KR20240002089A - Method, apparatus and system of providing contents service in multi-channel network - Google Patents

Abstract

The present invention relates to a method, device, and system for providing content services in a multi-channel network. The method for providing content services in a multi-channel network according to an embodiment of the present invention includes the steps of collecting multi-video platform data, the collection Extracting characteristic information about creators' channels and video content of the channel from data on a multi-video platform, learning the extracted characteristic information with artificial intelligence, and learning about the traffic induction algorithm of the multi-video platform through the learning. It may include obtaining first prediction data, generating service guide data based on the first prediction data, and providing a service with the generated service guide data.

Description

Method, apparatus and system for providing content service in multi-channel network {METHOD, APPARATUS AND SYSTEM OF PROVIDING CONTENTS SERVICE IN MULTI-CHANNEL NETWORK}

The present invention relates to content services, and more specifically, to a method, device, and system for providing content services related to traffic induction in a multi-channel network (MCN: Multi-channel Network).

Conventionally, content was mainly produced by broadcasting experts at broadcasting stations through broadcasting station cameras, and the content produced was generally provided through broadcasting channels.

However, with recent rapid developments in digital technology and changes in related environments, various internet streaming platforms are developing. As the number of people active on these Internet streaming platforms increases, a multi-channel network or multi-channel network (MCN: Multi-channel network), like a kind of agency, has emerged.

However, as content production and provision environments are different and needs are different for each country, video platform, and creator, the factors that must be considered to provide appropriate services are becoming increasingly diverse and numerous, leading to multi-channel networks (MCNs). Sufficient consideration and support for this is required. Additionally, systematic support for this is required.

Korean Patent Publication No. 10-2020-0113370 (published on October 7, 2020)

The work of the present invention is to predict the effect of producing the channel and/or content through prediction of traffic induction algorithms for channels and/or content of various multi-video platforms in a multi-channel network (MCN: Multi-channel network). To provide methods, devices, and systems that can increase service satisfaction by maximizing service satisfaction and reducing the time and cost associated with channel and/or content production and management.

A method of providing content services in a multi-channel network according to an embodiment of the present invention includes collecting multi-video platform data; Extracting characteristic information about creators' channels and video content of the corresponding channels from the collected multi-video platform data; Artificial intelligence learning of the extracted characteristic information; Obtaining first prediction data regarding the traffic guidance algorithm of the multi-video platform through the learning; generating service guide data based on the first prediction data; and providing a service using the generated service guide data.

According to the method for providing content services in a multi-channel network according to an embodiment of the present invention, the multi-video platform data is collected through API and crawling methods.

According to the method of providing content services in a multi-channel network according to an embodiment of the present invention, the characteristic information includes the upload time and keywords displayed in the thumbnail image in relation to the channel and/or video content on the multi-video platform. Presence and content, presence or absence of subtitles, type or number, number of subscribers, number of views, number of likes or recommendations, number/absence of comments, viewing age, viewing gender, presence and number of video content deleted from the channel due to regulations under the platform's internal regulations, and Contains at least one of the information about the platform's internal regulations related to the above deletion.

According to the method of providing content services in a multi-channel network according to an embodiment of the present invention, the first prediction data regarding the traffic induction algorithm includes the traffic generation area of the multi-video platform, the traffic generation time, the traffic-related exposure layer, It includes at least one of traffic-related exposure keywords and/or images, and traffic-related exposure duration or frequency.

According to the method of providing content services in a multi-channel network according to an embodiment of the present invention, the first prediction data regarding the traffic induction algorithm includes the reliability of the channel of the multi-video platform or the content of the channel, and the increase or decrease in traffic. Include at least one additional piece of information about the trend.

According to a method of providing content services in a multi-channel network according to an embodiment of the present invention, the information on the traffic increase/decrease trend includes changes in traffic depending on changes in the attributes of the content and whether or not a specific keyword and/or image is included. Includes analytical information.

According to the method of providing content services in a multi-channel network according to an embodiment of the present invention, the information on the traffic increase/decrease trend is provided to the same or similar channel and/or the corresponding channel of the corresponding or other multi-video platform within a predefined time. Includes comparative analysis information with traffic increase/decrease trends for the content.

According to the method for providing content services in a multi-channel network according to an embodiment of the present invention, the first prediction data for the traffic guidance algorithm is the same or the same among the second prediction data for the traffic guidance algorithm for other multi-video platforms. It further includes first prediction data and comparative analysis data for similar channels and content of the corresponding channels.

An apparatus for providing content services in a multi-channel network according to an embodiment of the present invention includes: a memory; And a processor that communicates with the memory, wherein the processor extracts characteristic information about creators' channels and video content of the channel from the collected multi-video platform data, performs artificial intelligence learning, and performs artificial intelligence learning on the multi-video First prediction data regarding the traffic induction algorithm of the platform is acquired, service guide data is generated, and the generated service guide data is provided to a service.

A content service provision system in a multi-channel network according to an embodiment of the present invention includes a terminal; And a computing device that performs data communication with the terminal, wherein the computing device extracts characteristic information about creators' channels and video content of the channel from the collected multi-video platform data, performs artificial intelligence learning, and performs artificial intelligence learning. It includes a processor that obtains first prediction data regarding the traffic guidance algorithm of the multi-video platform, generates service guide data, and provides a service with the generated service guide data.

According to an embodiment of the present invention, the effect of producing the channel and/or content is maximized through prediction of traffic induction algorithms for channels and/or content of various multi-video platforms in a multi-channel network, and the channel and/or content are maximized. /Or, it has the effect of increasing service satisfaction by reducing the time and costs related to content production and management.

