Method and system for tagging content data based on artificial intelligence

Abstract

According to the present invention, a method for tagging content data based on artificial intelligence, performed by an electronic device, may include: receiving a content file containing content data forming content from a first user terminal; identifying a type of content based on the title and file format of the received content file and obtaining a plurality of first tags corresponding to the type of content; removing noise data from the content data and extracting data to be analyzed based on the type of content; generating first attribute information corresponding to each of the plurality of first tags based on feature extraction of the data to be analyzed; and generating first feature information of the content including the plurality of first tags and the first attribute information corresponding to each of the plurality of first tags and storing it in the database.

Description

Technology Field

[0001] The present invention relates to a method and system for tagging content data based on artificial intelligence. Background Technology

[0002] With the recent acceleration of the digital transformation in the content industry, various forms of multimedia content, including video, music, design, and photography, are being generated and distributed in large quantities. Consequently, there is a growing need for sophisticated tagging technologies for the key components of content to effectively classify, recommend, and search for such content.

[0003] However, existing tag systems have largely relied on manual input or were limited to simple keyword-based automation, which has limited their ability to precisely reflect the semantic characteristics of content or user needs. In particular, creative content includes multi-layered information based not only on text but also on auditory and visual elements, requiring advanced technology to systematically interpret and structure it.

[0004] Furthermore, while companies and project organizers require precise analysis reflecting detailed attributes such as the style, atmosphere, and structure of content for content-based talent recommendation and project matching, existing systems have faced a problem in accurately identifying desired creators because they fail to systematically tag these specific characteristics.

[0005] Accordingly, the purpose of the present invention is to provide a method and system capable of precisely classifying and grouping content by utilizing artificial intelligence-based data analysis technology to automatically assign tags to various elements constituting the content itself and generating attribute information corresponding to each tag. Prior art literature

[0006] Prior Art 1: Korean Registered Patent No. 10-2710210 (September 26, 2024) Prior Art 2: Korean Registered Patent No. 10-2387829 (April 18, 2022) Prior Art 3: Korean Registered Patent No. 10-2297814 (September 3, 2021) Prior Art 4: Korean Registered Patent No. 10-2712179 (September 30, 2024) The problem to be solved

[0007] The present invention was devised to solve the aforementioned conventional problems, and its purpose is to enable matching between creators and companies whose desired creative styles accurately match by acquiring component-specific characteristics of a single piece of content and making various groupings possible for a single piece of content.

[0008] The purpose of this invention is to ensure that the characteristics of content created by a creator and the characteristics of content desired by a company are accurately matched through the analysis of the content data itself.

[0009] The objectives of the present invention are not limited to those mentioned above, and other unmentioned objectives will be clearly understood from the description below. means of solving the problem

[0010] According to embodiments of the present invention, a method for tagging content data based on artificial intelligence, performed by an electronic device, may include: receiving a content file containing content data forming content from a first user terminal; identifying a type of content based on the title and file format of the received content file and obtaining a plurality of first tags corresponding to the type of content; removing noise data from the content data and extracting data to be analyzed based on the type of content; generating first attribute information corresponding to each of the plurality of first tags based on feature extraction of the data to be analyzed; and generating first feature information of the content including the plurality of first tags and the first attribute information corresponding to each of the plurality of first tags and storing it in the database.

[0011] According to embodiments of the present invention, when a first recommendation content request is received from a second user terminal, the method may include: a step of extracting second feature information including a plurality of second tags and second attribute information corresponding to each of the plurality of second tags from the first recommendation content request; a step of identifying that at least a portion of the plurality of first tags and the first attribute information included in the first feature information matches the plurality of second tags and the second attribute information included in the second feature information; and a step of assigning the content to a group of recommendation content for the second user terminal.

[0012] According to embodiments of the present invention, the first user terminal is a creator terminal and the second user terminal is a corporate representative terminal, and the type of content includes at least one of video, music, design, or photograph, and when the type of content is identified as music, the plurality of first tags may include beat, melody, timbre, instrument, pitch of the instrument, chorus, and general part.

