KR102155342B1 - System for providing multi-parameter analysis based commercial service using influencer matching to company - Google Patents

Abstract

The present invention relates to a system for providing an advertising service using multi-parameter analysis-based influencer matching. The present invention includes: at least one influencer terminal having a plurality of numbers of subscribers and uploading content; an advertiser terminal requesting influencer advertising and receiving the result of matching with the at least one influencer terminal; and an advertising service providing server including a building unit building a manpower pool by collecting the content of the at least one influencer terminal, the quality of the content, the psychological code of a content subscriber, and influencer data, an analysis unit storing an analysis result in the manpower pool through preprocessing and analysis of big data corresponding to the manpower pool, a calculation unit calculating the degree of matching between advertising request information transmitted from the advertiser terminal and at least one influencer in the analyzed manpower pool, and a transmission unit transmitting the matching result listed up based on the degree of matching calculated from the calculation unit to the advertiser terminal.

Description

Advertisement service provision system using influencer matching based on multi-parameter analysis {SYSTEM FOR PROVIDING MULTI-PARAMETER ANALYSIS BASED COMMERCIAL SERVICE USING INFLUENCER MATCHING TO COMPANY}

The present invention relates to an advertisement service providing system using influencer matching based on multi-parameter analysis, and provides qualitative data by providing not only quantitative data, but also matching through multiple parameters including content, quality, psychological code, and propensity analysis. It provides a platform that provides optimized recommendations based on it.

Advertising refers to the act of unilaterally communicating opinions through the media in an effort by an advertiser to change the attitude of the audience who encounters the advertisement. In other words, it has the meaning of spreading. The development of the Internet continued the development of the advertising industry. With the spread of high-speed Internet, broadband communication network, and advancement of streaming technology, two-way ordering became possible, and new advertisement types such as mobile and influencers appeared. Influencers are users who already have fixed followers, so it is easy to attract other consumers, and they have a kind of fandom through various social media, so companies can acquire potential customers and conduct marketing. While most of the existing corporate marketing focuses on securing new customers and consumers, penetration marketing is a method of differential marketing that penetrates the minds of customers based on existing customers and connects them with new customers.

At this time, a method of mediating an influencer and an advertiser was researched and developed. In this regard, Korean Patent Publication No. 2019-0075585 (published on July 1, 2019), which is a prior art, discloses an influencer based on the input basic information. The composition of registering an unspeaker, the composition of collecting the activity information of each influencer by crawling the content posted by the registered influencer by platform, each influencer based on the basic information and the collected activity information and advertisement history information Influencers matching the advertiser's target product are extracted and transmitted to the advertiser's client when the advertiser's activity is analyzed to generate analysis information, and the influencer's advertising activity results A configuration for receiving monitoring information from a monitoring code embedded in the posted advertisement content by monitoring is disclosed.

However, the above-described configuration simply performs textual matching between the product and the influencer's activity information, and does not consider various factors such as the influencer's content, the content quality, and the influencer's follower's psychological code. Matching cannot be made, and simple term matching or word matching does not require an accurate analysis of why followers follow influencers, as well as a superficial matching method that does not help at all when advertisers choose influencers. It is only. Therefore, in addition to simple term matching, research and development of a matching method in consideration of parameters required when an advertiser selects an influencer is required.

According to an embodiment of the present invention, the influencer is not divided only by the number of subscribers, but the analysis result of the content uploaded by the influencer, the analysis result of the content quality, and the subscriber continuously subscribes to the content of the influencer. By in-depth analysis using the results of analysis such as psychological motives and reasons, influencers' disposition or issues, etc., not only quantitative data but also qualitative data can be accurately matched with multiple parameters. A method of providing advertisement service using influencer matching based on multi-parameter analysis, which helps both influencers and advertisers to select the desired advertisement and desired advertisement model by not superficially connecting the influencer and the advertiser by matching or category matching Can provide. However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention has a plurality of subscribers, at least one influencer terminal for uploading content, requesting an influencer advertisement, and at least one The advertiser terminal receiving the result matched with the influencer terminal of, and the content of at least one influencer terminal, the quality of the content, the psychological code of the subscriber who subscribes to the content, and the data of the influencer are collected The construction unit that builds the pool, the analysis unit that stores the analysis results in the manpower pool through pre-processing and analysis of big data corresponding to the manpower pool, the advertisement request information transmitted from the advertiser terminal, and included in the analyzed manpower pool And a calculation unit that calculates a matching degree between at least one influencer and a transmission unit that transmits a matching result listed based on the matching degree calculated from the calculation unit to an advertiser terminal.

