KR20190138412A - A method for presenting information on a product based on high speed similarity calculation and an apparatus therefor - Google Patents

Abstract

The present invention relates to a method for providing information on a product based on high-speed similarity calculation, and a recommendation server therefor. The method comprises the steps of: allowing a data collection server to collect, from user terminals, a plurality of behavior logs each including a user identifier and a product, and transmit the collected behavior logs to an analysis server; allowing the analysis server to delete some of the plurality of behavior logs; allowing the analysis server to calculate similarity by performing similarity calculation on the plurality of behavior logs of which some are deleted; allowing the analysis server to generate information on a product according to a result of the similarity calculation; and allowing the analysis server to transmit the information on the product to an application server. Thus, the load of the system can be reduced.

Description

A method for presenting information on a product based on high speed similarity calculation and an apparatus therefor}

The present invention relates to a technique for providing information on a product, and more particularly, to provide information about the product through the similarity analysis of the behavior log, while reducing the amount of data for the similarity operation to perform a high speed similarity operation The present invention relates to a method for deriving information on a product and to provide derived information, and an apparatus therefor.

As the market for applications running on mobile devices such as smartphones and tablet pads expands rapidly, the related advertising market is expanding rapidly.

In this regard, a mobile device (hereinafter referred to as a user terminal) may receive and display an advertisement provided from a recommendation server when executing an application, which is an advertisement medium, or accessing a service page (eg, a web page). If you choose to be able to access the advertiser page linked to the advertisement.

At this time, the recommendation server checks the attribute of the registered advertisement and the appropriate advertisement recipient group from the advertiser in order to enhance the effect of the advertisement, and adopts a kind of targeting technique that provides the corresponding advertisement to each user belonging to the identified advertisement recipient group.

Here, the advertisement recipient group may be classified by a segmentation technique in which attributes corresponding to advertisements for each user are defined as segments, and users corresponding to the same segment are classified into one advertisement recipient group. According to any classification criteria, a single group of recipients classified as defined by specific attributes may be referred to as segments.

In the existing targeting advertisement, each segment is extracted based on the behavior log information of the user, and the segment is extracted by analyzing the similarity of the behavior log information. However, the amount of such behavior log information is huge, and the computation time for similarity analysis puts a huge load on the system. Therefore, there is a need for a method capable of reducing the computation time.

Registered Korean Patent No. 10-1567217, November 2015 02 Registered (Name: Collaborative filtering recommendation method and system using social network analysis technique)

Therefore, an object of the present invention is to extract the information about the product through the similarity analysis of a large amount of behavior log information, to reduce the amount of data for the similarity operation to extract information about the product through a high-speed similarity operation, A method of providing extracted information and an apparatus therefor are provided.

Method for providing information about the product according to a preferred embodiment of the present invention for achieving the above object is a data collection server collects a plurality of behavior logs each containing a user identifier and a product from the user terminal Transmitting to an analysis server, clearing a part of a plurality of behavior logs by the analysis server, calculating a similarity by performing a similarity operation on the plurality of behavior logs in which the analysis server is partially erased; And generating, by the analysis server, information about a product according to the similarity calculation result, and transmitting, by the analysis server, information about the product to an application server.

The step of erasing some of the plurality of behavior logs includes determining an erase ratio which is a ratio of the behavior logs to be erased from the entire behavior log according to the amount of information on the product to be provided.

The step of erasing some of the plurality of behavior logs may include determining the number of purchased products of the behavior log to erase according to the determined erase ratio after determining the erase ratio.

The calculating of the similarity by performing the similarity operation may include an action login union including at least one of any one product and another product, and a behavior login intersection including both the one product and the other product. The degree of similarity between the one product and the other product is calculated using the molecule.

The generating of the information on the product according to the result of the similarity calculation may include deriving a predetermined number of products as the information on the product in the order of the high similarity according to the calculated similarity.

Apparatus for providing information about goods according to a preferred embodiment of the present invention for achieving the above object is an analysis server communication unit for communication with the application server, and the target from the application server through the analysis server communication unit Upon receiving a recommendation product request message including a number of products and recommended products, a deletion object is specified among a plurality of behavior logs including a user identifier and a purchased product corresponding to the user identifier, and the erase target is specified in the plurality of behavior logs. A preprocessing module for erasing an object to be erased, and a similarity calculation module for calculating a degree of similarity with the target product using a plurality of behavior logs from which the object to be erased is erased.

The preprocessing module may be configured to calculate an erase ratio, which is a ratio of behavior logs that can be erased according to the number of recommended products, and determine an erase target according to the calculated erase ratio and the number of purchased products of the behavior log. .

The similarity calculation module uses a behavior login union including at least one of a target product and another product as a denominator, and uses a behavior login intersection including both the target product and the other product as a numerator. The similarity is calculated.