[0013] According to embodiments of the present invention, if one of the plurality of first tags is an instrument, the names of all instruments used in the content are generated as the first attribute information, and if one of the plurality of first tags is a timbre, the timbre of a singer included in the content can be generated as the first attribute information.

[0014] According to embodiments of the present invention, when a second recommendation content request is received from a third user terminal, a third feature information including a plurality of third tags and third attribute information corresponding to each of the plurality of third tags is extracted from the second recommendation content request, and when it is identified that at least a portion of the plurality of first tags and the first attribute information included in the first feature information matches the plurality of third tags and the third attribute information included in the third feature information, the content is assigned to a group of recommendation content for the third user terminal, and the plurality of second tags and the plurality of third tags may be different subsets of the plurality of first tags. Effects of the invention

[0015] The present invention was devised to solve the aforementioned conventional problems. By analyzing the characteristics of various components within a content file using artificial intelligence and automatically generating multi-layered tag and attribute information based thereon, it automatically identifies key components according to content type (e.g., music, video, design, etc.) and assigns meaning-based tag and attribute information to each element, thereby overcoming the limitations of existing manual or keyword-based tagging methods.

[0016] The present invention allows for the simultaneous assignment of a single piece of content to multiple groups based on various tag combinations, thereby enabling content reclassification from various perspectives according to user purposes or corporate requirements.

[0017] The present invention enables the characteristics of content created by a creator to be accurately matched with the characteristics of content desired by a company through the analysis of the content data itself. Brief explanation of the drawing

[0018] FIG. 1 is an example diagram of the configuration of a system according to embodiments. FIG. 2 is a flowchart regarding a method for preprocessing data for various forms of content grouping according to embodiments. FIG. 3 is an example diagram regarding various groupings of data preprocessed content according to embodiments. FIG. 4 is a configuration diagram of an electronic device according to embodiments of the present invention. Specific details for implementing the invention

[0019] Hereinafter, embodiments are described in detail with reference to the attached drawings. However, various modifications may be made to the embodiments, and thus the scope of the patent application is not limited or restricted by these embodiments. It should be understood that all modifications, equivalents, and substitutions to the embodiments are included within the scope of the rights.

[0020] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed forms, and the scope of this specification includes modifications, equivalents, or substitutions that fall within the technical concept.

[0021] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0022] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or joined to that other component, or that there may be other components in between.

[0023] The terms used in the embodiments are for illustrative purposes only and should not be interpreted as intended to be limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as "comprising" or "having" are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0024] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments pertain. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0025] In addition, when describing with reference to the attached drawings, identical components are assigned the same reference numeral regardless of drawing symbols, and redundant descriptions thereof are omitted. In describing the embodiments, if it is determined that a detailed description of related prior art could unnecessarily obscure the essence of the embodiments, such detailed description is omitted.

[0026] The embodiments can be implemented in various forms of products such as personal computers, laptop computers, tablet computers, smartphones, televisions, smart home appliances, intelligent automobiles, kiosks, and wearable devices.

[0027] FIG. 1 is an exemplary configuration diagram of a system (100) according to embodiments of the present invention. The system (100) may be a system that operates an AI-based matching service between creators and companies based on various forms of content grouping and analysis of creators and companies.

[0028] Referring to FIG. 1, the system (100) may include an electronic device (110), creator terminals (120-1 to 120-m) and corporate representative terminals (130-1 to 130-n). The electronic device (110), creator terminals (120-1 to 120-m) and corporate representative terminals (130-1 to 130-n) may be connected via wired or wireless communication through a network (140).

[0029] According to embodiments, the electronic device (110) may be a server device that operates the platform of the service described above. The service may be operated through an application or through a website. In order to provide the service described above, the electronic device (110) may receive and store various information regarding creator terminals (120-1 to 120-m) and corporate representative terminals (130-1 to 130-n) that have registered as members of the service described above.

