Multilateral automatic matching method and system based on portfolio of individual creator

Abstract

According to the present invention, a multilateral automatic matching method, based on the portfolio of an individual creator, which is performed by an electronic device, comprises the steps of: acquiring, from a first user terminal of a creator, profile information, history information, portfolio information, platform behavior log information, and networking information about the creator; by using a first artificial intelligence model, acquiring feature information about each of one or more contents created by the creator and creation style information about the creator included in the portfolio information; by using a second artificial intelligence model, providing a plurality of surveys for analyzing the personality of the creator to the first user terminal and receiving a survey response for each of the plurality of surveys from the first user terminal; on the basis of the result of analyzing the received survey response by using the second artificial intelligence model, calculating a score for each of a plurality of personality elements that represent the personality of the creator; generating personality information about the creator on the basis of the score for each of the plurality of personality elements; associating the feature information about each content of the creator, the creation style information, the platform behavior log information, the networking information, and the personality information about the creator with the profile information and storing same in a database of the electronic device; on the basis of the feature information, the creation style information, the platform behavior log information, the networking information, and the personality information, determining, as recommendation information, at least one of recruitment information, a company, a project, a friend, or a mentor that matches the creator; providing the determined recommendation information to the first user terminal; and on the basis of the result of analyzing the survey response and feedback information about the recommendation information, updating a personality element list including the plurality of personality elements that represent the personality.

Description

Portfolio-based multi-party automatic matching method and system for individual creators

[0001] The present invention relates to a multi-party automatic matching method and system based on the portfolio of individual creators.

[0002] Existing recruitment platforms are currently structured entirely around text-based content, including job postings, resumes, and portfolios, in order to provide standardized recruitment services across various industries. This presents a problem in that such existing platforms are unsuitable for recruiting creators who produce content in diverse formats, such as video, music, design, and photography.

[0003] Furthermore, from the perspective of companies or project organizers, there was a problem in that hiring creators was difficult because they were traditionally recommended through personal connections, making it hard to recruit creators with content creation styles or personalities suitable for the specific work or company characteristics they intended to produce.

[0004] Furthermore, from the creators' perspective, there was a problem in that, due to the limitations of existing recruitment platforms, it was difficult to find opportunities to apply for companies or production projects suitable for their content creation style or personality, or to interact with other creators with similar styles and personalities and seek advice.

[0005] Therefore, a method is required to perform multilateral matching based on a creator's portfolio, which recommends other creators, companies, or projects to the creator based on a portfolio containing content created by the creator.

[0006] The present invention was devised to solve the aforementioned conventional problems, and its purpose is to enable automatic matching of other creators, companies, projects, etc., based on a creator's portfolio by considering characteristic information of the content included in the creator's portfolio and information on the creator's creative style.

[0007] The present invention aims to match other creators, companies, or projects that are suitable for both the creator's creative style and personality by analyzing not only the creator's portfolio but also personality elements, thereby enabling matching that considers both the characteristics of the creator's creative content and personality characteristics.

[0008] The purpose of the present invention is to enable more accurate matching in the matching of creators with recruitment information, companies, projects, friends, and mentors by continuously extracting personality elements that can serve as new consideration factors from survey responses and feedback information, and by customizing the list of personality elements by extracting personality elements that may be deemed unsuitable as consideration factors for matching.

[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.

[0010] According to embodiments of the present invention, a multi-party automatic matching method based on a personal creator's portfolio, performed by an electronic device, comprises: receiving profile information and portfolio information of the creator from a first user terminal of the creator; obtaining feature information of each of one or more contents created by the creator included in the portfolio information and creative style information of the creator using a first artificial intelligence model; providing a plurality of surveys for personality analysis of the creator to the first user terminal using a second artificial intelligence model and receiving survey responses for each of the plurality of surveys from the first user terminal; calculating a score for each of a plurality of personality elements representing the creator's personality based on the result of analyzing the received survey responses using the second artificial intelligence model; generating personality information of the creator based on the score for each of the plurality of personality elements; and storing the feature information of each of the creator's contents, the creative style information of the creator, and the personality information of the creator together with the profile information in a database of the electronic device. The method may include: determining at least one of recruitment information, a company, a project, a friend, and a mentor that match the creator as recommendation information based on the above feature information, the above creative style information, and the above personality information; providing the determined recommendation information to the first user terminal; and updating a list of personality elements including a plurality of personality elements representing the personality based on the results of analyzing the survey response and feedback information regarding the recommendation information.