The apparatus derives the products of the number of the recommended products in the order of high similarity according to the calculated similarity among the other products as recommended products, and transmits the derived recommended products to the application server through the analysis server communication unit. It further comprises an information providing module.

According to the present invention, a plurality of behavior logs that do not affect the result of the similarity calculation are identified as an erase target, and the speed of the similarity operation is improved by erasing the data in the preprocessing process, thereby reducing the load on the system.

1 is a configuration diagram schematically showing an information providing system according to an embodiment of the present invention.
2 is a block diagram showing the main configuration of a user terminal according to an embodiment of the present invention.
3 is a block diagram showing the main configuration of a data collection server according to an embodiment of the present invention.
4 is a block diagram showing the main configuration of the analysis server according to an embodiment of the present invention.
5 is a block diagram showing the main configuration of an application server according to an embodiment of the present invention.
6 is a flowchart illustrating a method for providing information about a product according to an embodiment of the present invention.
7 is a flowchart illustrating a fast similarity calculation method according to an embodiment of the present invention.
8 is a flowchart illustrating a method of providing information about a product according to another embodiment of the present invention.
9 is a screen example for explaining a method for providing information on a product according to another exemplary embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS To make the features and advantages of the present invention more clear, the present invention will be described in more detail with reference to specific embodiments shown in the accompanying drawings.

However, in the following description and the accompanying drawings, detailed descriptions of well-known functions or configurations that may obscure the subject matter of the present invention will be omitted. In addition, it should be noted that like elements are denoted by the same reference numerals as much as possible throughout the drawings.

The terms or words used in the following description and drawings should not be construed as being limited to the ordinary or dictionary meanings, and the inventors may appropriately define the concept of terms for explaining their own invention in the best way. It should be interpreted as meaning and concept corresponding to the technical idea of the present invention based on the principle that the present invention. Therefore, the embodiments described in the present specification and the configuration shown in the drawings are only the most preferred embodiments of the present invention, and do not represent all of the technical ideas of the present invention, and various alternatives may be substituted at the time of the present application. It should be understood that there may be equivalents and variations.

In addition, terms including ordinal numbers, such as first and second, are used to describe various components, and are used only to distinguish one component from another component, and to limit the components. Not used. For example, without departing from the scope of the present invention, the second component may be referred to as the first component, and similarly, the first component may also be referred to as the second component.

In addition, when a component is referred to as being "connected" or "connected" to another component, it means that it may be connected or connected logically or physically. In other words, although a component may be directly connected or connected to other components, it should be understood that other components may exist in the middle, and may be connected or connected indirectly.

In addition, the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In addition, the terms "comprises" or "having" described herein are intended to indicate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, and one or the same. It is to be understood that the present invention does not exclude in advance the possibility of the presence or addition of other features, numbers, steps, operations, components, parts, or combinations thereof.

In addition, the terms "?", "?", "Module", etc. described in the specification mean a unit for processing at least one function or operation, which may be implemented by hardware or software, or a combination of hardware and software. have.

Also, "a or an", "one", "the" and the like are also indicated differently herein in the context of describing the present invention (especially in the context of the following claims). Unless otherwise expressly contradicted by context, it may be used in the sense including both the singular and the plural.

In addition, embodiments within the scope of the present invention include computer readable media having or conveying computer executable instructions or data structures stored on computer readable media. Such computer readable media can be any available media that can be accessed by a general purpose or special purpose computer system. By way of example, such computer readable media may be in the form of RAM, ROM, EPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage, or computer executable instructions, computer readable instructions or data structures. And may include, but are not limited to, any other medium that can be used to store or deliver certain program code means, and can be accessed by a general purpose or special purpose computer system. .

In the following description and claims, “network” is defined as one or more data links that enable the transfer of electronic data between computer systems and / or modules. When information is transmitted or provided to a computer system via a network or other (wired, wireless, or a combination of wired or wireless) communication connections, this connection can be understood as a computer-readable medium. Computer-readable instructions include, for example, instructions and data that cause a general purpose or special purpose computer system to perform a particular function or group of functions. The computer executable instructions may be, for example, binary, intermediate format instructions such as assembly language, or even source code.

In addition, the present invention relates to personal computers, laptop computers, handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, mobile phones, PDAs, pagers In a network computing environment having various types of computer system configurations, including (pager) and the like, it may be applied to providing advertisements to the computer systems. The invention may also be practiced in distributed system environments where both local and remote computer systems that are linked via wired networks, wireless data links, or combinations of wired and wireless data links perform tasks. In a distributed system environment, program modules may be located in both local and remote memory storage devices.

First, an information providing system according to an embodiment of the present invention will be described. 1 is a configuration diagram schematically showing an information providing system according to an embodiment of the present invention.

Referring to Figure 1, the information providing system 100 according to an embodiment of the present invention is a plurality of user terminals (10: 10-1, 10-2, -10-n), data collection server 20, analysis server 30 and the application server 40.