[0030] According to embodiments, the electronic device (110) may store profile information, history and portfolio information, survey response information, platform behavior log information, networking information, etc. of a creator possessing a creator terminal (120-1 to 120-m). Profile information may include name, occupation, career, education, skills, interests, etc. Additionally, history and portfolio information may include projects, works, career details, awards, etc. Additionally, platform behavior log information may include records of activity within the platform, such as post creation history, comment history, and like history. Additionally, networking information may include a friend list, followers, following, etc. within the platform of the aforementioned service. Additionally, the electronic device (110) may obtain survey response information by providing a survey to the creator terminal (120-1 to 120-m) for analyzing the creator, and by analyzing the survey response received from the creator terminal (120-1 to 120-m) using a generative language model specialized in a psychological model. Survey response information may include user tendencies, goals, preferences, etc., and user tendencies may include tendencies such as extraversion, agreeableness, conscientiousness, emotional stability, and openness.

[0031] According to the embodiments, the electronic device (110) can collect posts uploaded to homepages, communities, and news on the web (not shown) and perform RAG (search augmentation generative) processing. Additionally, the electronic device (110) can store corporate profile information and survey response information written by corporate representatives corresponding to corporate representative terminals (130-1 to 130-n). The electronic device (110) can obtain survey response information by providing a survey for analyzing a company to the corporate representative terminals (130-1 to 130-n) and analyzing the survey responses received from the corporate representative terminals (130-1 to 130-n) using a generative language model specialized for corporate analysis models. The survey response information may include information regarding corporate characteristics such as strategy, structure, system, shared values, technology, style, and employees.

[0032] The electronic device (110) can receive a file of content created by a creator, i.e., a content file, from a creator terminal (120-1 to 120-m). According to embodiments, a creator may refer to a creator of various cultural and artistic content, such as a video producer, video editor, singer-songwriter, fashion designer, or photographer, who is seeking work opportunities such as joining a company or participating in a project. The creator can upload the content file as their portfolio to the platform of the service of the present disclosure through the creator terminal (120-1 to 120-m).

[0033] According to the embodiments, the electronic device (110) may identify the type of content based on a received content file and perform preprocessing on the content data based on the identified type to obtain characteristics of the content components from the content data included in the content file. According to the embodiments, the electronic device (110) may perform data preprocessing to obtain characteristics of the components by extracting data to be analyzed from the content data, extracting features of the data to be analyzed, and generating feature information including a plurality of tags for the content and corresponding attribute information based on the extracted features. The type of content may include video, music, design, or photography. The components of the content are elements that form the content and may be used to obtain various characteristics of the content. According to the embodiments, by obtaining various characteristics of the components for a single content, different groupings may be performed on a single content according to the requirements of the corporate representative terminal (130-1 to 130-n). In addition, the components of the content may be set differently depending on the type of content. For example, if the type of content is music, the components of the content may include beat, melody, timbre, instruments, pitch of the instruments, chorus, and general parts. For example, if the type of content is video, the components of the content may include video purpose, shooting technique, video length, etc. In addition, a person skilled in the art may pre-set appropriate components according to the type of content, not limited to the examples described above. Furthermore, more components may be set for the content as needed, not limited to the examples described above, and as the number of types of components of the content increases, content that more accurately reflects the requirements of the corporate representative terminal (130-1 to 130-n) can be identified.

[0034] According to embodiments, when the electronic device (110) receives a recommendation content request from a corporate representative terminal (130-1 to 130-n), it may identify content corresponding to the recommendation content request among various content of a pre-stored creator terminal (120-1 to 120-m) and assign the identified content to a recommendation content group for the corporate representative terminal. According to embodiments, the recommendation content request may include at least one of a job posting, a project posting, or a creator recommendation request received from the corporate representative terminal (130-1 to 130-n). The electronic device (110) may determine a creator that matches the company among the creators corresponding to the content assigned to the recommendation content group, based on user tendencies, goals, and preferences identified from survey response information for the creator terminal (120-1 to 120-m) and information regarding corporate characteristics identified from survey response information for the corporate representative terminal (130-1 to 130-n), and provide the determined creator as a recommendation creator for the company.

