KR102352994B1 - User interests duration learining method of content recommendation system and apparatus therefore - Google Patents

Abstract

Disclosed are a method and apparatus for learning a user interest validity period of a content recommendation system. A user interest validity period learning method according to an embodiment of the present invention is a method for learning a user interest validity period of a content recommendation system, comprising: a time axis for inputting a user interest and an effective period of the interest in the content recommendation system providing a two-dimensional interface; disposing an interest box in which an effective period for each of the user's interests is set on the two-dimensional interface based on the user's input; and learning an effective period for recommending content for each of the user's interests based on the interest corresponding to the arranged interest box and the validity period.

Description

User interest validity period learning method and device for content recommendation system {USER INTERESTS DURATION LEARINING METHOD OF CONTENT RECOMMENDATION SYSTEM AND APPARATUS THEREFORE}

The present invention relates to a user-customized content recommendation technology, and more particularly, a method for a content recommendation system to learn a period (interest validity period) in which an interest input by a user is effective as a basis for content recommendation for a user, and a method thereof It's about the device.

Today's content recommendation system actively learns the user's interests in order to recommend content such as movies, videos, music, blogs, news, and restaurants to users. For user interest learning, the content recommendation system provides the user with a list of interests as a view, and allows them to check/follow/subscribe their interests. In addition, the user is continuously provided with the opportunity to select such interests.

Most existing content recommendation systems consider the interests input by the user to be valid indefinitely as a basis for customized recommendations, and provide recommendations based on this. However, since the user's actual interest in most interests changes according to the passage of time and a change in user context, using the interest input by the user as the basis for indefinite recommendations causes a decrease in the quality of content recommendations. For example, when content is continuously recommended based on interests entered by short-term interest (eg, preparation for civil service exam, etc.), it is highly likely that a decrease in user satisfaction with the system will occur (eg, civil service exam preparation). After this is over, the video recommendation for civil service exam lectures to users).

Embodiments of the present invention provide a method and apparatus for a content recommendation system to learn a period (interest validity period) during which an interest input by a user is effective as a basis for content recommendation for the user.

Embodiments of the present invention provide a method and apparatus for providing a content recommendation with high satisfaction by using only the interest guaranteed to be valid at a specific point in time, by allowing the content recommendation system to learn the validity period of the interest.

A user interest validity period learning method according to an embodiment of the present invention is a method for learning a user interest validity period of a content recommendation system, comprising: a time axis for inputting a user interest and an effective period of the interest in the content recommendation system providing a two-dimensional interface; disposing an interest box in which an effective period for each of the user's interests is set on the two-dimensional interface based on the user's input; and learning an effective period for recommending content for each of the user's interests based on the interest corresponding to the arranged interest box and the validity period.

The disposing of the interest box may include arranging interest boxes of different colors for each of the user's interests on the two-dimensional interface, and adjusting the length of the horizontal axis of the interest box to adjust the validity period. have.

In the disposing of the interest box, the interest box may be moved horizontally and vertically based on the user's input, and the interest box may be additionally placed by copying the interest box according to selection of a button preset for the interest box. .

The disposing of the interest box may include recommending a validity period for each of the user's interests in consideration of the validity periods of other users for each of the interests, and the user based on the validity period for each of the recommended interests. The validity period for each of the interests may be set by input of .

Furthermore, the method for learning a user interest validity period according to an embodiment of the present invention may further include recommending content for an interest whose validity is guaranteed at a corresponding point in time based on the learned validity period.

A user interest validity period learning apparatus according to an embodiment of the present invention is a user interest validity period learning apparatus of a content recommendation system, comprising: a time axis for inputting a user's interest and an effective period of the interest in the content recommendation system a provider providing a two-dimensional interface; a setting unit for disposing an interest box in which an effective period for each of the user's interests is set on the two-dimensional interface based on the user's input; and a learning unit configured to learn an effective period for recommending content for each of the user's interests based on the interest corresponding to the interest box and the validity period.

The setting unit may arrange interest boxes of different colors on the two-dimensional interface for each of the user's interests, and adjust the validity period by adjusting a length of a horizontal axis of the interest boxes.

The setting unit may move the interest box horizontally and vertically based on the user's input, and may copy and additionally arrange the interest box according to selection of a button preset for the interest box.