According to any one of the above-described problem solving means of the present invention, the influencer is not divided only by the number of subscribers, but the analysis result of the content uploaded by the influencer, the analysis result of the quality of the content, the subscriber is the influencer. By in-depth analysis using analysis results such as psychological motives and reasons for continuously subscribing to the contents of, influencers' disposition or issues, it is possible to accurately match not only quantitative data but also qualitative data with multiple parameters. , By not connecting the influencer and the advertiser superficially by matching a simple word or keyword or matching a category, both the influencer and the advertiser can select the desired advertisement and the desired advertisement model. Matching inclinations, etc. allows each other to win-win and be satisfied.

1 is a diagram for explaining an advertisement service providing system using influencer matching based on multi-parameter analysis according to an embodiment of the present invention.
2 is a block diagram illustrating an advertisement service providing server included in the system of FIG. 1.
3 is a diagram for explaining an embodiment in which an advertisement service using influencer matching based on multi-parameter analysis is implemented according to an embodiment of the present invention.
4 is a diagram illustrating a process of transmitting and receiving data between components included in the advertisement service providing system using influencer matching based on multi-parameter analysis of FIG. 1 according to an embodiment of the present invention.
5 is a flowchart illustrating a method of providing an advertisement service using influencer matching based on multi-parameter analysis according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are assigned to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included, and one or more other features, not excluding other components, unless specifically stated to the contrary. It is to be understood that it does not preclude the presence or addition of any number, step, action, component, part, or combination thereof.

The terms "about", "substantially" and the like, as used throughout the specification, are used in or close to the numerical value when manufacturing and material tolerances specific to the stated meaning are presented, and are used in the sense of the present invention. To assist, accurate or absolute figures are used to prevent unfair use of the stated disclosure by unscrupulous infringers. As used throughout the specification of the present invention, the term "step (to)" or "step of" does not mean "step for".

In the present specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized using two or more hardware, or two or more units may be realized using one hardware.

In this specification, some of the operations or functions described as being performed by the terminal, device, or device may be performed instead in a server connected to the terminal, device, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed by a terminal, device, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means mapping or matching the unique number of the terminal or the identification information of the individual, which is the identification information of the terminal. Can be interpreted as.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram for explaining an advertisement service providing system using influencer matching based on multi-parameter analysis according to an embodiment of the present invention. Referring to FIG. 1, an advertisement service providing system 1 using influencer matching based on multi-parameter analysis includes at least one influencer terminal 100, an advertisement service providing server 300, and at least one advertiser terminal ( 400) may be included. However, since the advertisement service providing system 1 using influencer matching based on multi-parameter analysis of FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1.

In this case, each component of FIG. 1 is generally connected through a network 200. For example, as shown in FIG. 1, at least one influencer terminal 100 may be connected to an advertisement service providing server 300 through a network 200. In addition, the advertisement service providing server 300 may be connected to at least one influencer terminal 100 and at least one advertiser terminal 400 through the network 200. In addition, at least one advertiser terminal 400 may be connected to the advertisement service providing server 300 through the network 200.

Here, the network refers to a connection structure in which information exchange is possible between respective nodes such as a plurality of terminals and servers, and examples of such networks include RF, 3rd Generation Partnership Project (3GPP) network, and Long Term (LTE). Evolution) network, 5GPP (5th Generation Partnership Project) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network) , Personal Area Network (PAN), Bluetooth (Bluetooth) network, NFC network, satellite broadcasting network, analog broadcasting network, Digital Multimedia Broadcasting (DMB) network, and the like, but are not limited thereto.

In the following, the term “at least one” is defined as a term including the singular number and the plural number, and even if the term “at least one” does not exist, each component may exist in the singular or plural, and may mean the singular or plural. It will be self-evident. In addition, it will be possible to change according to the embodiment that each component is provided in a singular or plural.

The at least one influencer terminal 100 may be a terminal of an influencer that is matched with an advertiser using an advertisement service related web page, app page, program, or application using influencer matching based on multi-parameter analysis. . And, when the advertisement content is produced according to the selection of the advertiser after matching with the advertiser, the at least one influencer terminal 100 transmits real-time streaming and response data of the produced content to the advertisement service providing server 300 It may be a terminal that transmits to or allows access. In addition, the at least one influencer terminal 100 transmits original content other than advertisement content, that is, metadata about the content when an influencer uploads a video other than advertisement, to the advertisement service providing server 300. It may be a terminal that provides an input value to construct big data and create a manpower pool in the advertisement service providing server 300 by transmitting.

Here, at least one influencer terminal 100 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like. In this case, the at least one influencer terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one influencer terminal 100, for example, as a wireless communication device that is guaranteed portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular ), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smart phone (smartphone), smart pad (smartpad), can include all kinds of handheld (Tablet PC) based wireless communication devices such as.

