Method and device for providing video recommendation information

Abstract

Disclosed are a method and a device, the method comprising steps in which: a reception unit acquires recommendation keywords for videos for which a user account requests recommendations; a processor acquires a first video list, which is a video list including the recommendation keywords, through filtering using artificial intelligence; the processor acquires user characteristic information including the age and gender of a user from the user account; the processor determines a relevance level for the first video list on the basis of the first video list and the user characteristic information; and the processor provides, on the basis of the relevance level, a second video list, which is a portion of the video list of the first video list.

Description

Methods and devices for providing video recommendation information

[0001] The technical field of the present disclosure relates to a method and device for providing video recommendation information, and more specifically, to a method and device for obtaining a recommendation keyword for a video that is desired to be recommended from a user account to obtain a first video list, determining a relevance level for the first video list based on the first video list and user characteristic information, and providing a partial video list among the first video list based on the determined relevance level.

[0002]

[0003] Currently, while users have access to a wide variety of videos, it is difficult to find exactly the videos they desire amidst the vast number available. Furthermore, users face the inconvenience of having to manually check through videos one by one to find what they want, resulting in both time and financial losses. Although some video platforms offer recommendation features based on user history, these functions also struggle to accurately reflect users' specific needs.

[0004] Therefore, there is a need for technology development to improve these issues and provide effective video recommendation information by offering customized recommendations that meet user needs.

[0005]

[0006] The problem to be solved in the present disclosure is to provide a service in a system for providing video recommendation information, wherein recommendation keywords for videos that are to be recommended from a user account are obtained to obtain a first video list, a relevance level for the first video list is determined based on the first video list and user characteristic information, and a partial video list among the first video list is provided based on the determined relevance level.

[0007]

[0008] As a technical means for achieving the technical problem described above, a method for a device according to the first aspect of the present disclosure to provide video recommendation information may include: a step in which a receiving unit obtains recommendation keywords for a video that is desired to be recommended from a user account; a step in which a processor obtains a first video list, which is a list of videos including the recommendation keywords, through filtering using artificial intelligence; a step in which the processor obtains user characteristic information, including age and gender of a user, from the user account; a step in which the processor determines a relevance level for the first video list based on the first video list and the user characteristic information; and a step in which the processor provides a second video list, which is a list of some videos among the first video list, based on the relevance level.

[0009] In addition, the second video list may include a recommendation list that reflects the order of the partial video list.

[0010] Additionally, the step of determining the relevance level further includes the step of obtaining image characteristic information for the first image list; and the image characteristic information may include at least one of the user gender ratio, user age group, number of views, number of likes, number of shares, and number of cumulative comments for the image.

[0011] In addition, the step of determining the relevance level may determine the relevance level based on weights differently assigned to the user characteristic information, the user gender ratio, the user age group, the number of views, the number of likes, the number of shares, and the number of cumulative comments, respectively.

[0012] Additionally, the step of providing the second image list may further include the step of obtaining image usage purpose information; and the step of providing a second image list, which is a partial image list among the first image list, based on the image usage purpose information.

[0013] In addition, the above information on the purpose of use may include at least one of the purposes of employment, exercise, and study.

[0014] A device for providing video recommendation information according to a second aspect of the present disclosure may include: a receiver that obtains recommendation keywords for videos that are desired to be recommended from a user account; and a processor that obtains a first video list, which is a list of videos including the recommendation keywords, through filtering using artificial intelligence, obtains user characteristic information including age and gender of a user from the user account, determines a relevance level for the first video list based on the first video list and the user characteristic information, and provides a second video list, which is a list of some videos among the first video list, based on the relevance level.

[0015]

[0016] According to one embodiment of the present disclosure, by providing a user with user-customized video recommendation information, the time and economic losses incurred by the user in finding the desired video can be minimized.

[0017] In addition, user satisfaction can be improved by obtaining a first video list based on user recommendation keywords and providing a second video list based on the first video list and user characteristic information.

[0018] In addition, user convenience can be improved by providing a second video list, which is a subset of the first video list, based on weights that are assigned differently to the user's purpose of video use and video characteristic information.

[0019] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below.

[0020]

[0021] FIG. 1 is a block diagram schematically illustrating the configuration of a device according to one embodiment.

[0022] FIG. 2 is a flowchart illustrating each step of operation of a device providing image recommendation information according to one embodiment.