1 is a schematic diagram of a content service provision system processed in a multi-channel network according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating an integrated content management device in a multi-channel network according to an embodiment of the present invention.
Figure 3 is a flowchart illustrating a method of providing content services in a multi-channel network according to an embodiment of the present invention.
FIG. 4 is a diagram illustrating a method of providing content services in a multi-channel network according to another embodiment of the present invention.
Figure 5 is a diagram illustrating a traffic guidance algorithm inversion process according to an embodiment of the present invention.
Figure 6 is a diagram illustrating a traffic consideration matching process between platform-creator-product according to an embodiment of the present invention.
FIG. 7 is a diagram illustrating a channel/video content comparison method for providing traffic-considered content services in a multi-channel network according to an embodiment of the present invention.
FIG. 8 is a diagram illustrating recommendation of optimal content upload timing considering traffic in a multi-channel network according to an embodiment of the present invention.
Figure 9 is a diagram illustrating optimal title provision of content considering traffic in a multi-channel network according to an embodiment of the present invention.
10 to 14 are diagrams illustrating a user interface for providing traffic-considered content services in a multi-channel network according to an embodiment of the present invention.
Figure 15 is a block diagram of a content service providing device in a multi-channel network according to an embodiment of the present invention.

Below, with reference to the attached drawings, the embodiments will be described in detail so that those skilled in the art can easily perform them. However, the embodiments may be implemented in various forms and are not limited to the embodiments described herein. In order to clearly explain the embodiments in the drawings, parts that are not relevant to the description are omitted, and similar parts are given similar reference numerals.

The terminology was selected as a general term that is currently widely used as much as possible while considering the functions according to various embodiments, but this may vary depending on the intention or precedent of a technician working in the field, the emergence of new technology, etc. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the relevant embodiment. Therefore, the terms used here should be defined based on the meaning of the term and the content described here, not simply the name of the term.

Singular expressions include plural expressions unless the context clearly dictates otherwise. Terms such as "include" or "have" are intended to designate the presence of a feature, number, step, operation, component, part, or combination thereof, but not one or more other features, numbers, steps, operations, or composition. It should be understood that this does not exclude in advance the possibility of the presence or addition of elements, parts, or combinations thereof. In particular, the numbers are examples to aid understanding, and the embodiments should not be understood as being limited by the numbers listed.

Terms such as “-unit”, “-unit”, and “module” refer to a unit that processes at least one function or operation, which may be implemented as hardware or software, or as a combination of hardware and software.

Terms such as “first” and “second” are used to describe various components, but of course, these components are not limited by the terms. Terms such as “first” and “second” are simply used to distinguish one component from another component. Therefore, of course, the “first component” mentioned below may also be a “second component” within the technical spirit of the embodiment.

An expression such as "at least one" modifies the entire list of elements, not the elements of the list individually. For example, “at least one of A, B, and C” means only A, only B, only C, both A and B, both B and C, both A and C, all of A, B, and C, or any combination thereof. refers to

In this specification, various embodiments of a method, device, and system for providing content services in a multi-channel network (MCN: Multi-channel network or MPN: Multi-platform network) according to the present invention are described. At this time, the multi-channel network (MCN) is a method and device that supports the creator's content production and editing, traffic management, etc., and provides services so that the processed content can be provided to various video platforms. and systems.

Hereinafter, the term 'terminal' described in this specification includes all types of devices capable of producing and uploading content by the creator, and the term 'video platform' refers to a device that allows users to consume content provided by the terminal. It can contain all supported types of objects.

In addition, 'content' as used hereinafter refers to something that is uploaded to at least one video platform and viewed (or consumed) by a viewer (or consumer). This content is not limited by data format, and can be formed, for example, in video (or image) only, audio only, text only, or any combination of the above data formats.

In addition, the term 'channel' described hereinafter can be viewed as an upper layer that includes the content, and can be viewed as a route that provides the content. That is, one channel may include at least one content, and consumers can watch or consume the channel or content provided by the channel.

Hereinafter, various embodiments according to the present invention will be described with reference to the attached drawings, as follows.

Figure 1 is a schematic diagram of a content service provision system 1 in a multi-channel network (MCN) according to an embodiment of the present invention.

Referring to FIG. 1, an integrated content management system 1 processed in a multi-channel network (MCN) may be configured to include a terminal 10, a computing device 20, and a video platform 30. However, the present invention is not necessarily limited thereto.

Hereinafter, although only 'terminal 10', 'computing device 20', and 'video platform 30' are described in this specification, they may have singular or plural meanings depending on the context.

The terminal 10 can capture or create content to be consumed through a channel of the video platform 30. Depending on the embodiment, the terminal 10 may be a device only for capturing content, a device for editing or creating captured content, or a combination of the above devices, but is not limited thereto. Although it is expressed as a device above, it may be a part of the terminal 10 and may include a built-in or detachable hardware configuration or a software configuration such as a program or application for it.

Depending on the embodiment, the terminal 10 preferably has a keyboard, an image capture module, an audio input module, etc. built in or can be connected thereto.

Referring to Figure 1, a plurality of terminals (eg, terminal 1, terminal 2, ..., terminal n, where n is a positive integer) are shown. Each of the n terminals shown in FIG. 1 or at least two of the n terminals can be used to capture or produce content by one user, that is, a creator (or his account).

Depending on the embodiment, the terminal 10 includes fixed terminals such as PCs, TVs, kiosks, and digital signage, mobile terminals such as smartphones, tablet PCs, wearable devices, and digital photography devices, and content shooting or production devices. It may be any one of the dedicated terminals, but is not limited thereto.

Depending on the embodiment, the terminal 10 may be a dedicated device for primary processing such as content shooting, editing, and creation.

The video platform 30 may include any type of platform that can support or process content so that it can be consumed by subscribers or consumers when content is received or uploaded from the terminal 10.