The advertisement service providing server 300 may be a server that provides an advertisement service web page, an app page, a program, or an application using influencer matching based on multi-parameter analysis. In addition, the advertisement service providing server 300 collects content uploaded from at least one influencer terminal 100, metadata of the content, the number of subscribers, responses and reviews of subscribers, and a plurality of tags, and collects raw data (Raw Data) may be collected. In addition, the advertisement service providing server 300 analyzes the structured data, unstructured data and semi-structured data included in the collected raw data to analyze the content itself, the degree of quality and the type of quality that the content is completed, and the subscriber Analyzes psychological codes such as the reason for continuing to subscribe to the influencer's content and the reason for liking the influencer, and analyzes the influencer's own propensity, qualities, and history, and uses multiple parameters for influencer and content, etc. It may be a server that builds the result of analyzing the data into big data. In addition, the advertisement service providing server 300, from at least one advertiser terminal 400, advertiser's propensity, advertisement target object information, brand image or pursuit direction, psychological code of loyalty customers loyal to the brand, brand advertisement It may be a server that performs a preliminary task for matching by collecting data based on the same or similar analysis criteria as parameters analyzed by the influencer such as content quality level and type, and deriving analysis results. In addition, the advertisement service providing server 300 recommends an influencer matched to respond to an advertisement request of an advertiser, and provides information such as a reason for recommendation, a type of parameter for which recommendation was made, and a result prediction, to the advertiser terminal 400. It may be a server that can be sent to and aided in selection. In addition, the advertisement service providing server 300 analyzes the advertisement results to minimize matching errors, relearns big data, and when the advertiser's information for subsequent matching is input as a query, matching with a minimized error rate It could be a server that lets you provide results.

Here, the advertisement service providing server 300 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like.

The at least one advertiser terminal 400 may be a terminal of an advertiser using an advertisement service related web page, app page, program, or application using influencer matching based on multi-parameter analysis. At this time, when requesting an advertisement, the at least one advertiser terminal 400 provides the above-described multiple parameters such as advertisement target object, brand propensity, and the type and degree of quality of desired advertisement content, or allows access to the data. It can be a terminal. In addition, at least one advertiser terminal 400 receives a list of influencers listed as a matching result from the advertisement service providing server 300, and reports a high matching degree in a certain parameter as well as numerical data that is a matching degree. It may be a terminal that receives a prediction result such as whether or not the advertisement effect will be. In addition, the at least one advertiser terminal 400 may be a terminal that displays an intention to accept an advertisement contract by selecting one influencer and transmitting it to the advertisement service providing server 300.

Here, the at least one advertiser terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like. In this case, the at least one advertiser terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one advertiser terminal 400, for example, as a wireless communication device that is guaranteed portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS(Personal Handyphone System), PDA(Personal Digital Assistant), IMT(International Mobile Telecommunication)-2000, CDMA(Code Division Multiple Access)-2000, W-CDMA(W-Code Division Multiple Access), Wibro(Wireless Broadband Internet) ) All types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs may be included.

FIG. 2 is a block diagram illustrating an advertisement service providing server included in the system of FIG. 1, and FIG. 3 is an implementation of an advertisement service using influencer matching based on multi-parameter analysis according to an embodiment of the present invention. It is a figure for explaining an embodiment.

Referring to FIG. 2, the advertisement service providing server 300 includes a construction unit 310, an analysis unit 320, a calculation unit 330, a transmission unit 340, a classification unit 350, and a prediction unit 360. ) Can be included.

The advertisement service providing server 300 according to an embodiment of the present invention or another server (not shown) operated in conjunction with at least one influencer terminal 100 and at least one advertiser terminal 400 are multi-parameters When transmitting an advertisement service application, program, app page, web page, etc. using analysis-based influencer matching, at least one influencer terminal 100 and at least one advertiser terminal 400 may analyze multiple parameters It is possible to install or open an advertisement service application, program, app page, web page, etc. using base influencer matching. In addition, a service program may be driven in at least one influencer terminal 100 and at least one advertiser terminal 400 by using a script executed in a web browser. Here, the web browser is a program that enables you to use the web (WWW: world wide web) service, and refers to a program that receives and displays hypertext described in HTML (hyper text mark-up language). For example, Netscape , Explorer, chrome, etc. In addition, the application means an application on the terminal, and includes, for example, an app that is executed on a mobile terminal (smartphone).