The setting unit recommends a validity period for each of the user's interests in consideration of the validity periods of other users for each of the interests, A validity period may be established for each of the interests.

Furthermore, the apparatus for learning the validity period of user interests according to an embodiment of the present invention may further include a recommendation unit for recommending content for interests whose validity is guaranteed at a corresponding point in time based on the learned validity period.

According to an embodiment of the present invention, the content recommendation system learns the validity period of the interest, and can provide content recommendation with high satisfaction by using only the interest whose validity is guaranteed at a specific point in time.

According to an embodiment of the present invention, the user's interest validity period learning interface is mounted in the content recommendation system, so that (1) the user's degree of freedom in system manipulation and the need for continuous interest correction are reduced, and (2) the accuracy of system learning and content are increased. It has the effect of increasing the quality of recommendations.

In other words, according to the present invention, since the user can selectively input the name of interest and the validity period of the interest, the user can participate in the system personalization process more proactively, and since information on the validity of the interest can be input in advance, the user can continuously improve the interest The need to monitor and correct is reduced. In addition, according to the present invention, since the content recommendation system learns the interest validity period to accurately identify the topic and area that the user is actually interested in at a specific point in time, as a result, it is possible to provide a content recommendation with high satisfaction to the user.

1 is a flowchart illustrating a method for learning a user interest validity period according to an embodiment of the present invention.
2 shows an exemplary diagram of an interface provided by the present invention.
3 is a diagram illustrating an example of a service that provides a customized text based on a user's interest input.
4 is a diagram illustrating an example of a service that provides customized news based on a user's interest input.
5 is a diagram showing the configuration of a user interest validity period learning apparatus according to an embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be embodied in various different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the art to which the present invention pertains It is provided to fully inform those who have the scope of the invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for the purpose of describing the embodiments, and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, "comprises" and/or "comprising" refers to the presence of one or more other components, steps, operations and/or elements mentioned. or addition is not excluded.

Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used with the meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the accompanying drawings. The same reference numerals are used for the same components in the drawings, and repeated descriptions of the same components are omitted.

Two problems when the content recommendation system does not learn the validity period of user interests are as follows.

First, it is necessary to prevent users from freely operating the system and to make continuous efforts to correct unavoidable concerns. Even if the user is aware of the validity period for each interest, he or she may feel dissatisfied because there is no channel to input it into the system. In addition, in order to prevent recommendations based on interests that have lost their validity, it is necessary to continuously revise the interest list.

For example, since the user has to start studying for the exam from next week, he does not want to be recommended for 'entertainment gossip'-related content from next week, and wants to be recommended for 'entertainment gossip'-related content again after the test is over. (1) The user It is unfortunate because there is no way to inform the system of the facts in advance, and (2) it is inconvenient to have to wait until next week to delete the interest in 'entertainment gossip', and to add the interest to 'entertainment gossip' again after the test is over .

Second, there are problems with the low learning accuracy and low content recommendation quality of the content recommendation system. Since the system learns the user's interest without additional conditional information, it must understand the user's interest with low accuracy, which inevitably has to provide low-level customized content.

For example, the content recommendation system cannot understand, without the user's input, in what context it is valid to use this as a basis for recommendation with respect to the interest of 'Jeju Island restaurant' input by the user. For example, I do not know whether I need information on restaurants because I am currently traveling on Jeju Island, whether I am preparing for a winter trip to Jeju Island, or whether I am interested in Jeju Island food and want to periodically obtain information about restaurants in Jeju Island. For this reason, the content recommendation system has no choice but to recommend content without guaranteeing high user satisfaction.

According to the embodiments of the present invention, the content recommendation system learns the validity period of the interest, and provides content recommendation with high satisfaction using only the interest whose validity is guaranteed at a specific point in time.

At this time, in the present invention, by mounting the user interest validity period learning interface in the content recommendation system, it is possible to increase the user's degree of freedom in operating the system, reduce the need for continuous interest correction, increase the accuracy of system learning, and improve the quality of content recommendation.

That is, the present invention provides a 2D interface that allows a user to input a user's specific interest in which time period is valid, and by arranging the interest box on the horizontal axis-timeline, it can be determined that the interest is valid in the corresponding time period. can express

According to the present invention, since the user can freely adjust the position and the horizontal length of the interest, information on the validity period of the interest, that is, from when to when, can be input into the system.

