transmitted to the service device 30 by the terminal 10 . For example, when the inserted script has a form of "plugin.js? Key = value & key2 = value2", the terminal 10 transmits the values (value1, value2) .

The service device 30 receiving the user log data from the terminal 10 in the above-described manner stores the acquired user log data (S509).

The user log data collected through the method as shown in FIGS. 4 to 5 is shown in Table 2 below.

Table 2 illustrates the user log data collected by the service device 30.

KEY VALUE ref http://vanillashu.co.kr/front/php/product.php?product_no=13806&main_cate_no=1 site vanillashu.co.kr uid 44209103.136609 url http://vanillashu.co.kr/front/php/category.php?cate_no=30 time 20XX-YY-ZZ aa: bb: cc

The service device 30 extracts data necessary for the recommendation calculation to calculate a recommendation item from the user log data collected in step S301, And may be transformed into a data format and loaded (S303)

First, the service device 30 extracts a service identifier (SERVICE_ID) using the domain of the visit URL information from the collected user log data. For example, when the visited URL information is "http://www.foodfly.co.kr/restaurants/show/11378", " the service device 30 receives the domain" www.foodfly.com. 1 &quot; as the service identifier corresponding to &quot; kr "(SERVICE_ID = 1). At this time, the domain of the web site operated by each web server 20 and the service identifier can be mapped on a one-to-one basis. In this case, the service apparatus 30 may store the table information in which the domain of the website and the service identifier are mapped. In this case, the service apparatus 30 may extract the service identifier value by referring to the pre- have.

Then, the service device 30 extracts the item identifier (ITEM_ID) and the operation identifier (ACTION_ID) from the visit URL information by using regular expressions predefined for each service identifier (SERVICE_ID). Here, the regular expression is a formula for extracting a value of a parameter required in the URL information, and a different regular expression may be used for each service identifier and / or operation identifier. For example, "/restaurants//show//(*)$/" is used as a regular expression for extracting a 'VISIT' operation from a URL having the above-described service identifier 1 (SERVICE_ID = 1) (ACTION_ID = VISIT), and the parameter value 11378 located after the path indicates the item identifier (ITEM_ID = 11378). In this case, the '/ restaurants \ / show \ ). Here, \ is a variable indicating that '/' exists for distinguishing each path when a plurality of paths are included in the regular expression, and $ is a variable indicating that the regular expression is ended. Also, in the URL such as "http://www.foodfly.co.kr/order/11378" having the same service identifier (SERVICE_ID = 1), "/order//(.*)" as a "PURCHASE" regular expression, $ / "Can be used, in which case the '/ order \ /' path represents the 'PURCHASE' action (action_id = purchase) and the parameter value 11378 following the path represents the item identifier item_id = 11378).

Meanwhile, if the user ID value of the web server 20 is transferred and stored as meta information in the user log data collection step S301, the service device 30 uses the corresponding member ID as the user identifier USER_ID, If not, the terminal 10 uses the user identifier (USER_IDENTIFIER) generated based on the web browser cookie as the user identifier (USER_ID).

The service device 30 converts the user identifier (USER_ID) and the item identifier (ITEM_ID) extracted or obtained through the above-described method into a predefined numeric identifier, and extracts a numeric identifier . At this time, the service device 30 may convert the service identifier into a numeric identifier predetermined for each user identifier, an operation identifier, and an item identifier, such as a one-to-one mapping relationship between a domain and a service identifier, or may be converted into a numeric identifier Or granted).

Table 3 illustrates the converted user identifier table.

Service identifier
(SERVICE_ID) Source user identifier
(ORG_USER_ID) Converted user identifier
(CONVERTED_USER_ID) One chaehyun One One 44209103.136609 2 One 68709103.015529 3

In Table 3, 'chaehyun' indicates the case where the user's member information value of the web server 20 is transferred and used as the user identifier. '44209103.136609' or '68709103.015529' indicates the web browser cookie of the terminal 10 Is used as a user identifier.

Table 4 illustrates the converted item identifier table.

Service identifier
(SERVICE_ID) Original item identifier
(ORG_ITEM_ID) The converted item identifier
(CONVERTED_ITEM_ID) One 11378 One One 1245 2 One 21456 3

Table 5 illustrates the converted operation identifier table.

Action name (ACTION_NAME) The action identifier (ACTION_ID) VISIT One PURCHASE 101 Recommendation Algorithm 2
(RECOMMEND_VISIT_ALGORITHM_2) 2 Recommendation Algorithm 3
(RECOMMEND_VISIT_ALGORITHM_3) 3 Shopping cart (BASKET) 201

In Table 5, the recommended algorithm x (RECOMMEND_VISIT_ALGORITHM_x) indicates an operation that the user terminal 10 accesses to the web server 20 having the corresponding service identifier through the recommendation list providing result calculated using the recommendation algorithm (x) .

The final converted user log data is shown in Table 6 below.