The plurality of user terminals 10: 10-1, 10-2,? 10-n, the data collection server 20, the analysis server 30, and the application server 40 share data with each other through a communication network NW. Can send and receive

For example, the communication network NW may include a wireless communication network such as a wireless LAN (WLAN), Wi-Fi, Wibro, Wimax, High Speed Downlink Packet Access (HSDPA), Depending on how the system is implemented, it may include wired communication networks such as Ethernet, xDSL (ADSL, VDSL), Hybrid Fiber Coaxial Cable (HFC), Fiber to The Curb (FTTC), and Fiber To The Home (FTTH).

In addition, the communication network NW of the present invention may include, for example, a mobile communication network including a plurality of access networks (not shown) and a core network (not shown) connecting them. Here, the access network is a network that performs wireless communication by directly connecting to a terminal, for example, a plurality of base stations such as a base station (BS), a base transceiver station (BTS), a NodeB, an eNodeB, and a base station controller (BSC). It may be implemented as a base station controller such as a Radio Network Controller (RNC). In addition, as described above, the digital signal processing unit and the wireless signal processing unit, which are integrally implemented in the base station, are divided into digital units (hereinafter referred to as DUs and radio units (hereinafter referred to as RUs)). A plurality of RUs (not shown) may be installed in a plurality of areas, respectively, and a plurality of RUs may be connected to a centralized DU, and a core network (not shown) constituting a mobile network together with an access network may be connected with the access network. It serves to connect another communication network such as an external network, for example, the Internet network.

As described above, the core network is a network system that performs main functions for mobile communication services such as mobility control and switching between access networks, and performs circuit switching or packet switching. Manage and control the flow of packets within In addition, the core network may manage inter-frequency mobility and may play a role for interworking with traffic in the access network and the core network and other networks such as the Internet network. The core network may further include a serving gateway (SGW), a PDN gateway (PGW), a mobile switching center (MSC), a home location register (HLR), a mobile mobility entity (MME), and a home subscriber server (HSS). It may be.

In addition, the communication network (NW) according to the present invention may include an Internet network. The Internet network refers to a general public communication network, that is, a public network, through which information is exchanged according to the TCP / IP protocol.

Through the communication network (NW), a plurality of user terminals 10: 10-1, 10-2,? 10-n, the data collection server 20, the analysis server 30, and the application server 40 interoperate with each other. The information providing system 100 for providing product information according to the present invention is configured.

The plurality of user terminals 10 may each install and execute at least one application. In particular, the user terminal 10 may install an application interworking with the data collection server 20, and transmit an action log to the data collection server 20 according to the execution of the application. In this case, the plurality of user terminals 10 may transmit the behavior log to the data collection server 20 through the installed SDK (Software Development Kit). However, the present invention is not limited thereto, and the plurality of user terminals 10 may provide an action log to the data collection server 20 through a separate application installation in connection with the data collection server 20.

In this case, the plurality of user terminals 10 may extract a behavior log including a product purchase history through an API (Application Programming Interface) included in the installed SDK, and provide the extracted behavior log to the data collection server 20. . Here, the behavior log includes a user ID (UID), which is a unique code of the user terminal, and a purchased item. Here, the user identifier (UID) may be an identification number assigned to each mobile terminal to distinguish each of the user terminals 10.

Here, the plurality of user terminals 10 will be described as a representative example of the mobile communication terminal, but the terminal is not limited to the mobile communication terminal, and all information communication devices, multimedia terminals, wired terminals, fixed terminals and IP (Internet Protocol) terminals, etc. It can be applied to various terminals. In addition, the terminal may be advantageously used when the mobile terminal having various mobile communication specifications such as a mobile phone, a portable multimedia player (PMP), a mobile internet device (MID), a smart phone, and an information communication device. .

The data collection server 20 collects a behavior log including a user identifier (UID) and an item purchased by the user from the plurality of user terminals 10, and transfers the collected behavior log to the analysis server 30. Can be.

The analysis server 30 may sort the received behavior log according to the user identifier (UID) and the item (item). For example, the analysis server 30 may generate a table having a user identifier (UID) as a column and a product as a row. The analysis server 30 may analyze the behavior log collected from the data collection server 20 to derive information related to the product. For example, the analysis server 30 may analyze the behavior log to derive the 'product purchased together'. That is, the analysis server 30 may derive the 'product (RG) purchased together' with the target product TG through the similarity calculation. The analysis server 30 provides the information on the derived product, for example, the 'RG purchased together' to the application server 40.

The application server 40 is to provide an additional service for product marketing using the information on these products. Therefore, the application server 40 may provide information about the product when the user terminal 10 requests.

Meanwhile, in the embodiment of the present invention, the data collection server 20, the analysis server 30, and the application server 40 are described as independent devices, but are not limited thereto, and the shopping server 40 and the recommendation server 50 are not limited thereto. ) May be implemented as a single device.