Referring to FIG. 1, a plurality of video platforms (eg, video platform 1, video platform 2, ..., video platform m, where m is a positive integer) are shown. Each video platform belonging to the video platform 30 does not need to be closely related to each other, and there are no restrictions by location such as country or region.

The computing device 20 may support data communication between the video platform 30 and the terminal 10, which is another component of the content service provision system 1, in a multi-channel network (MCN).

The computing device 20 may provide various software/hardware configurations including a studio system for processing content of the terminal 10 belonging to the content service provision system 1 in a multi-channel network (MCN). .

The computing device 20 collects data from multiple video platforms in a multi-channel network (MCN), extracts characteristic information about creators' channels and video content of the channels from the collected multi-video platform data, and uses artificial intelligence (AI). : Artificial Intelligence), and through the learning, predicted data regarding the traffic induction algorithm of the multi-video platform can be obtained, service guide data can be generated, and the generated service guide data can be provided as a service.

According to the embodiment, the computing device 20 is a hardware/software configuration that performs various operation(s) for providing content services in a multi-channel network (MCN) according to an embodiment of the present invention, and is a server. It may be named and described by various names, such as computer, controller, etc.

Depending on the embodiment, the computing device 20 has a built-in memory or database, which is a storage means for storing software such as instructions and programs, firmware, information, data, etc. required to perform the above operations. You can connect with him. There may be a plurality of storage means, and they do not necessarily have to be built-in, and may be in a form that is connected to each other and allows data to be exchanged, such as a cloud.

Depending on the embodiment, the computing device 20 is a cloud server, an IP Multimedia Subsystem (IMS) server, a Telephony Application server, an Instant Messaging (IM) server, a Media Gateway Control Function (MGCF) server, and an MSG. It can be any one of (Messaging Gateway) server, CSCF (Call Session Control Function) server, etc.

In the multi-channel network (MCN) shown in FIG. 1, each component constituting the content service provision system 1 can perform data communication with each other according to wired/wireless communication protocols. The wireless communication protocols have already been implemented or commercialized, including 3G (generation), LTE (Long-Term Evolution), LTE-A (advanced), 5G, as well as Bluetooth ^TM and Wi-Fi. It includes all various wireless communication protocols that will be implemented or commercialized in the future.

Although not shown, each component of the content service provision system 1 in the multi-channel network (MCN) shown in FIG. 1 uses artificial intelligence (machine learning, deep-learning, etc.) in the content processing process. It can be done by using or combining ICT (Information & Communication Technology) technologies such as AI (eXtended Reality), Metaverse, and Block-chain. However, for convenience, reference is made to known technologies for detailed descriptions thereof, and separate detailed descriptions are omitted in this specification.

Next, content services in a multi-channel network (MCN) will be described.

In this specification, content service may include all processing including management of channels and/or content on a multi-channel network (MCN).

FIG. 2 is a diagram illustrating an integrated content management device in a multi-channel network according to an embodiment of the present invention.

Figure 3 is a flowchart illustrating a method of providing content services in a multi-channel network according to an embodiment of the present invention.

FIG. 4 is a diagram illustrating a method of providing content services in a multi-channel network according to another embodiment of the present invention.

FIG. 5 is a diagram illustrating a channel/video content comparison method for providing traffic-considered content services in a multi-channel network according to an embodiment of the present invention.

FIG. 6 is a diagram illustrating recommendation of optimal content upload timing considering traffic in a multi-channel network according to an embodiment of the present invention.

Referring to FIG. 2, the computing device 20 extracts characteristic information about creators' channels and the video content of the corresponding channels from the collected multi-video platform data, performs artificial intelligence learning, and learns the traffic of the multi-video platform through the learning. Predicted data related to the induction algorithm can be obtained, service guide data can be generated, and the generated service guide data can be provided to a service.

Referring to FIG. 2, the computing device 20 includes the studio system 210 and can perform operations for providing the above service.

The studio system 210 includes a data management system (dashboard or user interface) 220, a platform (API network module) 230, 260, a crawling module 240, a multi-video platform 250, and an anti-compilation system. It may include a system 270 and an automatic upload system 280.

The studio system 210 may be a platform provided by a multi-channel network (MCN), through which the terminal 10 and at least one video platform 30 may be connected. In other words, the studio system 210 may be a single video platform that involves creators in all necessary processes before uploading content to multiple video platforms and provides necessary functions or data.

Each component in FIG. 2 may be a hardware configuration that allows a program or software to run to execute or perform a related function. Depending on the embodiment, the components shown in FIG. 2 are modules for programs or software to perform functions and may be implemented by a single hardware configuration. In other words, Figure 2 is only for illustrating functions and is not limited thereto.

For convenience, each shown in FIG. 2 is described as a module, but it is not limited thereto.

The studio system 210 is a module that includes tools that process the creator's content in order to upload it to multiple video platforms. In the above, 'processing' includes editing such as changing data format, thumbnail resizing, adding text, prediction of traffic induction algorithm through learning and analysis of multi-video platform data, and services according to the prediction. It is meant to include various processing processes.

Meanwhile, the studio system 210 predicts each video platform to be uploaded later based on the collected information about the multiple video platforms or based on the information about the multiple video platforms, and the prediction through inversion of the traffic induction algorithm for the multiple video platforms. Appropriate tools can be provided to provide services according to .

Depending on the embodiment, all other components shown in FIG. 2 may be viewed as sub-configurations of the studio system 210 or as functions of the studio system 210. For example, a data management system 220 or an automatic upload system 280 or tools therefor may be provided through the studio system 210.