Table 6 illustrates the converted user log data.

version
(VERSION) Converted user identifier
(CONVERTED_USER_ID) The converted item identifier
(CONVERTED_ITEM_ID) Service identifier
(SERVICE_ID) Operation identifier
(ACTION_ID) Time
(TIME) 0 36368996 1404200 4 One 20XX-YY-ZZ aa: bb: cc 0 36346053 39861 4 One 20XX-YY-ZZ aa: bb: cc 0 4093797 46666 8 One 20XX-YY-ZZ aa: bb: cc 0 36352376 29640 4 One 20XX-YY-ZZ aa: bb: cc 0 4093800 97415 8 One 20XX-YY-ZZ aa: bb: cc 0 36344208 39160 4 One 20XX-YY-ZZ aa: bb: cc 0 36343108 3812418 4 One 20XX-YY-ZZ aa: bb: cc 0 36356140 3841659 4 One 20XX-YY-ZZ aa: bb: cc 0 36395318 3856063 4 One 20XX-YY-ZZ aa: bb: cc

Referring to Table 6, the service device 30 may assign different version information to distinguish the converted user log data according to the item of information included in the converted user log data. For example, as shown in Table 6, in the case of the converted user log data having the version 0, the conversion includes the converted user identifier, the converted item identifier, the service identifier, the operation identifier, In the case of the user log data, other information items excluding or including some of the information items included in version 0 may be added.

The service device 30 (in particular, the recommendation calculation unit 223) may calculate a recommendation item using various recommendation algorithms using the user log data converted in S303, and store the recommendation calculation result (S305).

The service device 30 may calculate a recommendation item by applying various recommendation algorithms to the service server 30 so as to apply an effective recommendation algorithm to the service provided by the web server 20 providing the recommendation result. That is, it is possible to calculate a recommendation item according to each recommendation algorithm by applying various recommendation algorithms based on the collected total converted user log data, or to group the collected total converted user log data according to a random or specific condition, It is possible to calculate recommended items according to different recommendation algorithms for each group. For example, it is possible to distinguish the converted user log data in which the user identifier (USER_ID) is odd and the converted user log data in the even number, and calculate a recommendation item using the A recommendation algorithm and the B recommendation algorithm, respectively.

The service device 30 calculates the similarity of all the items belonging to the converted user log data included in the predetermined range (i.e., the whole or the group) to all items other than the item except for the item. For example, when a total of 100 items belong to the converted user log data within a predetermined range, the similarity between the first item and 99 items other than the item is calculated, and the second item and 99 items other than the item The degree of similarity with other items is calculated for all the items.

The service device 30 may use various recommendation algorithms to calculate the similarity between the two items. For example, jacard similarity, log likelihood similarity, Pearson correlation, and the like can be used. These similarity calculation methods are omitted in the following description with known methods. Hereinafter, for convenience of explanation, it is assumed that jacquard similarity is used as a recommendation algorithm, and jacquard similarity is defined as Equation 1 below.

Referring to Equation (1), the jacquard similarity between two items indicates the number of users who visited both items (the number of users who accessed both web pages displaying two items) The number of users who have accessed at least one of the displayed web pages - the number of users who access both web pages displaying two items) is calculated. As a result, the more similar the users who visited both items, do. For example, if the number of users connected to the web page displaying the A item is 20, the number of users accessing the web page displaying the B item is 10, and the number of users visiting the web page displaying the A and B items When the number is 5, the calculation result of jacquard similarity is 5 / (20 + 10 - 5) = 1/5.

The service device 30 calculates all the similarities of all the items belonging to the user log data converted within the predetermined range (all or group) by using the recommendation algorithm, and then n items are referred to in ascending order of similarity for each item It is calculated as an item. At this time, the service device 30 calculates all the similarities for all the items, extracts items satisfying a certain condition (for example, the number of users who visited both items> = 50 and the similarity> 0.1) N items may be calculated as recommended items in descending order of degree of similarity among items.

The method of calculating the recommendation item using the above-described jacquard similarity is only one example. As described above, the service apparatus 30 can calculate a recommendation item for each item using various recommendation algorithms. In addition, even if the recommendation score of the recommendation item for each item is calculated using different recommendation algorithms, the recommendation score can be all set to the same level (for example, between 0 and 1). Table 7 shows the recommended calculation results for each recommended algorithm.

Table 7 illustrates the recommended calculation results calculated according to each recommendation algorithm.

The converted item identifier
(CONVERTED_ITEM_ID) Converted Recommended Item Identifier
(RECOMMENDED_ITEM_ID) Recommended Score (SCORE) METHOD One 11 0.05511811023622047 2 One 164 0.0894854586129754 2 One 218 0.04025423728813559 2 One 272 0.11278195488721804 2

Referring to Table 7, the SCORE value represents a value obtained by calculating the similarity between the item and the recommendation item according to the recommendation algorithm, and the METHOD represents an identification number for the recommendation algorithm used in the similarity calculation.

The service device 30 (particularly, the data processing unit 222) may convert the recommended calculation result calculated in step S305 into a data format suitable for providing to the web server 20 (S307).

First, the service device 30 changes the identifier of the item converted from the recommendation calculation result to the original identifier, and adds the service identifier and the date of the calculation of the result.

Table 8 illustrates the converted format of the recommendation calculation result.