Referring to FIG. 2, the construction unit 310 collects the content of at least one influencer terminal 100, the quality of the content, the psychological code of the subscriber who subscribes to the content, and the data of the influencer, and (Pool) can be built. At this time, the classification criteria for dividing the types of influencers are various. Depending on their influence, there are influencers that affect hundreds of thousands to millions of people, mega influencers, macro influencers that affect tens of thousands to hundreds of thousands of people, and micro-influencers and nano influencers. Also, depending on their age, they can be classified from kids influencers to older influencers, and another category that divides the type of influencer can be classified according to how the audience perceives the influencer's awareness. For example, if a person is already famous enough to get up and down, the degree to which they influence the audience will be different from that of the general influencer. Therefore, it can be divided into celebrity influencers and general influencers according to perceived awareness. In addition to the above-described classification, an embodiment of the present invention may collect information on the above-described parameters in order to quantitatively and qualitatively analyze matching between an advertiser or an advertisement object and an advertisement target.

At this time, the content of the at least one influencer terminal 100 may be classified as a category first, and may be analyzed and classified by subject, brand, and expression method as a subclass of the category, and at least one influencer The quality of the content of the terminal 100 may be measured by dividing the original content of the at least one influencer terminal 100 and the advertisement content of the at least one influencer terminal 100. In addition, the psychological code of the subscriber who subscribes to the content may include the reason why the subscriber follows the influencer and the driving force to continue to consume and subscribe to the subscriber's content, and the influencer's data is It may include data that analyzes the propensity and issues of the Ruencer.

For example, even if content is classified into categories, this is only a rough classification, and the content created by influencers is not sufficiently expressed. In other words, even for contents within the same category, differences in consumer reactions occur depending on factors such as themes and expression methods. The two most contrasting examples are the "A" channel and the "B" channel, which contains the stories of two men from England who lived in Korea. These two people have the same nationality, similar age group, and have content called YouTube about the lives of British people in Korea. In this case, if this is divided into categories only, even if nationality or gender is aside, foreigners can be classified into the same content in the same category as Korean life. However, the fandoms of these two channels are very different, and one is already giving off a celebrity atmosphere, and due to the many advertisements, the fans are in a state of being separated from the beginning. Fans who didn't say it unconditionally win a lot of ad collaborations by saying good words, and they are raising the problem that they are less authentic for profit. The other has fewer subscribers than the former case, but since he shares sincere opinions and sometimes criticizes, sometimes with praise, the splendid attraction is inferior to the former case, but earning a reputation for authenticity and a steady number of subscribers. I keep it. In this case, the results of matching may not be satisfactory because other factors are not considered at all. Therefore, introduction of various factors is required. Through this, meaningful results can be presented. Here, the analysis parameters are not limited to those described above and may be added or modified according to embodiments.

Since the quality of content is an important factor that can consider the ease of work and diversification of expression methods when producing advertising content, it is very important to measure it in advance and include it as a matching parameter. The quality can be measured by factors such as the editing technology and image quality of the content by dividing it into original content that influencers generally upload and advertisement content that has been advertised.

The psychological code is to make an optimized proposal to advertisers through an approach and analysis of the reason why subscribers follow the influencer and the driving force that makes them consume content continuously. For example, a YouTube channel called "Jindoli TV" is gaining popularity in recent years, and although there is no fancy sights or video editing technology, a factory dog that has to live a lifetime in a 1m line takes a walk every weekend, and the weekend is all employees. Many people are enthusiastic about the TV, which gives rice and water to Jindo Dog, who has been left in the hot sunlight for 48 hours in the absence of water and rice on Saturday and Sunday after work, and raises money and delivers it to YouTubers. Even unusual phenomena are appearing. The subscribers at this time feel satisfied that they do good deeds through Jindol TV, although they cannot directly go to them, and they do not skip advertisements so that they can return to YouTuber profits. I want to help. These psychological codes are clearly different from the motives of subscribing to famous celebrities' makeup and interior methods. In this way, when the sentiment of the subscribers who subscribe to the channel is grasped, it becomes clear which advertisements should be left to the YouTuber who runs Jindoli TV. For example, if an advertisement-oriented commercial advertisement takes the form of a commercial advertisement, the subscribers will turn away, and if the name of helping Jindol or the proceeds is used to help a 1m factory such as a TV, the subscribers themselves can share word of mouth or infinitely Will encourage the purchase of