[0011] According to embodiments of the present invention, feature information for each of the one or more contents can be obtained by analyzing features extracted from content data constituting each content.

[0012] According to embodiments of the present invention, the creative style information can be obtained based on calculating the similarity of feature information of each of the one or more contents.

[0013] According to embodiments of the present invention, a survey response for each of the plurality of surveys received from the first user terminal is composed of text information in the form of a sentence, and based on analyzing the text information in the form of a sentence, it can be identified which of the plurality of personality elements each survey response includes content regarding.

[0014] According to embodiments of the present invention, a portfolio-based multi-party automatic matching method for individual creators may further include: a step of identifying that the survey response contains content regarding personality elements different from the plurality of personality elements based on analyzing the sentence-form text information; and a step of obtaining personality elements output as a result of the clustering by performing AI-based clustering based on the identification of the content regarding the different personality elements.

[0015] According to embodiments of the present invention, a portfolio-based multi-party automatic matching method for an individual creator may further include: receiving feedback information regarding recommendation information from the first user terminal; identifying a personality element among the plurality of personality elements that exhibits a similarity level below a predetermined standard with respect to the recommendation information based on the feedback information; and determining the identified personality element as a personality element to be discarded when the plurality of feedback information is received that exhibits a similarity level below the predetermined standard with respect to the identified personality element.

[0016] According to embodiments of the present invention, the step of updating the personality element list may include the step of updating the personality element list based on at least one of adding a personality element output as a result of the clustering to the personality element list or discarding a personality element to be discarded from the personality element list.

[0017] According to embodiments of the present invention, the step of determining at least one of recruitment information, a company, a project, a friend, and a mentor that matches the creator as recommendation information may include the step of determining recommendation information that matches the creator based on content preference feature information, preferred creative style, or preferred personality information obtained by analyzing information regarding a plurality of recruitment information, a company, a project, a friend, and a mentor.

[0018] The present invention was devised to solve the aforementioned conventional problems, and by considering the characteristic information of the content included in the creator's portfolio and the creator's creative style information, it enables other creators, companies, projects, etc., to be automatically matched based on the creator's portfolio.

[0019] The present invention enables matching that considers both the characteristics of the creator's creative content and personality characteristics by analyzing not only the creator's portfolio but also personality elements, thereby allowing matching with other creators, companies, or projects that are suitable for both the creator's creative style and personality.

[0020] The present invention enables more accurate matching in the matching of creators with recruitment information, companies, projects, friends, and mentors by continuously extracting personality elements that can serve as new considerations from survey responses and feedback information, and by customizing the list of personality elements by extracting personality elements that may not be considered suitable for matching.

[0021] FIG. 1 is an example diagram of the configuration of a system according to embodiments.

[0022] FIG. 2 is a flowchart regarding a method for performing multi-party automatic matching based on a portfolio of individual creators according to embodiments.

[0023] FIG. 3 is an example diagram regarding the update of a list of personality elements according to embodiments.

[0024] FIG. 4 is a configuration diagram of an electronic device according to embodiments of the present invention.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or coupled with that other component, or that there may be other components in between.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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 multilateral automatic matching based on individual creators' portfolios.

[0034] 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).

[0035] 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.

[0036] According to embodiments, the electronic device (110) may store profile information, history information, portfolio information, survey response information, platform behavior log information, networking information, etc. of a creator possessing a creator terminal (120-1 to 120-m). According to embodiments, a creator may refer to a person seeking work opportunities, such as employment in a company or participation 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. Profile information may include name, occupation, career, education, skills, interests, etc. Additionally, history information may include career details, awards, etc., and portfolio information may include content such as projects, works, 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) can obtain survey response information by providing a survey to a creator terminal (120-1 to 120-m) for analyzing the creator's personality and analyzing the survey responses received from the creator terminal (120-1 to 120-m) using a generative language model specialized in a psychological model. The survey response information may include user tendencies, and user tendencies may include multiple personality elements such as extraversion, agreeableness, conscientiousness, emotional stability, and openness. The electronic device (110) can generate the creator's personality information based on multiple personality elements.