In this case, the horizontal axis may be a time axis, and the time frame may be changed by enlarging or reducing the horizontal axis. For example, according to the present invention, the horizontal axis can be enlarged or reduced to change to a unit of time, unit of time, unit of week, unit of month, or the like.

Also, in the present invention, all interests input by the user may be vertically arranged on the time frame as boxes of different colors.

At this time, the basic setting (default) horizontal length of the interest input by the user may be a preset period, for example, 14 days, and the user screens the left and right ends of the box corresponding to the interest placed on the time frame. The validity period of the interest can be shortened or extended by freely pulling it using a device such as a touch or a mouse.

Furthermore, according to the present invention, the interest box can be freely moved left and right based on the user's input and placed, and when a specific button placed next to the interest box, for example, the (+) button is pressed, the same interest box is copied and added can be

The present invention will be described with reference to FIGS. 1 to 5 as follows.

1 is a flowchart illustrating a method for learning a user interest validity period according to an embodiment of the present invention, and is a flowchart illustrating a method for learning a user interest validity period in a content recommendation system.

Referring to FIG. 1 , the method according to an embodiment of the present invention provides a two-dimensional (2D) interface including a time axis for inputting a user's interest and an effective period of interest in the content recommendation system ( S110 ).

When the 2D interface is provided by the step S110, an interest box in which the validity period for each of the user's interests is set is arranged on the 2D interface based on the user's input (S120).

For example, steps S110 and S120 provide a 2D interface for setting an interest and an effective period for each interest, as shown in FIG. 2 , and the validity period for each of the user interests is set on the provided 2D interface You can place interest boxes. That is, if the user is interested in "Jeju Island", "Mother's Day", "Seoul Jazz Festival", and "Coronavirus", an interest box for "Jeju Island", an interest box for "Mother's Day", and "Seoul Jazz Festival" A box of interest for and a box of interest for “coronavirus” can be placed on the 2D interface.

In this case, in step S120 , interest boxes of different colors are arranged on the 2D interface for each of the user's interests, and the validity period may be adjusted by adjusting the length of the horizontal axis of the interest boxes. For example, as shown in FIG. 2 , the validity period of the interest box can be reduced by dragging the right side of the interest box of “Mother’s Day” to the left, and the validity period can also be changed by moving the interest box of “Seoul Jazz Festival” have. Of course, it is not limited to resetting the validity period by adjusting and moving the length of the interest box, but by selecting a function key or shortcut key to set the validity period after selecting the interest box, an input window for entering the validity period is opened. You can also set or change the validity period via

In addition, each of the interest boxes may be arranged in the vertical direction of the 2D interface, and may be moved horizontally and vertically on the 2D interface based on a user's input, and each interest box is copied and added by a user selection of a preset button. may be placed. For example, as shown in Figure 2, by copying the interest box of "Coronavirus" and moving the interest box of the copied "Coronavirus" to the right, the validity period for the interest box of the copied "Coronavirus" , which allows you to set "coronavirus" as a concern in the first and second validity periods.

Furthermore, in step S120, in the case of an interest in which the user may have difficulty in predicting and inputting the validity period, the validity period for each of the user's interests is recommended in consideration of the validity period of other users for the interest, and the validity period is applied to the interest. The validity period of the interest may be set by a user's input based on the recommended validity period.

If, for each of the user's interests, an interest box with an expiration period is arranged on the 2D interface in step S120, content for each of the user's interests is recommended based on the interest corresponding to the placed interest box and the validity period It learns the effective period for doing (S130).

Then, when the validity period for each of the user's interests is learned in step S130, the content for the interest guaranteed to be valid at the time based on the learned validity period is recommended and provided to the user (S140).

In this method of the present invention, when the user is highly accustomed to using the existing content recommendation system, input of the validity period of interest may feel unfamiliar or unnecessary. It is also possible to determine whether to apply the method of the present invention according to the user's selection through the addition of the "do not use" function.