In the method of analyzing influencers, only general quantitative data on influencers are provided. In this case, it may be difficult to derive meaningful results depending on the influencer's tendency, major issues, and preferred brands. In addition to the quantitative data, analysis can be performed in the form of qualitative data being quantified and summed. If we keep citing the above-described example of Jindol TV, the influencer's tendency is a Caregiver who takes care of Jindol whenever he has time, and considers the animal's situation as his own (Affectionate, Empathetic), and It is a down-to-earth, easygoing character that accepts the words well and calmly walks his way, and a lot of donations show a sign of burden, and it has clearly clarified that it is not commercial care, so he is greedy for profit. Not a Greedy personality. And, the main issue is to remove the environment where the factory dogs are abused, such as giving snacks, filling water, or feeding feed to other 1m factory dogs tied around the factory. By applying the answer to the question or answer to Jindol immediately, it goes beyond facilitating communication with the subscribers, and by immediately realizing it as an action, it also delivers interesting elements to the subscribers. Therefore, if a product or brand that is non-profit and has caring or empathetic issues is matched with Jindol TV, the effect can be doubled. In this way, in order to understand which advertisement is effective when delivered by which influencer, the advertisement can be properly matched by grasping the characteristics of the influencer such as the propensity of the advertiser, the personality or propensity of the brand, the image, the personality of the product, etc. The effect can vary greatly. Of course, in addition to the above-described parameters, various parameters may be additionally defined and used, and it will be apparent that they are not limited to the above-described parameters and may be modified according to embodiments.

The analysis unit 320 may store the analysis result in the manpower pool through preprocessing and analysis of big data corresponding to the manpower pool. The analysis unit 320 stores raw data corresponding to the manpower pool in parallel and distributed, and stores unstructured data, structured data, and semi-structured data included in the stored raw data. structured), perform pre-processing including classification as metadata, and analyze pre-processed data including data mining.

At this time, the process of collecting big data can use a web crawler, and through crawling, the posting date, content, quantity, capacity, author information, URL, tags, etc. Data can be collected. Here, unlike broadcast content, the influencer content does not have metadata. Accordingly, metadata of each content may be generated or features may be extracted through image analysis of at least one frame included in each content, but in this case, a huge amount of resources, that is, computing and networking resources, are required for image analysis. Will be consumed. Accordingly, in an embodiment of the present invention, metadata is generated by analyzing a chat or comment written at an arbitrary time when a video is played. For example, in the case of content that is streamed in real time, metadata can be created to be synchronized with time by analyzing chat data. Even if the broadcast is not being streamed in real time, it is synchronized at the time the user writes a review. You can also use a method of estimating the content of the content. For example, if there is a comment saying "You really enjoy jajangmyeon" at view point B of content A, you can infer that the content of content at view B is the content of eating jajangmyeon. Accordingly, the reaction of the viewer and the contents of the video stream can be converted into big data based on the linguistic characteristics of the chat log generated in real time. In addition, when constructing the above-described big data, it is possible to analyze the correlation between the popularity index of the content and the non-verbal characteristics occurring in the chat. Of course, it does not exclude people from manually inputting metadata after viewing the video of each content or creating content through video analysis. Furthermore, the popularity of online streaming content can be predicted through the analysis of the chat log of subscribers or viewers, which can be implemented as a machine learning-based model.

In addition, it is also important not to collect unnecessary information for measuring influence among contents related to contents. After the raw data is collected, a pre-processing process of filtering is required. In the filtering process, in general, keywords may be filtered, documents may be selected by type, and meaningless information may be removed. In accordance with the basic purpose of measuring the impact when content is mentioned on social media, there are things to consider when selecting meaningless information.Even when analyzing big data, the same text is repeated indefinitely by focusing on the title or character, or The text data written at the time before is streamed should be screened. In addition, in the filtering process, it is necessary to systematically accumulate garbage, which is unnecessarily collected information. It is not an exaggeration to say that the reason why it is difficult to ensure accuracy and reliability even though big data analysis is a survey based on transmission. Therefore, it is necessary to quantify what proportion of the garbage occupies in the total collected information at the last stage of data collection, and disclose it as a garbage scale.

The next step is Natural Language Processing (NLP). At this time, in the natural language processing process, as morphemes or phrases included in text data are extracted, actual analysis data is indexed and accumulated in DB. The data accumulated in the DB in this process is substituted into an algorithm that measures the range of mention, so that practical analysis is performed, so that the analysis data by information of the above-described categories, namely, content, quality, psychological code, and influencer information, is not confused. Based on the data classification work should be done first. In particular, a separate identifier may be provided to allow selection of media outlets, bloggers, and community channel names or posting authors if they appear the same. The final process is the artificial intelligence learning and analysis process. In this case, for example, text mining may be used, but the present invention is not limited thereto. At this time, if data incorrectly collected in the natural language processing process is transferred to the text mining step before semantic or network analysis is performed, a system for transferring the data back to the natural language processing step must be established. In particular, nouns, adjectives, and verbs should be distinguished among the words mentioned in the tag or title of the content. If adjectives or verbs are accumulated in the database in the text mining stage, these data are accumulated in conjunction with the database in the natural language processing stage. It can also be designed as. Of course, in addition to the method of constructing big data by the above-described method, big data may be constructed by various methods, and the method of modeling and the result may be different.

