Method, device, and program for calaulating estimated revenue of collaboration with each content creator

Abstract

A method for calculating the expected collaboration revenue of a content creator by a processor of a device according to an embodiment of the present invention comprises: a step of obtaining information related to a first content creator; a step of calculating a traffic indicator of the first content creator; a step of calculating a commerciality indicator of the first content creator; and a step of calculating the expected collaboration revenue of the first content creator based on the traffic indicator and the commerciality indicator; and can contribute to saving time and resources when a brand or marketer selects a content creator for collaboration, enhancing the effectiveness of marketing such as collaboration, or enhancing the effectiveness of collaboration management by calculating expected sales, expected expenses, expected revenue, etc.

Description

Technology Field

[0001] The present invention relates to a method for calculating the expected collaboration revenue of a content creator, and more specifically, to a method, apparatus, and program for calculating traffic indicators and commerciality indicators based on content creator information, and thereby calculating and outputting the expected collaboration revenue. Background Technology

[0002] A content creator refers to a person who uploads content to social network services (SNS), including Instagram, TikTok, Facebook, YouTube, and internet blogs. Social network services are online services that build a network of relationships among people who share specific interests or activities, and content creators each have followers (users who subscribe to the content creator and receive content), thereby exerting influence over users of the social network service, including them.

[0003] Therefore, many brands collaborate with content creators to generate viral content and collect product reviews during the initial stages of market entry. To this end, the process of manually selecting creators capable of generating actual viral marketing effects relies primarily on subjective human judgment or utilizes follower counts as the sole metric. However, a significant number of content creators exploit this loophole by employing deceptive methods to artificially inflate their reported follower counts. For instance, there are even services that artificially boost follower numbers by generating a large number of so-called "ghost accounts" that are not actually used or active, or by manipulating the system to ensure these ghost accounts are not automatically detected.

[0004] Therefore, there is a need for practical methods and mechanisms to calculate projected revenue when deciding on or managing collaborations with content creators. The problem to be solved

[0005] The present invention is proposed to solve the above-mentioned problem and aims to provide a method, apparatus, and program for calculating traffic indicators and commercial viability indicators based on content creator information, and thereby calculating and outputting expected collaboration revenue.

[0006] The technical problems that the present invention aims to solve are not limited to those mentioned above, and various technical problems may be included within the scope obvious to a person skilled in the art from the contents described below. means of solving the problem

[0007] A method for calculating the expected collaboration revenue of a content creator by a processor of a device according to one embodiment of the present invention may include: a step of obtaining information related to a first content creator; a step of calculating a traffic indicator of the first content creator; a step of calculating a commerciality indicator of the first content creator; and a step of calculating the expected collaboration revenue of the first content creator based on the traffic indicator and the commerciality indicator.

[0008] The step of calculating a traffic indicator of the first content creator may include: a step of obtaining at least one piece of content-related information (first content data) posted by the first content creator; a step of selecting at least a portion of the first content data; and a step of calculating a traffic indicator for each of the selected at least portions of content.

[0009] The step of calculating traffic indicators for each of the at least some selected content may include the step of obtaining the number of reactions for each of the at least some selected content.

[0010] The number of reactions mentioned above may be the number of times specific users have performed at least some of liking, sharing, and saving for each of the selected at least some of the content.

[0011] The step of calculating the commerciality indicator of the first content creator may include: a step of obtaining at least one piece of content-related information (first content data) posted by the first content creator; a step of selecting at least a portion of the first content data; a step of extracting numerical data included in each of the selected at least portions of content; and a step of obtaining the commerciality indicator of the first content creator based on the numerical data.

[0012] The above numerical data may include at least one of the number of reactions, the number of content exposures, and the number of comments.

[0013] The step of calculating the commerciality index of the first content creator may include: a step of obtaining at least one piece of content-related information (first content data) posted by the first content creator; a step of dividing the first content data into at least one piece of data; a step of obtaining a valid score of the at least one piece of data; and a step of calculating the commerciality index of the first content creator based on the valid score.

[0014] The step of dividing the first content data into at least one data piece may include: a step of extracting text data from the first content data; and a step of dividing the text data into at least one data piece.

[0015] The above text data may be data generated by users other than the creator regarding the content.

[0016] The step of calculating the commerciality indicator of the first content creator based on the above valid scores may include the step of calculating the ratio of valid scores that are above a preset threshold.

[0017] The step of calculating the commerciality index of the first content creator may include: a step of obtaining the commerciality index of the second content creator; a step of obtaining the similarity between the first content creator and the second content creator; and a step of calculating the commerciality index of the first content creator based on the commerciality index of the second content creator and the similarity.

[0018] The step of obtaining a commerciality indicator of the second content creator may include: obtaining at least one piece of content-related information (second content data) posted by the second content creator; selecting at least a portion of the second content data; extracting numerical data included in each of the selected at least portions of content; and obtaining a commerciality indicator of the second content creator based on the numerical data.

[0019] The step of obtaining similarity between the first content creator and the second content creator may include: a step of inputting data related to the first content creator into a first artificial neural network model to obtain a first analysis result; a step of inputting data related to the second content creator into the first artificial neural network model to obtain a second analysis result; and a step of obtaining similarity between the first analysis result and the second analysis result.

[0020] The first analysis result and the second analysis result are vectors of the same dimension, and the step of obtaining similarity between the first analysis result and the second analysis result may include the step of calculating cosine similarity or Euclidean distance between the first analysis result and the second analysis result.

[0021] The step of calculating the commerciality indicator of the first content creator based on the commerciality indicator of the second content creator and the similarity may be a step of designating the commerciality indicator of the second content creator having the highest similarity to the first content creator among a plurality of similarities stored previously as the commerciality indicator of the first content creator.

[0022] The step of calculating the expected collaboration revenue of the first content creator based on the above traffic indicator and commerciality indicator may include the step of multiplying the above traffic indicator and the above commerciality indicator.

[0023] In one embodiment, the method for calculating the expected collaboration revenue of a content creator may further include the step of transmitting the expected collaboration revenue to an external party.