Next, the user terminal 10 according to an embodiment of the present invention will be described in more detail. 2 is a block diagram showing the main configuration of a user terminal according to an embodiment of the present invention.

Referring to FIG. 2, the user terminal 10 according to the exemplary embodiment of the present invention includes a communication unit 11, an input unit 13, a display unit 15, a storage unit 17, and a controller 19.

The communication unit 11 functions to perform communication of the user terminal 10. That is, the communication unit 11 transmits and receives data with the data collection server 20 through the communication network (NW). In particular, the communication unit 11 according to the embodiment of the present invention may transmit the behavior log to the data collection server 20.

The input unit 13 receives various information such as numeric and text information, and transmits a signal input in connection with setting of various functions and function control of the user terminal 10 to the controller 19. In addition, the input unit 13 may include at least one of a keypad and a touch pad generating an input signal according to a user's touch or manipulation. In this case, the input unit 13 may be configured in the form of one touch panel (or touch screen) together with the display unit 15 to simultaneously perform input and display functions. In particular, the input unit 13 may transmit an input signal for communication and data according to application execution to the controller 19 according to a user's manipulation. In addition, when the user terminal 10 is configured in the form of a touch screen, the input unit 13 may receive a signal touched on the screen, or receive an input such as a keyboard and a mouse.

The display unit 15 displays information on a series of operation states and operation results that occur during the functioning of the user terminal 10. In addition, the display unit 15 may display a menu of the user terminal 10 and user data input by the user. The display unit 15 may include a liquid crystal display (LCD), a thin film transistor LCD (TFT-LCD), organic light emitting diodes (OLED), a light emitting diode (LED), an active matrix organic LED (AMOLED), and a flexible display (Flexible). display) and a three-dimensional display (3 Dimension). In particular, when one of the plurality of web pages constituting the shopping mall web site is received, the display unit 15 displays the received web page on the screen.

The storage unit 17 stores an application program required for the functional operation of the user terminal 10. When the user terminal 10 activates each function in response to a user's request, the user terminal 10 executes corresponding application programs under the control of the controller 19 to provide each function. In addition, the data area is an area in which data generated according to the use of the user terminal 10 is stored.

The controller 19 may initialize each configuration of the user terminal 10 and perform necessary signal control. In particular, the control unit 19 according to an embodiment of the present invention accesses the shopping mall web server through the communication unit 11 to receive a web page constituting the shopping mall web site, and displays the received web page on the display unit 15. Indicated by. Accordingly, the user can purchase a predetermined product through the web page while viewing the web page. In particular, when the controller 19 detects a signal for selecting a specific product for purchase through the input unit 13 according to a user's operation, the controller 19 transmits a purchase request for the corresponding product to the shopping mall web server through the communication unit 11. The product can be purchased. Then, the controller 19 generates a behavior log through the purchase history of purchasing the product. Here, the behavior log includes a user identifier (UID) and a purchased item (item). Subsequently, the controller 19 may transmit the behavior log to the data collection server 20 through the communication unit 11.

Next, the configuration of the data collection server 20 according to an embodiment of the present invention to be described in more detail. 3 is a block diagram showing the main configuration of a data collection server according to an embodiment of the present invention.

Referring to FIG. 3, the data collection server 20 according to an embodiment of the present invention includes a collection server communication unit 21, a collection server storage unit 23, and a collection server control unit 25.

The collection server communication unit 41 has an interface for communicating with the user terminal 10, the analysis server 30, and the application server 40 through a communication network NW. In particular, the collection server communication unit 41 may receive a behavior log from the user terminal (10).

The collection server storage unit 23 stores data or programs executed or processed by the collection server control unit 25. The collection server storage unit 23 may store a behavior log in which a user identifier (UID) received from the user terminal 10 and a purchased product are mapped for a temporary or predetermined period of time.

The collection server controller 25 controls the overall operation of the data collection server 20 including the collection server communication unit 21 and the collection server storage unit 23, and may include a processor therefor. The collection server control unit 25 stores the behavior log received from the user terminal 10 in the collection server storage unit 23. The collection server control unit 25 may periodically transmit the behavior log stored in the collection server storage unit 23 to the analysis server 30 through the collection server communication unit 41.

Next, with reference to the drawings, the configuration of the analysis server 30 according to an embodiment of the present invention to be described in more detail. 4 is a block diagram showing the main configuration of the analysis server according to an embodiment of the present invention. Referring to FIG. 4, the analysis server 30 according to an embodiment of the present invention includes an analysis server communication unit 31, an analysis server storage unit 33, and an analysis server control unit 35.

The analysis server communication unit 31 has an interface for communicating with the data collection server 20 and the application server 30 through a communication network (NW). In particular, the analysis server communication unit 31 receives the behavior log from the data collection server 20, and transfers it to the analysis server control unit 35. In addition, the analysis server communication unit 31 receives information about the product (for example, the list of products purchased together) from the analysis server control unit 35, and transmits it to the application server 40.