Original item identifier
(ORG_ITEM_ID) Original referral item identifier
(ORG_RECOMMENDED_ITEM_ID) Recommendation score
(SCORE) Way
(METHOD) Service identifier
(SERVICE_ID) date
(DATE) 123 11149 0.055118 2 One 20XX-YY-ZZ 123 11113 0.089485 2 One 20XX-YY-ZZ 123 740 0.040254 2 One 20XX-YY-ZZ 123 179 0.112782 2 One 20XX-YY-ZZ

Then, the service device 30 can finally convert the recommendation calculation result into a data format suitable for providing to the web server 20 via the Internet, and store the result. At this time, the service apparatus 30 can be stored in the JSON (JavaScript Object Notation) format shown in Table 9 below. However, the JSON format is only one example, and the service apparatus 30 can store various data formats such as an extensible markup language (XML) format and a YAML (YAML is not markup language) format. have. Hereinafter, it is assumed that the JSON format is assumed.

Table 9 illustrates a recommendation result format that is finally converted and stored.

Hash
(HASH) Service identifier
(SERVICE_ID) Original item identifier
(ORG_ITEM_ID) count
(COUNT) JSON Time (TIME) 4cfc30c5e1c1bbcf
One 11057 3 "{" id ":" 11649 "," score ": 0.059867," method ":" 2 "}, {" id " "id": "12116", "score": 0.052083, "method": "2"}] 20XX-YY-ZZ aa: bb: cc c000365f48786906 One 11078 2 "{" id ":" 11021 "," score ": 0.033816," method ":" 2 "}, 20XX-YY-ZZ aa: bb: cc 96028a9562ba33de One 11099 10 "{" id ":" 553 "," score ": 0.061425," method ":" 2 "}, {{ "id": "849", "score": 0.055133, "method": "2"}, {"id": "622", "score": 0.051887, "method" "" Id: "," score ": 0.050532," method ":" 2 "}, {" id " "Id": "11614", "score": 0.046632, "method": "2"}, {"id": "786", "score": 0.044872, 2 "}, {" id ":" 11771 "," score ": 0.040925," method " 20XX-YY-ZZ aa: bb: cc

Referring to Table 9, the hash value is a value calculated so as not to store the recommendation item list for the item in a case where the recommended item list recommended for the specific item is the same, and includes a service identifier (SERVICE_ID) The identifier (ITEM_ID) and the recommendation item identifier (RECOMMENDED_ITEM_ID) are combined into one string, and then the hash function is applied to the combined string. By using such a hash value, even if the recommendation score of the recommendation items belonging to the recommendation item list is changed unless the recommendation item belonging to the recommendation item list is changed or the recommendation item belonging to the recommendation item list is changed, The item list may not be updated. That is, since the recommendation score for the recommendation item is not included in the variable for calculating the hash value, if the recommendation score of the recommendation item is changed when the recommendation item list is calculated again the next day, If the order is not changed, the hash value is not changed.

And the COUNT value indicates the number of recommendation items and how many items are recommended for a specific item. The JSON value includes information on a recommended number of items corresponding to the count value, and may include, for example, a recommendation item identifier, recommendation score, and recommendation algorithm information.

The service device 30 (in particular, the recommendation result providing unit 224) performs post-processing on the calculated recommendation result (or recommendation item list) and then recommends recommendation to the corresponding web server 20 that collected the user log data An item list can be provided (S309).

This will be described in more detail with reference to FIG. 6 below.

6 is a diagram illustrating a method of providing a list of recommended items in accordance with an embodiment of the present invention.

Referring to FIG. 6, the service device 30 may perform post-processing on the converted stored recommendation result (or recommended item list) (S601).

Post-processing of the recommendation result (or recommended item list) means adding, deleting or changing the recommendation item from the recommendation result (or recommended item list) or adding, deleting or changing the information item included in the recommendation item list . This post-processing process may be performed automatically at the service apparatus 30 or may be performed at the service apparatus 30 at a request from the web server 20. [

Specifically, the service apparatus 30 can remove the recommendation prohibited item from the recommendation result (or the recommended item list). For example, if the administrator of the web server 20 prohibits the recommendation of item B for item A, item B may be removed from the recommendation item list for item A. In addition, in the case of an item that should not be recommended for any item, such as when a particular item is sold out or a particular shop is no longer operating, the item can be removed from all the recommended item lists (i.e., recommendation results). When the recommendation prohibited item is removed from the recommendation result (or the recommended item list), the service device 30 deletes the item to be deleted from the previously generated recommendation result (or the recommended item list) The recommendation score can be changed to a lower value or the value of a variable can be adjusted so that a lower value is calculated to remove the recommended prohibited item from the recommendation result (or recommend item list).

In addition, the service apparatus 30 can add any item not included in the recommendation result (or recommendation item list) as a recommendation item. For example, when the administrator of the web server 20 does not like the result of the calculated recommendation item list, or when the recommendation item list for a specific item is not created, the service apparatus 30 sends a specific item It can be included as a recommendation result in the recommendation result (or a list of recommended items). Also in this case, the service apparatus 30 may arbitrarily add an item to be added in the created recommendation result (or a recommended item list), or may newly create a recommendation item list composed of specific items or recommend a recommendation item You can change the score to a higher value or adjust the value of the variable to be calculated to a higher value.