[0023] FIG. 3 is a configuration diagram showing an example of the configuration of an image recommendation information system according to one embodiment.

[0024] FIG. 4 is a diagram illustrating an example in which a device according to one embodiment provides image recommendation information.

[0025]

[0026] The advantages and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below but can be implemented in various different forms, and the embodiments provided are merely to make the disclosure complete and to fully inform those skilled in the art of the scope of the present disclosure.

[0027] The terms used in this specification are for describing embodiments and are not intended to limit the disclosure. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. The terms “comprises” and / or “comprising” as used in this specification do not exclude the presence or addition of one or more other components in addition to the components mentioned. Throughout the specification, the same reference numerals refer to the same components, and “and / or” includes each of the mentioned components and all combinations of one or more. Although terms such as “first,” “second,” etc., are used to describe various components, these components are not limited by these terms. These terms are used merely to distinguish one component from another. Accordingly, the first component mentioned below may be the second component within the technical scope of this disclosure.

[0028] Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by a person skilled in the art. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0029] Spatially relative terms such as "below," "beneath," "lower," "above," and "upper" may be used to facilitate the description of the relationship between one component and other components as illustrated in the drawings. Spatially relative terms should be understood as encompassing different orientations of components during use or operation, in addition to the orientations depicted in the drawings. For example, if a component depicted in a drawing is inverted, a component described as "below" or "beneath" of another component may be placed "above" of that component. Therefore, the exemplary term "below" may encompass both the lower and upper directions. Components may also be oriented in other directions, and accordingly, spatially relative terms may be interpreted according to the orientation.

[0030] Various embodiments are described in detail below with reference to the drawings.

[0031]

[0032] FIG. 1 is a block diagram schematically illustrating the configuration of a device (100) according to one embodiment.

[0033] Referring to FIG. 1, the device (100) may include a receiver (110) and a processor (120).

[0034] A receiving unit (110) according to one embodiment can obtain recommendation keywords for a video that is to be recommended from a user account.

[0035] A processor (120) according to one embodiment can obtain a first video list, which is a list of videos containing recommended keywords, through filtering using artificial intelligence. Additionally, a processor (120) according to one embodiment can obtain user characteristic information, including age and gender of a user, from a user account. Additionally, a processor (120) according to one embodiment can determine a relevance level for the first video list based on the first video list and the user characteristic information. Additionally, a processor (120) according to one embodiment can provide a second video list, which is a list of some videos among the first video list, based on the relevance level.

[0036] Additionally, it should be noted that the device (100) providing video recommendation information may be combined with various conventional network combinations, such as an internet network or a mobile communication network, in the process of obtaining recommendation keywords for a video that a user account wants to recommend from a receiving unit (110), obtaining a first video list which is a video list containing recommendation keywords from a processor (120), obtaining user characteristic information and determining a relevance level for the first video list based thereon, and providing a second video list which is a partial video list among the first video list based on the relevance level, and there are no special restrictions on this.

[0037] In addition, it will be understood by those skilled in the art that, in addition to the components illustrated in FIG. 1, other general-purpose components may be further included in the device (100) providing image recommendation information. For example, the device (100) providing image recommendation information may further include a memory (not shown) that stores relevant information, user characteristic information, etc., regarding a received recommendation keyword, and may further include a display (not shown) that provides a second image list, which is a partial image list of a first image list, based on a relevance level. Alternatively, it will be understood by those skilled in the art that, according to other embodiments, some of the components illustrated in FIG. 1 may be omitted.

[0038] A device (100) providing video recommendation information according to one embodiment can be used by a user and can be linked with all types of handheld-based wireless communication devices equipped with a touch screen panel, such as mobile phones, smartphones, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), and tablet PCs, and can also be included in or linked with devices that have a foundation for installing and running applications, such as desktop PCs, tablet PCs, laptop PCs, and IPTVs including set-top boxes.

[0039] A device (100) that provides video recommendation information may be implemented as a terminal such as a computer that operates through a computer program to realize the functions described in this specification.

[0040] A device (100) providing video recommendation information according to one embodiment may include, but is not limited to, a system (not shown) and a related server (not shown) that provide video recommendation-related information. A server according to one embodiment may support an application that provides video recommendation-related information.