[0024] According to one embodiment of the present invention, an apparatus for calculating the expected collaboration revenue of a content creator comprises: a processor; and a memory storing at least one instruction executed through the processor, wherein the at least one instruction may be executed by the processor to obtain information related to a first content creator, calculate a traffic indicator of the first content creator, calculate a commerciality indicator of the first content creator, and calculate the expected collaboration revenue of the first content creator based on the traffic indicator and the commerciality indicator.

[0025] In one embodiment, the device further comprises a communication device; and the at least one instruction may be further executed by the processor to transmit the collaboration expected profit to the outside through the communication device.

[0026] A computer program stored in a computer-readable storage medium according to one embodiment of the present invention performs steps for calculating the expected collaboration revenue of a content creator when executed in a processor of a device, and the steps may include: a step of obtaining information related to a first content creator; a step of calculating a traffic indicator of the first content creator; a step of calculating a commerciality indicator of the first content creator; and a step of calculating the expected collaboration revenue of the first content creator based on the traffic indicator and the commerciality indicator. Effects of the invention

[0027] According to one embodiment of the present invention, when a brand or marketer selects a content creator for collaboration, it can save time and resources and contribute to enhancing the effectiveness of marketing, such as collaboration.

[0028] In addition, it can contribute to enhancing the effectiveness of collaboration management by calculating projected sales, expenses, and profits. Brief explanation of the drawing

[0029] FIG. 1 is a block diagram illustrating the interaction between a device and an external environment according to one embodiment of the present invention. FIG. 2 is a block diagram illustrating the interaction between components of a device according to one embodiment of the present invention. FIG. 3 is a flowchart for explaining the operation of a device according to one embodiment of the present invention. FIG. 4 is a flowchart illustrating a method for calculating a commerciality index of content according to an embodiment of the present invention. FIG. 5 is a flowchart illustrating a method for calculating a commerciality index of a creator according to one embodiment of the present invention. FIG. 6 is a flowchart illustrating a method for analyzing similarity between content creators to calculate a commerciality index of a creator according to an embodiment of the present invention. FIG. 7 is a flowchart illustrating a method for outputting content creator-related information based on expected collaboration revenue according to an embodiment of the present invention. FIG. 8 is an example diagram of an interface output according to one embodiment of the present invention. FIG. 9 is an example of another interface output according to one embodiment of the present invention. Specific details for implementing the invention

[0030] The embodiments described herein are subject to various modifications and may have various forms; specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the scope of specific embodiments and should be understood to include various modifications, equivalents, and / or alternatives of the embodiments of the invention. In relation to the description of the drawings, similar reference numerals may be used for similar components.

[0031] In describing the present disclosure, if it is determined that a detailed description of related known functions or configurations could unnecessarily obscure the essence of the invention, such detailed description is omitted.

[0032] In addition, the following embodiments may be modified in various other forms, and the scope of the technical concept of the present invention is not limited to the following embodiments. Rather, these embodiments are provided to make the present disclosure more faithful and complete and to fully convey the technical concept of the present invention to those skilled in the art.

[0033] The terms used in this disclosure are used merely to describe specific embodiments and are not intended to limit the scope of the rights. Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0034] In the present disclosure, expressions such as “have,” “may have,” “include,” or “may include” indicate the presence of such features (e.g., numerical values, functions, actions, or components such as parts) and do not exclude the presence of additional features.

[0035] In the present disclosure, expressions such as “A or B,” “at least one of A or / and B,” or “one or more of A or / and B” may include all possible combinations of items listed together. For example, “A or B,” “at least one of A and B,” or “at least one of A or B” may refer to cases including (1) at least one A, (2) at least one B, or (3) both at least one A and at least one B.

[0036] Expressions such as "first," "second," "first," or "second" used in this disclosure may modify various components regardless of order and / or importance, and are used only to distinguish one component from another and do not limit said components.

[0037] Where it is stated that a component (e.g., Component 1) is "(operatively or communicatively) coupled with / to" or "connected to" another component (e.g., Component 2), it should be understood that the component may be directly connected to the other component or connected through the other component (e.g., Component 3).

[0038] On the other hand, when it is stated that a certain component (e.g., a first component) is "directly connected" or "directly coupled" to another component (e.g., a second component), it may be understood that no other component (e.g., a third component) exists between the certain component and the other component.

[0039] As used in this disclosure, the expression “configured to” may be replaced, depending on the context, with, for example, “suitable for,” “having the capacity to,” “designed to,” “adapted to,” “made to,” or “capable of.” The term “configured to” may not necessarily mean only “specifically designed to” in hardware.

[0040] Instead, in some situations, the expression “device configured to do something” may mean that the device is “capable of doing something” together with other devices or components. For example, the phrase “processor configured (or set) to perform A, B, and C” may mean a dedicated processor for performing those operations (e.g., an embedded processor), or a generic-purpose processor (e.g., a CPU or application processor) capable of performing those operations by executing one or more software programs stored in a memory device.

[0041] In the embodiments, a 'module' or 'part' performs at least one function or operation and may be implemented in hardware or software, or a combination of hardware and software. Additionally, a plurality of 'modules' or a plurality of 'parts' may be integrated into at least one module and implemented by at least one processor, except for the 'module' or 'part' that needs to be implemented in specific hardware.

[0042] The methods according to the present invention 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 computer-readable medium may be those specifically designed and configured for the present invention, or they may be those known and available to those skilled in the art of computer software.

[0043] Examples of computer-readable media include 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 produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The aforementioned hardware devices may be configured to operate as at least one software module to perform the operation of the present invention, and vice versa.

[0044] Meanwhile, the various elements and areas in the drawings are depicted schematically. Accordingly, the technical concept of the present invention is not limited by the relative sizes or spacing depicted in the attached drawings.

[0045] Hereinafter, embodiments according to the present disclosure are described in detail with reference to the attached drawings so that those skilled in the art can easily implement them.

[0046] FIG. 1 is a block diagram illustrating the interaction between a device and an external environment according to one embodiment of the present invention.