[0037] The electronic device (110) can perform data preprocessing on text data of a creator's profile information, history information, portfolio information, survey response information, platform behavior log information, and networking information. Specifically, the electronic device (110) can normalize and refine the text data of each piece of information, tokenize the text data using natural language processing techniques, and extract features such as keywords and topics from the tokenized text data. It will be obvious to a person skilled in the art that preprocessing, including normalization, refinement, tokenization, and feature extraction of text data as described above, can be performed using known techniques.

[0038] 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.

[0039] The electronic device (110) can perform data preprocessing on text data of corporate profile information and survey response information. Specifically, the electronic device (110) can normalize and refine the text data of each piece of information, tokenize the text data using natural language processing techniques, and extract features such as keywords and topics from the tokenized text data. It will be obvious to a person skilled in the art that preprocessing, including normalization, refinement, tokenization, and feature extraction of text data as described above, can be performed using known techniques.

[0040] 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). The creator uploads 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), and these contents may be included in portfolio information. According to embodiments, the electronic device (110) can identify the type of content based on the 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 embodiments, the electronic device (110) can perform data preprocessing to obtain characteristics of the components by extracting data to be analyzed from the content data, extracting characteristics 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 characteristics.

[0041] According to the embodiments, the type of content may include video, music, design, or photography. The components of the content serve as elements that form the content and can be used to obtain various characteristics of the content. According to the embodiments, by obtaining characteristics for each component of a single piece of content, feature information of the content can be obtained. Furthermore, 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, without being limited to the examples described above. Furthermore, more components may be set for the content as needed, without being limited to the examples described above; as the number of types of content components increases, the creator's creative style can be analyzed more finely, thereby allowing the requirements of both the creator and the company representative to be reflected more accurately.

[0042] According to the embodiments, the electronic device (110) can obtain creative style information of a creator based on feature information of each content. Additionally, the electronic device (110) can determine at least one of job information, companies, projects, friends, and mentors that match the creator as recommendation information based on feature information of each content, creative style information, and personality information. Additionally, the electronic device (110) can continuously update a list of personality elements including multiple personality elements based on the results of analyzing survey responses and the creator's feedback information regarding the recommendation information.

[0043] According to the embodiments, the creator terminal (120-1 to 120-m) may be a terminal possessed by a creator who is seeking work opportunities, such as joining a company or participating in a project, or who wishes to interact with other creators. According to the embodiments, the creator may be a creator of various cultural and artistic content, such as a video producer, a video editor, a singer-songwriter, a fashion designer, or a photographer.

[0044] 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.

[0045] FIG. 2 is a flowchart relating to a method for performing multi-party automatic matching based on a portfolio of individual creators according to embodiments. The method of FIG. 2 may be performed by an electronic device (e.g., the electronic device of FIG. 1 (110), the electronic device of FIG. 4 (400)).

[0046] Referring to FIG. 2, in step 201, the electronic device can obtain the creator's profile information, history information, portfolio information, platform behavior log information, and networking information from the creator's first user terminal.

[0047] According to the embodiments, a creator may refer to a person 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. Profile information may include the creator's name, occupation, career, education, skills, interests, etc. Additionally, history information may include 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, portfolio information may include content such as projects, works, etc. That is, the electronic device may receive content created by the creator as a content file in the form of a digital file, include it in the portfolio information of the first user terminal, and store it in a database.

[0048] In step 203, the electronic device can use the first artificial intelligence model to obtain feature information for each of one or more contents created by the creator included in the portfolio information and the creator's creative style information.

[0049] More specifically, the electronic device may obtain a plurality of first tags corresponding to a plurality of tag names pre-set for the type of content from the electronic device's database. That is, the electronic device may identify the type of content based on the title, file format, etc., of a received content file and obtain a plurality of first tags corresponding to the type of content. At this time, the tag names may correspond to the components of the content. That is, the electronic device may pre-store a plurality of first tags corresponding to a plurality of components of the content for each type of content in the database. 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, the 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 the purpose of the video, the filming technique, and the length of the video, and accordingly, a plurality of first tags may include the purpose of the video, the filming technique, and the length of the video. In addition, a person skilled in the art is not limited to the examples described above and may pre-set appropriate components and corresponding tag names according to the type of content.