The data management system 220 may manage and provide user interface(s) for content upload when a creator uses a multi-channel network (MCN). At this time, the user interface(s) also provides predictions based on traffic induction algorithm inversion for the multi-video platform and various information for providing services based on the predictions, prior to content production or upload of produced content. A service guide can be provided for your reference.

All or part of the operation of the content service provision method in the multi-channel network (MCN) shown in FIG. 3 below is performed on the computing device 20, but is not necessarily limited thereto.

With reference to FIG. 3, content service provision in a multi-channel network (MCN) performed by the computing device 20 will be described.

The computing device 20 may collect multiple video platform data (S101).

In the above, a multi-video platform may refer to a plurality of video platforms, and an individual video platform may refer to each video platform belonging to the multiple video platform.

The computing device 20 can collect, process, and store the collected multi-video platform data by dividing it into individual video platforms.

The computing device 20 can collect creator, channel, and user data for each platform.

Depending on the embodiment, the computing device 20 may collect, process, and store the collected multi-video platform data by classifying it according to predefined criteria such as data format, size, and type (or category).

Depending on the embodiment, the computing device 20 may store data collected from a plurality of video platforms as raw data or may store it after processing. In particular, in the latter case, the computing device 20 may add information such as a timestamp, category, data format, size, etc. to the collected multi-video platform data, and may take the form of a tag.

The computing device 20 may process and store the collected multi-image platform data by adding weights according to predefined criteria. The weight may be determined in relation to, for example, traffic to the creator, channel, and/or video.

Depending on the embodiment, the computing device 20 may generate a learning model based on the collected multi-video platform data, learn through machine learning or deep learning, and transfer the learning results to the multi-channel network (MCN). It can be used to provide content services.

The computing device 20 may use technologies such as object recognition and motion detecting when the collected multi-video platform data is an image or video.

The computing device 20 uses voice recognition technology such as STT (Speech to Text) when the collected multi-video platform data is audio, and conversely, when the collected multi-video platform data is text, it uses TTS (Text to Speech) technology and natural language processing technology. It can be processed through (NLP: Natural Language Processing) technology.

In this specification, collection may be performed using a crawling technique or an API (Application Program Interface), but is not limited thereto. Depending on the embodiment, the collection may be done by accessing a public database that separately collects and stores data about the platform.

In addition, the computing device 20 may update the data by continuously collecting data at a predetermined period/non-period.

The computing device 20 may receive content from the terminal 10 (S103).

Step S103 is a process of receiving content produced by the creator, such as raw data, data before processing, production data, primary processing data, etc., from the terminal 10, which includes steps S105 to S105 to be described later. Step S107 may be a pre-processing step by the studio system 210.

The computing device 20 may provide the terminal 10 with the studio system 210 for processing the received content (S105).

The computing device 20 may control the content processed through the provided studio system 210 to be automatically uploaded to the multi-video platform based on the collected multi-video platform data (S107). At this time, the multiple video platform may represent at least one individual video platform.

According to the embodiment, the process of FIG. 3 described above may be viewed as being performed not on the terminal 10 but on the web or virtual space.

Depending on the embodiment, unlike shown in FIG. 3, if the process is performed on the terminal 10 rather than on the web or a separately defined virtual space, the above-described step S20 is performed from the terminal 10 to the computing device 20. Rather than transmitting content, the creator downloads an application or program related to the multi-channel network (MCN) from the terminal 10, installs it, and then runs it, thereby storing the content stored in the memory of the terminal 10 through the studio system 210. You can also call or read it, and perform processing such as editing on the content. In this case, step S20 and/or step S30 may be replaced with or omitted as a process in which the computing device 20 receives a content processing request or a request to execute an application or program related to a multi-channel network (MCN) from the terminal 10. there is. Meanwhile, the terminal 10 may download and install an application or program related to a multi-channel network (MCN) in advance. At this time, the application or program related to the multi-channel network (MCN) is produced by the computing device 20, It may have been distributed.

Depending on the embodiment, the computing device 20 may temporarily store processed content. At this time, the computing device 20 does not store the content in the built-in memory or database, but stores it in another remotely located storage, and records only address data (e.g., url (uniform resource locator), etc.) related to the stored location. and can be saved. By doing so, the capacity of the server related to data storage can be reduced.

The computing device 20 may determine content to be uploaded to a multi-video platform from content stored later and process the content to be automatically uploaded to the multi-video platform.

Figure 3 shows the process of receiving content from the terminal 10 at the computing device 20 and uploading it to a video platform on a multi-channel network (MCN), and Figure 4 shows the process of receiving content from the terminal 10 in the computing device 20 and uploading it to the video platform(s) on the multi-channel network (MCN). Through the traffic induction algorithm inversion process as shown in Figure 5 and the traffic consideration matching process between platform-creator-product in Figure 6, traffic processing or management of the video platform(s) is predicted, and a service guide is provided based on the prediction results. It may be related to processing of the content to be uploaded.

The traffic induction algorithm inversion process of FIG. 5 and the traffic consideration matching process between platform-creator-product of FIG. 6 are one component within the computing device 20 of FIG. 1 or the computing device 20 of FIG. 2 or the process of FIG. 15 described later. It may be performed by hardware such as the processor 1420.

In particular, Figure 6 uses the derived result values to connect creators (content) that fit the platform characteristics and match products that fit the results to provide service guide data.

Through this, the computing device 20 not only allows the platform-user (creator, MCN)-developer to communicate organically to build an alliance system to respond to the rapidly changing video platform and content trend market, but also builds a more stable and highly usable system. We can provide services to do so.

The computing device 20 can also predict channel/content growth and performance and profitability. For example, the computing device 20 can analyze platform content consumption data and platform characteristic data to suggest future growth of the channel, and provide related service guide data by predicting the rate of return linked to channel/content achievement. .