The information items constituting the recommendation result (or the recommendation item list) may include only the recommendation item identifier, recommendation score, and recommendation algorithm information as shown in the example of Table 9 above, but the service device 30 may also include recommendation result Quot; recommended item list &quot;). For example, the service device 30 may include an item name recommended in a recommended item list, a URL for a thumbnail of an item to be recommended, pricing information of a recommended item, and the like.

The web server 20 transmits a message to the service device 30 to request a recommended item list related to the item displayed on the visited web page accessed by the terminal 10 (S603). The recommended item list request message includes a service identifier for the requesting web server 20, an item identifier for the requested item, and may further include version information, meta information, and the like.

Upon receiving the recommended item list request message from the web server 20, the service device 30 extracts a recommended item list related to the requested item (S605), and transmits the extracted recommended item list to the web server 20 (S607) .

Here, the service apparatus 30 may transmit the recommendation item list in a format of a recommended item list (i.e., JSON format) generated in the web server 20, but may transmit recommendation item lists in an iframe format. In the case of providing a recommendation item list in the JSON format, it is necessary to add a separate design in the web server 20 and then provide a recommendation item list on the web page, while in the case of an iframe, It has the advantage of being applied directly to web pages.

First, for example, when the recommendation item list is transmitted in the JSON format, the web server 20 transmits the recommendation item list to the service apparatus in the format "http://api.recopick.com/VERSION/recommend/SERVICE_ID/ITEM_ID?OPTIONS" A recommendation item list may be requested to the user 30. In this manner, when requesting a recommended item list in the JSON format, the recommendation item list request message may include a service identifier, version information and other meta information together with the item identifier.

For example, if the web server 20 requested a recommendation item list to the service device 30, such as "http://api.recopick.com/2/recommend/1/11057?field=meta&quot ;, &quot; The version of the recommended item list is 2, the service identifier is 1, the identifier of the requesting item is 11057, and the meta information is further requested. A list of recommendation items provided by the service apparatus 30 to the web server 20 in response to the request is shown in Table 10 below.

Table 10 illustrates a list of recommended items provided in JSON format.

"{" id ":" 11649 "," score ": 0.061947," method ":" 2 "," image ": {" src ":" http://www.foodfly.co.uk/upload/restaurant/ Http: //www.youtube.com/watch?v=1&lt;: " http: // ", " //www.foodfly.co.uk/upload/restaurant/1192962858506d36dc8981f.jpg"},"title":"YYY"},{"id":"12116","score":0.033345,"method":"2 "," image ": {" src ":" http://www.foodfly.co.kr/upload/restaurant/1138839503513839a99ea0e.jpg "}," title ":" ZZZ "}]

Referring to Table 10, the recommended item list may include a recommendation item identifier ("id"), a recommendation score ("score"), and recommendation algorithm information ("method"). In the case of Table 10, the service device 30 includes additional meta information in the recommended item list when additional meta information is additionally requested. The image information ("image" ), And recommended item name information ("title").

Next, for example, when the recommendation item list is transmitted in the iframe format, the web server 20 transmits the recommendation item list to the web server 20 as "http://api.recopick.com/VERSION/banner/SERVICE_ID/show?item_id=ITEM_ID&direction= [horizontal | vertical & count = recommend_size "to the service device 30 in the same format. In this way, when requesting a recommended item list in an iframe format, version information and other meta information may be included along with a service identifier, an item identifier, a frame direction (horizontal or vertical direction), a frame size,

For example, when the web server 20 requests the recommendation item list to the service device 30 as "http://api.recopick.com/2/banner/6/show?item_id=59&direction=horizontal&count=4" , The version of the recommendation item list to be requested is 2, the service identifier is 6, the identifier of the requesting item is 59, the horizontal direction is the direction of the frame, and the number of recommendation items is 4.

Also, for example, if the Web server 20 sends a recommendation item list to the service device 30 such as "http://api.recopick.com/2/banner/6/show?item_id=59&direction=vertical&count=2" The requested recommendation item list has a version of 2, the service identifier is 6, the identifier of the requesting item is 59, the direction of the frame is vertical, and the number of recommendation items is 2.

A recommendation item list provided by the service apparatus 30 to the web server 20 in response to the request is shown in FIG.

7 is a diagram illustrating a recommendation item list provided in an iFrame format according to an embodiment of the present invention.

7A shows a case where the recommended number of recommendation items provided by the service apparatus 30 is four in the horizontal direction and the recommended item is displayed in the horizontal direction, 7B illustrates a case where the web server 20 requests two recommendation items in the vertical direction. In response thereto, the number of recommendation items provided by the service apparatus 30 is two, &Lt; / RTI &gt; shown in FIG.

8 shows an example in which a recommendation item list provided in an iframe format according to an embodiment of the present invention is displayed on a web page.