[0050] An electronic device can extract data to be analyzed from 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 known techniques that identify data of interest according to the type of content.

[0051] Additionally, 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 for each type of content. The electronic device can analyze the attributes of each part of the content by generating an embedding vector for the data to be analyzed and inputting it into a first artificial intelligence model. The first artificial intelligence model can be trained to classify which attribute group the features of the components of the content belong to based on the attribute values ​​of the set of embedding vectors, and the attribute group output as a classification result can become the attribute information of the corresponding tag. Through this feature extraction, the electronic device can generate first attribute information corresponding to each of the first tags, and the first attribute information can correspond to the attribute group according to the attribute value for each of the first tags.

[0052] According to the embodiments, the first artificial intelligence model may be, for example, one of a deep neural network, a convolutional neural network, a recurrent neural network, a reinforcement learning model, or a machine learning model for classification-regression analysis, and may be implemented using algorithms such as a supervised learning method such as SVM (support vector machine) and a clustering method such as k-NN (k-Nearest Neighbor), but is not limited thereto and may be appropriately selected by a person skilled in the art.

[0053] 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 beat, the beat type of 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.

[0054] According to embodiments, an electronic device may generate first feature information of content, comprising a plurality of first tags and first attribute information corresponding to each of the plurality of first tags. Such feature information may be obtained for each of one or more contents included in portfolio information. Additionally, by calculating the similarity of attribute information by tag between one or more contents, the electronic device may obtain creative style information of the corresponding creator based on tags and attribute information where the similarity is greater than or equal to a predetermined value. For example, if it is identified that among a plurality of music contents created by a specific creator, a predetermined proportion or more has identical attribute information for instrument and beat tags, the electronic device may determine that the similarity of attribute information for instrument and beat tags between contents satisfies a predetermined criterion and include the identified attribute information for instrument and beat tags in the creative style information of the corresponding creator. For example, if the preset ratio is 70%, and among the 5 music contents included in the creator's portfolio information, the instrument tag attribute information of 4 music contents is piano and the tempo tag attribute information is medium tempo, then the similarity of the attribute information satisfies the preset criteria, so the tag and attribute information can be determined as the creator's creative style information.

[0055] In step 205, the electronic device may use a second artificial intelligence model to provide a plurality of surveys to the first user terminal for analyzing the creator's personality and receive survey responses for each of the plurality of surveys from the first user terminal. According to embodiments, the electronic device may use a generative language model to provide a plurality of surveys composed of text information in the form of sentences to the first user terminal and receive each survey response composed of text information in the form of sentences from the first user terminal. According to embodiments, the second artificial intelligence model is a generative artificial intelligence model and may be implemented using various types of publicly available large-scale language model APIs. For example, the second artificial intelligence model may be implemented using GPT-4, Claude, LLaMA, Alpaca, etc. GPT-4, Claude, LLaMA, and Alpaca, etc. are composed of a transformer-based decoder structure and operate by receiving text referred to as a command (prompt) and outputting text. Therefore, although omitted from description in this specification, it will be 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, may be additionally performed.

[0056] In step 207, the electronic device can calculate a score for each of a plurality of personality elements representing the creator's personality based on the results of analyzing the received survey response using the second artificial intelligence model. According to embodiments, the electronic device can identify which of the plurality of personality elements each survey response contains content about by tokenizing and analyzing the survey response, which consists of text information in the form of sentences. According to embodiments, the plurality of personality elements may include user tendencies such as extraversion, agreeableness, conscientiousness, emotional stability, and openness. That is, for each survey response of the creator, the electronic device can identify which of the personality elements—extraversion, agreeableness, conscientiousness, emotional stability, and openness—the response relates to, and calculate a score for the corresponding personality element. According to embodiments, each personality element may include a first tendency and a second tendency that are opposite to each other. For example, in the case of a personality element called extraversion, the first tendency may be introversion and the second tendency may be extraversion. The electronic device can identify the number of keywords corresponding to the first tendency or the second tendency in the survey response. In this case, the first tendency may be set to 0 points and the second tendency may be set to 10 points, and the tendency for each personality element of the creator may be calculated within the range of 0 to 10 points. Such scores are merely examples for illustrative purposes and are not limited thereto.

