KR102538408B1 - Personalized recommendation system based on data analysis - Google Patents

Abstract

The present invention relates to a data analysis-based personalized recommendation system implemented to extract factor items for recommendation from various collected data, automatically identify the importance of the extracted items, construct a weighted recommendation model, and provide recommendation services. As such, a recommendation terminal unit requesting a recommendation of a customized service; and when a request for recommendation of a customized service is received from the recommendation terminal unit, a factor item for recommendation is extracted from the collected data, and the importance of the item is automatically identified according to the recommendation domain and weighted to create the customized service. It includes; a recommendation server unit providing the recommendation terminal unit.

Description

Personalized recommendation system based on data analysis}

The present invention relates to a data analysis-based personalized recommendation system, and more particularly, to a data analysis-based personalized recommendation system implemented to provide personalized recommendations by converging structured and unstructured data.

Recently, with the development of mobile communication technology for 3G or 4G, portable terminals such as smart phones that can freely download wireless Internet and application apps are becoming popular.

In particular, recent portable terminals can freely access cloud servers or content servers that hold various types of contents provided by content providers (e.g., communication service companies, terminal manufacturers) anytime and anywhere, as long as they pay a fee. You can download and install the application you want, and use it.

However, each company has numerous types of content in its cloud server or content server, but from the user's point of view, it is not easy to find the content application they are looking for in the cloud server or content server.

In addition, various personal information is being collected according to the increase in various smartphone-based services, but the model and method of recommending through the convergence of various data rather than individual data-based recommendations are not clear.

On the other hand, the above-mentioned background art is technical information that the inventor possessed for derivation of the present invention or acquired in the process of derivation of the present invention, and cannot necessarily be said to be known art disclosed to the general public prior to filing the present invention. .

Korean Patent Publication No. 10-2013-0033505 (published on April 4, 2013)

One aspect of the present invention extracts factor items for recommendation from various collected data, automatically identifies the importance of the extracted items, constructs a weighted recommendation model, and implements personalized recommendation based on data analysis to provide recommendation services. provide the system.

The technical problem of the present invention is not limited to the technical problem mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

A data analysis-based personalized recommendation system according to an embodiment of the present invention includes a recommendation terminal unit requesting recommendation of a customized service; and when a request for recommendation of a customized service is received from the recommendation terminal unit, a factor item for recommendation is extracted from the collected data, and the importance of the item is automatically identified according to the recommendation domain and weighted to create the customized service. It may include; a recommendation server unit that provides the recommendation terminal unit.

In one embodiment, the recommendation server unit, a data collection module for collecting data on-line through crawling, API linkage and batch loading; a weighting module for selecting important items, selecting weights for each item, and assigning weights for each data from the data collected by using the data collected by the data collection module as input information; a data fusion module for generating new feature information, fusion between feature items, and embedding a similarity vector after data fusion using the data weighted by the weighting module; a learning and classification module for performing deep learning learning of vector data and verification of a learning result model using the data fused in the data fusion module; and a recommendation module for providing personalized recommendations using the results of model testing, model distribution, and deep learning learning to the recommendation terminal unit using the data learned and classified in the learning and classification module.

In one embodiment, the data collection module may collect data related to the user's personal profile, search/inquiry history, and consumption history of the recommendation terminal through crawling, API linkage, and batch loading.

In one embodiment, the weighting module may include: an atypical refinement unit that performs language analysis (morpheme analysis), keyword extraction, and keyword statistics; a data bias removal unit that removes unnecessary vocabularies and corrects a collected data ratio; a feature selection unit that calculates a recommended domain mapping rate and performs sorting in a mapping rate order; and a weight correction unit that corrects the mapping rate ranking with feature weights of collected data.

In one embodiment, the data analysis-based personalized recommendation system according to another embodiment of the present invention may individually check the result of the customized service provided by the recommendation server through at least one output screen of different standards. It may further include a result monitoring device that receives results of the customized service from the recommendation server unit and individually outputs them through at least one output screen of different standards.