[0035] Additionally, when the electronic device (110) receives a request for a recommendation announcement from a creator terminal (120-1 to 120-m), it can identify a job posting or project announcement among various job postings or project announcements received from a corporate representative terminal (130-1 to 130-n) that corresponds to the feature information of the content included in the portfolio information of the creator terminal (120-1 to 120-m), and assign the identified announcement to a recommendation announcement group for the creator terminal (120-1 to 120-m). The electronic device (110) can provide a job posting or project posting of the determined company as a recommended posting for the creator by determining a company that matches the creator among the companies corresponding to the posting assigned to the recommended posting group based on user tendencies, goals, and preferences identified from survey response information for the creator terminal (120-1 to 120-m) and information regarding corporate characteristics identified from survey response information for the corporate representative terminal (130-1 to 130-n).

[0036] According to the embodiments, the creator terminal (120-1 to 120-m) may be a terminal possessed by a creator seeking work opportunities, such as joining a company or participating in a project. According to the embodiments, the creator may be a creator of various cultural and artistic content, such as a video producer, video editor, singer-songwriter, fashion designer, or photographer. The creator terminal (120-1 to 120-m) may transmit a file of content created by the creator, i.e., a content file, to an electronic device (110) so that it is included in portfolio information. The creator terminal (120-1 to 120-m) may transmit a recommendation request to the electronic device (110) and receive a job posting or project posting from a company determined by the electronic device (110) to correspond to the creator terminal as a recommendation posting.

[0037] According to the embodiments, the corporate representative terminal (130-1 to 130-n) may be a terminal carried by a person in charge of corporate recruitment or seeking project personnel. The corporate representative terminal (130-1 to 130-n) may transmit a recommendation content request to the electronic device (110) including at least one of a recruitment notice, a project notice, or a creator recommendation request, and receive a creator determined by the electronic device (110) to correspond to the corporate representative terminal as a recommended creator for the company.

[0038] FIG. 2 is a flowchart relating to a method for preprocessing data for various forms of content grouping according to embodiments. The method of FIG. 2 can be performed by an electronic device (e.g., the electronic device (110) of FIG. 1, the electronic device (400) of FIG. 4).

[0039] Referring to FIG. 2, in step 201, the electronic device may receive a content file containing content data forming content from a first user terminal.

[0040] According to the embodiments, the first user terminal may be any one of the creator terminals (120-1 to 120-m). That is, the electronic device may receive content created by a creator corresponding to the creator terminal in the form of a digital file. According to the embodiments, the creator may refer to a person who is seeking work opportunities, such as joining a company or participating in a project, as a creator of various cultural and artistic content, such as a video producer, video editor, singer-songwriter, fashion designer, or photographer. The electronic device may include the content file received from the first user terminal in the portfolio information of the first user terminal and store it in a database.

[0041] In step 203, the electronic device can obtain a plurality of first tags corresponding to a plurality of tag names that are preset for the type of content from the electronic device's database. That is, the electronic device can identify the type of content based on the title, file format, etc. of the received content file and obtain a plurality of first tags corresponding to the type of content.

[0042] In this case, the tag name may correspond to the components of the content. That is, the electronic device may store in advance in a database a plurality of first tags corresponding to a plurality of components of the content according to the type of content. According to the embodiments, the type of content may include at least one of video, music, design, or photography. For example, if the type of content is music, the components of the content may include beat, melody, timbre, instrument, pitch of the instrument, chorus, and general part, and accordingly, a plurality of first tags may include beat, melody, timbre, instrument, pitch of the instrument, chorus, and general part. For example, if the type of content is video, the components of the content may include video purpose, shooting technique, and video length, and accordingly, a plurality of first tags may include video purpose, shooting technique, and video length. In addition, a person skilled in the art may pre-set appropriate components and corresponding tag names according to the type of content, without being limited to the examples described above.