[0041] In the following description, the device (100) providing video recommendation information according to one embodiment will be described primarily in an embodiment in which it independently provides video recommendation-related information; however, as previously mentioned, this may also be performed through integration with a server. That is, the device (100) providing video recommendation information according to one embodiment and the server may be implemented as an integrated unit in terms of their functions, the server may be omitted, and it can be seen that this is not limited to any one embodiment.

[0042] In one embodiment, the device (100) and the server may be interconnected, and the configuration for providing video recommendation information related services by communicating with the user account and the server may be performed by the server or by the device (100). For example, the device (100) may operate as a server, and below, it will be described uniformly as the device (100).

[0043]

[0044] FIG. 2 is a flowchart illustrating each step of operation of a device providing image recommendation information according to one embodiment.

[0045] Referring to step S210, a device (100) according to one embodiment may obtain recommendation keywords for a video that the user wants to be recommended from a user account. In one embodiment, the recommendation keywords may include keywords related to the subject of the video that the user wants to be provided, scenes included in the video, and the mood of the video.

[0046] Referring to step S220, a device (100) according to one embodiment can obtain a first list of images containing recommended keywords through filtering using artificial intelligence. In one embodiment, the first list of images may be a list of images containing recommended keywords or images related to recommended keywords.

[0047] Referring to step S230, a device (100) according to one embodiment can obtain user characteristic information including age and gender of a user from a user account.

[0048] Referring to step S240, a device (100) according to one embodiment may determine a relevance level for a first video list based on a first video list and user characteristic information. In one embodiment, the relevance level may indicate the degree of high or low relevance to user needs among the first video list. Specifically, the device (100) according to one embodiment may obtain video characteristic information for a first video list, and the video characteristic information may include at least one of the user gender ratio, user age group, number of views, number of likes, number of shares, and number of cumulative comments for the video. The video characteristic information may indicate the degree to which it is preferred by a large number of users or helpful for use. Additionally, the device (100) may determine a relevance level based on user characteristic information and weights that are differently assigned to the user gender ratio, user age group, number of views, number of likes, number of shares, and number of cumulative comments, respectively. For example, assuming that the user gender and the user gender ratio correspond (e.g., the user gender is “female” and the user gender ratio is high for “females”) and the user age and the user age group correspond, the device (100) can determine the relevance level based on the number of elements that reach a threshold value among the user age group, views, likes, shares, and cumulative comments for the video. To explain, when the user gender and the user gender ratio and the user age and the user age group correspond, and the number of elements that reach a threshold value among the user age group, views, likes, shares, and cumulative comments is 1 or less, the device (100) can determine that the video corresponds to the user's gender and age group but is not considered a video preferred by many users, and thus the video has low relevance to the user, and can determine the relevance level as ‘low’.Additionally, when the user gender, user gender ratio, user age, and user age group correspond, and the number of elements reaching a threshold value among the user age group, views, likes, shares, and cumulative comments is 2 or more and 3 or less, the device (100) can determine the relevance level as 'medium'. Additionally, when the user gender, user gender ratio, user age, and user age group correspond, and the number of elements reaching a threshold value among the user age group, views, likes, shares, and cumulative comments is 4 or more, the device (100) can determine that the video is highly relevant to the user and highly preferred by many users, and can determine the relevance level as 'high'. Additionally, when the user gender, user gender ratio, user age, and user age group correspond to 1 or less, the device (100) can determine the priority of the relevance level based on weights assigned lower in the order of shares, cumulative comments, likes, and views. For example, video sharing often occurs when users save content for personal viewing or recommend it to others; since a high number of shares suggests a video is likely preferred by a large number of users, the number of shares may be assigned the highest weight as the first priority. Additionally, writing comments on a video can be time-consuming compared to other activities, and consequently, a large cumulative number of comments indicates high user interest; thus, the cumulative number of comments may be assigned the second highest weight. Furthermore, while the number of likes can indicate positive user evaluations of the video, it may be difficult to verify specific opinions, so its importance is considered somewhat lower, and the number of likes may be assigned the third highest weight. Finally, although a high number of views may indicate a video preferred by many users, it may be difficult to identify specific purposes or tastes, so the number of views may be assigned the fourth highest weight.Accordingly, the device (100) can provide user-customized video recommendation information by determining a relevance level based on weights that are differently assigned to user characteristic information and video characteristic information for the first video list, respectively.