[0047] Referring to FIG. 1, according to one embodiment of the present invention, a device (200) for calculating the expected collaboration revenue of a content creator can communicate with a user terminal (100) or an external server (300) to exchange information. The device (200) for calculating the expected collaboration revenue of a content creator can obtain information related to a first content creator (e.g., information on at least one digital content uploaded by the first content creator) from the user terminal (100), obtain it from an external server (300), and obtain it from the external server (300) through a request based on the information obtained from the user terminal (100). Additionally, when the device (200) for calculating the expected collaboration revenue of a content creator outputs a calculation result in response to an external request, it can transmit the result to the user terminal (100) or to the outside of the user terminal (100) and the device (200) in response to a request from the user terminal (100).

[0048] The user terminal (100) may include at least one component among an input device, an output device, a memory, a communication device, and a processor, and may be an electronic device such as a computer, a tablet, or a smartphone.

[0049] The input device can receive commands or data to be used in a component (e.g., processor) of the user terminal (100) from outside the user terminal (e.g., user).

[0050] The input device may include, for example, a microphone, a mouse, a keyboard, or a digital pen (e.g., a stylus pen), a touch panel, etc. The touch panel may be composed of a capacitive touch panel that detects changes in electrical signals, a pressure-sensitive touch panel that detects physical pressure, an infrared touch panel that forms an infrared grid and detects changes in the infrared grid, a surface ultrasonic touch panel that forms an ultrasonic grid and detects changes in the ultrasonic grid, etc.

[0051] The output device may include lighting, speakers, text display devices, and display panels. In particular, the display panel may include various types of display panels such as LCD (Liquid Crystal Display) panels, OLED (Organic Light Emitting Diodes) panels, AM-OLED (Active-Matrix Organic Light-Emitting Diode), LcoS (Liquid Crystal on Silicon), QLED (Quantum dot Light-Emitting Diode), DLP (Digital Light Processing), PDP (Plasma Display Panel) panels, inorganic LED panels, and micro LED panels, but is not limited thereto. Meanwhile, the display panel may form a touch screen together with the touch panel described above, and may be made of a flexible panel.

[0052] Memory stores various programs or data temporarily or non-temporarily and transmits the stored information to the processor upon the processor's call. In addition, memory can store various information necessary for the processor's computation, processing, or control operations in an electronic format.

[0053] Memory may include, for example, at least one of main memory and secondary memory. Main memory may be implemented using a semiconductor storage medium such as ROM and / or RAM. ROM may include, for example, conventional ROM, EPROM, EEPROM and / or MASK-ROM. RAM may include, for example, DRAM and / or SRAM. Secondary memory may be implemented using at least one storage medium capable of storing data permanently or semi-permanently, such as a flash memory device, SD (Secure Digital) card, Solid State Drive (SSD), Hard Disc Drive (HDD), optical recording media such as a magnetic drum, Compact Disc (CD), DVD or laser disc, magnetic tape, magneto-optical disc and / or floppy disk.

[0054] The communication device may be a wired communication device or a wireless communication device, and may include both, but it is preferable to include a wireless communication device. Such wireless communication technologies may include, for example, Bluetooth, Bluetooth Low Energy, CAN communication, Wi-Fi, Wi-Fi Direct, ultrawide band (UWB), Zigbee, infrared data association (IrDA), or near field communication (NFC), and mobile communication technologies may include Wi-Max, LTE (Long Term Evolution), 5G, 6G, and subsequent communication standard technologies. The wireless communication interface may be implemented using an antenna, a communication chip, and a substrate, etc., capable of transmitting electromagnetic waves to the outside or receiving electromagnetic waves transmitted from the outside.

[0055] The processor is connected to the configuration of a user terminal (100) including memory, and by executing at least one instruction stored in the memory as described above, it can control at least some of the operations performed by the collaborative expected profit calculation device (200) through the user terminal (100). In particular, the processor may be implemented as a single processor as well as as a plurality of processors. In this case, the one or plurality of processors may be a general-purpose processor such as a CPU (Central Processing Unit) or AP (Application Processor), a graphics-dedicated processor such as a GPU (Graphic Processing Unit) or VPU (Vision Processing Unit), or an artificial intelligence-dedicated processor such as an NPU (Neural Processing Unit) or TPU (Tensor Processing Unit).

[0056] A device (200) for quantitatively evaluating content creators may request a crawling operation from a crawler (310) to obtain data from an external server (300). Crawling is a technology for automatically collecting data from an external server, which is a process of exploring an external server and retrieving HTML code or specific data, and the crawler (310) refers to a device that performs such crawling.

[0057] Additionally, referring to FIG. 1, the collaboration expected revenue calculation device (200) can quantitatively evaluate a content creator, such as by interacting with a traffic indicator calculation device (400) or a commerciality indicator calculation device (500) to calculate the collaboration expected revenue based on values ​​obtained from them. Each device may be a server including a processor, memory, and a communication device.

[0058] The traffic indicator calculation device (400) can acquire at least one piece of content-related information (first content data) posted by the first content creator, select at least some of the content-related information, acquire the number of reactions for each of the selected at least some pieces of content, and calculate a traffic indicator (Estimated traffic) based on the number of reactions.

[0059] In one embodiment, the commerciality index calculation device (500) includes a memory and a processor that store a natural language processing model including an artificial neural network, and the processor acquires information of at least one digital content, extracts text information from the information of the digital content, divides the text information into a plurality of data pieces, calculates a commerciality index for each of the plurality of data pieces through the natural language processing model in the memory, and can calculate a representative value from the calculated plurality of commerciality indicators.

[0060] In another embodiment, the commerciality index calculation device (500) includes a memory for storing a natural language processing model including an artificial neural network; and a processor; wherein the processor selects a content creator to calculate a commerciality index, determines at least one content among the content posted by the creator to be used for calculating the commerciality index, and can calculate the commerciality index of the at least one content through the method described above.

[0061] In another embodiment, a commerciality indicator calculation device (500) comprises at least one processor; and a memory that stores at least one instruction for calculating a commerciality indicator of a content creator account when executed by the at least one processor, wherein the at least one instruction may be executed to acquire first content data, which is at least one content data posted to an account within a first platform, extract numerical data included in said content data, and calculate a commerciality indicator based on said numerical data.