[0043] In step 205, the electronic device can extract data to be analyzed from the content data based on the type of content. Specifically, the electronic device can extract data corresponding to the content as data to be analyzed by removing noise data that does not correspond to the content from the content data. For example, if the type of content is music, the electronic device can separate data that does not correspond to the music part and data that corresponds to the music part, which may exist before or after the music part within the content file. This extraction of data to be analyzed can be performed using a known technique that identifies data of interest according to the type of content.

[0044] In step 207, the electronic device can generate first attribute information corresponding to each of a plurality of first tags based on feature extraction of the data to be analyzed. Specifically, the electronic device can perform feature extraction on the data to be analyzed when it extracts the data to be analyzed from the content data. According to the embodiments, feature extraction on the data to be analyzed may be performed using existing data analysis software via an Application Programming Interface (API) method depending on the type of content. Alternatively, the electronic device may directly analyze the data to be analyzed of the content data according to the type of content. The electronic device can analyze attributes for each part of the content by generating an embedding vector for the data to be analyzed or by converting the data to be analyzed into waveform data. Through this feature extraction, the electronic device can generate first attribute information corresponding to each of the first tags, and the first attribute information may correspond to attribute values ​​for each of the first tags.

[0045] For example, if the type of content is music, attributes such as frequency, amplitude, and wavelength for each part of the music can be analyzed by generating an embedding vector for the data to be analyzed or by converting the data to be analyzed into waveform data. First attribute information corresponding to each of the first tags—beat, melody, timbre, instrument, pitch of the instrument, chorus, and general part—can be generated. For example, if the first tag is an instrument, the names of all instruments used in the music can be generated as first attribute information. For example, if the first tag is timbre, the type of the singer's timbre in the music can be generated as first attribute information. In the same way, first attribute information corresponding to each of the first tags can be generated for other types of content.

[0046] In step 209, the electronic device may generate and store in a database first feature information of content, comprising a plurality of first tags and first attribute information corresponding to each of the plurality of first tags. The electronic device may organize the plurality of first tags and the first attribute information corresponding to each of the plurality of first tags into a data set and store the said data set in a database as first feature information of content. At this time, the electronic device may associate the first feature information with a creator terminal and store it in a database as portfolio information corresponding to the creator terminal.

[0047] As described above, the present invention enables various forms of grouping for a single piece of content by performing data preprocessing, which involves extracting data to be analyzed from content data, extracting features of the data to be analyzed, and generating feature information including a plurality of tags for the content and corresponding attribute information based on the extracted features.

[0048] In step 211, when the electronic device receives a first recommendation content request from a second user terminal, it can extract second feature information including a plurality of second tags and second attribute information corresponding to each of the plurality of second tags from the first recommendation content request.

[0049] According to the embodiments, the second user terminal may be any one of the corporate representative terminals (130-1 to 130-n). The corporate representative may refer to a person in charge of corporate recruitment or seeking project personnel. Additionally, the recommendation content request may include at least one of a job posting, a project posting, or a creator recommendation request. The electronic device may extract second feature information including a plurality of second tags and second attribute information corresponding to each of the plurality of second tags from the first recommendation content request by analyzing the first recommendation content request through an artificial intelligence model.

[0050] More specifically, the electronic device may receive a first recommendation content request that includes at least one component-specific feature of the content desired by the company. For example, a job posting or project announcement may include text information stating that it is recruiting a creator who has a portfolio of content having at least one component-specific feature. For example, a creator recommendation request may include information such as, “Recommend a work that is similar to the uploaded artwork and uses pop colors,” or “The vocal tone I like is Justin Bieber. Recommend a singer-songwriter who makes medium-tempo songs that are similar to this.” The electronic device may perform preprocessing such as normalization, tokenization, and feature extraction on the text data of the first recommendation content request, and if there is a content file uploaded together, analyze the content file as described above, thereby extracting second feature information from the first recommendation content request that includes a plurality of second tags and second attribute information corresponding to each of the plurality of second tags.