[0049] Referring to step S250, a device according to one embodiment may provide a second video list, which is a partial video list of a first video list, based on a relevance level. In one embodiment, the device (100) may obtain video usage purpose information from a user account and may provide a second video list, which is a partial video list of a first video list, based on the video usage purpose information. Specifically, the usage purpose information may include at least one of employment purpose, exercise purpose, and academic purpose, and the device (100) may provide a second video list based on the usage purpose information and video characteristic information regarding the first video list. For example, if the video usage purpose is employment purpose, the device (100) may provide a second video list, which is a partial video list of a first video list, based on weights assigned in the order of user age group, user gender ratio, number of shares, number of views, number of likes, and number of cumulative comments. Specifically, if the video usage purpose is employment purpose, users of a similar age group to the user may also be preparing for employment, so a high weight may be assigned to the user age group as the first priority. Furthermore, if the user's gender and the gender with the higher proportion of users are the same, the user gender ratio may be assigned a second-highest weight, as there may be a high correlation between the job videos preferred by that gender and the job videos preferred by the user. Additionally, if the number of shares is high, it may indicate that many users want to watch the video again or show it to others, so its importance is judged to be high and the number of shares may be assigned a third-highest weight. Moreover, if the number of views is high, it indicates that many users have watched the video and that the number of times the video has already been viewed is high, so its importance may be high and the number of views may be assigned a fourth-highest weight.Additionally, if the number of likes is high, it may be considered highly preferred by many users, but since it is difficult to verify specific opinions, its importance may be somewhat low, so the number of likes may be given a high weight of 5th rank. Also, if the number of accumulated comments is high, it may be a video that is of interest to many users, but since it may be difficult to consider it highly relevant to the user's purpose for watching the video, the number of accumulated comments may be given a high weight of 6th rank. Therefore, the device (100) can improve the user's satisfaction by providing a second video list, which is a partial video list of the first video list, based on weights that are assigned differently to the user's purpose for watching the video and the video characteristic information.

[0050] In another embodiment, when the purpose of video usage is for academic purposes, the device (100) may provide a second list of videos, which is a subset of the first list of videos, based on weights assigned in the order of user age group, cumulative number of comments, number of shares, number of likes, number of views, and user gender ratio. Specifically, if the purpose of video usage is for academic purposes, the user age group may be assigned a first-rank high weight because if it corresponds to the user's age, there is a high possibility that they will study a similar curriculum. Additionally, if the cumulative number of comments is high, a large number of users may have written comments regarding questions or areas for improvement regarding the video, and since this can be helpful to the user, a second-rank high weight may be assigned to the cumulative number of comments. Additionally, if the number of shares is high, a large number of users may have shared the video to watch it again, and since this may be a video that is academically helpful to the users, a third-rank high weight may be assigned to the number of shares. Additionally, if the number of likes is high, the video may be positive to the user, but since it is difficult to verify specific opinions, a fourth-rank high weight may be assigned to the number of likes. Additionally, if the number of views is high, it can be seen that many users have watched the video, but it may be difficult to determine whether the evaluation is positive or negative, so its importance is judged to be low, and thus a high weight of 5th rank may be assigned to the number of views. Also, the user gender ratio can determine which gender ratio prefers the video, but it may be difficult to determine the relevance to academic purposes, so a high weight of 6th rank may be assigned to the user gender ratio. Therefore, the device (100) can improve user satisfaction by providing a second video list, which is a partial video list of the first video list, based on weights that are assigned differently to the user's purpose of video use and video characteristic information.Additionally, the device (100) according to one embodiment may include a second video list, which is a partial video list among a first video list based on a relevance level, and a recommendation list that reflects the order of the partial video list. Not limited thereto, the device (100) may also provide information about videos related to the video in the recommendation list, and information about other videos preferred by users who prefer the video.

[0051]

[0052] FIG. 3 is a configuration diagram showing an example of the configuration of a video recommendation information system according to one embodiment. Referring to FIG. 3, a device (100) according to one embodiment can obtain recommendation keywords for videos that a user account wishes to recommend, and can perform first filtering by obtaining a first video list, which is a list of videos containing the recommendation keywords, through filtering using artificial intelligence. Additionally, it can obtain user characteristic information including age and gender of the user from the user account, determine a relevance level for the first video list based on the first video list and user characteristic information obtained by performing first filtering, and perform second filtering by obtaining a second video list, which is a list of some videos among the first video list, based on the determined relevance level. Accordingly, the device (100) can provide user-customized information by providing video recommendation information to the user account by performing first filtering and second filtering on a plurality of videos using artificial intelligence, and user satisfaction can be improved.