[0062] FIG. 2 is a block diagram illustrating the interaction between components of a device according to one embodiment of the present invention.

[0063] Referring to FIG. 2, the collaboration expected profit calculation device (200) may include a processor (210), memory (220), and a communication device (230).

[0064] The processor (210) is connected to the configuration of the collaborative expected revenue calculation device (200) including memory (220), and by executing at least one instruction stored in the memory (220), it can control overall operations performed by the collaborative expected revenue calculation device (200), such as the creation, modification, and execution of the traffic indicator calculation module (221) or the commerciality indicator calculation module (222). In particular, the processor (210) may be implemented as a single processor as well as as multiple processors. In this case, one or multiple processors may be a general-purpose processor such as a CPU (Central Processing Unit) or AP (Application Processor), a graphics-dedicated processor such as a GPU (Graphic Processing Unit) or VPU (Vision Processing Unit), or an artificial intelligence-dedicated processor such as an NPU (Neural Processing Unit) or TPU (Tensor Processing Unit).

[0065] The processor (210) may include a computation unit (211) capable of controlling a communication device (230) to perform communication with a user terminal (100) or an external server (300) and executing a series of instructions stored in a memory (220) including a traffic indicator calculation module (221) or a commerciality indicator calculation module (222), and a control unit (212) capable of storing data in the memory (220) or retrieving data stored in the memory (220).

[0066] The memory (220) stores various programs or data temporarily or non-temporarily and transmits the stored information to the processor upon the call of the processor (210). Additionally, the memory (220) can store various information necessary for the computation, processing, or control operations of the processor (210) in an electronic format. The user of the device (200) can store information related to the calculation of the expected collaboration revenue of a content creator requested by the user in the memory (220) through the user terminal (100) or input device (231). Additionally, information related to the overall analysis of the content creator can be stored.

[0067] The memory (220) may include, for example, at least one of a main memory and an auxiliary memory. The main memory may be implemented using a semiconductor storage medium such as ROM and / or RAM. The ROM may include, for example, a conventional ROM, EPROM, EEPROM and / or MASK-ROM. The RAM may include, for example, a DRAM and / or SRAM. The auxiliary memory may be implemented using at least one storage medium capable of storing data permanently or semi-permanently, such as a flash memory device, an SD (Secure Digital) card, a solid state drive (SSD), a hard disk drive (HDD), an optical recording medium such as a magnetic drum, a compact disc (CD), a DVD, or a laser disc, a magnetic tape, a magneto-optical disc and / or a floppy disk. Additionally, the memory (220) may be implemented as a storage located physically outside the collaborative expected profit calculation device (200), or may be composed of a logical combination of a storage located physically outside the collaborative expected profit calculation device (200) and a storage located inside the collaborative expected profit calculation device (200).

[0068] The memory (220) may logically include a traffic indicator calculation module (221) or a commerciality indicator calculation module (222). The components of these memory (220) may be physically implemented by assembling separate parts of the memory (220). Additionally, when each of these memory (220) is executed in a device including a processor (e.g., a collaborative expected revenue calculation device), the device may perform the role of a traffic indicator calculation device (400) or a commerciality indicator calculation device (500), and may execute through the processor (210) to perform calculations related to artificial intelligence functions. In particular, the device (200) may perform convolution operations in parallel using the computation unit (211) included in the processor (210).

[0069] A traffic indicator calculation module (221) or a commerciality indicator calculation module (222) can be generated by applying a learning algorithm to a number of learning data. This learning can be performed on the device (200) itself where the artificial intelligence model (neural network model) according to the present disclosure is executed, or it can be performed through a separate device (e.g., a server) or system.

[0070] An artificial intelligence model (neural network model) may be composed of multiple artificial neural network layers. Each layer has multiple weight values ​​and performs operations of the layer through the operation of the multiple weights and the operation of the previous layer. Examples of neural networks include CNN (Convolutional Neural Network), DNN (Deep Neural Network), RNN (Recurrent Neural Network), RBM (Restricted Boltzmann Machine), DBN (Deep Belief Network), BRDNN (Bidirectional Recurrent Deep Neural Network), and Deep Q-Networks; however, the neural networks in this disclosure are not limited to the aforementioned examples except where specified.

[0071] A learning algorithm is a method of training a specific target device (e.g., a robot) using a number of learning data to enable the target device to make decisions or predictions on its own. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, and the learning algorithms in this disclosure are not limited to the aforementioned examples except where specified.

[0072] When the collaboration expected revenue calculation device (200) includes a communication device (230), the collaboration expected revenue calculation device (200) may be a server that provides information or services to a client through a network, i.e., a collaboration expected revenue calculation server. The communication device (230) may be a wired communication device or a wireless communication device, and may include both, but it is preferable to include a wireless communication device. Such wireless communication technologies may include, for example, Bluetooth, Bluetooth Low Energy, CAN communication, Wi-Fi, Wi-Fi Direct, ultrawide band (UWB), Zigbee, infrared data association (IrDA), or near field communication (NFC), and mobile communication technologies may include Wi-Max, LTE (Long Term Evolution), 5G, 6G, and subsequent communication standard technologies. A wireless communication interface can be implemented using an antenna, a communication chip, a substrate, etc., capable of transmitting electromagnetic waves to the outside or receiving electromagnetic waves transmitted from the outside.

[0073] The communication device may include an input device (231) or an output device (232). The input device may receive commands or data to be used by a component (e.g., a processor) of the device (200) from outside the device (e.g., a user). The input device (231) may include, for example, a microphone, a mouse, a keyboard, or a digital pen (e.g., a stylus pen), a touch panel, etc. The touch panel may be composed of a capacitive touch panel that detects changes in electrical signals, a pressure-sensitive touch panel that detects physical pressure, an infrared touch panel that forms an infrared grid and detects changes in the infrared grid, a surface ultrasonic touch panel that forms an ultrasonic grid and detects changes in the ultrasonic grid, etc.