The computing device 20 can establish original content direction and content commerce strategies. For example, the computing device 20 can suggest categories and items with high growth potential through analysis of content supply and demand trends based on platform-user data and content-commerce related data.

The computing device 20 can connect issue/trend big data and content-commerce. For example, the computing device 20 can suggest content direction by analyzing global/local issue data and e-commerce trend data. The computing device 20 can provide services to establish marketing strategies through content-commerce correlation data.

The computing device 20 can match influencers suitable for promotional marketing purposes. For example, the computing device 20 may classify influencers through analysis of channel/content and e-commerce data and then provide influencer information suitable for the purpose of a company that wants to promote and sell products.

Computing device 20 may provide a business model. For example, the computing device 20 can continuously discover IP business-linked profit models centered on traffic IT secured through platform/channel expansion and content distribution, and content direction and commerce linkage strategies optimized for securing traffic within multiple platforms. Through this, we can provide services that help brands (advertisers) become global content commerce business partners. The computing device 20 uses the data collected through primary customer service to create insights necessary for secondary customers (for example, companies that carry out promotional marketing on various domestic and international platforms) and influencer information based on this. Matching services can be provided to expand the market.

Referring to FIGS. 4 to 6, the computing device 20 may collect multiple video platform data (S201).

The computing device 20 may extract characteristic information about the creator(s)' channel and the video content of the channel from the collected multi-video platform data (S203).

The computing device 20 can learn the extracted characteristic information using artificial intelligence (S205).

The computing device 20 can invert the traffic induction algorithm of the target multi-video platform through the learning, and obtain prediction data (for convenience, first prediction data) regarding the traffic induction of the multi-video platform based on this inversion. You can do it (S207).

The computing device 20 may generate service guide data for traffic management before uploading content based on the predicted data and provide the service.

As described above, the computing device 20 may collect the multi-video platform data through at least one of an API and a crawling method.

In the above, characteristic information refers to information related to channels and/or video content on the multi-video platform, including the channel upload time, the presence or absence of keywords (titles, etc.) displayed in the thumbnail image and their contents, the presence or absence of subtitles, and the presence or absence of subtitles. Type or number, number of subscribers, number of views, number of views, number of likes or recommendations, number of comments or presence of comments, subscriber or viewer age, subscriber or viewer gender, presence and number of video content deleted in the channel due to regulations under the platform's internal regulations, And it may include at least one of information about platform internal regulations related to the deletion.

Meanwhile, in the above, the predicted data regarding the traffic induction algorithm includes the traffic generation area of the multi-video platform, traffic generation time, traffic-related exposure layer, traffic-related exposure keywords and/or images, and traffic-related exposure duration or frequency. It may contain at least one or more.

Depending on the embodiment, the first prediction data regarding the traffic induction algorithm may include at least one of the reliability of the channel of the corresponding multi-video platform or the content of the corresponding channel, and information on traffic increase/decrease trends.

In the above, information on traffic increase/decrease trends may include analysis information on changes in traffic depending on changes in attributes of the content and whether or not specific keywords and/or images are included. For example, this traffic increase/decrease trend may be determined based on a predetermined period (e.g., day/week/month/quarter/year, etc.). Depending on the embodiment, the traffic increase/decrease trend may be determined based on the case where the corresponding keyword or image is included. In other words, traffic changes can be detected and used when a specific keyword or image is included or not for the same channel/content. The above is not necessarily limited to the same channel/content. Depending on the embodiment, by comparing the case of the same content with the case of different content for a specific keyword or image, the degree of change in traffic for the keyword or image may be analyzed, and traffic for the keyword or image may be considered accordingly. Weights can be determined.

Meanwhile, for keywords or images, similar keywords or images can be detected, related keywords or images can be grouped, and traffic comparison analysis on keywords or images in groups can also be performed. Within the group, priorities or different weights can be set for keywords or images, and they can also be divided into traffic-related keywords and traffic-unrelated keywords.

In addition, even for the same or similar keywords or images, information on traffic increase or decrease according to channel or content, gender, age, time zone, platform, etc. can be compared and analyzed for reference.

In addition, a traffic map for similar keywords or images for one keyword or image is constructed, and the priority or level of traffic consideration according to various criteria for each keyword or image in the traffic map is considered or managed by classifying it by hierarchy. You may.

Depending on the embodiment, the information on the traffic increase/decrease trend may include comparative analysis information with the traffic increase/decrease trend for the same or similar channel of the corresponding or other multi-video platform and/or the content of the corresponding channel within a predefined time. there is.

Depending on the embodiment, the first prediction data for the traffic guidance algorithm is compared with the first prediction data for the same or similar channel and the content of the channel among the second prediction data for the traffic guidance algorithm for another multi-video platform. May include analysis data.

Depending on the embodiment, the first prediction data for the traffic guidance algorithm may include first prediction data for the same time period and comparative analysis data among the second prediction data for the traffic guidance algorithm for other multi-video platforms. there is.

Depending on the embodiment, the first prediction data for the traffic guidance algorithm may include first prediction data for the same gender and comparative analysis data among the second prediction data for the traffic guidance algorithm for other multi-video platforms. .

Depending on the embodiment, the first prediction data for the traffic guidance algorithm may include comparative analysis data with the first prediction data for the same age group among the second prediction data for the traffic guidance algorithm for another multi-video platform. In the above, the same age group refers to a specific age or age group that mainly generates traffic (teens, 20s, 30s, etc.), or infant/child/middle school student/high school student/college student/adult, boy/youth/middle age/old age. It can be judged based on etc.

Depending on the embodiment, the first prediction data regarding the traffic guidance algorithm may include first prediction data and comparative analysis data for the same or similar category among the second prediction data for the traffic guidance algorithm for other multi-video platforms. You can. In the above, the same or similar category can be determined based on the properties of the platform and channel/content that mainly generate traffic.