In one embodiment, the product monitoring device is formed in a “ㅁ” shape, along the outer circumferential surface of each side, along the outer circumferential surface of each side to form an opening in the front of the sliding rail is formed extending; Mounting units spaced apart from each other at regular intervals along the inner circumferential surface of the rail unit to support the rail unit; at least one slider part connected to the sliding rail and slidingly moving along the sliding rail; and at least one or more display units of different standards, each installed in the slider unit, that selects and outputs an output screen corresponding to its own standard among output screens of a result of the customized service provided by the recommendation server unit. can do.

In one embodiment, the slider unit may include a support block seated on the sliding rail; an upper end support unit connected to the upper side of the support block, seated on the upper side of the inner space of the sliding rail, and moving the support block while sliding in the forward and backward directions along the upper side of the inner space of the sliding rail; It is installed on the lower side of the support block while facing the upper support portion, is seated on the lower side of the inner space of the sliding rail, and moves the support block while sliding in the forward and backward directions along the lower side of the inner space of the sliding rail lower support; and a cradle supported by the support block, seated on an outer circumferential surface of the rail unit, holding the rear surface of the display unit, and moving the display unit while moving along with the support block as it moves along the sliding rail. can do.

In one embodiment, the support block may include a block body seated on the sliding rail to support the cradle; It penetrates and connects the front end of the block body in the vertical direction, and the upper end exposed to the upper side of the block body is rotatably installed below the front end of the upper support part to support the front end of the upper support part, and the block a shear support having a lower end exposed to the lower side of the body connected to an upper portion of the front end of the lower support unit to be rotatably connected to support the front end of the lower support unit; And it penetrates and connects the rear end of the block body in the vertical direction, and the upper end exposed to the upper side of the block body is rotatably installed below the rear end of the upper support part to support the rear end of the upper support part, A lower end exposed to the lower side of the block body is rotatably connected to an upper end of the rear end of the lower support part and a rear end support supporting the rear end of the lower support part.

In one embodiment, the shear support may include a vertical communication hole formed through the front end of the block body in a vertical direction; It is seated in the vertical communication hole, and the upper and lower ends are exposed to the upper and lower sides of the block body and are rotatably connected to the lower front end of the upper support part and the upper front end of the lower support part, respectively, so as to be rotatably connected to the lower front end of the upper support part and a vertical support frame supporting the gap between the front ends of the lower support portion; an inner housing formed at a middle portion of the vertical communication hole while forming an inner diameter larger than that of the vertical communication hole; a support ring formed in a circular ring shape corresponding to the shape of the cross section of the inner housing, installed at an intermediate portion of the vertical support frame and disposed at an intermediate portion of the inner housing; an upper support spring installed on an upper side of the inner housing while the vertical support frame is disposed along an inner side and supporting an upper side of the support ring; and a lower support spring installed on the lower side of the inner housing while the vertical support frame is disposed along the inner side and supporting the lower side of the support ring.

In one embodiment, the upper support unit is connected so that at least one support sphere for reducing frictional force by being in close contact with one side and the other side inner surface of the sliding rail is spaced apart at regular intervals along one side and the other side so as to be rotatable. can

In one embodiment, the cradle may be connected so that at least one support sphere for reducing frictional force by being in close contact with the outer circumferential surface of the rail unit is spaced apart at regular intervals along the rear surface and is rotatable.

According to one aspect of the present invention described above, a recommendation service may be provided by extracting factor items for recommendation from various collected data, automatically identifying the importance of the extracted items, constructing a recommendation model to which weights are assigned.

Effects of the present invention are not limited to the effects mentioned above, and various effects may be included within a range apparent to those skilled in the art from the contents to be described below.

1 is a block diagram showing an integrated marketing system in which conventional Internet-based discount integrated marketing, on-offline advertisement, and other affiliated stores and member management are combined.
FIG. 2 is a diagram showing a recommendation server unit of FIG. 1 .
FIG. 3 is a diagram showing the concept of the recommendation server unit of FIG. 2 .
4 is a diagram showing the weighting module of FIG. 2;
5 is a diagram showing a schematic configuration of a data analysis-based personalized recommendation system according to another embodiment of the present invention.
6 and 7 are views showing the result monitoring device of FIG. 5 .
8 and 9 are views showing the slider part of FIG. 7 .
10 is a view showing the support block of FIG. 9 .