[0074] The output device (232) may include lighting, a speaker, a text display device, and a display panel. In particular, the display panel may include various types of display panels such as an LCD (Liquid Crystal Display) panel, an OLED (Organic Light Emitting Diodes) panel, an AM-OLED (Active-Matrix Organic Light-Emitting Diode), an LcoS (Liquid Crystal on Silicon), a QLED (Quantum dot Light-Emitting Diode), a DLP (Digital Light Processing), a PDP (Plasma Display Panel) panel, an inorganic LED panel, and a micro LED panel, but is not limited thereto. Meanwhile, the display panel may form a touch screen together with the touch panel described above, and may be made of a flexible panel.

[0075] FIG. 3 is a flowchart for explaining the operation of a device according to one embodiment of the present invention.

[0076] The series of processes illustrated in FIG. 3, or FIG. 4 to 6, may be initiated when the device (200) according to one embodiment of the present invention receives input from a user terminal (100), a crawler (310), or an external server (300). Alternatively, it may be initiated according to a rule set within the memory (220) (e.g., execution at regular intervals, when a change is detected in the received content data).

[0077] In step S310, the device (200) can obtain traffic indicators. Step S310 can be performed by the device (200) receiving traffic indicators of the first content creator from a traffic indicator calculation device (400) or an external database, or by calculating traffic indicators internally within the device (200).

[0078] A method for calculating a traffic indicator, performed through a collaboration estimated revenue calculation device (200), a traffic indicator calculation device (400), or a combination of the two devices, may include at least one step of obtaining at least one piece of content-related information (first content data) posted by a first content creator, a step of selecting at least a portion of the content-related information, a step of obtaining the number of reactions for each of the selected at least portions of content, and a step of calculating a traffic indicator (Estimated traffic) based on the number of reactions. It may also include at least one step of obtaining information related to the first content creator from an external source. At this time, the first content data may be selected based on similarity with the content to be collaborated on.

[0079] In step S320, the device (200) can obtain a commerciality indicator. Step S320 can be performed by the device (200) receiving the commerciality indicator of the first content creator from a commerciality indicator calculation device (500) or an external database, or by calculating a traffic indicator internally within the device (200).

[0080] A method for calculating a commerciality indicator, performed through a collaborative expected revenue calculation device (200), a commerciality indicator calculation device (500), or a combination of the two devices, may include at least one step of determining at least one content among the content posted by the first content creator to be used for calculating the commerciality indicator, a step of extracting text information from the information of the digital content, a step of dividing the text information into at least one data piece, a step of obtaining a valid score of the at least one data piece, and a step of calculating one representative value from the at least one valid score. The text information may be data generated by a user other than the creator regarding the content, and the step of dividing the text information into at least one data piece may be performed based on the creator of the data piece. Additionally, the step of dividing the text information into a plurality of data pieces may include a step of removing information unnecessary for calculating the commerciality indicator from the text information. At this time, the text information may include at least one of a data piece contained in the content itself, data converted from an image or video of the content, and data generated by a user other than the creator regarding the content.

[0081] Additionally, a method for calculating a commerciality indicator performed through a collaborative expected revenue calculation device (200), a commerciality indicator calculation device (500), or a combination of the two devices may include at least one step of acquiring first content data, which is at least one piece of content data posted on an account within a first platform; a step of extracting numerical data included in said content data; and a step of calculating a commerciality indicator based on said numerical data. At this time, the method for calculating a commerciality indicator may include at least one step of acquiring a first text analysis result by inputting text data included in said first content data into a first artificial neural network model; acquiring second content data, which is at least one piece of content posted on an account within a second platform; a step of acquiring a second text analysis result by inputting text data included in said second content data into said first artificial neural network model; and a step of deriving similarity between said first text analysis result and said second text analysis result.

[0082] In step S330, the device (200) can calculate the expected collaboration revenue based on the traffic indicator obtained in step S310 and the commerciality indicator obtained in step S320. Step S330 may include a step of performing a multiplication operation between the traffic indicator and the commerciality indicator.

[0083] In step S340, the device (200) can output the estimated collaboration profit calculated in step S330. The output of the estimated collaboration profit can be done through an output device (232) or by transmitting information through a communication device (230) so that it is output at the user terminal (100). The output can be transmitted directly to the user terminal (100) that sent the request or to an external source, and can be performed on a web browser or an installable / executable application provided by the device (200).

[0084] FIG. 4 is a flowchart illustrating a method for calculating a commerciality index of content according to an embodiment of the present invention.

[0085] In step S410, the device (200) may acquire content data. The content data may be information stored in memory (220) or information acquired from a user terminal (100), a crawler (310), or an external server (300). Additionally, the information stored in memory (220) and the information acquired from the user terminal (100), a crawler (310), or an external server (300) may be merged. Step S410 may include a step of selecting some of the content data acquired by the device (200). At this time, the selection criteria may be based on the purpose of collaboration or similarity with the content. Similarity may be based on cosine similarity or Euclidean distance after vectorizing content-related information, or it may be the output value of an artificial neural network model that receives an input value containing content-related information.

[0086] In step S430, the device (200) can extract text data from the content data obtained in step S410. Step S430 can be performed by processing the content information to retain only data that is significant in terms of commerciality or commerciality indicators. Additionally, the device (200) can store the extracted text data in memory (220).

[0087] In step S450, the device (200) may divide the text data extracted in step S430 into at least one data piece. The device (200) may adopt the method described through FIGS. 5 and 6, which will be described later, to calculate the commerciality index of the target content.

[0088] At least one data piece obtained in step S450 can be input into a classification model (600). The classification model (600) can classify the input value into at least one pre-set category, and each category can be represented as a numerical value. Accordingly, the classification model (600) can output a numerical value based on how close each input value is to each category. For example, if a category with a high commercial value indicator is represented as 1 and a category with a low commercial value indicator is represented as 0, each input value of the classification model can have an output value in the form of a rational number between 0 and 1. The classification model (600) may have a structure described in FIG. 10, which will be described later.

[0089] In step S471, the device (200) may obtain a temporary value or a temporary vector to obtain a valid vector from the output value of the classification model (600).