The calculation unit 340 may calculate a degree of matching between the advertisement request information transmitted from the advertiser terminal 400 and at least one influencer included in the analyzed manpower pool. When calculating the matching degree, the calculation unit 330 calculates the matching of quantitative data and qualitative data, and processes the quantitative data using numerical values, and the qualitative data by natural language processing and artificial intelligence learning methods. Can be. At this time, when calculating the matching degree, the calculation unit 340 includes the content of the content desired by the advertiser, the type and degree of the quality desired by the advertiser, the psychological code of the advertisement target set by the advertiser, and the advertiser's propensity. Influence data, including the content of the content of the influencer terminal 100, the type and degree of the quality of the content uploaded by the influencer, the psychological code of the psychology member who subscribes to the content of the influencer, and the influence of the influencer It is possible to calculate whether or not each of the data of the Luencer matches. At this time, the degree of matching can be based on the degree of similarity, and in the case of measuring the degree of similarity based on sentences processed in natural language, the word embedding model, word2vec, is used to convert it into vectors, and the similarity between these vectors and each parameter is measured. It allows you to measure the similarity between the parameters. Performances of Euclidean similarity, cosine similarity, and extended jacquard similarity, which are methods of measuring similarity between vectors, may be compared using actual data, but are not limited thereto.

Here, word2vec is a model that embeds the meaning of a word itself into a multidimensional vector space using data on the appearance frequency of a word within a sentence. Based on NNLM (Neural Net Language Model), a large amount of document corpus can be quickly learned and processed. Learning methods include CBOW (Continuous Bag of Word), a method that predicts intermediate words using surrounding words, and Skip-Gram, which predicts surrounding words using intermediate words. Because the contextual meaning of words is preserved numerically through learning, the similarity between words can be measured or handled numerically by using this. And, the Euclidean similarity measures the similarity by using the Euclidean distance between two vectors. The Euclidean distance represents the linear distance between two vectors, and is a widely used measure to consider all the differences between the elements constituting two vectors. Euclidean similarity has a smaller value as the Euclidean distance increases, and has a value between 0 and 1. Secondly, cosine similarity measures the similarity by the size of the inner angle formed by two vectors. Cosine similarity is widely used to calculate the similarity between documents when each document is expressed as a vector composed of the frequencies of words appearing in the corresponding document. In this case, the cosine similarity is very effective in finding documents having similar meanings or subjects, and can be used in the fields of data mining or information retrieval. When the angle between the vectors representing the two documents is 0°, the cosine similarity has a value of 1, and when the angle is 90°, it has a value of 0. When all elements of the vector have a value of 0 or more, the cosine similarity has a value between 0 and 1, and the closer the value is to 1, the higher the similarity. The cosine similarity is preferably used when the lengths of two documents to be compared are significantly different because the similarity is calculated using only the angle formed by the two vectors without considering the size of the vector. Third, the extended Jaccard similarity measures the similarity using an extended Jaccard coefficient, also known as a Tanimoto coefficient. The extended Jacquard coefficient represents the degree of similarity between two sets, and is an extension of the existing Jacquard coefficient to be applicable to consecutive numbers. Both the angle and the relative distance of the two vectors are considered, and the ratio between the union and the intersection of the elements constituting the vector is expressed. The extended jacquard coefficients range from 0 to 1, and the closer to 1, the more similar. If the text to be compared or the text corresponding to the cowword or parameter is short, LSTM (Long Short Term Memory), a type of Recurrent Neural Network, which is frequently used for CNN (Convolutional Neural Network) and sequential data processing May be used. Global Average Pooling and Attention Mechanism can also be used as a method of combining the weight vectors of LSTM. In addition to the above-described method, similarity or matching may be measured by various methods, and it is obvious that the degree of similarity is not limited to the above.

The transmission unit 340 may transmit the list-up matching result to the advertiser terminal 400 based on the matching degree calculated by the calculation unit 330. The advertiser terminal 400, as a result of requesting an influencer advertisement, may receive a result matched with at least one influencer terminal 100, and may select any one influencer to make an subscription. , When the influencer terminal 400 issues an indication of acceptance or when an indication of intention arrives, a contract may be concluded. When the advertiser terminal 400 selects one of the influencers listed as a matching result, the predictor 360 may transmit prediction data of the advertisement campaign based on the calculated matching degree. . At this time, here, based on the above-described matching degree, a random forest, a support vector machine (SVM), a Naive Bayes, a decision tree, a logistic regression, and a deep learning algorithm (Multi- layer Perceptron) algorithm can be used to predict the probability of success.