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The detailed description of the present invention which follows refers to the accompanying drawings which illustrate, by way of illustration, specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable one skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention are different from each other but are not necessarily mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be implemented in another embodiment without departing from the spirit and scope of the invention in connection with one embodiment. Additionally, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the detailed description set forth below is not to be taken in a limiting sense, and the scope of the present invention, if properly described, is limited only by the appended claims, along with all equivalents as claimed by those claims. Like reference numbers in the drawings indicate the same or similar function throughout the various aspects.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the drawings.

1 is a diagram showing a schematic configuration of a data analysis-based personalized recommendation system according to an embodiment of the present invention.

Referring to FIG. 1 , a data analysis-based personalized recommendation system 10 according to an embodiment of the present invention includes a recommendation terminal unit 100 and a recommendation server unit 200.

The recommendation terminal unit 100 requests the recommendation server unit 200 to recommend customized services requested by the user.

Here, one or more recommended terminal units 100 may be configured, and are widely used by the general public, such as desktop computers (PCs), notebooks, smart phones, tablet PCs, and the like. It is a broad concept meaning various types of information communication devices and multimedia devices that support wired/wireless networks, such as mobile communication terminals.

And, the network N may include, for example, wireless communication, wired communication, optical ultrasound, or a combination thereof. Body Area Network (BAN), satellite communications, cellular communications, Bluetooth, Near Field Communication (NFC), Infrared Data Association standard (IrDA), Wireless Fidelity (WiFi), and Worldwide Interoperability for Microwave access (WiMAX) will be included in the communication path. Ethernet, digital subscriber line (DSL), fiber to the home (FTTH), and plain old telephone service (POTS) are examples of wired communication that can be included in a communication network. Also, a communications network can traverse multiple network topologies and distances. For example, a communications network may include a direct connection, a personal area network (PAN), a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), or any combination thereof. In addition, it may be performed through a low power wide area network (Low Power Wide Area Network) including LoRaWAN, NB-Fi, and RPMA. However, the description of the network N is not limited to the above communication network, and any latest data communication network may be applied.

When a recommendation request for a customized service is received from the recommendation terminal unit 100, the recommendation server unit 200 extracts factor items for recommendation from the collected data, automatically identifies the importance of the items according to the recommendation domain, and then weights the items. The customized service created by giving is provided to the recommendation terminal 100 .

The recommendation server unit 200 having the configuration described above first 1) selects important feature terms for each recommendation domain, selects the importance of terms for each recommendation area after learning, and 2) in the case of financial product recommendation, product characteristics, interest rates, and interest rates , constraints, etc. are selected, and 3) in the case of digital product recommendation, "weight learning" can be performed by selecting terms such as screen size, weight, memory, speed, and price as important weights.

Next, “recommendation learning” may be performed through learning such as category classification for recommendation (eg, personalized news selection, product list, product list, etc.).

Next, 1) Select important items from the user information (consumption history, selected content, etc.) collected based on the list of weighted terms for each recommendation category and assign weights, 2) Vectorize the weighted user history information and use it in the recommendation system. It is possible to perform "selection of user weights and vectorization" through configuration so as to be able to classify.

Finally, it is possible to perform "recommendation of products, services, and other services" by classifying the vectorized user information into a learned recommendation model and providing a user-customized recommendation service.

The data analysis-based personalized recommendation system 10 according to an embodiment of the present invention having the configuration described above extracts factor items for recommendation from various collected data, automatically identifies the importance of the extracted items, and sets a weight It is possible to configure the given recommendation model and provide recommendation service.

FIG. 2 is a diagram showing a recommendation server unit of FIG. 1 .