In addition, in the method of the present invention, when a user manages multiple interests and their validity periods on one screen, it may feel difficult to operate the interface, so "free screen enlargement/reduction function" and "multiple It is also possible to solve the difficulty of operating the interface by adding the function of "selection of overlapping interests."

In addition, in the case of a specific interest, the method of the present invention additionally provides a function of providing statistical data on the validity period set by other users when inputting the interest, since the user may have difficulties in predicting and inputting the validity period in the case of a particular interest, can help users set validity periods for specific interests. For example, based on the statistics that most users set carnation interest keywords by May 8, you may provide a guide to users who are thinking about setting the validity period of carnation interests, that it is common to set them by May 8. have.

Although the present invention is applicable to various content service domains, it may be most effective for application to information-oriented content domains. For example, the present invention can be applied to news content, information posting content, and the like.

For example, user interests related to entertainment-oriented content domains such as music, movies, and shopping, for example, user interests related to information-oriented content domains such as news and postings, relative to preferred genres, preferred artists, and purchasing propensity, for example, members of the National Assembly Elections, Mother's Day, and Christmas gifts are more likely to change effectiveness over time. That is, the information-centric content domain may be a domain in which the necessity and importance of inputting the validity period of interest is more prominent.

As another example, the degree of improvement in user satisfaction due to the introduction of the interest validity period learning technology may be greater in the information-oriented content recommendation domain such as news and postings than in the entertainment-oriented content domain such as music, movie, and shopping. For example, the importance of not recommending content related to a musician or movie genre that you were interested in but lost interest in now vs. the importance of not recommending local information or news that you were interested in in the past but are not currently interested in

In view of the technological development capabilities of current IT companies, the present invention has high market introduction and commercialization potential, and is applicable to content recommendation services in various domains, but when applied to information-oriented content recommendation service development, the greatest User experience improvements may be made.

As a representative example of the information-oriented content recommendation service, as shown in FIG. 3, 'Today's Reading Service' provided by Naver through a portal and 'Google News Service' provided by Google as shown in FIG. can be heard Of course, in addition to Naver or Google, the present invention can be applied to various services that provide an online service that individually recommends content such as news, posts, blogs, encyclopedia information, and informational images by reflecting users' interests.

As described above, in the method according to the embodiment of the present invention, the content recommendation system learns the validity period of the interest, and can provide content recommendation with high satisfaction by using only the interest whose validity is guaranteed at a specific point in time.

In addition, in the method according to an embodiment of the present invention, the user interest validity period learning interface is mounted in the content recommendation system, so that (1) the user's degree of freedom in system manipulation and the need for continuous interest correction are reduced, and (2) the accuracy of system learning There is a synergistic effect and the quality of content recommendation is increased.

That is, in the method according to the embodiment of the present invention, since the user can selectively input the interest name and the validity period of the interest, it is possible to participate in the system personalization process more proactively, and to input information on the validity of the interest in advance. This reduces the need to constantly monitor and correct concerns. In addition, in the method according to an embodiment of the present invention, the content recommendation system learns the interest validity period, and as a result, the content recommendation system with high satisfaction is provided to the user because the subject and area that the user is actually interested in can be accurately identified at a specific point in time. can provide

5 shows a configuration of an apparatus for learning the validity period of user interest according to an embodiment of the present invention, and shows a conceptual configuration of an apparatus for performing the method of FIGS. 1 to 4 .

Referring to FIG. 5 , an apparatus 500 according to an embodiment of the present invention includes a providing unit 510 , a setting unit 520 , a learning unit 530 , and a recommendation unit 540 .

The providing unit 510 provides a 2D interface including a time axis for inputting the user's interest and the validity period of the interest.

The setting unit 520 arranges an interest box in which an effective period for each of the user's interests is set on the 2D interface based on the user's input.

In this case, the setting unit 520 may arrange interest boxes of different colors for each of the user's interests on the 2D interface, and adjust the validity period by adjusting the length of the horizontal axis of the interest boxes. Each of the interest boxes can be arranged in the vertical direction of the 2D interface, and can be moved horizontally and vertically on the 2D interface based on a user's input, and each interest box can be copied and additionally placed by a user selection of a preset button. may be

Furthermore, in the case of an interest in which the user may have difficulty in predicting and inputting the validity period, the setting unit 520 recommends an validity period for each of the user's interests in consideration of the validity period of other users for the interest, The validity period of the interest may be set by a user input based on the validity period recommended for the interest.