The analysis server storage unit 33 is a configuration for storing data or programs executed or processed by the analysis server control unit 35. The analysis server storage unit 33 may store a program for deriving a recommended product according to the similarity from the behavior log. In addition, the analysis server storage unit 33 may accumulate and store the behavior log received from the data collection server 20.

The analysis server control unit 35 serves to control the overall operation of the analysis server 30 including the analysis server communication unit 31 and the analysis server storage unit 33, and may include a processor therefor.

In particular, the analysis server control unit 35 may include a preprocessing module 35a, a similarity calculation module 35b, and an information providing module 35c.

The analysis server control unit 35 receives the behavior log through the analysis server communication unit 31 and stores it in the analysis server storage unit 32. The preprocessing module 35a loads a plurality of behavior logs stored in the analysis server storage unit 32 and erases a part of the behavior logs. At this time, the preprocessing module 55a erases some of the plurality of behavior logs. The similarity calculation module 35b calculates the similarity between the behavior logs in which some of the plurality of behavior logs are erased. Such similarity may be calculated using a jacquard similarity calculating technique. The information providing module 55c derives information on the product through a similarity calculation result, for example, a recommendation product such as a 'purchased product together', and extracts the derived recommendation product through the analysis server communication unit 51 through the application server 40. ) Can be sent.

Next, the configuration of the application server 40 according to an embodiment of the present invention to be described in more detail. 5 is a block diagram showing the main configuration of an application server according to an embodiment of the present invention.

Referring to FIG. 5, an application server 40 according to an embodiment of the present invention includes an application server communication unit 41, an application server storage unit 43, and an application server controller 45.

The application server communication unit 41 has an interface for communicating with the user terminal 10, the data collection server 20, and the analysis server 30 through a communication network NW. In particular, the application server communication unit 41 may receive information (eg, a list of products purchased together) according to the result of analyzing the behavior log from the analysis server 30.

The application server storage unit 43 stores data or programs executed or processed by the application server control unit 45. In addition, the application server storage unit 43 may store the information on the product received from the analysis server 30 (for example, the list of products purchased together) for a time or a predetermined period.

The application server controller 45 controls the overall operation of the application server 40 including the application server communication unit 41 and the application server storage unit 43, and may include a processor therefor. The application server controller 45 stores the information (eg, a list of products purchased together) received from the application server 40 in the collection server storage 43. And, if necessary, the collection server control unit 25 transmits information about the product (for example, a list of products purchased together) to the user terminal 10 through the collection server communication unit 41.

Next, a method for providing information on a product according to an embodiment of the present invention will be described. 6 is a flowchart illustrating a method for providing information about a product according to an embodiment of the present invention.

Referring to FIG. 6, the data collection server 20 may collect a plurality of behavior logs from the plurality of user terminals 10 in step S110. Here, the behavior log includes a user identifier (UID) and an item.

Next, the data collection server 20 transmits the plurality of behavior logs collected in step S120 to the analysis server 30. Then, the analysis server 30 analyzes the plurality of behavior logs received in step S130 through a similarity calculation to generate information about the product. In this case, the data collection server 20 erases some of the plurality of behavior logs during the similarity calculation and performs the similarity calculation through the remaining behavior logs. As a result, the speed of the similarity calculation is improved.

Next, a similarity calculation method according to an embodiment of the present invention will be described in detail.

The present invention calculates the similarity using the Jaccard similarity as shown in Equation 1 below.

That is, as shown in Equation 1, the value is calculated by using the denominator of the union of the behavior logs for the items A, ie, the commodity A and the commodity B, and the denominator of the interaction log of the commodities A and B. Here, the union of the behavior log for commodity A and commodity B is the behavior log where the purchased commodity includes at least one of commodity A and commodity B, and the intersection of the behavior log for commodity A and commodity B is the commodity A This is an action log that contains both and product B. The larger the calculated value, the higher the degree of similarity. The similarity between commodity A and commodity B is judged to be high.

For example, assume that data including six behavioral logs L1 to L6 are shown in Table 1 below.

Behavior log User identifier Item A Item B L1 UID1 One 0 L2 UID2 One 0 L3 UID3 One 0 L4 UID4 0 One L5 UID5 0 One L6 UID6 0 One

If three users purchased only product A, such as behavior logs L1, L2, and L3 in Table 1, and three users purchased only product B, such as behavior logs L4, L5, and L6, the similarity between product A and product B is (0/3 + 3-0) = 0 according to Equation 1. As such, the behavior log of a user who purchases only one product among the behavior logs may not affect the similarity calculation result. Accordingly, the present invention is intended to reduce unnecessary operations on the data (behavior log) during the operation by erasing the behavior log that does not affect the similarity calculation result.

Meanwhile, it is assumed that data including 200,000 behavior logs (L1 to L200,000) are shown in Table 2 below.