[0057] In step 209, the electronic device may generate personality information of a creator based on scores for each of a plurality of personality elements. The personality information may include the names of the plurality of personality elements and scores calculated for each of the plurality of personality elements. For example, the personality information of a specific creator may consist of extraversion 6 points, agreeableness 8 points, conscientiousness 2 points, emotional stability 3 points, and openness 7 points.

[0058] In step 211, the electronic device may store characteristic information of each of the creator's content, information on the creator's creative style, platform behavior log information, networking information, and personality information of the creator in association with profile information in the electronic device's database. The characteristic information of each of the content, creative style information, and personality information are as described in steps 203 and 209. According to the embodiments, the profile information may include name, occupation, career, education, skills, interests, etc. The platform behavior log information may include records of activity within the platform, such as post creation history, comment history, and like history. Additionally, the networking information may include a list of friends, followers, following, etc., within the platform of the aforementioned service.

[0059] In step 213, the electronic device can determine at least one of job information, companies, projects, friends, and mentors that match the creator as recommendation information based on feature information, creative style information, platform behavior log information, networking information, and personality information.

[0060] According to the embodiments, the electronic device can determine a job posting, company, or project that matches a creator based on feature information, creative style information, and personality information of each piece of content. By performing an analysis of text information of job postings and project announcements uploaded to a platform, and web information of the company that uploaded the job postings and project announcements, the electronic device can determine preferred feature information regarding the content in the job postings and project announcements, preferred creative style information regarding the creator, and preferred personality information in the corresponding job postings or project announcements. The electronic device can perform matching based on known similarity calculations and graph theory. That is, the electronic device can set the creator, job posting, company, and project as nodes, respectively, and perform matching between the creator and the job posting, company, and project by calculating the similarity between the characteristic information, creative style information, and personality information of each of the creator's content and the preferred feature information, preferred creative style information, and personality information of the job posting and project announcement. Through this, the electronic device can determine a job posting, company, or project that matches the characteristic information, creative style information, and personality information of each of the creator's content among a plurality of job postings, companies, and projects.

[0061] According to the embodiments, the electronic device can determine another creator matched with a creator as a friend or mentor based on feature information, creative style information, platform behavior log information, networking information, and personality information. The electronic device can acquire the feature information, creative style information, platform behavior log information, networking information, and personality information of multiple creators registered on a platform, and perform a similarity calculation with the creator's feature information, creative style information, platform behavior log information, networking information, and personality information by assigning weights to each of the information. The electronic device can perform matching based on known similarity calculations and graph theory. That is, the electronic device can set the creators as nodes and perform creator-to-creator matching by calculating the similarity between the creators' feature information, creative style information, platform behavior log information, networking information, and personality information. Through this, the electronic device can determine another creator among multiple creators as a friend or mentor that matches the feature information, creative style information, platform behavior log information, networking information, and personality information of each of the creator's contents. Whether to recommend as a friend or a mentor can be set as necessary. For example, the electronic device can check the career and job title in the profile information of other creators matched to the creator, and decide whether to recommend them as a friend or a mentor by comparing them with the creator's career and job title.

[0062] In step 215, the electronic device may provide the determined recommendation information to the first user terminal. That is, the electronic device may transmit job information, companies, projects, friends, and mentors matched with the creator as recommendation information to the first user terminal possessed by the creator.

[0063] In step 217, the electronic device can update a list of personality elements including multiple personality elements representing personality based on the results of analyzing survey responses and feedback information on recommendation information.

[0064] According to the embodiments, the electronic device can identify that the survey response contains content regarding personality elements different from a plurality of personality elements based on analyzing text information in the form of sentences constituting the survey response. Additionally, the electronic device can obtain personality elements output as a result of clustering by performing AI-based clustering based on the identification of content regarding different personality elements. According to the embodiments, the electronic device can receive feedback information regarding recommendation information from a first user terminal and, based on the feedback information, identify personality elements among a plurality of personality elements that exhibit a similarity level below a predetermined threshold with respect to the recommendation information. Additionally, if a plurality of feedback information is received in which the identified personality elements exhibit a similarity level below a predetermined threshold, the electronic device can determine the identified personality elements as personality elements to be discarded. According to the embodiments, the electronic device can update the personality element list based on at least one of adding personality elements output as a result of clustering to the personality element list or discarding personality elements to be discarded from the personality element list.