Referring to FIG. 8, the recommendation item list of iframe format provided by the service apparatus 30 is displayed on the web page of the web server 20 in the form provided by the service apparatus 30 as shown in FIG. 7 . Thus, since the service apparatus 30 provides the recommendation item list to the web server 20 in the form of a banner, the web server 20 may not perform the additional data processing procedure.

6 illustrates a method of transmitting a recommendation item list according to a request of the web server 30 after the service apparatus 30 performs a post-process. However, the service apparatus 30 may receive the recommendation item list from the web server 20 Upon receiving the recommendation item list request message, it may post-process the requested recommendation item list and transmit the post-processed recommendation item list to the web server 20. That is, the step of performing post-processing may be performed between steps S605 and S607.

The service apparatus 30 (in particular, the feedback processing unit 225) may collect the feedback of the user and reflect the feedback to the recommendation (S311).

The feedback of the user can be calculated according to the user's click rate, and the recommended view log data and the user's recommended click log data can be collected to calculate the click rate.

First, a method of collecting click log data will be described.

As a first method, when the recommendation item included in the recommendation item list of the user is clicked, the user is redirected to the service device 30 to acquire the click log data of the user, which will be described with reference to FIG.

9 is a diagram illustrating a method of collecting click log data according to an embodiment of the present invention.

9, when the terminal 10 selects (e.g., clicks or touches) a specific recommendation item included in a recommended item list displayed on a web page of the web server 20 (S901) , The terminal 10 requests connection to the service device 30 through the link URL of the recommendation item (S903). That is, the recommendation item may have URL information for moving to the service device 30 instead of the URL information for moving to the web page displaying the recommendation item.

For example, each referral item (s) in the referral item list may include a link URL in the format "http://api.recopick.com/VERSION/banner/SERVICE_ID/pick?source=SOURCE_ITEM_ID&pick=TARGET_ITEM_ID&method=ALGORITHM"Lt; / RTI &gt; The link URL of each recommendation item includes version information of a recommendation item list to which the recommendation item belongs, a service identifier, a source item (an item to be a target item for which a recommendation item is displayed), a target item (a recommendation item ) Identifier, algorithm information for calculating the selected recommendation item, and the like.

For example, if items 132, 178, and 200 are recommended in the item 59 of the Web server 20 having the service identifier (SERVICE_ID) of 6, and the user clicks on recommendation of the item 132 recommended by the algorithm 2, The terminal 10 moves to the service device 30 via a URL such as "http://api.recopick.com/1/banner/6/pick?source=59&pick=132&method=2&quot ;.

The service device 30 stores click log data for the terminal 10 attempting to access the service device 30 (S905). As described above, the recommendation item link URL may include version information of a recommended item list to which the recommendation item belongs, a service identifier, a source item identifier, a target item identifier, algorithm information for calculating a selected recommendation item, Through the URL to which the terminal 10 tries to connect, it is possible to check from which web server 20 any recommended item is clicked by the user and to confirm whether the recommended item has been calculated by the recommendation algorithm have.

The service device 30 transmits the redirect URL to the corresponding terminal 10 so that the terminal 10 can reconnect to the web server 20 (S907). For example, the service apparatus 30 transmits a URL such as "http://hellonature.net/goods/132?recopick=2" to the terminal 10 so that the terminal 10 can access the web page displaying the item 132 selected by the terminal 10. [ (10).

The receiving terminal 10 accesses the web server 20 through the received redirect URL (S909).

9, the click information of the user is transmitted to the service device 30 every time the user clicks on the recommendation item, so that the service device 30 realizes the user's click log data Can be stored.

As a second method, a predetermined parameter is added to a variable constituting a link of the recommendation item, and if the predetermined specific parameter described above exists in the user's visit URL information in the user log data collected in step S301, It can be judged by a click. That is, data including a predetermined parameter in the visit URL can be extracted from the user log data and stored as click log data. For example, if recopick = METHOD is added to the link variable of the recommendation item and the recopick exists in the user's visit URL in the user log data, it can be judged as a recommendation click. After confirming the item identifier (ITEM_ID) in the reference address (Referrer) information, the source item identifier can be confirmed using the item identifier (ITEM_ID). However, when the reference address information has the URL of the service device 30, it may not be judged as a recommendation click because it is already counted as the click log data in the first method.

The service device 30 described above can collect click log data using the first method and / or the second method and store the collected click log data.

Table 11 illustrates the format of the click log data.

Log type
(LOGTYPE) version
(VERSION) Service identifier (SERVICE_ID) Click item
(CLICK ITEM) Source Item
(SOURCE ITEM) algorithm
(METHOD) Time
(TIMESTAMP) click 2 One 597 117 2 20XX-YY-ZZ aa: bb: cc click 2 One 11556 11816 2 20XX-YY-ZZ aa: bb: cc

Referring to Table 11, the click log data may include a log type (click or view), version information for a recommended item list, service identifier, click item information, source item information, recommendation algorithm, click time information, and the like.

Next, the method of collecting view log data will be described. The service apparatus 30 can acquire and store view log data through a recommended item list provided whenever the web server 20 requests the recommended item list.

Table 12 illustrates the format of view log data.