[0090] In step S470, the device (200) may obtain a valid vector for each data piece by adding a temporary value or a temporary vector to the output of the classification model (600). Here, "adding" is not limited to simple addition operations and includes all types of operations capable of summing two values ​​or vectors. To improve the user experience, such as preventing abuse like manipulation of a creator's commerciality indicators, it is desirable that the temporary value or temporary vector be randomly generated or determined within a preset range.

[0091] Step S471 may be omitted. That is, the classification model (600) can output a valid vector.

[0092] In step S490, the device (200) may calculate a representative value from the valid vector of at least one data piece. The representative value may be a text analysis result calculated based on valid scores (a 0-dimensional or 1-dimensional valid vector). The representative value may be the mean, median, or mode of each valid score, may be a weighted average of each valid score, or may be calculated as the ratio of data pieces having valid scores greater than or equal to a threshold. For example, if the maximum value of the valid scores of the target content is 1 and the minimum value is 0, the threshold may be 0.5. That is, the ratio of valid scores having a value greater than or equal to 0.5 may be the text analysis result for the content data.

[0093] FIG. 5 is a flowchart illustrating a method for calculating a commerciality index of a creator according to one embodiment of the present invention.

[0094] In step S510, the device (200) may store the calculated similarity in memory (220) or external storage. An explanation of the calculation of similarity performed by the device (200) will be described later through FIG. 6.

[0095] In step S530, the device (200) may obtain an external request or obtain similarity between at least two accounts (e.g., an account within the first platform and an account within the second platform) from the similarity database according to rules stored in memory (220). Preferably, the step of the device (200) obtaining an external request is the step of receiving a request from the user terminal (100).

[0096] In step S550, the device (200) may obtain a commerciality indicator of an account within the second platform. Step S550 may include the step of obtaining a commerciality indicator from a database or repository that stores a commerciality indicator corresponding to at least one account. Alternatively, in step S550, the device (200) may perform the step of extracting numerical data included in the second content data or the step of calculating a commerciality indicator based on the numerical data. At this time, the second content data may be a set of data related to each of n content or video-containing content posted by an account within the second platform or a second content creator at the most recent time. Additionally, the numerical data may include at least one of the number of impressions, the number of reactions, and the number of comments. Here, the number of reactions may be the number of times users within the second platform have performed actions such as liking, sharing, or saving regarding at least one piece of content posted on the account. The step of the device (200) calculating a commerciality indicator based on the numerical data may be the step of calculating a commerciality indicator based on the average of at least one of the number of impressions, the number of reactions, and the number of comments.

[0097] In step S570, the device (200) can calculate the commerciality indicator of an account in the first platform based on the similarity obtained in step S530 and the commerciality indicator of an account in the second platform obtained in step S550. The first platform and the second platform may be the same platform, but it is preferable that they be different platforms. In this case, there is an effect of being able to calculate the commerciality indicator of an account in the first platform without providing some or all of the numerical data. Additionally, according to one embodiment, commerciality indicators of accounts in different platforms can be calculated and managed by correcting for differences in content data that appear due to the characteristics of the social network service or platform.

[0098] FIG. 6 is a flowchart illustrating a method for analyzing similarity between content creators to calculate a commerciality index of a creator according to an embodiment of the present invention.

[0099] In step S611, the device (200) may acquire first content data. It is preferable that the first content data be acquired from a crawler (310) or an external server (300). The acquired first content data may be input into the first artificial neural network model (600') either as is or after being processed according to a preset method stored in memory (220). The first artificial neural network model may include the classification model (600) described above. Step S611 may include a step of selecting a portion of the content data (or first content data) acquired by the device (200). At this time, the selection criteria may be based on the purpose of collaboration or similarity with the content. Similarity may be based on cosine similarity or Euclidean distance after vectorizing content-related information, or it may be the output value of an artificial neural network model that receives an input value containing content-related information.

[0100] In step S631, the device (200) may obtain a first text analysis result from the first artificial neural network model (600'). The obtained first text analysis result may be input into the second artificial neural network model (700') either as is or after being processed according to a preset method stored in memory (220). In another embodiment, step S331 may be omitted. That is, the output value of the first artificial neural network model (600') may be input into the second artificial neural network model (700') without passing through the device (200). For example, the similarity analysis device (200) may input the first content data into a separate device including the first artificial neural network model and the second artificial neural network model to obtain similarity from the said device. Alternatively, a single artificial neural network model may perform both the roles of the first artificial neural network model and the second artificial neural network model. That is, the first artificial neural network model and the second artificial neural network model may be the same artificial neural network model.

[0101] In step S612, the device (200) can acquire second content data. It is preferable that the second content data be acquired from a crawler (310) or an external server (300) based on input from a user terminal (100). Although the external server (300) is used as the same entity to perform the same role from the perspective of the device (200), it is preferable that the server acquiring the first content data and the external server acquiring the second content be different. That is, it is preferable that step S611 is the step of acquiring from the first external server, and step S612 is the step of acquiring from the second external server. The acquired second content data can be input into the second artificial neural network model either as is or after processing according to a preset method stored in memory (220). The preset method for processing the content data may be the same for both the first and second content data, but may differ if the first external server and the second external server are on different platforms. That is, different processing methods may be applied to content data acquired from different platforms or servers. Step S612 may include a step of selecting some of the content data (or second content data) acquired by the device (200). At this time, the selection criteria may be based on the purpose of collaboration or similarity with the content. Similarity may be based on cosine similarity or Euclidean distance after vectorizing content-related information, or it may be the output value of an artificial neural network model that receives an input value containing content-related information.

[0102] In step S632, the device (200) may obtain a second text analysis result from the first artificial neural network model (600'). The obtained first text analysis result may be input into the second artificial neural network model (700') either as is or after being processed according to a preset method stored in memory (220). In another embodiment, step S632 may be omitted. Alternatively, steps S631 and S632 may not be omitted, and the configuration including the second artificial neural network model (700') may be omitted. In this case, the device (200) may perform the similarity acquisition step (S350) without an artificial neural network model. More specifically, the device (200) may calculate the similarity between two text analysis results (e.g., a first text analysis result and a second text analysis result) based on cosine similarity or Euclidean distance. In this case, it is preferable that each text analysis result be expressed in the form of a vector of the same dimension.