[0065] According to the embodiments, when the electronic device analyzes text information in the form of sentences constituting the survey response in step 207, it can identify from the result that the response contains content regarding a personality element different from a plurality of pre-set personality elements. The database of the electronic device may store not only the names of the plurality of pre-set personality elements but also the names of various personality elements, and may store a large dataset of keywords corresponding to each personality element. Through this, the electronic device can identify cases where content regarding a personality element other than the plurality of pre-set personality elements is included in the survey response. According to the embodiments, the electronic device can obtain the personality element output as a result of clustering by performing AI-based clustering based on the identification of content regarding a different personality element. That is, if the survey response contains content regarding a personality element other than the plurality of pre-set personality elements, the electronic device may wait for statistical processing until survey response data containing that other personality element is accumulated. When a sufficient amount of survey response data is accumulated, the electronic device may determine that the other personality element as a new personality element to be added to the list of personality elements and add it to the list of personality elements. For example, if multiple pre-set personality elements are extraversion, agreeableness, conscientiousness, emotional stability, and openness, other personality elements such as honesty and humility may be identified in the survey responses in addition to these elements. These other personality elements may be added to the list of personality elements when a sufficient amount of data is accumulated.

[0066] According to the embodiments, the electronic device may receive feedback information from the first user terminal regarding the recommendation information provided in step 215. The feedback information may include text information in the form of sentences. If the creator determines that any of the job information, companies, projects, friends, or mentors provided as recommendation information is not suitable for them, the electronic device may receive from the first user terminal the reason in the form of a sentence why the creator determined that the recommendation information was not suitable. The electronic device may analyze the text information in the form of sentences constituting the feedback information to extract personality elements that received negative feedback from the feedback information, and may identify the extracted personality elements as having a similarity level below a predetermined standard with respect to the recommendation information. According to the embodiments, the electronic device may obtain personality elements output as a result of clustering by performing AI-based clustering based on the identification of personality elements that have a similarity level below a predetermined standard. That is, the electronic device may wait for feedback information containing personality elements that received negative feedback to accumulate for statistical processing. When a sufficient amount of feedback information is accumulated, the electronic device may determine that the corresponding personality element is not suitable as a consideration factor for matching and determine it as a personality element to be discarded from the list of personality elements. For example, if multiple pre-set personality elements are extraversion, agreeableness, conscientiousness, emotional stability, and openness, negative feedback regarding emotional stability can be identified in the feedback information. If enough negative feedback information regarding emotional stability accumulates, the electronic device may determine that emotional stability is not an important factor for performing matching and discard it from the list of personality elements.

[0067] FIG. 3 is an example diagram regarding the update of a list of personality elements according to embodiments.

[0068] Referring to FIG. 3, the electronic device can generate personality information of a creator based on a list of personality elements (310) composed of a plurality of preset personality elements A, B, C, D, E, and F, and provide recommendation information that matches the creator. If the electronic device analyzes a survey response received from the creator's user terminal, the electronic device can identify that the survey response contains content regarding personality element G, which is not included in the list of personality elements (310). The electronic device accumulates survey response data containing content regarding personality element G whenever it receives it, and when a predetermined amount of survey response data is accumulated, the electronic device can add personality element G to the list of personality elements. Accordingly, the list of personality elements (310) can be updated to a list of personality elements (320) containing a plurality of personality elements A, B, C, D, E, F, and G.

[0069] Meanwhile, the electronic device may receive feedback information after providing recommendation information to the user terminal. At this time, the feedback information may include negative feedback regarding personality element D. The electronic device may identify that there is negative feedback regarding personality element D in the feedback information and may accumulate feedback information containing negative feedback regarding personality element D whenever it receives it. When a predetermined amount of feedback information is accumulated, the electronic device may determine that personality element D is not suitable as a consideration for matching and may discard it from the list of personality elements. Accordingly, the list of personality elements (310) may be updated to a list of personality elements (330) including multiple personality elements A, B, C, E, and F.