The learning unit 530 is configured to, for each of the user's interests, when an interest box with a set validity period is disposed on the 2D interface, content for each of the user's interests based on the interest corresponding to the placed interest box and the validity period Learn the validity period for recommending

When the validity period for each of the user's interests is learned, the recommendation unit 540 recommends and provides the content for the interest whose validity is guaranteed at the corresponding point in time based on the learned validity period.

Although the description of the device of FIG. 5 is omitted, the device of FIG. 5 may include all of the contents described with reference to FIGS. 1 to 4 , which is apparent to those skilled in the art of the present invention. .

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a designable logic. One or more general purpose computers or special purpose computers, such as a field programmable gate array (FPGA), programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. It can be implemented using a computer. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that a processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that including For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

Software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be placed on any type of machine, component, physical device, virtual equipment, computer storage medium or device in order to be interpreted by or provide instructions or data to the processing device. It can be embody. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded in the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible by those skilled in the art from the above description. For example, the described techniques are performed in an order different from the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the following claims.

Claims (10)

In the user interest validity period learning method of the content recommendation system,
providing a two-dimensional interface including a time axis for inputting a user's interest and an effective period of the interest in the content recommendation system;
disposing an interest box in which an effective period for each of the user's interests is set on the two-dimensional interface based on the user's input; and
learning an effective period for recommending content for each of the user's interests based on the interest and the validity period corresponding to the arranged interest box;
including,
Recommending to the user the content for the interest whose validity is guaranteed at the time based on the learned validity period
further comprising,
The step of recommending the content for the interest with guaranteed validity to the user,
When the user uses the Internet site, providing an online service that recommends content for interests that are guaranteed to be valid at that point in time;
Determining whether to apply the content recommendation system according to the user's selection, and determining whether to use the user's interest and validity period input
User interest validity period learning method, characterized in that.
According to claim 1,
The step of placing the interest box is
For each of the interests of the user, interest boxes of different colors are arranged on the two-dimensional interface, and the validity period can be adjusted by adjusting the length of the horizontal axis of the interest boxes. Way.
According to claim 1,
The step of placing the interest box is
The user interest validity period learning method, characterized in that the interest box can be moved horizontally and vertically based on the user's input, and the interest box can be copied and additionally placed according to a selection of a button preset for the interest box .
According to claim 1,
The step of placing the interest box is
Recommend an effective period for each of the user's interests in consideration of the validity period of other users for each of the interests, and each of the interests by the user's input based on the validity period for each of the recommended interests User interest validity period learning method, characterized in that the validity period is set for.
delete In the user interest validity period learning apparatus of the content recommendation system,
a providing unit providing a two-dimensional interface including a time axis for inputting a user's interest and an effective period of the interest in the content recommendation system;
a setting unit arranging an interest box in which an effective period for each of the user's interests is set on the two-dimensional interface based on the user's input; and
A learning unit that learns an effective period for recommending content for each of the user's interests based on the interest and the validity period corresponding to the arranged interest box
including,
Based on the learned validity period, a recommendation unit that recommends to the user the content for the interest that is guaranteed to be valid at that point in time.
further comprising,
The recommendation is
When the user uses the Internet site, providing an online service that recommends content for interests that are guaranteed to be valid at that point in time;
Determining whether to apply the content recommendation system according to the user's selection, and determining whether to use the user's interest and validity period input
User interest validity period learning device, characterized in that.
7. The method of claim 6,
the setting unit
For each of the interests of the user, interest boxes of different colors are arranged on the two-dimensional interface, and the validity period can be adjusted by adjusting the length of the horizontal axis of the interest boxes. Device.
7. The method of claim 6,
the setting unit
User interest validity period learning apparatus, characterized in that the interest box can be moved horizontally and vertically based on the user's input, and the interest box can be copied and additionally arranged according to a selection of a button preset for the interest box .
7. The method of claim 6,
the setting unit
Recommend an effective period for each of the user's interests in consideration of the validity period of other users for each of the interests, and each of the interests by the user's input based on the validity period for each of the recommended interests User interest validity period learning apparatus, characterized in that the validity period is set for.
delete

Images