[0103] FIG. 7 is a flowchart illustrating a method for outputting content creator-related information based on expected collaboration revenue according to an embodiment of the present invention.

[0104] Referring to FIG. 7, a device (200) according to one embodiment of the present invention may be executed in accordance with information transmission or input from a user terminal (100). A user who wishes to select a content creator to collaborate with may transmit information related to candidate creators to the device (200) through the user terminal (100) so that the device (200) may perform a series of processes illustrated in FIG. 7. All processes illustrated in FIG. 7 may be omitted or replaced during implementation.

[0105] In step S710, the device (200) may obtain candidate creator-related information from the user terminal (100). The candidate creator-related information may include information necessary for selecting at least one candidate creator. For example, the candidate creator-related information may include the account of a specific creator to perform a similarity calculation to select a candidate creator. The device (200) that has obtained candidate creator-related information from the user terminal (100) may store the candidate creator-related information in the device's memory (220).

[0106] In step S730, the device (200) may request a candidate creator from an external server (300) based on candidate creator-related information obtained from a user terminal (100). Alternatively, the device (200) may perform step S730 through a crawler (310). The request transmitted by the device (200) to the external server (300) may be candidate creator-related information obtained from the user terminal (100), and the candidate creator-related information obtained from the user terminal (100) may be information processed according to a pre-configured method. Upon receiving such a request, the external server (300) may transmit candidate creator-related information to the device (200).

[0107] In step S750, the device (200) may obtain a set of candidate creators. The set of candidate creators may be all candidate creators obtained from an external server (300), a portion of candidate creators selected according to pre-set conditions, or selected based on additional information obtained from a user terminal. For example, the set of candidate creators may be a set of accounts in which at least one of the number of subscribers to the account or the number of reactions within the account's content is greater than or equal to a threshold value.

[0108] In step S770, the device (200) can obtain traffic indicators for each creator forming the set of candidate creators. To obtain traffic indicators for each creator forming the set of candidate creators, the device (200) can use a traffic indicator calculation module (221) stored in memory, send a request to a traffic indicator calculation device (400), and perform both. Additionally, in step S770, the device (200) can obtain commercial indicators for each creator forming the set of candidate creators. To obtain commercial indicators for each creator forming the set of candidate creators, the device (200) can use a commercial indicator calculation module (222) stored in memory, send a request to a commercial indicator calculation device (500), and perform both.

[0109] In step S770, the device (200) can calculate the estimated collaboration revenue of a creator based on traffic indicators and commerciality indicators. Additionally, the device (200) can calculate a score for each creator separately from the estimated collaboration revenue for making a judgment regarding the creator's output (e.g., whether to output, output order). The process by which the device (200) calculates the score of each creator forming a set of candidate creators can be performed by adding the value obtained by multiplying the commerciality indicator by the first weight, the value obtained by multiplying the traffic indicator by the second weight, and the value obtained by multiplying other values, such as the artificial neural network output result, by the third weight. It is preferable that the first to third weights are numbers between 0 and 1.

[0110] In step S790, the device (200) may output at least some of the creators forming the set of candidate creators to the user terminal (100) or output device (232). At this time, the device may determine whether the pre-set conditions are satisfied and determine at least some of the creators to be output to the user terminal (100) or output device (232). For example, the device may output only information related to creators whose scores calculated in step S770 have a value greater than or equal to a first threshold, or among creators whose similarity obtained in step S770 has a value greater than or equal to a second threshold, it may output only information related to creators whose scores calculated in step S770 have a value greater than or equal to a first threshold.

[0111] FIG. 8 is an example diagram of an interface output according to one embodiment of the present invention.

[0112] Referring to FIG. 8, the creator information displayed on the user terminal (100) or externally can be sorted in order of similarity to a specific content creator account, in order of commerciality indicators, or based on information related to candidate creators. The creator information displayed on the user terminal (100) or externally can be sorted or filtered according to criteria derived from at least one of the score calculated in step S770, commerciality indicators, similarity, number of subscribers of the account, number of reactions within the account's content, and the content of said reactions. The criteria derived from the commerciality indicators may be an expected revenue score.

[0113] The creator information that is sorted or filtered and output may include at least one of an estimated revenue score, commerciality indicators, similarity, account ID, profile picture, number of subscribers, viral score, and published content. The estimated revenue score may be a collaborative estimated revenue, or a value processed to make the collaborative estimated revenue easier for the user to recognize. In this case, if relevant information is insufficient, it may be displayed according to a pre-set display method. For example, if there is insufficient information to calculate the estimated revenue score, it may be displayed as N / A or 0. Additionally, the estimated revenue score is displayed based on a value stored in the device's memory (220), but it may not be exactly the same. For example, the estimated revenue score may be displayed rounded to the second decimal place for consistency. The estimated revenue score may be reflected only in the sorting order or only in the output result value.

[0114] Additionally, output-related records regarding output requests previously made by the user may be stored in a user terminal (100), a device (200), or other external storage for later verification. In this case, among the output-related records, information related to each account, namely the account ID, activity platform, profile picture, number of subscribers, viral score, posted content, and estimated collaboration revenue, may be information from the time of the previously performed estimated collaboration revenue calculation or output, and may be information updated at preset intervals or whenever the user requests output. It is desirable to output the previously performed similarity calculation, commerciality indicator calculation, or output time together in the user terminal (100), the device (200), or other external storage. In this case, the output may be transmitted directly to the user terminal (100) that sent the request or to an external entity, or it may be performed on a web browser or an installable / executable application provided by the device (200).

[0115] FIG. 9 is an example of another interface output according to one embodiment of the present invention.

[0116] Referring to FIG. 9, when the device (200) outputs analysis results regarding a content creator, it may output at least one of traffic metrics, account ID, profile picture, number of subscribers, and posted content together. Commercial metrics may be displayed under the name "Commercial Score." Collaboration estimated revenue may be expressed in actual currency units (e.g., won, dollar) or in the form of a score for comparison between creators. Such output may be transmitted directly to the user terminal (100) that sent the request or to an external source, and may be performed on a web browser or an installable / executable application provided by the device (200).