[0053] FIG. 4 is a diagram illustrating an example of providing recommendation information by a device (100) according to an embodiment. Referring to FIG. 4, the device (100) can obtain recommendation keywords for images that a user account wishes to recommend, and can obtain a first list of images containing the recommendation keywords through filtering using artificial intelligence, and can determine a relevance level for the first list of images based on the first list of images and user characteristic information. Additionally, based on the relevance level, it can provide a second list of images that is a sub-list of images from the first list of images, and the second list of images may include a recommendation list that reflects the order of the sub-list of images. Furthermore, without being limited thereto, the device (100) may also provide information about images related to the corresponding images and information about other images preferred by users who prefer the corresponding images together in the recommendation list.

[0054] According to one embodiment, a first video list can be obtained through filtering using artificial intelligence based on recommended keywords, a relevance level for the first video list is determined based on the first video list and user characteristic information, and a second video list, which is a partial video list among the first video list, is provided to a user account based on the relevance level, thereby improving user satisfaction and convenience of use.

[0055] Various embodiments of the present disclosure may be implemented as software comprising one or more instructions stored in a storage medium (e.g., memory) readable by a machine (e.g., a display device or a computer). For example, a processor (120) of the machine (e.g., processor (120)) may call at least one of the one or more instructions stored from the storage medium and execute it. This enables the machine to be operated to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' merely means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily.

[0056] According to one embodiment, the method according to the various embodiments disclosed herein may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or distributed online (e.g., download or upload) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created in a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0057] Although the present invention has been described with reference to the illustrated drawings, it is not limited by the disclosed embodiments and drawings, and those skilled in the art will understand that it may be implemented in modified forms without departing from the essential characteristics of the above description. Therefore, the disclosed methods should be considered in an illustrative rather than a restrictive sense. Even if the effects of the configuration according to the present invention are not explicitly described in the description of the embodiments, effects predictable by said configuration may also be recognized. The scope of the present invention is defined by the claims, not by the foregoing description, and all variations within the equivalent scope thereof should be interpreted as being included in the present invention.

Claims

1. Regarding the method by which a device provides video recommendation information, A step in which the receiver obtains recommendation keywords for videos that it wishes to receive recommendations for from a user account; A step in which a processor obtains a first list of videos, which is a list of videos containing the recommended keywords, through filtering using artificial intelligence; The step of the processor obtaining user characteristic information including age and gender of the user from the user account; The step of the processor determining a relevance level for the first image list based on the first image list and the user characteristic information; and A method comprising the step of the processor providing a second image list, which is a partial image list of a first image list, based on the relevance level.

2. In Paragraph 1, A method in which the second video list above includes a recommendation list reflecting the order of the partial video list above.

3. In Paragraph 1, The step of determining the above-mentioned correlation level is The method further includes the step of obtaining image characteristic information for the first image list; and The above video characteristic information includes at least one of the user gender ratio, user age group, views, likes, number of shares, and cumulative number of comments for the video.

4. In Paragraph 3, The step of determining the above-mentioned correlation level is A method for determining the relevance level based on the above user characteristic information and weights differently assigned to the above user gender ratio, above user age group, above view count, above like count, above share count, and above cumulative comment count.

5. In Paragraph 4, The step of providing the second image list above It further includes the step of obtaining information on the purpose of video use; and A method comprising the step of providing a second video list, which is a partial video list among the first video list, based on the information regarding the purpose of using the video.

6. In Paragraph 5, The above-mentioned usage purpose information includes at least one of employment purpose, exercise purpose, and academic purpose, a method.

7. In a device that provides video recommendation information, A receiver that obtains recommendation keywords for videos that are to be recommended from a user account; and A device comprising: a processor that obtains a first video list, which is a video list containing the recommended keyword, through filtering using artificial intelligence; obtains user characteristic information, including age and gender of a user, from the user account; determines a relevance level for the first video list based on the first video list and the user characteristic information; and provides a second video list, which is a partial video list among the first video list, based on the relevance level.

Images