Log type
(LOGTYPE) version
(VERSION) Service identifier (SERVICE_ID) Click item
(CLICK ITEM) Source Item
(SOURCE ITEM) Recommended list
RECOMMENDED LIST
)
(ITEM_ID: METHOD, ITEM_ID: METHOD, ITEM_ID: METHOD) Algorithm (METHOD) Time
(TIMESTAMP) viewing 2 One - 182 158: 2.73: 2.566: 2.85: 2.89: 2 2 20XX-YY-ZZ aa: bb: cc viewing 2 14 - 13830 13844: 2,13841: 2,13828: 2,13843: 2,13845: 2 2 20XX-YY-ZZ aa: bb: cc viewing 2 14 - 13670 13732: 2,13534: 2,13780: 2,13698: 2,13822: 2 2 20XX-YY-ZZ aa: bb: cc viewing 2 14 - 13670 13732: 2,13534: 2,13780: 2,13698: 2,13822: 2 2 20XX-YY-ZZ aa: bb: cc viewing 2 6 - 43 15: 2,299: 2,316: 2,329: 2,16: 2,42: 2,92: 2,210: 2,276: 2,83: 2 2 20XX-YY-ZZ aa: bb: cc viewing 2 One - 176 512: 2,153: 2,809: 2,637: 2,177: 2 2 20XX-YY-ZZ aa: bb: cc viewing 2 6 - 178 41: 2,398: 2,115: 2,421: 2,230: 2,12: 2,372: 2,177: 2,45: 2,293: 2 2 20XX-YY-ZZ aa: bb: cc viewing 2 14 - 13795 13796: 2,13785: 2,13787: 2 2 20XX-YY-ZZ aa: bb: cc

Referring to Table 12, the click log data includes a log type (click or view), version information for a recommended item list, service identifier, click item information, source item information, recommendation list, recommendation algorithm, .

In this way, the service device 30, which has collected the click log data and the view log data, can calculate the click rate using the click log data and the view log data. The service device 30 may add up the number of views exposed for a specific item by date and sum up the number of times the user clicks, and then calculate the click rate between each source item and each recommended item.

Table 13 illustrates the click rate.

date
(DATE) algorithm
(ALGORITHM) Source Item Identifier
(SOURCE_ITEM_ID) Recommended Item Identifier
(RECOMMENDED_ITEM_ID) Click count
(CLICK COUNT) View count
(VIEW COUNT) Click rate
(CLICK RATIO) 20XX-YY-ZZ 2 123 234 4 100 4% 20XX-YY-ZZ 2 123 345 11 100 11% 20XX-YY-ZZ 2 123 456 0 100 0% 20XX-YY-ZZ 2 123 789 7 100 7% 20XX-YY-ZZ 3 123 111 2 100 2% 20XX-YY-ZZ 3 123 222 3 100 3% 20XX-YY-ZZ 3 123 333 0 100 0% 20XX-YY-ZZ 3 123 444 5 100 5%

Referring to Table 13, the click rate of Algorithm 2 for Item 123 is 20%, and the click rate for 20XX YYYYZZZZ day is (4 +11 + 0 + 7) / 100 = 22% 2 + 3 + 0 + 5) / 100 = 10%.

The service device 30 may calculate the click rate between each source item and each recommendation item, and then designate the item as a prohibited item when the click rate continues to be lower than (or below) a predetermined threshold value for a predetermined period. That is, if the recommended item B for item A is less than 1% for 7 days, item B can be removed from the list of recommended items for item A. In addition, the service device 30 may designate a prohibited item as a prohibited item when the number of click counts between each source item and each recommendation item is less than (or less than) a specific threshold value for a certain period of time. When the recommendation prohibited item is removed from the recommendation result (or the recommended item list), the service device 30 deletes the item to be deleted from the previously generated recommendation result (or the recommended item list) The recommendation score can be changed to a lower value or the value of a variable can be adjusted so that a lower value is calculated to remove the recommended prohibited item from the recommendation result (or recommend item list).

This feedback processing process can be performed automatically in the service device 30. [ The service device 30 provides the web server 20 with the click rate information of the item and the click rate information or the click frequency information between the item and the recommendation item for each item serviced by the web server 20, A feedback process may be performed in the service device 30 at a request from the service device 30. [

10 is a diagram illustrating a click rate for each recommendation item according to an embodiment of the present invention.

10, the service apparatus 30 stores information about the source item 101, such as the name of the source item 101, the average click rate information for a certain period of time, and the schedule for the source item 101 in the web server 20 It is possible to provide the total recommended click rate 102 during the period. Also, it is possible to provide a recommendation item list 103 for the source item 101 and a name, an algorithm, a recommendation score, a click rate between source items, an operation input button, and the like for each recommendation item. Through such information, the administrator of the web server 20 can confirm the click rate trend of the source item 101 and the click rate trends of the corresponding source items 101 for each recommendation item by date. In the case of FIG. 10, it is illustrated that the click rate of the recommendation item 104 displayed at the bottom of the page is about 0% for a certain period of time. When the web server 20 administrator selects a recommendation prohibition button for the recommendation item having a low click rate, the web server 20 transmits the recommendation prohibition button to the service apparatus 30 so that the service apparatus 30 transmits the recommendation item as a source item It is possible to prohibit recommendation to the user 101. The web server 20 transmits the recommendation score to the service apparatus 30 so that the recommendation score of the selected recommendation item is displayed on the display unit 30. [ The recommendation item list can be generated so that the recommendation item is displayed with the highest priority (for example, at the uppermost or leftmost position) regardless of the recommendation item.