Referring to FIG. 2 , the recommendation server unit 200 includes a data collection module 210, a weighting module 220, a data fusion module 230, a learning and classification module 240, and a recommendation module 250. do.

The data collection module 210 collects online data through crawling, API linkage, and batch loading.

In one embodiment, the data collection module 210 may collect data related to the user's personal profile, search/inquiry history, and consumption history of the recommendation terminal unit 100 through crawling, API linkage, and batch loading. .

The weighting module 220 uses the data collected in the data collection module 210 as input information and selects important items from the collected data using automatic classification, selects weights for each item, and assigns weights for each data. .

The data fusion module 230 performs data fusion using data weighted by the weighting module 220 and then generates new feature information, fusion between feature items, and embedding similarity vectors.

That is, the data convergence module 230 1) "selects important features" through selection of important features (top N) from the feature keyword list reflecting weights, 2) configures the selected important feature keyword groups and prepares for vector embedding. “Feature fusion” and 3) “vector embedding” may be performed through vector embedding based on a pre-learning model of the domain.

The learning and classification module 240 performs deep learning learning of vector data and verification of a learning result model using the data fused in the data fusion module 230 .

In one embodiment, the learning and classification module 240, 1) "recommendation algorithm" through user feature information mapping and recommended content (product) recommendation, 2) domain keyword list and recommendation categories through domain feature learning management "Model learning" through learning, and 3) "model verification" through learning model verification can be performed.

The recommendation module 250 uses the data learned and classified in the learning and classification module 240 to provide model testing, model distribution, and personalized recommendation using deep learning learning results to the recommendation terminal 100. .

In one embodiment, the recommendation module 250 may perform 1) "model test" through recommendation performance check/supplementation and distribution version confirmation, and 2) "model distribution" through model recommendation system distribution.

4 is a diagram showing the weighting module of FIG. 2;

Referring to FIG. 4 , the weighting module 220 includes an atypical refinement unit 221 , a data bias removal unit 222 , a feature selection unit 223 and a weight correction unit 224 .

The atypical refinement unit 221 performs language analysis (morpheme analysis), keyword extraction, and keyword statistics.

The data bias removal unit 222 removes unnecessary vocabularies and corrects the collected data ratio.

The feature selector 223 calculates a recommended domain mapping rate and performs sorting in order of mapping rates.

The weight correction unit 224 corrects the mapping rate ranking with feature weights of collected data.

5 is a diagram showing a schematic configuration of a data analysis-based personalized recommendation system according to another embodiment of the present invention.

Referring to FIG. 5 , a data analysis-based personalized recommendation system 20 according to another embodiment of the present invention includes a recommendation terminal unit 100, a recommendation server unit 200, and a result monitoring device 300.

Here, since the recommendation terminal unit 100 and the recommendation server unit 200 are the same as the components of FIG. 1 , descriptions thereof will be omitted to avoid duplication of description.

The result monitoring device 300 monitors the result of the customized service from the recommendation server unit 200 so that the result of the customized service provided by the recommendation server unit 200 can be individually checked through at least one output screen of different standards. It is received and individually output through at least one or more output screens S-1 to S-N of different standards (that is, each screen of the display unit 340 to be described later).

In the data analysis-based personalized recommendation system 20 according to another embodiment of the present invention having the configuration described above, the output screen (S- 1 to S-N) (that is, each screen of the display unit 340 to be described later) to be individually output through the user or the administrator of the recommendation server 200 to confirm, the quality of the customized service based on data analysis according to the present invention Improvement and satisfaction can be promoted.

6 and 7 are views showing the result monitoring device of FIG. 5 .

6 and 7, the result monitoring device 300 includes a rail unit 310, a holder unit 320, at least one slider unit 330, and at least one display unit 340 of different standards. includes

The rail unit 310 is formed in a “ㅁ” shape, and along the outer circumferential surface of each side, a sliding rail 311 extending forward to form an opening is formed.

The mounting portion 320 is installed spaced apart at regular intervals along the inner circumferential surface of the rail portion 310 to mount the rail portion 310 .