[0051] In step 213, the electronic device can identify that at least some of the plurality of first tags and first attribute information included in the first feature information matches the plurality of second tags and second attribute information included in the second feature information. That is, since the first feature information for the content of the creator terminal is obtained by analyzing the content data itself, it may include all first tags and corresponding first attribute information corresponding to a plurality of tag names pre-set in relation to the content type. For example, if the content type is music, the first feature information may include first attribute information for beat, melody, timbre, instrument, pitch of the instrument, chorus, and all general parts. Meanwhile, the second feature information obtained from at least one of the text information or content file included in the first recommendation content request may include second tags and corresponding second attribute information corresponding to at least some of the tag names among the plurality of tag names corresponding to the content type. For example, if the content type is music, the second feature information may include only second attribute information for some of the beat, melody, timbre, instrument, pitch of the instrument, chorus, and general parts. The electronic device can identify that a plurality of second tags and second attribute information obtained by analyzing a first recommendation content request corresponds to at least a portion of a plurality of first tags and first attribute information included in the first feature information of specific content.

[0052] In step 215, the electronic device may assign content to a group of recommended content for the second user terminal. If the electronic device identifies content that includes a plurality of first tags and first attribute information included in the first feature information, and a plurality of second tags and second attribute information included in the first recommended content request, the electronic device may assign the content to a group of recommended content for the second user terminal.

[0053] According to the embodiments, the electronic device may receive a second recommendation content request from a third user terminal. That is, the electronic device may receive another second recommendation content request from a third user terminal, which is a corporate representative terminal different from the second user terminal. The electronic device may extract third feature information from the second recommendation content request, including a plurality of third tags and third attribute information corresponding to each of the plurality of third tags. If it is identified that at least a portion of the plurality of first tags and first attribute information included in the first feature information matches the plurality of third tags and third attribute information included in the third feature information, the electronic device may assign the content to a group of recommendation content for the third user terminal. In this case, the plurality of second tags and the plurality of third tags may be different subsets of the plurality of first tags. For example, even if both the second and third user terminals transmit requests for music recommendation content, the first recommendation content request may include second feature information including attribute information regarding beat, melody, timbre, instrument, and pitch of the instrument among the first tags, and the second recommendation content request may include third feature information including attribute information regarding timbre, instrument, and pitch of the instrument among the first tags. In this case, the same content may be simultaneously assigned to a group of recommendation content for different user terminals.

[0054] According to the embodiments, the electronic device may receive a second recommendation content request from a second user terminal. That is, the electronic device may receive another second recommendation content request from the second user terminal that transmitted the first recommendation content request. The electronic device may extract third feature information from the second recommendation content request, including a plurality of third tags and third attribute information corresponding to each of the plurality of third tags. The electronic device may identify tag names and attribute information that are common to each other among the plurality of second tags and second attribute information included in the second feature information and the plurality of third tags and third attribute information included in the third feature information. If it is identified that the tag names and attribute information that are common to each other match at least a part of the plurality of first tags and first attribute information included in the first feature information, the electronic device may assign the content to a group of recommendation content for the second user terminal. For example, if both the first and second recommendation content requests relate to music recommendations, the first recommendation content request may include second feature information including attribute information regarding beat, melody, timbre, instrument, and pitch of the instrument among the first tags, and the second recommendation content request may include third feature information including attribute information regarding timbre, instrument, and pitch of the instrument among the first tags, and the attribute information regarding timbre, instrument, and pitch of the instrument in the second and third feature information may have the same value. In this case, the timbre, instrument, pitch of the instrument, and the attribute information thereon may be identified by a common tag name and attribute information, and content having feature information including the corresponding tag and attribute information may be assigned to a group of recommendation content for the second user terminal.

[0055] As such, the present invention enables various groupings for a single piece of content by acquiring component-specific characteristics of the content itself, thereby enabling matching between creators and companies whose desired creative styles accurately match.