In addition, the service device 30 can automatically select the most suitable algorithm for each web server 20 in consideration of the click rate information and the click frequency information.

First, the service apparatus 30 transmits user log data to the web server 20 under a specific condition or a plurality of (preferably, a plurality of) conditions for applying the algorithm with the best efficiency (that is, the highest click rate or the highest number of clicks) , And provides a list of recommended items calculated by different algorithms for each group. For example, the service device 30 arbitrarily divides the user log data into groups A and B (for example, group A when the user identifier is odd and group B when the user identifier is even) A recommendation is calculated with the algorithm 2 in the group B, and the recommendation item list can be provided to the web server 20. In addition, the service device 20 may use the user agent information of the web browser in the user log data to group the user connected to the web server 20 through the mobile terminal and the group connected to the web server 20 through the fixed terminal, The web server 20 can provide a list of recommended items by dividing the log data and calculating the recommendation through different algorithms.

Then, the service device 30 can calculate the recommendation by separately calculating the click rate for each group and selecting the algorithm having the highest click rate or the algorithm having the highest number of clicks as the algorithm of the corresponding service. This feedback process may also be performed automatically by the service device 30 and the service device 30 may transmit the click rate information or click frequency information to the web server 20 by user group 20 and a feedback process may be performed in the service device 30 by a request from the web server 20. [

11 is a diagram illustrating a recommendation rate for each algorithm according to an embodiment of the present invention.

11, since the recommendation rate for the algorithm 1 applied to the user group A is continuously higher than the recommendation rate for the algorithm 2 for a certain period of time, the service apparatus 30 transmits the recommendation algorithm for the web server 20 .

Embodiments in accordance with the present invention may be implemented by various means, for example, hardware, firmware, software, or a combination thereof. In the case of hardware implementation, an embodiment of the present invention may include one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs) field programmable gate arrays, processors, controllers, microcontrollers, microprocessors, and the like.

In addition, in the case of an implementation by firmware or software, an embodiment of the present invention may be embodied in the form of a module, a procedure, a function, and the like for performing the functions or operations described above, Lt; / RTI &gt; Here, the recording medium may include program commands, data files, data structures, and the like, alone or in combination. Program instructions to be recorded on a recording medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. For example, the recording medium may be an optical recording medium such as a magnetic medium such as a hard disk, a floppy disk and a magnetic tape, a compact disk read only memory (CD-ROM), a digital video disk (DVD) Includes a hardware device that is specially configured to store and execute program instructions such as a magneto-optical medium such as a floppy disk and a ROM, a random access memory (RAM), a flash memory, do. Examples of program instructions may include machine language code such as those generated by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like. Such hardware devices may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

While the present invention has been described in connection with what is presently considered to be practical exemplary embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, It will be apparent to those skilled in the art. Furthermore, although specific terms are used in this specification and the drawings, they are used in a generic sense only to facilitate the description of the invention and to facilitate understanding of the invention, and are not intended to limit the scope of the invention. Accordingly, the foregoing detailed description is to be considered in all respects illustrative and not restrictive. The scope of the present invention should be determined by rational interpretation of the appended claims, and all changes within the scope of equivalents of the present invention are included in the scope of the present invention.

In addition, a device or terminal according to the present invention may be driven by instructions that cause one or more processors to perform the functions and processes described above. Such instructions may include, for example, interpreted instructions such as script commands, such as JavaScript or ECMAScript commands, or other instructions stored in executable code or computer readable media. Further, the apparatus according to the present invention may be implemented in a distributed manner across a network, such as a server farm, or may be implemented in a single computer device.

Further, a computer program (also known as a program, software, software application, script or code) that is embedded in the apparatus according to the present invention and which implements the method according to the present invention includes a compiled or interpreted language, a priori or procedural language , And may be deployed in any form including standalone programs or modules, components, subroutines, or other units suitable for use in a computer environment. A computer program does not necessarily correspond to a file in the file system. The program may be stored in a single file provided to the requested program, or in multiple interactive files (e.g., a file storing one or more modules, subprograms, or portions of code) (E.g., one or more scripts stored in a markup language document). A computer program may be deployed to run on multiple computers or on one computer, located on a single site or distributed across multiple sites and interconnected by a communications network.

Moreover, in describing the embodiments according to the present invention, operations are depicted in the drawings in a particular order, but it is to be understood that they should perform such operations in that particular order or sequential order shown in order to obtain the desired result, Should not be understood as being performed. In certain cases, multitasking and parallel processing may be advantageous. Also, the separation of the various system components of the above-described embodiments should not be understood as requiring such separation in all embodiments, and the described program components and systems will generally be integrated together into a single software product or packaged into multiple software products It should be understood.