The classification unit 350 classifies at least one influencer terminal 100 according to the number of subscribers, and is a mega-influencer having a subscriber of 100,000 units to a million units, and a macro influencer having a unit of 10,000 to less than 100,000 units. , A micro-influencer of tens to less than ten thousand units, and a nano-influencer of tens to less than a thousand units. Since this is the same as described above, a redundant description will be omitted.

Hereinafter, an operation process according to the configuration of the advertisement service providing server of FIG. 2 will be described in detail with reference to FIG. 3 as an example. However, it will be apparent that the embodiment is only any one of various embodiments of the present invention, and is not limited thereto.

Referring to FIG. 3, (a) the advertisement service providing server 300 divides the manpower pool into the number of subscribers, content, quality, psychological codes of subscribers, influencer tendencies, etc., and models big data with a classifier. Then, when data corresponding to a classifier is input as a query, big data can be constructed to find similar influencers. Accordingly, the advertisement service providing server 300 collects information such as (b) the content of the advertisement that the advertiser wants to create from the advertiser terminal 400, the desired quality, the psychological code of the target customer, and the propensity of the advertiser. It inputs data as an input value, that is, a query, and provides a matched influencer list as an output value. Here, when the advertiser terminal 400 does not clearly present the desired advertisement concept, content content, or quality, or the advertiser himself does not know what he wants and fails to present it, that is, it is often ambiguous. It acts as the number one contributor to annoying companies that received orders for outsourcing advertisements with infinite repetition and rework. In this case, in such a case, similar contents that best contain the advertisement concept desired by the advertiser may be provided so that it can be entered as a query for matching. In addition, the advertisement service providing server 300 (c) collects the reaction of the advertisement when the advertisement is produced and uploaded by an influencer, thereby providing big data with feedback that can correct errors in the construction of big data or matching. Relearn.

The matters not described with respect to the method of providing an advertisement service using influencer matching based on multi-parameter analysis of FIGS. 2 and 3 are described above with respect to a method of providing an advertisement service using influencer matching based on multi-parameter analysis through FIG. Since the content is the same as the description or can be easily inferred from the description, the following description will be omitted.

4 is a diagram illustrating a process of transmitting and receiving data between components included in the advertisement service providing system using influencer matching based on multi-parameter analysis of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of a process in which data is transmitted/received between each component will be described with reference to FIG. 4, but the present application is not limitedly interpreted as such an embodiment, and is illustrated in FIG. 4 according to various embodiments described above. It is apparent to those skilled in the art that the process of transmitting and receiving data may be changed.

4, the advertisement service providing server 300 collects information from the influencer terminal 100 (S4100), divides the manpower pool by the number of subscribers (S4200), and analyzes the content of the influencer. (S4200), analyzing the quality of the content (S4300), analyzing the psychological code (S4310), analyzing the psychological code of the subscriber (S4330), and analyzing the influencer's own propensity (S4350), big data And the learning is performed to be modeled with the above-described parameters (S4400). And, when an advertisement request is received from the advertiser terminal 400 (S4500), by analyzing the advertiser and the advertisement itself (S4600), the analysis result or text is queried as an input value in big data, and the result value, that is, The influencer matching result is listed (S4700), the advertisement prediction result is generated based on the matching degree, etc., and transmitted to the advertiser terminal 400 (S4800). At this time, when the advertisement service providing server 300 selects an influencer from the advertiser terminal 400 (S4810), it transmits it to the selected influencer terminal 100 (S4810), and the influencer terminal 100 When the advertisement content is uploaded (S4900), the result is monitored and analyzed, the result is transmitted to the influencer terminal 100 and the advertiser terminal 400, and the big data is relearned as a monitoring result to reduce the error rate. Do (S4920).

The order between the above-described steps S4100 to S4920 is only an example and is not limited thereto. That is, the order of the above-described steps (S4100 to S4920) may be mutually changed, and some of the steps may be executed or deleted at the same time.

For the information that is not described about the method of providing an advertisement service using influencer matching based on multi-parameter analysis of FIG. 4, a method for providing an advertisement service using influencer matching based on multi-parameter analysis is described above with reference to FIGS. Since the content is the same as the description or can be easily inferred from the description, the following description will be omitted.

5 is a flowchart illustrating a method of providing an advertisement service using influencer matching based on multi-parameter analysis according to an embodiment of the present invention. Referring to FIG. 5, the advertisement service providing server collects the content of at least one influencer terminal, the quality of the content, the psychological code of the subscriber who subscribes to the content, and the data of the influencer to create a pool. Construct (S5100).