Behavior log User identifier Item A Item B L1 UID1 One 0 L2 UID2 One 0 L3 UID3 One 0 ? ? ? ? L100,000 UID100,000 One 0 L100,001 UID100,001 0 One L100,002 UID100,002 0 One L100,003 UID100,003 0 One ? ? ? ? L199,999 UID199,999 0 One L200,000 UID200,000 One One

For Table 2, 100,000 users purchased Product A, such as Behavior Logs L1 through L100,000, 199,999 users purchased only Product B, such as Behavior Logs L100,001 through L199,999, and Behavior Log L200,000. As such, it is assumed that one user has purchased both product A and product B.

In this case, the similarity between product A and product B yields 1 / (100,001 + 100,000-1) = 1 / 200,000 according to equation (1).

Here, if one user erases all of the behavior logs in which only one product is purchased, the similarity between the goods A and B is 1 / (1 + 1-1) = 1 according to Equation (1). This leads to distortion of the result.

As such, when a user of one of the plurality of behavior logs deletes all behavior logs in which only one product is purchased, the result of the similarity calculation may be distorted.

As shown in the behavior logs L1 to L6 of Table 1, when only two products A and B are considered, it can be determined that the user of each behavior log has purchased only one product. However, since a user may have purchased a product H, I, etc., deleting the user's behavior log may distort the similarity calculation result.

Accordingly, the present invention can specify the behavior log, that is, the object to be erased, according to the number of recommended products RG and the number of purchased products in the behavior log so as to reduce the computation amount without distorting the result of the similarity calculation. .

According to the method as described above, the analysis server 30 calculates information on the product through the similarity calculation.

Subsequently, the analysis server 30 transmits the information on the product generated in step S140 to the application server 40. Information about such a product may be, for example, a list of products purchased together. The application server 40 which has received the information about the product may provide the user terminal 10 with the information about the product if necessary.

Then, in more detail, a method of performing the similarity operation by specifying the erase target so as to reduce the amount of calculation without distorting the result of the similarity operation in step S130 described above will be described in more detail. 7 is a flowchart illustrating a fast similarity calculation method according to an embodiment of the present invention. This embodiment with reference to FIG. 7 is for explaining the step S130 of FIG. 6 in more detail.

Referring to FIG. 7, the preprocessing module 35a reads a plurality of behavior logs stored in the analysis server storage unit 32 in step S131, and the user logs and items of the plurality of behavior logs in step S132. You can sort by. For example, the preprocessing module 35a may generate a table having a user identifier (UID) as a column and a product as a row.

Subsequently, the preprocessing module 35a performs preprocessing to erase some of the plurality of behavior logs in step S133. At this time, the preprocessing module 35a determines an erasing ratio which is the ratio of the behavior log to be erased from the entire behavior log according to the amount of information on the product to be provided. In addition, the preprocessing module 35a determines the behavior log (the number of goods purchased in the behavior log) to be erased according to the determined erase ratio. For example, when a user wants to search, temporarily store (add to cart) or purchase a target product (TG) through the user terminal 10, the recommended product (RG), that is, purchased together Assume a situation where you want to provide 'product' as information about a product. In this case, as the number of recommended products RG, which is the amount of information on the product to be provided, increases, the erase ratio, which is the ratio of the behavior log to erase, decreases. As the number of recommended products RG decreases, the erase ratio, which is the ratio of the behavior log to erase, increases. The preprocessing module 35a deletes the behavior log of the number of purchased products if the ratio of the behavior log having the number of purchased products is one less than the erasure ratio. It is not possible to clear the behavior log of the number of purchased goods because of the influence. Therefore, the behavior log to be erased is determined according to the determined erase ratio. In detail, the preprocessing module 35a may erase the corresponding behavior log when the number of behavior logs indicated as having purchased one product is less than the determined erasing ratio relative to the total behavior logs.

Next, the preprocessing module 35a sorts the plurality of behavior logs according to the name of the product in step S134. In operation S135, the preprocessing module 35a groups the plurality of action logs according to the name of the product.

Next, the similarity calculation module 35b performs a similarity calculation according to the name of the product in step S136. Here, the similarity calculation module 35b uses a behavior login union including at least one of any one product and another product as a denominator, and the behavior login intersection including all of one product and other products as a numerator. Calculate the similarity between At this time, since the behavior log according to the purchase history of purchasing one product in advance is erased, the operation speed is improved.

Next, the information providing module 35c generates information about the product according to the similarity calculation result of the similarity calculating module 35b in step S137. Here, the information providing module 35c may generate a predetermined number of products as information about the products in order of high similarity according to the similarity calculated by the similarity calculating module 35b.

Information about such a product may be, for example, a list of products purchased together. The information providing module 35c may transmit the information about the generated product to the application server 40 through the analysis server communication unit 31.