[0070] Meanwhile, the electronic device may receive both survey responses containing content regarding personality element G that is not included in the personality element list (310) and feedback information containing negative feedback regarding personality element D. In this case, the electronic device may accumulate the survey response data containing content regarding personality element G and the feedback information containing negative feedback regarding personality element D whenever it receives them. When a predetermined amount of information is accumulated, the electronic device may add personality element G to the personality element list and discard personality element D. Accordingly, the personality element list (310) may be updated to a personality element list (340) containing multiple personality elements A, B, C, E, F, and G.

[0071] In this way, the present invention can customize the list of personality elements for more accurate matching by continuously updating the list of personality elements through the extraction of personality elements that may become new consideration factors from survey responses and feedback information, and the extraction of personality elements that may not be considered suitable as consideration factors for matching.

[0072] 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 performing multi-party automatic matching based on a portfolio of an individual creator according to the present invention, or the electronic device (110) may be included in the electronic device (400).

[0073] 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.

[0074] 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.

[0075] 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 regarding the method of performing multi-party automatic matching based on the portfolio of individual creators described throughout this disclosure.

[0076] Memory (430) may store program code and information necessary to execute a computer program for performing a method of performing multi-party automatic matching based on a portfolio of individual creators described throughout this disclosure. Memory (430) may be volatile memory or non-volatile memory.

[0077] The database (440) can store various information. The database (440) can store multiple artificial intelligence models used to generate feature information of content, provide surveys, and receive and analyze survey responses under the control of the processor (420), and can store various data collected from homepages, communities, etc. Additionally, the database (440) can store training data for training these artificial intelligence models.

[0078] 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.

[0079] 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.

[0080] 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.

[0081] 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.

[0082] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

1. A multi-party automatic matching method based on an individual creator's portfolio, performed by an electronic device, A step of obtaining the creator's profile information, history information, portfolio information, platform behavior log information, and networking information from the creator's first user terminal; A step of obtaining feature information for each of one or more contents created by the creator included in the portfolio information and creative style information of the creator using a first artificial intelligence model; A step of using a second artificial intelligence model to provide a plurality of surveys for personality analysis of the creator to the first user terminal, and receiving survey responses for each of the plurality of surveys from the first user terminal; A step of calculating a score for each of a plurality of personality elements representing the personality of the creator based on the result of analyzing the received survey response using the second artificial intelligence model; A step of generating personality information of the creator based on scores for each of the plurality of personality elements; A step of associating characteristic information of each of the creator's content, creative style information of the creator, platform behavior log information, networking information, and personality information of the creator with profile information and storing them in a database of the electronic device; A step of determining at least one of job information, companies, projects, friends, and mentors that match the creator as recommendation information based on the above feature information, the above creative style information, the above platform behavior log information, and the above personality information; A step of providing the above-determined recommendation information to the first user terminal; and A method comprising the step of updating a list of personality elements including a plurality of personality elements representing the personality based on the results of analyzing the above survey responses and feedback information regarding the above recommendation information.

2. In Paragraph 1, The feature information of each of the above one or more contents is obtained by analyzing the features extracted from the content data constituting each content, and A method in which the above-mentioned creative style information is obtained based on calculating the similarity of each of the above-mentioned feature information of one or more of the content.

3. In Paragraph 2, The survey response for each of the plurality of surveys received from the first user terminal is composed of text information in the form of a sentence, and A method for identifying which of the plurality of personality elements each survey response contains based on the analysis of the above-mentioned sentence-form text information.

4. In Paragraph 3, A step of identifying, based on analyzing the text information in the form of the sentence above, that the survey response contains content regarding personality elements different from the plurality of personality elements; and A method further comprising the step of obtaining a personality element output as a result of said clustering by performing AI-based clustering based on the identification of the content regarding the different personality elements above.

5. In Paragraph 4, A step of receiving feedback information regarding the recommendation information from the first user terminal; A step of identifying a personality element among the plurality of personality elements that exhibits a similarity level below a predetermined standard with respect to the recommendation information based on the feedback information; and A method further comprising the step of determining the identified personality element as a personality element to be discarded when a plurality of feedback information is received in which the identified personality element indicates a similarity level below a predetermined standard.

Images