The advertisement service providing server stores the analysis result in the manpower pool through pre-processing and analysis of big data corresponding to the manpower pool (S5200), advertisement request information transmitted from the advertiser terminal, and at least one included in the analyzed manpower pool The degree of matching between the influencers of is calculated (S5300).

In addition, the advertisement service providing server transmits the matching result listed based on the calculated matching degree to the advertiser terminal (S5400).

The matters not described with respect to the method of providing an advertisement service using influencer matching based on multi-parameter analysis of FIG. 5 are described above with respect to the method of providing an advertisement service using influencer matching based on multi-parameter analysis through FIGS. 1 to 4. Since the content is the same as the description or can be easily inferred from the description, the following description will be omitted.

The method of providing an advertisement service using influencer matching based on multi-parameter analysis according to the exemplary embodiment described with reference to FIG. 5 includes a recording medium including a computer-executable instruction such as an application or program module executed by a computer. It can also be implemented in a form. Computer-readable media can be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Further, the computer-readable medium may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The method for providing an advertisement service using influencer matching based on multi-parameter analysis according to an embodiment of the present invention described above includes an application basically installed in a terminal (this includes a program included in a platform or operating system basically installed in the terminal). It may be executed by the application store server, an application, or an application (ie, a program) directly installed on the master terminal through an application providing server such as a web server related to the service. In this sense, the method of providing an advertisement service using influencer matching based on multi-parameter analysis according to an embodiment of the present invention described above is implemented as an application (i.e., a program) installed in a terminal or directly installed by a user, and It can be recorded on a computer-readable recording medium such as E.

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains can understand that it is possible to easily transform it into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

Claims (7)

At least one influencer terminal having a plurality of subscribers and uploading content;
An advertiser terminal that requests an influencer advertisement and receives a result matched with at least one influencer terminal; And,
A construction unit that collects the content of the at least one influencer terminal, the quality of the content, the psychological code of the subscriber who subscribes to the content, and the data of the influencer to build a manpower pool, the manpower pool An analysis unit that stores the analysis result in the manpower pool through pre-processing and analysis of big data corresponding to, matching between the advertisement request information transmitted from the advertiser terminal and at least one influencer included in the analyzed manpower pool Including; an advertisement service providing server including a calculation unit for calculating a degree, and a transmission unit for transmitting the matching result listed based on the matching degree calculated by the calculation unit to the advertiser terminal,
The calculation unit, when calculating the matching degree, includes the content of the content desired by the advertiser, the type and degree of the quality desired by the advertiser, the psychological code of the advertisement target set by the advertiser, and the advertiser's propensity. The data includes the content of the content of the influencer terminal, the type and degree of the quality of the content uploaded by the influencer, the psychological code of a psychological person who subscribes to the content of the influencer, and the influence of the influencer. Calculate whether or not they match each of the influencer's data,
The content of the at least one influencer terminal is first classified into a category, and analyzed and classified by subject, brand, and expression method as a subclass of the category, and the content of the at least one influencer terminal The quality is measured by dividing the original content of the at least one influencer terminal and the advertisement content of the at least one influencer terminal, and the psychological code of the subscriber who subscribes to the content is determined by the subscriber The reason for following the ruoner and the driving force to continuously consume and subscribe to the content of the subscriber are included, and the data of the influencer includes data obtained by analyzing the propensity and issue of the influencer,
The advertisement service providing server, when the advertiser terminal selects one of the influencers listed as a matching result, a prediction unit that transmits prediction data of an advertisement campaign based on the calculated matching degree Advertising service providing system using influencer matching based on multi-parameter analysis, characterized in that it further comprises.
delete The method of claim 1,
When calculating the matching degree, the calculation unit calculates, including matching quantitative data and qualitative data,
An advertisement service providing system using influencer matching based on multi-parameter analysis, characterized in that the quantitative data is processed using numerical values, and the qualitative data is processed by natural language processing and artificial intelligence learning methods.
The method of claim 1,
By classifying the at least one influencer terminal according to the number of subscribers, mega influencers with subscribers of 100,000 to 1 million units, macro influencers of 10,000 to less than 100,000 units, micro influencers of 1,000 to less than 10,000 units A classification unit for classifying an influencer into an influencer, and a nano-influencer of ten units to less than a thousand units;
Advertising service providing system using influencer matching based on multi-parameter analysis, characterized in that it further comprises.
delete The method of claim 1,
The analysis unit,
Raw data corresponding to the workforce pool is stored in parallel and distributed, and unstructured data, structured data, and semi-structured data included in the stored raw data are purified. , An advertisement service providing system using influencer matching based on multi-parameter analysis, characterized in that pre-processing including classification as meta data is performed, and analysis including data mining of the pre-processed data is performed.
delete

Images