Meanwhile, a method of providing information about a product based on a fast similarity calculation according to a more specific embodiment of the present invention will be described. 8 is a flowchart illustrating a method of providing information about a product according to another embodiment of the present invention. 9 is a screen example for explaining a method for providing information on a product according to another exemplary embodiment of the present invention. 8 and 9 are more specific embodiments of FIG. 6 and step S130 of FIG. 7.

8 and 9, it is assumed that the analysis server control unit 35 receives a product recommendation request message from the application server 40 through the analysis server communication unit 31 in step S210. The product recommendation request message is a message for requesting a recommendation product RG for the target product TG, as shown in FIG. 9. Accordingly, the product recommendation request message includes the number of the target product TG and the recommended product RG. For example, when the application server 40 attempts to search, temporarily store (add to cart), or purchase a target product TG through the user terminal 10 through the web site, the recommended product RG In other words, it is assumed that the situation is to show six 'goods purchased together', the number of the recommended product (RG) is six.

Upon receiving the product recommendation request message, the preprocessing module 35a sorts the plurality of behavior logs stored in the analysis server storage unit 32, that is, the entire behavior logs in step S220, for each user. For example, as shown in Table 3 below, the preprocessing module 35a generates a table in which the entire behavior log is a row of the user identifier (UID) of the user, and the row of the item purchased. Can be.

Behavior log User identifier Item A Item B Item C Product D ? L1 UID1 One 0 One One ? L2 UID2 0 One 0 One ? L3 UID3 One 0 0 0 ? L4 UID4 0 One One 0 ? L5 UID5 0 0 0 One ? L6 UID6 One One 0 One ? ? ? ? ? ? ?

Next, the preprocessing module 35a determines an erase ratio, which is a ratio of behavior logs that can be erased from the entire behavior log, according to the number of recommended products RG of the product recommendation request message in step S230. Here, the erase ratio decreases as the number of recommended products increases. Intuitively, the erase ratio may be inversely proportional to the number of recommended products. For example, when the number of the recommended products RG is 6, if the erase ratio is 10%, if the number of the recommended products RG is 30, the erase ratio may be 5%. Next, the preprocessing module 35a determines an erase target according to the erase ratio and the number of purchased goods in the behavior log in step S240. As an example, it is assumed that the number of recommended products RG is 6, and thus the erase ratio is 10%. The preprocessing module 35a calculates a ratio of the behavior logs of which the number of purchased goods of a user is two or less, as in L2, L3, L4, and L5 of Table 3 of the entire behavior logs. At this time, if the calculated ratio is 15%, the preprocessing module 35a excludes the activity log having the number of purchase products of two or less because the calculated ratio is greater than or equal to the erase ratio (10% <15%). The preprocessing module 35a calculates a ratio of the log of the behavioral log of which the number of purchased goods of one user is one, as in L3 and L5 of Table 3. At this time, if the calculated ratio is 8%, the preprocessing module 35a determines the behavior log whose number of purchased products is one because the calculated ratio is less than the erase ratio (10%> 8%).

Subsequently, the preprocessing module 35a erases the previously determined behavior log from the entire behavior log at step S250.

Next, the preprocessing module 35a sorts the entire behavior log from which the object to be erased has been removed in step S260 according to a product name, groups them according to the product name, and then extracts a group for the target product TG. do. For example, if the target product TG is a product A, that is, to recommend a product purchased with the product A, all the behavior logs including the purchased product A are extracted. That is, in the case of the behavior login in which the number of purchased products to be erased is one, L1 and L6 may be groups for the goods A because the data L3 is erased.

Next, the similarity calculation module 35b calculates similarity between the target product TG and a plurality of other products according to Equation 1 in operation S270. That is, the similarity calculation module 35b uses the behavior login union including at least one of the target product TG and other products as the denominator, and the behavior login intersection including both the target product TG and other products as the numerator. The similarity between the target product TG and another product is calculated.

For example, when the target product TG is the product A, the similarity calculation module 35b calculates the similarity between the product A and each of the other products (products B, C, D, E,?).

The similarity calculation module 35b calculates the union of the behavior log for the target product TG, for example, the product A and another product (products B, C, D, E,?) According to Equation 1 as the denominator and the target product ( The similarity can be calculated by using the intersection of TG) and the log of behavior for other products as the denominator. Here, the union of the behavior log for the target product and the other product is the behavior log in which the purchased product includes at least one of the target product and the other product, and the behavior for the target product and the other product. The intersection of the logs is the behavior log in which the purchased product includes both the target product (TG) and other products.

Subsequently, the information providing module 35c derives the number of products (eg, six) of the recommended products RG as recommended products in the order of high similarity according to the similarity calculated by the similarity calculation module 55b in step S280. . Then, the information providing module 35c transmits the derived recommendation product to the application server 40 through the analysis server communication unit 31 as information about the product. Accordingly, the application server 40 may construct a web page screen as shown in FIG. 9 and provide the same to the user terminal 10.

According to the present invention as described above, by specifying a plurality of behavior logs that do not affect the results of the similarity operation as the erase target, and by erasing in the preprocessing process, the speed of the similarity operation is improved, thereby reducing the load on the system. Can be.