[0117] When the device (200) outputs analysis results regarding a content creator, it may also output country information statistics of subscribers or followers. Additionally, when the device (200) outputs analysis results regarding a content creator, such as commerciality indicators, it may also output analysis results related to the creator's content posting activities or analysis results regarding the content posted by the creator. The analysis results related to the creator's content posting activities may be statistics on the number or frequency of content posted, uploaded, or posted by the creator based on time (e.g., the last 10 weeks) or based on the number of content (e.g., the last 36 posts). The analysis results regarding the content posted by the creator may be statistics on user engagement (e.g., likes, comments) for selected content based on time (e.g., the last 10 weeks) or based on the number of content (e.g., the last 36 posts) or on the content itself (e.g., whether images or videos are included, length of the text). The aforementioned statistics may be output in the form of numbers, graphs, tables, or pictures.

[0118] Although preferred embodiments of the present invention have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the invention as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present invention.

Claims

Claim 1 A method for calculating the expected collaboration revenue of a content creator by a processor of a device, comprising: a step of obtaining information related to a first content creator; a step of calculating a traffic indicator of the first content creator; a step of calculating a commerciality indicator of the first content creator; and a step of calculating the expected collaboration revenue of the first content creator based on the traffic indicator and the commerciality indicator. Claim 2 A method according to claim 1, wherein the step of calculating a traffic indicator of the first content creator comprises: a step of obtaining at least one content-related information (first content data) posted by the first content creator; a step of selecting at least a portion of the first content data; and a step of calculating a traffic indicator for each of the selected at least a portion of the content. Claim 3 In paragraph 2, the step of calculating a traffic indicator for each of the selected at least portions of content comprises the step of obtaining the number of reactions for each of the selected at least portions of content. Claim 4 In paragraph 3, the method wherein the number of reactions is the number of times specific users have performed at least some of like, share, and save for each of the selected at least some of the content. Claim 5 A method according to claim 1, wherein the step of calculating a commerciality index of the first content creator comprises: a step of obtaining at least one piece of content-related information (first content data) posted by the first content creator; a step of selecting at least a portion of the first content data; a step of extracting numerical data included in each of the selected at least portions of content; and a step of obtaining a commerciality index of the first content creator based on the numerical data. Claim 6 In paragraph 5, the method comprises the numerical data including at least one of the number of reactions, the number of content exposures, and the number of comments. Claim 7 A method according to claim 1, wherein the step of calculating a commerciality index of the first content creator comprises: a step of obtaining at least one piece of content-related information (first content data) posted by the first content creator; a step of dividing the first content data into at least one piece of data; a step of obtaining a valid score of the at least one piece of data; and a step of calculating a commerciality index of the first content creator based on the valid score. Claim 8 In claim 7, the step of dividing the first content data into at least one data piece comprises: the step of extracting text data from the first content data; and the step of dividing the text data into at least one data piece. Claim 9 In paragraph 8, the method wherein the text data is data generated by a user other than the creator regarding the content. Claim 10 In claim 7, the step of calculating the commerciality index of the first content creator based on the valid score comprises the step of calculating the ratio of valid scores that are greater than or equal to a preset threshold. Claim 11 A method according to claim 1, wherein the step of calculating the commerciality index of the first content creator comprises: the step of obtaining the commerciality index of the second content creator; the step of obtaining the similarity between the first content creator and the second content creator; and the step of calculating the commerciality index of the first content creator based on the commerciality index of the second content creator and the similarity. Claim 12 In claim 11, the step of obtaining a commerciality indicator of the second content creator comprises: obtaining at least one piece of content-related information (second content data) posted by the second content creator; selecting at least a portion of the second content data; extracting numerical data included in each of the selected at least portions of content; and obtaining a commerciality indicator of the second content creator based on the numerical data. Claim 13 In claim 11, the step of obtaining similarity between the first content creator and the second content creator comprises: a step of inputting data related to the first content creator into a first artificial neural network model to obtain a first analysis result; a step of inputting data related to the second content creator into the first artificial neural network model to obtain a second analysis result; and a step of obtaining similarity between the first analysis result and the second analysis result. Claim 14 In claim 13, the first analysis result and the second analysis result are vectors of the same dimension, and the step of obtaining similarity between the first analysis result and the second analysis result includes the step of calculating cosine similarity or Euclidean distance between the first analysis result and the second analysis result. Claim 15 In claim 11, the step of calculating the commerciality index of the first content creator based on the commerciality index of the second content creator and the similarity is a step of designating the commerciality index of the second content creator, which has the highest similarity to the first content creator among a plurality of similarities stored previously, as the commerciality index of the first content creator. Claim 16 A method according to claim 1, wherein the step of calculating the expected collaboration revenue of the first content creator based on the traffic indicator and the commerciality indicator comprises the step of multiplying the traffic indicator and the commerciality indicator. Claim 17 A method comprising, in addition to the step of transmitting the expected collaboration profit to an external party in claim 1. Claim 18 A device for calculating the expected collaboration revenue of a content creator, comprising: a processor; and a memory storing at least one instruction executed through the processor; wherein the at least one instruction is executed by the processor to obtain information related to a first content creator, calculate a traffic indicator of the first content creator, calculate a commerciality indicator of the first content creator, and calculate the expected collaboration revenue of the first content creator based on the traffic indicator and the commerciality indicator. Claim 19 In paragraph 18, the device further comprises a communication device; wherein at least one instruction is further executed by the processor to transmit the collaboration expected revenue to the outside through the communication device. Claim 20 A computer program stored on a computer-readable storage medium, wherein, when the computer program is executed on a processor of a device, the computer program performs steps for calculating the expected collaboration revenue of a content creator, the steps comprising: a step of obtaining information related to a first content creator; a step of calculating a traffic indicator of the first content creator; a step of calculating a commerciality indicator of the first content creator; and a step of calculating the expected collaboration revenue of the first content creator based on the traffic indicator and the commerciality indicator.

Images