Depending on the embodiment, the first prediction data regarding the traffic guidance algorithm may include first prediction data and comparative analysis data for the same or similar area among the second prediction data for the traffic guidance algorithm for other multi-video platforms. You can. The above-mentioned same or similar area refers to administrative districts such as provinces/cities/counties/districts, GPS, geographic information such as latitude and longitude, and geographic information such as Asia/Europe/North America/South America/Africa based on the location that generates traffic. It can be judged based on etc.

Depending on the embodiment, the first prediction data regarding the traffic induction algorithm is comparative analysis data with the first prediction data on the same or similar content among the second prediction data for the traffic induction algorithm for other multi-video platforms of the same creator. It can be included.

When using or considering traffic according to the present invention, it may be decided based on only one of the factors or criteria described above, but by quantifying the determined results for each and standardizing the average value, more information about the target channel/content can be obtained. Objective standards can also be presented. For example, the standardization information can be used to predict the current expected traffic score or high or low expected traffic of the target content, and provide recommended information that can additionally trigger or induce traffic based on such predictions. there is.

Figures 7 and 8 describe the provision of optimal timing of content according to the analysis of the traffic induction algorithm through the content service of the present invention.

In Figure 7 (a), traffic comparison results from individual video platforms belonging to a multi-channel network (MCN) are shown.

Depending on the embodiment, (a) of FIG. 7 may show traffic comparison results on a channel basis or content basis on a specific video platform. The content unit may be a traffic comparison result for content provided by a specific channel or for the content on all channels or all video platforms.

In Figure 7(b), information on comparison target data shown through the traffic comparison result graph in Figure 5(a) is shown. In (b) of FIG. 7, content is shown for convenience, but it is not limited thereto and may also include channels or video platforms.

Referring to FIG. 8, the computing device 20 may include a first processing unit 810 and a second processing unit 820 that have a circular structure. The first processing unit 810 collects traffic data for each video platform. The second processing unit 820 determines the optimal upload timing for each video platform based on the traffic data for each video platform collected by the first processing unit 810, and generates an upload timing recommendation data set according to the determination result. can do. The first processing unit 810 and the second processing unit 820 may have a circular structure so that improved upload timing can be determined by learning by applying or sharing each data. This circular structure can also be applied to the above-described Figure 9.

The computing device 20 can provide recommended information about the video platform to upload, the time to upload, etc. for the content of the terminal 10 using the traffic comparison data shown in (a) and (b) of FIG. 7. there is. This recommended information may include optimal timing information for each channel, video platform, and content.

In addition to the optimal timing of FIGS. 7 and 8 described above, FIG. 9 explains the provision of optimal titles for content according to analysis of a traffic induction algorithm through the content service of the present invention.

FIG. 9 is a diagram illustrating a method of providing an optimal title for integrated management content in a multi-channel network (MCN) according to an embodiment of the present invention.

Referring to FIG. 9, the computing device 20 continuously monitors traffic data for content uploaded from multiple video platforms and detects various keywords (good keywords) related to traffic from individual video platforms. You can.

These traffic-related keywords can be divided into traffic-inducing keywords and traffic-unrelated keywords.

The latter traffic-irrelevant keywords may refer to keywords that do not directly or indirectly affect traffic induction. At this time, the term “no effect” may include not only cases where there is no effect completely below a predefined threshold, but also cases where the effect is minimal.

On the other hand, the former traffic-related keyword may represent a keyword that induces traffic or has an effect on inducing traffic. These traffic-related keywords can be further divided into direct traffic-related keywords and indirect traffic-related keywords. Directly related traffic keywords may represent keywords that independently cause significant traffic (traffic above a threshold). On the other hand, indirect traffic-related keywords may represent keywords that, although they do not independently cause significant traffic, lead to significant traffic when combined with other keywords.

The computing device 20 may generate a tag for the detected keyword based on its properties.

Depending on the embodiment, the computing device 20 may generate a traffic (keyword) learning model based on a machine learning or deep learning algorithm using tag data.

The computing device 20 can use the learning model created in this way to perform learning, such as keywords, from data extracted from multi-video platform data collected later.

Based on the learning results, the computing device 20 may classify keywords related to traffic, particularly keywords related to the title of the content, and provide recommended title data for the content to be uploaded.

Depending on the embodiment, the computing device 20 may provide a plurality of recommended title data and traffic prediction data according to each recommended title data. Computing device 20 may also generate a learning model related to the traffic prediction data.

According to another embodiment, the computing device 20 may perform an update on the previously created artificial intelligence learning model through comparative analysis of traffic expected data when applying a title according to the recommendation and actual traffic data later.

Meanwhile, the computing device 20 may recommend optimal title data or later perform text mining on related traffic data and generate a success or failure tag. The tag data generated in this way may be reflected in the creation or learning of the learning model described above.

The computing device 20 may objectively determine which tag data to generate during the above-described monitoring and tag creation process according to predefined criteria. These judgment criteria include, for example, the threshold for increase/decrease in channel/content traffic set by the creator, the threshold for increase/decrease in the number of channel/content subscribers or/and views, and the threshold for increase/decrease in the number of channel/content subscribers or/and views, and the relationship between other channels/content selected based on the category or attribute to which the channel/content belongs. May include comparisons, etc.

In the above, in comparison with other channels/contents, channels/contents that have traffic changes greater than a threshold within a preset period before and after the upload of the target channel/content may be selected. In the above, in comparison with other channels/contents, at least one content with the most traffic fluctuations and at least one content with the least traffic fluctuations within a preset period before and after the upload of the target channel/content are selected as the other channels/contents. It can be.