As described above, the specification includes the details of a number of specific implementations, but these should not be understood as being limited to the scope of any invention or claimable, but rather may be specific to a particular embodiment of a particular invention. It should be understood as a description of the features. Certain features that are described in this specification in the context of separate embodiments may be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable subcombination. Furthermore, while the features may operate in a particular combination and may be initially depicted as so claimed, one or more features from the claimed combination may in some cases be excluded from the combination, the claimed combination being a subcombination Or a combination of subcombinations.

Likewise, although the operations are depicted in the drawings in a specific order, it should not be understood that such operations must be performed in the specific order or sequential order shown in order to obtain desirable results or that all illustrated operations must be performed. In certain cases, multitasking and parallel processing may be advantageous. Moreover, 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 that it can.

Specific embodiments of the subject matter described in this specification have been described. Other embodiments are within the scope of the following claims. For example, the actions recited in the claims can be performed in a different order but still achieve desirable results. As an example, the process depicted in the accompanying drawings does not necessarily require that particular depicted or sequential order to obtain desirable results. In certain implementations, multitasking and parallel processing may be advantageous.

The foregoing description presents the best mode of the invention, and provides examples to illustrate the invention and to enable those skilled in the art to make and use the invention. The specification thus produced is not intended to limit the invention to the specific terms presented. Thus, while the present invention has been described in detail with reference to the examples described above, those skilled in the art can make modifications, changes and variations to the examples without departing from the scope of the invention.

Therefore, the scope of the present invention should be determined by the claims rather than by the embodiments described.

The present invention relates to a method for recommending a product based on a fast similarity calculation, and a recommendation server for the same. When the similarity calculation used to derive a recommendation product is used, the present invention eliminates unnecessary behavior logs. Can improve speed. Accordingly, the load on the system can be reduced and the speed of the system can be improved. This may soon contribute to the development of the service industry, and in addition, the present invention has industrial applicability because the present invention is not only commercially available or commercially viable, but also practically and clearly implementable.

10: user terminal 11: communication unit
13: input section 15: display section
17: storage unit 19: control unit
20: data collection server 21: collection server communication unit
23: collection server storage unit 25: collection server control unit
30: analysis server 31: analysis server communication unit
33: analysis server storage unit 35: analysis server control unit
35a: preprocessing module 35b: similarity calculation module
35c: information providing module 40: application server
41: application server communication unit 43: application server storage unit
45: application server control unit

Claims (9)

Collecting, by the data collection server, a plurality of behavior logs, each of which includes a user identifier and a product, from the user terminal to the analysis server;
Clearing, by the analysis server, some of the plurality of behavior logs;
Calculating, by the analysis server, a similarity operation by performing a similarity operation on the plurality of behavior logs whose portions have been partially erased;
Generating, by the analysis server, information about a product according to a result of the similarity calculation; And
And transmitting, by the analysis server, the information about the product to an application server. The method of claim 1,
Clearing some of the plurality of behavior logs
And determining an erase ratio, which is a ratio of a behavior log to be erased from the entire behavior log, according to the amount of information on the product to be provided. The method of claim 2,
Clearing some of the plurality of behavior logs
After determining the erase ratio,
And determining the number of purchased goods in the behavior log to erase according to the determined erase rate. The method of claim 1,
Computing the similarity by performing the similarity operation
Denominator the action login union that includes at least one of one product and another product,
By using a behavior login intersection that includes both the one product and the other product as a molecule
And calculating the similarity between the one product and the other product. The method of claim 4, wherein
Generating information about the product according to the result of the similarity calculation
And deriving a predetermined number of products as information about the products in order of high similarity according to the calculated similarity. Analysis server communication unit for communication with the application server;
Upon receiving the recommendation product request message including the number of the target product and the recommended product from the application server through the analysis server communication unit, the erase target is deleted from the plurality of behavior logs including the user identifier and the purchased product corresponding to the user identifier. A preprocessing module that specifies and erases the specified erasing object from a plurality of behavior logs; And
And a similarity calculation module configured to calculate a similarity with the target product by using the plurality of behavior logs in which the object to be erased is erased. The method of claim 6,
The pretreatment module
Calculating an erase ratio, which is a ratio of an action log that can be erased according to the number of recommended products,
And an object to be erased according to the calculated erase ratio and the number of purchased goods in the behavior log. The method of claim 6,
The similarity calculation module
Denominator the action login union that includes at least one of the target product and another product,
By using the behavior login intersection that includes both the target product and the other product as a molecule
Apparatus for providing information about the product, characterized in that for calculating the similarity between the target product and the other product. The method of claim 6,
Deriving the product of the number of the recommended products in the order of high similarity according to the calculated similarity among the other products as recommended products,
And an information providing module for transmitting the derived recommendation goods to the application server through the analysis server communication unit.

Images