The method of providing the recommendation result of the present invention can be applied to various wired / wireless communication systems.

10: terminal 20: web server 30: service device
40: network 210: communication unit 220:
221: Data collecting unit 222: Data processing unit 223:
224: Recommendation result providing unit 225: Feedback processing unit 230:

Claims (24)

A communication unit for transmitting and receiving data;
A storage unit for storing user log data and recommendation results; And
The method includes collecting the user log data related to the web site from a terminal connected to the web site through a script inserted in the web site, and using the recommendation algorithm based on the user log data, Extracting a recommended item list related to the requested source item from the recommendation result in response to a recommendation item list request received from a web server of the web site, To the web server. The apparatus of claim 1,
And calculates a click rate for a recommendation item related to each source item through click log data and view log data for the recommendation item. 3. The apparatus of claim 2,
And excludes a recommendation item in which the click rate is continuously lower than a threshold value for a predetermined period of time from the recommendation result. The apparatus of claim 1,
Divides the user log data into predetermined conditions or arbitrarily into a plurality of groups, and calculates the recommendation result by using different recommendation algorithms for each group. 5. The apparatus of claim 4,
Wherein the click rate calculation unit calculates the click rate for each group through the click log data and the view log data for the recommendation item and calculates the recommendation result with a recommendation algorithm used for the group having the highest click rate. The apparatus of claim 1,
And acquires click log data for the recommendation item through the connection URL of the terminal when the terminal is connected through the link of the recommendation item connected to the service device. The apparatus of claim 1,
Extracts user data including a predetermined parameter value from a visit URL (Uniform Resource Locator) included in the user log data, and obtains the extracted user data as click log data for the recommendation item. The apparatus of claim 1,
And acquires view log data for the recommendation item through the recommendation item list if the recommendation item list request from the web server is received. The apparatus of claim 1,
And extracts item information displayed on the visit URL from a visit URL (Uniform Resource Locator) included in the user log data and operation information related to the operation of the terminal on the visit URL. The apparatus of claim 1,
A recommendation result for each source item is separately stored, and a hash is added to a string including a service identifier for identifying the web site, an item identifier for the source item, and a recommendation item identifier for a recommendation item related to the source item hash function, and stores the calculated value together with the recommendation result. The apparatus of claim 1,
And transmits a recommendation item list related to the requested source item in a JavaScript Object Notation (JSON) format or an iFrame format. The method according to claim 1,
Wherein the user log data includes a domain of the website, a visit URL (Uniform Resource Locator) of the terminal, a user identifier, and visit time information. 13. The method of claim 12,
Wherein the user identifier is generated by a web browser cookie of the terminal, and is generated by combining an arbitrary number with the generation time. Collecting the user log data related to the website from a terminal connected to the web site through a script inserted in the web site by the service device;
Calculating a recommendation result for one or more recommendation items related to each source item served by the service apparatus using the recommendation algorithm based on the user log data; And
Extracting a recommendation item list related to the requested source item from the recommendation result in response to a recommendation item list request received from the web server of the website, and transmitting the recommendation item list to the web server; Item providing method. 15. The method of claim 14,
Further comprising the step of the service device calculating a click rate for a recommendation item associated with each source item via click log data and view log data for the recommendation item. 16. The method of claim 15,
Further comprising the step of the service device excluding a recommendation item in which the click rate is continuously lower than a threshold value for a predetermined period of time from the recommendation result. 15. The method of claim 14, wherein the calculating the recommendation result comprises:
Wherein the service apparatus divides the user log data into a predetermined condition or a plurality of groups, and calculates the recommendation result using a different recommendation algorithm for each group. 18. The method according to claim 17, wherein the step of calculating the recommendation result comprises:
Wherein the service device calculates a click rate for each group through click log data and view log data for the recommendation item and calculates the recommendation result with a recommendation algorithm used for the group having the highest click rate . 15. The method of claim 14,
Further comprising the step of acquiring the click log data for the recommendation item through the connection URL of the terminal when the terminal is connected through the link of the recommendation item to which the service apparatus is connected to the service apparatus Way. 15. The method of claim 14,
Further comprising the step of the service device extracting user data including a predetermined parameter value from a visit URL (Uniform Resource Locator) included in the user log data and using the extracted user data as click log data for the recommendation item Item providing method. 15. The method of claim 14,
Further comprising the step of obtaining view log data for the recommendation item through the recommendation item list if the service apparatus requests the recommendation item list of the web server. 15. The method of claim 14,
Further comprising extracting, from the Uniform Resource Locator (URL) included in the user log data, item information displayed on the visit URL and operation information related to the operation of the terminal in the visit URL, How to provide recommended items. 15. The method of claim 14,
Wherein the service apparatus stores the recommendation result for each source item separately and stores the service identifier for identifying the website, the item identifier for the source item, and the recommendation item identifier for the recommendation item related to the source item Further comprising: storing a value calculated by applying a hash function to a string together with the recommendation result. A computer-readable recording medium recording a program for executing the recommendation item providing method according to any one of claims 14 to 23.

Images