Meanwhile, the contents of FIGS. 8 and 9 can be applied to each video platform, each channel/content, and each creator.

Even with the traffic induction algorithm described in this specification, different methods may be applied for each platform, each channel, and each creator as an objective factor, and in addition, a subjective factor, that is, the channel/content or the creator providing it. It is desirable to reflect the elements of .

In the above, in relation to channel/content and traffic induction, find trends related to current traffic induction or induction on multiple video platforms, reduce traffic in accordance with the trend, or exclude content unrelated to traffic as much as possible. , Conversely, it may be intended to maximize the effect by providing a service guide to creators so that they can increase traffic or provide channels/content with content related to traffic generation. In this respect, the optimal timing of FIG. 8 and the optimal title of FIG. 9 may be taken into consideration such traffic induction. Through this, profitability can be improved in channels/content related to profitability depending on the properties or type of channel/content, and by providing information on channels/content that match related trends, channels/content unrelated to traffic or trends Service satisfaction can be increased by reducing the cost and time required for production.

10 to 14 are diagrams to explain a user interface (UI) for providing traffic-considered content services in a multi-channel network (MCN) according to an embodiment of the present invention.

The first user interface of FIGS. 10 can be divided into a general user interface, the second user interface of FIGS. 11 and 12 can be divided into a video user interface, and the third user interface of FIGS. 13 and 14 can be divided into a platform user interface.

First, referring to FIG. 10, the first user interface displays information related to the multi-channel network (MCN) in the first area 1010, such as the total number of subscribers, the total number of IPs/CNs, the total number of views, and the total video upload. You can post information such as: The first user interface may post information about hot creators among creators using a multi-channel network (MCN) in the second area 1020. At this time, for example, in relation to traffic, the hot creator may represent top creators with the highest total traffic generation/induction, or may represent creators whose recent traffic increase is above a threshold. For example, the creator information may be provided in sequential order according to criteria such as day, month, quarter, and year.

The first user interface may post a traffic chartboard for creators using a multi-channel network (MCN) in the third area 1030.

Next, when describing the video user interface of FIGS. 11 and 12, unlike the configuration of the first user interface of FIG. 10 described above, it may be a user interface configured based on traffic data about video or video content.

Referring to FIG. 11, an example of the configuration of the second user interface, that is, the video user interface, is shown. The platform, all channels, and all IPs in use in relation to the multi-channel network (MCN) are displayed in the first area 1110. , information about the total number of videos, etc. is provided. The first area 1110 provides a tool for a search function, through which it is possible to search and select a specific video platform and channel/content whose traffic increase/decrease is more than a threshold, select a search period, and select the title of the channel/video content. You can enter search terms or search criteria such as creator name, channel name, keyword, etc. In the second area 1120, the video content with the highest number of views this week based on traffic induction/triggering among the video contents of creators using a multi-channel network (MCN) is sorted and provided, and in the third area 1130, the multi-channel network (MCN) ( Among the video content of creators using MCN, information on a list of video content deleted from a certain platform(s) may be provided, and in the fourth area 1140, a list of video content with a rapid increase in traffic may be provided in a sorted manner.

On the other hand, referring to FIG. 12, the configuration of the video user interface is shown when the search function is used in the first area 1110 of FIG. 11. In the second area 1210, a list of search results can be arranged and provided. . The search result list may be provided sorted according to the number of traffic or other settings.

Lastly, when describing the platform user interface of FIGS. 13 and 14, unlike the configuration of the first user interface of FIG. 10 and the video user interface of FIGS. 11 and 12 described above, a creator or his content using a multi-channel network (MCN) This may be a platform unit for which traffic data is considered or a user interface configured to post platform-related information.

Referring to FIG. 13, it shows an example of the configuration of the third user interface, that is, the platform user interface, and provides information about the platform used by creators using the multi-channel network (MCN) in the first area 1310, that is, the platform. , information on total channels/content, total IP, total number of subscribers, etc. is provided. In the second area 1320, detailed information about traffic on the platform of the first area 1310 may be provided.

On the other hand, referring to FIG. 14, the platform user interface can be configured to provide detailed information about a specific platform selected in consideration of traffic through the first area 1310 or the second area 1320 of FIG. 13. In the first area 1410, information on the active channel information and total number of videos of the corresponding platform of creators using a multi-channel network (MCN) is provided, and in the second area 1420, creators using a multi-channel network (MCN) are provided. A list of information related to popularity considering traffic on the corresponding platform is provided in an ordered manner, and in the third area 1430, information on the most consumed video content considering traffic on the corresponding platform of creators using a multi-channel network (MCN) is provided. The list may be provided sorted.

Meanwhile, in FIGS. 10 to 14 described above, when each area or the information or list provided in each area is hovered or selected, related detailed information may be provided or the corresponding video content may be played and provided in a pop-up window format.

Referring again to FIG. 2, the platforms (API network modules) 230 and 260 and the crawling module 240 are modules that collect various data about the multi-video platform 250.

The anti-compilation system 270 may perform processing on the collected data.

The automatic upload system 280 can automatically upload content requested by the creator to a multiple video platform according to a predefined method.

Figure 15 is a block diagram of a content service providing device in a multi-channel network (MCN) according to an embodiment of the present invention.

The integrated content management device in the multi-channel network (MCN) of FIG. 15 may be a block diagram of the computing device 20 of FIG. 1 .

A content integrated management device in a multi-channel network (MCN) may include a memory 1510 and a processor 1520. At this time, FIG. 2 may be a configuration of the process 1520.

The memory 1510 may store various instructions, and the stored instructions may be executed by the processor 1520 to perform corresponding functions.

The memory 1510 can store data or information that is generated or processed during the content service process in the above-described multi-channel network (MCN).