At least one slider part 330 is installed connected to the sliding rail 311 and slides along the sliding rail 311 .

At least one or more display units 340 of different standards are respectively installed in the slider unit 330 and output screens corresponding to their own standards among the output screens of the result of the customized service provided by the recommendation server unit 200. Select and output.

The result monitoring device 300 having the configuration as described above displays the result of the customized service generated by the recommendation server 200 to one or more different standard output screens S-1 to S-N (ie, at least one or more different output screens S-1 to S-N). It is individually output through the screen of the display unit 340 of a different standard) to be confirmed through the user or the administrator of the recommendation server 200, thereby improving the quality and satisfaction of the customized service based on data analysis according to the present invention. can

8 and 9 are views showing the slider part of FIG. 7 .

Referring to FIGS. 8 and 9 , the slider part 330 includes a support block 400 , an upper support part 332 , a lower support part 333 and a cradle 334 .

The support block 400 is seated on the sliding rail 311 .

In one embodiment, the support block 400 may include a block body 410, a front support 420 and a rear support 430.

The block body 410 is seated on the sliding rail 311 to support the cradle 334 .

The shear support 420 penetrates and connects the front end of the block body 410 in the vertical direction, and the upper end exposed to the upper side of the block body 410 is rotatably connected to the lower front end of the upper support 332. It is installed to support the front end of the upper support part 332, and the lower end exposed to the lower side of the block body 410 is rotatably connected to the upper part of the front end of the lower support part 333 to support the front end of the lower support part 333. .

The rear support 430 penetrates and connects the rear end of the block body 410 in the vertical direction, and the upper end exposed upward of the block body 410 is rotatably connected to the lower rear end of the upper support 332. It is installed to support the rear end of the upper support part 332, and the lower end exposed to the lower side of the block body 410 is rotatably connected to the upper part of the rear end of the lower support part 333 to support the rear end of the lower support part 333. .

In one embodiment, the shear support 420 includes a vertical through hole 421, a vertical support frame 422, an inner housing 423, a support ring 424, an upper support spring 425, and a lower support spring 426 ) may be included.

The vertical communication hole 421 is formed through the front end of the block body 410 in the vertical direction.

The vertical support frame 422 is seated in the vertical communication hole 421, and the upper and lower ends are exposed to the upper and lower sides of the block body 410, the front end of the upper support part 332, the lower part and the front end of the lower support part 333. It is connected to the upper part so as to be rotatable, and supports the gap between the lower front end of the upper support part 332 and the front end of the lower support part 333.

The inner housing 423 is formed at the middle of the vertical communication hole 421 while forming an inner diameter larger than that of the vertical communication hole 421 .

The support ring 424 is formed in a circular ring shape corresponding to the shape of the cross section of the inner housing 423, and is installed at the middle of the vertical support frame 422 and disposed at the middle of the inner housing 423.

The upper support spring 425 is installed on the upper side of the inner housing 423 while the vertical support frame 422 is disposed along the inner side, and supports the upper side of the support ring 424 .

The lower support spring 426 is installed on the lower side of the inner housing 423 while the vertical support frame 422 is disposed along the inner side, and supports the lower side of the support ring 424 .

The upper support part 332 is connected to the upper side of the support block 400 and is seated on the upper side of the inner space of the sliding rail 311, while sliding in the forward and backward direction along the upper side of the inner space of the sliding rail 311. The support block 400 is moved.

In one embodiment, the upper support part 332 is spaced apart at regular intervals along one side and the other side of the support sphere B1 for reducing frictional force by being in close contact with the inner surface of one side and the other side of the sliding rail 311, and at least one It can be connected and installed so that it can rotate more than once.

The lower support part 333 is connected to the lower side of the support block 400 while facing the upper support part 332 and is seated on the lower side of the inner space of the sliding rail 311, and the lower side of the inner space of the sliding rail 311 It moves the support block 400 while sliding in the forward and backward directions along the .

The cradle 334 is supported by the support block 400, is seated on the outer circumferential surface of the rail unit 310 and supports the rear surface of the display unit 340, and the support block 400 along the sliding rail 311. As it moves, it moves the display unit 340 while moving together.