[0056] The process of generating attribute information corresponding to multiple tags based on the feature extraction of data as described above can be implemented according to the type of content using existing artificial intelligence models. Furthermore, it is obvious to a person skilled in the art that the process of analyzing text information and content files of recommendation content requests can also be implemented according to the type of content using existing artificial intelligence models. For example, the artificial intelligence model that analyzes text information of recommendation content requests is a generative artificial intelligence model and can be implemented using various publicly available large-scale language model APIs, such as GPT-4, Claude, LLaMA, and Alpaca. GPT-4, Claude, LLaMA, and Alpaca are composed of a transformer-based decoder structure and operate by receiving text referred to as a command (prompt) as input and outputting text. Therefore, although omitted from description in this specification, it is obvious to a person skilled in the art that various processes, such as indexing of sentences and representation as vectors, which are typically performed for data processing through widely known language models, can be additionally performed.

[0057] FIG. 3 is an example diagram regarding various groupings of data preprocessed content according to embodiments. Referring to FIG. 3, an electronic device may receive content files from Creator 1 and Creator 2, respectively, who have created content of the same type. The electronic device may obtain first feature information (310) by analyzing the content file received from Creator 1. The first feature information (310) may include attribute information such as aa, ba, ca, da, and ea for a plurality of tags A, B, C, D, and E, respectively. Additionally, the electronic device may obtain second feature information (320) by analyzing the content file received from Creator 2. The second feature information (320) may include attribute information such as aa, bb, ca, da, and ea for a plurality of tags A, B, C, D, and E, respectively.

[0058] Additionally, the electronic device may receive a first recommendation content request and a second recommendation content request (340) from Company 1, and may receive a third recommendation content request from Company 2. The first to third recommendation content requests may all be recommendation requests for types of content created by Creator 1 and Creator 2. The electronic device may obtain third feature information (330) by analyzing the first recommendation content request received from Company 1. The third feature information (330) includes attribute information for all of the plurality of tags A, B, C, D, and E, and may include attribute information such as aa, ba, ca, da, and ea, respectively. The electronic device may obtain fourth feature information (340) by analyzing the second recommendation content request received from Company 1. The fourth feature information (340) includes attribute information for all of the plurality of tags A, B, C, D, and E, and may include attribute information such as aa, ba, ca, da, and ec, respectively. The electronic device can obtain fifth feature information (350) by analyzing a third recommendation content request received from Enterprise 2. The fifth feature information (350) includes only attribute information for B, D, and E among a plurality of tags A, B, C, D, and E, and these may be ba, da, and ea, respectively.

[0059] In this case, multiple recommendation content requests are received from Company 1, and the third feature information (330) and the fourth feature information (340) may have aa, ba, ca, and da, which are common attribute information for tags A, B, C, and D. Since the first feature information (310) has attribute information aa, ba, ca, and da for tags A, B, C, and D and additionally has attribute information ea for tag E, all of the common attribute information of the third feature information (330) and the fourth feature information (340) is included in the first feature information (310). However, since the second feature information (320) has attribute information bb for tag B, all of the common attribute information of the third feature information (330) and the fourth feature information (340) is not included in the second feature information (320). Therefore, the electronic device can assign content created by Creator 1 to a group of recommendation content for Company 1.

[0060] Additionally, the fifth feature information (350) may have attribute information ba, da, and ea for tags B, D, and E. Since the first feature information (310) has attribute information ba, da, and ea for tags B, D, and E, and additionally has attribute information aa and ea for tags A and E, the fifth feature information (350) is included in the first feature information (310). However, since the second feature information (320) has attribute information bb for tag B, the fifth feature information (350) is not included in the second feature information (320). Therefore, the electronic device can also assign content created by Creator 1 to the group of recommended content for Company 2. In this way, by analyzing the characteristics of the content itself, the same content can be simultaneously assigned to the recommended content group for different companies, and the optimal content can be assigned for the needs of each company.

[0061] FIG. 4 is a configuration diagram of an electronic device according to embodiments of the present invention. The electronic device (400) may be included in the electronic device (110) of a system (100 of FIG. 1) for preprocessing data for various forms of content grouping according to the present invention, or the electronic device (110) may be included in the electronic device (400).