The processor 1520 can read data from the memory 1510 and generate, process, and transmit information.

The processor 1520 may perform or control various operations in FIGS. 2 to 14 described above.

Meanwhile, the sequences shown in the flowcharts described in this specification may be operated differently from the sequences shown in the corresponding drawings. For example, the order of some operations in each flowchart may be changed or performed simultaneously despite being shown. Meanwhile, depending on the embodiment, some operation(s) shown in each flowchart may be omitted or some operation(s) although not shown may be added.

According to at least one of the various embodiments of the present invention described above, a multi-channel network (MCN) predicts traffic induction algorithms for channels/content of various multi-video platforms to channel/content based on artificial intelligence technology. By providing recommended services and guide data to drive traffic, the effect of producing the channel/content can be maximized, and service satisfaction can be increased by reducing the time and costs related to the production and management of the channel/content.

For example, according to the present invention, through prediction and recommendation services through traffic induction inversion on various video platforms, the effectiveness of sales or advertising of products or products related to e-commerce, and the increase in the popularity or reliability of individual creators. , Not only does it reduce time and cost due to indiscriminate production/upload of traffic-independent content, but also improves server usage capacity due to meaningless traffic consumption, improves service use satisfaction of consumers consuming such channels/content, improves service speed, and improves the traffic induction algorithm itself. Services on various multi-channel networks (MCNs) become possible through combinations of satisfaction, reliability, and new recommendation algorithms based on traffic induction.

Methods according to embodiments may be implemented in the form of hardware, software, or a combination of hardware and software. If the embodiment is implemented using software, one or more programs (software, software modules) may be used. The program may be included in a computer-readable recording medium, but is not limited thereto. The Program may also be included in a computer program product. A computer-readable recording medium storing the program may be included in the computer program product. The program is configured to be executable by one or more processors within the electronic device. One or more programs may include instructions, and the instructions may be executed by one or more processors included in the electronic device, allowing the electronic device to execute methods according to embodiments.

Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include both computer storage media and communication media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transmission mechanism, and includes any information delivery medium. Additionally, some embodiments may be implemented as a computer program or computer program product that includes instructions executable by a computer, such as a computer program executed by a computer. A plurality of computer-readable recording media may be distributed across computer systems connected to a network, and data stored in the distributed recording media, such as program instructions and code, may be executed by at least one computer. there is.

The functions of the various elements shown in the drawings can be provided through the use of dedicated hardware as well as hardware capable of executing software in conjunction with appropriate software. When provided by a processor, these functions may be provided by a single dedicated processor, a single shared processor, or multiple separate processors, some of which may be shared. Additionally, explicit use of the terms "processor" or "control section" should not be construed to refer exclusively to hardware capable of executing the software, including, without limitation, digital signal processor (DSP) hardware, read-only for storing the software. It may implicitly include memory (ROM), random access memory (RAM), and non-volatile storage devices.

Unless there is an explicit order or description to the contrary regarding the steps constituting the method according to the embodiments, the steps may be performed in an appropriate order. The embodiment is not limited by the order of description of the steps. The use of any examples or illustrative terms (e.g., etc.) is merely to describe the embodiments in detail and does not limit the scope of the disclosure by the examples or illustrative terms unless limited by the claims. .

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements can be made by those skilled in the art using the basic concept of the present invention defined in the following claims. falls within the scope of rights.

The present invention's method, device, and system for providing content services in a multi-channel network can be used in various methods, devices, and systems for providing content services in a multi-channel network.

Claims (7)

collecting multi-video platform data;
Extracting characteristic information about creators' channels and video content of the corresponding channels from the collected multi-video platform data;
Artificial intelligence learning of the extracted characteristic information;
Obtaining first prediction data regarding the traffic guidance algorithm of the multi-video platform through the learning;
generating service guide data based on the first prediction data; and
Including the step of providing a service with the generated service guide data,
A method of providing content services in a multi-channel network. According to paragraph 1,
The multi-video platform data is collected through API and crawling methods,
The above characteristic information is,
With regard to channels and/or video content on said multi-video platform,
Upload time, presence and content of keywords displayed in the thumbnail image, presence or absence of subtitles, type or number, number of subscribers, number of views, number of likes or recommendations, number/absence of comments, viewing age, viewing gender, due to regulations within the platform's internal regulations for the channel. Contains at least one of the following information about the presence and number of deleted video content and the platform's internal regulations related to the deletion,
A method of providing content services in a multi-channel network. According to paragraph 2,
The first prediction data regarding the traffic guidance algorithm is,
Containing at least one of the traffic generation area of the multi-video platform, traffic generation time, traffic-related exposure layer, traffic-related exposure keywords and/or images, and traffic-related exposure duration or frequency,
A method of providing content services in a multi-channel network. According to paragraph 3,
The first prediction data regarding the traffic guidance algorithm is,
Further comprising at least one of the following: reliability of the channel of the multi-video platform or the content of the channel, and information on traffic increase/decrease trends,
A method of providing content services in a multi-channel network. According to clause 4,
Information on the above traffic increase/decrease trend,
Contains analysis information on changes in traffic depending on changes in the properties of the content and whether or not specific keywords and/or images are included;
A method of providing content services in a multi-channel network. According to clause 4,
Information on the above traffic increase/decrease trend,
Contains comparative analysis information with the traffic increase/decrease trend for the same or similar channel and/or content of the channel on the corresponding or other multi-video platform within a predefined time,
A method of providing content services in a multi-channel network. According to clause 4,
The first prediction data regarding the traffic guidance algorithm is,
Among the second prediction data for the traffic induction algorithm for other multi-video platforms, it further includes first prediction data and comparative analysis data for the same or similar channel and the content of the channel,
A method of providing content services in a multi-channel network.