In one embodiment, the holder 334 is connected so that at least one support sphere B2 for reducing frictional force by being in close contact with the outer circumferential surface of the rail unit 310 is spaced apart at regular intervals along the rear surface and is rotatable. can

The slider unit 330 having the configuration described above not only can stably hold the display unit 340, but also allows the user to check the display unit 340 by moving the display unit 340. In addition to improving convenience, by buffering vibration or shock that may occur during the movement of the display unit 340, effects such as improved durability and reduced noise of the device can be expected.

The data analysis-based personalized recommendation system having the configuration described above may execute or manufacture various software based on an operating system (OS), that is, a system. The operating system is a system program for enabling software to use the hardware of the device, and is a mobile computer operating system such as Android OS, iOS, Windows mobile OS, Bada OS, Symbian OS, Blackberry OS, and Windows-based, Linux-based, Unix-based, It can include all computer operating systems such as MAC, AIX, and HP-UX.

The term '~unit' used in the above embodiments means software or a hardware component such as a field programmable gate array (FPGA) or ASIC, and '~unit' performs certain roles. However, '~ part' is not limited to software or hardware. '~bu' may be configured to be in an addressable storage medium and may be configured to reproduce one or more processors. Therefore, as an example, '~unit' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program patent code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.

Functions provided within components and '~units' may be combined into smaller numbers of components and '~units' or separated from additional components and '~units'.

In addition, components and '~units' may be implemented to play one or more CPUs in a device or a secure multimedia card.

The data analysis-based personalized recommendation system may also be implemented in the form of a computer-readable medium storing instructions and data executable by a computer. In this case, instructions and data may be stored in the form of program codes, and when executed by a processor, a predetermined program module may be generated to perform a predetermined operation. Also, computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, a computer-readable medium may be a computer recording medium, which is a volatile and non-volatile memory implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data. It can include both volatile, removable and non-removable media. For example, the computer recording medium may be a magnetic storage medium such as HDD and SSD, an optical recording medium such as CD, DVD, and Blu-ray disc, or a memory included in a server accessible through a network.

Also, the data analysis-based personalized recommendation system may be implemented as a computer program (or computer program product) including instructions executable by a computer. A computer program includes programmable machine instructions processed by a processor and may be implemented in a high-level programming language, object-oriented programming language, assembly language, or machine language. . Also, the computer program may be recorded on a tangible computer-readable recording medium (eg, a memory, a hard disk, a magnetic/optical medium, or a solid-state drive (SSD)).

Accordingly, the data analysis-based personalized recommendation system may be implemented by executing the above-described computer program by a computing device. A computing device may include at least some of a processor, a memory, a storage device, a high-speed interface connected to the memory and a high-speed expansion port, and a low-speed interface connected to a low-speed bus and a storage device. Each of these components are connected to each other using various buses and may be mounted on a common motherboard or mounted in any other suitable manner.

Here, the processor may process commands within the computing device, for example, to display graphic information for providing a GUI (Graphic User Interface) on an external input/output device, such as a display connected to a high-speed interface. Examples include instructions stored in memory or storage devices. As another example, multiple processors and/or multiple buses may be used along with multiple memories and memory types as appropriate. Also, the processor may be implemented as a chipset comprising chips including a plurality of independent analog and/or digital processors.

Memory also stores information within the computing device. In one example, the memory may consist of a volatile memory unit or a collection thereof. As another example, the memory may be composed of a non-volatile memory unit or a collection thereof. Memory may also be another form of computer readable medium, such as, for example, a magnetic or optical disk.

Also, the storage device may provide a large amount of storage space to the computing device. A storage device may be a computer-readable medium or a component that includes such a medium, and may include, for example, devices in a storage area network (SAN) or other components, such as a floppy disk device, a hard disk device, an optical disk device, or a tape device, flash memory, or other semiconductor memory device or device array of the like.

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

The scope to be protected through this specification is indicated by the following claims rather than the detailed description above, and should be construed to include all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof. .