[0062] Referring to FIG. 4, the electronic device (400) may include a transceiver (410), a processor (420), and a memory (430). FIG. 4 illustrates only the components of the electronic device (400) related to the embodiment of the present disclosure. Therefore, it will be understood by those skilled in the art related to the present embodiment that other general components may be included in the electronic device in addition to the components illustrated in FIG. 4.

[0063] The transceiver (410) can establish a communication channel with an external device (e.g., creator terminal, corporate representative terminal, etc.) and transmit and receive various data with the external device. The transceiver (410) can transmit and receive relevant information by performing wired / wireless communication. The communication technologies used by the transceiver (410) may include, but are not limited to, GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), LTE (Long Term Evolution), 5G, WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Bluetooth (Bluetooth™), RFID (Radio Frequency Identification), Infrared Data Association (IrDA), ZigBee, NFC (Near Field Communication), etc.

[0064] The processor (420) can control the overall operation of the electronic device (400) and process data and signals. The processor (420) may be composed of at least one hardware unit. Additionally, the processor (420) may be operated by one or more software modules generated by executing program code stored in memory (430). The processor (420) can control the overall operation of the electronic device (400) and process data and signals by executing computer programs or instructions stored in memory (430). The processor (420) may be configured to perform the content relating to a method of preprocessing data for various forms of content grouping described throughout this disclosure.

[0065] The memory (430) may store program code and information necessary to execute a computer program for performing a method of preprocessing data for various forms of content grouping described throughout the present disclosure. The memory (430) may be volatile memory or non-volatile memory.

[0066] The database (440) can store various information. The database (440) can store multiple artificial intelligence models used to generate attribute information corresponding to multiple tags based on feature extraction of data under the control of the processor (420), analyze text information and content files of recommendation content requests, and store various data collected from homepages, communities, etc. Additionally, the database (440) can store training data for training these artificial intelligence models.

[0067] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0068] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0069] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0070] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0071] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 A method for tagging content data based on artificial intelligence, performed by an electronic device, comprising: receiving a content file containing content data forming content from a first user terminal; identifying the type of content based on the title and file format of the received content file and obtaining a plurality of first tags corresponding to the type of content; removing noise data from the content data and extracting data to be analyzed based on the type of content; generating first attribute information corresponding to each of the plurality of first tags based on the feature extraction of the data to be analyzed; and generating and storing in a database first feature information of the content including the plurality of first tags and the first attribute information corresponding to each of the plurality of first tags; when a first recommendation content request is received from a second user terminal, extracting second feature information including a plurality of second tags and second attribute information corresponding to each of the plurality of second tags from the first recommendation content request; and identifying that at least a portion of the plurality of first tags and the first attribute information included in the first feature information matches the plurality of second tags and the second attribute information included in the second feature information.A tag assignment method comprising the step of assigning the above content to a group of recommended content for the second user terminal, wherein the first user terminal is a creator terminal and the second user terminal is a corporate representative terminal, wherein the type of the content includes at least one of video, music, design, or photo, and when the type of the content is identified as music, the plurality of first tags include beat, melody, timbre, instrument, pitch of the instrument, chorus, and general part, wherein when one of the plurality of first tags is an instrument, the names of all instruments used in the content are generated as the first attribute information, and when one of the plurality of first tags is a timbre, the timbre of the singer included in the content is generated as the first attribute information. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 A tag assignment method according to claim 1, wherein when a second recommendation content request is received from a third user terminal, a third feature information including a plurality of third tags and third attribute information corresponding to each of the plurality of third tags is extracted from the second recommendation content request, and when it is identified that at least a portion of the plurality of first tags and the first attribute information included in the first feature information matches the plurality of third tags and the third attribute information included in the third feature information, the content is assigned to a group of recommendation content for the third user terminal, and the plurality of second tags and the plurality of third tags are different subsets of the plurality of first tags.

Images