10, 20: Personalized recommendation system based on data analysis
100: request terminal
200: recommendation server unit
300: result monitoring device

Claims (2)

Recommendation terminal unit for requesting recommendation of customized services; and
When a request for recommendation of a customized service is received from the recommendation terminal unit, a factor item for recommendation is extracted from the collected data, and the importance of the item is automatically identified according to the recommendation domain and weighted. A recommendation server unit provided to the terminal unit; includes,
In order to individually check the result of the customized service provided by the recommendation server unit through at least one output screen of different standards, the result of the customized service is received from the recommendation server unit and output screens of at least one different standard are displayed. It further includes; a result monitoring device that individually outputs through
The result monitoring device,
A rail portion formed in a “ㅁ” shape and extending along an outer circumferential surface of each side and extending a sliding rail forming an opening in the forward direction;
Mounting units spaced apart from each other at regular intervals along the inner circumferential surface of the rail unit to support the rail unit;
at least one slider part connected to the sliding rail and slidingly moving along the sliding rail; and
At least one or more display units of different standards installed in the slider unit and selecting and outputting an output screen corresponding to its own standard from among output screens of a result of a customized service provided by the recommendation server unit; ,
The slider part,
a support block seated on the sliding rail;
an upper end support unit connected to the upper side of the support block, seated on the upper side of the inner space of the sliding rail, and moving the support block while sliding in the forward and backward directions along the upper side of the inner space of the sliding rail;
It is installed on the lower side of the support block while facing the upper support portion, is seated on the lower side of the inner space of the sliding rail, and moves the support block while sliding in the forward and backward directions along the lower side of the inner space of the sliding rail lower support; and
A cradle supported by the support block, seated on an outer circumferential surface of the rail unit, holding the rear surface of the display unit, and moving the display unit while moving together as the support block moves along the sliding rail; ,
The support block is
a block body seated on the sliding rail to support the cradle;
It penetrates and connects the front end of the block body in the vertical direction, and the upper end exposed to the upper side of the block body is rotatably installed below the front end of the upper support part to support the front end of the upper support part, and the block a shear support having a lower end exposed to the lower side of the body connected to an upper portion of the front end of the lower support unit to be rotatably connected to support the front end of the lower support unit; and
It penetrates and connects the rear end of the block body in the vertical direction, and the upper end exposed to the upper side of the block body is rotatably installed below the rear end of the upper support part to support the rear end of the upper support part, and the block A rear end support for supporting the rear end of the lower support part by being rotatably installed at the lower end exposed to the lower side of the body to the upper end of the rear end of the lower support part,
The shear support,
a vertical communication hole formed through the front end of the block body in a vertical direction;
It is seated in the vertical communication hole, and the upper and lower ends are exposed to the upper and lower sides of the block body and are rotatably connected to the lower front end of the upper support part and the upper front end of the lower support part, respectively, so as to be rotatably connected to the lower front end of the upper support part and a vertical support frame supporting the gap between the front ends of the lower support portion;
an inner housing formed at a middle portion of the vertical communication hole while forming an inner diameter larger than that of the vertical communication hole;
a support ring formed in a circular ring shape corresponding to the shape of the cross section of the inner housing, installed at an intermediate portion of the vertical support frame and disposed at an intermediate portion of the inner housing;
an upper support spring installed on an upper side of the inner housing while the vertical support frame is disposed along an inner side and supporting an upper side of the support ring; and
A lower support spring installed on the lower side of the inner housing while the vertical support frame is disposed along the inner side and supporting the lower side of the support ring; includes,
The upper support part,
At least one support sphere for reducing frictional force by being in close contact with the inner surface of one side and the other side of the sliding rail is spaced apart at regular intervals along one side and the other side and connected so as to be rotatable,
the cradle,
A data analysis-based personalized recommendation system in which support spheres for reducing frictional force by being in close contact with the outer circumferential surface of the rail unit are spaced apart at regular intervals along the rear surface and connected to one or more rotatably. delete

Images